Journal of Intelligent & Fuzzy Systems - Volume 38, issue 5

Authors: Hsiao, Shou-Ching | Liu, Zi-Yuan | Tso, Raylin | Kao, Da-Yu | Chen, Chien-Ming

Article Type: Research Article

Abstract: Gated Recurrent Unit (GRU) has wide application fields, such as sentiment analysis, speech recognition, and other sequential data processing. For efficient prediction, a growing number of model owners choose to deploy the trained GRU models through the machine-learning-as-a-service method (MLaaS). However, deploying a GRU model in cloud generates privacy issues for both model owners and prediction clients. This paper presents the architecture of PrivGRU and designs the privacy-preserving protocols to complete the secure inference. The protocols include base protocols and principal protocols. Base protocols define basic linear and non-linear computations, while principal protocols construct the gating mechanisms of GRUs. The …main benefit of PrivGRU is to address privacy problems while enjoying the efficiency and convenience of MLaaS. The overall secure inference is performed on shares, which retain two properties of security: correctness and privacy. To prove the security, this work adopts Universal Composability (UC) framework with the honest-but-curious corruption model. As each protocol is proved to UC-realize the ideal functionality, it can be arbitrarily composed in any manner. This strong security feature makes PrivGRU more flexible and practical in future implementation. Show more

Keywords: Privacy-preserving, MLaaS, gated recurrent unit, additive secret sharing, UC framework

DOI: 10.3233/JIFS-179652

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 5, pp. 5627-5638, 2020

Authors: Luo, Tai-Li | Wu, Mu-En | Chen, Chien-Ming

Article Type: Research Article

Abstract: Quantitative trading is a crucial aspect of money management; however, conventional trading strategies are based on indicators and signals, despite the fact that position sizing is arguably the most important issue. In this study, we present a stock evaluation function that outputs the size of the stock in each fixed period as well as the consequences of increasing or decreasing the size of one’s position. The difficulties involved in using machine learning to adjust stock weighting can be attributed to difficulties in obtaining definite answers via supervised learning. We therefore train our evaluation function using reinforcement learning via CNN within …the EIIE network architecture and have the agent adjust the size of the position with the purpose of maximizing profits. Back testing was performed using the top 50 stocks in Taiwan, based on market capitalization. In experiments, most of the stock returns outperformed conventional strategies in terms of cumulative stock value. Show more

Keywords: Deep reinforcement learning, convolution neural networks, evaluation function, position sizing, money management

DOI: 10.3233/JIFS-179653

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 5, pp. 5639-5649, 2020

Authors: Wu, Mu-En | Lin, Sheng-Hao | Wang, Jia-Ching

Article Type: Research Article

Abstract: The objective in using the Kelly criterion for money management is to maximize returns; however, in many cases, the risk level exceeds that which the investor can bear. In this study, we present an algorithm to calculate the bidding fraction, while taking into account the level of risk (i.e., the maximum drawdown). The proposed algorithm is based on ensemble learning with a combination of bagging and subset resampling. Our assessment results obtained using the FF48 (i.e., Fama-French-48) dataset revealed that when the maximum drawdown was 5% and 10%, ensemble learning outperformed the conventional approach by 2% and 4%, respectively.

Keywords: Kelly criterion, ensemble learning, Monte Carlo simulation, money managemen

DOI: 10.3233/JIFS-179654

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 5, pp. 5651-5659, 2020

Authors: Meng, Zhenyu | Yang, Cheng | Meng, Fanjia | Chen, Yuxin | Lin, Fang

Article Type: Research Article

Abstract:  Differential Evolution (DE) was an easy-coding and efficient stochastic algorithm for global optimization, and the whole optimization process simulates biological evolution. Superior individuals of the population that were suitable for the environment were retained during the evolution, and consequently the tolerable solutions could be obtained in the end. Despite the excellent performance of DE algorithm, there were still some shortcomings. For example, the general performance of DE depended largely on mutation strategy and control parameters, how to design the appropriate control parameters and mutation strategy were difficult tasks. Here a novel DE variant was proposed to overcome these shortcomings. By …incorporating the depth information of previous generations of populations, a better diversity of trial vector candidates could be secured during the evolution process. Moreover, the thought that successful parameters should be retained to guide the update of themselves during the evolution was also incorporated into the novel algorithm. The optimization performance of the new proposed DE variant was verified under CEC 2013 test suit containing 28 benchmarks, and the results showed its competitiveness with several state-of-the-art DE variants. Show more

Keywords: Differential evolution, depth information, global optimization, real-parameter optimization

DOI: 10.3233/JIFS-179655

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 5, pp. 5661-5671, 2020

Authors: Chu, Shu-Chuan | Chen, Yuxin | Meng, Fanjia | Yang, Chen | Pan, Jeng-Shyang | Meng, Zhenyu

Article Type: Research Article

Abstract:  Optimization demands exist everywhere in the real world especially in science studies and engineering practices, and it is important that the method to deal with intricacy optimization problems should itself be relative simple. Particle Swarm Optimization (PSO) and Differential Evolution (DE) both are simple evolutionary algorithms (EAs) which are proposed for single-objective optimization and both of them have been proved to be efficient methods for optimizing applications, however, there are still some weakness existing within them. A innovative evolutionary method named QUasi-Affine TRansformation Evolutionary (QUATRE) algorithm which is derived from, also tackles some weaknesses of PSO and DE algorithm, and …obtains better performance on commonly used test suites. The key characteristic of QUATRE is that an automatically generated matrix named evolution matrix M is implemented in evolutionary process, which is taken as an alternative of employing the crossover rate CR . Here in this paper, we present a novel QUATRE variant, named IS-QUATRE, which can explore the search area in a better way comparison with the previous method, and relatively good optimization ability can be obtained by our proposed IS-QUATRE algorithm under CEC2013 test suit. And the conducted experimental results validate that our proposed IS-QUATRE is competitive with some other famous PSO and DE variants. Show more

Keywords: Internal search, QUATRE, single-objective optimization, stochastic optimization, real-parameter optimization

DOI: 10.3233/JIFS-179656

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 5, pp. 5673-5684, 2020

Authors: Zhang, Fuquan | Wang, Yiou | Wu, Chensheng

Article Type: Research Article

Abstract:  Digital creativity is creative expression derived from cultural creativity and information technology. In order to overcome the problem in the creative generation in the condition of fuzzy and uncertain ideas, an automatic generation method of cross-modal fuzzy creativity (AGMCFC) is proposed. In this subject, fuzzy creative data sets and learning retrieval network are constructed for the sake of extracting original creative data effectively. And the logical correlations between creative objects are acquired dynamically based on the graph neural network. Creative objects and creative styles are generated by using generative adversarial nets technology and style transfer technology, respectively. Then, the projectiles, …boundary markers and location words of the creative scene objects are generated by analyzing related attributes of each entity. After adjusting the layout, creative works are automatically generated. A fuzzy creative generating environment is implemented. Experimental results show that the screened number of AGMCFC method is about twice as much as that of manual method, and the accuracy rate of AGMCFC method is improved compared with the manual method. AGMCFC method performs well at creative generation of fuzzy ideas automatically. Show more

Keywords: Generation of fuzzy creativity, cross-modal, graph neural network, creative works

DOI: 10.3233/JIFS-179657

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 5, pp. 5685-5696, 2020

Authors: Zhang, Jinxin | Li, Hui | Zhang, Xiufang | Yu, Hua | Liang, Fengna | Qin, Zijun | Jiang, Miaohua

Article Type: Research Article

Abstract: Soil erosion is one of the main environmental problems in the world, and also an important branch of natural environment protection. Taking Minjiang River Basin as the research area, based on the supervised classification of land use status map, the comprehensive soil erosion modulus map was generated by referring to the soil erosion evaluation index and the revised soil loss equation (RUSLE). The results showed that the Minjiang River Basin is dominated by mild eroded area and middle eroded area, accounting for 41.50% and 54.81% of the total area respectively. High eroded area accounted for only 3.69%, mainly in the …north and west, and there was no extremely sensitive area. From the perspective of land use types, the construction land and water body are mainly slightly sensitive areas, and forest land, garden land and cultivated land are mainly mild or middle sensitive areas, while the unused lands are shown as middle sensitive areas or highly sensitive areas. Through the discussion of the sensitivity evaluation of soil erosion in Minjiang River Basin, it can provide some references for the relevant departments to the soil and water conservation work in Minjiang River Basin. Show more

Keywords: Soil erosion, sensitivity assessment, Minjiang River Basin, land use

DOI: 10.3233/JIFS-179658

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 5, pp. 5697-5705, 2020

Authors: Liu, Wei | Mao, Yu | Ci, Linlin | Zhang, Fuquan

Article Type: Research Article

Abstract:  It is not foolproof for intrusion detection to focus only on the network level and the program level. Internal security and external security of information systems should be given equal attention. User-level intrusion detection can deter and curtail attackers from damaging information systems. Even if the mimic attacker has gained and enhanced the host user privileges that he illegally obtained. In this paper, a novel method based on recurrent neural networks (RNNs) is used to predict user command sequences and prophesy user behaviors. The experimental results show that our command sequence-to-sequence model is robust and effective for solving long sequential …problem on three different data sets including Purdue University data set, SEA data set and self-collected data set. Show more

Keywords: User behavior, recurrent neural networks, anomaly intrusion detection, attacks and defenses

DOI: 10.3233/JIFS-179659

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 5, pp. 5707-5716, 2020

Authors: Xie, Chao-Fan | Xu, Lu-Xiong | Zhang, Fuquan

Article Type: Research Article

Abstract: Because of high efficiency and cleanness, the simulated moving bed (SMB) is the most important technology in chromatographic separation. SMB system, which contains several sectors of flow rate, the switching time of valves and many other possible influencing variables, is complex, highly sensitive and difficult to control. This paper proposes adjusted fuzzy control; the adjusted fuzzy controller is applied to the SMB system to control the separation concentration by establishing a variable direction correction formula. Compared with the traditional fuzzy controller, the adjusted fuzzy controller does not need to analyze the dynamic direction of the control force in advance, moreover, …the control accuracy is high and the fluctuation is small for SMB system. Show more

Keywords: Chromatographic, SMB, fuzzy, control

DOI: 10.3233/JIFS-179660

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 5, pp. 5717-5729, 2020

Authors: Li, Zhanhui | Fan, Jiancong | Ren, Yande | Tang, Leiyu

Article Type: Research Article

Abstract: As a common disease, migraine has a high incidence but the pathogenesis is still not clear. Resting-state Functional Magnetic Resonance Imaging (rs-fMRI) is an important research topic in the field of brain medicine, which can classify rs-fMRI data to automatically diagnose brain diseases. However, the original features of the rs-fMRI data are difficult to be extracted and the high-dimensional characteristics, which make the data analysis an extremely complicated task. Those have also plagued many researchers and bring great challenges to the existing pattern classification methods. Aiming at the high dimensionality of rs-fMRI data, in this paper, we propose a feature …extraction approach based on the combination of neighborhood rough set and PCA, thereby improving the accuracy of migraine identification. Firstly, Resting-State fMRI Data Analysis Toolkit plus was applied for preprocessing, calculating three characteristic indices: Amplitude of Low Frequency Fluctuation (ALFF), Regional Homogeneity (ReHo) and Functional Connectivity (FC. The inter-group difference analysis was performed by two-sample T test and GRF correction. Then, correlation coefficient matrix original features extraction was performed by means of automatic anatomical label template (AAL). Finally, the original features were trained by the traditional classification algorithm in machine learning. The experimental results show that the propose approach can obtain good performance in predicting migraine. Show more

Keywords: Resting state functional magnetic resonance imaging, migraine, correlation coefficient matrix, neighborhood rough set, principal component analysis, classification

DOI: 10.3233/JIFS-179661

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 5, pp. 5731-5741, 2020