KCKuo-Ming Chao

Kuo-Ming Chao

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

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


Kuo-Ming Chao has a total of 282 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Multiple GRAphs-oriented Random wAlk (MulGRA2) for social link prediction

    by Tianliang Qi, Yujie Li, Weihua Ji, Kuo-Ming Chao, Yan Chen, Haiping Zhu, Caixia Yan, Jun Liu, Mo Xu, Zhihai Suo, et al.


  • Open Access

    SplitGNN: Spectral Graph Neural Network for Fraud Detection against Heterophily

    by Bin Wu, Xinyu Yao, Boyan Zhang, Kuo-Ming Chao, Yinsheng Li

    Fraudsters in the real world frequently add more legitimate links while concealing their direct ones with other fraudsters, leading to heterophily in fraud graphs, which is a problem that most GNN-based techniques are not built to solve. Several works have been proposed to tackle the issue from the spatial domain. However, researches on addressing the heterophily problem in the spectral domain are still limited due to a lack of understanding of spectral energy distribution in graphs with heterophily. In this paper, we analyze the spectral distribution with different heterophily degrees and observe that the heterophily of fraud nodes leads to the spectral energy moving from low-frequency to high-frequency. Further, we verify that splitting graphs using heterophilic and homophilic edges can obtain more significant expressions of signals in different frequency bands. The observation drives us to propose the spectral graph neural network, SplitGNN, to capture signals for fraud detection against heterophily. SplitGNN uses an edge classifier to split the original graph and adopts flexible band-pass graph filters to learn representations. Extensive experiments on real-world datasets demonstrate the effectiveness of our proposed method. The code and data are available at https://github.com/Split-GNN/SplitGNN.


  • Open Access

    Ensemble Learning for Threat Classification in Network Intrusion Detection on a Security Monitoring System for Renewable Energy

    by Hsiao-Chung Lin, Ping Wang, Kuo-Ming Chao, Wen-Hui Lin, Zong-Yu Yang

    Most approaches for detecting network attacks involve threat analyses to match the attack to potential malicious profiles using behavioral analysis techniques in conjunction with packet collection, filtering, and feature comparison. Experts in information security are often required to study these threats, and judging new types of threats accurately in real time is often impossible. Detecting legitimate or malicious connections using protocol analysis is difficult; therefore, machine learning-based function modules can be added to intrusion detection systems to assist experts in accurately judging threat categories by analyzing the threat and learning its characteristics. In this paper, an ensemble learning scheme based on a revised random forest algorithm is proposed for a security monitoring system in the domain of renewable energy to categorize network threats in a network intrusion detection system. To reduce classification error for minority classes of experimental data in model training, the synthetic minority oversampling technique scheme (SMOTE) was formulated to re-balance the original data sets by altering the number of data points for minority class to imbue the experimental data set. The classification performance of the proposed classifier in threat classification when the data set is unbalanced was experimentally verified in terms of accuracy, precision, recall, and F1-score on the UNSW-NB15 and CSE-CIC-IDS 2018 data sets. A cross-validation scheme featuring support vector machines was used to compare classification accuracies.


  • Open Access

    Wind Power Forecasting with Deep Learning Networks: Time-Series Forecasting

    by Wen-Hui Lin, Ping Wang, Kuo-Ming Chao, Hsiao-Chung Lin, Zong-Yu Yang, Yu-Huang Lai

    Studies have demonstrated that changes in the climate affect wind power forecasting under different weather conditions. Theoretically, accurate prediction of both wind power output and weather changes using statistics-based prediction models is difficult. In practice, traditional machine learning models can perform long-term wind power forecasting with a mean absolute percentage error (MAPE) of 10% to 17%, which does not meet the engineering requirements for our renewable energy project. Deep learning networks (DLNs) have been employed to obtain the correlations between meteorological features and power generation using a multilayer neural convolutional architecture with gradient descent algorithms to minimize estimation errors. This has wide applicability to the field of wind power forecasting. Therefore, this study aimed at the long-term (24–72-h ahead) prediction of wind power with an MAPE of less than 10% by using the Temporal Convolutional Network (TCN) algorithm of DLNs. In our experiment, we performed TCN model pretraining using historical weather data and the power generation outputs of a wind turbine from a Scada wind power plant in Turkey. The experimental results indicated an MAPE of 5.13% for 72-h wind power prediction, which is adequate within the constraints of our project. Finally, we compared the performance of four DLN-based prediction models for power forecasting, namely, the TCN, long short-term memory (LSTM), recurrent neural network (RNN), and gated recurrence unit (GRU) models. We validated that the TCN outperforms the other three models for wind power prediction in terms of data input volume, stability of error reduction, and forecast accuracy.


  • From Music Information Retrieval to Stock Market Analysis: Theoretical Discussion on Feature Extraction Transfer

    by Hanchao Li, Xiang Fei, Ming Yang, Kuo-Ming Chao, Chaobo He

    Finding similar objects and patterns based on the similarity score is one of the fundamental and useful tasks in Data Mining. Different applications may introduce different features that need to be extract and analyzed. However, if two applications share some similar core concepts, it is possible to transfer some features that will be beneficial to transfer learning. Thus, this paper uses some features from Music Information Retrieval and Stock Market Analysis to theoretically illustrate the possibility of Feature Extraction Transfer. We use a 3-tuple or 6-tuple vector to record the music fundamental melody whereas a 5-tuple vector to record the daily behavior of the stock market from the candlestick chart. Hence, the flow of one music melody and the flow of one stock market can be treat as a time series vector sequence. Using this linkage, we have computed some feature exaction from Music Information Retrieval onto Stock Market Analysis and obtained some positive results. For example, the similarity between Activision Blizzard Inc and Zynga Inc have achieved a similarity score of 0.6250. Moreover, these positive results gave some ideas on implementing a self-supervised learning based system to manage your stock market and the potential of implementing a transfer learning between these two applications.


  • Open Access

    Identifying the Attack Sources of Botnets for a Renewable Energy Management System by Using a Revised Locust Swarm Optimisation Scheme

    by Hsiao-Chung Lin, Ping Wang, Wen-Hui Lin, Kuo-Ming Chao, Zong-Yu Yang

    Distributed denial of service (DDoS) attacks often use botnets to generate a high volume of packets and adopt controlled zombies for flooding a victim’s network over the Internet. Analysing the multiple sources of DDoS attacks typically involves reconstructing attack paths between the victim and attackers by using Internet protocol traceback (IPTBK) schemes. In general, traditional route-searching algorithms, such as particle swarm optimisation (PSO), have a high convergence speed for IPTBK, but easily fall into the local optima. This paper proposes an IPTBK analysis scheme for multimodal optimisation problems by applying a revised locust swarm optimisation (LSO) algorithm to the reconstructed attack path in order to identify the most probable attack paths. For evaluating the effectiveness of the DDoS control centres, networks with a topology size of 32 and 64 nodes were simulated using the ns-3 tool. The average accuracy of the LS-PSO algorithm reached 97.06 for the effects of dynamic traffic in two experimental networks (number of nodes = 32 and 64). Compared with traditional PSO algorithms, the revised LSO algorithm exhibited a superior searching performance in multimodal optimisation problems and increased the accuracy in traceability analysis for IPTBK problems.


  • Open Access

    Feature Super-Resolution Based Facial Expression Recognition for Multi-scale Low-Resolution Faces

    by Wei Jing, Feng Tian, Jizhong Zhang, Kuo-Ming Chao, Zhenxin Hong, Xu Liu

    Facial Expressions Recognition(FER) on low-resolution images is necessary for applications like group expression recognition in crowd scenarios(station, classroom etc.). Classifying a small size facial image into the right expression category is still a challenging task. The main cause of this problem is the loss of discriminative feature due to reduced resolution. Super-resolution method is often used to enhance low-resolution images, but the performance on FER task is limited when on images of very low resolution. In this work, inspired by feature super-resolution methods for object detection, we proposed a novel generative adversary network-based feature level super-resolution method for robust facial expression recognition(FSR-FER). In particular, a pre-trained FER model was employed as feature extractor, and a generator network G and a discriminator network D are trained with features extracted from images of low resolution and original high resolution. Generator network G tries to transform features of low-resolution images to more discriminative ones by making them closer to the ones of corresponding high-resolution images. For better classification performance, we also proposed an effective classification-aware loss re-weighting strategy based on the classification probability calculated by a fixed FER model to make our model focus more on samples that are easily misclassified. Experiment results on Real-World Affective Faces (RAF) Database demonstrate that our method achieves satisfying results on various down-sample factors with a single model and has better performance on low-resolution images compared with methods using image super-resolution and expression recognition separately.

  • Open Access

    New Technologies and the Impact on Personality Rights in Brazil

    by Marcelo Negri Soares, Marcos Eduardo Kauffman, Kuo-Ming Chao, Maktoba Omar Saad

    As technology continues to evolve at an exponentially increasing pace, it transforms our lives and societies, thus shaping our perceptions of reality with high speed and impacting the relationship between the individual and the society, including businesses and, as a result, the legal system. The young area of law is trying to explore the effects of new technologies in our relationships with it, as well as identify the best use of new technologies to reduce the gap among new technology, new societal behaviors and various legal systems. The purpose of this paper is to examine the current uses of wearable technologies in Brazil and the legal issues emerging from the various uses of these technologies and their impact on personality rights. So, to what extent do the Brazilian users of emerging technologies appreciate the terms and conditions agreed by themselves and their impact on personality rights? The authors used empirical quantitative data from a cross-section of Brazilian users to explore the level of awareness in regards to the terms and conditions associated with the use of emerging technologies and the impact on their personality rights. The authors found that the large majority of these users of technology are unaware of the adverse impact of the agreed terms and conditions on their personality rights. Furthermore, they are also unaware of the basics of how the technology operates and therefore are unable to enforce their rights. The research is based on data collected by using only one survey with a sample of 500 students from three universities in three Brazilian States with an age range between 18 and 40 years old. This paper extends the previous research on the impact of emerging technologies on personality rights and demonstrates with empirical data that there is a serious risk of erosion of such rights. Furthermore, this research provides a unique insight into the users of emerging technologies in the emerging Brazilian market and the impact on the Brazilian legal system.