Ting-Wei Wu

Prof. Ting-Wei Wu

orcid

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
Dong-Her ShihDong-Her Shih
Dong-Her Shih
FHFeng-Chuan Huang
Feng-Chuan Huang
CCChia-Yi Chieh
Chia-Yi Chieh
MSMing-Hung Shih
Ming-Hung Shih
TWTing-Wei Wu
Ting-Wei Wu
With the rapid development of e-commerce services, online retail has evolved from multi-channel to omni-channel in order to provide customers with more services. However, reverse logistics services (returns and exchanges) have become the target of many fraudulent activities, causing a lot of economic losses for many online retail companies. The current challenge of the traditional countermeasure is it requires a lot of manpower and training resources. In this study, we propose ESPRES, a system that adopts blockchain technology to prevent fraudulent behavior in the process of returns and exchanges with the smart contract and multi-attribute decision-support method to help consumers choose a suitable payment program. A practical implication of this study is that by adopting blockchain technology, a great amount of manpower used on determining whether each return or exchange is fraudulent can be reduced since merchants can check the product ownership. In addition, due to the fact that the footprint of goods cannot be forged, it can also prevent counterfeit or parallel imports of goods.

18 March 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Dong-Her ShihDong-Her Shih
Dong-Her Shih
TWTing-Wei Wu
Ting-Wei Wu
MSMing-Hung Shih
Ming-Hung Shih
GCGuan-Wei Chen
Guan-Wei Chen
DYDavid C. Yen
David C. Yen
The Industrial Internet of Things (IIoT) plays an important role in Industry 4.0, but the existing IIoT systems could be vulnerable to a single point of failure and malicious attacks, failing to provide reliable services. IIoT devices have some particularities, such as mobility, limited performance, and distributed deployment, which are challenging to traditional centralized access control methods in the large-scale IIoT environment. To resolve the challenges, we propose an access control system for the Industrial Internet of Things. The system contains three smart contracts: device contract (DC), policy contract (PC), and access contract (AC). The device contract provides a method of storing the URL of the resource data generated by the equipment and a query method. The policy contract provides the function of managing the attribute-based access control (ABAC) of the administrator user. The access contract is the core program that implements the access control method for ordinary users. Combining ABAC and blockchain technology provides decentralized, fine-grained, and dynamic access control management for IIoT.

Dong-Her ShihDong-Her Shih
Dong-Her Shih
THTo Thi Hien
To Thi Hien
Ly Sy Phu NguyenLy Sy Phu Nguyen
Ly Sy Phu Nguyen
TWTing-Wei Wu
Ting-Wei Wu
WYWen-Ting You
Wen-Ting You
In recent years, with rapid economic development, air pollution has become extremely serious, causing many negative effects on health, environment and medical costs. PM2.5 is one of the main components of air pollution. Therefore, it is necessary to know the PM2.5 air quality in advance for health. Many studies on air quality are based on the government’s official air quality monitoring stations, which cannot be widely deployed due to high cost constraints. Furthermore, the update frequency of government monitoring stations is once an hour, and it is hard to capture short-term PM2.5 concentration peaks with little warning. Nevertheless, dealing with short-term data with many stations, the volume of data is huge and is calculated, analyzed and predicted in a complex way. This alleviates the high computational requirements of the original predictor, thus making Spark suitable for the considered problem. This study proposes a PM2.5 instant prediction architecture based on the Spark big data framework to handle the huge data from the LASS community. The Spark big data framework proposed in this study is divided into three modules. It collects real time PM2.5 data and performs ensemble learning through three machine learning algorithms (Linear Regression, Random Forest, Gradient Boosting Decision Tree) to predict the PM2.5 concentration value in the next 30 to 180 min with accompanying visualization graph. The experimental results show that our proposed Spark big data ensemble prediction model in next 30-min prediction has the best performance (R2 up to 0.96), and the ensemble model has better performance than any single machine learning model. Taiwan has been suffering from a situation of relatively poor air pollution quality for a long time. Air pollutant monitoring data from LASS community can provide a wide broader monitoring, however the data is large and difficult to integrate or analyze. The proposed Spark big data framework system can provide short-term PM2.5 forecasts and help the decision-maker to take proper action immediately.

13 December 2021 in Mathematics
Verified
Journal Article
Open access
PDF file
Dong-Her ShihDong-Her Shih
Dong-Her Shih
TWTing-Wei Wu
Ting-Wei Wu
MSMing-Hung Shih
Ming-Hung Shih
WTWei-Cheng Tsai
Wei-Cheng Tsai
DYDavid C. Yen
David C. Yen
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.

18 June 2026 in Engineering Proceedings
Verified
Conference Paper
Open access
PDF file
KLKuan chu LU
Kuan chu LU
TWTing-Wei Wu
Ting-Wei Wu
CCChun-Han Cheng
Chun-Han Cheng
Class imbalance in datasets is a common issue across various fields, including banking, medicine, and information security. Data augmentation is a frequently used approach to address this problem by generating additional samples of the minority class to rebalance the dataset. Other studies have employed methods such as Generative Adversarial Networks (GAN) and Synthetic Minority Over-sampling Technique (SMOTE)for this purpose. Therefore, this study aims to compare the differences between the two oversampling techniques, GAN and SMOTE, in handling class imbalance problems. The results of this study show the accuracy of distinguishing between real and generated data to determine which method offers a greater advantage. The method demonstrates better performance in multi-class classification tasks. The GAN model can be effectively applied to both binary classification and the generation of diverse samples from minority and majority classes, even in extreme cases where the number of minority samples is tiny. Moreover, in terms of classification accuracy and the quality of generated samples, GAN outperforms SMOTE in data augmentation and oversampling. It maintains strong performance even when the number of instances in the minority class is limited.

21 September 2026 in Mathematics
Verified
Journal Article
Open access
PDF file
KLKuan chu LU
Kuan chu LU
TWTing-Wei Wu
Ting-Wei Wu
Class imbalance in medical classification can substantially affect model performance, particularly when resampling intensity and decision threshold are considered separately. This study systematically investigates their joint effects using the Pima Indians Diabetes, Heart Failure, and Thoracic Surgery datasets. Five classifiers were evaluated with Baseline, SMOTE, and ADASYN under multiple oversampling intensities and decision thresholds ranging from 0.30 to 0.70 using leakage-free, repeated, stratified 10-fold cross-validation with five repetitions. The best mean F1-scores were 0.6890 for PIMA, 0.7684 for Heart Failure, and 0.3375 for Thoracic Surgery, with the preferred threshold and oversampling intensity differing across datasets. A mixed-effects analysis confirmed a significant interaction between oversampling intensity and decision threshold (χ2(16) = 141.77, p < 0.001). In contrast, the matched difference between SMOTE and ADASYN was negligible (ΔF1 = 0.0009, p = 0.663). Thresholds below 0.50 were particularly beneficial for PIMA and Thoracic Surgery, whereas Heart Failure performed best near 0.50. Oversampling also tended to increase Brier scores, indicating that improvements in threshold-specific F1-score did not necessarily correspond to better probability calibration. These findings demonstrate that dataset-specific joint evaluation of oversampling intensity and decision threshold is more informative than selecting a resampling method in isolation.