Results 241 to 250 of about 61,624 (324)

FastKAN-DDD: A novel fast Kolmogorov-Arnold network-based approach for driver drowsiness detection optimized for TinyML deployment. [PDF]

PLoS One
Essahraui S, Lamaakal I, Maleh Y, El Makkaoui K, Bouami MF, Ouahbi I, Elmannai H, Abd El-Latif AA.   +7 more
europepmc   +1 more source

Robust Facial Recognition Using Unified Optimised Feature Fusion and Selection of Handcrafted and Deep Learning Features

IET Image Processing, Volume 20, Issue 1, January/December 2026.
This study presents a robust facial recognition framework based on a unified optimised feature vector that fuses handcrafted descriptors and deep learning embeddings. Using binary grey wolf optimisation for feature selection, the approach reduces redundancy while preserving discriminative power.
Farid Ayeche, Adel Alti
wiley   +1 more source

A Multi-Step Grasping Framework for Zero-Shot Object Detection in Everyday Environments Based on Lightweight Foundational General Models. [PDF]

Sensors (Basel)
Li R, Zhang T, Zou Y.
europepmc   +1 more source

Optimization of Diabetes Disease Classification Using Learning Vector Quantization Algorithm(LVQ)

Eska Avelina Sianipar, M. S.
openalex   +2 more sources

PC‐LLMRec: Large Language Model for Personalized Interaction Recommendations in Intelligent Cockpit

IET Intelligent Transport Systems, Volume 20, Issue 1, January/December 2026.
This paper proposes an innovative two‐stage recommendation framework, PC‐LLMRec, specifically designed for customized recommendations in intelligent cockpits. This framework effectively balances the complexity of the cockpit system under the conditions of multi‐task collaboration and highly diversified personalized needs.
Haomin Dong, Wenbin Wang, Dali Jiang, Yunting He, Xiaojun Ge, Chengzhe Li, Yi Chen, Xiaohan Li, Fei Gao, Jixin Wang   +9 more
wiley   +1 more source

A Performance Study of Deep Neural Network Representations of Interpretable ML on Edge Devices with AI Accelerators. [PDF]

Sensors (Basel)
Schauer J, Goodarzi P, Morsch J, Schütze A.   +3 more
europepmc   +1 more source

Deep Reinforcement Learning Reconfigurable Smart Surface Sensing MAC Protocol for Terahertz Mesh Networks

IET Networks, Volume 15, Issue 1, January/December 2026.
This paper proposes a reconfigurable intelligent surface‐based deep reinforcement learning MAC (RIS‐DRL‐MAC) protocol for terahertz mesh networks. By embedding RIS perception into the MAC decision loop and using a distributed TD3 algorithm, the proposed scheme achieves a cross‐layer optimisation of beam direction, access timing and RIS phase control ...
Wenjian Zhang, Ping Li
wiley   +1 more source

NeuroDetect: Deep Learning-Based Signal Detection in Phase-Modulated Systems with Low-Resolution Quantization. [PDF]

Sensors (Basel)
Luckshan C, Gayan S, Inaltekin H, Zhang R, Akman D.   +4 more
europepmc   +1 more source

A Private Blockchain and IPFS‐Based Secure and Decentralized Framework for People Surveillance via Deep Learning Techniques

IET Software, Volume 2026, Issue 1, 2026.
The modern metropolis essentially demands the use of state‐of‐the‐art, real‐time surveillance systems, which should be reliable, scalable, and respectful of privacy at the same time. Critical shortcomings in traditional architectures are single points of failure, poor scalability, frequent data breaches, and inadequately managed privacy.
Shihab Sarar, Ali Imran Mehedi, Fabbiha Tahsin Prova, Saha Reno, Vimal Dwivedi   +4 more
wiley   +1 more source

Affine‐Image‐Driven and Finite‐Time Stable Formation Control for Multi‐AUV Systems With Unknown Complex Disturbances: A Geometric Perspective

IET Signal Processing, Volume 2026, Issue 1, 2026.
Formation control of multi‐autonomous underwater vehicle (AUV) systems is essential for collaborative ocean tasks such as environmental monitoring and resource exploration, but it is hindered by challenges like limited flexibility in formation transformation, model uncertainties, and unknown ocean current disturbances.
Fan Luan, Ping Zhang, Xiasheng Shi, Li Chai   +3 more
wiley   +1 more source