Journal of Intelligent & Fuzzy Systems - Volume 39, issue 3

Authors: Sun, Zhe | Zou, Jiayang | He, Defeng | Man, Zhihong | Zheng, Jinchuan

Article Type: Research Article

Abstract: Due to the complex driving conditions confronted by an autonomous vehicle, it is significant for the vehicle to possess a robust control system to achieve effective collision-avoidance performance. This paper proposes a neural network-based adaptive integral terminal sliding mode (NNAITSM) control scheme for the collision-avoidance steering control of an autonomous vehicle. In order to describe the vehicle’s lateral dynamics and path tracking characteristics, a two-degrees-of-freedom (2DOF) dynamic model and a kinematic model are adopted. Then, an NNAITSM controller is designed, where a radial basis function neural network (RBFNN) scheme is utilized to online approximate the optimal upper bound of lumped …system uncertainties such that prior knowledge about the uncertainties is not required. The stability of the control system is proved via Lyapunov, and the selection guideline of control parameters is provided. Last, Matlab-Carsim co-simulations are executed to test the performance of the designed controller under different road conditions and vehicle velocities. Simulation results show that compared with conventional sliding mode (CSM) and nonsingular terminal sliding mode (NTSM) control, the proposed NNAITSM control scheme owns evident superiority in not only higher tracking precision but also stronger robustness against various road surfaces and vehicle velocities. Show more

Keywords: Autonomous vehicle, neural networks, sliding mode control, vehicle dynamics and control

DOI: 10.3233/JIFS-200625

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 3, pp. 4689-4702, 2020

Authors: Min, Qu | Yu, Chen | Xing-Fu, Xiong | Jiang, Wu

Article Type: Research Article

Abstract: A comprehensive evaluation indicator system is the basis of car sharing systems (CSS) evaluation. The purpose of this study is to introduce the principles and methods of indicator selection for CSS, and to identify indicators for evaluating car sharing systems due to the reason that the importance of indicators can never be overestimated in CSS evaluation. A framework to identify indicators for evaluating CSS is proposed with four steps. First of all, the structure for indicator selection is established with application of AHP method. Secondly, adequacy check and redundancy check are carried out to ensure the structure is adequate and …redundant. Thirdly, underlying individual indicators are proposed according to questionnaires. Fourthly, to ensure the necessity, identification, and feasibility of indicators, we conduct N-I-F check. We carry out a case study of CSS evaluation indicators to validate the proposed framework from four dimensions: economic, environmental, systematic, and social. The proposed framework is quantitative and it is helpful in CSS evaluation to identify proper indicators and find out the best CSS option. Show more

Keywords: Car sharing systems, indicator selection, evaluation

DOI: 10.3233/JIFS-200646

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 3, pp. 4703-4721, 2020

Authors: Azzam, A. A. | Khalil, Ahmed Mostafa | Li, Sheng-Gang

Article Type: Research Article

Abstract: It is known that mathematical statics, mathematical modeling, and differential equations are used to give an in-depth understanding of many medical problems. On the edge of the information revolution, minimal structures show some qualitative properties issues that are difficult to deal with it, such as quality of education, nutrition, etc. The aim of this paper is to discuss two medical applications and show that a minimal structure space is suitable for analyzing several real-life problems. Then, the accuracy of the decision-making and attributes reduction of the medical information system are explained and obtained. Furthermore, we introduce a comparison between our …approach and Pawlak’s approach to find accuracy for decision-making. Finally, the accuracy of decision-making via a variable precision model is improved. Show more

Keywords: Minimal structure, upper approximation, lower approximation, reduction of attributes, accuracy

DOI: 10.3233/JIFS-200651

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 3, pp. 4723-4730, 2020

Authors: Deepika, T. | Prakash, P. | Dhanya, N.M.

Article Type: Research Article

Abstract: By leveraging the performance of small and medium-scale data centers (SMSDCs), which are involved in high-performance computing, data centers are central to the current modern industrial business world. Extensive enhancements in the SMSDC infrastructure comprise a diverse set of connected devices that disseminate resources to the end users. The high certainty workloads of end users and over resource provisioning result in high power consumption in SMSDCs, which are pivotal factors contributing to high carbon footprints from SMSDCs. The excessive emission of CO 2 is higher in SMSDCs compared with that of hyperscale data centers (HSDCs). An exorbitant amount of …electricity is utilized by 8.6 million data centers worldwide, and is expected to increase by up to 13% in 2030. The power requirement of an SMSDC domain is expected to be 5% of the global power production. However, the power consumption of SMSDCs changes annually. To aid SMSDCs, machine learning prediction is deployed. Literature review indicates that many studies have focused on the recurring issues of HSDCs rather than those of SMSDC. Herein, a regressive predictive analysis, i.e., multi-output random forest regressor, is proposed to forecast the resource usage and power utilization of virtual machines. These prediction results in diminishes the power utilization of SMSDC whilst reduces the CO 2 emission from SMSDC. The obtained result shows that the proposed approach yields better predictions than other single-output prediction methods for future resource demand from end users. Show more

Keywords: Cloud computing, virtual machine, power consumption prediction, machine learning

DOI: 10.3233/JIFS-200653

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 3, pp. 4731-4747, 2020

Authors: Yang, LiGuo | Li, Chaoling | Lu, Lin | Guo, Tai

Article Type: Research Article

Abstract: The marine economy has become a growth point for the regional economy. International resource exchange is mainly achieved through marine transportation. Ports play a vital role in marine transportation and also play an important role in some large-scale international rescue activities. When an emergency occurs in the port, the port emergency logistics system has an important impact on the collection and distribution of materials, which can effectively reduce the negative impact and economic loss caused by the emergency. Through in-depth analysis of the emergency logistics system, design the comprehensive evaluation system of the port emergency logistics distribution system, and based …on the characteristics of the grey, fuzzy and difficult to quantify the influencing factors of the emergency logistics distribution system, apply the analytic hierarchy process and grey system theory to establish the gray level comprehensive evaluation model of the port emergency logistics distribution system. In this model, the analytic hierarchy process is used to determine the index weight, and then the grey theory is used to comprehensively evaluate the emergency logistics distribution system. Finally, the port is used as a case to verify the practicability and effectiveness of the model. Show more

Keywords: Port emergency logistics, grey AHP, evaluating indicator

DOI: 10.3233/JIFS-200674

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 3, pp. 4749-4761, 2020

Authors: Akram, Muhammad | Peng, Xindong | Al-Kenani, Ahmad N. | Sattar, Aqsa

Article Type: Research Article

Abstract: Complex Pythagorean fuzzy (CPF), a worthwhile generalization of Pythagorean fuzzy set, is a powerful tool to deal with two-dimensional or periodic information. In this paper, we develop two prioritized aggregation operators (AOs) under CPF environment, namely, complex Pythagorean fuzzy prioritized weighted averaging (CPFPWA) operator and complex Pythagorean fuzzy prioritized weighted geometric (CPFPWG) operator. We consider the prioritization relationship among criteria and decision makers (DMs) to make our result more accurate as in real decision making (DM) problems, the criteria and DMs have different priority level. Further, we discuss remarkable properties of our proposed AOs. Moreover, we promote the evolution of …MCDM problem by investigating an algorithm in CPF environment with its flow chart. Finally, to check the superiority and validity of proposed operators, we compare the computed results with the different existing techniques. Show more

Keywords: Complex pythagorean fuzzy sets, prioritized aggregation operators, decision making

DOI: 10.3233/JIFS-200684

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 3, pp. 4763-4783, 2020

Authors: Do Xuan, Cho | Dao, Mai Hoang | Nguyen, Hoa Dinh

Article Type: Research Article

Abstract: Advanced Persistent Threat (APT) attacks are a form of malicious, intentionally and clearly targeted attack. This attack technique is growing in both the number of recorded attacks and the extent of its dangers to organizations, businesses and governments. Therefore, the task of detecting and warning APT attacks in the real system is very necessary today. One of the most effective approaches to APT attack detection is to apply machine learning or deep learning to analyze network traffic. There have been a number of studies and recommendations to analyze network traffic into network flows and then combine with some classification or …clustering methods to look for signs of APT attacks. In particular, recent studies often apply machine learning algorithms to spot the present of APT attacks based on network flow. In this paper, a new method based on deep learning to detect APT attacks using network flow is proposed. Accordingly, in our research, network traffic is analyzed into IP-based network flows, then the IP information is reconstructed from flow, and finally deep learning models are used to extract features for detecting APT attack IPs from other IPs. Additionally, a combined deep learning model using Bidirectional Long Short-Term Memory (BiLSTM) and Graph Convolutional Networks (GCN) is introduced. The new detection model is evaluated and compared with some traditional machine learning models, i.e. Multi-layer perceptron (MLP) and single GCN models, in the experiments. Experimental results show that BiLSTM-GCN model has the best performance in all evaluation scores. This not only shows that deep learning application on flow network analysis to detect APT attacks is a good decision but also suggests a new direction for network intrusion detection techniques based on deep learning. Show more

Keywords: Advanced persistent threat, APT attack detection, network traffic, flow, bidirectional long short term memory, graph convolutional networks

DOI: 10.3233/JIFS-200694

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 3, pp. 4785-4801, 2020

Authors: Kreinovich, Vladik

Article Type: Book Review

DOI: 10.3233/JIFS-189178

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 3, pp. 4803-4805, 2020

Authors: Kreinovich, Vladik

Article Type: Book Review

DOI: 10.3233/JIFS-189308

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 3, pp. 4807-4810, 2020