International Journal of Engineering Intelligent Systems

Academic Domain Importance: Judgment of Literature Resource Citations Using Index Analysis

2026-05-10T02:23:32-07:00

This paper briefly introduces the citation indexes used to measure the academic influence of researchers. These are the H index, G index, Gm index, and Y index. Then, taking 20 graduate tutors of Jinan University as subjects, the papers published by these 20 tutors by June 1, 2024 were collected from China National Knowledge Infrastructure for acase analysis of academic influence. The results showed that there was a significant correlation between H index and G index and between Gm index and Y index, which can indicate the academic influence of researchers, and the academic influence ranking of tutors that changed under different citation indexes. According to these changes, the academic influence of tutors can be analyzed more comprehensively.

Keywords: academic influence, literature citation, citation index, ranking

Cite As

W. Liu, "Academic Domain Importance: Judgment of Literature Resource Citations Using Index Analysis", vol. 34 no. 2, pp. 143-147, 2026.

Anti-Tampering Simulation Algorithm for Supply Chain Financial Big Data Based on Artificial Intelligence and Blockchain

2026-05-10T02:31:07-07:00

Social development and the progress of science and technology have driven the rapid advancement of computer technology. As an important research direction at this stage, computer vision multimodal learning of human-computer interaction has attracted the research interest of many scholars. Artificial intelligence (AI) and blockchain in terms of the multi-mode computer vision of human-computer interaction have also received a lot of attention. At present, AI has been widely used in various fields. Blockchain is mostly used for the prevention of data tampering and the protection of data security. Blockchain supply chain finance has encountered many problems in actual tamper proof applications. Many scholars have proposed corresponding countermeasures against the anti-tampering problem of blockchain. However, most of them focus on the identity of users and the privacy of transactions. There are few tamper proof studies on financial big data. On the basis of previous scholars’ research on blockchain, this paper proposes the anti-tampering algorithm of supply chain financial big data of artificial intelligence and blockchain and conducts empirical research. The research on AI and blockchain of computer vision multimodal learning of human-computer interaction showed that this method was feasible. When the number of pieces of information was 3050, the number tampered with after the application of the proposed method was 226 lower than that of traditional methods for counter attack. Regarding the security of data transmission, the number of pieces of information that had been tampered with was 101 lower than that secured by traditional methods. For the reliability of data storage, this method had 224 fewer tampered information than
traditional methods. This showed that the algorithm proposed in this paper was more resistant than traditional methods to attacks on the security of financial big data information of the supply chain, the protocol security during data transmission, and the reliability during data storage. At the same time, the research on AI and blockchain contributes to the development of computer vision multimodal learning for human-computer interaction.

Keywords: supply chain, financial big data, artificial intelligence and blockchain, tamper-proof simulation algorithm

Cite As

X. Wu, H. Wu, "Anti-Tampering Simulation Algorithm for Supply Chain Financial Big Data Based on Artificial Intelligence and Blockchain", vol. 34 no. 2, pp. 149-157, 2026.

Application of Artificial Intelligent Systems Intelligence Special Effects in the Design of 3D Stereo Animation

2026-05-10T02:38:00-07:00

The progress of computer software and hardware technology has promoted the rapid development of the animation industry from two-plane animation to three-dimensional animation. After entering the 21st century, the rapid development of 3D animation technology offers people both convenience and enjoyment. It provides substantial technical support in the fields of architecture, games, advertising, film and television, exhibitions, medicine and so on. The application of special effects technology to film and television 3D animation will not only help to change the way that film and television content is created content; it also has a significant impact on film art. Special effects in film and television productions are artificially created illusions.
Following a review of the relevant literature, this current research study examines the special effects technology used for 3D animation, comprising four different approaches: special effects light and shadow art, lens transition special effects, space dynamic special effects, and interactive special effects. The fusion of it and special effects is discussed, and the application of special effects in three-dimensional animation of film and television is analyzed. It is anticipated that this study has reference value for the special effects creation of 3D animation. This study conducted performance tests of the 3D animation production system, finding that when the data comprises fewer than 10,000 blocks, the terrain data is quite fast from loading to display. However, when the number of block data exceeds 50,000, the processing time of terrain data will increase due to the increase of the index and search time of the block data, and the limited processing capability of the hardware.

Keywords: Special Effects, 3D Animation, Artificial Intelligence, Virtual Worlds

Cite As

Y. Liu, Q. Li, "Application of Artificial Intelligent Systems Intelligence Special Effects in the Design of 3D Stereo Animation",
Engineering Intelligent Systems, vol. 34 no. 2, pp. 159-170, 2026.

Application of Human-Computer Interaction and Digital Image Processing Technology in Virtual Simulation Game Design

2026-05-12T02:28:54-07:00

Human beings perceive, understand and contact the world through five senses. These five senses are the most obvious way for human beings to perceive the world. However, the way for human beings to perceive the world is not limited to the five senses. Through the brain’s information analysis and processing of the perception system, human beings can obtain richer feelings. Human beings’ feelings of real life come from the feelings of human organs. Now, there is a virtual simulation technology that can let people express their feelings through virtual information. In virtual simulation, the information that human beings are exposed to may be unreal and not be truly perceived by the five senses. However, human beings can really perceive the information in it via virtual simulation technology. Nowadays, this technology has been applied in many industries. In this research, the design and application of virtual simulation was studies in relation to the game field. Because the key technology of the existing virtual
simulation game is relatively simple, and the sense of picture and experience of the game is inadequate, this paper proposes a method whereby human-computer interaction and digital image processing technology are applied to the design of a virtual simulation tennis game. The effectiveness of the proposed method was tested via comparative experiments and a questionnaire survey. The results of the comparative experiment showed that among the four game-experienced players, Player A and Player B spent 47 minutes in the overall entry time in the virtual simulation tennis game with human-computer interaction and digital image processing technology. However, Player C and Player D spent 97 minutes in the overall entry time in the virtual simulation tennis game created with traditional technology. Overall, results indicate that the virtual simulation tennis game based on
human-computer interaction and digital image processing technology is easier to operate, and is better able to capture and retain players’ interest in the game and sense of participation. Therefore, the proposed approach can effectively enhance the game experience of virtual simulation tennis games, and improve the richness of the screen elements, giving players better visual enjoyment and game atmosphere.

Keywords: digital image processing technology, game design application, human-computer interaction, virtual reality, virtual simulation

Cite As

J. Liu, M. Shen, "Application of Human-Computer Interaction and Digital Image Processing Technology in Virtual
Simulation Game Design", Engineering Intelligent Systems, vol. 34 no. 2, pp. 171-179, 2026.

Artificial Intelligence Aided Diagnosis and Feedback System in English Teaching

2026-05-12T02:35:42-07:00

Because English isnow the main language used for international communication, the innovation of its teaching methods is particularly important given the increase of globalization and technological progress. This study explores the ways that digital technology and intelligent teaching can improvethe efficiency and effect of language learning. After conducting an in-depth analysis of digital technology applications in education, the theoretical basis of intelligent assisted instruction, and its practical application in the teaching of English, this study designed and implemented a series of experiments. After collecting data from specific target groups, the study constructed an artificial intelligence-(AI-) assisted diagnosis and feedback system with
advanced algorithms and technologies, aimed at providing personalized learning paths and real-time feedback for learners of English. The results show that the system can significantly improve learners’ English ability, especially in terms of accuracy and fluency of language use. Through the evaluation and analysis of the model performance, the study further verified the intelligent CAI(Computer-Assisted Instruction) system’s potential to improve the quality and efficiency of education. It is anticipated that this research will provide innovative pedagogy for the teaching of English, and also offer theoretical and practical references for the development and application of educational technology in the future.

Keywords:artificial intelligence (AI) assisted instruction, English teaching, diagnosis and feedback system, intelligent teaching technology, personalized learning path

Cite As

J. Fang, J. Du, "Artificial Intelligence Aided Diagnosis and Feedback System in English Teaching", Engineering Intelligent Systems, vol. 34 no. 2, pp. 181-193, 2026.

Autonomous Decision-Making and Control Algorithm for Live Working Robots Based on Artificial Intelligence

2026-05-12T02:43:04-07:00

The current autonomous operation of live working robots in high-voltage power environments faces problems such as inadequate decision-making precision, poor adaptability, and slow response. This is mainly because the existing algorithms lack the flexibility to deal with complex dynamic environments. To solve this problem, this paper proposes an autonomous decision-making and control algorithm that combines deep learning with classical control strategies to improve the robot’s operating ability and execution efficiency in high-voltage environments. First, a Deep Convolutional Neural Network (DCNN) is used to extract the spatial features of the environment; this is used together with Long Short-Term Memory (LSTM) to model time series data to capture the dynamic change information of the environment. Then, Deep Q-Network (DQN) is applied for decision optimization,
enabling the robot to autonomously adjust its operating strategy in a complex environment. Secondly, at the control level, the robot evaluates the operating risk through a neural network, and achieves precise motion control based on PID (Proportional Integral Derivative) control and fuzzy control strategies to improve the stability and safety of the operation. The experimental results show that the task success rate of this method in the live working environment reaches 90%. When facing complex environmental changes, the execution time is reduced by about 30%, and the response time is shorter than that of the traditional algorithm. The research results verify the effectiveness of the proposed method in improving the autonomous working ability and efficiency of the live working robot.

Keywords: Autonomous Decision-making; Control Algorithm; Deep Q-Network; Reinforcement Learning; Live Working Robot

Cite As

Y. Ying, S. Zhou, B. Shen, "Autonomous Decision-Making and Control Algorithm for Live Working Robots Based on Artificial Intelligence", Engineering Intelligent Systems, vol. 34 no. 2, pp. 195-209, 2026.

Detail Enhancement of 3D Animation Images Based on Swarm Intelligence Algorithm

2026-05-15T18:00:33-07:00

The absence of image details in the area of 3D animation design and generation causes the expression creation process of animation to be concealed, resulting in unnaturally image animation expressions. However, the traditional progression of 3D animation graphics has the issue of the inferior visual effect of image improvement. Hence, this paper proposes an Improved Particle Swarm Optimization based Image Enhancement Model (IPSO-IEM) to address the challenges of poor image effect and enhancement in conventional 3D image automatic generation. The data are taken from the iCartoon face dataset for 3D animation image enhancement. Firstly, the image can lose significant data when the size is reduced in 3D animation design. Therefore, the image is transformed from the spatial domain to achieve multi resolution. Secondly, Gamma adjustment is a proven method that creates a natural look and conserves the mean brightness of the picture with the choice of optimal gamma value. PSO selects the optimal gamma values and is utilized as a global search approach for the best optimum value and most improved image. In this research, an efficient fitness function is suggested to increase the performance of the PSO algorithm.

Keywords: 3D Animation Images, Image Enhancement, Particle Swarm Optimization, Swarm Intelligence

Cite As

J. Yang, "Detail Enhancement of 3D Animation Images Based on Swarm Intelligence Algorithm",
Engineering Intelligent Systems, vol. 34 no. 2, pp. 211-219, 2026.

Hierarchical Multi-Agent Deep Reinforcement Learning Architecture in Complex Industrial Production Scheduling

2026-05-15T18:09:33-07:00

Complex industrial production scheduling problems are characterized by high dimensionality, dynamics, and multi-objectives. Existing scheduling methods are usually based on mathematical programming or a single-agent architecture, which have problems such as insufficient model complexity and dynamics, difficulty in dealing with high-dimensional problems, and poor scalability. In particular, they have limited performance when facing multi-task collaborative optimization and real-time environmental changes.Therefore, we designed a hierarchical multi-agent deep reinforcement learning (DRL) architecture that separates global task allocation from local execution through a hierarchical structure. The high-level deep Q-network
(DQN) is used for resource allocation, while the low-level proximal policy optimization (PPO) is used to achieve fine scheduling. The centralized training with a decentralized execution (CTDE) framework is included to coordinate the behavior of multiple agents. At the same time, the graph neural network (GNN) is used to model task dependencies and design reward functions to balance short-term and long-term objectives, thereby improving scheduling efficiency, flexibility, and adaptability to uncertainty and providing an efficient and intelligent solution for complex industrial production scheduling. Experimental results show that the hierarchical multi-agent deep reinforcement learning system is significantly better than other algorithms in terms of key indicators such as task completion time, resource utilization, system delay rate, cost saving rate, and scheduling failure rate. In large-scale task scheduling, the average task completion time is reduced by 15%–25% compared with other methods, and the system delay rate is kept at around 5%. In a dynamic environment’s equipment failure recovery scenario, the scheduling failure rate drops rapidly from 18% to below 10%, demonstrating its efficient global optimization and local adjustment capabilities. The research results show that the hierarchical multi-agent method provides an efficient and flexible solution for complex industrial production scheduling, which has important theoretical value and practical significance.

Keywords: Complex Industrial Production Scheduling, Deep Reinforcement Learning, Hierarchical Multi-agent, Centralized Training with Decentralized Execution, Graph Neural Network

Cite As

H. Peng, G. Li, Z. Zhang, R. Zhou, "Hierarchical Multi-Agent Deep Reinforcement Learning Architecture in Complex
Industrial Production Scheduling", Engineering Intelligent Systems, vol. 34 no. 2, pp. 221-233, 2026.

Information Display Interaction System Design Based on Visual Communication

2026-05-15T18:15:06-07:00

In the digital era, information display interaction systems are pivotal for advertising design, yet traditional solutions suffer from information overload, inadequate interactivity, and mismatches between design and technology. To address these issues, this study develops a visual communication-based information display interaction system for advertising. The system integrates four core modules: visual presentation with hierarchical information processing, user data analysis via the Transformers model, personalized recommendations using collaborative filtering, and technical support with multi-layered security safeguards. Experimental results validate its superior performance: the advertising click-through conversion rate reaches 4%, doubling that
of traditional advertising; in personalized recommendations, it achieves a precision of 0.82, recall rate of 0.78, and F1 score of 0.80,
outperforming other mainstream strategies; the average response time is 250.97 ms, with a request failure rate below 5% even under high load. This system maintains robust stability and efficiency in high-concurrency scenarios, significantly enhancing advertising effectiveness. It not only proves reliable in practical application but also offers valuable insights for the optimization of future advertising information display systems.

Keywords: Information Display Interactive System; Advertising Design; Visual Communication; Personalized Recommendations; System Stability

Cite As

Q. Wang, "Information Display Interaction System Design Based on Visual Communication", Engineering Intelligent Systems,
vol. 34 no. 2, pp. 235-244, 2026.

Instructor-Centered Education and Performance in Vocational Education for the Digital Economy Using the Fuzzy Logic Algorithm

2026-05-16T21:06:06-07:00

Vocational Education (VE) responses to the digital economy have recently improved based on instructor-centric education. The VE performance influencing thedigital economyis improved usingtheinstructor’s knowledgeand consistent assessments. To enhance theevaluation of VE performance, this article proposes an Instructor Skill-based Assessment Method (ISAM) using fuzzy logic (FL).This method analyzes the performance using instructor skills for improving the digital economy. First, the crisp inputs from the various instructor skills and experience factors are analyzed using different fuzzification levels. The levels are determined using the maximum output generated after each factor analysis. This encourages multiple-level outputs for preventing nullified assessments. These assessments are eliminated from the fuzzification process to reduce time complexity. The instructor
knowledge update and skill improvements are recommended based on the avoidance count. This recommendation is intended to leverage the digital economy regardless of the instructor’s experience. Therefore, the proposed method improves instructors’ performance and the digital economy.

Keywords: digital economy, fuzzy logic, performance assessment, vocational education

Cite As

M.Li, "Instructor-Centered Education and Performance inVocational Education for the Digital Economy
Using the Fuzzy Logic Algorithm", Engineering Intelligent Systems, vol. 34 no. 2, pp. 245-259, 2026.

Feasibility Study of Social Media Data in Macroeconomic Forecasting

2026-05-16T21:11:05-07:00

As a new type of information source, social media data can reflect the micro-level characteristics of economic activities, providing a new perspective and rich materials for macroeconomic analysis. Traditional macroeconomic forecasting methods rely on officially released statistics, which usually havealongrelease cycle andtime lag, making it difficult to capturethe impact ofmarket sentiment fluctuations andunexpected events onthe economic environment. This study evaluates and validates the feasibility of social media data in macroeconomic forecasting and constructs a macroeconomic forecasting model based on social media data. The experimental results show that social media data can provide a valuable flow of information that helps to capture the economic pulse that cannot be reflected in time by traditional statistics, and enhances the insight into the macroeconomic situation. At the same time, social media data can also improve the accuracy and sensitivity of macroeconomic forecasts, providing policy makers,
corporate decision makers and market participants with a more forward-looking basis for decision making.

Keywords: social media data, macroeconomic forecasting, feasibility study.

Cite As

B. Shi, "Feasibility Study of Social Media Data in Macroeconomic Forecasting", Engineering Intelligent Systems, vol. 34 no. 2,
pp. 261-272, 2026.

Robot Information Intelligent Perception and Navigation Based on Multi-Sensor Fusion

2026-05-16T21:19:03-07:00

Various sensors are different in terms of time synchronization, data dimension, and sampling frequency, which makes the deep fusion of heterogeneous data difficult. In addition, the existing high-precision fusion algorithms rely heavily on computational resources and cannot meet the needs of lightweight robots with limited computing power. To address these issues, this research work applies a fusion method based on a multimodal convolutional neural network (2D-ResNet-50 + 3D-CNN) and a cross-modal attention mechanism to ensure the synchronization and unified format of multi-sensor data by means of data preprocessing and time alignment technology. Then, a convolutional neural network is used to extract features from visual image data, laser radar point cloud data, and inertial measurement unit (IMU) data, and the information from different sensors is fused through a cross-modal attention mechanism. A modular architecture is used to optimize the computational efficiency of the system. The system is
divided into multiple independent modules, each responsible for a specific task. The event trigger mechanism is used to dynamically activate and schedule related modules to enhance the system’s intelligence. This method is deployed on NVIDIA’s Jetson Xavier NX platform, and the experiments are conducted under the Robot Operating System framework. Experiments show that the robot’s control error does not exceed 0.25 when performing path tracking tasks. The path planning time in various environments does not exceed 150 milliseconds. This method can improve perception precision while maintaining high real-time performance and efficiency with limited computational resources, significantly optimizing the robot’s navigation performance in complex dynamic environments.

Keywords: multi-sensor fusion, robot navigation, deep learning, cross-modal attention mechanism, modular architecture

Cite As

X. Li, Y. Luo, M. Bao, H. Sun, "Robot Information Intelligent Perception and Navigation Based on Multi-Sensor Fusion",
Engineering Intelligent Systems, vol. 34 no. 2, pp. 273-284, 2026.