Model Of Intelligent System Research Articles

Optimization Strategy Analysis of Intelligent Product Service System Based on Computer Simulation Technology

In order to solve the needs of a large number of users and the efficiency of user service requirements, an optimization strategy analysis method of intelligent product service system based on computer simulation technology is proposed. Aiming at the two challenges of massive requests and efficient service in the network intelligent service system, the characteristics of the network intelligent service system are analyzed, and the network intelligent service system is formally modeled as an agent system. The performance modeling, performance evaluation, and performance optimization methods of the network intelligent service system are proposed. In order to solve this massive demand, the performance modeling of the network intelligent service system is carried out based on queuing theory. This paper proposes a task assignment algorithm for the network intelligent service system. Through the application of these results, the processing efficiency of the entire medical insurance application system has been greatly improved, and the average completion time of all businesses has been shortened by 59%, providing new ideas for optimizing service methods and improving service quality.

Research on Fuzzy Control System of Intelligent Irrigation Based on Soil Moisture

Smart irrigation for sustainable agricultural water supply has been a critical initiative. In this paper, a fuzzy control system is designed to realize intelligent and precise irrigation by combining fuzzy control with traditional feedback control based on the features that soil moisture has significant influence and ease of detection and adjustment in practical irrigation. The opening time of solenoid valve is decided by the control system in real time, and the deviation and deviation rate of change for soil moisture are regarded as input variables. The model of intelligent irrigation fuzzy control system is built and compared with the model of PID control by Simulink for simulation. The results show that the fuzzy control system operates stably and achieves real-time precise irrigation with faster response and stronger robustness. The issue of reduced accuracy in irrigation due to the coupling between human and environmental factors is effectively solved by this design.

Fusion of deep learning based cyberattack detection and classification model for intelligent systems

Fusion of deep learning based cyberattack detection and classification model for intelligent systems

Operation Optimization of Microgrid System Based on Intelligent System Model

In order to improve the operation optimization effect of the microgrid system, this paper combines the intelligent system model to construct the operation optimization model of the microgrid system. Moreover, this paper conducts a quantitative calculation and research on the maximum compensation capacity of the active power filter device and proposes a harmonic power adaptive compensation control strategy in the case of the limited output capacity of the APF device. In addition, this paper adopts the method of extracting the harmonic current command in the synchronous coordinate system based on the band-pass filter composed of SOGI and combines the RDFT algorithm to determine the number of harmonics that can be compensated and the degree of compensation for the harmonic number. Finally, this paper combines simulation experiments and comprehensive evaluation to study and verify that the operation optimization effect of the microgrid system based on the intelligent system model is better and can effectively improve the operation effect of the microgrid system.

SYNTHESIS OF A FUZZY INTELLIGENT CONTROL SYSTEM FOR A DYNAMIC OBJECT BASED ON FUZZY LOGIC

This article discusses the synthesis of a fuzzy dynamic object-driven intelligent control system using a fuzzy mathematical apparatus. If the exact description of the control object is rather complicated and there is no a priori information about the operation of the system, it is considered more important to apply fuzzy intelligent control systems to control objects. Unlike classical models, fuzzy models are more flexible and allow taking into account the experience and intuition of specialists in a particular field. The fuzzy model of control and diagnostics is more adequate to the simulated reality, and the correct solution is obtained due to the accuracy of the initial data. Operating principle A fuzzy model of a fuzzy intelligent control system based on a fuzzy logical statement of the type "If A..., then B" has been created.

An Intelligent Bridge Management and Maintenance Model Using BIM Technology

In recent years, the bridge construction industry of China has developed rapidly. With the increase in bridge service lifetime, numerous damages and cracks have appeared that pose a direct threat to its structure and transportation safety. Therefore, a new approach to bridge management and maintenance is proposed using building information modeling (BIM) system. The objective of this paper is to monitor and manage bridge problems in real time. It will develop an intelligent bridge management and maintenance system model. This system will improve bridge management and maintenance and reduce the number of accidents on unsafe bridges. According to the data, the management and maintenance units can adopt scientific and reasonable methods to manage and restore bridges. This will ensure the safety and property of people. To improve the efficiency of bridge management and maintenance, a visible and accurate model is built with a combination of BIM technology. In this model, bridge damages are controlled and analyzed using BIM technology. The results show that the changes in the cracks and damage to the bridge within a year continue to rise from January to September and decrease from September to October. The crack of width and length continues to increase from October to December. As a case study, Tianyuan Bridge is selected to evaluate the technical condition of the bridge. The overall evaluation of the bridge result indicates a class II bridge.

Construction and Model Realization of Financial Intelligence System Based on Multisource Information Feature Mining.

Multisource information mining systems and related business intelligence technology are currently a hot topic of research. However, the current commercial applications and applications are not ideal in terms of application. Because there is still much work to be done before decision support, it is best to transition to them only financially. This paper examines the multisource part of the information used in mining and introduces research hotspots in the fields of accounting informatization, the development status of intelligent financial analysis software, the research and application status of data warehouse, data mining, and decision support systems. This paper examines the specific composition and content of a financial information system using information mining to lay a solid foundation. Financial intelligent analysis, financial intelligent monitoring, financial intelligent decision-making, and financial intelligent early warning are the four parts of the financial intelligent system. It then examined the structure and processing of the financial intelligence system and proposed a financial intelligence system operation strategy. Financial intelligence low-risk integrated implementation strategies and ideal financial intelligence models, according to the current state of research and practical applications. According to the findings, the overall discrimination accuracy of the financial information system based on mining multisource information features is up to 95%, which is 42% higher than the traditional model. The development and use of financial information benefit from the realization and exploration of the financial intelligence system model.

The diagnostic ability to classify neoplasias occurring in inflammatory bowel disease by artificial intelligence and endoscopists: A pilot study.

Although endoscopic resection with careful surveillance instead of total proctocolectomy become to be permitted for visible low-grade dysplasia, it is unclear how accurately endoscopists can differentiate these lesions, as classifying neoplasias occurring in inflammatory bowel disease (IBDN) is exceedingly challenging due to background chronic inflammation. We evaluated a pilot model of an artificial intelligence (AI) system for classifying IBDN and compared it with the endoscopist's ability. This study used a deep convolutional neural network, the EfficientNet-B3. Among patients who underwent treatment for IBDN at two hospitals between 2003 and 2021, we selected 862 non-magnified endoscopic images from 99 IBDN lesions and utilized 6375352 images that were increased by data augmentation for the development of AI. We evaluated the diagnostic ability of AI using two classifications: the "adenocarcinoma/high-grade dysplasia" and "low-grade dysplasia/sporadic adenoma/normal mucosa" groups. We compared the diagnostic accuracy between AI and endoscopists (three non-experts and four experts) using 186 test set images. The diagnostic ability of the experts/non-experts/AI for the two classifications in the test set images had a sensitivity of 60.5% (95% confidence interval [CI]: 54.5-66.3)/70.5% (95% CI: 63.8-76.6)/72.5% (95% CI: 60.4-82.5), specificity of 88.0% (95% CI: 84.7-90.8)/78.8% (95% CI: 74.3-83.1)/82.9% (95% CI: 74.8-89.2), and accuracy of 77.8% (95% CI: 74.7-80.8)/75.8% (95% CI: 72-79.3)/79.0% (95% CI: 72.5-84.6), respectively. The diagnostic accuracy of the two classifications of IBDN was higher than that of the experts. Our AI system is valuable enough to contribute to the next generation of clinical practice.

ASATM: Automated security assistant of threat models in intelligent transportation systems

The evolution of technology has led to the appearance of smart cities. An essential element in such cities is smart mobility that covers the subjects related to Intelligent Transportation Systems (ITS). The problem is that the ITS vulnerabilities may considerably harm the life quality and safety status of human beings living in smart cities. In fact, software and hardware systems are more exposed to security risks and threats. To reduce threats and secure software design, threat modelling has been proposed as a preventive solution in the software design phase. On the other hand, threat modelling is always criticised for being time consuming, complex, difficult, and error prone. The approach proposed in this study, that is, Automated Security Assistant of Threat Models (ASATM), is an automated solution that is capable of achieving a high level of security assurance. By defining concepts and conceptual modelling as well as implementing automated security assistant algorithms, ASATM introduces a new approach to identifying threats, extracting security requirements, and designing secure software. The proposed approach demonstrates a quantitative classification of security at three levels (insecure, secure, and threat), twelve sub-levels (nominal scale and colour scale), and a five-layer depth (human understandability and conditional probability). In this study, to evaluate the effectiveness of our approach, an example with various security parameters and scenarios was tested and the results confirmed the superiority of the proposed approach over the latest threat modelling approaches in terms of method, learning, and model understanding.

Petite term traffic flow prediction using deep learning for augmented flow of vehicles

An Intelligent Transport System (ITS) model that is contingent on the compulsion and expertise of the Traffic Prediction System in the contemporary urban context is proposed in this paper. Deep Learning (DL) is computationally becoming comfortable to train and set as many hyperparameters automatically as possible. The researchers and practitioners crave to set as many hyperparameters inevitably as possible in the DL. To be a great enabler, ITS has to find suitable solutions to issues like—alert on live time traffic information to interested parties along with facility to retrieve on demand the long-term statistical data, reduce the middling waiting time for commuters, offer protected, consistent, value-added services, control with vitality the signal timing based on the traffic flow etc., All these limitations call for instant attention. Among all the listed issues the problems like the sharp nonlinearities due to changeovers amid free flow, breakdown, retrieval and congestion. The contributions in this paper are as follows: (i) Adopt an ascendable approach to kindle the scarce information formed; (ii) Exploit the attention mechanism to exterminate the disadvantages of Long Short-Term Memory (LSTM) methods for traffic prediction; (iii) Suggest a new fusion smoothing model; (iv) Investigating, developing, and utilizing the Bayesian contextual bandits; (v) Recommend a Linear model based on LSTM, in combo with Bayesian contextual bandits. The travel speed prediction is done by LSTM. The results authenticate that the proposed model can adeptly achieve the goal of developing a system. The proposed model is definitely the best solution to overcome the issues.

Operational Data-Driven Intelligent Modelling and Visualization System for Real-World, On-Road Vehicle Emissions—A Case Study in Hangzhou City, China

On-road vehicle emissions play a crucial role in affecting air quality and human exposure, particularly in megacities. In the absence of comprehensive traffic monitoring networks with the general lack of intelligent transportation systems (ITSs) and big-data-driven, high-performance-computing (HPC) platforms, it remains challenging to constrain on-road vehicle emissions and capture their hotspots. Here, we established an intelligent modelling and visualization system driven by ITS traffic data for real-world, on-road vehicle emissions. Based on the HPC platform (named “City Brain”) and an agile Web Geographic Information System (WebGISs), this system can map real-time (hourly), hyperfine (10~1000 m) vehicle emissions (e.g., PM2.5, NOx, CO, and HC) and associated traffic states (e.g., vehicle-specific categories and traffic fluxes) over the Xiaoshan District in Hangzhou. Our results show sharp variations in on-road vehicle emissions on small scales, which even fluctuated up to 31.2 times within adjacent road links. Frequent and widespread emission hotspots were also exposed. Over custom spatiotemporal scopes, we virtually investigated and visualized the impacts of traffic control policies on the traffic states and on-road vehicle emissions. Such results have important implications for how traffic control policies should be optimized. Integrating this system with chemical transport models and air quality measurements would bridge the technical gap between air pollutant emissions, concentrations, and human exposure.

Cognitive Hybrid Intelligent Diagnostic System: Typical Architecture

The research refers to the modeling of the meaningful and relatively stable visual-figurative and verbal-sign representation of real problems in medical diagnostics of the human organs and systems. The core results of the research are presented. Here, a new visual metalanguage is proposed. It describes the solution of a diagnostic problem by combining several interconnected processes of reasoning in different languages defining “a state of human organs and systems”, “a diagnostic problem” and elements of its decomposition. In the paper, a subject-figurative model of the cognitive hybrid intelligent diagnostic system, its typical architecture, and a synthesis algorithm are provided. Due to the integration of imitation of an internal subject-figurative vision of medical diagnostic problems and the corresponding communication statements of private diagnoses with imitation of the behavior inherent for councils in problem situations, the future implementation of such system prototypes will reduce the number of medical errors. The further stage of this research is the approbation of all solutions for the problem of diagnosing diseases of the pancreas on the materials of the Kaliningrad Regional Clinical Hospital and experimental study of the system. The research is limited by the subject area of medicine but can be generalized to the other areas.

Evaluation model and algorithm of intelligent manufacturing system based on pattern recognition and big data

Evaluation model and algorithm of intelligent manufacturing system based on pattern recognition and big data

AoI research on PMU cloud side Cooperative System of active distribution network

Phasor measurement units (PMUs) are being widely installed in transmission networks. Many PMU based power system applications have been developed or are under development in academia and industry. For these applications, data status update is usually a key factor affecting its performance, especially for distribution network equipment information acquisition and control computing delay performance cannot accurately ensure the timely processing of services. Therefore, an index of information freshness is proposed—age of information(AoI). According to the model of intelligent computing system of distribution network equipment, the average peak information age of the system is calculated. Finally, the DQN method is adopted to minimize the peak information age. Simulation results show that the proposed service unloading optimization scheme based on DQN can effectively reduce the peak AoI of the system.

Intellectualization of information processing systems for monitoring complex objects and systems

Creating intelligent information processing systems for monitoring complex technical objects and systems is an important task today. This paper presents the principles and models for creating systems of this class. The decision-making process in intelligent information-measuring monitoring systems is described. The article presents a model of intelligent monitoring system and a model of decision-making in intelligent monitoring systems. The presented model of decision-making in intelligent monitoring systems allows estimating the efficiency of their functioning. The article proposes a structural scheme reflecting the sequence of decision-making tasks.

Application of Artificial Intelligence Techniques for the Determination of Groundwater Level Using Spatio-Temporal Parameters.

Increasing the depth of mining leads to the location of the mine pit below the groundwater level. The entry of groundwater into the mining pit increases costs as well as reduces efficiency and the level of work safety. Prediction of the groundwater level is a useful tool for managing groundwater resources in the mining area. In this study, to predict the groundwater level, multilayer perceptron, cascade forward, radial basis function, and generalized regression neural network models were developed. Moreover, four optimization algorithms, including Bayesian regularization, Levenberg–Marquardt, resilient backpropagation, and scaled conjugate gradient, are used to improve the performance and prediction ability of the multilayer perception and cascade forward neural networks. More than 1377 data points including 12 spatial parameters divided into two categories of sediments and bedrock (longitude, latitude, hydraulic conductivity of sediments and bedrock, effective porosity of sediments and bedrock, the electrical resistivity of sediments and bedrock, depth of sediments, surface level, bedrock level, and fault), and besides, 6 temporal parameters are used (day, month, year, drainage, evaporation, and rainfall). Also, to determine the best models and combine them, 165 extra validation data points are used. After identifying the best models from the three candidate models with a lower average absolute relative error (AARE) value, the committee machine intelligence system (CMIS) model has been developed. The proposed CMIS model predicts groundwater level data with high accuracy with an AARE value of less than 0.11%. Sensitivity analysis indicates that the electrical resistivity of sediments had the highest effect on the groundwater level. Outliers’ estimation applying the Leverage approach suggested that only 2% of the data points could be doubtful. Eventually, the results of modeling and estimating groundwater level fluctuations with low error indicate the high accuracy of machine learning methods that can be a good alternative to numerical modeling methods such as MODFLOW.

On the Performance of Machine Learning Models for Anomaly-Based Intelligent Intrusion Detection Systems for the Internet of Things

Anomaly-based machine learning-enabled intrusion detection systems (AML-IDSs) show low performance and prediction accuracy while detecting intrusions in the Internet of Things (IoT) than that of deep learning-based intrusion detection systems (DL-IDSs). In particular, AML-IDS that employ low complexity models for IoT, such as the principal component machine (PCA) method and the one-class support vector machine (1-SVM) method, are inefficient in detecting intrusions when compared to DL-IDS with the two-class neural network (2-NN) method. PCA and 1-SVM AML-IDS suffer from low detection rates compared to DL-IDS. The size of the data set and the number of features or variants in the data set may influence how well PCA and 1-SVM AML-IDS perform compared to DL-IDS. We attribute the low performance and prediction accuracy of the AML-IDS model to an imbalanced data set, a low similarity index between the training data and testing data, and the use of a single-learner model. The intrinsic limitations of the single-learner model have a direct impact on the accuracy of an intelligent IDS. Also, the dissimilarity between testing data and training data leads to an increasingly high rate of false positives (FPs) in AML-IDS than DL-IDS, which have low false alarms and high predictability. In this article, we examine the use of optimization techniques to enhance the performance of single-learner AML-IDS, such as PCA and 1-SVM AML-IDS models for building efficient, scalable, and distributed intelligent IDS for detecting intrusions in IoT. We evaluate these AML-IDS models by tuning hyperparameters and ensemble learning optimization techniques using the Microsoft Azure ML Studio (AMLS) platform and two data sets containing malicious and benign IoT and industrial IoT (IIoT) network traffic. Furthermore, we present a comparative analysis of AML-IDS models for IoT regarding their performance and predictability.

Research and Application of the Data Mining Technology in Economic Intelligence System.

In the context of the rapid development of the modern economy, information is particularly important in the economic field, and information determines the decision-making of enterprises. Therefore, how to quickly dig out information that is beneficial to the enterprise has become a crucial issue. This topic applies data mining technology to economic intelligent systems and obtains the data object model of economic intelligent systems through the integration of information. This article analyzes the interrelationship between its objects on this basis and uses data mining-related methods to mine it. The establishment of economic intelligence systems not only involves the establishment of mathematical models of economic systems, but also includes research on the algorithms applied to them. How to apply an algorithm to quickly and accurately extract the required economic intelligence domain information from the potential information in the database, or to provide a method to find the best solution, involves the use of association rules and classification prediction methods. The application of data mining algorithms can be used to study the application of economic intelligence systems. This paper develops and designs an economic intelligence information database and realizes the economic intelligence system on this basis, and realizes the research results. Finally, this paper has tested the dataset, and the results show that the classification accuracy of this algorithm is 2.64% higher than that of the ID3 algorithm.

Digital Protection Technology of Cultural Heritage Based on ArcGIS Geographic Information Technology Algorithm

In order to improve the effect of digital protection of cultural heritage, this paper analyzes the spatial and temporal characteristics of cultural heritage with the support of ArcGIS technology, conducts research on ArcGIS’ geographic information technology algorithm, and improves the algorithm with the support of digital technology. Moreover, this paper combines the watermark algorithm to digitally mark cultural heritage to improve the copyright effect of cultural heritage. In addition, this paper proposes a topological integrity verification method based on weak watermark vector geographic data to improve the reliability of digital processing of cultural heritage, and build an intelligent cultural heritage digital protection system model. The research results show that digital protection technology of cultural heritage based on the ArcGIS geographic information technology algorithm in this paper can play an important role in the digital protection of cultural heritage.

Energy Management Model of Intelligent Park Based on Improved Depth Deterministic Gradient Strategy Algorithm

The traditional distribution automation system, demand side management system, and distributed generation access and control system, respectively, solve the problems of regional distribution network power supply, customer power consumption, and new energy utilization to varying degrees. Intelligent Park evolved from the concept of intelligent park of State Grid Corporation, Modern enterprises, or residential areas that can make full use of modern communication, computer, automation, and other technologies to implement the power supply demand of the park. For the modern intelligent park with user-side temperature control load and demand response load access, an intelligent park energy management and optimal scheduling method based on deep reinforcement learning (DRL) algorithm is proposed. Through the interaction between the agent and the energy environment of the intelligent park, the control strategy is adaptively learned. This method can realize the continuous action control of energy management in intelligent park and can realize the optimal scheduling decision of intelligent park in various scenarios. Firstly, based on the characteristics and types of intelligent park aggregation unit, the environment model of intelligent park energy management system interacting with agent is established. Secondly, the basic principle of deep deterministic policy gradient deep algorithm is introduced, and on this basis, the key links of deep reinforcement learning algorithm, such as action space, state space, reward mechanism, neural network structure, and learning process, are designed. Finally, the effectiveness of the proposed algorithm is verified by an example of a city intelligent park.