An Introduction to Complex Systems Science and Its ApplicationsRead the full article
Complexity publishes original research and review articles across a broad range of disciplines with the purpose of reporting important advances in the scientific study of complex systems.
Chief Editor, Prof Sayama, is currently researching complex dynamical networks, human and social dynamics, artificial life, and interactive systems while working at Binghamton University, State University of New York.
Latest ArticlesMore articles
Research on the Key Issues of Big Data Quality Management, Evaluation, and Testing for Automotive Application Scenarios
This paper provides an in-depth analysis and discussion of the key issues of quality management, evaluation, and detection contained in big data for automotive application scenarios. A generalized big data quality management model and programming framework are proposed, and a series of data quality detection and repair interfaces are built to express the processing semantics of various data quality issues. Through this data quality management model and detection and repair interfaces, users can quickly build custom data quality detection and repair tasks for different data quality requirements. To improve the operational efficiency of complex data quality management algorithms in large-scale data scenarios, corresponding parallelization algorithms are studied and implemented for detection and repair algorithms with long computation time, including priority-based multiconditional function-dependent detection and repair algorithms, entity detection, and extraction algorithms based on semantic information and chunking techniques, and plain Bayesian-based missing value filling algorithms, and this paper proposes a data validity evaluation algorithm and enhances the validity of the original data in practical applications by adding temporal weights, and finally it passed the experimental validation. Through the comprehensive detection process of data importance, network busyness, duration of transmission process, and failure situation, the efficiency has been increased by 20%, and an adaptive data integrity detection method based on random algorithm and encryption algorithm is designed. After experimental verification, this method can effectively detect the integrity of the data transmission process and improve the application of data value, and the final effect is increased by 30.5%.
Multiple-Attribute Decision-Making Method Based on Normalized Geometric Aggregation Operators of Single-Valued Neutrosophic Hesitant Fuzzy Information
As a generalization of both single-valued neutrosophic element and hesitant fuzzy element, single-valued neutrosophic hesitant fuzzy element (SVNHFE) is an efficient tool for describing uncertain and imprecise information. Thus, it is of great significance to deal with single-valued neutrosophic hesitant fuzzy information for many practical problems. In this paper, we study the aggregation of SVNHFEs based on some normalized operations from geometric viewpoint. Firstly, two normalized operations are defined for processing SVNHFEs. Then, a series of normalized aggregation operators which fulfill some basic conditions of a valid aggregation operator are proposed. Additionally, a decision-making method is developed for resolving multiattribute decision-making problems based on the proposed operators. Finally, a numerical example is provided to illustrate the feasibility and effectiveness of the method.
Disturbance Observer-Based Robust Formation-Containment of Discrete-Time Multiagent Systems with Exogenous Disturbances
This paper investigates robust formation-containment control of discrete-time multiagent systems (MASs) with exogenous disturbances. Based on the discrete-time disturbance observer method, both state feedback and output feedback control protocols are proposed. Formation-containment conditions are obtained and convergency analysis is given according to Lyapunov stability theory. And, the corresponding control gains are obtained by solving some discrete-time algebraic Riccati equations. Numerical simulations are presented to illustrate the theoretical findings.
Application of Bayesian Vector Autoregressive Model in Regional Economic Forecast
The Bayesian vector autoregressive (BVAR) model introduces the statistical properties of variables as the prior distribution of the parameters into the traditional vector autoregressive (VAR) model, which can overcome the problem of too little freedom. The BVAR model established in this paper can overcome the problem of short time series data by using prior statistical information. In theory, it should have a good effect in China’s regional economic forecasting. Most regional forecasting model literature lacks out-of-sample forecasting error evaluation research in the real sense, but our early forecasts of major economic indicators provide an excellent opportunity for this paper to evaluate the actual forecast errors of the BVAR model in detail. The analysis in this paper shows that the prediction error of the BVAR model is very small and the prediction ability is very satisfactory. At the same time, this article also analyzes and points out the direction of efforts to further improve the prediction accuracy of the BVAR model.
Group Abnormal Behaviour Detection Algorithm Based on Global Optical Flow
Abnormal behaviour detection algorithm needs to conduct behaviour analysis on the basis of continuous video inclination tracking, and the robustness of the algorithm is reduced for the occlusion of moving targets, the occlusion of the environment, and the movement of targets with the same colour. For this reason, the optical flow information between RGB (red, green, and blue) images and video frames is used as the input of the network in view of group behaviour. Then, the direction, velocity, acceleration, and energy of the crowd were weighted and fused into a global optical flow descriptor. At the same time, the crowd trajectory map is extracted from the original image of a single frame. Following, in order to realize the detection of large displacement moving target and solve the problem that the traditional optical flow algorithm is only suitable for the detection of displacement moving target, a video abnormal behaviour detection algorithm based on the double-flow convolutional neural network is proposed. The network uses two network branches to learn spatial dimension information and temporal dimension information, respectively, and uses short- and long-time neural network to model the dependency relationship between long-time video frames, so as to obtain the final behaviour classification results. Simulation test results show that the proposed method can achieve good recognition effect on multiple datasets, and the performance of abnormal behaviour detection can be significantly improved by using interframe motion information.
Artificial Intelligence Teaching System and Data Processing Method Based on Big Data
With the rapid development of big data, artificial intelligence teaching systems have gradually been developed extensively. The powerful artificial intelligence teaching systems have become a tool for teachers and students to learn independently in various universities. The characteristic of artificial intelligence teaching system is to get rid of the constraints of traditional teaching time and space and build a brand-new learning environment, which is the mainstream trend of future learning. As the carrier of students’ autonomous learning, the artificial intelligence teaching system provides a wealth of learning resources and learning tools on the one hand, and on the other hand, it gradually accumulates more and more learning behaviors, learning status, and other large amounts of data, which is an in-depth study of online learning and provides valuable and generative dynamic resources. Based on relevant researches on domestic and foreign related learning analysis and common big data analysis methods, combined with actual learning evaluation goals, this paper proposes an artificial intelligence teaching system using big data analysis methods and a modeling process framework for online learning evaluation and uses student data to carry out predictive evaluation modeling to evaluate student learning outcomes. The evaluation results can enable teachers to predict whether students can successfully complete the course of learning after a period of teaching. Through the final evaluation, students’ learning problems can be discovered in time based on the evaluation results, and targeted interventions can be made for students who are at risk. The scientific and objective learning evaluation obtained in this study through data analysis can not only provide teachers with relevant information and provide personalized guidance to students, but also improve the adaptive and personalized service functions of the learning platform of the artificial intelligence teaching system, greatly reducing teachers teaching burden. Artificial intelligence teaching evaluation can help educators understand the problems in teaching, adjust teaching strategies in time, and improve teaching results.