A5064947657- Neural Networks and Applications
- Advanced Clustering Algorithms Research
- Data Mining Algorithms and Applications
- Face and Expression Recognition
- Natural Language Processing Techniques
- Time Series Analysis and Forecasting
- Data Visualization and Analytics
- Solar Radiation and Photovoltaics
- Web Data Mining and Analysis
- Photovoltaic System Optimization Techniques
- Explainable Artificial Intelligence (XAI)
- Algorithms and Data Compression
- Topic Modeling
- Data Management and Algorithms
- Image Retrieval and Classification Techniques
- Machine Learning in Healthcare
- Machine Learning and Data Classification
- Hand Gesture Recognition Systems
- COVID-19 diagnosis using AI
- Anomaly Detection Techniques and Applications
- Advanced Control Systems Design
- Hydrological Forecasting Using AI
- Artificial Intelligence in Healthcare and Education
- Imbalanced Data Classification Techniques
- Human Pose and Action Recognition
National Yunlin University of Science and Technology
2010-2024
Weatherford College
2023
River streamflow is an essential hydrological parameters for optimal water resource management. This study investigates models used to estimate monthly time-series river data at two stations in the USA (Heise and Irwin on Snake River, Idaho). Five diverse types of machine learning (ML) model were tested, support vector machine-radial basis function (SVM-RBF), SVM-Polynomial (SVM-Poly), decision tree (DT), gradient boosting (GB), random forest (RF), long short-term memory (LSTM). These...
Vehicular Ad Hoc Network (VANETs) need methods to control traffic caused by a high volume of during day and night, the interaction vehicles, pedestrians, vehicle collisions, increasing travel delays, energy issues. Routing is one most critical problems in VANET. One machine learning categories reinforcement (RL), which uses RL algorithms find more optimal path. According feedback they get from environment, these can affect system through previous actions reactions. This paper provides...
The modeling of human body kye-points is the most significant aspect pose estimation appropriately. Computer vision algorithm identifies pose, body-movement, and action in many ways. Most previous works taken advantage for finding accuracy or efficiency terms speed. However, techniques suffer intensive computational demands with low-latency higher proceeding We have designed a unique approach single-person recognition which well suited fitness application mobility activities. proposed...
With urbanization and increasing consumption, there is a growing need to prioritize sustainable development across various industries. Particularly, hindered by air pollution, which poses threat both living organisms the environment. The emission of combustion gases containing particulate matter (PM 2.5) during human social activities major cause pollution. To mitigate health risks, it crucial have accurate reliable methods for forecasting PM 2.5 levels. In this study, we propose novel...
Nowadays, raw dermoscopic images in melanoma detection do not have acceptable performance. Machine learning helps detect accurately. There are extensive studies classic and deep learning-based approaches for the literature. Still, they accurate or require high data. This paper proposes a hybrid mechanism automated on based Discrete Cosine Transform features metadata. It is composed of three steps. First, extra information/artifacts deleted; remaining pixels standardized processing. Second,...
Fault detection and failure mode diagnosis are of crucial importance in operation maintenance (O&M) photovoltaic (PV) power stations. In this work, advanced artificial intelligence techniques exploited to optimize these O&M tasks for 150 PV stations Taiwan with total rating around 54 MW. First, the response each inverter under maximal tracking is monitored analyzed by machine learning algorithms every five minutes. The alert fault will be activated if output significantly different from its...
Many real-world datasets are of mixed types, having numeric and categorical attributes. Even though difficult, analyzing mixed-type is important. In this paper, we propose an extended self-organizing map (SOM), called MixSOM, which utilizes a data structure distance hierarchy to facilitate the handling values in direct, unified manner. Moreover, model regularizes prototype between neighboring neurons proportion their so that structures clusters can be portrayed better on map. Extensive...
The original self-organizing map (SOM) was proposed in the context of processing numeric data. In previous studies, an extended SOM incorporating data structure distance hierarchies has been to facilitate handling categorical values. model could take into account semantics embed ded values via hierarchies. addition manual construction by domain experts, approach learning from datasets devised. However, study based on supervised which demands presence a class attribute dataset. real-world...
Recruitment is an important issue of human resource management (HRM).The main purpose recruitment to obtain talent from internal and external organization.However, excellent maybe will be missed at the pre-screening process under lack complete information for managers judge.In this paper, a personnel selection tool based on fuzzy data mining method proposed assist business find eligible more efficiently.
Data mining uncovers hidden, previously unknown, and potentially useful information from large amounts of data. Compared to the traditional statistical machine learning data analysis techniques, emphasizes providing a convenient complete environment for analysis. In this paper, we propose an integrated framework visualized, exploratory clustering, pattern extraction mixed We further discuss its implementation techniques: generalized self-organizing map (GSOM) extended attribute-oriented...