Journal of Interconnection Networks

A recent trend in human-computer interaction has facilitated content production, such as innovation and information growth through intelligent systems, enabling unqualified users to describe a machine’s behaviour through visual programming. However, the difficulty could become similar to the standard coding techniques as the number of elements to be managed increases. Entrepreneurial education is defined as a collection of formalized lessons that advise, train, and educate all people who want to participate in socio-economic development through a project that promotes knowledge of entrepreneurship to advance the business. Hence, in this paper, the Human-computer interaction-based Entrepreneurship learning platform (HCI-ELP) has been proposed to boost student quality of life by enhancing self-confidence and changing the learning timeframe. HCI provides several promising implications for integrating knowledge management approaches, taking advantage of computer-supported interactive learning from entrepreneurship learning platforms. The suggested approach recommends collaboration to learn for students’ opinions on learning developed through a questionnaire’s tasks. Thus, the experimental results show that HCI-ELP achieves the highest performance rate to 97.66% and enhances student interaction in completing the task to improve curriculum development.

Education refers to ideologies, traditions, culture, and values that guide education to economics, politics, morals, religions, information, reality, comparative and historical aesthetic, and artistic school knowledge. The challenging characteristics in political education include lack in knowledge sharing, user’s interactive experience, and incentive mechanism has become an essential factor. In this paper, the Deep Learning-Based Innovative Ideological Behavior Education Model (DL-IIBEM) has been proposed to strengthen the mechanism to promote information exchange, enhance the user’s interactive experience, and make the platform perform efficiently. Knowledge Network Mechanism Analysis is integrated with DL-IIBEM to strengthen user feedback probability, the average probability of completing social media tasks on a popular network, and the predicted utility degree for individual users. The entire platform is dramatically improved. The simulation analysis is performed based on the performance ratio based on data set 1 (98.2%) and 2 (95.3%), skill development ratio (95.3%), accuracy ratio, the teaching methods in ideological and political education, and Students Achievements ratio (98.2%) prove the proposed framework’s reliability.

Our objective is to describe the speech production system from a non-linear physiological system perspective and reconstruct the attractor from the experimental speech data. Mutual information method is utilized to find out the time delay for embedding. The False Nearest Neighbour (FNN) method and Principal Component Analysis (PCA) method are used for optimizing the embedding dimension of time series. The time series obtained from the typical non-linear systems, Lorenz system and Rössler system, is used to standardize the methods and the Malayalam speech vowel time series of both genders of different age groups, sampled at three sampling frequencies (16kHz, 32kHz, 44.1kHz), are taken for analysis. It was observed that time delay varies from sample to sample and, it ought to be better to figure out the time delay with the embedding dimension analysis. The embedding dimension is shown to be independent of gender, age and sampling frequency and can be projected as five. Hence a five-dimensional hyperspace will probably be adequate for reconstructing attractor of speech time series.

Recently, the teaching and learning method in the conventional engineering education system needs a group of learners with personalized learning paths. The introduction of technologies like Artificial Intelligence will aid the learners to identify and detect learning opportunities utilizing historical information, present student profile and success data from an institution, and recommend learning measures to enhance their performance. This study proposes an Artificial Intelligence-based Meta-Heuristic Approach (AIMHA) for personalized learning detection systems and quality management. The proposed model has been utilized to optimize learning effectiveness by considering the nature of the learning path and the number of simultaneous visits to every learning action. In addition, a quality resolution can be determined by a meta-heuristic approach. The simulation findings of the learning actions have been utilized to examine the efficiency of the suggested method. The proposed method is evaluated learning activities achieved an efficiency ratio of 92.3%, sensitivity analysis ratio of 88.4%, performance ratio of 92.3%, precision ratio of 94.3% compared to other existing models.

In the digital world of today, any enterprise that deals with the amounts of data in Warehouse Management Systems (WMS) are an important component. Furthermore, the amount of data being raisedand its complexity have become more challenging to maintain the WMS efficiency. Therefore, a device is required, which can manage such complexities autonomously with no human intervention. In this paper, Hybrid Machine Learning with the Internet of Things (HML-IoT) improves isolated doors. Furthermore, operating machine performance in the factory of hazardous goods. Decision-Making Algorithm (DMA) Data from the customer’s holding space’s dangerous goods warehouses shall be checked using separated doors. This paper’s significant aspect is that inventory and inventory operation’s organizational performance can be increased, further logistics costs minimized utilizing the fair use of isolated doors. Finally, the HML-IoT model integrated hazardous goods warehouse with isolated doors has been contrasted with the current one, demonstrating that the previous one has greater efficacy.

Nowadays, in various educational institutions, artificial intelligence technology is applied effectively and successfully. This artificial intelligence improves learning and student development in academic performance. Challenges of the conventional education approach, students’ dependence on teachers in all resources for study, unavailability of professional instructors, and a greater focus on conditioning learning than practical usefulness lead to lower learning performance. In this paper integrated teaching-learning model approach has been proposed using artificial intelligence in student education. It involves speeding up fulfilling education targets by reducing barriers to entry, automating management processes, and maximizing learning performance. The proposed ITLMA method used the naive Bayes algorithm to evaluate the student ranking using a class score, task, project score, and final exam. The result of artificial intelligence-based ITLMA and naive Bayes algorithm hasa high accuracy ratio of 80.1% with less error ratio of 15.7%, high prediction 88.2%, precision 98.2%, and improves student and teacher interaction compared to other existing methods.

Automobile architecture is a crucial phase in the process of design. The model assessment process in the hybrid vehicle modeling assessment becomes more in-depth, and designers exchange ideas. The critical aspect of automotive modeling is that various models have varying views on vehicle styling. The evaluation process is long, complicated, and efficient in automotive simulation. The evaluation process takes time. Therefore, in the paper, an Automobile Modelling Optimization Design Based on Virtual Reality Technology (AMOD-VRT) is proposed to improve automobile modeling and design research to be more interactive. Computational Design Method is used to create and design the entire vehicle as well as its surrounding environment. An Integrated Virtual Analysis can enclose the models mentioned above and create a virtual environment in which the user can interact to design a model virtually by themselves. The paper provides complete virtual design modeling of an automobile, allowing the user to work more efficiently based on the results. By applying virtual reality technology in the automobile design phase, interactive and network-based remote research on automobile modeling can make the automobile design progression more appropriate, easier to communicate with designers and decrease automobile design’s development cost and cycle. The simulation analysis is performed based on safety, performance, and efficiency, proving the reliability of the proposed framework. Various parameters obtain the simulation results on automobile design as the automobile vehicle design performance ratio is 87.16%, increasing the visual effects in AMOD ratio is 88.77%, improving visual effects with optimized design ratio is 84.5%, interaction and collaboration of automobile modeling ratio are 82.26% and reduce vehicles accident using virtual reality ratio is 93.80%. The computer-based virtual reality technology in the automotive industry can effectively accelerate new product development in the future.

Big data is an unstructured data set with a considerable volume, coming from various sources such as the internet, business organizations, etc., in various formats. Predicting consumer behavior is a core responsibility for most dealers. Market research can show consumer intentions; it can be a big order for a best-designed research project to penetrate the veil, protecting real customer motivations from closer scrutiny. Customer behavior usually focuses on customer data mining, and each model is structured at one stage to answer one query. Customer behavior prediction is a complex and unpredictable challenge. In this paper, advanced mathematical and big data analytical (BDA) methods to predict customer behavior. Predictive behavior analytics can provide modern marketers with multiple insights to optimize efforts in their strategies. This model goes beyond analyzing historical evidence and making the most knowledgeable assumptions about what will happen in the future using mathematical. Because the method is complex, it is quite straightforward for most customers. As a result, most consumer behavior models, so many variables that produce predictions that are usually quite accurate using big data. This paper attempts to develop a model of association rule mining to predict customers’ behavior, improve accuracy, and derive major consumer data patterns. The finding recommended BDA method improves Big data analytics usability in the organization (98.2%), risk management ratio (96.2%), operational cost (97.1%), customer feedback ratio (98.5%), and demand prediction ratio (95.2%).

With the rapid explosion of the data streams from the applications, ensuring accurate data analysis is essential for effective real-time decision making. Nowadays, data stream applications often confront the missing values that affect the performance of the classification models. Several imputation models have adopted the deep learning algorithms for estimating the missing values; however, the lack of parameter and structure tuning in classification, degrade the performance for data imputation. This work presents the missing data imputation model using the adaptive deep incremental learning algorithm for streaming applications. The proposed approach incorporates two main processes: enhancing the deep incremental learning algorithm and enhancing deep incremental learning-based imputation. Initially, the proposed approach focuses on tuning the learning rate with both the Adaptive Moment Estimation (Adam) along with Stochastic Gradient Descent (SGD) optimizers and tuning the hidden neurons. Secondly, the proposed approach applies the enhanced deep incremental learning algorithm to estimate the imputed values in two steps: (i) imputation process to predict the missing values based on the temporal-proximity and (ii) generation of complete IoT dataset by imputing the missing values from both the predicted values. The experimental outcomes illustrate that the proposed imputation model effectively transforms the incomplete dataset into a complete dataset with minimal error.

Air contamination, water waste, and radioactive contamination are significant environmental issues. Adequate supervision is needed to ensure economic sustainability through the preservation of a good society. Environmental tracking has become a Smart environment monitoring (SEM) system in recent times, with developments in the Internet of Things and the creation of advanced detectors. This situation evaluates substantial achievements and scientific studies on SEM, including air quality control, water management, radiation emissions, and agricultural practices. A Wireless sensor network and IoT integrated system for Smart environment monitoring (WSN-IoT-SEC) framework are proposed in this research. The analysis will be divided employing SEM techniques applications, and each aim will then be further studied in terms of the detectors, machine learning models, and classifiers operated. A systematic study was carried out based on the study’s evaluated results and patterns, indicating important suggestions and the SEM analysis’s influence. The researchers have discussed objectively how the advancements in mobile technologies, IoT, and wireless sensor networks allow the control of the atmosphere an intelligent monitoring device. Eventually, the concept of rigorous machine learning techniques has been proposed, denouncing techniques and developing appropriate WSN specifications.

There are various applications of clustering in the fields of machine learning, data mining, data compression along with pattern recognition. The existent techniques like the Llyods algorithm (sometimes called k-means) were affected by the issue of the algorithm which converges to a local optimum along with no approximation guarantee. For overcoming these shortcomings, an efficient k-means clustering approach is offered by this paper for stream data mining. Coreset is a popular and fundamental concept for k-means clustering in stream data. In each step, reduction determines a coreset of inputs, and represents the error, where P represents number of input points according to nested property of coreset. Hence, a bit reduction in error of final coreset gets n times more accurate. Therefore, this motivated the author to propose a new coreset-reduction algorithm. The proposed algorithm executed on the Covertype dataset, Spambase dataset, Census 1990 dataset, Bigcross dataset, and Tower dataset. Our algorithm outperforms with competitive algorithms like Streamkm++, BICO (BIRCH meets Coresets for k-means clustering), and BIRCH (Balance Iterative Reducing and Clustering using Hierarchies.

In this context, the uses of computers, the Human-computer interface (HCI) system, can assist interaction on-demand services. HCI method facilitates ventilated patients to interact with computers about their needs using their brain’s electrical activity. To accomplish this, an HCI framework is developed in this research to facilitate visual feedback system (VFS) using an augmentative communication approach. Augmentative communication (AC.) or icon-based services are incorporated with a portable monitor placed in front of a patient; they can look at the screen to select (ask) their appropriate needs-related icons. The services have been achieved by capturing and processing patients’ electromagnetic brain activates during the icon selection by their eye flickering moment recording using wearable Electroencephalogram (EEG). The flickering icons on the screen conveying an appropriate message to the monitoring unit computer, and the monitoring unit can respond to the patient’s request using VFS. The HCI system is comprised of the following methodologies to achieve augmentative communication-based services such as EEG signals acquisition, filtering, partition-based feature extraction, and fusion and fish swarm optimized Deep Hopfield neural network FSODHNN based classifier. The evolution results of the VSF based HCI framework are demonstrated successfully. It obtained the highest accuracy of 99.11%, specificity of 99.05%, the sensitivity of 99.09%, and the lowest RMSE of 0.98, MSE of 0.92 in icon identification/ selection.

It is now possible to make the logical thinking of humans, computer-controlled robots, and technology on the educational Environment platform by using artificial intelligence. These method-based robotic systems begin replacing human resources in all industries, which helps resolve various characteristic difficulties that include emotional skills, creative thinking, cognitive, and depletion in the educational platform. The Adaptive Artificial Intelligence Technique (AAIT) has been refined in this study to fulfill the learning objective of increased higher-order learning and skill acquisition in the Educational Environment. It enables more intelligent decision-making by taking into account all essential aspects of a company. As a result, big data plays a crucial role in today’s businesses. A powerful tool for proactive and automated management when combined with artificial intelligence (AI). Saving time and money by automating and optimizing routine tasks may be possible for your business with the right AI technology. Productivity and operational efficiencies will be increased. Use cognitive technologies to make faster business decisions. Therefore, the learning achievement model (LAM) and Risk Student Model (RSM) are established on the educational environment platform. As well as optimizing interpersonal resilience, the Learning Achievement Model is also utilized to increase innovative abilities in the Educational Platform. In the Danger Class Diagram, the Estimation Algorithm reduces the risk of learning failure, enhances cognition, and deprives the recognizing platform. Experiments and simulations are conducted to determine the reliability of the proposed framework based on the accuracy, F-Means, Sensitivity, specificity, and Performance (SSP).

Consumers can select their goods and resources in several ways, significantly affecting customer preference in the online world and raising network customers’ demands to anticipate their purchasing pattern. The current work aims to identify buying patterns from consumers’ purchase history (IBP-CPH) framework for analyzing the evolving trend of customer decision-making in the global marketplace. The project is carried out in two stages to achieve the goals. A comprehensive research analysis is conducted to evaluate the latest consumer behavior trends in the digital economy in this first stage. In the second stage, identifying buying patterns from consumers’ purchase history (IBP-CPH) framework identifies the finalized factor’s preference amounts (s). The concept of a fugitive setting requires the incoherence of information to be recorded. The results achieved in this research stated that buyers are very aware of new and sophisticated brands and brand consistency so that internet companies can keep their customers on their web platforms.

Against the background of the growing development of the Internet of Things, this article conducts research on more efficient methods for controlling the interconnection of all things, and proposes that smart devices use the same operating platform, and the human-computer interface presents universal modular controls for manipulation, it can satisfy the requirement that one device controls several different types of controlled device simultaneously. At the same time, the interactive method uses the controlled device to actively submit control content to the control device, and discusses the human-computer interactive control method applicable to the Internet of Everything, and strives to achieve a convenient and easy-to-use human-computer control experience.

Artificial Intelligence (AI) assisted educational institutions extensively utilize electronic learning context to guarantee improved teaching and learning experiences accompanied by educational activities. E-learning or online learning plays a significant role in Chinese higher education. There is a challenge to implement e-learning in China’s higher education to improve course resources, student learning style prediction, teaching quality, and service support. Hence in this paper, Artificial Intelligence based Efficient E-learning Framework (AI-EELF) has been proposed to overcome the challenges faced by China’s higher education while implementing e-learning modules. The collected student data can be efficiently utilized and exploited to progress in an adaptive learning environment. The proposed AI-EELF method introduces multiple learning models to enhance teaching quality and predict the student learning style. The experimental results show that the proposed AI-EELF achieves high performance, prediction ratio in determining students’ learning style and improves teaching quality compared to other existing methods.

Based on the big data mining method of petrophysical data, this paper studies the method and application of BP neural network to establish nonlinear interpretation model in distributed cloud computing environment. The nonlinear mapping relationship between the relative objective logging response and actual formation component is established by extracting the data mining result model, which overcomes existing deficiencies of the conventional logging interpretation procedure based on the homogeneity theory, linear hypothesis and the use of statistical experience simplifying model and parameters. The results show that network prediction model has been improved and has superior reference value for solving practical problems of interpretation under complex geological conditions.

As the decision-making brain for power system operation, grid regulation and operation is a comprehensive decision-making control that combines a large amount of data, mechanism analysis, operating procedures and professional experience, and a new generation of artificial intelligence development ideas and evolution characterized by data-driven and knowledge-guided. The directions are very close. However, the current scheduling control is still based on experience and manual analysis. The massive and diverse data of the control center and the lack of logical models between the plans require a large amount of experience and knowledge associations by the control personnel. There are more repetitive human brain labor and relatively low intelligence. Therefore, deep learning is applied to the learning of power control knowledge, and a semantic understanding network based on deep Long Short Term Memory is proposed. It uses sequence labeling to extract in-depth semantic related information of different keywords and query questions, and finds key information about language problems in order to achieve fine-grained and precise query. Experiments show that the proposed network model is superior to the previous methods, and it achieves better performance in the joint extraction of fine-grained evaluation words and evaluation objects, extracts the key information and deep semantic information of query problems and corresponding cases, and realizes power scheduling based on voice interaction The model can be effectively applied in the field of power dispatching and solve a large number of problems in power dispatching and control.

A synopsis of a multidisciplinary research initiative focused on critical strategies for the genuine independent flight of tiny, vertical flying take-off (VTOL) unmanned aerial vehicles (UAVs). The research activities are the flight testbed, a simulation and test environment, and integrated components for onboard navigation, perception, design, and control. The necessity to create an unmanned helicopter system in different new civil applications cannot be overlooked. A highly reliable model may be used in the design, analysis, and implementation. The helicopter is fitted with a reference system for flight test data measurement and recording attitude heading reference system (AHRS) and the accompanying data storage modules. Recently, artificial intelligence-based deep learning (DL) has demonstrated excellent outcomes for a wide range of robotic activities in the areas of perception, planning, location, and management. Its remarkable skills to learn from complex data obtained in actual surroundings make it appropriate for many autonomous robotic applications. At the same time, UHS is currently widely utilized in various civil tasks in security, cinematography, disaster assistance, package delivery, or warehouse management (Unmanned Helicopter System). This paper conducted detailed work on current applications and the most significant advances and their performance and limits for the DL-UHS method. Furthermore, the essential strategies for deep learning are explained in depth — finally, discussing the principal hurdles of applying deep learning for UHS solutions. The proposed DL-UHS enhance outcome to evaluate the control strategies for the unmanned helicopter to achieve the low signal to noise error ratio of 31.3%, the error rate of 33.6%, the high-performance ratio of 91.4%, enhance accurate path planning 97.5%, prediction ratio of 96.3%, less trajectory cost ratio of 17.8% and increased safety tracking rate 93.6% when compared to other popular methods.

The appreciation system of art works is a system that combines art with computer. It can realize the appreciation and appreciation of art works through computer, so that more people can come into contact with art works and improve people’s appreciation ability and spiritual and cultural life level of art works. The system is an application system based on Web application program and running under Windows system. The whole project development framework is a popular web framework. It is an application-oriented system constructed by using java development language, Oracle database as data storage support in persistence layer, Tomcat as application server and JSP technology. The function of the system is mainly divided into two parts. The administrator part only realizes the operation of adding, modifying and deleting the relevant information of the art works, including the detailed information of the works, the relevant information of the painter, the background art management and comment management of the art works, and the user information management; In the user part, it mainly realizes the functions of browsing, understanding and learning art works, and increases the functions of attention and comment on works. After development and debugging, the system runs normally, all functions of the administrator side are basically realized, and relevant operations can be carried out; The functions of the client are basically all realized. Users can choose some functions of the system according to their preferences.

Theft of electricity is a significant loss of power sources. This fraud is mostly attributed to users’ actions such as removing the power supply, misuse of the power supply, etc. This analysis provides a way to handle the bypass and abuse of energy meters. A detection method of disconnection of low voltage anti-theft transformer (DM-DLVATT) to detect electricity theft is proposed in this research. The device architecture on a designed microcontroller’s measurement of two sensors. Although one of the new sensors controls the consumer charge’s power, the consumer has mounted the energy consumed by all modules while maintaining the device. The robbery suggests some difference between the interpreted values. There is also a temporary adjustment in the meter to restart the meter until it is altered. To recharge power products and track carbon emissions, the consumer often has remote access to electricity monitors. The device has been calculated correctly, and any effort has been made to circumvent or modify the voltage regulator. Finally, all disreputable actions using GSM technologies have been registered.

This exploration aims to transfer, process and store multimedia information timely, accurately and comprehensively through computer comprehensive technology processing, and organically combine various elements under the background of big data analysis, so as to form a complete intelligent platform design for multimedia information processing and application. In this exploration, the intelligent vehicle monitoring system is taken as an example. Data acquisition, data transmission, real-time data processing, data storage and data application are realized through the real-time data stream processing framework of $\mathrm{\text{Flume}}+\mathrm{\text{Kafka}}+\mathrm{\text{Storm}}$ of big data technology. Data interaction is realized through Spring, Spring MVC, VUE front-end framework, and Ajax asynchronous communication local update technology. Data storage is achieved through Red is cache database, and intelligent vehicle operation supervision system is achieved through multimedia information technology processing. Its purpose is to manage the vehicle information, real-time monitor the running state of the vehicle and give an alarm when there are some problems. The basic functions of vehicle operation monitoring and management system based on big data analysis are realized. The research on the design of vehicle operation monitoring and management system based on big data analysis shows that big data technology can be applied to the design of computer multimedia intelligent platform, and provides a reference case for the development of computer multimedia intelligent platform based on big data analysis.

Socially, politically, and morally, the world of sport is still changing. On the other hand, technology has been the most prevalent transition in the sport over the last century. Thanks to modern science, athletes can now go higher, run quicker, and, most importantly, remain healthy. Although academics, agencies, and policymakers had already urged physical education teachers to use technology in their classrooms, in many of these situations, technology is used for administrative purposes, including tracking enrolment and measuring, documenting, and reporting students’ work. Thus, this paper suggests an intelligent Student Actions Evaluation System using Deep Learning (iSAES-DL)for student monitoring in physical education. This model uses the deep convolution neural network for the classification of risky actions. This model further evaluates the learners’ degree of learning, retention, and achievements and suggests improvements and corrective measures. It highlights the benefits, uses, and limitations of applying deep learning techniques and IoT devices to develop learning analytics systems in the physical, educational domain. Eventually, output criteria such as comprehension, concentration, retention, and learner attainment are given a feature-by-feature analysis of the proposed methodology and traditional teaching-learning approaches. Finally, the classification algorithm is contrasted to other deep learning algorithms with an F1-score of 97.86%.

With the widespread application of Geographic Information System (GIS) technology in urban green space management system, the refinement of greening management puts forward the demand for upgrading the system. Taking the construction of urban green space management system in Wuxi as an example, this paper reverses the conventional operation of building database before system, and puts forward the method of management-oriented system upgrading. Through the research on the status quo of urban greening management, starting from the analysis of management requirements, the management requirements are transformed into system design requirements, so that the system upgrade is guided by the urban greening management requirements. It solves the problems of large amount of and time-consuming data input during the upgrading and construction of the system, which leads to long process and data lag when it is put into use. After the rapid upgrade, along with the refinement of daily management, the system has been continuously improved, and has received good results in the depth and breadth of data.

To strengthen urban tourism sustainable development, this paper puts forward the extraction method of tourism sustainable development path under the background of artificial intelligence + smart city construction. Based on the conceptual model of influencing factors of smart city sustainable development, this paper analyzes the connotation of latent variables. And we are designing a structural analysis model to analyze the current situation of urban tourism sustainable development, analyzing the total effect of parameter factors, formulating the path of smart city tourism sustainable development corresponding to the parameters, and taking Anhui Province as an example. To guide the construction and perfection of the industrial chain of the smart city’s sustainable development of industrial tourism, this paper constructs the system model of smart city, analyses the sustainable development model of Anhui smart city, and designs the extraction method of the sustainable development path of intelligent city tourism.

For the accuracy of network security management, an ISM-based analysis method on the influencing factors of network security situation (NSS) is proposed. The 17 factors of NSS were constructed first, the ISM of NSS influencing factors was established, and Matlab2019 was used for simulation. The results showed that the offensive and defensive game factors, such as attack method, attack tool, attack path, and defense strategy, are the direct influencing factors of NSS; the internal environmental factors such as operating system, application service, network bandwidth, network security device, user security awareness, and network topology are the necessary influencing factors; the external environmental factors such as legal environment, institutional environment, technical environment and business importance (economic environment) are the indirect influencing factors; the vulnerability factors such as asset value, vulnerability and open port are the fundamental influencing factors. The corresponding advice for management was put forward at the end of the paper.

Attribute reduction is proved to be a non-deterministic polynomial problem (NP). Minimal attribute reduction is the main research content in rough set theory. We find that in the traditional rough set attribute reduction algorithm, the rough set attribute reduction based on discrete particle swarm optimization (DPSO) performs well. However, the fitness function of this method has some limitations. When the minimum attribute reduction result is the conditional attribute set itself, the correct result cannot be obtained. For enhancing the accuracy and efficiency of attribute reduction, we propose an attribute reduction algorithm based on DPSO and variable precision rough set (VPRS). The proposed algorithm uses VPRS to process data more accurately. The new fitness function is constructed, and the attribute dependence is used as the function judgment basis. It can be adjusted automatically as the discrete binary particle swarm evolves, ensuring the convergence speed and evolution direction. Experimental results show that compared with traditional method, the proposed algorithm has stronger effectiveness and higher application value.

Artificial intelligence can open modern opportunities and potentials for smart education. Smart learning purposes at providing holistic learning to learners utilizing modern technologies to fully prepare them for a fast-evolving world where adaptability is vital. With the advancement of technologies and within modern society, smart education will pose several challenges, like educational structures, pedagogical theory, educational ideology, technology leadership, and teachers’ learning leadership. Therefore, in this paper, an Intelligent Knowledge-based recommender system (IKRS) has been proposed using artificial intelligence for smart education. The recommendation is generated by the genetic algorithm and K-nearest neighbor algorithm (KNN) utilizing the optimized weight attributes vectors that signify the learner’s opinions. The experimental results show that the suggested IKRS model enhances student-teacher interaction, student involvement level, learning quality and predicts students’ learning style compared to other existing methods.

The integrated chatbot for artificial intelligence customizes the learning experience for the students in higher education platform. The chatbot tests the answers of the students and offers insights for the students to improve their learning skills. Further, It helps to improve students’ thinking ability and expectations in higher education platform. The demanding factors for the students in the higher education platform include the need for interactive learning in a non-linear world, enhancing the thinking ability and expectations of the students. This paper proposes Artificial Intelligence Based Inquiry Evaluation Student Learning System (AI-IESLS) to increase interactive learning experience in a non-linear environment. The principal aim of this system is to improve the learning ability of the student on a specific subject using concept mapping in the chatbot. In addition, mapping has been validated for students based on the probability distribution analysis using a concept mapping. Besides, the probability graph’s curve generated by this system assesses the student’s understanding of the topic. The simulation results have been analyzed among students based on concept mapping using the AI-IESLS system in correlation with the traditional approach based on assessment ratio, feedbacks, reciprocity, timing analysis, expectation ratio, and active learning factor.

With the continuous expansion of the city scale and the increasing population, people have put forward higher requirements for the speed, reliability and economy of logistics distribution. Although there have been many achievements in the research on the vehicle optimal scheduling decision model and its solution algorithm, there are some problems such as low solution efficiency, long time consumption, and easy to fall into the local optimal solution. The purpose of this paper is to study the model of vehicle scheduling problem in distribution center based on improved differential evolution algorithm. This paper firstly makes a simple analysis of the vehicle distribution route optimization problem, and points out the main factors that constitute the route optimization problem; then analyzes the principle of the differential evolution algorithm, and on this basis, the differential evolution algorithm is improved. In the experimental part, this paper takes a distribution center as the research object, and proposes the implementation steps of the algorithm of the vehicle scheduling problem based on the improved differential evolution algorithm. And test the running cost of the improved differential evolution algorithm and differential evolution algorithm. Experimental results show that applying the improved differential evolution algorithm to vehicle scheduling problems has certain practicality. When the number of iterations reaches 60, the running cost of the improved differential evolution algorithm is 1,200 yuan, and the running cost of the differential evolution algorithm is 1,300 yuan.

The traditional low delay transmission model of Internet of things has the problem of high packet loss rate, so a low delay transmission model of Internet of things based on data spectrum is designed. Firstly, the data preprocessing of the Internet of things mainly includes data fusion, data compression and data filtering, then the trust model is established, and finally the task transmission link model of the Internet of things is constructed to realize the low delay transmission of the Internet of things. The experimental results show that the low delay transmission model of IOT based on data spectrum has lower packet loss rate, higher network throughput and higher network resource utilization than the traditional model.

In order to solve the problem that the evaluation algorithm is easy to fall into local extremum, which leads to slow convergence speed, a skilled talent quality evaluation algorithm based on a deep belief network model was designed. Establish an evaluation set with 4 first level indicators and 14 second level indicators, and calculate the corresponding weights to complete the construction of the evaluation index system. A DBN structure composed of several RBMs and a BP network is constructed. Based on the DBN, a quality evaluation algorithm is designed. The algorithm training is used to evaluate the test data and output the evaluation level. The experimental results show that the convergence speed of DBN based evaluation algorithm is significantly better than that of BP neural network and SVM based evaluation algorithm under the same number of iterations, which is suitable for the accurate evaluation of talent quality.

With the deepening of China’s reform and opening up, people’s living standards have been continuously improved, which has promoted the rapid development of our country’s culture and arts, such as music. As an important part of music, dance plays an important role in the culture and art of our country. People can use dance gestures to express moods or inner feelings that cannot be expressed in words. In order for the dance to be received and favored by people, it is necessary to have better ideas to express emotions, which is related to the choreographer of the dance. This article takes choreographer as the research object, uses the music feature extraction technology in machine learning to the choreographer, applies the extracted music feature information to the choreographer, and synchronizes the audio and video to achieve better dance effect, which has important research value.

The control of local network information flow can effectively improve the real-time and smooth transmission of network information. Therefore, a big data information flow control method based on semantic features in the cloud computing environment is proposed. In the cloud computing environment, by calculating the network big data information frame size, calculating the data frame rate adjustment series, according to the detected big data information flow rate and transmission rate, to ensure that the big data information flow transmission rate is not less than the frame rate. The big data information flow is dynamically corrected and hierarchical controlled. According to the semantic feature extraction coefficient obtained by decomposition, a threshold is selected to reconstruct the original signal of the big data information flow and remove the communication interference of the big data information flow. Referring to the idea of network link weight, when balancing network congestion, the load of each big data information flow is balanced according to the bandwidth occupancy ratio of each big data information flow, and the load of each sub flow is balanced by setting the network bandwidth occupancy ratio parameter. By setting the network bandwidth occupancy ratio parameter of big data information flow, the load of each sub flow is balanced, and the real-time control of big data information flow is realized. Experimental results show that the big data information flow control method based on semantic features in the cloud computing environment can not only reduce the noise content of big data information flow, but also improve the control speed of big data information flow, with better control performance.

Software updates are one of the most critical considerations in the production phase of any IoT project at a very early stage. If a production team maintains the program, anything that goes wrong can be corrected, and new characteristics can be implemented promptly, provided remote upgrades are successful, secure, and trusted. The fast growth of embedded and wireless technologies has eventually led to the convergence of embedded and wireless systems. Therefore, products should be pushed into development beforehand to provide the potential for a different approach, including remote upgrades if new enhancements are ready or if bugs have been remedied with the existing version. For the most part, it’s good to have a software upgrade mechanism during the very early stages of the product or application definition. The paper offers an ARM and FPGA-based data acquisition framework. It aims to capture the bandwidth of wireless signals from 70MHz to 6GHz using the proposed framework in the article. The framework included the user interface to configure sample rate, bandwidth, sample center frequency, sample time, and data storage parameters for sampling — the proposed framework consists of software and software architecture for the hardware framework. The hardware is supported by ARM and FPGA. The software is based on the Xilinx software development kit (SDK). In particular, for fast transmission and storing of data over ETHERNET, a remote data acquisition scheme based on the server and client model is built.

Rock mass fraction is one of the main indexes to evaluate the blasting effect of mining. We take some rock blocks after blasting as the research objects and use 3D laser scanner to obtain the point cloud data of rock blocks. Then we use statistical filtering method to process the original point cloud data, and then calculate the point cloud data after pre-processing. We obtain the supervoxel clustering point cloud. On the supervoxel clustering algorithm, the concave convex criterion is used to fuse the clustering results. The regional growth algorithm is used to complete the segmentation of rock point cloud, so as to achieve the purpose of automatic recognition of blasting rock block contour. Based on the segmentation results of the rock block point cloud, the rock block point cloud with obvious characteristics is extracted, and the length of the long axis of the rock block is obtained according to the feature information of the rock block. The results show that the method can solve the defects of traditional measurement methods. The proposed recognition algorithm will meet the requirement of the intelligent of blasting fragmentation analysis. Additionally, it will satisfy the requirements of blasting quality analysis and evaluation.

The online practicum teaching is necessary to provide practical experience for college students and to cultivate their employability. Students’ career decision-making self-efficacy makes students more likely to engage in the online practicum to acquire more practical skills in consideration of career selection, and predicts students’ satisfaction with the online practicum teaching. This study aims to find out influencing mechanism of college students’ career decision-making self-efficacy on their satisfaction with the online practicum teaching. The sample of 291 engineering undergraduates filled in the self-reporting questionnaires of career decision-making self-efficacy and the perception and satisfaction of the online practicum teaching quality. Correlation analysis revealed that there were significant positive correlations among students’ career decision-making self-efficacy (CDMSE), students’ perception of the online practicum teaching quality (SPOPTQ), and students’ satisfaction with the online practicum teaching (SSOPT). Mediation model analysis showed that CDMSE directly had a significant positive prediction effect on SPOPTQ and SSOPT respectively, and SPOPTQ presents partly mediating effect between CDMSE and SSOPT. College students have a higher degree of confidence in completing job-related tasks in the future career decision-making process. Such confidence can be positively transferred to the online practicum learning, stimulate the emotion and grit of students, and positively affect their perception quality and their satisfaction in the practical experience of the online practicum activities.

The application and management system of scientific research projects adopts the mature B/S mode, and uses the technologies of jqGrid, Layui, jQuery, PHP and MYSQL to design and realize the function modules of project application, online evaluation, project process management and project query statistics. At present, as a comprehensive management system of Weinan science and technology business, the system has been officially put into use, and has completed the application and evaluation of Weinan science and technology plan projects since 2018. The system is stable, beautiful interface, easy to operate, and can meet the daily needs of science and technology project management. It has produced certain economic and social benefits, and the system has certain application and promotion value in colleges and universities, scientific research institutes, science and technology management departments and other similar units.

In order to improve the retrieval ability of super-resolution multi-space block images, a texture retrieval method of block images based on depth hash is proposed. A texture feature analysis model of super-resolution multi-dimensional partitioned images is constructed, which combines texture spatial structure mapping method to realize depth information fusion of partitioned images, adopts edge feature detection and texture sparse feature clustering to realize texture hierarchical structure feature decomposition of super-resolution multi-dimensional partitioned images, and adopts deep image parameter analysis method to construct pixel structure recombination model of multi-dimensional partitioned images. Multi-dimensional texture parameter structure analysis and information clustering are realized for the collected partitioned images in multi-dimensional space. According to the information clustering results, the texture retrieval and extraction of partitioned images are realized by using the deep hash fusion algorithm, and the information detection and feature recognition capabilities of partitioned images in multi-dimensional space are improved. Simulation results show that this method has higher precision and better feature resolution in texture retrieval of partitioned images in multidimensional space, which improves the texture retrieval and recognition ability of partitioned images.

Estimating the relative pose between two calibrated views with 2D-to-2D correspondences is a fundamental problem in computer vision and 2D perception. In this paper, we present the first certifiably globally optimal solver that can simultaneously incorporate both points and lines as the non-minimal 2D-to-2D correspondences for this problem. Our first contribution is to derive a generalized polynomial-based objective function based on the geometric constraints of orthogonal and parallel line pairs. Built upon it, our second contribution is to reformulate the relative pose estimation problem as a constrained global optimization problem with a unified representation of both point and line pair correspondences. Our third contribution lies in relaxing this non-convex optimization problem to a convex Semi-Definite Program (SDP) using Sum of Squares (SOS) relaxations so as to solve it via Gloptipoly 3 with a reliable guarantee of global optimality. In both synthetic and real experiments, we show that adopting line pairs as supplementary correspondences can greatly improve estimation accuracy, especially in the point-sparse situations, and that our solver, named SPLP (SOS-Point-and-Line-Pair), can outperform other state-of-the-art solvers.

Recent advances in technology have accelerated the Fourth Industrial Revolution. With the emergence of artificial intelligence, not only the manufacturing sector but also all sectors of society are expected to undergo changes in the future. In this age of the Fourth Industrial Revolution, it is going to be more important for learners to improve their creativity than to acquire knowledge. So scholars are exploring new ways of teaching to cultivate suitable talent for the future society. Among these various methods of education, Maker Education at Micro Manufacturing Space is recognized as the optimal method for the AI era. This study, in light of this, analyzed the operation of Micro Manufacturing Space, which is located in a university, and further suggested the direction of development of Micro Manufacturing Space in the Fourth Industrial Revolution. The results of this study are as follows. At the university’s Micro Manufacturing Space, students can be trained to think innovatively and improve creativity. In addition, this space can also be used as an open learning and meeting space for university students to visit freely. Moreover, the place can be built for the purpose of a start-up space. Therefore, future Micro Manufacturing Space in universities, as it were, will definitely prove to be a multifunctional space providing support to foster and improve creativity of the main force of the future of society. The findings can be used as theoretical basic data in the creation of a Micro Manufacturing Space for design thingking.