Jahid Shahidul Islam
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jahid Shahidul Islam has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Asif Ali Laghari
Department of Computer Science, Sindh Madressatul Islam University, Karachi, Pakistan
1 shared publication Fengli Zhang
School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China
1 shared publication- Jiahao Wang
School of Software Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu 611731, China, China
1 shared publication - Jiaxuan Wei
School of Software Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, P.R.China
1 shared publication - John Idriss Lahai
University of New England
1 shared publication - Muhammad Waqas
School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China
1 shared publication
Latest Publications
- 24 September 2026
- Published by SAGE Publications in Intelligent Data Analysis: An International Journal
Deep-MultiAPP: First-impression based apparent personality trait prediction from short videos with multimodal deep learning
Automated Apparent Personality Prediction (APP) from multimodal data holds significant promise for enhancing Human-Computer Interactions (HCIs), yet existing models often fall short in effectively fusing diverse cues like visual expressions, audio prosody, and textual semantics, leading to suboptimal accuracy and interpretability in real-world applications. This study introduces Deep-MultiAPP, a novel multimodal deep learning architecture designed to address these limitations by integrating Residual Network (ResNet-50) and Vision Transformer (ViT-B/16) for hybrid visual feature extraction, Gated Recurrent Unit (GRU) for temporal modeling, enhanced audio Multilayer Perceptrons (MLPs) for incorporating mean-pooled log-Mel spectrograms, and Bidirectional Encoder Representations from Transformers (BERT) for text embeddings with late decision-level fusion combines modality-specific regressors (weights: vision 0.6, audio 0.3, text 0.1). On the ChaLearn First Impressions V2 dataset, Deep-MultiAPP achieved a state-of-the-art mean regression accuracy of 91.77% across the Big-Five traits, outperforming prior baselines by ∼0.25–0.47%. Binarized classification at a 0.5 threshold yielded a macro-averaged precision of 79.54%, recall of 80.13%, and F1-score of 79.83%, as validated by confusion matrices showing balanced error distributions despite class imbalances. These results demonstrate Deep-MultiAPP's superior capability in capturing nuanced personality cues, paving the way for more reliable artificial intelligence (AI) systems in fields like recruitment, mental health screening, and social robotics, while highlighting the need for bias audits and cross-cultural validations to ensure equitable deployment for responsible real-world use.
- 24 September 2026
- Published by SAGE Publications in Intelligent Data Analysis: An International Journal
Deep-MultiAPP: First-impression based apparent personality trait prediction from short videos with multimodal deep learning
Automated Apparent Personality Prediction (APP) from multimodal data holds significant promise for enhancing Human-Computer Interactions (HCIs), yet existing models often fall short in effectively fusing diverse cues like visual expressions, audio prosody, and textual semantics, leading to suboptimal accuracy and interpretability in real-world applications. This study introduces Deep-MultiAPP, a novel multimodal deep learning architecture designed to address these limitations by integrating Residual Network (ResNet-50) and Vision Transformer (ViT-B/16) for hybrid visual feature extraction, Gated Recurrent Unit (GRU) for temporal modeling, enhanced audio Multilayer Perceptrons (MLPs) for incorporating mean-pooled log-Mel spectrograms, and Bidirectional Encoder Representations from Transformers (BERT) for text embeddings with late decision-level fusion combines modality-specific regressors (weights: vision 0.6, audio 0.3, text 0.1). On the ChaLearn First Impressions V2 dataset, Deep-MultiAPP achieved a state-of-the-art mean regression accuracy of 91.77% across the Big-Five traits, outperforming prior baselines by ∼0.25–0.47%. Binarized classification at a 0.5 threshold yielded a macro-averaged precision of 79.54%, recall of 80.13%, and F1-score of 79.83%, as validated by confusion matrices showing balanced error distributions despite class imbalances. These results demonstrate Deep-MultiAPP's superior capability in capturing nuanced personality cues, paving the way for more reliable artificial intelligence (AI) systems in fields like recruitment, mental health screening, and social robotics, while highlighting the need for bias audits and cross-cultural validations to ensure equitable deployment for responsible real-world use.
- Open Access
- 8 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. PP, 1
Adaptive Sensor Fusion-Enhanced Deep Reinforcement Learning for Fault-Tolerant Autonomous Control
This study presents a deep reinforcement learning–based control architecture with an adaptive sensor fusion module for complex, sensor-driven autonomous systems. The agent, trained in simulation using PPO with domain randomization, learns robust policies from multi-modal inputs (LiDAR, IMU, camera). Rigorous evaluation (10 random seeds) against PID and MPC baselines under nominal and fault-injection scenarios demonstrates statistically significant improvements in tracking accuracy, rise time, and fault recovery. The adaptive fusion mechanism, formally defined using residual-based attention, reduces RMSE by 56% and enables recovery from sensor faults in 0.9s. Results validate the feasibility of DRL in safety-critical, real-time embedded environments.
- 8 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. PP, 1
Open AccessAdaptive Sensor Fusion-Enhanced Deep Reinforcement Learning for Fault-Tolerant Autonomous Control
This study presents a deep reinforcement learning–based control architecture with an adaptive sensor fusion module for complex, sensor-driven autonomous systems. The agent, trained in simulation using PPO with domain randomization, learns robust policies from multi-modal inputs (LiDAR, IMU, camera). Rigorous evaluation (10 random seeds) against PID and MPC baselines under nominal and fault-injection scenarios demonstrates statistically significant improvements in tracking accuracy, rise time, and fault recovery. The adaptive fusion mechanism, formally defined using residual-based attention, reduces RMSE by 56% and enables recovery from sensor faults in 0.9s. Results validate the feasibility of DRL in safety-critical, real-time embedded environments.