A hybrid of neuro-fuzzy inference system and hidden Markov Model for activity-based mobility modeling of cellphone users

“A hybrid of neuro-fuzzy inference system and hidden Markov Model for activity-based mobility modeling of cellphone users” has been published By: Shiva Rahimipour, Mehdi Ghatee, S.M. Hashemi, Ahmad Nickabadi, in Computer Communications Volume 173, 1 May 2021, Pages 79-94. Abstract: The aim of this paper is to develop an activity-based travel demand model by receiving… Continue reading A hybrid of neuro-fuzzy inference system and hidden Markov Model for activity-based mobility modeling of cellphone users

A Systematic Review on Overfitting Control in Shallow and Deep Neural Networks

“A Systematic Review on Overfitting Control in Shallow and Deep Neural Networks” By: Mohammad Mahdi Bejani, & Mehdi Ghatee has been published in “Artificial Intelligence Review” Abstract: Shallow neural networks process the features directly, while deep networks extract features automatically along with the training. Both models suffer from overfitting or poor generalization in many cases.… Continue reading A Systematic Review on Overfitting Control in Shallow and Deep Neural Networks

Least auxiliary loss-functions with impact growth adaptation (Laliga) for convolutional neural networks

By Mohammad Mahdi Bejani & Mehdi Ghatee Published: Neurocomputing, 2021. Abstract: Model selection is a challenge, and a popular Convolutional Neural Networks (CNN) usually takes extra-need parameters. It causes overfitting in real applications. Besides, the extracted hidden features would be lost when the number of convolution layers increases. We use the least auxiliary loss-functions to… Continue reading Least auxiliary loss-functions with impact growth adaptation (Laliga) for convolutional neural networks

Theory of adaptive SVD regularization for deep neural networks

By: Mohammad Mahdi Bejani & Mehdi Ghatee Published: Neural Networks, Volume 128, August 2020, Pages 33-46. Abstract: Deep networks can learn complex problems, however, they suffer from overfitting. To solve this problem, regularization methods have been proposed that are not adaptable to the dynamic changes in the training process. With a different approach, this paper… Continue reading Theory of adaptive SVD regularization for deep neural networks

Adaptive neural tree exploiting expert nodes to classify high-dimensional data

By: Shadi Abpeikar, Mehdi Ghatee, Gian Luca Foresti & Christian Micheloni Published: Neural Networks, Volume 124, April 2020, Pages 20-38. Abstract: Classification of high dimensional data suffers from curse of dimensionality and over-fitting. Neural tree is a powerful method which combines a local feature selection and recursive partitioning to solve these problems, but it leads… Continue reading Adaptive neural tree exploiting expert nodes to classify high-dimensional data

Convolutional Neural Network With Adaptive Regularization to Classify Driving Styles on Smartphones

By: Mohammad Mahdi Bejani, Mehdi Ghatee Published: IEEE Transactions on Intelligent Transportation Systems, Volume: 21, Issue: 2, Feb. 2020. Abstract: Driving style evaluation by smartphones depends on the quality of the features extracted from sensors data. Typically, these features are extracted based on experiments, expertness, or heuristics. In more modern approaches, some automatic methods such as… Continue reading Convolutional Neural Network With Adaptive Regularization to Classify Driving Styles on Smartphones

Neural trees with peer-to-peer and server-to-client knowledge transferring models for high-dimensional data classification

By: Shadi Abpeykar, & Mehdi Ghatee Published: Expert Systems with Applications, Volume 137, 15 December 2019, Pages 281-291 Abstract: Classification of the high-dimensional data by a new expert system is followed in the current paper. The proposed system defines some non-disjoint clusters of highly relevant features with the least inner-redundancy. For each cluster, a neural… Continue reading Neural trees with peer-to-peer and server-to-client knowledge transferring models for high-dimensional data classification

Ensemble decision forest of RBF networks via hybrid feature clustering approach for high-dimensional data classification

By: Shadi Abpeykar, Mehdi Ghatee, & Hadi Zare Published: Computational Statistics & Data Analysis Volume 131, March 2019, Pages 12-36. Abstract: Classification of the high-dimensional data is challenging due to the curse of dimensionality, heavy computational burden and decreasing precision of algorithms. In order to mitigate these effects, feature selection approaches that can determine an… Continue reading Ensemble decision forest of RBF networks via hybrid feature clustering approach for high-dimensional data classification

Convolution neural network joint with mixture of extreme learning machines for feature extraction and classification of accident images

By: Ali Pashaei, Mehdi Ghatee & Hedieh Sajedi Published: Journal of Real-Time Image Processing, 17(4), 1051-1066 – February 2019 https://doi.org/10.1007/s11554-019-00852-3 Abstract: This paper considers the accident images and develops a deep learning method for feature extraction together with a mixture of experts for classification. For the first task, the outputs of the last max-pooling layer… Continue reading Convolution neural network joint with mixture of extreme learning machines for feature extraction and classification of accident images

A similarity-based neuro-fuzzy modeling for driving behavior recognition applying fusion of smartphone sensors

By: Hamid Reza Eftekhari, & Mehdi Ghatee Published: Journal of Intelligent Transportation Systems Technology, Planning, and Operations Volume 23, 2019 – Issue 1 Abstract: Drivers’ behavior evaluation is one of the most important problems in intelligent transportation systems and driver assistant systems. It has a great influence on driving safety and fuel consumption. One of… Continue reading A similarity-based neuro-fuzzy modeling for driving behavior recognition applying fusion of smartphone sensors