A5091531578- Fuzzy Logic and Control Systems
- Adaptive Control of Nonlinear Systems
- Neural Networks and Applications
- Vibration Control and Rheological Fluids
- Adaptive Dynamic Programming Control
- Data Stream Mining Techniques
- Biomimetic flight and propulsion mechanisms
- Seismic Performance and Analysis
- Domain Adaptation and Few-Shot Learning
- Anomaly Detection Techniques and Applications
- Advanced Neural Network Applications
- Imbalanced Data Classification Techniques
- Machine Learning and Data Classification
- Fault Detection and Control Systems
- Distributed Control Multi-Agent Systems
- Structural Engineering and Vibration Analysis
- Advanced Control Systems Optimization
- Hydraulic and Pneumatic Systems
- Underwater Vehicles and Communication Systems
- Image Enhancement Techniques
- Robotic Path Planning Algorithms
- Control Systems and Identification
- Metaheuristic Optimization Algorithms Research
- Water Quality Monitoring Technologies
- Electricity Theft Detection Techniques
Gulf University
2024-2025
Nanyang Technological University
2018-2024
Institute for Infocomm Research
2021-2024
Agency for Science, Technology and Research
2021-2024
University of New Orleans
2023-2024
UNSW Sydney
2016-2021
Australian Defence Force Academy
2017-2021
University of Canberra
2017-2019
UNSW Canberra
2017-2019
National University of Singapore
2018
Smart materials are kinds of designed whose properties controllable with the application external stimuli such as magnetic field, electric stress, and heat. rheological controlled by externally applied field known magneto-rheological materials. Magneto-rheological actively used for engineering applications include fluids, foams, grease, elastomers, plastomers. In last two decades, have gained great attention researchers significantly because their salient potential to various fields...
Data stream has been the underlying challenge in age of big data because it calls for real-time processing with absence a retraining process and/or an iterative learning approach. In realm fuzzy system community, is handled by algorithmic development self-adaptive neuro-fuzzy systems (SANFS) characterized single-pass mode and open structure property that enables effective handling fast rapidly changing natures streams. The bottleneck SANFSs lies its design principle, which involves high...
In recent times, with the incremental demand for fully autonomous systems, research interests are observed in learning machine-based intelligent, self-organizing, and evolving controllers. this paper, a new self-organizing controller, namely generic-controller (G-controller), is proposed. The G-controller works online mode minor expert domain knowledge. It developed by incorporating sliding control (SMC) theory an advanced machine, generic neuro-fuzzy inference system. controller starts...
Integral to the success of semiconductor industry in keeping up with Moore's law is importance failure analysis (FA). Accurate and fast FA vital ensuring yield, reliability, rapid production industry. However, locating defects among tens billions transistors packed tiny modern microchip not a trivial task. Not only process technology has achieve such high integration devices evolved become astoundingly sophisticated but also debugging for these chips remarkably complex. With electrical...
Enabling effective learning using only a few presented examples is crucial but difficult computer vision objective. Few-shot have been proposed to address the challenges, and more recently variational inference-based approaches are incorporated enhance few-shot classification performances. However, current dominant strategy utilized Kullback-Leibler (KL) divergences find log marginal likelihood of target class distribution, while neglecting possibility other probabilistic comparative...
Recently, the quadcopter configuration is becoming prevalent for both civilian and military applications, research continuing to improve its controllability. However, most control methodologies depend on accurate system models which are derived from six degrees of freedom nonlinear dynamics they generally do not consider realistic outdoor perturbations uncertainties. As a solution, model-free data-driven identification controlling have been refined in this paper. This multiple input-multiple...
Incorporating deep learning (DL) classification models into unmanned aerial vehicles (UAVs) can significantly augment search-and-rescue operations and disaster management efforts. In such critical situations, the UAV's ability to promptly comprehend crisis optimally utilize its limited power processing resources narrow down search areas is crucial. Therefore, developing an efficient lightweight method for scene of utmost importance. However, current approaches tend prioritize accuracy on...
While evolving neuro-fuzzy systems have shown promise for learning from non-stationary streaming data with concept drift, most existing models lack transparency due to the limited interpretability of Takagi-Sugeno fuzzy architecture's linear rule consequents. The limits reliability crucial applications. To address this limitation, paper proposes a new system called X-Fuzz that enhances by integrating LIME technique provide local explanations and evaluates them using faithfulness monotonicity...
Abstract Advanced and accurate modelling of a Flapping Wing Micro Air Vehicle (FW MAV) its control is one the recent research topics related to field autonomous MAVs. Some desiring features FW MAV are quick flight, vertical take-off landing, hovering, fast turn, enhanced manoeuvrability contrasted with similar-sized fixed rotary wing Inspired by MAV’s advanced features, four-wing Nature-inspired (NI) modelled controlled in this work. The Fuzzy C-Means (FCM) clustering algorithm utilized...
Real-time forecasting of the financial time-series data is challenging for many machine learning (ML) algorithms. First, ML models operate offline, where they need a batch data, which may not be available during training. Besides, due to fixed architecture majority offline-based models, suffer deal with uncertain nature data. In contrast, online mode evolving-structured could promising forecasting. For real-time deployment such low memory demand must. model’s explainability plays crucial...
In this study, an magnetorheological (MR) damper has been designed based on its energy harvesting capability which combines the key benefits of generation (reusing lost energy) and damping (controllable force). The part a magnet coil arrangement to generate energy. A two-dimensional axisymmetric model proposed is developed in COMSOL Multiphysics where different magnetic field properties are analysed generally by finite element method. Finally, tested universal testing machine observed...
Many real-world classification problems have imbalanced frequency of class labels; a well-known issue known as the "class imbalance" problem. Classic algorithms tend to be biased towards majority class, leaving classifier vulnerable misclassification minority class. While literature is rich with methods fix this problem, dimensionality problem increases, many these do not scale-up and cost running them become prohibitive. In paper, we present an end-to-end deep generative classifier. We...