A5089620090- Advanced Queuing Theory Analysis
- Advanced Image and Video Retrieval Techniques
- Image Retrieval and Classification Techniques
- Image and Object Detection Techniques
- Fuzzy Systems and Optimization
- Multi-Criteria Decision Making
- Reliability and Maintenance Optimization
- Medical Image Segmentation Techniques
- Industrial Vision Systems and Defect Detection
- Robotics and Sensor-Based Localization
- Probability and Risk Models
- Image Processing Techniques and Applications
- Advanced Wireless Network Optimization
- Video Analysis and Summarization
- Advanced Vision and Imaging
- Image Processing and 3D Reconstruction
- Optimization and Mathematical Programming
- Supply Chain and Inventory Management
- Scheduling and Optimization Algorithms
- Remote-Sensing Image Classification
- Simulation Techniques and Applications
- Vehicle License Plate Recognition
- 3D Shape Modeling and Analysis
- Smart Agriculture and AI
- Face and Expression Recognition
National Taichung University of Science and Technology
2014-2024
Abstract Left ventricular hypertrophy (LVH) indicates subclinical organ damage, associating with the incidence of cardiovascular diseases. From medical perspective, electrocardiogram (ECG) is a low-cost, non-invasive, and easily reproducible tool that often used as preliminary diagnosis for detection heart disease. Nowadays, there are many criteria assessing LVH by ECG. These usually include voltage combination RS peaks in multi-lead ECG must be greater than one or more thresholds diagnosis....
In this study, adaptive local binary patterns (ALBP) are proposed for image retrieval and classification. ALBP based on texture features patterns. The were used to propose an histogram (ALBPH) gradient (GALBP) in study. Two most useful describing the relationship a neighbourhood. ALBPH shows distribution of by identifying employing difference between centre pixel neighbourhood values. GALBP, each is computed sum number adopted as feature. set colour greyscale images generate variety subsets....
Abstract This article aims to develop a method for the detection and segmentation of cytoplast nucleus from cervix smear image. First, technique equalization with Gaussian filter is adopted eliminate noise in Second, new edge enhancement proposed work out coarseness each pixel, which later used as determining characteristic reinforced object images. A two‐group then reinforce this according rough pixels. Third, detector enhances gradients edges while suppressing gradients, specifies pixels...
This paper proposes a multi–convolutional neural network (CNN)-based system for the detection, tracking, and recognition of emotions dogs in surveillance videos. detects each frame video, tracks recognizes dogs’ emotions. The uses YOLOv3 model dog detection. are tracked real time with deep association metric (DeepDogTrack), which Kalman filter combined CNN processing. Thereafter, emotional behaviors categorized into three types—angry (or aggressive), happy excited), neutral general)...
Journal Article Image Retrieval System Based on Adaptive Color Histogram and Texture Features Get access Chuen-Horng Lin, Lin * 1Graduate School of Computer Science Information Technology, National Taichung Institute Taichung, Taiwan, Republic China *Corresponding author: linch@ntit.edu.tw Search for other works by this author on: Oxford Academic Google Scholar Wei-Chih 2Department Management, No. 129, Sec. 3, Sanmin Rd., The Journal, Volume 54, Issue 7, July 2011, Pages 1136–1147,...
This paper considers an M/M/r queueing system with infinite capacity, in which the number of working servers changes depending on queue length. The steady-state probability distributions and expected customers are derived, used to construct a cost function. In order minimize system, we use genetic algorithm find best thresholds length activating their corresponding service rate. Some illustrative examples provided demonstrate how process this works for optimal management policy multi-server system.
This study has developed an object detection and segmentation technique for processing cytoplasm cell nucleus on ThinPrep-cervical smear images at various magnifications. Both edge techniques region growing adaptive threshold were applied to a segment nucleus, cytoplasm, backgrounds using cervical image. To validate the accuracy feasibility of proposed method, we took variety perform series experiments. The superficial cells, intermediate abnormal with each taken from ThinPrep smears results...