A5102015752- Image Retrieval and Classification Techniques
- EEG and Brain-Computer Interfaces
- Industrial Vision Systems and Defect Detection
- Biosensors and Analytical Detection
- Acute Ischemic Stroke Management
- Additive Manufacturing and 3D Printing Technologies
- Optical Systems and Laser Technology
- Electrochemical sensors and biosensors
- PAPR reduction in OFDM
- Thin-Film Transistor Technologies
- Context-Aware Activity Recognition Systems
- Stability and Control of Uncertain Systems
- Human Pose and Action Recognition
- Stroke Rehabilitation and Recovery
- Model Reduction and Neural Networks
- Advanced Image Fusion Techniques
- Medical Image Segmentation Techniques
- Olfactory and Sensory Function Studies
- Analytical Chemistry and Sensors
- Venous Thromboembolism Diagnosis and Management
- Advanced Battery Materials and Technologies
- Intracerebral and Subarachnoid Hemorrhage Research
- SARS-CoV-2 detection and testing
- Advanced Data Compression Techniques
- Cerebrovascular and genetic disorders
Guizhou University
2024
Fuzhou University
2024
National Taiwan University
1989-2023
Fujian University of Traditional Chinese Medicine
2021-2022
Hong Kong University of Science and Technology
2022
University of Hong Kong
2022
King Abdullah University of Science and Technology
2022
University of Southern California
2020
Chung Yuan Christian University
2009
National Yang Ming Chiao Tung University
2003
The 3-D shape accuracy is a critical performance measure for products built via additive manufacturing (AM). With advances in computing and increased accessibility of AM product data, machine learning (ML4AM) has become viable strategy enhancing printing performance. A proper description the formation through layer-by-layer fabrication process to ML4AM, such as feature selection modeling. physics-based modeling simulation approaches present voxel-level an object from points lines, lines...
Combining low-dimensional layers of dissimilar metal oxide materials to form a heterojunction structure offers potent strategy improve the performance and stability thin-film transistors (TFTs). Here, we study impact channel layer thicknesses on operating characteristics In2O3/ZnO TFTs prepared via sputtering. The conduction band offset present at heterointerface affects device's characteristics, as is thickness individual layers. latter investigated using variety experimental computational...
Solid-state transistor sensors that can detect biomolecules in real time are highly attractive for emerging bioanalytical applications. However, combining upscalable manufacturing with the required performance remains challenging. Here, an alternative biosensor concept is developed, which relies on a solution-processed In2 O3 /ZnO semiconducting heterojunction featuring geometrically engineered tri-channel architecture rapid, real-time detection of important biomolecules. The sensor combines...
Abstract Identifying the type of stimuli that attracts human visual attention has been an appealing topic for scientists many years. In particular, marking salient regions in images is useful both psychologists and computer vision applications. this paper, we propose a computational approach producing saliency maps using statistics machine learning methods. Based on four assumptions, three properties (Feature-Prior, Position-Prior, Feature-Distribution) can be derived combined by simple...
Defect inspection plays a critical role in thin film transistor liquid crystal display (TFT-LCD) manufacture, and has received much attention the field of automatic optical (AOI). Previously, most focus was put on problems macro-scale Mura-defect detection cell process, but it recently been found that defects which substantially influence yield rate LCD panels are actually those TFT array is first process TFT-LCD manufacturing. therefore considered difficult task. This paper presents novel...
Leukoaraiosis (LA) results from ischemic injury in small cerebral vessels, which may be attributable to decreased vascular density, reduced cerebrovascular angiogenesis, blood flow, or microcirculatory dysfunction the brain. In this study, we enrolled 357 patients with mild intracerebral hemorrhage (ICH) five hospitals China and analyzed relationships between LA clinical symptom severity at admission, neurological function prognosis 3 months, 1-year stroke recurrence. Patients were divided...
The minimum-fuel control problem is investigated for a class of multiinput affine nonlinear systems whose associated Lie algebra nilpotent. After preliminary notions and definitions are presented, emphasis on the solution to optimal generated by certain system vector fields Consequences maximum principle deduced such systems.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
This paper focuses on the development of a P300 speller and design rehabilitation robot using brain-machine interface. The combined feature set provides norm that can be used to assess trends user's increased or decreased independence. is found maintain 90% sorting rate; it also reduce relationship individual independence for each subject. Among results, highest classification accuracy by 36.04%. A novel adaptive coupled elastic actuator (ACEA) proposed uses adjustable characteristics adapt...
The purpose of this study was to assess the efficacy and safety combination tirofiban with intravenous thrombolysis (IVT) in treating patients capsular warning syndrome (CWS) who failed respond treatment alone. Tirofiban approved for CWS fluctuating symptoms or no substantial improvement after within 24 h our hospital from October 2019 June 2021. Patients were evaluated National Institutes Health Stroke Scale (NIHSS) at admission, 72 post-thrombolysis, 1-week, 3-months modified Rankin Scales...
With the advancement of robotics, importance service robots in society is increasing. It crucial for to understand their environment so that they can offer suitable responses humans. To realize use space, primarily an model. This paper focused on development model based human behaviors. In this model, a new neural network structure called dynamic highway networks applied recognize humans’ addition, two-dimensional pose estimator, Laban movement analysis, and fuzzy integral are employed....
A parameterised contour that is invariant against affine transformations a convenient substitution of the object image for shape recognition. Generally, parameterisation needs several representative signals to fit transformation model. When fail carry information thoroughly, loss occurs in resulting contour, and so accuracy recognition may deteriorate. Synthesised feature are shown, which represent an without can be extracted with partial Fourier synthesis or cosine synthesis. Lossless...
Abstract In this paper, we present a new compression method for color document images based on the wavelet transform and fuzzy picture‐text segmentation. This approach addresses segmentation method, which separates pictures texts by using coefficients from images. The picture components text are encoded zerotree coding modified run‐length Huffman coding, respectively. Key words: transformzerotree codingfuzzy segmentationcolor image Notes Corresponding author. (Tel: 886–3–5712122 ext. 54313;...