Journal of Intelligent & Fuzzy Systems - Volume 37, issue 5

Authors: Xia, Chenhong

Article Type: Research Article

Abstract: There is a certain correlation between human health and actual exercise. This has always been one of the focuses of many scholars. When analyzing the movement of human body, a lot of modern technology and equipment need to be used. In order to better realize the physical health of young people in our country, the health service system based on sensor technology has been put forward. By introducing accelerometer technology, real-time data capture and analysis of human motion posture and movement trajectory were carried out. At the same time, the reliability of the algorithm was improved. In order to verify …the feasibility of the method, a practical case was verified. Experimental results showed that the method was more scientific and reasonable in motion capture analysis. Show more

Keywords: Sensor technology, motion index, health system

DOI: 10.3233/JIFS-179189

Citation: Journal of Intelligent & Fuzzy Systems, vol. 37, no. 5, pp. 6063-6069, 2019

Authors: Zhu, Xianwen

Article Type: Research Article

Abstract: At this stage, the rapid development of computer technology and information technology in China has provided favorable conditions for the development of the game. In order to pursue the game experience, how to use artificial intelligence in the game has become a new research hotspot. Therefore, the current situation of artificial intelligence used in games was investigated, and the principles of Unity3D game engine were studied; then the intelligent behavior model for NPC was established by using the behavior tree as the basic algorithm, and the AI architecture of the agent in the game was designed; moreover, combined with the …above analysis, the behavior tree model based on Q learning algorithm was calculated, and the application of Unity3D in the game was completed; finally, a game model was developed in combination with Unity3D game engine. The results show that the behavior tree based on Unity3D game engine can realize NPC’s intelligent behavior simply and efficiently, and the system can run at a good speed, which has theoretical guidance for the follow-up research of game artificial intelligence and simulation training. Show more

Keywords: Unity3D, intelligent behavior, behavior tree, non-player character (NPC)

DOI: 10.3233/JIFS-179190

Citation: Journal of Intelligent & Fuzzy Systems, vol. 37, no. 5, pp. 6071-6079, 2019

Authors: Li, Xiaohong | Li, Maolin

Article Type: Research Article

Abstract: Traditional information recommendation system using only the user’s score is calculated and recommended, although to a certain extent, can obtain the implied characteristics of users or resources, but the lack of enough semantic interpretation, affecting the effects of recommendation. This article studied and analyzed the recommendation based on attribute coupled matrix decomposition algorithm in the application of Internet of things, on the foundation of the matrix decomposition model successively introduced global offset and time offset, in order to improve the prediction accuracy and the quality is recommended. In this paper, the algorithm is proved by experiment and the prediction accuracy …of the algorithm is improved. Show more

Keywords: Property coupling, matrix decomposition, recommendation algorithm, internet of things

DOI: 10.3233/JIFS-179192

Citation: Journal of Intelligent & Fuzzy Systems, vol. 37, no. 5, pp. 6081-6089, 2019

Authors: Wang, Bin | Dai, Jing

Article Type: Research Article

Abstract: With the continuous improvement of the social and economic level, the investment in fixed assets in the whole society is increasing steadily, while the phenomenon of uncontrollable investment is becoming more and more serious. Therefore, it is very important to increase the investment estimate in the early stage of the project construction. Based on this, in this paper, by studying the BP neural network, a mathematical model of the prediction of engineering cost based on the improved BP neural network model was proposed; then, taking a 15-storey tall building in a residential district as a prediction object, by collecting and …sorting out engineering cost data similar to the predicted object, the improved BP neural network model was estimated and trained; finally, the prediction of the engineering cost data for the project was carried out, and the actual results were compared with the estimation results of the traditional prediction model; thus, the speediness and accuracy of the proposed improved BP neural network model in the field of the prediction of engineering cost were verified. Show more

Keywords: BP neural network, improved BP algorithm, engineering cost, prediction model

DOI: 10.3233/JIFS-179193

Citation: Journal of Intelligent & Fuzzy Systems, vol. 37, no. 5, pp. 6091-6098, 2019

Authors: Zhang, Ming

Article Type: Research Article

Abstract: With the rapid development of wireless networks, the issue of information security in wireless communications has gradually emerged, and it has become one of the biggest obstacles to the popularization of this technology. To meet the increasing security and reliability requirements of new network environments, wireless network security standards and protocols are constantly being updated and enhanced. Based on the current development of wireless networks in Beijing, this paper discusses the optimization of encryption protocols in network security protocols, introduces the PrefixSpan algorithm and improves its algorithms, and then performs data mining based on Prefix, and analyzes the intrusion lines …and their correlations. Finally, the feasibility of using the improved PrefixSpan algorithm to optimize the encryption protocol is verified through experiments. Show more

Keywords: Prefixspan algorithm, data mining, network security, encryption protocol

DOI: 10.3233/JIFS-179194

Citation: Journal of Intelligent & Fuzzy Systems, vol. 37, no. 5, pp. 6099-6106, 2019

Authors: Tan, Lingling | Li, Qian

Article Type: Research Article

Abstract: With the popularity of computer technology, big data, Internet of things and other new IT technologies appear. With the rapid transformation of the times, the traditional logistics industry can no longer meet the needs. Therefore, the new logistics method has been studied by various technicians. Petri network logistics is one of the new methods. The knowledge flow modeling of supply chain under Petri network is expounded. The basic theory and method of logistics are analyzed. Using the particle swarm optimization (PSO) algorithm of data Petri network to combine the Internet of things with Petri network, the innovation research is carried …out and the supply chain knowledge flow model is built. In the test of information operation efficiency of the algorithm, it is proved that our algorithm is feasible. Show more

Keywords: Petri network, logistics, supply chain knowledge flow

DOI: 10.3233/JIFS-179195

Citation: Journal of Intelligent & Fuzzy Systems, vol. 37, no. 5, pp. 6107-6114, 2019

Authors: Li, Jiangbo | Wang, Yumin

Article Type: Research Article

Abstract: Industrial cluster is a common phenomenon in the process of industrialization. It is an external scale formed by agglomeration effect. Cluster enterprises based on their comparative advantages, innovation will be in the system innovation, management innovation, technological innovation, corporate culture innovation and other all-round development. The empirical results show that the development of industrial clusters attracts and promotes a large number of intermediary service-oriented organizations, as well as institutions providing research and development and technical support, providing innovative incubation platform. The diffusion behavior of technological innovation of enterprises in clusters plays an important role in upgrading industrial clusters, but uncontrolled …imitation behavior will reduce the expected profits of enterprises taking the lead in innovation and increase innovation risks. At the same time, the supporting innovation service system integrates and improves the factors gathering and optimization needed for innovation, and provides a technological support platform for enterprises in clusters to innovate.Therefore, the government’s policy should be biased towards establishing an effective mechanism for the interaction between scientific and technological innovation and industrial clusters, so as to achieve a good situation of the interaction between economy and science and technology. Show more

Keywords: Fuzzy model, industrial cluster, technological innovation, complex network

DOI: 10.3233/JIFS-179196

Citation: Journal of Intelligent & Fuzzy Systems, vol. 37, no. 5, pp. 6115-6126, 2019

Authors: Yansong, Liu | Li, Zhu | Feng, Liu

Article Type: Research Article

Abstract: The security of massive data has always been the focus of computer security research. With the increase of data storage, the computing platform of single node can not deal with the increasing security of massive data. It is urgent to use distributed computing platform to improve computing efficiency and detection accuracy. The physical deployment of intrusion detection system on cloud computing platform consists of monitoring server, Hadoop master server, IDS server, node and IDS terminal management. The experimental results show that the proposed intrusion detection system based on Hadoop cloud node has better detection effect. This paper searches for the …optimal weights, and then begins the training of the neural network. The whole process uses the Hadoop framework of distributed computing platform to implement the genetic algorithm and the neural network algorithm in the cloud computing platform. At the same time, the algorithm is improved to improve the efficiency and accuracy of intrusion detection. The results show that the intrusion detection technology is very effective to protect the application system and help it against various types of intrusion attacks. Show more

Keywords: Intrusion detection algorithms, cloud computing, distributed networks, detection rate

DOI: 10.3233/JIFS-179197

Citation: Journal of Intelligent & Fuzzy Systems, vol. 37, no. 5, pp. 6127-6138, 2019

Authors: Chen, Gang

Article Type: Research Article

Abstract: The effective supply guarantee of fresh agricultural products is a systematic problem. Farmers should not only pursue economic effectiveness, but also ensure the quality of products. This paper analyzes the supply decision of agricultural products based on negative exponential utility function and game analysis. The negative exponential utility function has been widely used in the study of the risk preferences of farmers. This paper analyses the impact of price fluctuation on the supply of agricultural products. At the same time, it analyses the problem of quality and safety from the perspective of the main body of agricultural products supply under …the framework of economics. The income of agricultural products is an important factor affecting their behavioral decision-making. The result shows that: (1) price affects utility values by affecting the profit values and the mean risk-aversion coefficients; (2) market competition gives producers and operators inherent motivation to improve the quality of agricultural products. In the process of production decision-making, it is necessary to ensure that the profit of supplying safe agricultural products is not less than that of supplying conventional agricultural products. Therefore, the government can adopt economic incentive and policy incentive mechanism to protect the economic interests of the main body of safe agricultural products supply. Show more

Keywords: Utility function, optimal decision, supply chain network, quality of agricultural products

DOI: 10.3233/JIFS-179198

Citation: Journal of Intelligent & Fuzzy Systems, vol. 37, no. 5, pp. 6139-6149, 2019

Authors: Yu, Wang | Huafeng, Wang

Article Type: Research Article

Abstract: Extreme value theory can analyze the extreme changes of financial market returns, and it is an effective financial risk management model. The distribution characteristics of financial assets’ returns are the core content of all financial models. The assumptions about the fluctuation behavior of returns and its distribution characteristics are of great theoretical and practical significance for the measurement and management of financial risks. We compare the estimates of value at risk by the peak over threshold model with that by the traditional variance-covariance method. During downturns, the peak over threshold model based value at risk estimates is higher relative to …that by the traditional variance-covariance approach. At the same time, this paper conducts statistical analysis of basic data through data collection and combines the establishment of statistical methods to study the practical effects of various factors on carbon productivity in China. In addition, this paper constructs a low-carbon economic neural network model based on particle swarm optimization to study carbon emissions. Finally, on the basis of analysis and research, this paper puts forward policy recommendations for China’s future low-carbon development model, and then provides reference for guiding the development of China’s future low-carbon model and provides theoretical basis for subsequent related research. Show more

Keywords: Particle swarm optimization, multidimensional analysis, neural network, financial risk

DOI: 10.3233/IFS-179199

Citation: Journal of Intelligent & Fuzzy Systems, vol. 37, no. 5, pp. 6151-6163, 2019