Journal of Intelligent & Fuzzy Systems - Volume 40, issue 4

Authors: Chen, Yenming J. | Tsai, Jinn-Tsong | Huang, Wei-Tai | Ho, Wen-Hsien

Article Type: Research Article

Abstract: The uncertainty issue in real-work optimization affects the level of optimization significantly. Because most future uncertainties cannot be foreseen in advance, the optimization must take the uncertainties as a risk in an intelligent way in the process of computation algorithm. Based on our risk-sensitive filtering algorithm, this study adopts a model-predictive control to construct a risk-averse, predictable model that can be used to regulate the level of a real-world system. Our model is intelligent in that the predictive model needs not to identify the system parameters in advance, and our algorithm will learn the parameters through data. When the real-world …system is under the disturbance of unexpected events, our model can still maintain suitable performance. Our results show that the intelligent model designed in this study can learn the system parameters in a real-world system and minimize unexpected real-world disturbances. Through the learning process, our model is robust, and the optimal performance can still be retained even the system parameters deviate from expected, e.g., material shortage in a supply chain due to earthquake. When parameter error risks occur, the control rules can still drive the overall system with a minimal performance drop. Show more

Keywords: Intelligent optimization, model-predictive control, risk-sensitive filtering, robust algorithm

DOI: 10.3233/JIFS-189608

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 4, pp. 7863-7873, 2021

Authors: Lee, Bor-Hon | Yang, Albert Jing-Fuh | Chen, Yenming J.

Article Type: Research Article

Abstract: A large categories of time series fluctuate dramatically, for example, prices of agriculture produce. Traditional methods in time series and stochastic prediction may not capture such dynamics. This paper tries to use machine learning to tune the model for a real situation by establishing a price determination mechanism on the model of stochastic automata (SA) and evolutionary game (EG). Time series volatility attributed to the chaotic process can be obtained through the learning algorithm of Markov Chain Monte Carlo (MCMC). Using machine learning through the chaotic analysis of stochastic automata and evolutionary games, we find that a more spatially aggregated …distribution (smaller entropy) leads to larger time series fluctuations, regardless of the initial distribution of crops. By integrating the factors discovered in this study, we can develop a better learning algorithm in a highly volatile time series in agriculture prices. Show more

Keywords: Distribution entropy, spatial diffusion, stochastic automata (SA), evolutionary game (EG), machine learning

DOI: 10.3233/JIFS-189609

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 4, pp. 7875-7881, 2021

Authors: Chen, Yao-Mei | Chen, Yenming J. | Tsai, Yun-Kai | Ho, Wen-Hsien | Tsai, Jinn-Tsong

Article Type: Research Article

Abstract: A multi-layer convolutional neural network (MCNN) with hyperparameter optimization (HyperMCNN) is proposed for classifying human electrocardiograms (ECGs). For performance tests of the HyperMCNN, ECG recordings for patients with cardiac arrhythmia (ARR), congestive heart failure (CHF), and normal sinus rhythm (NSR) were obtained from three PhysioNet databases: MIT-BIH Arrhythmia Database, BIDMC Congestive Heart Failure Database, and MIT-BIH Normal Sinus Rhythm Database, respectively. The MCNN hyperparameters in convolutional layers included number of filters, filter size, padding, and filter stride. The hyperparameters in max-pooling layers were pooling size and pooling stride. Gradient method was also a hyperparameter used to train the MCNN model. …Uniform experimental design approach was used to optimize the hyperparameter combination for the MCNN. In performance tests, the resulting 16-layer CNN with an appropriate hyperparameter combination (16-layer HyperMCNN) was used to distinguish among ARR, CHF, and NSR. The experimental results showed that the average correct rate and standard deviation obtained by the 16-layer HyperMCNN were superior to those obtained by a 16-layer CNN with a hyperparameter combination given by Matlab examples. Furthermore, in terms of performance in distinguishing among ARR, CHF, and NSR, the 16-layer HyperMCNN was superior to the 25-layer AlexNet, which was the neural network that had the best image identification performance in the ImageNet Large Scale Visual Recognition Challenge in 2012. Show more

Keywords: Convolutional neural network, hyperparameter, human electrocardiogram, PhysioNet, uniform experimental design approach

DOI: 10.3233/JIFS-189610

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 4, pp. 7883-7891, 2021

Authors: Chou, Fu-I | Ho, Wen-Hsien | Chen, Yenming J. | Tsai, Jinn-Tsong

Article Type: Research Article

Abstract: This study proposes a framework implementing triangular estimation for better modeling and forecasting time series. In order to improve the performance of estimation, we employ two sources of triangulation to generate a time series, which is statistically indistinguishable with the latent time series hidden in a system. Thanks to Bayesian hierarchical estimation, which is akin to deep learning but more sophisticate and longer history, the framework has been validated by a large amount of records in vegetable auctions. The hierarchical Bayesian estimation and Monte Carlo Markov Chain particle filters used in hidden Markov model are appreciated during the massive bootstrapping …of data. Our results demonstrate excellent estimation performance in discovering hidden states. Show more

Keywords: Generative estimation, time series forecasting, triangulation data assimilation

DOI: 10.3233/JIFS-189611

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 4, pp. 7893-7899, 2021

Authors: Ouyang, Chen-Sen | Chen, Yenming J. | Tsai, Jinn-Tsong | Chang, Yiu-Jen | Huang, Tian-Hsiang | Hwang, Kao-Shing | Ho, Yuan-Chih | Ho, Wen-Hsien

Article Type: Research Article

Abstract: Atrial fibrillation (AF) is a type of paroxysmal cardiac disease that presents no obvious symptoms during onset, and even the electrocardiograms (ECG) results of patients with AF appear normal under a premorbid status, rendering AF difficult to detect and diagnose. However, it can result in deterioration and increased risk of stroke if not detected and treated early. This study used the ECG database provided by the Physionet website (https://physionet.org ), filtered data, and employed parameter-extraction methods to identify parameters that signify ECG features. A total of 31 parameters were obtained, consisting of P-wave morphology parameters and heart rate variability parameters, …and the data were further examined by implementing a decision tree, of which the topmost node indicated a significant causal relationship. The experiment results verified that the P-wave morphology parameters significantly affected the ECG results of patients with AF. Show more

Keywords: Atrial fibrillation, electrocardiogram (ECG), data mining, decision tree

DOI: 10.3233/JIFS-189612

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 4, pp. 7901-7908, 2021

Authors: Ko, Joonho | Cho, Hyun Woong | Kim, Jung In | Kim, Hyunmyung | Lee, Young-Joo | Suh, Wonho

Article Type: Research Article

Abstract: Transportation system management and traveler information systems evolve with the development of data communications and intelligence of traffic simulations. Variety of roadside and mobile sensing platforms will be deployed to allow communication between vehicles with Dedicated Short Range Communications (DSRC). Traffic data received from moving vehicles will be transmitted to each individual vehicle and traffic management center to provide real time traffic information. Microscopic traffic simulation models will be used for generating intelligence from real time data in the form of traffic analysis and prediction, since they have the highest detailed level of prediction such as vehicle / driver characteristics …and have the capability to capture dynamically changing traffic conditions through the simulation. In this study, three communication methods for data communication and intelligence in traffic simulation environments are used including Ethernet, off-the-shelf wireless network, and one commercial network provider for data communication. Simulation time is measured and statistically analyzed using three different communication methods and one non-communication case. Also, traffic simulation performance is investigated to demonstrate the intelligence of traffic simulation tools in modeling traffic congestion. Show more

Keywords: Traffic simulation environments, data communication, intelligence of traffic simulation, simulation analysis, network simulation

DOI: 10.3233/JIFS-189613

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 4, pp. 7909-7916, 2021

Authors: Ko, Joonho | Cho, Hyun Woong | Kim, Jung In | Kim, Hyunmyung | Lee, Young-Joo | Suh, Wonho

Article Type: Research Article

Abstract: Traffic simulation tools are becoming more popular as complexity and intelligence are growing in transportation systems. The need for more accurate and intelligent traffic modeling is increasing rapidly as transportation systems are having more congestion problems. Although traffic simulation models have been continuously updated to represent various traffic conditions more realistically, most simulation models still have limitations in overcapacity congested traffic conditions. In traditional traffic simulation models, when there is no available space due to traffic congestion, additional traffic demand may never be allowed to enter the network. The objective of this paper is to investigate one possible method to …address the issue of unserved vehicles in overcapacity congested traffic conditions using the VISSIM trip chain. The VISSIM trip chain is used for this analysis as it has the advantage of holding a vehicle without eliminating it when traffic congestion prevents its entrance onto a network. This will allow the vehicle to enter when an acceptable gap becomes available on the entry link. To demonstrate the difference between the simulation using standard traffic input and the trip chain method, a sample congested traffic network is built and congested traffic scenarios are created. Also, simulations with different minimum space headway parameters in the priority rules are analyzed to model congested traffic conditions more realistically. This will provide the insight about the sensitivity of the model to this parameter. Based on the analysis conducted it is concluded that, with appropriate calibrations, the trip chain feature in VISSIM has the potentials to be useful in modeling overcapacity congested traffic conditions more realistically. Show more

Keywords: Traffic simulation environments, traffic congestion modeling, intelligence of traffic simulation, simulation analysis, network simulation

DOI: 10.3233/JIFS-189614

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 4, pp. 7917-7923, 2021

Authors: Chen, Joy Iong-Zong | Hengjinda, P.

Article Type: Research Article

Abstract: Smart Robot embedded with GMM-UBM (Gaussian mixture model- universal background model) based on the machine learning scheme is presented in the article. Authors have designed a smart robot for the farmer and which is designed controlled by the concept of machine learning. On the other hand, the techniques of machine learning are applied to develop a smart robot for helping farmers recognize the environment conditions, e.g . weather, and disease protection in rice or plant. The smart robot is implemented to detect and to recognize the environment conditions around a fixed area. The sensing way through vision devices, such as …camera, look like a human’s eye to distinguish various types of target. The QR code is deployed to simulate working conditions allows the robot to separate conditions and act according to conditions precisely. Besides, the smart robot is embedded with GMM-UBM algorithm for promoting the accuracy of recognition from the deployment of machine learning. The smart robot, mainly combines with AI (Artificial intelligence) techniques, consists of the following equipments: 1) a control movement subsystem, 2) a sensor control subsystem, and 3) an analysis subsystem. The researcher has determined the condition of the message options via QR code. In addition, the contents of the QR code tag will be processed a text message and saved to a memory device, once the reading is finished. The data analysis subsystem then reads the text and recommends the robot to move according to the specified conditions. The results from QR code data allow the smart robot to accurately collect many kinds of prefer data (e.g ., climate data) in the farm at the specified location. Show more

Keywords: Artificial intelligence, GMM-UBM, machine learning, smart robot, vision devices

DOI: 10.3233/JIFS-189615

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 4, pp. 7925-7937, 2021

Authors: Yu, Meng | Lu, Bao | Li, Xiong | Li, Wenfeng

Article Type: Research Article

Abstract: Online Distance teaching for multiple smart classrooms by famous teachers, as an effective solver for the problem of lack of excellent teachers, has become a new popular teaching mode. However, one of the key problems to be solved urgently for this teaching mode is how to monitor children’s class status and effectively feedback their listening standing to teachers. Installation of intelligent pressure cushion on the chair of smart classroom to monitor children’s classroom state can be a powerful way to improve teaching effectiveness for the online distance teaching mode. This paper presents a new method for monitoring children’s classroom behavior …based on intelligent cushion, which can identify basic children’s classroom behavior by classifying the original intelligent cushion pressure signal and evaluating the effectiveness of the classifier. To be concrete, the present method uses intelligent pressure cushion to collect data and denoises the original data by digital filter, and then extracts the time-domain and frequency-domain features of time-series pressure signals based on sliding time window. Finally, it uses machine learning to identify children’s status. In addition, by feature selection to reduce the data dimension, integrating different classifier to classify the extracted features, the efficiency of the present method is greatly improved. Show more

Keywords: Smart cushion, child behavior recognition, pressure sensor

DOI: 10.3233/JIFS-189616

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 4, pp. 7939-7949, 2021

Authors: Pan, Nan | Jiang, Xuemei | Pan, Dilin | Liu, Yi

Article Type: Research Article

Abstract: This article has been retracted, and the online PDF has been watermarked “RETRACTED”. The retraction notice is available at https://doi.org/10.3233/JIFS-219327 .

DOI: 10.3233/JIFS-189617

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 4, pp. 7951-7956, 2021