Journal of Intelligent & Fuzzy Systems - Volume Pre-press, issue Pre-press

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. Pre-press, no. Pre-press, pp. 1-9, 2021

Authors: Wang, Xiaodong | Wang, Xiaoming | Wu, Junfeng | Zheng, Kai | Pang, Yanhong | Gang, Song

Article Type: Research Article

Abstract: For the weak part of the quality traceability ability of cigarette logistics and products, this paper proposes a quality traceability method which integrates PDCA quality cycle with information strategy. This method firstly establishes the quality cycle process of cigarette logistics through PDCA quality cycle process, and then constructs IS-PDCA process based on information strategy (IS) to analyze the quality traceability process of cigarette products. The key links are determined according to the traceability process of cigarette logistics, and the traceability resource scheduling function is determined through the product. Then, according to the determined scheduling function and RFID technology, the optimal …allocation strategy is constructed to complete the feature extraction and classification identification of cigarette quality labels. For assessing the quality of cigarette evaluation, classification based on fuzzy is proposed and artificial neural network are utilized for calculating the grade of cigarette. Finally, a process of cigarette quality traceability combining PDCA quality cycle and information strategy is formed, and the quality traceability results are constructed by means of QR code technology, so as to realize the process system of cigarette quality traceability and improve the quality control ability of cigarettes. The simulation results show that the cigarette quality traceability method constructed in this paper can obtain the cigarette quality control with good adaptive performance, and the control process shows a strong ability, which improves the feasibility and effectiveness of the cigarette quality traceability. Show more

Keywords: Information strategy, Artificial Intelligence (AI), PDCA quality cycle, cigarette logistics, quality traceability, fuzzy, artificial neural network

DOI: 10.3233/JIFS-189644

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-10, 2021

Authors: Jing, Wu | Jie, Tian

Article Type: Research Article

Abstract: China remains one among largest agricultural countries in the world and one of the fastest growing Internet countries in the world. The further thorough and penetration of the Internet into the rural hinterland indicates that the combination of the Internet and the rural areas already has the technical foundation. The transformation of rural economy with Internet as medium is the future direction of rural development. Starting from the current situation of rural Internet development, based on the annotation of “Internet plus”, this paper explores the theoretical and practical application of rural e-commerce development. We utilize Intuitionistic Fuzzy Sets operator for …modelling multiple attribute issues related to decision making to estimate influence of e-commerce in industries. This paper puts forward the measure method of industrial transformation and proves that “Internet plus” e-commerce has exerted a great influence on the commercial civilization, industrial structure and economic structure transformation of rural areas. The steady and lasting impact of this continuous release may become a new paradigm of technological economy. It is of great significance to the formation of the “four modernizing” linkage mechanism with information as media and the innovation of the conventional path of rural economic development and the rapid growth of rural economy. Show more

Keywords: Rural e-commerce, industrial structure, transformation, artificial intelligence (AI), “Internet plus”, fuzzy sets

DOI: 10.3233/JIFS-189643

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-9, 2021

Authors: Luo, Xiaolin

Article Type: Research Article

Abstract: Along with improvement of technology in network and continuous expansion of network economy and network applications, the Internet has gradually become an indispensable part of the modern society. However, an endless stream of hacker attacks and network virus events make network security issues stand out. Therefore, network security has become a hot spot in computer network research and development. This paper aims at establishing a real-time detection and dynamic defense security system and makes an in-depth study of intrusion detection technology and defense decision-making technology. The strategy involved in finding the intrusion behavior since the fuzzy base contains the better …group of rules. We have utilized an automated fuzzy rule generation strategy. An adaptive network intrusion detection and defense system model is established, and the architecture of the model is discussed in detail. The platform independence, good self-adaptability, expansibility, multi-level data analysis and dynamic defense decision-making are expounded. The experiment proves that the model proposed in this article has a good self-adaptability and open construction, and effectively combines the functions of intrusion detection and defense decision-making. Show more

Keywords: Artificial intelligence, adaptive network, defense system, fuzzy rule

DOI: 10.3233/JIFS-189645

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-9, 2021

Authors: Wang, Jie | Yan, Linhuang | Yang, Qiaohe | Yuan, Minmin

Article Type: Research Article

Abstract: In this paper, a single-channel speech enhancement algorithm is proposed by using guided spectrogram filtering based on masking properties of human auditory system when considering a speech spectrogram as an image. Guided filtering is capable of sharpening details and estimating unwanted textures or background noise from the noisy speech spectrogram. If we consider the noisy spectrogram as a degraded image, we can estimate the spectrogram of the clean speech signal using guided filtering after subtracting noise components. Combined with masking properties of human auditory system, the proposed algorithm adaptively adjusts and reduces the residual noise of the enhanced speech spectrogram …according to the corresponding masking threshold. Because the filtering output is a local linear transform of the guidance spectrogram, the local mask window slides can be efficiently implemented via box filter with O(N) computational complexity. Experimental results show that the proposed algorithm can effectively suppress noise in different noisy environments and thus can greatly improve speech quality and speech intelligibility. Show more

Keywords: Auditory masking properties, guided filtering, guided spectrogram filtering, spectrogram, speech enhancement

DOI: 10.3233/JIFS-202278

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-12, 2021

Authors: Abu Saleem, M.

Article Type: Research Article

Abstract: The main aim of this article is to present neutrosophic folding and neutrosophic retractions on a single-valued neutrosophic graph Ğ from the viewpoint of geometry and topology. For this reason, we use a sequence of neutrosophic transformations on Ğ to obtain a new single-valued neutrosophic graph G ˇ 1 which contains different parameters under new conditions. We deduce the isometric neutrosophic folding on neutrosophic spheres and neutrosophic torii. Also, we determine the relationship between the limit neutrosophic folding and the limit of neutrosophic retraction on Ğ. Theorems regulating these relations are attained.

Keywords: Single valued neutrosophic graph, Neutrosophic folding, Neutrosophic retraction, 51H20, 57N10, 57M05, 14F35, 20F34

DOI: 10.3233/JIFS-201957

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-7, 2021

Authors: Zhou, Wei

Article Type: Research Article

Abstract: Decentralized application (DAPP), replacing traditional business logic and data access layer with block chain, is a new form of Internet service. Testing DAPP requires large-scale distributed systems. Performing experiments in a real system is costly and difficult. This article carefully analyses the process of block generation and synchronization and explains the reasons for the low efficiency of block chain system simulation. We incorporate fuzzy rule based model for enhancing the logging system in blockchain. Rules based on fuzzy are utilized inside system of fuzzy logic to obtain outcome on basis of input variables. The data of Ethereum and Bitcoin proves …that the block generation interval conforms to the exponential distribution, and the real PoW calculation can be replaced with random numbers. Both block verification and network propagation processes have latency, which can be simulated with asynchronous messaging. Based on the above analysis, this article proposes a high-performance simulation method based on event-driven model, which is suitable for describing the communication and synchronization behave our of block chain networks. The method can effectively describe the block generation, the synchronization process between nodes, and supports different equity proof forms. Using this method, the performance of the PoW systemis tested. Under the ecs.c6.xlargeinstance,the simulation running speed reaches 782 times of actual system. Further experiments show that this method can be efficiently used in larger-scale networks and is an effective tool for DAPP developing and testing. Show more

Keywords: Decentralized applications, blockchain, complex network, distributed system, artificial intelligence, fuzzy logic, fuzzy rule

DOI: 10.3233/JIFS-189633

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-7, 2021

Authors: Wang, Qian | Wang, Jianxu | Li, Hua | Li, Xiang

Article Type: Research Article

Abstract: Equipment manufacturing industry is the core industry of national economy. The development of artificial intelligence technology provides new development opportunities for the transformation and upgrading of equipment manufacturing industry, but in this process, China’s equipment manufacturing enterprises are faced with serious financing constraints and financing efficiency needs to be improved. Based on the panel data of Listed Companies in equipment manufacturing industry from 2009 to 2018, the article constructs a panel data regression model by using stochastic frontier analysis to measure the financing efficiency of equipment manufacturing industry and study its influencing factors. The results show that the average financing …efficiency of China’s equipment manufacturing enterprises is in the medium level, while the traditional equipment manufacturing industry is lower; external financing has a positive impact on the financing efficiency of enterprises, and labor input has a negative impact; in the analysis of influencing factors, the Capital structure, R&D investment, Accounts receivable turnover rate, Fixed assets turnover rate have a great impact on the financing efficiency. The research results have a certain reference significance for equipment manufacturing enterprises to improve financing efficiency. Show more

Keywords: Equipment manufacturing, financing efficiency, stochastic frontier analysis

DOI: 10.3233/JIFS-189635

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-10, 2021

Authors: Yafeng, Wen

Article Type: Research Article

Abstract: With the promotion of BIM Technology, prefabricated building is developed rapidly in China. However, BIM technology has been only partially applied to prefabricated building, and there is still a gap between prefabricated building and intelligent construction. This paper focus on BIM 5D, together with relevant information technologies, all of which will be highly integrated and applied to prefabricated building, with the mission to get related information and enable the rapid flow of information, as well as bringing human perception, memory, knowledge and wisdom into prefabricated building, driving the development of prefabricated buildings to intelligence and leanness. Intelligent construction is …an innovated construction model based on the combination of latest information technology and engineering construction. Thus, it is particularly important to train personnel with corresponding knowledge structure, knowledge system and professional ability for intelligent construction. This paper also discusses about how to train personnel on prefabricated building and intelligent construction. Show more

Keywords: BIM5D, prefabricated building, intelligent construction, personnel training

DOI: 10.3233/JIFS-189625

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-9, 2021

Authors: Pan, Nan | Shen, Xin | Guo, Xiaojue | Cao, Min | Pan, Dilin

Article Type: Research Article

Abstract: In recent years, electricity stealing has been repeatedly prohibited, and as the methods of stealing electricity have become more intelligent and concealed, it is growing increasingly difficult to extract high-dimensional data features of power consumption. In order to solve this problem, a correlation model of power-consumption data based on convolutional neural networks (CNN) is established. First, the original user signal is preprocessed to remove the noise. The user signal with a fixed signal length is then intercepted and the parallel class labelled. The segmented user signals and corresponding labels are input into the convolutional neural network for training, and the …trained convolutional neural network is then used to detect and classify the test user signals. Finally, the actual steal leak dataset is used to verify the effectiveness of this algorithm, which proves that the algorithm can effectively carry out anti–-electricity stealing by warning of abnormal power consumption behavior. There are lots of line traces on the surface of the broken ends which left in the cable cutting case crime scene along the high-speed railway in China. The line traces usually present nonlinear morphological features and has strong randomness. It is not very effective when using existing image-processing and three-dimensional scanning methods to do the trace comparison, therefore, a fast algorithm based on wavelet domain feature aiming at the nonlinear line traces is put forward to make fast trace analysis and infer the criminal tools. The proposed algorithm first applies wavelet decomposition to the 1-D signals which picked up by single point laser displacement sensor to partially reduce noises. After that, the dynamic time warping is employed to do trace feature similarity matching. Finally, using linear regression machine learning algorithm based on gradient descent method to do constant iteration. The experiment results of cutting line traces sample data comparison demonstrate the accuracy and reliability of the proposed algorithm. Show more

Keywords: Anti–electricity stealing, high-dimensional data features, convolutional neural network, early warning

DOI: 10.3233/JIFS-189621

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-7, 2021