This page has only limited features, please log in for full access.

Prof. Rung-Ching Chen
The department of Information Management, Chaoyang University of Technology, Taiwan

Basic Info


Research Keywords & Expertise

0 Network Technology
0 Applications of artificial intelligence
0 Domain ontology
0 Pattern recognition and knowledge engineering
0 IoT and data analysis

Fingerprints

Domain ontology
Pattern recognition and knowledge engineering
IoT and data analysis

Honors and Awards

The user has no records in this section


Career Timeline

The user has no records in this section.


Short Biography

Rung-Ching Chen received a B.S. from the Department of Electrical Engineering, and an M. S. from the Institute of Computer Engineering, both from National Taiwan University of Science and Technology, Taipei, Taiwan. He received his Ph.D. from the Department of Applied Mathematics in computer science, National Chung Hsing University in 1998. Further, He is now a distinguished professor in the Department of Information Management, Chaoyang University of Technology, Taichung, Taiwan. Also, His research concerns including network technology, pattern recognition, knowledge engineering, the Internet of Things, data analysis, and Artificial Intelligence.

Following
Followers
Co Authors
The list of users this user is following is empty.
Following: 0 users

Feed

Conference paper
Published: 29 July 2021 in Communications in Computer and Information Science
Reads 0
Downloads 0

The online P2P platform’s major advantage is that people can borrow or lend money free of intermediary interference. Prediction of the credit risk by the platform should ensure the borrowed money’s repayment. This research used Random Forest (RF) in comparison with other machine learning (ML) techniques like Logistic Regression, K-Nearest Neighbor, and Multi-Layer Perception to predict the default borrowers. Lending Club’s dataset is utilized for training and analyzing ML models. Statistical measures such as accuracy, recall, precision, F1-score, and the ROC curve are used to compare the data obtained in this study. The results were in accordance with Logistic Regression with the highest precision of 0.95 and RF with the highest AUC of 0.94. This study provides an overall understanding of different models and their prediction of default borrowers. Comparison of these models helps us to identify the most suitable model for the P2P platform.

ACS Style

Li-Hua Li; Alok Kumar Sharma; Ramli Ahmad; Rung-Ching Chen. Predicting the Default Borrowers in P2P Platform Using Machine Learning Models. Communications in Computer and Information Science 2021, 267 -281.

AMA Style

Li-Hua Li, Alok Kumar Sharma, Ramli Ahmad, Rung-Ching Chen. Predicting the Default Borrowers in P2P Platform Using Machine Learning Models. Communications in Computer and Information Science. 2021; ():267-281.

Chicago/Turabian Style

Li-Hua Li; Alok Kumar Sharma; Ramli Ahmad; Rung-Ching Chen. 2021. "Predicting the Default Borrowers in P2P Platform Using Machine Learning Models." Communications in Computer and Information Science , no. : 267-281.

Journal article
Published: 28 June 2021 in Symmetry
Reads 0
Downloads 0

Design: At the heart of time series forecasting, if nonlinear and nonstationary data are analyzed using traditional time series, the results will be biased. At the same time, if just using machine learning without any consideration given to input from traditional time series, not much information can be obtained from the results because the machine learning model is a black box. Purpose: In order to better study time series forecasting, we extend the combination of traditional time series and machine learning and propose a hybrid cascade neural network considering a metaheuristic optimization genetic algorithm in space–time forecasting. Finding: To further show the utility of the cascade neural network genetic algorithm, we use various scenarios for training and testing while also extending simulations by considering the activation functions SoftMax, radbas, logsig, and tribas on space–time forecasting of pollution data. During the simulation, we perform numerical metric evaluations using the root-mean-square error (RMSE), mean absolute error (MAE), and symmetric mean absolute percentage error (sMAPE) to demonstrate that our models provide high accuracy and speed up time-lapse computing.

ACS Style

Rezzy Caraka; Hasbi Yasin; Rung-Ching Chen; Noor Goldameir; Budi Supatmanto; Toni Toharudin; Mohammad Basyuni; Prana Gio; Bens Pardamean. Evolving Hybrid Cascade Neural Network Genetic Algorithm Space–Time Forecasting. Symmetry 2021, 13, 1158 .

AMA Style

Rezzy Caraka, Hasbi Yasin, Rung-Ching Chen, Noor Goldameir, Budi Supatmanto, Toni Toharudin, Mohammad Basyuni, Prana Gio, Bens Pardamean. Evolving Hybrid Cascade Neural Network Genetic Algorithm Space–Time Forecasting. Symmetry. 2021; 13 (7):1158.

Chicago/Turabian Style

Rezzy Caraka; Hasbi Yasin; Rung-Ching Chen; Noor Goldameir; Budi Supatmanto; Toni Toharudin; Mohammad Basyuni; Prana Gio; Bens Pardamean. 2021. "Evolving Hybrid Cascade Neural Network Genetic Algorithm Space–Time Forecasting." Symmetry 13, no. 7: 1158.

Communication
Published: 25 May 2021 in Sustainability
Reads 0
Downloads 0

Background and objectives: The impacts of COVID-19 are like two sides of one coin. During 2020, there were many research papers that proved our environmental and climate conditions were improving due to lockdown or large-scale restriction regulations. In contrast, the economic conditions deteriorated due to disruption in industry business activities and most people stayed at home and worked from home, which probably reduced the noise pollution. Methods: To assess whether there were differences in noise pollution before and during COVID-19. In this paper, we use various statistical methods following odds ratios, Wilcoxon and Fisher’s tests and Bayesian Markov chain Monte Carlo (MCMC) with various comparisons of prior selection. The outcome of interest for a parameter in Bayesian inference is complete posterior distribution. Roughly, the mean of the posterior will be clear with point approximation. That being said, the median is an available choice. Findings: To make the Bayesian MCMC work, we ran the sampling from the conditional posterior distributions. It is straightforward to draw random samples from these distributions if they have regular shapes using MCMC. The case of over-standard noise per time frame, number of noise petition cases, number of industry petition cases, number of motorcycles, number of cars and density of vehicles are significant at α = 5%. In line with this, we prove that there were differences of noise pollution before and during COVID-19 in Taiwan. Meanwhile, the decreased noise pollution in Taiwan can improve quality of life.

ACS Style

Rezzy Caraka; Yusra Yusra; Toni Toharudin; Rung-Ching Chen; Mohammad Basyuni; Vilzati Juned; Prana Gio; Bens Pardamean. Did Noise Pollution Really Improve during COVID-19? Evidence from Taiwan. Sustainability 2021, 13, 5946 .

AMA Style

Rezzy Caraka, Yusra Yusra, Toni Toharudin, Rung-Ching Chen, Mohammad Basyuni, Vilzati Juned, Prana Gio, Bens Pardamean. Did Noise Pollution Really Improve during COVID-19? Evidence from Taiwan. Sustainability. 2021; 13 (11):5946.

Chicago/Turabian Style

Rezzy Caraka; Yusra Yusra; Toni Toharudin; Rung-Ching Chen; Mohammad Basyuni; Vilzati Juned; Prana Gio; Bens Pardamean. 2021. "Did Noise Pollution Really Improve during COVID-19? Evidence from Taiwan." Sustainability 13, no. 11: 5946.

Journal article
Published: 24 April 2021 in Neural Computing and Applications
Reads 0
Downloads 0

Traffic sign detection and recognition perform a vital function in real-world driver guidance applications, including driver assistance systems. Research into vision-based traffic sign detection (TSD) and traffic sign recognition (TSR) has gained considerable attention in the scientific community, led mainly by three variables: identification, monitoring, and classification. In addition, TSR provides valuable details and alerts for smart cars including advanced driving assistance (ADAS) and cooperative intelligent transport systems (CITS). Our work will generate high-quality synthetic prohibitory sign images using deep convolutional generative adversarial networks (DCGAN). This paper analyzes and discusses CNN models incorporating different backbone architectures and feature extractors, focusing on Resnet 50 and Densenet for object detection. Assessment of the models provides important information, including mean average accuracy (mAP), workspace capacity, detection period, and the amount of billion floating-point operations (BFLOPS). The maximum average accuracy is 92% (Densenet DCGAN), led by 91% (Resnet 50 DCGAN), 88% (Densenet), and 63% (Resnet 50). We find when using the original image and a synthetic image, accuracy increases, while detection time falls. Our findings show that combining original images and synthetic images in the dataset for training can improve intersection over union (IoU) and traffic sign recognition performance.

ACS Style

Christine Dewi; Rung-Ching Chen; Yan-Ting Liu; Shao-Kuo Tai. Synthetic Data generation using DCGAN for improved traffic sign recognition. Neural Computing and Applications 2021, 1 -16.

AMA Style

Christine Dewi, Rung-Ching Chen, Yan-Ting Liu, Shao-Kuo Tai. Synthetic Data generation using DCGAN for improved traffic sign recognition. Neural Computing and Applications. 2021; ():1-16.

Chicago/Turabian Style

Christine Dewi; Rung-Ching Chen; Yan-Ting Liu; Shao-Kuo Tai. 2021. "Synthetic Data generation using DCGAN for improved traffic sign recognition." Neural Computing and Applications , no. : 1-16.

Journal article
Published: 12 April 2021 in Symmetry
Reads 0
Downloads 0

Design: Health issues throughout the sustainable development goals have also been integrated into one ultimate goal, which helps to ensure a healthy lifestyle as well as enhances well-being for any and all human beings of all social level. Meanwhile, regarding the clime change, we may take urgent action to its impacts. Purpose: Nowadays, climate change makes it much more difficult to control the pattern of diseases transmitted and sometimes hard to prevent. In line with this, Centres for Disease Control (CDC) Taiwan grouped the spread of disease through its source in the first six main groups. Those are food or waterborne, airborne or droplet, vector-borne, sexually transmitted or blood-borne, contact transmission, and miscellaneous. According to this, academics, government, and the private sector should work together and collaborate to maintain the health issue. This article examines and connects the climate and communicable aspects towards Penta-Helix in Taiwan. Finding: In summary, we have been addressing the knowledge center on the number of private companies throughout the health care sector, the number of healthcare facilities, and the education institutions widely recognized as Penta Helix. In addition, we used hierarchical likelihood structural equation modeling (HSEMs). All the relationship variables among climate, communicable disease, and Penta Helix can be interpreted through the latent variables with GoF 79.24%.

ACS Style

Rezzy Caraka; Maengseok Noh; Rung-Ching Chen; Youngjo Lee; Prana Gio; Bens Pardamean. Connecting Climate and Communicable Disease to Penta Helix Using Hierarchical Likelihood Structural Equation Modelling. Symmetry 2021, 13, 657 .

AMA Style

Rezzy Caraka, Maengseok Noh, Rung-Ching Chen, Youngjo Lee, Prana Gio, Bens Pardamean. Connecting Climate and Communicable Disease to Penta Helix Using Hierarchical Likelihood Structural Equation Modelling. Symmetry. 2021; 13 (4):657.

Chicago/Turabian Style

Rezzy Caraka; Maengseok Noh; Rung-Ching Chen; Youngjo Lee; Prana Gio; Bens Pardamean. 2021. "Connecting Climate and Communicable Disease to Penta Helix Using Hierarchical Likelihood Structural Equation Modelling." Symmetry 13, no. 4: 657.

Conference paper
Published: 05 April 2021 in Transactions on Petri Nets and Other Models of Concurrency XV
Reads 0
Downloads 0

Recently, Convolutional neural networks (CNN) with properly annotated training data and results will obtain the best traffic sign detection (TSD) and traffic sign recognition (TSR). The efficiency of the whole system depends on the data collection, based on neural networks. The traffic sign datasets in most countries around the world are therefore difficult to identify because they are so different from one to others. To solve this issue, we need to generate a synthetic image to enlarge our dataset. We employ Wasserstein generative adversarial networks (Wasserstein GAN, WGAN) to synthesize realistic and various added training images to supply the data deficiency in the original image distribution. This research explores primarily how the WGAN images with different parameters are generated in terms of consistency. For training, we use a real image with a different number and scale. Moreover, the Image quality was measured using the Structural Similarity Index (SSIM) and the Mean Square Error (MSE). The SSIM values between images and their respective actual images were calculated in our work. The images generated exhibit high similarity to the original image when using more training images. Our experiment results find the most leading SSIM values reached when using 200 total images as input, images size 32 × 32, and epoch 2000.

ACS Style

Christine Dewi; Rung-Ching Chen; Yan-Ting Liu. Wasserstein Generative Adversarial Networks for Realistic Traffic Sign Image Generation. Transactions on Petri Nets and Other Models of Concurrency XV 2021, 479 -493.

AMA Style

Christine Dewi, Rung-Ching Chen, Yan-Ting Liu. Wasserstein Generative Adversarial Networks for Realistic Traffic Sign Image Generation. Transactions on Petri Nets and Other Models of Concurrency XV. 2021; ():479-493.

Chicago/Turabian Style

Christine Dewi; Rung-Ching Chen; Yan-Ting Liu. 2021. "Wasserstein Generative Adversarial Networks for Realistic Traffic Sign Image Generation." Transactions on Petri Nets and Other Models of Concurrency XV , no. : 479-493.

Journal article
Published: 24 March 2021 in Applied Sciences
Reads 0
Downloads 0

A synthetic image is a critical issue for computer vision. Traffic sign images synthesized from standard models are commonly used to build computer recognition algorithms for acquiring more knowledge on various and low-cost research issues. Convolutional Neural Network (CNN) achieves excellent detection and recognition of traffic signs with sufficient annotated training data. The consistency of the entire vision system is dependent on neural networks. However, locating traffic sign datasets from most countries in the world is complicated. This work uses various generative adversarial networks (GAN) models to construct intricate images, such as Least Squares Generative Adversarial Networks (LSGAN), Deep Convolutional Generative Adversarial Networks (DCGAN), and Wasserstein Generative Adversarial Networks (WGAN). This paper also discusses, in particular, the quality of the images produced by various GANs with different parameters. For processing, we use a picture with a specific number and scale. The Structural Similarity Index (SSIM) and Mean Squared Error (MSE) will be used to measure image consistency. Between the generated image and the corresponding real image, the SSIM values will be compared. As a result, the images display a strong similarity to the real image when using more training images. LSGAN outperformed other GAN models in the experiment with maximum SSIM values achieved using 200 images as inputs, 2000 epochs, and size 32 × 32.

ACS Style

Christine Dewi; Rung-Ching Chen; Yan-Ting Liu; Hui Yu. Various Generative Adversarial Networks Model for Synthetic Prohibitory Sign Image Generation. Applied Sciences 2021, 11, 2913 .

AMA Style

Christine Dewi, Rung-Ching Chen, Yan-Ting Liu, Hui Yu. Various Generative Adversarial Networks Model for Synthetic Prohibitory Sign Image Generation. Applied Sciences. 2021; 11 (7):2913.

Chicago/Turabian Style

Christine Dewi; Rung-Ching Chen; Yan-Ting Liu; Hui Yu. 2021. "Various Generative Adversarial Networks Model for Synthetic Prohibitory Sign Image Generation." Applied Sciences 11, no. 7: 2913.

Journal article
Published: 19 February 2021 in Procedia Computer Science
Reads 0
Downloads 0

Global warming arising from climate change can increase the spread of deadly diseases. Effort is needed to develop a set of policies for the government to stem or reduce health risks from global warming. The purpose of this paper is to examine more detail and comprehensively about the relationship among climate and event disease count in Taiwan using the partial least square latent regression model. The results obtained that of the 17 types of diseases in Taiwan, that has the most significant loading factor is Amoebiasis, Malaria and Chikungunya. At the same time, climate variables that have the biggest most significant factor are Number day with max temp more than 30, Number day Temp more than 25, and Rainfall PH. Cronbach’s Alpha infectious disease 0.9696 and climate 0.2813. At the same time, the value of Dillon Goldstein’s rho infectious disease 0.974 and climate 0.6404, respectively.

ACS Style

Rezzy Eko Caraka; Rung Ching Chen; Youngjo Lee; Prana Ugiana Gio; Arif Budiarto; Bens Pardamean. Latent Regression and Ordination Risk of Infectious Disease and Climate. Procedia Computer Science 2021, 179, 25 -32.

AMA Style

Rezzy Eko Caraka, Rung Ching Chen, Youngjo Lee, Prana Ugiana Gio, Arif Budiarto, Bens Pardamean. Latent Regression and Ordination Risk of Infectious Disease and Climate. Procedia Computer Science. 2021; 179 ():25-32.

Chicago/Turabian Style

Rezzy Eko Caraka; Rung Ching Chen; Youngjo Lee; Prana Ugiana Gio; Arif Budiarto; Bens Pardamean. 2021. "Latent Regression and Ordination Risk of Infectious Disease and Climate." Procedia Computer Science 179, no. : 25-32.

Article
Published: 19 January 2021 in Communications in Statistics - Simulation and Computation
Reads 0
Downloads 0

One of information needed in weather forecast is air temperature. This value might change any time. Prediction of air temperature is very valuable for some communities and occasions. Therefore, high accuracy prediction is needed. Since the information about air temperature might vary over time, it is necessary to implement methods that can adapt to this situation. The use of neural network methods such as long short term memory (LSTM), nowadays, becomes popular in facing big data including unexpected fluctuation on the data. Thus, the model is used in this paper which provides long series data on air temperature. In addition, recently, Facebook announced an accurate method of forecasting, called Prophet model’s, for data which have trend, seasonality, holidays, missing data, not to mention outliers. Hence, the forecast of five-year daily air temperatures in Bandung on this paper is modeled by LSTM and Facebook Prophet. The result shows that, for minimum temperature, Prophet performs better on maximum air temperature while LSTM performs better on minimum air temperature. However, the difference on the value of RMSE is not too large significant.

ACS Style

Toni Toharudin; Resa Septiani Pontoh; Rezzy Eko Caraka; Solichatus Zahroh; Youngjo Lee; Rung Ching Chen. Employing long short-term memory and Facebook prophet model in air temperature forecasting. Communications in Statistics - Simulation and Computation 2021, 1 -24.

AMA Style

Toni Toharudin, Resa Septiani Pontoh, Rezzy Eko Caraka, Solichatus Zahroh, Youngjo Lee, Rung Ching Chen. Employing long short-term memory and Facebook prophet model in air temperature forecasting. Communications in Statistics - Simulation and Computation. 2021; ():1-24.

Chicago/Turabian Style

Toni Toharudin; Resa Septiani Pontoh; Rezzy Eko Caraka; Solichatus Zahroh; Youngjo Lee; Rung Ching Chen. 2021. "Employing long short-term memory and Facebook prophet model in air temperature forecasting." Communications in Statistics - Simulation and Computation , no. : 1-24.

Journal article
Published: 26 October 2020 in IEEE Access
Reads 0
Downloads 0

The H-likelihood method proposed by Lee and Nelder (1996) is extensively used in a wide range of data. In terms of direction, repetitive measured data within classification can be examined employing hierarchical generalized linear models (HGLMs). Whether we are concerned in multiple endpoints which are correlated, instead Multivariate Double Hierarchical Generalized Linear Models (DHGLM) can be taken into consideration. This article addresses the implementation of this principle to vector selection and support machines. Based on the analysis with the fish morphology class Sardinella lemuru ( Bali sardinella ) and setting the best epsilon 0.7 cost 4 parameter reaching best performance: 0.2327401. Predictive value of fish sex was calculated 0.997319 and Region under the curve: 0.8967. At the same time, we extend the large-scale case studies for stress testing of the SVM method by using three datasets from UCI machine learning repository including the bank marketing dataset, the car evaluation database and human activity recognition using smartphones dataset. In a nutshell by employing SVM-DHGLM increased the accuracy, precision, recall, for feature selection and classification. Long story short, the $H$ -likelihood provides an excellent and usable structure for statistical inference of the unobservable general deterministic model, while preserving the advantages of the original probability structure for fixed parameters. We presume that more new groups of models will be created and that the $H$ -likelihood will be commonly used for their inferences and the application in big data and machine learning.

ACS Style

Rezzy Eko Caraka; Youngjo Lee; Rung Ching Chen; Toni Toharudin. Using Hierarchical Likelihood towards Support Vector Machine: Theory and Its Application. IEEE Access 2020, 8, 1 -1.

AMA Style

Rezzy Eko Caraka, Youngjo Lee, Rung Ching Chen, Toni Toharudin. Using Hierarchical Likelihood towards Support Vector Machine: Theory and Its Application. IEEE Access. 2020; 8 ():1-1.

Chicago/Turabian Style

Rezzy Eko Caraka; Youngjo Lee; Rung Ching Chen; Toni Toharudin. 2020. "Using Hierarchical Likelihood towards Support Vector Machine: Theory and Its Application." IEEE Access 8, no. : 1-1.

Journal article
Published: 07 October 2020 in Applied Sciences
Reads 0
Downloads 0

In the area of traffic sign detection (TSD) methods, deep learning has been implemented and achieves outstanding performance. The detection of a traffic sign, as it has a dual function in monitoring and directing the driver, is a big concern for driver support systems. A core feature of autonomous vehicle systems is the identification of the traffic sign. This article focuses on the prohibitive sign. The objective is to detect in real-time and reduce processing time considerably. In this study, we implement the spatial pyramid pooling (SPP) principle to boost Yolo V3's backbone network for the extraction of functionality. Our work uses SPP for more comprehensive learning of multiscale object features. Then, perform a comparative investigation of Yolo V3 and Yolo V3 SPP across various scales to recognize the prohibitory sign. Comparisons with Yolo V3 SPP models reveal that their mean average precision (mAP) is higher than Yolo V3. Furthermore, the test accuracy findings indicate that the Yolo V3 SPP model performs better than Yolo V3 for different sizes.

ACS Style

Shao-Kuo Tai; Christine Dewi; Rung-Ching Chen; Yan-Ting Liu; Xiaoyi Jiang; Hui Yu. Deep Learning for Traffic Sign Recognition Based on Spatial Pyramid Pooling with Scale Analysis. Applied Sciences 2020, 10, 6997 .

AMA Style

Shao-Kuo Tai, Christine Dewi, Rung-Ching Chen, Yan-Ting Liu, Xiaoyi Jiang, Hui Yu. Deep Learning for Traffic Sign Recognition Based on Spatial Pyramid Pooling with Scale Analysis. Applied Sciences. 2020; 10 (19):6997.

Chicago/Turabian Style

Shao-Kuo Tai; Christine Dewi; Rung-Ching Chen; Yan-Ting Liu; Xiaoyi Jiang; Hui Yu. 2020. "Deep Learning for Traffic Sign Recognition Based on Spatial Pyramid Pooling with Scale Analysis." Applied Sciences 10, no. 19: 6997.

Article
Published: 29 August 2020 in Multimedia Tools and Applications
Reads 0
Downloads 0

Traffic sign recognition is meaningful for real-world applications such as self-sufficient driving, traffic surveillance, and driver safety. However, traffic sign recognition is a hard problem because different sizes, illuminations, and noises affect the sign detection and recognition. This work recognizes Taiwan’s prohibitory signs using deep learning methods. First, we develop a traffic sign database since there is no such kind of database available in Taiwan. Next, we adopt three different You Only Look Once (Yolo) networks (Yolo A, Yolo B, and Yolo C) and three various Yolo V3 SPP networks (Yolo D, Yolo E, and Yolo F) for prohibitory sign recognition. Finally, we conduct the comparative experiment of Yolo V3 and Yolo V3 SPP with different weights provided by the darknet framework (the best weight, the final weight, and the last weight). Experimental results show that the mean average precision (mAP) observation of all models that the Yolo V3 SPP is better than other models. Yolo D took the optimum average accuracy at 99.0%, followed by Yolo E and Yolo F 98.9%. The accuracy of Yolo V3 SPP is growing within the detection time, but it needs more time to identify the sign.

ACS Style

Christine Dewi; Rung-Ching Chen; Hui Yu. Weight analysis for various prohibitory sign detection and recognition using deep learning. Multimedia Tools and Applications 2020, 79, 32897 -32915.

AMA Style

Christine Dewi, Rung-Ching Chen, Hui Yu. Weight analysis for various prohibitory sign detection and recognition using deep learning. Multimedia Tools and Applications. 2020; 79 (43-44):32897-32915.

Chicago/Turabian Style

Christine Dewi; Rung-Ching Chen; Hui Yu. 2020. "Weight analysis for various prohibitory sign detection and recognition using deep learning." Multimedia Tools and Applications 79, no. 43-44: 32897-32915.

Journal article
Published: 23 July 2020 in Journal of Big Data
Reads 0
Downloads 0

Feature selection becomes prominent, especially in the data sets with many variables and features. It will eliminate unimportant variables and improve the accuracy as well as the performance of classification. Random Forest has emerged as a quite useful algorithm that can handle the feature selection issue even with a higher number of variables. In this paper, we use three popular datasets with a higher number of variables (Bank Marketing, Car Evaluation Database, Human Activity Recognition Using Smartphones) to conduct the experiment. There are four main reasons why feature selection is essential. First, to simplify the model by reducing the number of parameters, next to decrease the training time, to reduce overfilling by enhancing generalization, and to avoid the curse of dimensionality. Besides, we evaluate and compare each accuracy and performance of the classification model, such as Random Forest (RF), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), and Linear Discriminant Analysis (LDA). The highest accuracy of the model is the best classifier. Practically, this paper adopts Random Forest to select the important feature in classification. Our experiments clearly show the comparative study of the RF algorithm from different perspectives. Furthermore, we compare the result of the dataset with and without essential features selection by RF methods varImp(), Boruta, and Recursive Feature Elimination (RFE) to get the best percentage accuracy and kappa. Experimental results demonstrate that Random Forest achieves a better performance in all experiment groups.

ACS Style

Rung-Ching Chen; Christine Dewi; Su-Wen Huang; Rezzy Eko Caraka. Selecting critical features for data classification based on machine learning methods. Journal of Big Data 2020, 7, 1 -26.

AMA Style

Rung-Ching Chen, Christine Dewi, Su-Wen Huang, Rezzy Eko Caraka. Selecting critical features for data classification based on machine learning methods. Journal of Big Data. 2020; 7 (1):1-26.

Chicago/Turabian Style

Rung-Ching Chen; Christine Dewi; Su-Wen Huang; Rezzy Eko Caraka. 2020. "Selecting critical features for data classification based on machine learning methods." Journal of Big Data 7, no. 1: 1-26.

Journal article
Published: 09 July 2020 in IEEE Access
Reads 0
Downloads 0

Virtual Reality (VR) research has been widely applied in many fields. VR promises to deliver the experience that is beyond the user’s imagination. One of the advantages of VR is the feeling it gives of being there. VR can provide experiences impossible in the real world, such as flying, diving in deep water, exploring outer space, or living with dinosaurs. Despite the improvements in the software and hardware, the problem of motion sickness remains. We implement a deep learning model to train and predict motion sickness. A questionnaire is a well-known method to measure motion sickness. The weakness of the questionnaire is the measurement carried out after the user experiences motion sickness symptoms. By using the deep learning and EEG, the system will learn and classify motion sickness. The system learns the user’s EEG pattern when they begin to feel the sickness symptoms. The system will be trained using deep learning to identify the sickness patterns in the future. By the EEG patterns, the system can predict the sickness symptoms before it occurs. Our model outperforms traditional models in loss values, accuracy, and F-measure metrics in Roller Coaster. With other datasets, our model also performs well. Our model can achieve 82.83% accuracy from the dataset. We also found that the time steps to predict motion sickness during 5 minute periods is a suitable configuration.

ACS Style

Chung-Yen Liao; Shao-Kuo Tai; Rung-Ching Chen; Hendry Hendry. Using EEG and Deep Learning to Predict Motion Sickness Under Wearing a Virtual Reality Device. IEEE Access 2020, 8, 126784 -126796.

AMA Style

Chung-Yen Liao, Shao-Kuo Tai, Rung-Ching Chen, Hendry Hendry. Using EEG and Deep Learning to Predict Motion Sickness Under Wearing a Virtual Reality Device. IEEE Access. 2020; 8 ():126784-126796.

Chicago/Turabian Style

Chung-Yen Liao; Shao-Kuo Tai; Rung-Ching Chen; Hendry Hendry. 2020. "Using EEG and Deep Learning to Predict Motion Sickness Under Wearing a Virtual Reality Device." IEEE Access 8, no. : 126784-126796.

Journal article
Published: 27 May 2020 in Electronics
Reads 0
Downloads 0

Traffic sign recognition (TSR) is a noteworthy issue for real-world applications such as systems for autonomous driving as it has the main role in guiding the driver. This paper focuses on Taiwan’s prohibitory sign due to the lack of a database or research system for Taiwan’s traffic sign recognition. This paper investigates the state-of-the-art of various object detection systems (Yolo V3, Resnet 50, Densenet, and Tiny Yolo V3) combined with spatial pyramid pooling (SPP). We adopt the concept of SPP to improve the backbone network of Yolo V3, Resnet 50, Densenet, and Tiny Yolo V3 for building feature extraction. Furthermore, we use a spatial pyramid pooling to study multi-scale object features thoroughly. The observation and evaluation of certain models include vital metrics measurements, such as the mean average precision (mAP), workspace size, detection time, intersection over union (IoU), and the number of billion floating-point operations (BFLOPS). Our findings show that Yolo V3 SPP strikes the best total BFLOPS (65.69), and mAP (98.88%). Besides, the highest average accuracy is Yolo V3 SPP at 99%, followed by Densenet SPP at 87%, Resnet 50 SPP at 70%, and Tiny Yolo V3 SPP at 50%. Hence, SPP can improve the performance of all models in the experiment.

ACS Style

Christine Dewi; Rung-Ching Chen; Shao-Kuo Tai. Evaluation of Robust Spatial Pyramid Pooling Based on Convolutional Neural Network for Traffic Sign Recognition System. Electronics 2020, 9, 889 .

AMA Style

Christine Dewi, Rung-Ching Chen, Shao-Kuo Tai. Evaluation of Robust Spatial Pyramid Pooling Based on Convolutional Neural Network for Traffic Sign Recognition System. Electronics. 2020; 9 (6):889.

Chicago/Turabian Style

Christine Dewi; Rung-Ching Chen; Shao-Kuo Tai. 2020. "Evaluation of Robust Spatial Pyramid Pooling Based on Convolutional Neural Network for Traffic Sign Recognition System." Electronics 9, no. 6: 889.

Journal article
Published: 25 April 2020 in Applied Sciences
Reads 0
Downloads 0

Metro systems play a key role in meeting urban transport demands in large cities. The close relationship between historical weather conditions and the corresponding passenger flow has been widely analyzed by researchers. However, few studies have explored the issue of how to use historical weather data to make passenger flow forecasting more accurate. To this end, an hourly metro passenger flow forecasting model using a deep long short-term memory neural network (LSTM_NN) was developed. The optimized traditional input variables, including the different temporal data and historical passenger flow data, were combined with weather variables for data modeling. A comprehensive analysis of the weather impacts on short-term metro passenger flow forecasting is discussed in this paper. The experimental results confirm that weather variables have a significant effect on passenger flow forecasting. It is interesting to find out that the previous variables of one-hour temperature and wind speed are the two most important weather variables to obtain more accurate forecasting results on rainy days at Taipei Main Station, which is a primary interchange station in Taipei. Compared to the four widely used algorithms, the deep LSTM_NN is an extremely powerful method, which has the capability of making more accurate forecasts when suitable weather variables are included.

ACS Style

Lijuan Liu; Rung-Ching Chen; Shunzhi Zhu. Impacts of Weather on Short-Term Metro Passenger Flow Forecasting Using a Deep LSTM Neural Network. Applied Sciences 2020, 10, 2962 .

AMA Style

Lijuan Liu, Rung-Ching Chen, Shunzhi Zhu. Impacts of Weather on Short-Term Metro Passenger Flow Forecasting Using a Deep LSTM Neural Network. Applied Sciences. 2020; 10 (8):2962.

Chicago/Turabian Style

Lijuan Liu; Rung-Ching Chen; Shunzhi Zhu. 2020. "Impacts of Weather on Short-Term Metro Passenger Flow Forecasting Using a Deep LSTM Neural Network." Applied Sciences 10, no. 8: 2962.

Conference paper
Published: 04 March 2020 in Automata, Languages and Programming
Reads 0
Downloads 0

Many applications for Restricted Boltzmann Machines (RBM) have been developed for a large variety of learning problems. Recent developments have demonstrated the capacity of RBM to be powerful generative models, able to extract useful features from input data or construct deep artificial neural networks. In this work, we propose a learning algorithm to find the optimal model complexity for the RBM by improving the hidden layer. We compare the classification performance of regular RBM use RBM() function, classification RBM use stackRBM() function and Deep Belief Network (DBN) use DBN() function with different hidden layer. As a result, Stacking RBM and DBN could improve our classification performance compare to regular RBM.

ACS Style

Christine Dewi; Rung-Ching Chen; Hendry; Hsiu-Te Hung. Comparative Analysis of Restricted Boltzmann Machine Models for Image Classification. Automata, Languages and Programming 2020, 285 -296.

AMA Style

Christine Dewi, Rung-Ching Chen, Hendry, Hsiu-Te Hung. Comparative Analysis of Restricted Boltzmann Machine Models for Image Classification. Automata, Languages and Programming. 2020; ():285-296.

Chicago/Turabian Style

Christine Dewi; Rung-Ching Chen; Hendry; Hsiu-Te Hung. 2020. "Comparative Analysis of Restricted Boltzmann Machine Models for Image Classification." Automata, Languages and Programming , no. : 285-296.

Journal article
Published: 06 February 2020 in Sensors
Reads 0
Downloads 0

Convolutional Neural Networks (CNNs) have become one of the state-of-the-art methods for various computer vision and pattern recognition tasks including facial affective computing. Although impressive results have been obtained in facial affective computing using CNNs, the computational complexity of CNNs has also increased significantly. This means high performance hardware is typically indispensable. Most existing CNNs are thus not generalizable enough for mobile devices, where the storage, memory and computational power are limited. In this paper, we focus on the design and implementation of CNNs on mobile devices for real-time facial affective computing tasks. We propose a light-weight CNN architecture which well balances the performance and computational complexity. The experimental results show that the proposed architecture achieves high performance while retaining the low computational complexity compared with state-of-the-art methods. We demonstrate the feasibility of a CNN architecture in terms of speed, memory and storage consumption for mobile devices by implementing a real-time facial affective computing application on an actual mobile device.

ACS Style

Yuanyuan Guo; Yifan Xia; Jing Wang; Hui Yu; Rung-Ching Chen. Real-Time Facial Affective Computing on Mobile Devices. Sensors 2020, 20, 870 .

AMA Style

Yuanyuan Guo, Yifan Xia, Jing Wang, Hui Yu, Rung-Ching Chen. Real-Time Facial Affective Computing on Mobile Devices. Sensors. 2020; 20 (3):870.

Chicago/Turabian Style

Yuanyuan Guo; Yifan Xia; Jing Wang; Hui Yu; Rung-Ching Chen. 2020. "Real-Time Facial Affective Computing on Mobile Devices." Sensors 20, no. 3: 870.

Journal article
Published: 30 October 2019 in IEEE Access
Reads 0
Downloads 0
ACS Style

Rezzy Eko Caraka; Rung Ching Chen; Toni Toharudin; Bens Pardamean; Hasbi Yasin; Shih Hung Wu. Prediction of Status Particulate Matter 2.5 Using State Markov Chain Stochastic Process and HYBRID VAR-NN-PSO. IEEE Access 2019, 7, 161654 -161665.

AMA Style

Rezzy Eko Caraka, Rung Ching Chen, Toni Toharudin, Bens Pardamean, Hasbi Yasin, Shih Hung Wu. Prediction of Status Particulate Matter 2.5 Using State Markov Chain Stochastic Process and HYBRID VAR-NN-PSO. IEEE Access. 2019; 7 ():161654-161665.

Chicago/Turabian Style

Rezzy Eko Caraka; Rung Ching Chen; Toni Toharudin; Bens Pardamean; Hasbi Yasin; Shih Hung Wu. 2019. "Prediction of Status Particulate Matter 2.5 Using State Markov Chain Stochastic Process and HYBRID VAR-NN-PSO." IEEE Access 7, no. : 161654-161665.

Journal article
Published: 31 May 2019 in IEEE Transactions on Computational Social Systems
Reads 0
Downloads 0

Deep learning is a methodology applied across many fields. User comments are important for recommender systems because they include various types of emotional information that may influence the correctness or precision of the recommendation. Improving the accuracy of user ratings from obtained feasible recommendations is essential. In this paper, we propose a deep learning model to process user comments and to generate a possible user rating for user recommendations. First, the system uses sentiment analysis to create a feature vector as the input nodes. Next, the system implements noise reduction in the data set to improve the classification of user ratings. Finally, a deep belief network and sentiment analysis (DBNSA) achieves data learning for the recommendations. The experimental results indicated that this system has better accuracy than traditional methods.

ACS Style

Rung-Ching Chen; Hendry. User Rating Classification via Deep Belief Network Learning and Sentiment Analysis. IEEE Transactions on Computational Social Systems 2019, 6, 535 -546.

AMA Style

Rung-Ching Chen, Hendry. User Rating Classification via Deep Belief Network Learning and Sentiment Analysis. IEEE Transactions on Computational Social Systems. 2019; 6 (3):535-546.

Chicago/Turabian Style

Rung-Ching Chen; Hendry. 2019. "User Rating Classification via Deep Belief Network Learning and Sentiment Analysis." IEEE Transactions on Computational Social Systems 6, no. 3: 535-546.