Model Of Intelligent System Research Articles

IoT-based model for intelligent innovation practice system in higher education institutions

This article first provides an overview of the Internet of Things technology, mainly analyzing the characteristics of the Internet of Things technology and the impact of core technologies on education reform; secondly, it studies the specific impact of the Internet of Things technology on the education reform of local applied universities, which is mainly divided into three On the one hand, it promotes the construction of smart campus, the second is the realization of personalized learning methods, and the third is the promotion of smart teaching. Subsequently, the intelligent teaching based on the intelligent robot platform was proposed and the teaching demonstration was carried out. This research conducted an empirical study on third-year university students as the objects of teaching implementation. In the preparatory stage of teaching, the micro-curriculum of guided learning is produced, teaching activities are designed, and the study attitude and learner satisfaction questionnaire and interview outline are compiled. After the empirical teaching, analyzing the empirical results and related data, it is found that the application of intelligent robots in science courses can stimulate students’ interest in and enthusiasm in science courses; it can improve students’ creative thinking level and students’ learning satisfaction. Students’ perceived ease of use and perceived usefulness of the intelligent robot platform will affect students’ learning satisfaction, thereby affecting the teaching effect.

Use of Factors Related to the Consumption of Fast Moving Consumer Goods in Business Intelligence System for Managing Orders to Suppliers in Retail Chain

The study examines some aspects related to current trends in the modeling of business intelligent systems (BIS) specializing in retail chains for Fast Moving Consumer Goods (FMCG ) . Current concepts related to factors that influence business processes and their application in business intelligent order management systems in retail chains for FMCG are presented. The aim of the present study is to investigate the factors that have the strongest influence on the consumption of FMCG in retail chains and to derive the values that support business-intelligent processes for automated order management to suppliers. The studied factors presented in the presentation also include consideration of the structure of the incoming data streams, their extraction and their application in practice.

Нормативно-технические вопросы разработки безопасных автоматизированных интеллектуальных систем

Purpose of the Article. The purpose of the article is to address the regulatory and technical issues of effective creation, operation and operation of safe, reliable and effective systems based on artificial intelligence. The research method. Opportunities for conceptual and logical modeling of ergasystems and invariant architectures of rational modeling based on the problem-oriented version of the integrated “information-cybernetic-didactic” approach using the information and mathematical structure of the automated optical-electronic system of groundspace monitoring are considered. Results. Presented conceptual and logical model of the system of regulatory and technical regulation of systems based on artificial intelligence technologies, and the invariant architecture of the rational model of the artificial intelligence system, developed a method of solving the problem of the operation of the automated optical-electronic system of ground-space monitoring.

A methodological approach to the development of a technological platform for intelligent integrated energy system modelling

Modeling of intelligent integrated energy systems, which has a complex structure, is performed using specialized software, which is caused by the computational complexity of the models, methods and algorithms used. The paper lists the requirements for software for modeling intelligent integrated energy systems and concludes that it is necessary to develop a technological platform. A methodological approach to the development of a technological platform for modeling integrated energy systems is presented. The methodological approach includes the following components: principles of building a technological platform, architecture of a technological platform, and the structure of an ontology system, a method of automated integration of software components into a software system.

Compromised multi-granulation rough sets based on an attribute-extension chain

The multi-granulation rough sets serve as important hierarchical models for intelligent systems. However, their mainstream optimistic and pessimistic models are respectively too loose and strict, and this defect becomes especially serious in hierarchical processing on an attribute-expansion sequence. Aiming at the attribute-addition chain, compromised multi-granulation rough set models are proposed to systematically complement and balance the optimistic and pessimistic models. According to the knowledge refinement and measure order induced by the attribute-enlargement sequence, the basic measurement positioning and corresponding pointer labeling based on equilibrium statistics are used, and thus we construct four types of compromised models at three levels of knowledge, approximation, and accuracy. At the knowledge level, the median positioning of ordered granulations derives Compromised-Model 1; at the approximation level, the average positioning of approximation cardinalities is performed, and thus the separation and integration of dual approximations respectively generate Compromised-Models 2 and 3; at the accuracy level, the average positioning of applied accuracies yields Compromised-Model 4. Compromised-Models 1–4 adopt distinctive cognitive levels and statistical perspectives to improve and perfect the multi-granulation rough sets, and their properties and effectiveness are finally verified by information systems and data experiments.

Learning Bayesian Network Parameters With Small Data Set: A Parameter Extension under Constraints Method

Recent advances have illustrated substantial benefits from learning Bayesian networks (BNs). However, when the available data size is small, the BN parameter learning becomes a key challenge in many intelligent applications. By integrating both sample data and expert constraints, we propose a BN parameter learning algorithm with extension method-parameter extension under constraints (PEUC) by introducing related domain expert knowledge. Knowledge is transformed into inequality constraints which candidate parameter sets arise from the relative constraints space.The maximum entropy principle helps to estimate the parameter in statistical averaging model while candidate sets of BN parameters satisfy the constrained knowledge by bootstrapping techniques. Then BN parameters are estimated based on the real available sampled data set and extension streams of candidate parameters samples from the constraints space. The sample size is also taken into account according to the contribution to the final parameters. Experimental results of benchmark BN modeling problems demonstrate that PEUC algorithm tends to the classical MLE algorithm when the modeling data size is sufficient. Furthermore, when the available data size is small, the parameters of BN can be estimated by PEUC as well, and the learned accuracy is superior to MLE, MAP or QMAP algorithm. Finally, PEUC is also applied to a real bearing fault diagnosis case. The presented approach provides a new promising BN parameter learning way for more intelligent system modeling problems, particularly when the data sets are small.

Application of cognitive technologies for the formation of speech dialogue management models

Purpose of research. The aim of the study is the use of cognitive technologies for the formation of speech dialogue management models. At present, for the development of the Internet of things, the expansion of communicative opportunities for their interaction, it is important to improve speech dialogue management models in many areas. The need for dialogue can arise between cyber-physical systems, between a person and cyber-physical systems, between users, developers, and administrators. The speech dialogue management models covers many issues related to processing a speech signal, semantic analysis, understanding the meaning of speech, using cognitive mechanisms for interaction, and some others. A special place among them is occupied by the problem of building a speech dialogue between users, developers, and cyberphysical systems. This article is devoted to the consideration of the use of speech dialogue management models of intelligent systems, as well as users, developers, administrators.Materials and methods of research. New approaches and methods are required to solve the problems within the framework of the Industry 4.0. The industry 4.0 concept represents a variety of technologies, including the creation of cyber-physical systems, a variety of different protocols for their interaction. One of its main directions is the Internet of things. Cognitive mechanisms associated with the formation and application of concrete sensory images, concepts-representations, concepts-frames are used to solve the problems of model formation. To form the abilities and speech skills for the communicative activities of the participants of the interaction within the framework of the Industry 4.0 concept, the methods associated with mastering foreign language technologies were used. The ultimate goal of their use is to achieve the ability to master spontaneous speech in both everyday and professional situations. Mastering a foreign language involves the use of cognitive technologies, which allows you to develop the structure of mental operations.Results. Some features of the formation of a voice dialogue management model for intelligent systems and the preparation of interaction participants in the framework of the concept — users, developers, and industrial system administrators – are considered. The application of cognitive mechanisms for organizing and using the model of speech dialogue management is shown. The use of conceptual representations and scripting concepts in intelligent systems allows us to develop the structure of the world model. The application of cognitive mechanisms for training interaction participants, within the framework of the Industry 4.0 concept, improves their training by improving understanding of the material being studied by building logical connections and a mental model of the material. Using concepts allows you to build mental models of your own thoughts. At the end of all mental operations, participants in the interaction acquire the ability to form speech dialogue management models.Conclusion. The use of cognitive technologies makes it possible, both for intelligent systems and for interaction participants, to use generalized static structures of concepts, situations, and dynamic structures for real and mental operations. The active use of such structures makes it possible to better understand the current situation and successfully formulate and use voice dialogue management models for solving problems arising during the development of the Industry 4.0 concept.

Accurate vehicle location and tracking algorithms based on improved kernelized correlation motion model and Kalman filter in intelligent transport surveillance system

Vision-based traffic surveillance, an indispensable part of intelligent transport system (ITS), has been widely studied over past few years. Due to the factors such as visual occlusion, illumination change and pose variation, it is a challenging task to develop effective and efficient models for vehicle detection and tracking in surveillance videos. Although plenty of existing related models have been proposed, many problems still need to be resolved. A novel improved kernelized correlation tracking algorithm based on Kalman filter and motion model is proposed to solve the tracking accuracy deteriorated by fast-moving and severe occlusion. Firstly, an adaptive search region location method is proposed, where the optimal position is estimated by the uncertainty theory of the motion model so as to obtain the optimal search window. Secondly, a confidence strategy for similarity measurement is calculated by using the sharpness of the correlation peak and the smoothness constraint. Finally, the optimal confidence is introduced to get an adaptive update model. A large number of simulation experiments show that our proposed algorithm has more robust performance and anti-interference ability than the traditional KCF algorithm, which is suitable for intelligent transport system application.

Framework to forecast environment changes by optimized predictive modelling based on rough set and Elman neural network

The techniques pertaining to soft computing are the base for commencement, model and organization of intelligent systems in order to offer more perfect, economical and realistic solution which has minimal complexity levels. The concept of intelligent systems has for long supported objectives on sustainability, improvisation of efficiency and symbolized various kinds of activities like creation of jobs, earning profits, providing services and improvement in capacities in ICT. The applications based on this system are widespread in the technological market because of massive development in grid, cloud, mobile and big data applications and its corresponding connectivity advantages. ICT triggers data scientists to satisfy technical-based demands of intelligent systems around data analytics and big data applications. The major features of big data like that of reservation of designs on information and knowledge have offered the public undertaking an opportunity to enhance production levels, improved efficiency and its effectiveness. The main objective of this paper is to enhance the accuracy of predictive modelling using an optimized predictive modelling based on rough set (RS) and Elman neural network (ElNN). These advanced predictive models are designed on the basis of RS approach in initial stages and in later processes enhanced with the support of Elman-NN. RS has an excellent feature selection capability, and Elman-NN is the best at nonlinear system modelling. By integrating them, the proposed method can limit the input dimension and optimize the structure for ElNN modelling. This can reduce the mathematical computation complexity with the progress of predictive models. The experimental results indicate that through RS feature selection and the structure of Elman-NN, the predictive model can be simplified significantly with enhanced model performance. The predictive accuracy of data sets, namely air quality in Northern Taiwan, hazardous air pollutants, historical hourly weather data and US pollutants through optimization, is above 99%, and this model proves that the results of optimized predictive error are far better than those obtained by other neural networks like PCA-RBF, PCA-NN, FFNN-BP with PCA, MLR, FFNN-BP, ELM, SOM, RBF and ART2.

The construction of internet + piano intelligent network teaching system model

The construction of internet + piano intelligent network teaching system model

Establishment and research of state model of intelligent vehiclebend system based on kalman filter

In view of the problems of route selection and driving stability of intelligent vehicle in the process of turning, a state model of intelligent vehicle turning system control based on Kalman filter is proposed. Taking intelligent vehicle as the research object, according to the route of intelligent vehicle passing through a certain bend at uniform speed, the corresponding state transition model of intelligent vehicle’s speed and position is established, and the state model of intelligent vehicle’s bend system is analyzed, and the system state equation of intelligent vehicle in the process of bend movement based on Kalman filter is obtained. According to the state equation of the system, it can effectively monitor the speed, position and trajectory of the intelligent vehicle on the bend. Combining with Kalman filter algorithm, it can effectively reduce the noise of the control process and observation noise. It can be used to achieve more stable and accurate control of the intelligent vehicle in the bend movement.

Scheme Construction of VR Cloud Integration Intelligent System Based on Internet of Things

With the rapid development of mobile Internet and intelligent terminals, the privacy data generated by mobile applications is increasing. Because of the limited computing and storage capacity of mobile intelligent terminals, the security measures designed for traditional network terminal devices are not suitable for mobile intelligent terminals. This paper analyses the current application situation of virtual reality technology and Internet of Things technology and the bottleneck of engineering application and popularization, and probes into relevant problems. On this basis, a new model of intelligent system based on virtual reality and Internet of Things is proposed. The extended Spice protocol provides efficient support for front-end separation of displays and calculations. The encryption master key is generated by splicing the keys generated by the authentication cloud and the mobile intelligent terminal, and the master key is used to effectively prevent the mobile intelligent terminal and the cloud storage server from leaking the privacy data of the mobile user. Realize the unified management, flexible deployment, flexible delivery and automatic operation and maintenance of basic resources, and promote the transformation of application deployment from applying for equipment to applying for service.

Model Sistem Intelejensia Bisnis Untuk Perbaikan Pelayanan E-Service Pada PT. X

PT. X is one of the best airlines in Indonesia. The business intelligence system can participate as a tool to provide accurate and useful information for decision makers within the time limit that is determined to support decision making in the company's E-service services. The purpose of this study is to identify the factors that are attributes of E-Service services at PT. X. and proposed the adoption of the Business Intelligence system model for PT.X airline E-service services as a proposed service improvement. The data used are customer comment data on the Jakarta route to Singapore and Singapore to Jakarta for the period January to December 2015. The research method used is a combination to develop business intelligence research is the Pareto Diagram, Unified Modeling Language (UML), Naïve Bayes Data Mining algorithm, On Line Analytical Processing (OLAP), Extract, Transform, Loading (ETL), and Data Warehousing. From the results of data processing that has been done, it can be seen the factors attributes of E-service services are case origin, comment type, flight number, root case, and unit to charge. From the results of the calculation of the second stage of Naïve Bayes data mining, it is obtained that the greatest probability of the highest probability on the Jakarta route to Singapore is the prior probability between the customer care classification class and the suggestion form with a prior probability value of 0.92, between the inflight service classification class and the customer care priority value. equal to 1, class classification comment type compliment and customer care with prior values probability of 0.76. The prior probability of the greatest probability on the Singapore route to Jakarta is the prior probability between the customer care classification class and the suggestion form with the prior probability value of 0.92, between the inflight service classification class and the customer care with a probability prior value of 1, and between class classifications comment type compliment and customer care with a prior value of probability of 0.78. Based on the results of the largest posterior calculations, the proposed improvements were prioritized more on divisions or units to charge.

Modeling of intelligent distribution network self-healing control state transition based on FSM

In order to realize effective prevention from faults, cut-off the fault quickly and power supply recovery from power loss load in intelligent distribution network, this paper proposed a state transition model of self-healing control for intelligent distribution network based on Finite State Machine (FSM). We divided the running states into normal state and fault state, added finite variables to FSM. determined the operation state transition control schemes of intelligent distribution network self-healing control. Considering distributed generation(DG), we established the state transition model of intelligent distribution network self-healing control system on Matlab/Stateflow platform and applied to simulation example. The results show that the proposed state transition scheme is feasible and effective.

A Statistical out-of-Sample Forecast to Estimate Lithium-Ion Parameters That Determine State of Charge

Predicting state of charge (SOC) is crucial for an intelligent battery management system. Most of the existing SOC estimator models in literature use traditional methods such as bookkeeping and direct measurement, or rely on adaptive techniques such as neural networks. However, these models require the acquisition of significant experimental data on cell voltage and current, among others, to predict SOC with acceptable generalization performance. This paper proposes to compare two available statistical time-series forecasting methods, autoregressive integrated moving average (ARIMA) and Holt-Winters Exponential Smoothing (HWES), to forecast cell current and voltage of an actual 3.7V, 3.5Ah Lithium-ion battery for an unknown charging/discharging rate (C-rate) of C/10 using the values of the corresponding parameters from preceding C-rates of C/2, C/4, C/6, and C/8 obtained by performing lifecycle tests. The forecast values of current and voltage could, in practice, be used to calculate SOC using Coulomb-counting method [1]. The results are finally documented as a table in the attached figure. Proposed Work: Predicting the state of charge (SOC) of Lithium-ion batteries is critical for applications such as electric vehicles to determine the available capacity and function accordingly. Under scenarios where access to infrastructure and means to acquire experimental data on battery parameters is limited, the availability of an estimator model that is pre-trained for a given battery that can directly be used to predict SOC for any required C-rate is favorable. The paper proposes to use ARIMA and HWES algorithms to forecast current and voltage using historical time-series values of the same parameters obtained for C-rates C/2 to C/8. The voltage and current data are stationary as they both reject the null hypothesis in the Augmented Dickey-Fuller test [2] with a p-value of 0.01. Correlograms of the autocorrelation and partial autocorrelation functions for current and voltage are shown in Figure A in the attachment. The optimal values for the autoregressive integrative, and moving average terms are selected to be (34,1,4) such that their combination minimized the Akaike Information Criterion (AIC) [2]. The ACF and PACF plots for the fitted ARIMA model is illustrated in Figure B. The results of cell current and voltage predictions for C/10 made using the ARIMA model are shown in Figs. C and D, respectively, in the attachment. Results and discussion: The experimental setup comprised a 3.7V, 3.5Ah Li-ion battery that was subjected to different C-rates: C/2, C/4, C/6, C/8, and C/10, for 60 cycles each at discharging and charging currents of 850mAh and 2.6Ah for each test, respectively. The cell current and voltage values for C-rates C/2 through C/8 were augmented to form the time-series datasets to be used by ARIMA and HWES for model fitting. The corresponding datasets for C/10 were used solely during the forecasting phase, thereby making the forecasting process out-of-sample. For ARIMA, the mean squared error (MSE) between the forecast and observed values for C/10 voltage and current are 0.019 and 0.079, respectively. For HWES, the MSE values for C/10 voltage and current turned out to be higher, with 0.3996 and 1.6775, respectively. Besides MSE, three other errors, root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE), are also calculated for both models in predicting C/10 current and voltage. This table is also included in the attachment as Fig. G. It can be seen that ARIMA had a superior performance than HWES for this specific problem. Conclusion and Future Work: To develop a reliable SOC estimator model for intelligent battery management systems that are capable of predicting SOC for future, unseen C-rates using the available cell current and voltage data from previous C-rates, this paper proposes to use ARIMA. Results show that between ARIMA and HWES, the two most widely used statistical time-series forecasting methods, ARIMA shows superior performance. As a future work, artificial neural network-based SOC and voltage estimation techniques will be identified.

Design of Artificial Music Intelligence System Based on Fuzzy Perception Learning

The music intelligence of simulated human is of great significance in the research of music informatics. The purpose of this paper is to establish a formal system for describing music intelligence from the perspective of music memory-perception relationship, namely artificial music intelligent system. First, music intelligence is defined as the memory-perception ability of music elements, and a music intelligent system based on music memory mapping and music perception inversion is established by applying the principle of relational mapping-inversion. Secondly, from the perspective of music memory-perception fuzziness, music intelligence index based on fuzzy memory-perception and non-fuzzy memory-perception is proposed, and the solution method is given. Finally, a learning model of music intelligent system is established. Research shows that artificial music intelligence system is a kind of learning system of fuzzy memory-perception, the learning system embodies the basic characteristics of the music nervous system of the human brain, and to establish the artificial music intelligence system to explore people’s music intelligence, improve people’s music cognitive ability and value of music research has far-reaching significance.

The experimental system of automatic wheel drift and vehicle rollover prevention

The research topic relevance is determined by the global significance level of traffic safety improvement. The purpose of the work is to create mathematical model and software for the active vehicle safety experimental intelligent system. To solve this problem, methods of indirect vehicle state variables measurements were used. As a mathematical model, we used a system of equations for the wheels rotation speed on a bend. For estimating the parameters of the mass center and the wheels motion, standard wheel speed sensors and algorithms for processing the measurement data are used. The task of angular drift velocity determining based on wheels rotation frequency measurements is ill-posed and additional conditions are introduced to solve it. To predict the wheel drift and car rollover, extrapolate algorithms are used. These phenomena are prevented by the certain brake formation that limit the object speed at the predicted boundaries level. The research novelty is to create algorithms for an experimental system that provides the solution to the wheel drift and rollover prevention problem in a minimal configuration of technical means.

Application and Research of Intelligent Warehousing Based on IoT

The Internet of things (IoT) technology has been applied in many industries because of the basic features of total perception, reliable transmission and intelligent processing. At the same time, it also drives the innovation of the whole logistics industry, and its application field is expanding. At present, most of the domestic warehouse management systems still stay in the human information input, computer storage semi-automation level. There are many shortcomings such as low efficiency of management, large cost of manpower, slow information processing, low accuracy and so on. With the development of embedded equipment and wireless communication technology, the two dimensional code technology, intelligent computing technology, radio frequency technology and wireless sensing technology are applied to warehouse management. The realization of object and object perception, identifiable, networked intelligent management system has become an inevitable trend of development. In this paper, a model of intelligent storage system based on Internet of things is discussed in detail, and it is applied and verified in practical production and work.

Mathematical modeling of hybrid intelligent system to longitudinal landing control design

Mathematical modeling of hybrid intelligent system to longitudinal landing control design

รูปแบบคลาวด์เลิร์นนิงแบบอัจฉริยะเพื่อพัฒนาการรู้ดิจิทัลและทักษะการเรียนรู้แบบร่วมมือกัน

รูปแบบคลาวด์เลิร์นนิงแบบอัจฉริยะเพื่อพัฒนาการรู้ดิจิทัลและทักษะการเรียนรู้แบบร่วมมือกัน