¾Ã¾Ã¾«Æ·

Dr Aboozar Taherkhani, received the PhD degree from Ulster University, Londonderry, U.K, in 2017. Aboozar currently works at the Faculty of Computing, Engineering, and Media, ¾Ã¾Ã¾«Æ·, UK as a senior lecturer. Previously he was a full-time research fellow at the Computational Neuroscience and Cognitive Robotics Laboratory, at Nottingham Trent University, Nottingham, UK. He worked as a research fellow on the Leverhulme Trust Research Project entitled “Novel Approaches for Constructing Optimised Multimodal Data Spaces”.

Aboozar does research in Computer Science and Neuroscience. His current research interests include artificial intelligence, data science, big data, deep neural network, image and nonlinear signal processing, multimodal data analysis, and spiking neural network. He is also interested in using machine learning methods for robotics, internet of things (IOT), activity recognition, and Natural Language Processing.

Institute of Artificial Intelligence (IAI)

• A. Taherkhani, G. Cosma, and T.M. Mcginnity, AdaBoost-CNN: An Adaptive Boosting algorithm for Convolutional Neural Networks to classify Multi-Class Imbalanced datasets using Transfer Learning, 404, 351-366, Neurocomputing, 2020. 
• A. Taherkhani, Ammar Belatreche, Yuhua Li, Georgina Cosma, Liam P. Maguire, and T. M McGinnity, A review of learning in biologically plausible spiking neural networks, Neural Network, 122, 253-272, 2020.
• A. Alani, G. Cosma and A. Taherkhani, "Classifying Imbalanced Multi-modal Sensor Data for Human Activity Recognition in a Smart Home using Deep Learning," 2020 International Joint Conference on Neural Networks (IJCNN), 2020, pp. 1-8, doi: 10.1109/IJCNN48605.2020.9207697
• A. Taherkhani, G. Cosma, and T.M. Mcginnity, Optimization of output spike train encoding for a spiking neuron based on its spatiotemporal input pattern, IEEE Transactions on Cognitive and Developmental Systems, 2019. 
• A. Taherkhani, G. Cosma, and T.M. Mcginnity, Deep-FS: a feature selection algorithm for deep Boltzmann machines. Neurocomputing, vol. 322, 2018. 
• B. Pandya, G. Cosma, AA. Alani, A. Taherkhani, V Bharadi, TM McGinnity, Fingerprint classification using a deep convolutional neural network, 2018 4th International Conference on Information Management (ICIM), 86-91
• AA. Alani, G. Cosma, A. Taherkhani, TM. McGinnity, Hand gesture recognition using an adapted convolutional neural network with data augmentation, 2018 4th International Conference on Information Management (ICIM), 5-12
• A. Taherkhani, A. Belatreche, Y. Li and L. P. Maguire, "A Supervised Learning Algorithm for Learning Precise Timing of Multiple Spikes in Multilayer Spiking Neural Networks." IEEE Transactions on Neural Networks and Learning Systems (2018).
• A. Taherkhani, A. Belatreche, Y. Li and L. P. Maguire, "DL-ReSuMe: A Delay Learning based Remote Supervised Method for Spiking Neurons," IEEE Transactions On Neural Networks and Learning Systems, vol. 26, pp. 3137-3149, 2015. 

Please see: , for a full list of publications

• Artificial intelligence 
• Data science and big data 
• Deep neural networks
• Image processing
• Multimodal data analysis 
• Spiking neural network
• Robotics 
• Internet of things (IOT)
• Natural Language processing
• Activity recognition

For more information please see:

• Intelligent Mobile Robots
• Natural Language Processing
• Deep Neural network
• Object Oriented Programming in C++
• Introduction to C++
• Algorithms and Data Structures
• Basic and advanced C# programming concepts 
• Basic and advanced python programming concepts
• Embedded Systems and Information Systems Development
• Programmable logic controllers (PLC), industrial instrumentation and control, AVR microcontrollers, and electrical circuit analysis

• PhD - Computer Science and Intelligent Systems
• MSc - Biomedical Engineering (Bioelectronics)
• BSc - Electronic Engineering

IMAT5233_ Intelligent Mobile Robots, IMAT5118_2021_520 Natural Language Processing based Deep Learning

The Leverhulme Trust Research Project Grant RPG-2016-252 entitled “Novel Approaches for Constructing Optimised Multimodal Data Spaces”.

0000-0002-3627-6362