A5031691031- Neural Networks and Applications
- Domain Adaptation and Few-Shot Learning
- Machine Learning and ELM
- Fuzzy Logic and Control Systems
- Machine Learning and Data Classification
- Face and Expression Recognition
- Metaheuristic Optimization Algorithms Research
- Evolutionary Algorithms and Applications
- Context-Aware Activity Recognition Systems
- Advanced Statistical Process Monitoring
- Generative Adversarial Networks and Image Synthesis
- Anomaly Detection Techniques and Applications
- Scientific Measurement and Uncertainty Evaluation
- AI in cancer detection
- IoT and Edge/Fog Computing
- Image Retrieval and Classification Techniques
- Reinforcement Learning in Robotics
- Imbalanced Data Classification Techniques
- Fault Detection and Control Systems
- Multimodal Machine Learning Applications
- Orthopedic Infections and Treatments
- Adversarial Robustness in Machine Learning
- Video Analysis and Summarization
- Advanced Multi-Objective Optimization Algorithms
- Brain Tumor Detection and Classification
Queen's University
2023-2025
University of Windsor
2021-2024
Shenzhen University
2019-2022
Southern University of Science and Technology
2018
Universiti Sains Malaysia
2015-2016
Fuzzy twin support vector machine (FTSVM) is an effective learning technique that able to overcome the negative impact of noise and outliers in tackling data classification problems. In FTSVM, degree membership function sample space describes between input class center, while ignoring position feature simply miscalculated ledge vectors as noises. This paper presents intuitionistic FTSVM (IFTSVM) combines idea fuzzy number with (TSVM). An adequate employed reduce created by pollutant inputs....
In this paper, a quadcopter unmanned aerial vehicle (UAV) system based on neural-network enhanced dynamic inversion control is proposed for multiple real-world application scenarios. A sigma-pi neural network (SPNN) used as the compensator to reduce model error and improve performance in presence of uncertainties UAV dynamics, payload, environment. Besides, we present technical framework fast robust implementation multipurpose systems develop testbed evaluation by using high-precision...
Abstract In profile monitoring, it is usually assumed that the observations between or within each are independent of other. However, this assumption often violated in manufacturing practice, and utmost importance to carefully consider autocorrelation effects underlying models for monitoring. For reason, various statistical control charts have been proposed monitor profiles when between- within-data correlated Phase II, which main aim develop with quicker detection ability. As a novel...
An early detection of fault components is crucial for unmanned aerial vehicles (UAVs), The goal this paper to develop a monitoring system detect possible faults UAV motors and propellers. Motor current signature analysis (MCSA) approach used analyze the stator signals under different conditions. Then, fuzzy adaptive resonance (Fuzzy ART) neural network (NN), which an unsupervised learning scheme, employed judge whether are operating in normal or faulty condition. In addition, vibration (VSA)...
Breast cancer is the most commonly diagnosed worldwide, and early detection essential for reducing mortality rates. Digital mammography currently best standard detection, as it can assist physicians in treating disease. However, inaccurate diagnoses from are common lead to patients undergoing unnecessary tests treatments. To address this challenge, deep-learning techniques have shown promising results improving accuracy reliability of breast detection. existing methods face two primary...
We address the problem of federated domain generalization in an unsupervised setting for first time. theoretically establish a connection between shift and alignment gradients learning show that aligning at both client server levels can facilitate model to new (target) domains. Building on this insight, we propose novel method named FedGaLA, which performs gradient level encourage clients learn domain-invariant features, as well global obtain more generalized aggregated model. To empirically...