Research

Quantitative investment increasingly relies on artificial intelligence to analyze complex financial data and support investment decisions. This study develops an AI-driven stock selection framework for the Taiwan equity market by integrating industry-specific modeling, multi-period return prediction, downside risk estimation, and explainable artificial intelligence. The proposed framework groups stocks according to industry characteristics and compares several…

Cerebrovascular disease classification from magnetic resonance imaging (MRI) is an important task in medical image analysis. This study focuses on using deep learning techniques to automatically classify three cerebrovascular diseases, including Moyamoya Disease (MMD), Arteriovenous Malformation (AVM), and Cerebral Aneurysm (CA), based on T2-weighted MRI images. Multiple deep learning architectures are evaluated, including convolutional neural…

Breast cancer diagnosis using ultrasound imaging is an important task in medical image analysis, particularly for identifying and assessing suspicious breast lesions. This study focuses on integrating deep learning-based tumor segmentation and image classification techniques to develop an automated computer-aided analysis framework for breast ultrasound images. Multiple segmentation models, including DeepLabV3+, Swin-UNet, Mask R-CNN, YOLOv8,…

Thyroid nodules are common endocrine abnormalities, and their detection has increased with the widespread use of high-resolution ultrasound. However, ultrasound images are often affected by noise, low image contrast, and differences in diagnostic experience, which may lead to inconsistent assessments of benign and malignant nodules. This study focuses on developing a deep learning–based computer-aided diagnosis…

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…

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 various brain tumors, including Glioblastoma Multiforme (GBM), one of the most aggressive types. The research explores advanced segmentation models such as UNet,…

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…

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 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…

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…