A5071391610- Fuzzy Logic and Control Systems
- Data Mining Algorithms and Applications
- Rough Sets and Fuzzy Logic
- Neural Networks and Applications
- Image Retrieval and Classification Techniques
- Water Quality Monitoring Technologies
- Advanced Image and Video Retrieval Techniques
- Big Data and Business Intelligence
- Fuzzy Systems and Optimization
- Smart Cities and Technologies
- Grey System Theory Applications
- Interactive and Immersive Displays
- Imbalanced Data Classification Techniques
- Industrial Vision Systems and Defect Detection
- Artificial Intelligence in Healthcare
- Data Management and Algorithms
- Retinal Imaging and Analysis
- Multi-Criteria Decision Making
- Anomaly Detection Techniques and Applications
- Tactile and Sensory Interactions
- Music and Audio Processing
- Brain Tumor Detection and Classification
- Video Analysis and Summarization
- Medical Image Segmentation Techniques
- Air Quality Monitoring and Forecasting
National Penghu University of Science and Technology
2021-2025
National Taipei University of Technology
2016-2025
National Taipei University
2016-2025
Chaoyang University of Technology
2020-2025
Engineering Systems (United States)
2019-2024
Machine Science
2019-2024
Jiangyin Traffic Planning Survey & Design Institute (China)
2024
Institute of Electrical and Electronics Engineers
2020-2024
University of Memphis
2020-2024
UCLouvain
2022-2024
During the past few years, severe air-pollution problem has garnered worldwide attention due to its effect on health and wellbeing of individuals. As a result, analysis prediction air pollution attracted good deal interest among researchers. The research areas include traditional machine learning, neural networks deep learning. How effectively accurately predict becomes an important issue. In this paper, we propose Aggregated LSTM (Long Short-Term Memory) model (ALSTM) based learning method....
Birdwatching is a common hobby but to identify their species requires the assistance of bird books. To provide birdwatchers handy tool admire beauty birds, we developed deep learning platform assist users in recognizing 27 birds endemic Taiwan using mobile app named Internet Birds (IoB). Bird images were learned by convolutional neural network (CNN) localize prominent features images. First, established and generated bounded region interest refine shapes colors object granularities...
Numerous bird species have become extinct because of anthropogenic activities and climate change. The destruction habitats at a rapid pace is significant threat to biodiversity worldwide. Thus, monitoring the distribution identifying elements that make up region are essential for designing conservation stratagems. However, from images complicated tedious task owing interclass similarities fine-grained features. To overcome this, in this study, we developed transfer learning-based method...
Retinopathy of prematurity (ROP) is a disease that can cause blindness in premature infants. It characterized by immature vascular growth the retinal blood vessels. However, early detection and treatment ROP significantly improve visual acuity high-risk patients. Thus, diagnosis crucial preventing impairment. several patients refrain from owing to lack medical expertise diagnosing disease; this especially problematic considering number cases on rise. To end, we applied transfer learning five...
Manual inspection and harvesting of ripening tomatoes is time consuming labor intensive. Smart agriculture can emphasize the use digital horticultural resources for farming increase farm sustainability; to that end, we proposed a fuzzy Mask R-CNN model automatically identify ripeness levels cherry tomatoes. First, annotate images automatically, c-means was used maintain spatial information various foreground background elements image. Then, Hough transform method applied locate specific...
A method is presented for scene detection and estimation using high-resolution imagery acquired through autonomous drone navigation aided with landmark recognition. The proposed system comprises a platform that facilitates efficient flight; it can capture images provide real-time video streaming of the ground cover camera equipped 14-megapixel CMOS sensor fish-eye lens. In addition, recognition was performed by applying histogram oriented gradients linear support vector machine methods on...
The increasing global population has escalated the demand for fish products. This calls a stable supply which can only be met through improved aquaculture practices. automatic recognition of diseases from diseased underwater images is one such practices that aims to control disease, improve production and optimize profits. However, due lack public disease dataset, there been limited research towards recognition. Moreover, low quality complex environments, traditional hand-designed feature...
Humans often experience unstable blood sugar due to interference factors such as environmental factors, instruments, and abnormal sugar. People with diabetes may develop hyperglycemic insufficient insulin secretion or physical abnormalities. A balanced diet regular exercise are the best ways ensure that is within normal control reduce chance of developing diabetes. This paper emphasizes importance accurate glucose monitoring for effective management, big data analytics play a pivotal role in...
Proposes a practical design method of fuzzy proportional-integral-derivative (PID) control system. Like conventional PID controllers there are several kinds controllers. Being simple structure, the research on how to choose type for different controlled plants is successful. Based analysis relationship between controller and controller, we propose suitable plant. Firstly selected designed have same property with corresponding because parameters its rule base calculated according tuned...
To automatically detect and classify the early stages of retinopathy prematurity (ROP) using a deep convolutional neural network (CNN).This retrospective cross-sectional study was conducted in referral medical centre Taiwan. Only premature infants with no ROP, stage 1 ROP or 2 were enrolled. Overall, 11 372 retinal fundus images compiled split into 10 235 (90%) for training, 1137 (10%) validation 244 testing. A CNN implemented to according stage. Data collected from December 17, 2013 May 24,...
This article presented a new set theory to deal with ambiguousness, which was entitled as an "Ambiguous Set Theory". The proposed ambiguous can represent any feature into four degrees of memberships, viz., true, false, ambiguous-true and ambiguous-false. kind representation provides granular visualization features, helps model uncertainties very effectively. In this article, initially we discussed the motivation introduce set. Then, methodology by: 1) defining it in precise way, 2)...
For total knee replacement (TKR) patients, rehabilitation after the surgery is key to regaining mobility. This study proposes a sensor-based system for effectively monitoring progress TKR. The comprises hardware module consisting of triaxial accelerometer and gyroscope, microcontroller, Bluetooth module, software app motion joint. Three indices, namely number swings, maximum flexion angle, duration practice each time, were used as metrics measure progress. proposed sensor device has...
Parkinson's disease (PD) is one of the serious diseases in neurodegenerative group, whose early stage pre-diagnosis still very tedious. Radiologists and medical practitioners mostly depended on analysis PD patients' magnetic resonance images (MRIs) to identify this disease. Due presence grayscale features uncertain inherited information MRIs, their pattern recognition visualization were complex. With motivation, a new method for analyzing visualizing patterns MRI was presented study. For...
An interactive museum-guide system exploits RFID and handheld computers to let museum visitors better explore exhibition objects. The uses both high-frequency ultrahigh-frequency technologies achieve a kind of two-way communication.