WDWei-Chang Du

Wei-Chang Du

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Wei-Chang Du has a total of 24 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    TWO-HANDED DYNAMIC GESTURE RECOGNITION USING RGB-D SENSORS

    by Yu-Chi Pu, Wei-Chang Du, Kai-Wei Shih

    Sign language is a form of visual-gestural communication that conveys semantic content through hand movements and postures. It comprises a structured set of gestures, each associated with specific meanings. For individuals with hearing impairments, sign language serves as a primary medium for expression, perception, and interaction with the external world. However, due to the general lack of sign language proficiency among the broader population, effective communication remains a significant challenge. This paper uses an RGB-D imaging device to capture both color and depth information of dynamic hand gestures, enabling more robust and discriminative feature extraction than traditional RGB-based approaches. The proposed system focuses on recognizing two-handed dynamic gestures by analyzing spatial configurations and temporal motion patterns. A gesture symbolization mechanism facilitates the recognition process, wherein complex gesture sequences are encoded into a set of primitive symbols representing key postures and transitions. These symbolic representations are then compared using a fuzzy matching algorithm, which accounts for variations in gesture execution and temporal alignment, thereby enhancing the system's tolerance. This methodology aims to provide a reliable and flexible framework for real-time gesture recognition in natural interaction scenarios.


  • Open Access

    Classification of Color Fundus Photographs Using Fusion Extracted Features and Customized CNN Models

    by Jing-Zhe Wang, Nan-Han Lu, Wei-Chang Du, Kuo-Ying Liu, Shih-Yen Hsu, Chi-Yuan Wang, Yun-Ju Chen, Li-Ching Chang, Wen-Hung Twan, Tai-Been Chen, et al.

    This study focuses on overcoming challenges in classifying eye diseases using color fundus photographs by leveraging deep learning techniques, aiming to enhance early detection and diagnosis accuracy. We utilized a dataset of 6392 color fundus photographs across eight disease categories, which was later augmented to 17,766 images. Five well-known convolutional neural networks (CNNs)—efficientnetb0, mobilenetv2, shufflenet, resnet50, and resnet101—and a custom-built CNN were integrated and trained on this dataset. Image sizes were standardized, and model performance was evaluated via accuracy, Kappa coefficient, and precision metrics. Shufflenet and efficientnetb0demonstrated strong performances, while our custom 17-layer CNN outperformed all with an accuracy of 0.930 and a Kappa coefficient of 0.920. Furthermore, we found that the fusion of image features with classical machine learning classifiers increased the performance, with Logistic Regression showcasing the best results. Our study highlights the potential of AI and deep learning models in accurately classifying eye diseases and demonstrates the efficacy of custom-built models and the fusion of deep learning and classical methods. Future work should focus on validating these methods across larger datasets and assessing their real-world applicability.


  • Open Access

    Efficient Strike Artifact Reduction Based on 3D-Morphological Structure Operators from Filtered Back-Projection PET Images

    by Chun-Yi Chiu, Yung-Hui Huang, Wei-Chang Du, Chi-Yuan Wang, Huei-Yong Chen, Yun-Shiuan Shiu, Nan-Han Lu, Tai-Been Chen

    Positron emission tomography (PET) can provide functional images and identify abnormal metabolic regions of the whole-body to effectively detect tumor presence and distribution. The filtered back-projection (FBP) algorithm is one of the most common images reconstruction methods. However, it will generate strike artifacts on the reconstructed image and affect the clinical diagnosis of lesions. Past studies have shown reduction in strike artifacts and improvement in quality of images by two-dimensional morphological structure operators (2D-MSO). The morphological structure method merely processes the noise distribution of 2D space and never considers the noise distribution of 3D space. This study was designed to develop three-dimensional-morphological structure operators (3D MSO) for nuclear medicine imaging and effectively eliminating strike artifacts without reducing image quality. A parallel operation was also used to calculate the minimum background standard deviation of the images for three-dimensional morphological structure operators with the optimal response curve (3D-MSO/ORC). As a result of Jaszczak phantom and rat verification, 3D-MSO/ORC showed better denoising performance and image quality than the 2D-MSO method. Thus, 3D MSO/ORC with a 3 × 3 × 3 mask can reduce noise efficiently and provide stability in FBP images.

  • Open Access

    Integrating ECG Monitoring and Classification via IoT and Deep Neural Networks

    by Li-Ren Yeh, Wei-Chin Chen, Hua-Yan Chan, Nan-Han Lu, Chi-Yuan Wang, Wen-Hung Twan, Wei-Chang Du, Yung-Hui Huang, Shih-Yen Hsu, Tai-Been Chen

    Anesthesia assessment is most important during surgery. Anesthesiologists use electrocardiogram (ECG) signals to assess the patient’s condition and give appropriate medications. However, it is not easy to interpret the ECG signals. Even physicians with more than 10 years of clinical experience may still misjudge. Therefore, this study uses convolutional neural networks to classify ECG image types to assist in anesthesia assessment. The research uses Internet of Things (IoT) technology to develop ECG signal measurement prototypes. At the same time, it classifies signal types through deep neural networks, divided into QRS widening, sinus rhythm, ST depression, and ST elevation. Three models, ResNet, AlexNet, and SqueezeNet, are developed with 50% of the training set and test set. Finally, the accuracy and kappa statistics of ResNet, AlexNet, and SqueezeNet in ECG waveform classification were (0.97, 0.96), (0.96, 0.95), and (0.75, 0.67), respectively. This research shows that it is feasible to measure ECG in real time through IoT and then distinguish four types through deep neural network models. In the future, more types of ECG images will be added, which can improve the real-time classification practicality of the deep model.


  • Open Access

    Classification of the Multiple Stages of Parkinson’s Disease by a Deep Convolution Neural Network Based on 99mTc-TRODAT-1 SPECT Images

    by Shih-Yen Hsu, Li-Ren Yeh, Tai-Been Chen, Wei-Chang Du, Yung-Hui Huang, Wen-Hung Twan, Ming-Chia Lin, Yun-Hsuan Hsu, Yi-Chen Wu, Huei-Yung Chen

    Single photon emission computed tomography (SPECT) has been employed to detect Parkinson’s disease (PD). However, analysis of the SPECT PD images was mostly based on the region of interest (ROI) approach. Due to limited size of the ROI, especially in the multi-stage classification of PD, this study utilizes deep learning methods to establish a multiple stages classification model of PD. In the retrospective study, the 99mTc-TRODAT-1 was used for brain SPECT imaging. A total of 202 cases were collected, and five slices were selected for analysis from each subject. The total number of images was thus 1010. According to the Hoehn and Yahr Scale standards, all the cases were divided into healthy, early, middle, late four stages, and HYS I~V six stages. Deep learning is compared with five convolutional neural networks (CNNs). The input images included grayscale and pseudo color of two types. The training and validation sets were 70% and 30%. The accuracy, recall, precision, F-score, and Kappa values were used to evaluate the models’ performance. The best accuracy of the models based on grayscale and color images in four and six stages were 0.83 (AlexNet), 0.85 (VGG), 0.78 (DenseNet) and 0.78 (DenseNet).


  • Open Access

    Feasible Classified Models for Parkinson Disease from 99mTc-TRODAT-1 SPECT Imaging

    by Shih-Yen Hsu, Hsin-Chieh Lin, Tai-Been Chen, Wei-Chang Du, Yun-Hsuan Hsu, Yi-Chen Wu, Po-Wei Tu, Yung-Hui Huang, Huei-Yung Chen

    The neuroimaging techniques such as dopaminergic imaging using Single Photon Emission Computed Tomography (SPECT) with 99mTc-TRODAT-1 have been employed to detect the stages of Parkinson’s disease (PD). In this retrospective study, a total of 202 99mTc-TRODAT-1 SPECT imaging were collected. All of the PD patient cases were separated into mild (HYS Stage 1 to Stage 3) and severe (HYS Stage 4 and Stage 5) PD, according to the Hoehn and Yahr Scale (HYS) standard. A three-dimensional method was used to estimate six features of activity distribution and striatal activity volume in the images. These features were skewness, kurtosis, Cyhelsky’s skewness coefficient, Pearson’s median skewness, dopamine transporter activity volume, and dopamine transporter activity maximum. Finally, the data were modeled using logistic regression (LR) and support vector machine (SVM) for PD classification. The results showed that SVM classifier method produced a higher accuracy than LR. The sensitivity, specificity, PPV, NPV, accuracy, and AUC with SVM method were 0.82, 1.00, 0.84, 0.67, 0.83, and 0.85, respectively. Additionally, the Kappa value was shown to reach 0.68. This claimed that the SVM-based model could provide further reference for PD stage classification in medical diagnosis. In the future, more healthy cases will be expected to clarify the false positive rate in this classification model.


  • Open Access

    Integrate Weather Radar and Monitoring Devices for Urban Flooding Surveillance

    by Shih-Yen Hsu, Tai-Been Chen, Wei-Chang Du, Jyh-Horng Wu, Shih-Chieh Chen

    With the increase of extreme weather events, the frequency and severity of urban flood events in the world are increasing drastically. Therefore, this study develops ARMT (automatic combined ground weather radar and CCTV (Closed Circuit Television System) images for real-time flood monitoring), which integrates real-time ground radar echo images and automatically estimates a rainfall hotspot according to the cloud intensity. Furthermore, ARMT combines CCTV image capturing, analysis, and Fourier processing, identification, water level estimation, and data transmission to provide real-time warning information. Furthermore, the hydrograph data can serve as references for relevant disaster prevention, and response personnel may take advantage of them and make judgements based on them. The ARMT was tested through historical data input, which showed its reliability to be between 83% to 92%. In addition, when applied to real-time monitoring and analysis (e.g., typhoon), it had a reliability of 79% to 93%. With the technology providing information about both images and quantified water levels in flood monitoring, decision makers can quickly better understand the on-site situation so as to make an evacuation decision before the flood disaster occurs as well as discuss appropriate mitigation measures after the disaster to reduce the adverse effects that flooding poses on urban areas.