Publications

Mathematics

Genghis Khan Shark Optimizer for multi-objective mechanical truss design

Mechanical structures in engineering are increasingly designed under stringent requirements for low-weight, high-stiffness, and safety, making multi-objective structural optimization central to innovative, cost-effective-products. This work…

Fatima Daqaq, Siham Ouhimmou, David Bassir, Ghanshyam G Tejani

Results in Control and Optimization - 2026

Image Processing

Multi-Modal Self-Supervised Learning for Aligned Satellite Image Time Series Encoder

Foundation models based on self-supervised learning (SSL) have attracted a great deal of interest in land monitoring. While early approaches relied primarily on masked autoencoder (MAE) strategies, attention is now turning to discriminative SSL…

Iris Dumeur, Ekaterina Kalinicheva, Silvia Valero, Jordi Inglada

Engineering Sciences

MQAD-net: multi-modal quantum-attentive deep learning framework for early mental health detection and personalized therapy recommendation

This research delves into the impact of varying printing angles in the range (0°, 15°, 30°, 45°) on the thermal and mechanical characteristics of carbon fibre–PLA/PHA composites fabricated via fused filament fabrication (FFF). The microstructural…

Khalil Hamdi Ateyeh Al-Shqeerat, Ahmad Hamed Al Abadleh, Sunil Kumar Sharma, Pankaj Kumar, Ghanshyam Tejani, David Bassir

Egyptian Informatics Journal - 2026

Engineering Sciences

SaurKshetra: A curated dataset and ML-based classification for solar energy site selection

Yash Shivgan, Chandan Bhirud, Anshul Jamgade, Atharva Kulkarni, Rutuja Patil, Gagandeep Kaur, David Bassir, Ghanshyam Tejani

Data in Brief - 2026

Engineering Sciences

DSE-YOLO11: Dynamic feature adaptation for key traffic element detection in complex road scenes

Accurate detection of key traffic elements in complex road scenes is critical for autonomous driving and intelligent transportation systems. However, existing lightweight detectors often suffer from missed detections under small targets, large-scale…

Yange Chen, Baohua Guo, David Bassir, Anthony Sigama, Yuandi Zhang

PLoS ONE - 2026

Engineering Sciences

DOA-RL: Reinforcement learning enhanced dream optimization algorithm with adaptive operator selection for continuous optimization

Ibrahim I.M. Manhrawy, Ahmed Elashry, Abrar Yaqoob, Amro Soliman, Ghanshyam Tejani, David Bassir, Arar Al Tawil

Results in Control and Optimization - 2026

Engineering Sciences

Machine learning-enhanced multi-sensor e-nose to quantify and classify low-level ammonia under dynamic environmental condition

Electronic nose (enose) Metal oxide (MOX) gas sensors Ammonia detection Environmental compensation Machine learning Support vector machine (SVM) XGBoost LightGBM Gas classification Real-time monitoring Sensor performance evaluation Temperature and…

Ata Jahangir Moshayedi, Meixia Wang, Jiandong Hu, Gang Kuan, David Bassir

Sensors and Actuators Reports - 2026

Artificial Intelligence

Beyond ReLU: Bifurcation, Oversmoothing, and Topological Priors

Graph Neural Networks (GNNs) learn node representations through iterative network-based message-passing. While powerful, deep GNNs suffer from oversmoothing, where node features converge to a homogeneous, non-informative state. We re-frame this…

Erkan Turan, Gaspard Abel, Maysam Behmanesh, Emery Pierson, Maks Ovsjanikov

ICML 2026 - International Conference on Machine Learning - 2026

Computer Vision and Pattern Recognition

Generalization Limits in Vehicle Re-Identification

Vehicle re-identification focuses on retrieving images of the same vehicle from a gallery given a query image. Upon closer inspection of commonly used datasets, we observe that vehicles with few visual differences-e.g., the same make, model, and…

Anis Yassine Ben Mabrouk, Antoine Tadros, Rafael Grompone von Gioi, Gabriele Facciolo, Axel Davy, Rodrigo Verschae

Machine Learning

SPHERE-JEPA: Spherical Prediction with Homogeneous Embeddings

A fundamental open question in self-supervised learning (SSL) is the explicit characterization of the optimal geometry of the learned representations. Recently, LeJEPA identified isotropic Gaussian embeddings as optimal for minimizing downstream…

Léo Nicollier, Max Dunitz, Marc Pic, Pablo Musé, Enric Meinhardt-Llopis, Gabriele Facciolo