Researches Overview
AI-Based Safety Recognition System for Steel Structure Construction
This project focuses on enhancing AI-driven safety recognition systems in construction, particularly for steel structure operations. It aims to improve existing recognition models, evaluate system adaptability across different construction environments, and address data drift challenges in AI recognition. The research involves upgrading AI-based image recognition systems to detect fall prevention facilities and personal protective equipment…
Deep Learning-Based Identification and Prediction of Comorbidity Risk Factors for Sepsis
Sepsis is a life-threatening systemic inflammatory response syndrome, often triggered by infection, which can rapidly progress to multiple organ failure and death. Clinical observations have shown that many patients develop sepsis in the presence of one or more chronic comorbidities, such as diabetes, chronic kidney disease, or cancer. These comorbidities may significantly influence both the…
Automatic Brain Tumor Recognition and Classification in MRI Based on Semantic Segmentation and Deep Learning
Brain tumor detection and classification from MRI images are crucial tasks in medical imaging. This study focuses on utilizing semantic segmentation models and deep learning techniques to automate the segmentation and classification of brain tumors in MRI scans. The research explores advanced segmentation models such as UNet, Swin-UNet, and YOLO-based architectures to accurately delineate tumor…
Multi-Omics Data Integration and Classification for Alzheimer’s Disease Based on Multi-Layer Attention Graph Learning
Alzheimer’s disease is a common neurodegenerative disorder and the leading cause of dementia in the elderly, characterized by memory loss, language difficulties, and cognitive decline. Its causes involve abnormal brain protein accumulation, genetics, and aging. While there is no cure, early detection can slow progression and improve quality of life. This study proposes a multi-omics…
Deep Learning-Based Automated Diagnosis of Moyamoya Disease Using Magnetic Resonance Angiography
Moyamoya Disease (MMD) is a rare and progressive cerebrovascular disorder characterized by the gradual narrowing or occlusion of the intracranial internal carotid arteries and their major branches. This process leads to the compensatory proliferation of collateral vessels, forming the characteristic “moyamoya” network. MMD can result in severe ischemic or hemorrhagic strokes, with a particularly high…
Epilepsy Classification Based on EEG Spectral Analysis Combined with Machine Learning and Deep Learning
Epilepsy is a common chronic neurological disorder characterized by recurrent abnormal brain electrical activity. Due to the wide range of epilepsy types and varied clinical manifestations, diagnosis traditionally depends on the interpretation of EEG (electroencephalography) signals by experienced physicians—a process that is often time-consuming and subjective. In recent years, the need for objective and automated…
Multi-Gene and Rule-Guided Classification of Influenza Viruses via Cellular Automata Genomic Image Transformation and Deep Learning
This research aims to establish a reliable classification framework for the influenza virus using genomic image transformation and deep learning. The system employs cellular automata to transform viral gene sequences into structured image formats, facilitating virus visualization, identification, and subtyping. This approach has the potential to generate a more accurate understanding of viral detection and…
Automated Lumbar Intervertebral Disc Detection and Classification System Based on a Hybrid Deep Learning Framework
This study proposes a hybrid deep learning framework that integrates object detection and classification models to achieve a fully automated assessment of intervertebral disc health. The system first employs the YOLOv7 model to accurately locate intervertebral discs within DICOM images, extracting regions of interest (ROIs) while preserving anatomical features and eliminating irrelevant tissue interference. To…
Prediction to Progression-Free Survival Model in Patients with Brain Tumor
Project Overview Brain tumors, prevalent across all ages, arise from complex brain structures. Abnormal cell growth forms tumors, classified as benign or malignant. Early detection is crucial, as these slow-growing masses often lack symptoms. Due to their diverse locations and effects, treatment is challenging. This project aims to leverage deep learning and machine learning for…
The Future of Data – Data Mining and Metaverse
Project Overview In order to embrace the wave of new courses in Metaverse and further increase the development and diversity of subsequent courses, this project will use VR equipment and software to combine with data mining courses, expand data into 3D visualization, and conduct two-way interaction in the virtual space. In the new course content,…
Development of Talent Selection and Intellectual Tactical System in Competitive Table Tennis
Project Overview This project aims to build an integrated system for competitive table tennis using intelligent technology and multidisciplinary research. Key areas include talent selection, pressure assessment, injury prevention, and tactical analysis. This aims to improve player performance, inform opponent strategies, and advance both table tennis and sports science. By bringing together experts from various…
Problem-based Learning (PBL) Project
Project Overview In today’s society with diverse challenges, exploring solutions through Artificial Intelligence (AI) technology has become a global trend. However, classroom learning often lacks context and real-world application. This project addresses this by leveraging the Sustainable Development Goals (SDGs) framework. Students explore datasets related to the SDGs and apply data mining techniques to develop…
Breast Tumor Early Detection and Diagnosis
Project Review The main purpose is to build a deep learning model for the detection of breast tumors in ultrasound images. This will help doctors to reduce the time it takes to read ultrasound images and to diagnose breast tumors more accurately, thereby helping patients to receive treatment as early as possible. This project is…
Social Network Financial Behavior Prediction
Project Overview With the rapid growth of the Internet, the amount of text data has also grown exponentially. This data can be used to obtain information for decision-making. Text analysis can effectively obtain potential information, which may include public opinion, product usage opinions, or market trend information. How to extract important features from text is…
Social Media Mood Prediction with Emotional Exploration and Personality Traits
Project Overview With the mature development of the Internet and virtual communities, how to accurately analyze potential and future development trends from the massive document data of online communities will be an important emerging topic in the field of humanities and social sciences. Therefore, in the first year of this project, we hope to use…
FinTech Mobile APP Intelligent Safety Environment Research
Project Overview This research project is divided into three phases. In the first year, a fast and effective system will be developed based on machine learning models to detect malicious Android apps. In the second year, the knowledge representation characteristics of the system will be used to effectively outline the unchangeable behavior features of mobile…
Identification Technology Based on EEG and DNA Sequencing
Project Overview As fingerprint recognition and retina scanning technology become increasingly widespread in the field of biometrics, scientists have begun to focus on brain science. Because the brain waves generated by each person are unique when stimulated by external stimuli, non-invasive electrodes can be attached to the cerebral cortex to record brain wave fluctuations using…
Cultivating High School Information Science Education Program
Project Overview This program aims to encourage collaboration between universities and high schools to promote information science education at the high school level. It provides high school students with opportunities to learn about the information technology industry and information science. The main development directions of this program are: (1) Offering introductory programming courses: To equip participating…
Trend Analysis of Endometriosis and Endometrial Cancer in Taiwan
Project Overview Endometriosis is a common gynecological disease. According to different diagnostic criteria, endometriosis is found in many women of reproductive age and often occurs in women after menopause. Most of these women have abdominal pain symptoms, and endometriosis is one of the causes of their symptoms and pain. In addition, because the incidence of…
Mobile Broadband Cutting-Edge Technology Course Promotion Project
Project Overview This project aims to integrate cross-school resources in Taiwan to: (1) Develop mobile broadband teaching capacity: Enhance education capabilities through resource sharing and collaboration, empowering schools to prepare future generations for success in this field. (2) Build a teaching practice and application verification platform: Establish a robust platform for hands-on learning and real-world testing, bridging the gap…
Spatial Analysis on Ovarian Cancer
Project Overview Ovarian cancer is often asymptomatic in the early stages, and patients are often diagnosed with advanced ovarian cancer, which delays the best time for treatment. The current method for detecting ovarian cancer is to draw blood to determine the biomarker: CA-125, and to use ultrasound and gynecological examination as auxiliary diagnosis. However, the…
Drug Automation Information Analysis System Applied in Hippocampus of Rats
Project Overview Motion sickness drugs commonly sold in Taiwan target brain acetylcholine, effectively treating symptoms but causing concerns about learning and memory side effects. This project investigates gene expression in the hippocampus, a key memory region, to assess the impact of these drugs on cognitive function. This project studies how motion sickness drugs impact the…
Pituitary Gland Tumor Prediction Systems
Project Overview The pituitary gland, the conductor of our body’s hormonal orchestra, plays a crucial role in regulating various systems. However, tumors can disrupt this delicate balance, leading to a cascade of health problems. To achieve early detection and treatment, medical advancements often bridge the gap between medicine and technology. This project exemplifies synergy by…
RFID and LBS Based Systems on Mobile Medical Instruments for Healthcare Units
Project Overview The aging population, healthcare professional shortage, and rising mortality rates from medical errors have driven the global trend of healthcare informatization. The healthcare industry is facing increasing pressure from rising medical costs, peer competition, and growing consumer awareness. Reducing medical costs, promoting rational resource allocation, and improving operating performance are key goals for…
Autoimmune Cell Recognition System
Project Overview Cellular Automata (CA) is a mathematical model used to simulate complex systems composed of individual cells. Each cell can be defined with different possible states, and all cells are updated synchronously according to user-defined “rules”. The state of each cell depends on its own state and the states of its neighbors. Their states…
Colon Cancer Genetic Markers Prediction Systems
Project Overview Colorectal cancer, consistently the third deadliest in Taiwan, demands early detection for a 90% five-year survival rate. Yet, only 39% are caught early. Its rising incidence across age groups, influenced by diet, gender, and genetics, necessitates further research. This Industry Cooperation project tackles this by building a standalone colorectal cancer patient database with…