Ming-Hung Shih
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Ming-Hung Shih has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Dong-Her Shih
Department of Information Management, National Yunlin University of Science and Technology, Douliu 64002, Taiwan
5 shared publications - David C. Yen
Texas Southern University
3 shared publications - Ting-Wei Wu
Department of Information Management, National Yunlin University of Science and Technology, Douliu 64002, Taiwan
2 shared publications - Yi-Huei Wu
Department of Information Management, National Yunlin University of Science and Technology, Yunlin, Douliu, Taiwan
2 shared publications - Che-Lun Chang
National Yunlin University of Science & Technology
1 shared publication - Ho-Cheng Lin
Department of Information Management, National Yunlin University of Science and Technology, 123, Section 3, University Road, Douliu, Yunlin, Taiwan, ROC
1 shared publication
Latest Publications
- Open Access
- 21 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 160030-160051
Classifying Dementia Severity Using MRI Radiomics Analysis of the Hippocampus and Machine Learning
Dementia is a leading cause of global mortality, with limited treatment options available. Patients progress through three stages: cognitive normal (CN), mild cognitive impairment (MCI), and Alzheimer’s disease (AD). Accurate prediction of these stages can significantly slow deterioration. Recent research suggests analyzing MRI images, focusing on markers like whole brain, hippocampus, and entorhinal cortex atrophy, is diagnostically valuable. However, most methods analyze 2D MRI images, losing anatomical context. Our study processes 3D MRI data with AC-PC alignment correction and extracts radiomic features from the segmented hippocampus, followed by discretization and principal component analysis for optimization. Machine learning and deep learning methods are then used for classification with cross-validation, achieving the highest accuracy with support vector machine (SVM). Compared with other studies, our results show the highest accuracy among the three dementia severity classifications. Combining the radiomic features from segmented hippocampus in MRI with machine learning promises unprecedented accuracy in predicting dementia severity, potentially slowing progression and enhancing patients’ quality of life.
- 21 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 160030-160051
Open AccessClassifying Dementia Severity Using MRI Radiomics Analysis of the Hippocampus and Machine Learning
Dementia is a leading cause of global mortality, with limited treatment options available. Patients progress through three stages: cognitive normal (CN), mild cognitive impairment (MCI), and Alzheimer’s disease (AD). Accurate prediction of these stages can significantly slow deterioration. Recent research suggests analyzing MRI images, focusing on markers like whole brain, hippocampus, and entorhinal cortex atrophy, is diagnostically valuable. However, most methods analyze 2D MRI images, losing anatomical context. Our study processes 3D MRI data with AC-PC alignment correction and extracts radiomic features from the segmented hippocampus, followed by discretization and principal component analysis for optimization. Machine learning and deep learning methods are then used for classification with cross-validation, achieving the highest accuracy with support vector machine (SVM). Compared with other studies, our results show the highest accuracy among the three dementia severity classifications. Combining the radiomic features from segmented hippocampus in MRI with machine learning promises unprecedented accuracy in predicting dementia severity, potentially slowing progression and enhancing patients’ quality of life.
- Open Access
- 16 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 130091-130104
Stroke Prediction Using Deep Learning and Transfer Learning Approaches
Stroke is one of the leading causes of death and disability worldwide. The ideal solution to the stroke problem is to prevent it in advance by controlling metabolic factors, atrial fibrillation, hypertension, smoking, Etc. However, unless the physiological indicators are abnormal, it is difficult for medical personnel to decide whether special precautions are necessary for a patient based solely on monitoring the potential patient. There was a great category imbalance between stroke and non-stroke patients, so this study tried to use various techniques to solve the problem of categorical unbalanced stroke prediction problem. Then, deep learning models were used to predict whether the patients would have a stroke. Finally, the classification experiment is carried out through transfer learning to observe whether the evaluation metrics are further improved. According to the experimental results, this study effectively reduced the false negative rate (FNR) and false positive rate (FPR) of stroke prediction and improved the overall accuracy of stroke prediction through the category imbalance treatment and deep learning method.
- 16 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 130091-130104
Open AccessStroke Prediction Using Deep Learning and Transfer Learning Approaches
Stroke is one of the leading causes of death and disability worldwide. The ideal solution to the stroke problem is to prevent it in advance by controlling metabolic factors, atrial fibrillation, hypertension, smoking, Etc. However, unless the physiological indicators are abnormal, it is difficult for medical personnel to decide whether special precautions are necessary for a patient based solely on monitoring the potential patient. There was a great category imbalance between stroke and non-stroke patients, so this study tried to use various techniques to solve the problem of categorical unbalanced stroke prediction problem. Then, deep learning models were used to predict whether the patients would have a stroke. Finally, the classification experiment is carried out through transfer learning to observe whether the evaluation metrics are further improved. According to the experimental results, this study effectively reduced the false negative rate (FNR) and false positive rate (FPR) of stroke prediction and improved the overall accuracy of stroke prediction through the category imbalance treatment and deep learning method.
- Open Access
- 13 December 2021
- Published by MDPI AG in Mathematics
- Vol. 9 (24) , 3214
A Novel Auction Blockchain System with Price Recommendation and Trusted Execution Environment
Online auctions are now widely used, with all the convenience and efficiency brought by internet technology. Despite the advantages over traditional auction methods, some challenges still remain in online auctions. According to the World Business Environment Survey (WBES) conducted by the World Bank, about 60% of companies have admitted to bribery and manipulation of the auction results. In addition, buyers are prone to the winner’s curse in an online auction environment. Since the increase in information availability can reduce uncertainty, easy access to relevant auction information is essential for buyers to avoid the winner’s curse. In this study, we propose an Online Auction Price Suggestion System (OAPSS) to protect the data from being interfered with by third-party programs based on Intel’s Software Guard Extensions (SGX) technology and the characteristics of the blockchain. Our proposed system provides a smart contract by using α-Sutte indicator in the final transaction price prediction as a bidding price recommendation, which helps buyers to reduce the information uncertainty on the value of the product. The amount spent on the smart contract in this study, excluding deployed contracts, plus the rest of the fees is less than US$1. Experimental results of the simulation show that there is a significant difference (p < 0.05) between the recommended price group and the actual price group in the highest bid. Therefore, we may conclude that our proposed bidder’s price recommendation function in the smart contract may mitigate the loss of buyers caused by the winner’s curse.
- 13 December 2021
- Published by MDPI AG in Mathematics
- Vol. 9 (24) , 3214
Open AccessA Novel Auction Blockchain System with Price Recommendation and Trusted Execution Environment
Online auctions are now widely used, with all the convenience and efficiency brought by internet technology. Despite the advantages over traditional auction methods, some challenges still remain in online auctions. According to the World Business Environment Survey (WBES) conducted by the World Bank, about 60% of companies have admitted to bribery and manipulation of the auction results. In addition, buyers are prone to the winner’s curse in an online auction environment. Since the increase in information availability can reduce uncertainty, easy access to relevant auction information is essential for buyers to avoid the winner’s curse. In this study, we propose an Online Auction Price Suggestion System (OAPSS) to protect the data from being interfered with by third-party programs based on Intel’s Software Guard Extensions (SGX) technology and the characteristics of the blockchain. Our proposed system provides a smart contract by using α-Sutte indicator in the final transaction price prediction as a bidding price recommendation, which helps buyers to reduce the information uncertainty on the value of the product. The amount spent on the smart contract in this study, excluding deployed contracts, plus the rest of the fees is less than US$1. Experimental results of the simulation show that there is a significant difference (p < 0.05) between the recommended price group and the actual price group in the highest bid. Therefore, we may conclude that our proposed bidder’s price recommendation function in the smart contract may mitigate the loss of buyers caused by the winner’s curse.
- 8 April 2014
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 74 (18) , 7489-7514
A robust copyright and ownership protection mechanism for music
- 8 April 2014
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 74 (18) , 7489-7514
A robust copyright and ownership protection mechanism for music
- 25 June 2011
- Published by Elsevier in Expert Systems with Applications
- Vol. 38 (12) , 15344-15355
An implementation and evaluation of recommender systems for traveling abroad
- 25 June 2011
- Published by Elsevier in Expert Systems with Applications
- Vol. 38 (12) , 15344-15355
An implementation and evaluation of recommender systems for traveling abroad