A5042919549- Energy Load and Power Forecasting
- Neural Networks and Applications
- Machine Learning and ELM
- Stock Market Forecasting Methods
- Forecasting Techniques and Applications
- EEG and Brain-Computer Interfaces
- Maritime Navigation and Safety
- Maritime Ports and Logistics
- Time Series Analysis and Forecasting
- Maritime Transport Emissions and Efficiency
- Image and Signal Denoising Methods
- Anomaly Detection Techniques and Applications
- Neural Networks and Reservoir Computing
- Muscle activation and electromyography studies
- ECG Monitoring and Analysis
- Blind Source Separation Techniques
- Face and Expression Recognition
- Hydrological Forecasting Using AI
- Prosthetics and Rehabilitation Robotics
- Advanced Memory and Neural Computing
- Non-Invasive Vital Sign Monitoring
- Advanced Neural Network Applications
- Traffic Prediction and Management Techniques
- Underwater Acoustics Research
- Air Quality Monitoring and Forecasting
Northwestern Polytechnical University
2025
Nanyang Technological University
2020-2024
Fraunhofer Singapore
2022
Neural networks have been successfully employed in various domains such as classification, regression and clustering, etc. Generally, the back propagation (BP) based iterative approaches are used to train neural networks, however, it results issues of local minima, sensitivity learning rate slow convergence. To overcome these issues, randomization random vector functional link (RVFL) network proposed. RVFL model has several characteristics fast training speed, direct links, simple...
Electroencephalogram (EEG) has become increasingly popular in driver fatigue monitoring systems. Several decomposition methods have been attempted to analyze the EEG signals that are complex, nonlinear and non-stationary improve decoding performance different applications. However, it remains challenging extract more distinguishable features from decomposed components for recognition. In this work, we propose a novel decomposition-based hybrid ensemble convolutional neural network (CNN)...
Financial time series forecasting is crucial in empowering investors to make well-informed decisions, manage risks effectively, and strategically plan their investment activities. However, the non-stationary non-linear characteristics inherent data pose significant challenges when accurately predicting future forecasts. This paper proposes a novel Recurrent ensemble deep Random Vector Functional Link (RedRVFL) network for financial forecasting. The proposed model leverages randomly...
With the advancement of satellite communication technology, maritime Internet Things (IoT) has made significant progress. As a result, vast amounts Automatic Identification System (AIS) data from global vessels are transmitted to various stakeholders through Maritime IoT systems. AIS contains large amount dynamic and static information that requires effective intuitive visualization for comprehensive analysis. However, two major deficiencies challenge current models: lack consideration...
This paper proposes a three-stage online deep learning model for time series based on the ensemble random vector functional link (edRVFL). The edRVFL stacks multiple randomized layers to enhance single-layer RVFL's representation ability. Each hidden layer's is utilized training an output layer, and of all forms edRVFL's output. However, original not designed learning, nature features harmful extracting meaningful temporal features. In order address limitations extend mode, this dynamic...
This work investigated the use of an ensemble deep random vector functional link (edRVFL) network for electroencephalogram (EEG)-based driver fatigue recognition. Against low feature learning capability edRVFL from raw EEG signals, two strategies were exploited in this work. Specifically, first one was to exploit advantages extractor module CNNs, i.e., CNN features as input network. The second improve An enhanced edRFVL named FGloWD-edRVFL proposed, which four enhancements implemented,...
Hospitals can predetermine the admission rate and facilitate resource allocation based on valid emergency requests bed capacity estimation. The excess unoccupied beds be determined with help of forecasting number discharged patients. Extracting predictive features mining temporal patterns from historical observations are crucial for accurate reliable forecasts. Machine learning algorithms have demonstrated ability to learn knowledge make predictions unseen inputs. This paper utilizes several...