Abdelhak is Associate Professor of computer science and permanent researcher at L'IMIARF Laboratory at Mohammed V University (Rabat, Morocco). His main research involves ML/DL in computer vision and natural language processing applied to healthcare. In 2021, Abdelhak co-founded Deepecho, a healthtech startup building AI product for antenatal diagnosis. In 2014, he joined, as a postdoc ML researcher, the Partnerships for Enhanced Engagement in Research (PEER) project administered by the U.S. National Academy of Sciences (NAS). In 2010, he worked as a machine learning research engineer at CNRS (Marseille, France) under the Neuromed project in the 7th European Framework.

Courses

Research

Deep Learning for Computer Vision

Mask-RCNN for Automating Aircraft Maintenance Inspection

CNN-Based Approach for Cervical Cancer Classification in Whole-Slide Histopathology Images

Deep Learning for Language

Towards A Sign Language Gloss Representation Of Modern Standard Arabic

Exploring BERT for Name Entity Recognition task

Deep Learning for Time Series

Fully Convolutional Networks for Earthquake Detection

Exploring CTC and Transformers in Speech Recognition

Deep Learning for Internet of Things

Indoor Localization with Bluetooth Low Energy: A semi-supervised Deep Reinforcement Learning Approach

Indoor Localization with Bluetooth Low Energy: A semi-supervised Deep Reinforcement Learning Approach

Publications

• Youness Choubik, Abdelhak Mahmoudi, Mohammed Majid Himmi and Lahcen El Moudnib. STA/LTA trigger algorithm implementation on a seismological dataset using Hadoop MapReduce.IAES International Journal of Artificial Intelligence, 2020, 9(2), pp. 269-275. (link)

• Hanane Arahmane, Abdelhak Mahmoudi, El Mehdi Hamzaoui, Yann Ben Maissa, and Rajaa Cherkaoui El Moursli. Neutron-gamma discrimination based on support vector machine combined to nonnegative matrix factorization and continuous wavelet transform. Measurement, 149 :106958, 2020. (link)

• Abdelhak Mahmoudi, Fakhita Regragui. Synthetic minority oversampling and linear crossvalidated support vector machine-based recursive feature elimination to classify weld flaws in radiographic images. Materials Evaluation. 2015;73 (2) :186-197. (link)

• Abdelhak Mahmoudi, Sylvain Takerkart, Fakhita Regragui, Driss Boussaoud, Andrea Brovelli. Multivoxel Pattern Analysis for fMRI Data: A Review. Computational and Mathematical Methods in Medicine. 2012;2012 :1–14. (link)

• Fatima Eddaoudi, Fakhita Regragui, Abdelhak Mahmoudi, Najib Lamouri. Masses detection using SVM classifier based on textures analysis. Applied Mathematical Sciences. 2011;5 (5-8) :367-379. (link)

• Ferdaous Idlahcen, Abdelhak Mahmoudi and Mohammed Majid Himmi. Cnn-Based Approach for Cervical Cancer Classification in Whole-Slide Histopathology Images. To Appear in ICLR 2020 AI4CC workshop.

• Salma El Anigri, Abdelhak Mahmoudi and Mohammed Majid Himmi. Towards A Sign Language Gloss Representation Of Modern Standard Arabic. To Appear in ICLR 2020 AfricaNLP workshop.

• Hajar Ait Addi, Redouan Ezzahir and A. Mahmoudi. Three-level binary tree structure for sentiment classification in Arabic text. ACM International Conference Proceeding Series, 2020. (link)

• Mohamed El-Kaddoury, Abdelhak Mahmoudi, and Mohammed Majid Himmi. Deep generative models for image generation: A practical comparison between variational autoencoders and generative adversarial networks. In Mobile, Secure, and Programmable Networking - 5th International Conference, MSPN 2019, Mohammedia, Morocco, April 23-24, 2019, Revised Selected Papers, pages 1–8, 2019. (link)

• Arahmane Hanane, El Mehdi Hamzaoui, Abdelhak Mahmoudi and Rajaa Cherkaoui Elmoursli. Time-Scale Characterization of Neutron and Gamma Signals Using Continuous Wavelet Transform. ISIVC, 2018. (link)

• Marouane Benmoussa and Abdelhak Mahmoudi. Machine Learning for Hand Gesture Recognition Using Bag-of-words, to be published in Proceedings of the IEEE ISCV’2018 Conference April 2-4, 2018. (link)

• Marouane Hamda and Abdelhak Mahmoudi. Hand Gesture Recognition Using Kinect's Geometric and HOG Features, in Proceedings of the 2Nd International Conference on Big Data, Cloud and Applications. New York, NY, USA: ACM ; 2017 :48:1–48:5. (link)

• Youness Choubik and Abdelhak Mahmoudi. Machine Learning for Real Time Poses Classification Using Kinect Skeleton Data. Proceedings - Computer Graphics, Imaging and Visualization: New Techniques and Trends, CGiV 2016. 2016 :307-311. (link)

• Salma Tayeb, Abdelhak Mahmoudi, Fakhita Regragui and Mohammed Majid Himmi. Efficient detection of P300 using Kernel PCA and support vector machine. 2014 2nd World Conference on Complex Systems, WCCS 2014. 2015 :17-22. (link)

• Abdelhak Mahmoudi, Fakhita Regragui. A fast segmentation method for defects detection in radiographic images of welds. 2009 IEEE/ACS International Conference on Computer Systems and Applications, AICCSA 2009. 2009 :857-860. (link)

• Abdelhak Mahmoudi, Fakhita Regragui. Welding defect detection by segmentation of radiographic images. 2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009. 2009;7 :111-115. (link)

• Abdelhak Mahmoudi, Fakhita Regragui, Fatima Eddaoudi, El Houssine Bouyakhf. and Himmi M.M. A Novel Method for Welding Defects Detection in Radiographic Images, 4th International Symposium on Image/Video Communications over fixed and mobile networks (ISIVC’2008), Spain. (link

• Abdelhak Mahmoudi and Fakhita Regragui. Local Thresholding Towards Defect Detection in Radiographic Images of Welds, 2ème Journées Scientifiques en Technologie de l'Information et de la Communication (JOSTIC’2008), Morocco. (link)

Awards

• 2019 Africa Innovation Award of Artificial intelligence for Development (AI4D) in Africa.
• 1^st Place - 2018 Moroccan Award of Research and Innovation in Disabilities.