International Journal of Engineering Intelligent Systems

Construction of Internet of Things Resource-Sharing Platform Based on Intelligent Information Processing from the Perspective of Network Security

Bin Wang — 2025-05-01

The Internet ofThings (IoT) technology has become part of the daily life of many people, with its advanced concept, convenience and practicality, and has played a huge role in many aspects. The application of the IoT technology can establish a sound intelligent service system that plays a positive role in the productivity of enterprises and the lives of individuals. Taking into account the characteristics and needs of the current various types of large-scale IoT businesses, this paper designs a set of cross-domain business management solutions, unified modeling, unified identification and unified representation, thus enhancing the scalability of applications. Open industrial services provide a bridge for different industries and achieve cross-industry and cross-field service cooperation. The application of the IoT in many fields, through data sharingand resource sharing, enables systems
in various sub regions to be connected to each other for the purpose of exchanging and sharing information. In this study, a data-based, fine-grained access control mechanism is designed, which uses three layers of access control permissions to ensure that access to data legally authorized during the data exchange process, and to prevent data leakage and illegal access. Hence, this paper proposes a secure resource sharing system based on the IoT, with a minimum energy consumption of 28 milliseconds. The method proposed in this paper effectively prevents a collusion attack by malicious members, thereby improving the control of access to resources and confirming that this protocol performs well in terms of ensuring the security of data.

Keywords: IoT Resource Sharing Platform, Network Security, Intelligent Information Processing, IoT Services

Cite As

B. Wang, Y. Ye, "Construction of Internet of Things Resource-Sharing Platform Based on Intelligent Information
Processing from the Perspective of Network Security", Engineering Intelligent Systems, vol. 33 no. 3, pp. 239-248, 2025.

Design and Implementation of an Automatic Evaluation System for English-Chinese Interpretation Based on Artificial Intelligence

Fang Ren — 2025-05-01

With the development of globalization, English-Chinese interpretation plays an increasingly important role in international communication. The aim of this study is to design and implement an artificial intelligence-based automatic evaluation system for English-Chinese interpreting, and to provide an objective and efficient tool for the evaluation of interpretation quality. By using a hybrid model comprising a constitutional neural network (CNN) and a long short-term memory network (LSTM), the system can effectively deal with complex linguistic phenomena in interpreting content. In this study, through comprehensive data collection and re-processing, high-quality data was obtained as input for model training. System tests show that the model achieves good results in terms of functionality, performance and user experience, especially in regard to semantic accuracy and fluency. However, the study also has limitations, such as the diversity of data samples and the processing power in complex contexts. Future research will focus on expanding the datasets and further optimizing the algorithm to improve the generalization ability and accuracy of the system. In general, this study provides a new technical perspective for the field of automatic assessment of English-Chinese interpreting, and provides a valuable reference for related research.

Keywords: artificial intelligence, English-Chinese interpretation, automatic evaluation system, convolution neural network, long short-term memory network.

Cite As

F. Ren, "Design and Implementation of an Automatic Evaluation System for English-Chinese Interpretation Based on Artificial Intelligence", Engineering Intelligent Systems, vol. 33 no. 3, pp. 249-261, 2025.

Dynamic Access Control using Blockchain-based Attribute Encryption Scheme for Big Data Cloud Storage

Wei Fu — 2025-05-01

As one of the most crucial aspects of cloud computing, cloud storage allows users to overcome a lack of available storage space and speed without having to invest in new devices. Big data refers to a wide range of data characterized by its volume and rate of change. Traditional databases cannot handle the massive amount of information that big data operations generate. Therefore, ideally, the storage and processing of large data should occur on the cloud. However, ensuring privacy and access control is crucial before putting big data on the cloud. This requires encrypting the data and limiting the number of people accessing it. Hence, this study proposes Blockchain-assisted Cohesive Authentication using Attribute-Based Encryption Scheme (BCA-ABES) for dynamic control of access to big data stored in the cloud. The ABE scheme provides less computation overhead in the encryption process and decreases the decryption time required for effective dynamic access control. Organizations may use smart contracts to record their blockchain access control policy and assign appropriate roles to users. The suggested architecture uses smart contracts’ access control computation technique to control access to huge data resources in cloud storage. Our suggested approach has been thoroughly tested for security vulnerabilities and shown great computing efficiency, and meets the indistinguishability criteria in theoretical and practical evaluations.

Keywords: Dynamic Access Control, Big Data Analytics, Cloud Computing, Blockchain Technologies, Big Data Cloud Storage.

Cite As

W. Fu, L. Zhang, C. Li, "Dynamic Access Control using Blockchain-based Attribute Encryption Scheme for Big Data Cloud Storage", Engineering Intelligent Systems, vol. 33 no. 3, pp. 263-273, 2025.

Evaluation of Financial Intelligent Systems Digitalization Maturity of Small and Medium-sized Enterprises Based on Fuzzy Logic Algorithm

Tong Tian — 2025-05-01

In response to the problem of having inadequate and inaccurate methods of evaluating the digital maturity evaluation of small and medium-sized enterprises (SMEs), this study designed a financial digital maturity evaluation method based on the size of enterprises in a provincial region of China. By analyzing the current status of financial digitization in SMEs, evaluation indicators were determined, and a digital maturity evaluation model was constructed using fuzzy logic algorithms and analytic hierarchy process. Verification showed that the Cronbach’s Alpha coefficient of the established evaluation model was 0.87, and the consistency ratio of the judgment matrix was 0.030. The average scores for digital management, input, output, and
external digital environment of the 25 selected SMEs were 2.8008, 2.0588, 1.4964, and 1.7568, respectively. The average score for overall financial digital maturity was 1.6768, which is a relatively weak level. The results indicate that the financial digitalization maturity level of SMEs in the study area is relatively low. When undertaking digital transformation, it is necessary to strengthen the application of enterprise digital technology, optimize the digital business capabilities of enterprise finance, and promote the digital transformation of enterprise finance. The use of fuzzy logic algorithms to evaluate the digital maturity of enterprise finance can improve the efficiency and accuracy of evaluation and has positive practical significance in the field of evaluation.

Keywords: Fuzzy logic algorithm; AHP; SMEs; Digital transformation; Digital maturity; Evaluation model

Cite As

T. Tian, "Evaluation of Financial Intelligent Systems Digitalization Maturity of Small and Medium-sized Enterprises Based
on Fuzzy Logic Algorithm", Engineering Intelligent Systems, vol. 33 no. 3, pp. 275-284, 2025.

Evaluation of UWB Indoor Intelligent Systems Location Algorithm Based on 6G Edge Cloud and Computer Vision

Wei Zhang — 2025-05-01

In the field of interior design, precise spatial positioning technology is essential for the creation of spaces that are both functional and aesthetically pleasing. Given the difficulty of positioning signal propagation in the indoor environment, it is particularly critical to study an ultra-wideband (UWB) indoor positioning algorithm that combines 6G edge cloud and computer vision technology. In this article, an indoor visual positioning technology for 2D-3Dfeature point matching is proposed. Through the binocular visual information obtained by the depth camera, the indoor image submitted by the user is accurately matched with the feature points stored in the database, thereby determining the coordinate position of the image in three-dimensional space. To improve the operating efficiency of the ultra-wideband system, 6G edge cloud technology is used in this study. When the ultra-wideband
ranging module deviates greatly, the positioning accuracy is guaranteed by switching to the vision subsystem. The federal Kalman filtering program applied in the study enables the root mean square deviation between the estimated coordinates and the actual coordinates to be controlled within 0.3 meters, which significantly improves the reliability of the positioning system. The ultra-wideband indoor positioning algorithm developed in this study is not only suitable for a variety of indoor environments, but also provides important technical support for interior design, helping designers to more accurately grasp the spatial layout and improve the overall quality of design works.

Keywords: ultra-wideband indoor positioning algorithm, computer vision, 6g edge cloud, 2d-3d feature point matching, interior design

Cite As

W. Zhang, X. He, "Evaluation of UWB Indoor Intelligent Systems Location Algorithm Based on 6G Edge Cloud and Computer Vision", Engineering Intelligent Systems, vol. 33 no. 3, pp. 285-294, 2025.

Group behaviour decision of real estate investment in multi-information fusion for intelligent environment interaction

Xiaomeng Ma — 2025-05-01

Urban population migration is often accompanied by people’s investment in real estate. The intelligent environment of human-computer interaction contains a massive amount of information, and the intelligent push of the platform always has an impact on investors’ understanding of the market. At the same time, in the intelligent environment, the connection of the network changes the investment trend changes from individual to group investment behavior. Unlike previous studies, this work considers the characteristics of homebuyers’ behavioral decision-making in an intelligent environment, focuses on the interaction mechanism between homebuyers’ cognitive bias and behavioral decision-making, and uses the catastrophe theory to construct a group investment behavioral decision-making model under population migration. The research results show that the just-in-need investors are the driving force of the real estate market demand. Under the optimistic market expectation, whenthe initial proportion of people without houses is 50%, the increase of investment intention is significantly weaker than the interactive increase when 80% of people are without houses. However, although the rapid decline in house prices will encourage the just-in-need investors to buy a first home, it will not increase the probability of speculators buying a home. In addition, price changes have a lag for population migration and changes in the proportion of homebuyers.

Keywords: Behavior decision; Intelligent environment; Catastrophe model; Cognitive bias

Cite As

X. Ma, Y. Song, "Group behaviour decision of real estate investment in multi-information fusion for intelligent
environment interaction", Engineering Intelligent Systems, vol. 33 no. 3, pp. 295-310, 2025.

Optimization Strategy for Teacher Performance Management in Higher Vocational Colleges Based on Deep Learning

Shengpeng Zang — 2025-05-01

Economic and educational factors have become increasingly important for the development of modern society. Also, the economy provides strong material support for the development of education and affects educational reform and the speed of education development. When higher education is optimized during the transformation of modern society, a series of problems arise that affect the overall quality of education, the most obvious one being the performance management of teachers in higher vocational colleges. Based on a deep learning algorithm, this paper uses scientific intelligence to study the influencing factors and optimization strategies of teacher performance management in higher vocational colleges. Firstly, the deep learning network is used to extract the relevant factors affecting the performance appraisal and evaluation of teachers in higher vocational colleges. Then, a network relationship graph is established according to the interrelationship between the impact factors and other factors. By means of a questionnaire, this study explores the main problems in the performance appraisal and management of teachers in higher vocational colleges. Secondly, the researcher designs the preliminary structure of the management model based on the current standards and implementation plans for the performance management of teachers in such colleges. The optimization path of performance management is analysed by using deep learning and a Bayesian network algorithm. Finally, the factors affecting teacher performance management and performance management optimization strategies are experimentally verified and applied to establish a scientific and effective performance evaluation system, so as to make the assessmentandperformance
management results accurate and objective. The experimental results show that deep learning algorithms can be used effectively to process dynamic data and address optimization path problems. The scientific basis and accuracy of performance management also affect teachers’ attitudes to their work tasks and the future development of the education sector.

Keywords: deep learning; higher vocational colleges; performance management; optimization; Bayesian algorithm

Cite As

S. Zang, "Optimization Strategy for Teacher Performance Management in Higher Vocational Colleges Based on
Deep Learning", Engineering Intelligent Systems, vol. 33 no. 3, pp. 311-320, 2025.

Path Planning Strategy Design of Autonomous Mobile Robot Based on Fuzzy Control

Xiaosheng Chen — 2025-05-01

At present, various parts of my country have begun to build a deeply intelligent industrial chain, which has not only increased the research and development efforts on key technologies such as computer vision and natural language processing, but also invested a lot of human and material resources in the research and development of robotics technology. In the current information age, robot technology is a comprehensive high-tech development which combines manytechnologies suchascomputer, bionics, andartificial intelligence (AI).With thedeepening ofresearch, subsequent results and advancements have been widely applied in many fields. The application of robot technology in many fields in reality is not a simple and inadequate substitute for humans engaged in repetitive work. By imitating human intelligence or skills, robot technology combines the advantages of human beings with the advantages of mechanical devices. This technology enables the robot to analyze and judge the working environment and tasks quickly, and at the same time it provides the advantages of having a machine execute long-term and high-precision work. Therefore, robot technology can be said to be an important production and service equipment in the industrial field, which can provide better automation devices for advanced manufacturing technology in different regions. In the research and development of robot technology, the path planning of an autonomous mobile robot is also the focus of the current research and development of robot technology. At present, through computer technology and autonomous mobile robot path planning strategies, the robot’s motion path in various complex scenarios can be simulated and optimized more accurately. The current fuzzy control technology can better improve such problems. Fuzzy control is a non-linear control technology which can better complete the dynamic description of complex and variable-rich systems through the application of the theory of fuzzy mathematics. Firstly, this study determined the feasibility of applying fuzzy control technology to the path planning strategy of an autonomous mobile robot, and proposed a new path planning strategy based on fuzzy control. The simulation results showed that the performance of this new path planning strategy in many respects was about 7.4% better than the existing path planning strategies.

Keywords: robot technology; path planning strategy; fuzzy control; data mining

Cite As

X. Chen, X. Lu, W. Chen, " Path Planning Strategy Design of Autonomous Mobile Robot Based on Fuzzy
Control", Engineering Intelligent Systems, vol. 33 no. 3, pp. 321-327, 2025.

Performance Improvement Strategy for Few-shot Semantic Segmentation Assisted by Large Language Models

Xue Han — 2025-05-01

Few-shot semantic segmentation is a computer vision technology that is used to segment pixel-level objects in images segment a small number into labeled samples. Traditional methods have limited generalization capability, are sensitive to background interference, susceptible to class imbalance, and have inadequate feature representation. This study explored the use of Large Language Models (LLMs) for few-shot semantic segmentation tasks. Using ChatGLM (Chat Generative Language Model), with its powerful semantic understanding and feature extraction, Named Entity Recognition (NER) with image context was achieved. The NER results were used to enhance few-shot semantic segmentation, improving its ability to process and understand image semantics. Experimental results showed significant improvements in the mean Intersection over Union (mIoU) evaluation metric using a few-shot semantic segmentation model assisted by LLMs. The small-sample semantic segmentation model assisted by the large language model has a higher mIoU ratio scores on 5 validation sets than the SETR (Segmentation Transformer) model and Mask R-CNN (Mask Region-based Convolutional Neural Network), indicating that the application of the large language model effectively improves the accuracy and generalization ability of small-sample semantic segmentation.

Keywords: few-shot semantic segmentation, large language models, named entity recognition, mean intersection over union, feature extraction

Cite As

X. Han, S. Zhang, Y. Li, " Performance Improvement Strategy for Few-shot Semantic Segmentation
Assisted by Large Language Models", Engineering Intelligent Systems, vol. 33 no. 3, pp. 329-338, 2025.

Personalized learning of college English using knowledge graphs combined with user portraits

Ningfang Wang — 2025-05-01

In this study, user portraits were combined with knowledge graphs to develop a personalized recommendation algorithm for English exercises and applied it to the teaching of English. A case analysis was conducted using sophomore students from the School of Foreign Languages at Ningxia Medical University. The optimal parameters of the long short-term memory (LSTM) algorithm for classifying exercise knowledge points were tested first, and a knowledge graph of English exercises was then constructed. The students were divided into a control group and an experimental group. The control group received traditional multimedia teaching, while the experimental group utilized the personalized recommendation algorithm for
English exercises to facilitate their learning. English tests were conducted before and after a four-week teaching period. Moreover, a questionnaire was administered to the experimental group to gather feedback on the new teaching method. The results showed that the LSTM algorithm performed best in classifying exercise knowledge points when the number of nodes in the hidden layer was 128, and the activation function was sigmoid. The teaching mode, assisted by the personalized recommendation algorithm based on the user portrait and knowledge graph, effectively improved students’ English
scores and increased their interest in learning English.

Keywords: user portrait, knowledge graph, English, personalized recommendation

Cite As

N. Wang, "Personalized learning of college English using knowledge graphs combined with user portraits", Engineering Intelligent Systems, vol. 33 no. 3, pp. 339-343, 2025.

The analysis of student Intelligent Systems achievement using data mining in practical teaching informatization

Ying Zhong — 2025-05-01

This paper offers a brief introduction to the decision tree model in data mining technology. A clustering algorithm was employed to discretize the continuous data samples to facilitate processing. Then, the one-semester English course scores of students studying at Guilin Medical University were used for the case study. The improved decision tree model was compared with the ID3 decision tree model and the unmodified decision tree model. The results showed that the improved decision tree model was faster to build and, moreover, had higher classification accuracy than the other two models. The final exam score had the most impact on the overall score, followed by the scores for in-class tests, completion of daily homework, and number of lateness to class.

Keywords: educational informatization, data mining, decision tree, K-means

Cite As

Y. Zhong, J. Mo, "The analysis of student Intelligent Systems achievement using data mining in practical
teaching informatization", Engineering Intelligent Systems, vol. 33 no. 3, pp. 345-350, 2025.