2026<\/span>Journal article<\/small><\/div>GERIS: A Game-Theoretic Framework for Filtering Instance-Dependent Label Noise in License Plate Data Augmentation<\/h2>AUT Journal of Mathematics and Computing. 2026<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>SSJ Shani, R Ahmadian, A Rahmani, M Bideh, M Ghatee<\/bdi><\/p>\nGERIS: A Game-Theoretic Framework for Filtering Instance-Dependent Label Noise in License Plate Data Augmentation<\/li>\n<\/ul>\nSSJ Shani, R Ahmadian, A Rahmani, M Bideh, M Ghatee<\/p>\nAUT Journal of Mathematics and Computing. 2026<\/p>\nDOI: 10.22060\/ajmc.2025.23680.1288<\/a><\/p><\/div><\/details><\/div><\/div><\/article>2026<\/span>Journal article<\/small><\/div>Multi-Stage Self-Distillation for Class-Imbalanced Anomaly Detection<\/h2>IEEE Transactions on Emerging Topics in Computational Intelligence( Volume: 10, Issue: 4, August 2026),<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>B Yousefimehr, M Ghatee, R Razavi-Far<\/bdi><\/p>\nMulti-Stage Self-Distillation for Class-Imbalanced Anomaly Detection<\/li>\n<\/ul>\nB Yousefimehr, M Ghatee, R Razavi-Far<\/p>\nIEEE Transactions on Emerging Topics in Computational Intelligence( Volume: 10, Issue: 4, August 2026), Page(s):<\/strong> 2866 - 2875<\/p>\nDOI:<\/strong> 10.1109\/TETCI.2026.3671131<\/a><\/p><\/div><\/details><\/div><\/div><\/article>2026<\/span>Journal article<\/small><\/div>A systematic review for 2019\u20132025 on deep learning models in the film production industry<\/h2>Entertainment Computing 56, 101076<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>Behnam Yousefimehr, Mehdi Ghatee, Shervin Ghaffari, Arash Arasteh, Parsa Ahmadi, Amirhossein Ghane, Sina Esnaasharieh<\/bdi><\/p>\nA systematic review for 2019\u20132025 on deep learning models in the film production industry<\/li>\n<\/ul>\nBehnam Yousefimehr, Mehdi Ghatee, Shervin Ghaffari, Arash Arasteh, Parsa Ahmadi, Amirhossein Ghane, Sina Esnaasharieh<\/p>\nEntertainment Computing 56, 101076Ref: https:\/\/doi.org\/10.1016\/j.entcom.2025.101076<\/a><\/p>Read research update<\/a>Journal<\/a>Issue<\/a>Archived share link<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2026<\/span>Journal article<\/small><\/div>Multi-teacher knowledge distillation framework for lightweight anomaly detection<\/h2>Neural Networks 195, (2026) 108267<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>B Yousefimehr, M Ghatee, R Razavi-Far<\/bdi><\/p>Multi-teacher knowledge distillation framework for lightweight anomaly detection<\/p>\nB Yousefimehr, M Ghatee, R Razavi-Far<\/p>\nNeural Networks 195, (2026) 108267Ref: https:\/\/doi.org\/10.1016\/j.neunet.2025.108267<\/a><\/p>Read research update<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2025<\/span>Journal article<\/small><\/div>A systematic survey and empirical comparison of hybrid methods for imbalanced fraud detection: Combining resampling and machine learning<\/h2>AUT Journal of Mathematics and Computing, (2025)<\/p>DOI<\/a>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>B Yousefimehr, M Ghatee<\/bdi><\/p>\nA systematic survey and empirical comparison of hybrid methods for imbalanced fraud detection: Combining resampling and machine learning<\/li>\n<\/ul>\nB Yousefimehr, M Ghatee<\/p>\nAUT Journal of Mathematics and Computing, (2025)Ref: https:\/\/doi.org\/10.22060\/AJMC.2025.24642.1446<\/a><\/p>Read research update<\/a>A Systematic Survey and Empirical Comparison of Hybrid\u2026<\/a>AUT Journal of Mathematics and Computing.<\/a>Imbalanced Learning<\/a>Oversampling<\/a>Undersampling<\/a>Ensemble Learning<\/a>Auto Insurance Fraud Detection<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2025<\/span>Journal article<\/small><\/div>Fast inference in classification of Optical Coherence Tomography (OCT) images for real-time retinal disease diagnosis<\/h2>DOI<\/a>Publisher<\/a>Publisher<\/a>Authors & full citation<\/summary>Authors: <\/strong>Amin\u00a0Rahmani, Mehdi Ghatee<\/bdi><\/p>\nFast inference in classification of Optical Coherence Tomography (OCT) images for real-time retinal disease diagnosis<\/li>\n<\/ul>\nAmin\u00a0Rahmani, Mehdi Ghatee, Biomedical Signal Processing and Control<\/a>, Volume 103<\/a>,\u00a0May 2025, 107365<\/p>\nRef: https:\/\/doi.org\/10.1016\/j.bspc.2024.107365<\/a><\/p>Read research update<\/a>Journal<\/a>Issue<\/a><\/a>https:\/\/authors.elsevier.com\/a\/1kLO4_djyJXLUF<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2025<\/span>Journal article<\/small><\/div>A distribution-preserving method for resampling combined with LightGBM-LSTM for sequence-wise fraud detection in credit card transactions<\/h2>Expert Systems with Applications 262, (2025) 125661<\/p>DOI<\/a>Publisher<\/a>Authors & full citation<\/summary>Authors: <\/strong>B Yousefimehr, M Ghatee<\/bdi><\/p>\nA distribution-preserving method for resampling combined with LightGBM-LSTM for sequence-wise fraud detection in credit card transactions<\/li>\n<\/ul>\nB Yousefimehr, M Ghatee<\/p>\nExpert Systems with Applications 262, (2025) 125661Ref: https:\/\/doi.org\/10.1016\/j.eswa.2024.125661<\/a><\/p>Read research update<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2025<\/span>Journal article<\/small><\/div>Enhancing user identification through batch averaging of independent window subsequences using smartphone and wearable data<\/h2>Computers & Security, Volume 150, March 2025, 104265<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>R Ahmadian, M Ghatee, J Wahlstr\u00f6m<\/bdi><\/p>\nEnhancing user identification through batch averaging of independent window subsequences using smartphone and wearable data<\/li>\n<\/ul>\nR Ahmadian, M Ghatee, J Wahlstr\u00f6m<\/p>\nComputers & Security, Volume 150, March 2025, 104265<\/p>\nDOI: https:\/\/doi.org\/10.1016\/j.cose.2024.104265<\/a><\/p>Read research update<\/a>Journal<\/a>https:\/\/authors.elsevier.com\/a\/1kHD~c43v4OnK<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Journal article<\/small><\/div>An Ensemble of Deep Clustering Models With Autoencoders to Mine Travel Patterns From Smart Card Data<\/h2>IEEE Transactions on Intelligent Transportation Systems ( Volume: 25, Issue: 12, December 2024) Page(s): 20960 - 20969<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>S Saronian, B Yousefimehr, M Ghatee, MM Bejani<\/bdi><\/p>\nAn Ensemble of Deep Clustering Models With Autoencoders to Mine Travel Patterns From Smart Card Data<\/li>\n<\/ul>\nS Saronian, B Yousefimehr, M Ghatee, MM BejaniIEEE Transactions on Intelligent Transportation Systems ( Volume: 25, Issue: 12, December 2024) Page(s): 20960 - 20969DOI: 10.1109\/TITS.2024.3475295<\/p>Read research update<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Journal article<\/small><\/div>Uncertainty quantification to enhance probabilistic fusion based user identification using smartphones<\/h2>IEEE Internet of Things Journal ( Volume: 11, Issue: 20, 15 October 2024), Page(s): 33450 - 33458<\/p>DOI<\/a>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10599325<\/a>Authors & full citation<\/summary>Authors: <\/strong>R Ahmadian, M Ghatee, J Wahlstr\u00f6m, H Zare<\/bdi><\/p>\nUncertainty quantification to enhance probabilistic fusion based user identification using smartphones<\/li>\n<\/ul>\nR Ahmadian, M Ghatee, J Wahlstr\u00f6m, H Zare<\/p>\nIEEE Internet of Things Journal ( Volume: 11, Issue: 20, 15 October 2024), Page(s): 33450 - 33458DOI: 10.1109\/JIOT.2024.3429011<\/p>Read research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Publication announcement; type not stated in Papers heading<\/small><\/div>Enhanced Multi-Modal Gas Leakage Detection with NSMOTE: A Novel Over-sampling Approach<\/h2>2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)<\/p>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570108<\/a>Authors & full citation<\/summary>Authors: <\/strong>Aref Azizian, Behnam Yousefimehr, Mehdi Ghatee<\/bdi><\/p>\nEnhanced Multi-Modal Gas Leakage Detection with NSMOTE: A Novel Over-sampling Approach<\/a><\/p>\n\n\n\nBy<\/p>\n\n\n\nAref Azizian, Behnam Yousefimehr, Mehdi Ghatee<\/p>\n\n\n\nhas been published in \"2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)\".<\/p>\n\n\n\nAbstract:<\/p>\n\n\n\nUrbanization and the emergence of smart cities have led to increased industrial activities, raising concerns about safety and environmental hazards. Detecting and monitoring gas leaks accurately is crucial due to the significant risks they pose to public health and the environment. In this study, we propose a novel approach that combines thermal imaging with sensor data to enhance gas detection accuracy in urban and industrial settings. By employing advanced algorithms and analyzing extensive datasets, our methodology achieves an impressive accuracy rate of 99.32%, setting a new standard in gas leak detection. Our innovation lies in the utilization of a unique oversampling technique called Normal Synthetic Minority Oversampling Technique (NSMOTE), coupled with the simultaneous integration of thermal imaging and sensor data within a multimodal framework. This breakthrough not only underscores the potential of integrating diverse data sources for environmental monitoring but also represents a significant stride in mitigating the risks associated with industrial gas emissions.<\/p>\n\n\n\nRef: https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570108<\/a><\/p>\nRead research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Publication announcement; type not stated in Papers heading<\/small><\/div>Calibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/h2>2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)<\/p>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>Authors & full citation<\/summary>Authors: <\/strong>M Moeini, R Ahmadian, M Ghatee<\/bdi><\/p>\nCalibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/a><\/p>\n\n\n\nBy<\/p>\n\n\n\nM Moeini, R Ahmadian, M Ghatee<\/p>\n\n\n\nhas been accepted in \"2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)\"<\/p>\n\n\n\nAbstract:<\/p>\n\n\n\nWith the rapid advancement of artificial intelligence technologies in human life, particularly within the automotive industry, the popularity of smart vehicles has increased. Designing an intelligent car cabin capable of seamless interactions with both the driver and the vehicle emerges as a crucial solution to address human-vehicle interaction challenges. This project aims to implement a digital voice assistant that recognizes vehicle commands. It utilizes three main techniques: speech-to-text conversion, text classification, and calibrating the classifier in order to detect out-of-distribution (OOD) sentences. Using Vosk, an LLM model, voices in the vehicle environment are converted into text format. Then, after pre-processing the text, an SVM classifies them. Using Platt scaling the SVM classifier outputs become calibrated, which makes them probabilistic. The experimental result shows that the proposed model achieves command recognition with 96.43% accuracy, 96.83% precision, 96.43% recall, 96.39% F1-score, and 0.1437 cross-entropy loss. Furthermore, the optimal threshold for OOD sentences is 0.4.<\/p>\n\n\n\nRef: https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>\u00a0<\/p>\nRead research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2023<\/span>Journal article<\/small><\/div>Branch-and-Price Based Heuristic Algorithm for Fuzzy Multi-Depot Bus Scheduling Problem<\/h2>International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 31 (2023) 859-888<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>
2026<\/span>Journal article<\/small><\/div>Multi-Stage Self-Distillation for Class-Imbalanced Anomaly Detection<\/h2>IEEE Transactions on Emerging Topics in Computational Intelligence( Volume: 10, Issue: 4, August 2026),<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>B Yousefimehr, M Ghatee, R Razavi-Far<\/bdi><\/p>\nMulti-Stage Self-Distillation for Class-Imbalanced Anomaly Detection<\/li>\n<\/ul>\nB Yousefimehr, M Ghatee, R Razavi-Far<\/p>\nIEEE Transactions on Emerging Topics in Computational Intelligence( Volume: 10, Issue: 4, August 2026), Page(s):<\/strong> 2866 - 2875<\/p>\nDOI:<\/strong> 10.1109\/TETCI.2026.3671131<\/a><\/p><\/div><\/details><\/div><\/div><\/article>2026<\/span>Journal article<\/small><\/div>A systematic review for 2019\u20132025 on deep learning models in the film production industry<\/h2>Entertainment Computing 56, 101076<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>Behnam Yousefimehr, Mehdi Ghatee, Shervin Ghaffari, Arash Arasteh, Parsa Ahmadi, Amirhossein Ghane, Sina Esnaasharieh<\/bdi><\/p>\nA systematic review for 2019\u20132025 on deep learning models in the film production industry<\/li>\n<\/ul>\nBehnam Yousefimehr, Mehdi Ghatee, Shervin Ghaffari, Arash Arasteh, Parsa Ahmadi, Amirhossein Ghane, Sina Esnaasharieh<\/p>\nEntertainment Computing 56, 101076Ref: https:\/\/doi.org\/10.1016\/j.entcom.2025.101076<\/a><\/p>Read research update<\/a>Journal<\/a>Issue<\/a>Archived share link<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2026<\/span>Journal article<\/small><\/div>Multi-teacher knowledge distillation framework for lightweight anomaly detection<\/h2>Neural Networks 195, (2026) 108267<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>B Yousefimehr, M Ghatee, R Razavi-Far<\/bdi><\/p>Multi-teacher knowledge distillation framework for lightweight anomaly detection<\/p>\nB Yousefimehr, M Ghatee, R Razavi-Far<\/p>\nNeural Networks 195, (2026) 108267Ref: https:\/\/doi.org\/10.1016\/j.neunet.2025.108267<\/a><\/p>Read research update<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2025<\/span>Journal article<\/small><\/div>A systematic survey and empirical comparison of hybrid methods for imbalanced fraud detection: Combining resampling and machine learning<\/h2>AUT Journal of Mathematics and Computing, (2025)<\/p>DOI<\/a>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>B Yousefimehr, M Ghatee<\/bdi><\/p>\nA systematic survey and empirical comparison of hybrid methods for imbalanced fraud detection: Combining resampling and machine learning<\/li>\n<\/ul>\nB Yousefimehr, M Ghatee<\/p>\nAUT Journal of Mathematics and Computing, (2025)Ref: https:\/\/doi.org\/10.22060\/AJMC.2025.24642.1446<\/a><\/p>Read research update<\/a>A Systematic Survey and Empirical Comparison of Hybrid\u2026<\/a>AUT Journal of Mathematics and Computing.<\/a>Imbalanced Learning<\/a>Oversampling<\/a>Undersampling<\/a>Ensemble Learning<\/a>Auto Insurance Fraud Detection<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2025<\/span>Journal article<\/small><\/div>Fast inference in classification of Optical Coherence Tomography (OCT) images for real-time retinal disease diagnosis<\/h2>DOI<\/a>Publisher<\/a>Publisher<\/a>Authors & full citation<\/summary>Authors: <\/strong>Amin\u00a0Rahmani, Mehdi Ghatee<\/bdi><\/p>\nFast inference in classification of Optical Coherence Tomography (OCT) images for real-time retinal disease diagnosis<\/li>\n<\/ul>\nAmin\u00a0Rahmani, Mehdi Ghatee, Biomedical Signal Processing and Control<\/a>, Volume 103<\/a>,\u00a0May 2025, 107365<\/p>\nRef: https:\/\/doi.org\/10.1016\/j.bspc.2024.107365<\/a><\/p>Read research update<\/a>Journal<\/a>Issue<\/a><\/a>https:\/\/authors.elsevier.com\/a\/1kLO4_djyJXLUF<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2025<\/span>Journal article<\/small><\/div>A distribution-preserving method for resampling combined with LightGBM-LSTM for sequence-wise fraud detection in credit card transactions<\/h2>Expert Systems with Applications 262, (2025) 125661<\/p>DOI<\/a>Publisher<\/a>Authors & full citation<\/summary>Authors: <\/strong>B Yousefimehr, M Ghatee<\/bdi><\/p>\nA distribution-preserving method for resampling combined with LightGBM-LSTM for sequence-wise fraud detection in credit card transactions<\/li>\n<\/ul>\nB Yousefimehr, M Ghatee<\/p>\nExpert Systems with Applications 262, (2025) 125661Ref: https:\/\/doi.org\/10.1016\/j.eswa.2024.125661<\/a><\/p>Read research update<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2025<\/span>Journal article<\/small><\/div>Enhancing user identification through batch averaging of independent window subsequences using smartphone and wearable data<\/h2>Computers & Security, Volume 150, March 2025, 104265<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>R Ahmadian, M Ghatee, J Wahlstr\u00f6m<\/bdi><\/p>\nEnhancing user identification through batch averaging of independent window subsequences using smartphone and wearable data<\/li>\n<\/ul>\nR Ahmadian, M Ghatee, J Wahlstr\u00f6m<\/p>\nComputers & Security, Volume 150, March 2025, 104265<\/p>\nDOI: https:\/\/doi.org\/10.1016\/j.cose.2024.104265<\/a><\/p>Read research update<\/a>Journal<\/a>https:\/\/authors.elsevier.com\/a\/1kHD~c43v4OnK<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Journal article<\/small><\/div>An Ensemble of Deep Clustering Models With Autoencoders to Mine Travel Patterns From Smart Card Data<\/h2>IEEE Transactions on Intelligent Transportation Systems ( Volume: 25, Issue: 12, December 2024) Page(s): 20960 - 20969<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>S Saronian, B Yousefimehr, M Ghatee, MM Bejani<\/bdi><\/p>\nAn Ensemble of Deep Clustering Models With Autoencoders to Mine Travel Patterns From Smart Card Data<\/li>\n<\/ul>\nS Saronian, B Yousefimehr, M Ghatee, MM BejaniIEEE Transactions on Intelligent Transportation Systems ( Volume: 25, Issue: 12, December 2024) Page(s): 20960 - 20969DOI: 10.1109\/TITS.2024.3475295<\/p>Read research update<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Journal article<\/small><\/div>Uncertainty quantification to enhance probabilistic fusion based user identification using smartphones<\/h2>IEEE Internet of Things Journal ( Volume: 11, Issue: 20, 15 October 2024), Page(s): 33450 - 33458<\/p>DOI<\/a>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10599325<\/a>Authors & full citation<\/summary>Authors: <\/strong>R Ahmadian, M Ghatee, J Wahlstr\u00f6m, H Zare<\/bdi><\/p>\nUncertainty quantification to enhance probabilistic fusion based user identification using smartphones<\/li>\n<\/ul>\nR Ahmadian, M Ghatee, J Wahlstr\u00f6m, H Zare<\/p>\nIEEE Internet of Things Journal ( Volume: 11, Issue: 20, 15 October 2024), Page(s): 33450 - 33458DOI: 10.1109\/JIOT.2024.3429011<\/p>Read research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Publication announcement; type not stated in Papers heading<\/small><\/div>Enhanced Multi-Modal Gas Leakage Detection with NSMOTE: A Novel Over-sampling Approach<\/h2>2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)<\/p>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570108<\/a>Authors & full citation<\/summary>Authors: <\/strong>Aref Azizian, Behnam Yousefimehr, Mehdi Ghatee<\/bdi><\/p>\nEnhanced Multi-Modal Gas Leakage Detection with NSMOTE: A Novel Over-sampling Approach<\/a><\/p>\n\n\n\nBy<\/p>\n\n\n\nAref Azizian, Behnam Yousefimehr, Mehdi Ghatee<\/p>\n\n\n\nhas been published in \"2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)\".<\/p>\n\n\n\nAbstract:<\/p>\n\n\n\nUrbanization and the emergence of smart cities have led to increased industrial activities, raising concerns about safety and environmental hazards. Detecting and monitoring gas leaks accurately is crucial due to the significant risks they pose to public health and the environment. In this study, we propose a novel approach that combines thermal imaging with sensor data to enhance gas detection accuracy in urban and industrial settings. By employing advanced algorithms and analyzing extensive datasets, our methodology achieves an impressive accuracy rate of 99.32%, setting a new standard in gas leak detection. Our innovation lies in the utilization of a unique oversampling technique called Normal Synthetic Minority Oversampling Technique (NSMOTE), coupled with the simultaneous integration of thermal imaging and sensor data within a multimodal framework. This breakthrough not only underscores the potential of integrating diverse data sources for environmental monitoring but also represents a significant stride in mitigating the risks associated with industrial gas emissions.<\/p>\n\n\n\nRef: https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570108<\/a><\/p>\nRead research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Publication announcement; type not stated in Papers heading<\/small><\/div>Calibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/h2>2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)<\/p>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>Authors & full citation<\/summary>Authors: <\/strong>M Moeini, R Ahmadian, M Ghatee<\/bdi><\/p>\nCalibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/a><\/p>\n\n\n\nBy<\/p>\n\n\n\nM Moeini, R Ahmadian, M Ghatee<\/p>\n\n\n\nhas been accepted in \"2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)\"<\/p>\n\n\n\nAbstract:<\/p>\n\n\n\nWith the rapid advancement of artificial intelligence technologies in human life, particularly within the automotive industry, the popularity of smart vehicles has increased. Designing an intelligent car cabin capable of seamless interactions with both the driver and the vehicle emerges as a crucial solution to address human-vehicle interaction challenges. This project aims to implement a digital voice assistant that recognizes vehicle commands. It utilizes three main techniques: speech-to-text conversion, text classification, and calibrating the classifier in order to detect out-of-distribution (OOD) sentences. Using Vosk, an LLM model, voices in the vehicle environment are converted into text format. Then, after pre-processing the text, an SVM classifies them. Using Platt scaling the SVM classifier outputs become calibrated, which makes them probabilistic. The experimental result shows that the proposed model achieves command recognition with 96.43% accuracy, 96.83% precision, 96.43% recall, 96.39% F1-score, and 0.1437 cross-entropy loss. Furthermore, the optimal threshold for OOD sentences is 0.4.<\/p>\n\n\n\nRef: https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>\u00a0<\/p>\nRead research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2023<\/span>Journal article<\/small><\/div>Branch-and-Price Based Heuristic Algorithm for Fuzzy Multi-Depot Bus Scheduling Problem<\/h2>International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 31 (2023) 859-888<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>
2026<\/span>Journal article<\/small><\/div>A systematic review for 2019\u20132025 on deep learning models in the film production industry<\/h2>Entertainment Computing 56, 101076<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>Behnam Yousefimehr, Mehdi Ghatee, Shervin Ghaffari, Arash Arasteh, Parsa Ahmadi, Amirhossein Ghane, Sina Esnaasharieh<\/bdi><\/p>\nA systematic review for 2019\u20132025 on deep learning models in the film production industry<\/li>\n<\/ul>\nBehnam Yousefimehr, Mehdi Ghatee, Shervin Ghaffari, Arash Arasteh, Parsa Ahmadi, Amirhossein Ghane, Sina Esnaasharieh<\/p>\nEntertainment Computing 56, 101076Ref: https:\/\/doi.org\/10.1016\/j.entcom.2025.101076<\/a><\/p>Read research update<\/a>Journal<\/a>Issue<\/a>Archived share link<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2026<\/span>Journal article<\/small><\/div>Multi-teacher knowledge distillation framework for lightweight anomaly detection<\/h2>Neural Networks 195, (2026) 108267<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>B Yousefimehr, M Ghatee, R Razavi-Far<\/bdi><\/p>Multi-teacher knowledge distillation framework for lightweight anomaly detection<\/p>\nB Yousefimehr, M Ghatee, R Razavi-Far<\/p>\nNeural Networks 195, (2026) 108267Ref: https:\/\/doi.org\/10.1016\/j.neunet.2025.108267<\/a><\/p>Read research update<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2025<\/span>Journal article<\/small><\/div>A systematic survey and empirical comparison of hybrid methods for imbalanced fraud detection: Combining resampling and machine learning<\/h2>AUT Journal of Mathematics and Computing, (2025)<\/p>DOI<\/a>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>B Yousefimehr, M Ghatee<\/bdi><\/p>\nA systematic survey and empirical comparison of hybrid methods for imbalanced fraud detection: Combining resampling and machine learning<\/li>\n<\/ul>\nB Yousefimehr, M Ghatee<\/p>\nAUT Journal of Mathematics and Computing, (2025)Ref: https:\/\/doi.org\/10.22060\/AJMC.2025.24642.1446<\/a><\/p>Read research update<\/a>A Systematic Survey and Empirical Comparison of Hybrid\u2026<\/a>AUT Journal of Mathematics and Computing.<\/a>Imbalanced Learning<\/a>Oversampling<\/a>Undersampling<\/a>Ensemble Learning<\/a>Auto Insurance Fraud Detection<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2025<\/span>Journal article<\/small><\/div>Fast inference in classification of Optical Coherence Tomography (OCT) images for real-time retinal disease diagnosis<\/h2>DOI<\/a>Publisher<\/a>Publisher<\/a>Authors & full citation<\/summary>Authors: <\/strong>Amin\u00a0Rahmani, Mehdi Ghatee<\/bdi><\/p>\nFast inference in classification of Optical Coherence Tomography (OCT) images for real-time retinal disease diagnosis<\/li>\n<\/ul>\nAmin\u00a0Rahmani, Mehdi Ghatee, Biomedical Signal Processing and Control<\/a>, Volume 103<\/a>,\u00a0May 2025, 107365<\/p>\nRef: https:\/\/doi.org\/10.1016\/j.bspc.2024.107365<\/a><\/p>Read research update<\/a>Journal<\/a>Issue<\/a><\/a>https:\/\/authors.elsevier.com\/a\/1kLO4_djyJXLUF<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2025<\/span>Journal article<\/small><\/div>A distribution-preserving method for resampling combined with LightGBM-LSTM for sequence-wise fraud detection in credit card transactions<\/h2>Expert Systems with Applications 262, (2025) 125661<\/p>DOI<\/a>Publisher<\/a>Authors & full citation<\/summary>Authors: <\/strong>B Yousefimehr, M Ghatee<\/bdi><\/p>\nA distribution-preserving method for resampling combined with LightGBM-LSTM for sequence-wise fraud detection in credit card transactions<\/li>\n<\/ul>\nB Yousefimehr, M Ghatee<\/p>\nExpert Systems with Applications 262, (2025) 125661Ref: https:\/\/doi.org\/10.1016\/j.eswa.2024.125661<\/a><\/p>Read research update<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2025<\/span>Journal article<\/small><\/div>Enhancing user identification through batch averaging of independent window subsequences using smartphone and wearable data<\/h2>Computers & Security, Volume 150, March 2025, 104265<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>R Ahmadian, M Ghatee, J Wahlstr\u00f6m<\/bdi><\/p>\nEnhancing user identification through batch averaging of independent window subsequences using smartphone and wearable data<\/li>\n<\/ul>\nR Ahmadian, M Ghatee, J Wahlstr\u00f6m<\/p>\nComputers & Security, Volume 150, March 2025, 104265<\/p>\nDOI: https:\/\/doi.org\/10.1016\/j.cose.2024.104265<\/a><\/p>Read research update<\/a>Journal<\/a>https:\/\/authors.elsevier.com\/a\/1kHD~c43v4OnK<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Journal article<\/small><\/div>An Ensemble of Deep Clustering Models With Autoencoders to Mine Travel Patterns From Smart Card Data<\/h2>IEEE Transactions on Intelligent Transportation Systems ( Volume: 25, Issue: 12, December 2024) Page(s): 20960 - 20969<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>S Saronian, B Yousefimehr, M Ghatee, MM Bejani<\/bdi><\/p>\nAn Ensemble of Deep Clustering Models With Autoencoders to Mine Travel Patterns From Smart Card Data<\/li>\n<\/ul>\nS Saronian, B Yousefimehr, M Ghatee, MM BejaniIEEE Transactions on Intelligent Transportation Systems ( Volume: 25, Issue: 12, December 2024) Page(s): 20960 - 20969DOI: 10.1109\/TITS.2024.3475295<\/p>Read research update<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Journal article<\/small><\/div>Uncertainty quantification to enhance probabilistic fusion based user identification using smartphones<\/h2>IEEE Internet of Things Journal ( Volume: 11, Issue: 20, 15 October 2024), Page(s): 33450 - 33458<\/p>DOI<\/a>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10599325<\/a>Authors & full citation<\/summary>Authors: <\/strong>R Ahmadian, M Ghatee, J Wahlstr\u00f6m, H Zare<\/bdi><\/p>\nUncertainty quantification to enhance probabilistic fusion based user identification using smartphones<\/li>\n<\/ul>\nR Ahmadian, M Ghatee, J Wahlstr\u00f6m, H Zare<\/p>\nIEEE Internet of Things Journal ( Volume: 11, Issue: 20, 15 October 2024), Page(s): 33450 - 33458DOI: 10.1109\/JIOT.2024.3429011<\/p>Read research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Publication announcement; type not stated in Papers heading<\/small><\/div>Enhanced Multi-Modal Gas Leakage Detection with NSMOTE: A Novel Over-sampling Approach<\/h2>2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)<\/p>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570108<\/a>Authors & full citation<\/summary>Authors: <\/strong>Aref Azizian, Behnam Yousefimehr, Mehdi Ghatee<\/bdi><\/p>\nEnhanced Multi-Modal Gas Leakage Detection with NSMOTE: A Novel Over-sampling Approach<\/a><\/p>\n\n\n\nBy<\/p>\n\n\n\nAref Azizian, Behnam Yousefimehr, Mehdi Ghatee<\/p>\n\n\n\nhas been published in \"2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)\".<\/p>\n\n\n\nAbstract:<\/p>\n\n\n\nUrbanization and the emergence of smart cities have led to increased industrial activities, raising concerns about safety and environmental hazards. Detecting and monitoring gas leaks accurately is crucial due to the significant risks they pose to public health and the environment. In this study, we propose a novel approach that combines thermal imaging with sensor data to enhance gas detection accuracy in urban and industrial settings. By employing advanced algorithms and analyzing extensive datasets, our methodology achieves an impressive accuracy rate of 99.32%, setting a new standard in gas leak detection. Our innovation lies in the utilization of a unique oversampling technique called Normal Synthetic Minority Oversampling Technique (NSMOTE), coupled with the simultaneous integration of thermal imaging and sensor data within a multimodal framework. This breakthrough not only underscores the potential of integrating diverse data sources for environmental monitoring but also represents a significant stride in mitigating the risks associated with industrial gas emissions.<\/p>\n\n\n\nRef: https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570108<\/a><\/p>\nRead research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Publication announcement; type not stated in Papers heading<\/small><\/div>Calibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/h2>2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)<\/p>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>Authors & full citation<\/summary>Authors: <\/strong>M Moeini, R Ahmadian, M Ghatee<\/bdi><\/p>\nCalibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/a><\/p>\n\n\n\nBy<\/p>\n\n\n\nM Moeini, R Ahmadian, M Ghatee<\/p>\n\n\n\nhas been accepted in \"2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)\"<\/p>\n\n\n\nAbstract:<\/p>\n\n\n\nWith the rapid advancement of artificial intelligence technologies in human life, particularly within the automotive industry, the popularity of smart vehicles has increased. Designing an intelligent car cabin capable of seamless interactions with both the driver and the vehicle emerges as a crucial solution to address human-vehicle interaction challenges. This project aims to implement a digital voice assistant that recognizes vehicle commands. It utilizes three main techniques: speech-to-text conversion, text classification, and calibrating the classifier in order to detect out-of-distribution (OOD) sentences. Using Vosk, an LLM model, voices in the vehicle environment are converted into text format. Then, after pre-processing the text, an SVM classifies them. Using Platt scaling the SVM classifier outputs become calibrated, which makes them probabilistic. The experimental result shows that the proposed model achieves command recognition with 96.43% accuracy, 96.83% precision, 96.43% recall, 96.39% F1-score, and 0.1437 cross-entropy loss. Furthermore, the optimal threshold for OOD sentences is 0.4.<\/p>\n\n\n\nRef: https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>\u00a0<\/p>\nRead research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2023<\/span>Journal article<\/small><\/div>Branch-and-Price Based Heuristic Algorithm for Fuzzy Multi-Depot Bus Scheduling Problem<\/h2>International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 31 (2023) 859-888<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>
2026<\/span>Journal article<\/small><\/div>Multi-teacher knowledge distillation framework for lightweight anomaly detection<\/h2>Neural Networks 195, (2026) 108267<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>B Yousefimehr, M Ghatee, R Razavi-Far<\/bdi><\/p>Multi-teacher knowledge distillation framework for lightweight anomaly detection<\/p>\nB Yousefimehr, M Ghatee, R Razavi-Far<\/p>\nNeural Networks 195, (2026) 108267Ref: https:\/\/doi.org\/10.1016\/j.neunet.2025.108267<\/a><\/p>Read research update<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2025<\/span>Journal article<\/small><\/div>A systematic survey and empirical comparison of hybrid methods for imbalanced fraud detection: Combining resampling and machine learning<\/h2>AUT Journal of Mathematics and Computing, (2025)<\/p>DOI<\/a>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>B Yousefimehr, M Ghatee<\/bdi><\/p>\nA systematic survey and empirical comparison of hybrid methods for imbalanced fraud detection: Combining resampling and machine learning<\/li>\n<\/ul>\nB Yousefimehr, M Ghatee<\/p>\nAUT Journal of Mathematics and Computing, (2025)Ref: https:\/\/doi.org\/10.22060\/AJMC.2025.24642.1446<\/a><\/p>Read research update<\/a>A Systematic Survey and Empirical Comparison of Hybrid\u2026<\/a>AUT Journal of Mathematics and Computing.<\/a>Imbalanced Learning<\/a>Oversampling<\/a>Undersampling<\/a>Ensemble Learning<\/a>Auto Insurance Fraud Detection<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2025<\/span>Journal article<\/small><\/div>Fast inference in classification of Optical Coherence Tomography (OCT) images for real-time retinal disease diagnosis<\/h2>DOI<\/a>Publisher<\/a>Publisher<\/a>Authors & full citation<\/summary>Authors: <\/strong>Amin\u00a0Rahmani, Mehdi Ghatee<\/bdi><\/p>\nFast inference in classification of Optical Coherence Tomography (OCT) images for real-time retinal disease diagnosis<\/li>\n<\/ul>\nAmin\u00a0Rahmani, Mehdi Ghatee, Biomedical Signal Processing and Control<\/a>, Volume 103<\/a>,\u00a0May 2025, 107365<\/p>\nRef: https:\/\/doi.org\/10.1016\/j.bspc.2024.107365<\/a><\/p>Read research update<\/a>Journal<\/a>Issue<\/a><\/a>https:\/\/authors.elsevier.com\/a\/1kLO4_djyJXLUF<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2025<\/span>Journal article<\/small><\/div>A distribution-preserving method for resampling combined with LightGBM-LSTM for sequence-wise fraud detection in credit card transactions<\/h2>Expert Systems with Applications 262, (2025) 125661<\/p>DOI<\/a>Publisher<\/a>Authors & full citation<\/summary>Authors: <\/strong>B Yousefimehr, M Ghatee<\/bdi><\/p>\nA distribution-preserving method for resampling combined with LightGBM-LSTM for sequence-wise fraud detection in credit card transactions<\/li>\n<\/ul>\nB Yousefimehr, M Ghatee<\/p>\nExpert Systems with Applications 262, (2025) 125661Ref: https:\/\/doi.org\/10.1016\/j.eswa.2024.125661<\/a><\/p>Read research update<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2025<\/span>Journal article<\/small><\/div>Enhancing user identification through batch averaging of independent window subsequences using smartphone and wearable data<\/h2>Computers & Security, Volume 150, March 2025, 104265<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>R Ahmadian, M Ghatee, J Wahlstr\u00f6m<\/bdi><\/p>\nEnhancing user identification through batch averaging of independent window subsequences using smartphone and wearable data<\/li>\n<\/ul>\nR Ahmadian, M Ghatee, J Wahlstr\u00f6m<\/p>\nComputers & Security, Volume 150, March 2025, 104265<\/p>\nDOI: https:\/\/doi.org\/10.1016\/j.cose.2024.104265<\/a><\/p>Read research update<\/a>Journal<\/a>https:\/\/authors.elsevier.com\/a\/1kHD~c43v4OnK<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Journal article<\/small><\/div>An Ensemble of Deep Clustering Models With Autoencoders to Mine Travel Patterns From Smart Card Data<\/h2>IEEE Transactions on Intelligent Transportation Systems ( Volume: 25, Issue: 12, December 2024) Page(s): 20960 - 20969<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>S Saronian, B Yousefimehr, M Ghatee, MM Bejani<\/bdi><\/p>\nAn Ensemble of Deep Clustering Models With Autoencoders to Mine Travel Patterns From Smart Card Data<\/li>\n<\/ul>\nS Saronian, B Yousefimehr, M Ghatee, MM BejaniIEEE Transactions on Intelligent Transportation Systems ( Volume: 25, Issue: 12, December 2024) Page(s): 20960 - 20969DOI: 10.1109\/TITS.2024.3475295<\/p>Read research update<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Journal article<\/small><\/div>Uncertainty quantification to enhance probabilistic fusion based user identification using smartphones<\/h2>IEEE Internet of Things Journal ( Volume: 11, Issue: 20, 15 October 2024), Page(s): 33450 - 33458<\/p>DOI<\/a>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10599325<\/a>Authors & full citation<\/summary>Authors: <\/strong>R Ahmadian, M Ghatee, J Wahlstr\u00f6m, H Zare<\/bdi><\/p>\nUncertainty quantification to enhance probabilistic fusion based user identification using smartphones<\/li>\n<\/ul>\nR Ahmadian, M Ghatee, J Wahlstr\u00f6m, H Zare<\/p>\nIEEE Internet of Things Journal ( Volume: 11, Issue: 20, 15 October 2024), Page(s): 33450 - 33458DOI: 10.1109\/JIOT.2024.3429011<\/p>Read research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Publication announcement; type not stated in Papers heading<\/small><\/div>Enhanced Multi-Modal Gas Leakage Detection with NSMOTE: A Novel Over-sampling Approach<\/h2>2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)<\/p>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570108<\/a>Authors & full citation<\/summary>Authors: <\/strong>Aref Azizian, Behnam Yousefimehr, Mehdi Ghatee<\/bdi><\/p>\nEnhanced Multi-Modal Gas Leakage Detection with NSMOTE: A Novel Over-sampling Approach<\/a><\/p>\n\n\n\nBy<\/p>\n\n\n\nAref Azizian, Behnam Yousefimehr, Mehdi Ghatee<\/p>\n\n\n\nhas been published in \"2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)\".<\/p>\n\n\n\nAbstract:<\/p>\n\n\n\nUrbanization and the emergence of smart cities have led to increased industrial activities, raising concerns about safety and environmental hazards. Detecting and monitoring gas leaks accurately is crucial due to the significant risks they pose to public health and the environment. In this study, we propose a novel approach that combines thermal imaging with sensor data to enhance gas detection accuracy in urban and industrial settings. By employing advanced algorithms and analyzing extensive datasets, our methodology achieves an impressive accuracy rate of 99.32%, setting a new standard in gas leak detection. Our innovation lies in the utilization of a unique oversampling technique called Normal Synthetic Minority Oversampling Technique (NSMOTE), coupled with the simultaneous integration of thermal imaging and sensor data within a multimodal framework. This breakthrough not only underscores the potential of integrating diverse data sources for environmental monitoring but also represents a significant stride in mitigating the risks associated with industrial gas emissions.<\/p>\n\n\n\nRef: https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570108<\/a><\/p>\nRead research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Publication announcement; type not stated in Papers heading<\/small><\/div>Calibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/h2>2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)<\/p>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>Authors & full citation<\/summary>Authors: <\/strong>M Moeini, R Ahmadian, M Ghatee<\/bdi><\/p>\nCalibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/a><\/p>\n\n\n\nBy<\/p>\n\n\n\nM Moeini, R Ahmadian, M Ghatee<\/p>\n\n\n\nhas been accepted in \"2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)\"<\/p>\n\n\n\nAbstract:<\/p>\n\n\n\nWith the rapid advancement of artificial intelligence technologies in human life, particularly within the automotive industry, the popularity of smart vehicles has increased. Designing an intelligent car cabin capable of seamless interactions with both the driver and the vehicle emerges as a crucial solution to address human-vehicle interaction challenges. This project aims to implement a digital voice assistant that recognizes vehicle commands. It utilizes three main techniques: speech-to-text conversion, text classification, and calibrating the classifier in order to detect out-of-distribution (OOD) sentences. Using Vosk, an LLM model, voices in the vehicle environment are converted into text format. Then, after pre-processing the text, an SVM classifies them. Using Platt scaling the SVM classifier outputs become calibrated, which makes them probabilistic. The experimental result shows that the proposed model achieves command recognition with 96.43% accuracy, 96.83% precision, 96.43% recall, 96.39% F1-score, and 0.1437 cross-entropy loss. Furthermore, the optimal threshold for OOD sentences is 0.4.<\/p>\n\n\n\nRef: https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>\u00a0<\/p>\nRead research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2023<\/span>Journal article<\/small><\/div>Branch-and-Price Based Heuristic Algorithm for Fuzzy Multi-Depot Bus Scheduling Problem<\/h2>International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 31 (2023) 859-888<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>
2025<\/span>Journal article<\/small><\/div>A systematic survey and empirical comparison of hybrid methods for imbalanced fraud detection: Combining resampling and machine learning<\/h2>AUT Journal of Mathematics and Computing, (2025)<\/p>DOI<\/a>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>B Yousefimehr, M Ghatee<\/bdi><\/p>\nA systematic survey and empirical comparison of hybrid methods for imbalanced fraud detection: Combining resampling and machine learning<\/li>\n<\/ul>\nB Yousefimehr, M Ghatee<\/p>\nAUT Journal of Mathematics and Computing, (2025)Ref: https:\/\/doi.org\/10.22060\/AJMC.2025.24642.1446<\/a><\/p>Read research update<\/a>A Systematic Survey and Empirical Comparison of Hybrid\u2026<\/a>AUT Journal of Mathematics and Computing.<\/a>Imbalanced Learning<\/a>Oversampling<\/a>Undersampling<\/a>Ensemble Learning<\/a>Auto Insurance Fraud Detection<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2025<\/span>Journal article<\/small><\/div>Fast inference in classification of Optical Coherence Tomography (OCT) images for real-time retinal disease diagnosis<\/h2>DOI<\/a>Publisher<\/a>Publisher<\/a>Authors & full citation<\/summary>Authors: <\/strong>Amin\u00a0Rahmani, Mehdi Ghatee<\/bdi><\/p>\nFast inference in classification of Optical Coherence Tomography (OCT) images for real-time retinal disease diagnosis<\/li>\n<\/ul>\nAmin\u00a0Rahmani, Mehdi Ghatee, Biomedical Signal Processing and Control<\/a>, Volume 103<\/a>,\u00a0May 2025, 107365<\/p>\nRef: https:\/\/doi.org\/10.1016\/j.bspc.2024.107365<\/a><\/p>Read research update<\/a>Journal<\/a>Issue<\/a><\/a>https:\/\/authors.elsevier.com\/a\/1kLO4_djyJXLUF<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2025<\/span>Journal article<\/small><\/div>A distribution-preserving method for resampling combined with LightGBM-LSTM for sequence-wise fraud detection in credit card transactions<\/h2>Expert Systems with Applications 262, (2025) 125661<\/p>DOI<\/a>Publisher<\/a>Authors & full citation<\/summary>Authors: <\/strong>B Yousefimehr, M Ghatee<\/bdi><\/p>\nA distribution-preserving method for resampling combined with LightGBM-LSTM for sequence-wise fraud detection in credit card transactions<\/li>\n<\/ul>\nB Yousefimehr, M Ghatee<\/p>\nExpert Systems with Applications 262, (2025) 125661Ref: https:\/\/doi.org\/10.1016\/j.eswa.2024.125661<\/a><\/p>Read research update<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2025<\/span>Journal article<\/small><\/div>Enhancing user identification through batch averaging of independent window subsequences using smartphone and wearable data<\/h2>Computers & Security, Volume 150, March 2025, 104265<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>R Ahmadian, M Ghatee, J Wahlstr\u00f6m<\/bdi><\/p>\nEnhancing user identification through batch averaging of independent window subsequences using smartphone and wearable data<\/li>\n<\/ul>\nR Ahmadian, M Ghatee, J Wahlstr\u00f6m<\/p>\nComputers & Security, Volume 150, March 2025, 104265<\/p>\nDOI: https:\/\/doi.org\/10.1016\/j.cose.2024.104265<\/a><\/p>Read research update<\/a>Journal<\/a>https:\/\/authors.elsevier.com\/a\/1kHD~c43v4OnK<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Journal article<\/small><\/div>An Ensemble of Deep Clustering Models With Autoencoders to Mine Travel Patterns From Smart Card Data<\/h2>IEEE Transactions on Intelligent Transportation Systems ( Volume: 25, Issue: 12, December 2024) Page(s): 20960 - 20969<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>S Saronian, B Yousefimehr, M Ghatee, MM Bejani<\/bdi><\/p>\nAn Ensemble of Deep Clustering Models With Autoencoders to Mine Travel Patterns From Smart Card Data<\/li>\n<\/ul>\nS Saronian, B Yousefimehr, M Ghatee, MM BejaniIEEE Transactions on Intelligent Transportation Systems ( Volume: 25, Issue: 12, December 2024) Page(s): 20960 - 20969DOI: 10.1109\/TITS.2024.3475295<\/p>Read research update<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Journal article<\/small><\/div>Uncertainty quantification to enhance probabilistic fusion based user identification using smartphones<\/h2>IEEE Internet of Things Journal ( Volume: 11, Issue: 20, 15 October 2024), Page(s): 33450 - 33458<\/p>DOI<\/a>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10599325<\/a>Authors & full citation<\/summary>Authors: <\/strong>R Ahmadian, M Ghatee, J Wahlstr\u00f6m, H Zare<\/bdi><\/p>\nUncertainty quantification to enhance probabilistic fusion based user identification using smartphones<\/li>\n<\/ul>\nR Ahmadian, M Ghatee, J Wahlstr\u00f6m, H Zare<\/p>\nIEEE Internet of Things Journal ( Volume: 11, Issue: 20, 15 October 2024), Page(s): 33450 - 33458DOI: 10.1109\/JIOT.2024.3429011<\/p>Read research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Publication announcement; type not stated in Papers heading<\/small><\/div>Enhanced Multi-Modal Gas Leakage Detection with NSMOTE: A Novel Over-sampling Approach<\/h2>2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)<\/p>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570108<\/a>Authors & full citation<\/summary>Authors: <\/strong>Aref Azizian, Behnam Yousefimehr, Mehdi Ghatee<\/bdi><\/p>\nEnhanced Multi-Modal Gas Leakage Detection with NSMOTE: A Novel Over-sampling Approach<\/a><\/p>\n\n\n\nBy<\/p>\n\n\n\nAref Azizian, Behnam Yousefimehr, Mehdi Ghatee<\/p>\n\n\n\nhas been published in \"2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)\".<\/p>\n\n\n\nAbstract:<\/p>\n\n\n\nUrbanization and the emergence of smart cities have led to increased industrial activities, raising concerns about safety and environmental hazards. Detecting and monitoring gas leaks accurately is crucial due to the significant risks they pose to public health and the environment. In this study, we propose a novel approach that combines thermal imaging with sensor data to enhance gas detection accuracy in urban and industrial settings. By employing advanced algorithms and analyzing extensive datasets, our methodology achieves an impressive accuracy rate of 99.32%, setting a new standard in gas leak detection. Our innovation lies in the utilization of a unique oversampling technique called Normal Synthetic Minority Oversampling Technique (NSMOTE), coupled with the simultaneous integration of thermal imaging and sensor data within a multimodal framework. This breakthrough not only underscores the potential of integrating diverse data sources for environmental monitoring but also represents a significant stride in mitigating the risks associated with industrial gas emissions.<\/p>\n\n\n\nRef: https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570108<\/a><\/p>\nRead research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Publication announcement; type not stated in Papers heading<\/small><\/div>Calibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/h2>2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)<\/p>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>Authors & full citation<\/summary>Authors: <\/strong>M Moeini, R Ahmadian, M Ghatee<\/bdi><\/p>\nCalibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/a><\/p>\n\n\n\nBy<\/p>\n\n\n\nM Moeini, R Ahmadian, M Ghatee<\/p>\n\n\n\nhas been accepted in \"2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)\"<\/p>\n\n\n\nAbstract:<\/p>\n\n\n\nWith the rapid advancement of artificial intelligence technologies in human life, particularly within the automotive industry, the popularity of smart vehicles has increased. Designing an intelligent car cabin capable of seamless interactions with both the driver and the vehicle emerges as a crucial solution to address human-vehicle interaction challenges. This project aims to implement a digital voice assistant that recognizes vehicle commands. It utilizes three main techniques: speech-to-text conversion, text classification, and calibrating the classifier in order to detect out-of-distribution (OOD) sentences. Using Vosk, an LLM model, voices in the vehicle environment are converted into text format. Then, after pre-processing the text, an SVM classifies them. Using Platt scaling the SVM classifier outputs become calibrated, which makes them probabilistic. The experimental result shows that the proposed model achieves command recognition with 96.43% accuracy, 96.83% precision, 96.43% recall, 96.39% F1-score, and 0.1437 cross-entropy loss. Furthermore, the optimal threshold for OOD sentences is 0.4.<\/p>\n\n\n\nRef: https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>\u00a0<\/p>\nRead research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2023<\/span>Journal article<\/small><\/div>Branch-and-Price Based Heuristic Algorithm for Fuzzy Multi-Depot Bus Scheduling Problem<\/h2>International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 31 (2023) 859-888<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>
2025<\/span>Journal article<\/small><\/div>Fast inference in classification of Optical Coherence Tomography (OCT) images for real-time retinal disease diagnosis<\/h2>DOI<\/a>Publisher<\/a>Publisher<\/a>Authors & full citation<\/summary>Authors: <\/strong>Amin\u00a0Rahmani, Mehdi Ghatee<\/bdi><\/p>\nFast inference in classification of Optical Coherence Tomography (OCT) images for real-time retinal disease diagnosis<\/li>\n<\/ul>\nAmin\u00a0Rahmani, Mehdi Ghatee, Biomedical Signal Processing and Control<\/a>, Volume 103<\/a>,\u00a0May 2025, 107365<\/p>\nRef: https:\/\/doi.org\/10.1016\/j.bspc.2024.107365<\/a><\/p>Read research update<\/a>Journal<\/a>Issue<\/a><\/a>https:\/\/authors.elsevier.com\/a\/1kLO4_djyJXLUF<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2025<\/span>Journal article<\/small><\/div>A distribution-preserving method for resampling combined with LightGBM-LSTM for sequence-wise fraud detection in credit card transactions<\/h2>Expert Systems with Applications 262, (2025) 125661<\/p>DOI<\/a>Publisher<\/a>Authors & full citation<\/summary>Authors: <\/strong>B Yousefimehr, M Ghatee<\/bdi><\/p>\nA distribution-preserving method for resampling combined with LightGBM-LSTM for sequence-wise fraud detection in credit card transactions<\/li>\n<\/ul>\nB Yousefimehr, M Ghatee<\/p>\nExpert Systems with Applications 262, (2025) 125661Ref: https:\/\/doi.org\/10.1016\/j.eswa.2024.125661<\/a><\/p>Read research update<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2025<\/span>Journal article<\/small><\/div>Enhancing user identification through batch averaging of independent window subsequences using smartphone and wearable data<\/h2>Computers & Security, Volume 150, March 2025, 104265<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>R Ahmadian, M Ghatee, J Wahlstr\u00f6m<\/bdi><\/p>\nEnhancing user identification through batch averaging of independent window subsequences using smartphone and wearable data<\/li>\n<\/ul>\nR Ahmadian, M Ghatee, J Wahlstr\u00f6m<\/p>\nComputers & Security, Volume 150, March 2025, 104265<\/p>\nDOI: https:\/\/doi.org\/10.1016\/j.cose.2024.104265<\/a><\/p>Read research update<\/a>Journal<\/a>https:\/\/authors.elsevier.com\/a\/1kHD~c43v4OnK<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Journal article<\/small><\/div>An Ensemble of Deep Clustering Models With Autoencoders to Mine Travel Patterns From Smart Card Data<\/h2>IEEE Transactions on Intelligent Transportation Systems ( Volume: 25, Issue: 12, December 2024) Page(s): 20960 - 20969<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>S Saronian, B Yousefimehr, M Ghatee, MM Bejani<\/bdi><\/p>\nAn Ensemble of Deep Clustering Models With Autoencoders to Mine Travel Patterns From Smart Card Data<\/li>\n<\/ul>\nS Saronian, B Yousefimehr, M Ghatee, MM BejaniIEEE Transactions on Intelligent Transportation Systems ( Volume: 25, Issue: 12, December 2024) Page(s): 20960 - 20969DOI: 10.1109\/TITS.2024.3475295<\/p>Read research update<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Journal article<\/small><\/div>Uncertainty quantification to enhance probabilistic fusion based user identification using smartphones<\/h2>IEEE Internet of Things Journal ( Volume: 11, Issue: 20, 15 October 2024), Page(s): 33450 - 33458<\/p>DOI<\/a>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10599325<\/a>Authors & full citation<\/summary>Authors: <\/strong>R Ahmadian, M Ghatee, J Wahlstr\u00f6m, H Zare<\/bdi><\/p>\nUncertainty quantification to enhance probabilistic fusion based user identification using smartphones<\/li>\n<\/ul>\nR Ahmadian, M Ghatee, J Wahlstr\u00f6m, H Zare<\/p>\nIEEE Internet of Things Journal ( Volume: 11, Issue: 20, 15 October 2024), Page(s): 33450 - 33458DOI: 10.1109\/JIOT.2024.3429011<\/p>Read research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Publication announcement; type not stated in Papers heading<\/small><\/div>Enhanced Multi-Modal Gas Leakage Detection with NSMOTE: A Novel Over-sampling Approach<\/h2>2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)<\/p>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570108<\/a>Authors & full citation<\/summary>Authors: <\/strong>Aref Azizian, Behnam Yousefimehr, Mehdi Ghatee<\/bdi><\/p>\nEnhanced Multi-Modal Gas Leakage Detection with NSMOTE: A Novel Over-sampling Approach<\/a><\/p>\n\n\n\nBy<\/p>\n\n\n\nAref Azizian, Behnam Yousefimehr, Mehdi Ghatee<\/p>\n\n\n\nhas been published in \"2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)\".<\/p>\n\n\n\nAbstract:<\/p>\n\n\n\nUrbanization and the emergence of smart cities have led to increased industrial activities, raising concerns about safety and environmental hazards. Detecting and monitoring gas leaks accurately is crucial due to the significant risks they pose to public health and the environment. In this study, we propose a novel approach that combines thermal imaging with sensor data to enhance gas detection accuracy in urban and industrial settings. By employing advanced algorithms and analyzing extensive datasets, our methodology achieves an impressive accuracy rate of 99.32%, setting a new standard in gas leak detection. Our innovation lies in the utilization of a unique oversampling technique called Normal Synthetic Minority Oversampling Technique (NSMOTE), coupled with the simultaneous integration of thermal imaging and sensor data within a multimodal framework. This breakthrough not only underscores the potential of integrating diverse data sources for environmental monitoring but also represents a significant stride in mitigating the risks associated with industrial gas emissions.<\/p>\n\n\n\nRef: https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570108<\/a><\/p>\nRead research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Publication announcement; type not stated in Papers heading<\/small><\/div>Calibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/h2>2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)<\/p>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>Authors & full citation<\/summary>Authors: <\/strong>M Moeini, R Ahmadian, M Ghatee<\/bdi><\/p>\nCalibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/a><\/p>\n\n\n\nBy<\/p>\n\n\n\nM Moeini, R Ahmadian, M Ghatee<\/p>\n\n\n\nhas been accepted in \"2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)\"<\/p>\n\n\n\nAbstract:<\/p>\n\n\n\nWith the rapid advancement of artificial intelligence technologies in human life, particularly within the automotive industry, the popularity of smart vehicles has increased. Designing an intelligent car cabin capable of seamless interactions with both the driver and the vehicle emerges as a crucial solution to address human-vehicle interaction challenges. This project aims to implement a digital voice assistant that recognizes vehicle commands. It utilizes three main techniques: speech-to-text conversion, text classification, and calibrating the classifier in order to detect out-of-distribution (OOD) sentences. Using Vosk, an LLM model, voices in the vehicle environment are converted into text format. Then, after pre-processing the text, an SVM classifies them. Using Platt scaling the SVM classifier outputs become calibrated, which makes them probabilistic. The experimental result shows that the proposed model achieves command recognition with 96.43% accuracy, 96.83% precision, 96.43% recall, 96.39% F1-score, and 0.1437 cross-entropy loss. Furthermore, the optimal threshold for OOD sentences is 0.4.<\/p>\n\n\n\nRef: https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>\u00a0<\/p>\nRead research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2023<\/span>Journal article<\/small><\/div>Branch-and-Price Based Heuristic Algorithm for Fuzzy Multi-Depot Bus Scheduling Problem<\/h2>International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 31 (2023) 859-888<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>
2025<\/span>Journal article<\/small><\/div>A distribution-preserving method for resampling combined with LightGBM-LSTM for sequence-wise fraud detection in credit card transactions<\/h2>Expert Systems with Applications 262, (2025) 125661<\/p>DOI<\/a>Publisher<\/a>Authors & full citation<\/summary>Authors: <\/strong>B Yousefimehr, M Ghatee<\/bdi><\/p>\nA distribution-preserving method for resampling combined with LightGBM-LSTM for sequence-wise fraud detection in credit card transactions<\/li>\n<\/ul>\nB Yousefimehr, M Ghatee<\/p>\nExpert Systems with Applications 262, (2025) 125661Ref: https:\/\/doi.org\/10.1016\/j.eswa.2024.125661<\/a><\/p>Read research update<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2025<\/span>Journal article<\/small><\/div>Enhancing user identification through batch averaging of independent window subsequences using smartphone and wearable data<\/h2>Computers & Security, Volume 150, March 2025, 104265<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>R Ahmadian, M Ghatee, J Wahlstr\u00f6m<\/bdi><\/p>\nEnhancing user identification through batch averaging of independent window subsequences using smartphone and wearable data<\/li>\n<\/ul>\nR Ahmadian, M Ghatee, J Wahlstr\u00f6m<\/p>\nComputers & Security, Volume 150, March 2025, 104265<\/p>\nDOI: https:\/\/doi.org\/10.1016\/j.cose.2024.104265<\/a><\/p>Read research update<\/a>Journal<\/a>https:\/\/authors.elsevier.com\/a\/1kHD~c43v4OnK<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Journal article<\/small><\/div>An Ensemble of Deep Clustering Models With Autoencoders to Mine Travel Patterns From Smart Card Data<\/h2>IEEE Transactions on Intelligent Transportation Systems ( Volume: 25, Issue: 12, December 2024) Page(s): 20960 - 20969<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>S Saronian, B Yousefimehr, M Ghatee, MM Bejani<\/bdi><\/p>\nAn Ensemble of Deep Clustering Models With Autoencoders to Mine Travel Patterns From Smart Card Data<\/li>\n<\/ul>\nS Saronian, B Yousefimehr, M Ghatee, MM BejaniIEEE Transactions on Intelligent Transportation Systems ( Volume: 25, Issue: 12, December 2024) Page(s): 20960 - 20969DOI: 10.1109\/TITS.2024.3475295<\/p>Read research update<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Journal article<\/small><\/div>Uncertainty quantification to enhance probabilistic fusion based user identification using smartphones<\/h2>IEEE Internet of Things Journal ( Volume: 11, Issue: 20, 15 October 2024), Page(s): 33450 - 33458<\/p>DOI<\/a>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10599325<\/a>Authors & full citation<\/summary>Authors: <\/strong>R Ahmadian, M Ghatee, J Wahlstr\u00f6m, H Zare<\/bdi><\/p>\nUncertainty quantification to enhance probabilistic fusion based user identification using smartphones<\/li>\n<\/ul>\nR Ahmadian, M Ghatee, J Wahlstr\u00f6m, H Zare<\/p>\nIEEE Internet of Things Journal ( Volume: 11, Issue: 20, 15 October 2024), Page(s): 33450 - 33458DOI: 10.1109\/JIOT.2024.3429011<\/p>Read research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Publication announcement; type not stated in Papers heading<\/small><\/div>Enhanced Multi-Modal Gas Leakage Detection with NSMOTE: A Novel Over-sampling Approach<\/h2>2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)<\/p>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570108<\/a>Authors & full citation<\/summary>Authors: <\/strong>Aref Azizian, Behnam Yousefimehr, Mehdi Ghatee<\/bdi><\/p>\nEnhanced Multi-Modal Gas Leakage Detection with NSMOTE: A Novel Over-sampling Approach<\/a><\/p>\n\n\n\nBy<\/p>\n\n\n\nAref Azizian, Behnam Yousefimehr, Mehdi Ghatee<\/p>\n\n\n\nhas been published in \"2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)\".<\/p>\n\n\n\nAbstract:<\/p>\n\n\n\nUrbanization and the emergence of smart cities have led to increased industrial activities, raising concerns about safety and environmental hazards. Detecting and monitoring gas leaks accurately is crucial due to the significant risks they pose to public health and the environment. In this study, we propose a novel approach that combines thermal imaging with sensor data to enhance gas detection accuracy in urban and industrial settings. By employing advanced algorithms and analyzing extensive datasets, our methodology achieves an impressive accuracy rate of 99.32%, setting a new standard in gas leak detection. Our innovation lies in the utilization of a unique oversampling technique called Normal Synthetic Minority Oversampling Technique (NSMOTE), coupled with the simultaneous integration of thermal imaging and sensor data within a multimodal framework. This breakthrough not only underscores the potential of integrating diverse data sources for environmental monitoring but also represents a significant stride in mitigating the risks associated with industrial gas emissions.<\/p>\n\n\n\nRef: https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570108<\/a><\/p>\nRead research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Publication announcement; type not stated in Papers heading<\/small><\/div>Calibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/h2>2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)<\/p>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>Authors & full citation<\/summary>Authors: <\/strong>M Moeini, R Ahmadian, M Ghatee<\/bdi><\/p>\nCalibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/a><\/p>\n\n\n\nBy<\/p>\n\n\n\nM Moeini, R Ahmadian, M Ghatee<\/p>\n\n\n\nhas been accepted in \"2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)\"<\/p>\n\n\n\nAbstract:<\/p>\n\n\n\nWith the rapid advancement of artificial intelligence technologies in human life, particularly within the automotive industry, the popularity of smart vehicles has increased. Designing an intelligent car cabin capable of seamless interactions with both the driver and the vehicle emerges as a crucial solution to address human-vehicle interaction challenges. This project aims to implement a digital voice assistant that recognizes vehicle commands. It utilizes three main techniques: speech-to-text conversion, text classification, and calibrating the classifier in order to detect out-of-distribution (OOD) sentences. Using Vosk, an LLM model, voices in the vehicle environment are converted into text format. Then, after pre-processing the text, an SVM classifies them. Using Platt scaling the SVM classifier outputs become calibrated, which makes them probabilistic. The experimental result shows that the proposed model achieves command recognition with 96.43% accuracy, 96.83% precision, 96.43% recall, 96.39% F1-score, and 0.1437 cross-entropy loss. Furthermore, the optimal threshold for OOD sentences is 0.4.<\/p>\n\n\n\nRef: https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>\u00a0<\/p>\nRead research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2023<\/span>Journal article<\/small><\/div>Branch-and-Price Based Heuristic Algorithm for Fuzzy Multi-Depot Bus Scheduling Problem<\/h2>International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 31 (2023) 859-888<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>
2025<\/span>Journal article<\/small><\/div>Enhancing user identification through batch averaging of independent window subsequences using smartphone and wearable data<\/h2>Computers & Security, Volume 150, March 2025, 104265<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>R Ahmadian, M Ghatee, J Wahlstr\u00f6m<\/bdi><\/p>\nEnhancing user identification through batch averaging of independent window subsequences using smartphone and wearable data<\/li>\n<\/ul>\nR Ahmadian, M Ghatee, J Wahlstr\u00f6m<\/p>\nComputers & Security, Volume 150, March 2025, 104265<\/p>\nDOI: https:\/\/doi.org\/10.1016\/j.cose.2024.104265<\/a><\/p>Read research update<\/a>Journal<\/a>https:\/\/authors.elsevier.com\/a\/1kHD~c43v4OnK<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Journal article<\/small><\/div>An Ensemble of Deep Clustering Models With Autoencoders to Mine Travel Patterns From Smart Card Data<\/h2>IEEE Transactions on Intelligent Transportation Systems ( Volume: 25, Issue: 12, December 2024) Page(s): 20960 - 20969<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>S Saronian, B Yousefimehr, M Ghatee, MM Bejani<\/bdi><\/p>\nAn Ensemble of Deep Clustering Models With Autoencoders to Mine Travel Patterns From Smart Card Data<\/li>\n<\/ul>\nS Saronian, B Yousefimehr, M Ghatee, MM BejaniIEEE Transactions on Intelligent Transportation Systems ( Volume: 25, Issue: 12, December 2024) Page(s): 20960 - 20969DOI: 10.1109\/TITS.2024.3475295<\/p>Read research update<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Journal article<\/small><\/div>Uncertainty quantification to enhance probabilistic fusion based user identification using smartphones<\/h2>IEEE Internet of Things Journal ( Volume: 11, Issue: 20, 15 October 2024), Page(s): 33450 - 33458<\/p>DOI<\/a>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10599325<\/a>Authors & full citation<\/summary>Authors: <\/strong>R Ahmadian, M Ghatee, J Wahlstr\u00f6m, H Zare<\/bdi><\/p>\nUncertainty quantification to enhance probabilistic fusion based user identification using smartphones<\/li>\n<\/ul>\nR Ahmadian, M Ghatee, J Wahlstr\u00f6m, H Zare<\/p>\nIEEE Internet of Things Journal ( Volume: 11, Issue: 20, 15 October 2024), Page(s): 33450 - 33458DOI: 10.1109\/JIOT.2024.3429011<\/p>Read research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Publication announcement; type not stated in Papers heading<\/small><\/div>Enhanced Multi-Modal Gas Leakage Detection with NSMOTE: A Novel Over-sampling Approach<\/h2>2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)<\/p>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570108<\/a>Authors & full citation<\/summary>Authors: <\/strong>Aref Azizian, Behnam Yousefimehr, Mehdi Ghatee<\/bdi><\/p>\nEnhanced Multi-Modal Gas Leakage Detection with NSMOTE: A Novel Over-sampling Approach<\/a><\/p>\n\n\n\nBy<\/p>\n\n\n\nAref Azizian, Behnam Yousefimehr, Mehdi Ghatee<\/p>\n\n\n\nhas been published in \"2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)\".<\/p>\n\n\n\nAbstract:<\/p>\n\n\n\nUrbanization and the emergence of smart cities have led to increased industrial activities, raising concerns about safety and environmental hazards. Detecting and monitoring gas leaks accurately is crucial due to the significant risks they pose to public health and the environment. In this study, we propose a novel approach that combines thermal imaging with sensor data to enhance gas detection accuracy in urban and industrial settings. By employing advanced algorithms and analyzing extensive datasets, our methodology achieves an impressive accuracy rate of 99.32%, setting a new standard in gas leak detection. Our innovation lies in the utilization of a unique oversampling technique called Normal Synthetic Minority Oversampling Technique (NSMOTE), coupled with the simultaneous integration of thermal imaging and sensor data within a multimodal framework. This breakthrough not only underscores the potential of integrating diverse data sources for environmental monitoring but also represents a significant stride in mitigating the risks associated with industrial gas emissions.<\/p>\n\n\n\nRef: https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570108<\/a><\/p>\nRead research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Publication announcement; type not stated in Papers heading<\/small><\/div>Calibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/h2>2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)<\/p>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>Authors & full citation<\/summary>Authors: <\/strong>M Moeini, R Ahmadian, M Ghatee<\/bdi><\/p>\nCalibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/a><\/p>\n\n\n\nBy<\/p>\n\n\n\nM Moeini, R Ahmadian, M Ghatee<\/p>\n\n\n\nhas been accepted in \"2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)\"<\/p>\n\n\n\nAbstract:<\/p>\n\n\n\nWith the rapid advancement of artificial intelligence technologies in human life, particularly within the automotive industry, the popularity of smart vehicles has increased. Designing an intelligent car cabin capable of seamless interactions with both the driver and the vehicle emerges as a crucial solution to address human-vehicle interaction challenges. This project aims to implement a digital voice assistant that recognizes vehicle commands. It utilizes three main techniques: speech-to-text conversion, text classification, and calibrating the classifier in order to detect out-of-distribution (OOD) sentences. Using Vosk, an LLM model, voices in the vehicle environment are converted into text format. Then, after pre-processing the text, an SVM classifies them. Using Platt scaling the SVM classifier outputs become calibrated, which makes them probabilistic. The experimental result shows that the proposed model achieves command recognition with 96.43% accuracy, 96.83% precision, 96.43% recall, 96.39% F1-score, and 0.1437 cross-entropy loss. Furthermore, the optimal threshold for OOD sentences is 0.4.<\/p>\n\n\n\nRef: https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>\u00a0<\/p>\nRead research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2023<\/span>Journal article<\/small><\/div>Branch-and-Price Based Heuristic Algorithm for Fuzzy Multi-Depot Bus Scheduling Problem<\/h2>International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 31 (2023) 859-888<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>
2024<\/span>Journal article<\/small><\/div>An Ensemble of Deep Clustering Models With Autoencoders to Mine Travel Patterns From Smart Card Data<\/h2>IEEE Transactions on Intelligent Transportation Systems ( Volume: 25, Issue: 12, December 2024) Page(s): 20960 - 20969<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>S Saronian, B Yousefimehr, M Ghatee, MM Bejani<\/bdi><\/p>\nAn Ensemble of Deep Clustering Models With Autoencoders to Mine Travel Patterns From Smart Card Data<\/li>\n<\/ul>\nS Saronian, B Yousefimehr, M Ghatee, MM BejaniIEEE Transactions on Intelligent Transportation Systems ( Volume: 25, Issue: 12, December 2024) Page(s): 20960 - 20969DOI: 10.1109\/TITS.2024.3475295<\/p>Read research update<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Journal article<\/small><\/div>Uncertainty quantification to enhance probabilistic fusion based user identification using smartphones<\/h2>IEEE Internet of Things Journal ( Volume: 11, Issue: 20, 15 October 2024), Page(s): 33450 - 33458<\/p>DOI<\/a>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10599325<\/a>Authors & full citation<\/summary>Authors: <\/strong>R Ahmadian, M Ghatee, J Wahlstr\u00f6m, H Zare<\/bdi><\/p>\nUncertainty quantification to enhance probabilistic fusion based user identification using smartphones<\/li>\n<\/ul>\nR Ahmadian, M Ghatee, J Wahlstr\u00f6m, H Zare<\/p>\nIEEE Internet of Things Journal ( Volume: 11, Issue: 20, 15 October 2024), Page(s): 33450 - 33458DOI: 10.1109\/JIOT.2024.3429011<\/p>Read research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Publication announcement; type not stated in Papers heading<\/small><\/div>Enhanced Multi-Modal Gas Leakage Detection with NSMOTE: A Novel Over-sampling Approach<\/h2>2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)<\/p>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570108<\/a>Authors & full citation<\/summary>Authors: <\/strong>Aref Azizian, Behnam Yousefimehr, Mehdi Ghatee<\/bdi><\/p>\nEnhanced Multi-Modal Gas Leakage Detection with NSMOTE: A Novel Over-sampling Approach<\/a><\/p>\n\n\n\nBy<\/p>\n\n\n\nAref Azizian, Behnam Yousefimehr, Mehdi Ghatee<\/p>\n\n\n\nhas been published in \"2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)\".<\/p>\n\n\n\nAbstract:<\/p>\n\n\n\nUrbanization and the emergence of smart cities have led to increased industrial activities, raising concerns about safety and environmental hazards. Detecting and monitoring gas leaks accurately is crucial due to the significant risks they pose to public health and the environment. In this study, we propose a novel approach that combines thermal imaging with sensor data to enhance gas detection accuracy in urban and industrial settings. By employing advanced algorithms and analyzing extensive datasets, our methodology achieves an impressive accuracy rate of 99.32%, setting a new standard in gas leak detection. Our innovation lies in the utilization of a unique oversampling technique called Normal Synthetic Minority Oversampling Technique (NSMOTE), coupled with the simultaneous integration of thermal imaging and sensor data within a multimodal framework. This breakthrough not only underscores the potential of integrating diverse data sources for environmental monitoring but also represents a significant stride in mitigating the risks associated with industrial gas emissions.<\/p>\n\n\n\nRef: https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570108<\/a><\/p>\nRead research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Publication announcement; type not stated in Papers heading<\/small><\/div>Calibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/h2>2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)<\/p>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>Authors & full citation<\/summary>Authors: <\/strong>M Moeini, R Ahmadian, M Ghatee<\/bdi><\/p>\nCalibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/a><\/p>\n\n\n\nBy<\/p>\n\n\n\nM Moeini, R Ahmadian, M Ghatee<\/p>\n\n\n\nhas been accepted in \"2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)\"<\/p>\n\n\n\nAbstract:<\/p>\n\n\n\nWith the rapid advancement of artificial intelligence technologies in human life, particularly within the automotive industry, the popularity of smart vehicles has increased. Designing an intelligent car cabin capable of seamless interactions with both the driver and the vehicle emerges as a crucial solution to address human-vehicle interaction challenges. This project aims to implement a digital voice assistant that recognizes vehicle commands. It utilizes three main techniques: speech-to-text conversion, text classification, and calibrating the classifier in order to detect out-of-distribution (OOD) sentences. Using Vosk, an LLM model, voices in the vehicle environment are converted into text format. Then, after pre-processing the text, an SVM classifies them. Using Platt scaling the SVM classifier outputs become calibrated, which makes them probabilistic. The experimental result shows that the proposed model achieves command recognition with 96.43% accuracy, 96.83% precision, 96.43% recall, 96.39% F1-score, and 0.1437 cross-entropy loss. Furthermore, the optimal threshold for OOD sentences is 0.4.<\/p>\n\n\n\nRef: https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>\u00a0<\/p>\nRead research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2023<\/span>Journal article<\/small><\/div>Branch-and-Price Based Heuristic Algorithm for Fuzzy Multi-Depot Bus Scheduling Problem<\/h2>International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 31 (2023) 859-888<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>
2024<\/span>Journal article<\/small><\/div>Uncertainty quantification to enhance probabilistic fusion based user identification using smartphones<\/h2>IEEE Internet of Things Journal ( Volume: 11, Issue: 20, 15 October 2024), Page(s): 33450 - 33458<\/p>DOI<\/a>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10599325<\/a>Authors & full citation<\/summary>Authors: <\/strong>R Ahmadian, M Ghatee, J Wahlstr\u00f6m, H Zare<\/bdi><\/p>\nUncertainty quantification to enhance probabilistic fusion based user identification using smartphones<\/li>\n<\/ul>\nR Ahmadian, M Ghatee, J Wahlstr\u00f6m, H Zare<\/p>\nIEEE Internet of Things Journal ( Volume: 11, Issue: 20, 15 October 2024), Page(s): 33450 - 33458DOI: 10.1109\/JIOT.2024.3429011<\/p>Read research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Publication announcement; type not stated in Papers heading<\/small><\/div>Enhanced Multi-Modal Gas Leakage Detection with NSMOTE: A Novel Over-sampling Approach<\/h2>2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)<\/p>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570108<\/a>Authors & full citation<\/summary>Authors: <\/strong>Aref Azizian, Behnam Yousefimehr, Mehdi Ghatee<\/bdi><\/p>\nEnhanced Multi-Modal Gas Leakage Detection with NSMOTE: A Novel Over-sampling Approach<\/a><\/p>\n\n\n\nBy<\/p>\n\n\n\nAref Azizian, Behnam Yousefimehr, Mehdi Ghatee<\/p>\n\n\n\nhas been published in \"2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)\".<\/p>\n\n\n\nAbstract:<\/p>\n\n\n\nUrbanization and the emergence of smart cities have led to increased industrial activities, raising concerns about safety and environmental hazards. Detecting and monitoring gas leaks accurately is crucial due to the significant risks they pose to public health and the environment. In this study, we propose a novel approach that combines thermal imaging with sensor data to enhance gas detection accuracy in urban and industrial settings. By employing advanced algorithms and analyzing extensive datasets, our methodology achieves an impressive accuracy rate of 99.32%, setting a new standard in gas leak detection. Our innovation lies in the utilization of a unique oversampling technique called Normal Synthetic Minority Oversampling Technique (NSMOTE), coupled with the simultaneous integration of thermal imaging and sensor data within a multimodal framework. This breakthrough not only underscores the potential of integrating diverse data sources for environmental monitoring but also represents a significant stride in mitigating the risks associated with industrial gas emissions.<\/p>\n\n\n\nRef: https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570108<\/a><\/p>\nRead research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Publication announcement; type not stated in Papers heading<\/small><\/div>Calibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/h2>2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)<\/p>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>Authors & full citation<\/summary>Authors: <\/strong>M Moeini, R Ahmadian, M Ghatee<\/bdi><\/p>\nCalibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/a><\/p>\n\n\n\nBy<\/p>\n\n\n\nM Moeini, R Ahmadian, M Ghatee<\/p>\n\n\n\nhas been accepted in \"2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)\"<\/p>\n\n\n\nAbstract:<\/p>\n\n\n\nWith the rapid advancement of artificial intelligence technologies in human life, particularly within the automotive industry, the popularity of smart vehicles has increased. Designing an intelligent car cabin capable of seamless interactions with both the driver and the vehicle emerges as a crucial solution to address human-vehicle interaction challenges. This project aims to implement a digital voice assistant that recognizes vehicle commands. It utilizes three main techniques: speech-to-text conversion, text classification, and calibrating the classifier in order to detect out-of-distribution (OOD) sentences. Using Vosk, an LLM model, voices in the vehicle environment are converted into text format. Then, after pre-processing the text, an SVM classifies them. Using Platt scaling the SVM classifier outputs become calibrated, which makes them probabilistic. The experimental result shows that the proposed model achieves command recognition with 96.43% accuracy, 96.83% precision, 96.43% recall, 96.39% F1-score, and 0.1437 cross-entropy loss. Furthermore, the optimal threshold for OOD sentences is 0.4.<\/p>\n\n\n\nRef: https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>\u00a0<\/p>\nRead research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2023<\/span>Journal article<\/small><\/div>Branch-and-Price Based Heuristic Algorithm for Fuzzy Multi-Depot Bus Scheduling Problem<\/h2>International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 31 (2023) 859-888<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>
2024<\/span>Publication announcement; type not stated in Papers heading<\/small><\/div>Enhanced Multi-Modal Gas Leakage Detection with NSMOTE: A Novel Over-sampling Approach<\/h2>2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)<\/p>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570108<\/a>Authors & full citation<\/summary>Authors: <\/strong>Aref Azizian, Behnam Yousefimehr, Mehdi Ghatee<\/bdi><\/p>\nEnhanced Multi-Modal Gas Leakage Detection with NSMOTE: A Novel Over-sampling Approach<\/a><\/p>\n\n\n\nBy<\/p>\n\n\n\nAref Azizian, Behnam Yousefimehr, Mehdi Ghatee<\/p>\n\n\n\nhas been published in \"2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)\".<\/p>\n\n\n\nAbstract:<\/p>\n\n\n\nUrbanization and the emergence of smart cities have led to increased industrial activities, raising concerns about safety and environmental hazards. Detecting and monitoring gas leaks accurately is crucial due to the significant risks they pose to public health and the environment. In this study, we propose a novel approach that combines thermal imaging with sensor data to enhance gas detection accuracy in urban and industrial settings. By employing advanced algorithms and analyzing extensive datasets, our methodology achieves an impressive accuracy rate of 99.32%, setting a new standard in gas leak detection. Our innovation lies in the utilization of a unique oversampling technique called Normal Synthetic Minority Oversampling Technique (NSMOTE), coupled with the simultaneous integration of thermal imaging and sensor data within a multimodal framework. This breakthrough not only underscores the potential of integrating diverse data sources for environmental monitoring but also represents a significant stride in mitigating the risks associated with industrial gas emissions.<\/p>\n\n\n\nRef: https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570108<\/a><\/p>\nRead research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2024<\/span>Publication announcement; type not stated in Papers heading<\/small><\/div>Calibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/h2>2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)<\/p>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>Authors & full citation<\/summary>Authors: <\/strong>M Moeini, R Ahmadian, M Ghatee<\/bdi><\/p>\nCalibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/a><\/p>\n\n\n\nBy<\/p>\n\n\n\nM Moeini, R Ahmadian, M Ghatee<\/p>\n\n\n\nhas been accepted in \"2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)\"<\/p>\n\n\n\nAbstract:<\/p>\n\n\n\nWith the rapid advancement of artificial intelligence technologies in human life, particularly within the automotive industry, the popularity of smart vehicles has increased. Designing an intelligent car cabin capable of seamless interactions with both the driver and the vehicle emerges as a crucial solution to address human-vehicle interaction challenges. This project aims to implement a digital voice assistant that recognizes vehicle commands. It utilizes three main techniques: speech-to-text conversion, text classification, and calibrating the classifier in order to detect out-of-distribution (OOD) sentences. Using Vosk, an LLM model, voices in the vehicle environment are converted into text format. Then, after pre-processing the text, an SVM classifies them. Using Platt scaling the SVM classifier outputs become calibrated, which makes them probabilistic. The experimental result shows that the proposed model achieves command recognition with 96.43% accuracy, 96.83% precision, 96.43% recall, 96.39% F1-score, and 0.1437 cross-entropy loss. Furthermore, the optimal threshold for OOD sentences is 0.4.<\/p>\n\n\n\nRef: https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>\u00a0<\/p>\nRead research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2023<\/span>Journal article<\/small><\/div>Branch-and-Price Based Heuristic Algorithm for Fuzzy Multi-Depot Bus Scheduling Problem<\/h2>International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 31 (2023) 859-888<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>
2024<\/span>Publication announcement; type not stated in Papers heading<\/small><\/div>Calibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/h2>2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)<\/p>https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>Authors & full citation<\/summary>Authors: <\/strong>M Moeini, R Ahmadian, M Ghatee<\/bdi><\/p>\nCalibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation<\/a><\/p>\n\n\n\nBy<\/p>\n\n\n\nM Moeini, R Ahmadian, M Ghatee<\/p>\n\n\n\nhas been accepted in \"2024 8th International Conference on Smart Cities, Internet of Things and Applications (SCIoT)\"<\/p>\n\n\n\nAbstract:<\/p>\n\n\n\nWith the rapid advancement of artificial intelligence technologies in human life, particularly within the automotive industry, the popularity of smart vehicles has increased. Designing an intelligent car cabin capable of seamless interactions with both the driver and the vehicle emerges as a crucial solution to address human-vehicle interaction challenges. This project aims to implement a digital voice assistant that recognizes vehicle commands. It utilizes three main techniques: speech-to-text conversion, text classification, and calibrating the classifier in order to detect out-of-distribution (OOD) sentences. Using Vosk, an LLM model, voices in the vehicle environment are converted into text format. Then, after pre-processing the text, an SVM classifies them. Using Platt scaling the SVM classifier outputs become calibrated, which makes them probabilistic. The experimental result shows that the proposed model achieves command recognition with 96.43% accuracy, 96.83% precision, 96.43% recall, 96.39% F1-score, and 0.1437 cross-entropy loss. Furthermore, the optimal threshold for OOD sentences is 0.4.<\/p>\n\n\n\nRef: https:\/\/ieeexplore.ieee.org\/abstract\/document\/10570106<\/a>\u00a0<\/p>\nRead research update<\/a>Google Scholar<\/a><\/div><\/div><\/details><\/div><\/div><\/article>2023<\/span>Journal article<\/small><\/div>Branch-and-Price Based Heuristic Algorithm for Fuzzy Multi-Depot Bus Scheduling Problem<\/h2>International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 31 (2023) 859-888<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>
2023<\/span>Journal article<\/small><\/div>Branch-and-Price Based Heuristic Algorithm for Fuzzy Multi-Depot Bus Scheduling Problem<\/h2>International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 31 (2023) 859-888<\/p>DOI<\/a>Authors & full citation<\/summary>Authors: <\/strong>