International Journal of Engineering Intelligent Systems

Agile Supply Chain Management Collaboration Based on Artificial Intelligence Traceability System

Jie Wei — 2024-09-01

With the rapid development of the market economy and the manufacturing industry, the market has already reached saturation. The fierce competition between enterprises is reflected in their products and services, which is fundamentally a matter of the competition between supply chain management modes. In recent years, artificial intelligence (AI) has developed rapidly. The application of human-computer interaction technology to supply chain management (SCM) systems can improve the efficiency of SCM. Although the traditional SCM mode is adequate for product manufacturing, transportation and sales, it is unable to rapidly customize the customer’s product demand. The traceability function is a production control system that can track companies’ products. This paper compared the collaboration mode of agile SCM based on AI traceability system with the traditional
SCM mode. The experimental results showed that the responsiveness of the traditional SCM mode and the agile SCM collaboration mode based on AI traceability system were 76% and 89.8% respectively in a small supply chain. In large supply chains, the responsiveness of the traditional SCM mode and the agile SCM collaboration mode based on AI traceability system were 70.8% and 87.6% respectively. Therefore, human-computer interaction in the collaboration mode of agile SCM based on AI traceability system can improve the responsiveness of the supply chain to customer needs.

Keywords: Supply chain (SC), agile supply chain, manage collaboration, traceability system, artificial intelligence, multimodal learning

Cite As

J. Wei, "Agile Supply Chain Management Collaboration Based on Artificial Intelligence Traceability System",
Engineering Intelligent Systems, vol. 32 no. 5, pp. 401-410, 2024.

Animation Design System Based on 3D Image Technology

Fan Jiang — 2024-09-01

With the rapid development of computer technology, imaging technology, in particular the 3D(three-dimensional) modeling and simulation techniques are being increasingly used. However, due to the complexity of the 3D mapping technique itself, in the development of new 3D mapping technology as well as in the implementation in the engine, how to produce a 3D drawing has become difficult in today’s design and drawing domains. Therefore, based on the existing 3D mapping techniques, an in-depth analysis of the characteristics of the existing 3D drawing techniques is carried out, and a drawing system based on 3D technology is proposed. Also, in this study, the engine structure is divided, and the architecture and functional design of the 3D engine animation system is completed. Regarding the 3D image engine, the analysis of the animation design system indicated that when
the HDR (High-Dynamic Range) effect is on and off, the rendered frame rates averaged 133.76FPS and 233.44FPS respectively. Therefore, a study of the animation design system is necessary.

Keywords: Animation design system, three-dimensional image, rendering effect, high dynamic range

Cite As

F. Jiang, "Animation Design System Based on 3D Image Technology", Engineering
Intelligent Systems, vol. 32 no. 5, pp. 411-419, 2024.

Big Data Theory of Industrial Supply Chain Based on Complex Information Integration

Weihuang Dai — 2024-09-01

The development of big data provides a more adequate foundation for the management and construction of traditional industrial supply chain finance. This article discusses the research on big data theory in industrial supply chains based on complex information integration. This paper proposes and designs a big data system for the common industry supply chain. The whole system architecture is comprised of: platform support layer, data resource layer, data processing layer, internal business layer and public service layer. The platform support layer provides public services for financial big data, and addresses all problems related to infrastructure, hardware resources, and software environment. The data resource layer is used for the
management of the list of rights and responsibilities and the list of events. The data processing layer can transform the information into understandable knowledge. The internal business layer is logically isolated from the Internet to ensure information security. The operation module of the supply chain industry standardizes the interface between logistics, the supply chain management system and related collaborative supervision system. Based on this, the research on complex information integration of industrial supply chain is carried out to improve the parallel processing efficiency of big data. Through complex information integration, the parallel processing efficiency of big data in industrial supply chain has increased by 76%, the
execution time is short, and the alignment performance is better. The results show that the system designed in this paper can reasonably develop the data resources in the online supply chain and improve the parallel processing efficiency of big data in the industrial supply chain.

Keywords: Big Data, Complex Information Integration, Industrial Supply Chain, Complex System Theory

Cite As

W. Dai, Z. Zhu, D. Qi, "Big Data Theory of Industrial Supply Chain Based on Complex Information Integration",
Engineering Intelligent Systems, vol. 30 no. 5, pp. 421-433, 2024.

Blockchain Data Privacy Protection Mechanism for Enterprise Finance and Data Mining Algorithms

Xuejun Ma — 2024-09-01

The establishment of a data privacy protection scheme that integrates information and public query is of great benefit to promoting the development of the financial aspects of a supply chain. Based on data encryption technology, this study adopted appropriate encryption methods for transaction information without changing the original consensus algorithm and verification mechanism of the blockchain, thus ensuring that attackers could not obtain transaction information in clear text form. This paper constructed a blockchain model for the financial data of enterprises, and achieved data sharing and visualization of enterprise asset management, asset securitization, and cross-border trade, thus ensuring that financial data was protected
in a timely manner. Data mining algorithms were used to select the optimal financial data privacy protection scheme from multiple potential suppliers of financial data. This study established 60 accounts for retailers, and the Bitcoin model established a total of 25 accounts for sales parties. This model is able establish new accounts for active retailers and block adjacent retailers, thereby better protecting the privacy of the financial data of retailers.

Keywords: Corporate finance, data mining algorithms, blockchain data, privacy protection

Cite As

X. Ma, Y. Zhang, "Blockchain Data Privacy Protection Mechanism for Enterprise Finance and
Data Mining Algorithms", Engineering Intelligent Systems, vol. 32 no. 5, pp. 435-443, 2024.

Credit Risk Evaluation of Science and Technology Finance Based on Artificial Intelligence and Bayesian Algorithm

Yang Gao — 2024-09-01

Since the US subprime mortgage crisis (2007–2010), the prevention of financial systemic risks has been a top priority of all regulatory authorities. In the technology finance industry, new technologies based on big data and underpinned by artificial intelligence are infiltrating the technology finance field. Due to the objective and superior ability of AI data processing, credit risk can be predicted to a certain extent. Based on the Bayesian method, this paper discusses the risk spillover effect of the science and technology finance industry. When carrying out Bayesian quantile regression, two main tasks need to be done: first, determine the prior distribution of each parameter; second, obtain the posterior parameter distribution of samples. The
experimental results show that the maximum value of parameter Alpha1 reached 0.02762 at 75%. The maximum value of parameter Alpha2 reached 0.3031 at 75%, and the value of parameter Alpha2 was larger than that of parameter Alpha1 on the whole. The posterior simulation method not only does not need to assume that all parameters follow the normal distribution; it can also correct them during simulation. The use of artificial intelligence to analyze any changes of debt yield helps to give a comprehensive indication of the overall risk. In addition to the analysis of volatility, it can also more accurately predict the probability of default.

Keywords: Technology finance credit, risk evaluation, artificial intelligence, Bayesian algorithm

Cite As

Y. Gao, L. Sun, "Credit Risk Evaluation of Science and Technology Finance Based on Artificial Intelligence
and Bayesian Algorithm", Engineering Intelligent Systems, vol. 32 no. 5, pp. 445-455, 2024.

Design of Intelligent Traffic Sign Image Recognition System Based on Machine Learning Algorithms

Jing Wang — 2024-09-01

While automobiles offer a convenient mode of transport, autonomous driving and unmanned driving have also begun to enter the commercial stage, but they have also given rise to an increasing number of vehicle safety issues. The image recognition of traffic signs (TS) is crucial for road safety. Therefore, research on automatic recognition of TS images is essential. However, changes in weather, shadows, and light intensity can easily affect the recognition of TS, which poses significant safety risks to autonomous driving. In this paper, the function and problems of TS detection method were studied by analyzing the methods of TS identification and detection; also, corresponding system design analysis was conducted based on machine learning. The purpose of this study is to develop a high-precision and real-time TS detection system based on the interference problems
in complex environments. The relevant experimental analysis of the intelligent recognition system was carried out. The analysis showed that the recognition accuracy and anti-interference performance of TS image recognition system based on a machine learning algorithm were higher than those of traditional image recognition systems; the recognition accuracy was improved by 6.8%, and the anti-interference ability was improved by 0.24. These results suggest that machine learning algorithms can definitely improve the performance of TS image recognition systems.

Keywords: Traffic signs, image recognition systems, machine learning, traffic sign detection

Cite As

J. Wang, "Design of Intelligent Traffic Sign Image Recognition System Based on Machine Learning
Algorithms", Engineering Intelligent Systems, vol. 32 no. 5, pp. 457-464, 2024.

Design of Interface Display Optimization Algorithm for In-vehicle Interaction System Based on Artificial Intelligence

Shujuan Qu — 2024-09-01

With the development of vehicle intelligence, the in-vehicle interaction system becomes an important means of information exchange between drivers and vehicles. The traditional in-vehicle interaction system has problems such as inaccurate information display and poor user experience. The purpose of this study is to use the algorithm optimization of artificial intelligence to improve the interface display of in-vehicle interaction system, enhance the user experience and improve safety. Firstly, the user’s preferences, habits and needs are determined; these will constitute the original user data set, and deep learning algorithms are used to construct the user profile in order to optimize the personalized interface. After that, wavelet transform was
applied to carry out multi-scale redrawing and rendering of images to enhance the visual effect of interface image display. Finally, a collaborative filtering algorithm was used to construct an intelligent recommendation model. The items in the recommendation set were arranged according to the weighted degree of recommendation from the largest to the smallest, so as to realize the intelligent recommendation and optimization of the interface information being displayed. In order to verify the effect of the interface display optimization algorithm of in-vehicle interaction system based on artificial intelligence, this study evaluated the optimized display interface in terms of user satisfaction, operation efficiency, error rate and interaction effect. The evaluation results showed that in the user satisfaction survey, the proportion of users who are satisfied and very satisfied with the personalized level, comfort level, and information readability of the optimized display interface was 61.0%, 50.5%, and 50.0%, respectively. The research results indicate that the interface display optimization algorithm based on artificial intelligence for in-vehicle interaction systems caneffectively meet the different needs of users and help improve the safety of the driver.

Keywords: Algorithm optimization, interface display, artificial intelligence, in-vehicle interaction system, deep neural network

Cite As

S. Yu, "Design of Interface Display Optimization Algorithm for In-vehicle Interaction System Based on Artificial
Intelligence", Engineering Intelligent Systems, vol. 32 no. 5, pp. 465-475, 2024.

Face Recognition Image Processing Technology Based on SIFT Algorithm

Hao Zhao — 2024-09-01

With the development of image recognition technology, the processing of human face information can confirm human identity. Facial recognition technology has been widely used in many fields, effectively improving the efficiency of facial information entry and recognition. The core of the face recognition process is an analysis of the characteristics of face images. The traditional facial image recognition method involves a local binary pattern (LBP) algorithm, which has high recognition accuracy when facial images contain complete information. However, actual collected face images can be affected by various environmental factors, and traditional image recognition methods find it difficult to accurately determine facial characteristics. This paper applied a scale invariant feature transform (SIFT) algorithm to facial image recognition, and compared and analyzed the traditional LBP algorithm and SIFT algorithm in respect to four factors: illumination intensity, facial expression, image occlusion ratio, and face offset angle. Experimental results showed that for male facial images, the average face recognition accuracy rates of the LBP algorithm and the SIFT algorithm under different light intensities were 94.64% and 99.52%, respectively. For female facial images, the average face recognition accuracy rates of the LBP algorithm and the SIFT algorithm under different light intensities were 92.04% and 99.08%, respectively. Therefore, the application of SIFT algorithms can improve the accuracy of facial recognition under different light intensities.

Keywords: Image processing; facial recognition; scale invariant feature transform (SIFT); local binary patterns

Cite As

H. Zhao, P. Li, "Face Recognition Image Processing Technology Based on SIFT Algorithm",
Engineering Intelligent Systems, vol. 32 no. 5, pp. 477-485.

Intelligent Cloud Platform for Interior Design Based on Digital Twins

Tao Ju — 2024-09-01

In order to improve the human-machine interaction and intelligent control capabilities of smart homes, the researchers designed a new smart home human-machine interaction system. A dynamic equation for the Internet of Things in smart urban areas was constructed based digital twin technology. The expected output of the smart interior design platform was established by utilizing the mapping relationship between the continuous packet loss and the maximum delay value in smart interior design. Combined with the design of information quality management algorithms for smart interior design services, the software design of the platform was completed, achieving automated management of smart interior design. By utilizing data fusion
technology to establish a big data fusion model for human-machine interaction in smart homes, data fusion output is carried out to optimize the control of human-machine interaction instructions in order to achieve the design of a smart home human-machine interaction system. The experimental results indicated that the login and operation functions of the platform meet user requirements, reducing the packet loss rate of the platform, decreasing the time delay effect, and ensuring the stable operation of smart indoor design. The information accuracy of the system during human-computer interaction is higher, although the accuracy may fluctuate due to uncontrollable factors, both are higher than the two comparison methods, and the fastest complete human-machine interaction can be achieved within 4 seconds, and the accuracy of human-machine interaction instructions is as high as 97%. Test results demonstrate that the intelligent cloud platform for interior design based on digital twins has good performance and certain application value.

Keywords: Digital twin technology, expected output, smart home, human-computer interaction

Cite As

T. Ju, X. Yu, "Intelligent Cloud Platform for Interior Design Based on Digital Twins", Engineering
Intelligent Systems, vol. 32 no. 5, pp. 487-496, 2024.

Intelligent Logistics Supply Chain Management Based on Internet of Things Technology

Jing Yi — 2024-09-01

Nowadays, a significant amount of research is being conducted on intelligent systems for supply chain management (SCM). The logistics industry is under enormous pressure due to the increasing number of people who are shopping online. The traditional logistics industry is in urgent need of high-tech support. It is a novel idea to use the Internet of Things to design a logistics management system, which combines the current field of logistics management with the field of the Internet of Things. There are many problems in the current logistics field, such as weak management, limited management scope and long management time. These shortcomings make traditional logistics management approaches unsuitable for the rapid development of online shopping in today’s world. To solve these problems, this paper proposes a hybrid SCM system based on the integration of the Internet of Things with traditional logistics management systems and high-tech network technology. The method proposed in this paper uses a combination of the positioning algorithm of trilateration in the Internet of Things and the Multiple Dimensional Scaling (MDS) positioning algorithm to locate and transmit logistics information. The combination of the two has created a new digital logistics management system. The analytical results showed that with the proposed hybrid logistics management system, the weight of distribution reliability in logistics service was 0.371 and the user caring weight was 0.268, giving a total of 0.639, which is more than half of the total weight. This indicates that these two dimensions play a crucial role in the quality of logistics services. In addition, surveys were conducted on logistics pickup services and online shopping services. The survey results demonstrate that the proposed logistics management system is feasible. Overall, the results yielded by this study clearly show that the Internet
of Things technology can be applied successfully to the current logistics management system, providing a possible direction for the future development of an efficient logistics management system.

Keywords: Internet of Things, logistics management, online shopping network, multidimensional scaling

Cite As

J. Yi, "Intelligent Logistics Supply Chain Management Based on Internet of Things Technology",
Engineering Intelligent Systems, vol. 32 no. 5, pp. 497-506, 2024.

Intelligent Security System in Food Supply Chain Based on Big Data Analysis

Xin Zhang — 2024-09-01

Traditional security management systems established and applied in the food supply chain mostly use relational databases and parallel data warehouses to store, manage and analyze data. With the continuous development of technology, today’s data sources are more diverse, and traditional methods no longer meet the requirements for data processing efficiency and availability. Therefore, big data analysis can be used to establish an intelligent security system in the food supply chain, which segments massive data, decomposes tasks, and summarizes results. This facilitates intelligent security monitoring and the management of every link in the food supply chain specialization on food supply chain platform. Firstly, a large amount of security-related data in the food supply chain is collected through Internet of Things (IoT) devices and radio frequency identification (RFID) technology, including sensor data, monitoring data, etc. Then, the Hadoop Distributed File System (HDFS) is selected to store the collected raw data. At the same time, the data is preprocessed for subsequent analysis and processing. The preprocessing involves data cleaning, deduplication, conversion, and standardization. Various big data analysis techniques such as Spark and k-means algorithms are utilized to analyze and mine stored data in order to detect abnormal patterns, identify risk events and behaviors, and predict potential threats. Data visualization tools are used to present the analysis results in a way that is easy to understand and visualize. Displaying sensor data, food source information, etc., can help users understand security trends and key indicators in real time. Based on the analysis results, some security responses and decision-making processes are automated by, for instance, automatically invoking security measures and emergency response processes to quickly handle and mitigate security incidents. By continuously optimizing and analyzing models, algorithms, and strategies, as well as learning and training new data, the accuracy and response efficiency of intelligent security systems can be improved. In this study, when using big data analysis technology to process data, the average response time for reading data is 3.647 seconds, and the average response time for writing data is 6.139 seconds, with an average throughput of 896MB/s. Compared with traditional methods, this is a significant improvement of data processing speed, reflecting its stronger parallel processing ability. Big data analysis has good scalability in data processing, and can therefore handle a mixture of multiple types of data. It can also comprehensively and efficiently control security throughout the entire platform for food supply chain specialization to build an intelligent security system. The application of intelligent security systems based on big data analysis in the food industry chain can improve the safety, quality, and traceability of food.

Keywords: Internet of Things Devices, Hadoop Distributed File System, Intelligent Security System, Food Supply chain, Radio
Frequency Identification

Cite As

X. Zhang, "Intelligent Security System in Food Supply Chain Based on Big Data Analysis", Engineering Intelligent Systems,
vol. 32 no. 5, pp. 507-520, 2024.

Investigation and Design of Drainage Network Renovation Engineering in Residential Areas Based on BP Neural Network

Bai Fang — 2024-09-01

Nowadays, residential district drainage systems play a significant role in designing and investigating renovation projects to prevent water contamination and stormwater runoff. After investigating the challenges associated with existing urban drainage pipeline systems, including runoff and its impact on society and the environment, an efficient drainage network renovation is proposed, which is essential for residents’ health and quality of life. A deep learning (DL) technique called backpropagation neural network for residential drainage renovation (BPN2-RDR) is employed in district drainage network projects. Firstly, existing residential drainage infrastructures and the associated challenges are investigated. Secondly, optimized design parameters, including pipe flow, channel capacity, and slopes for controlling runoff, are adopted for the renovation strategies. The training of the neural network model with pertinent data obtained from Waipa district council, including 766 records and 36 attributes, enables the discovery of various design patterns and the identification of the relationships of the parameters within the drainage network system. The design phase utilizes the trained neural network to predict potential issues and optimize the drainage system for enhanced performance. For performance evaluation, the proposed method is analyzed using metrics such as peak flow reduction rate of the drainage system, accuracy, precision, recall, and Root Mean Square Error (RMSE). The result findings confirm the superiority of the proposed algorithm when applied to the district residential drainage network renovation
projects, thereby enhancing the residents’ quality of life.

Keywords: Backpropagation, deep learning, neural network, design parameters, residential drainage network, renovation project, stormwater.

Cite As

B. Fang, R. Hu, "Investigation and Design of Drainage Network Renovation Engineering in Residential Areas Based on BP Neural Network", Engineering Intelligent Systems, vol. 32 no. 5, pp. 521-532, 2024.

Investigation of AI-based Image Recognition Technology Combined with Sensor Technology for Power Grid Quality and Safety

Zhiwei Liu — 2024-09-01

The power grid (PG) has the important task of transmitting, distributing, and supplying electricity, and is an indispensable infrastructure in modern society. Its quality and safety are directly related to productivity, economic development, and people’s everyday lives. The current traditional power grid quality and safety monitoring rely mainly on manual inspection, which has the problems of poor efficiency and high labor costs. In order to enhance the quality and safety of the power grid, improve the efficiency of power grid monitoring, and reduce energy consumption, this study combines image recognition technology with sensor technology based on artificial intelligence (AI) to conduct in-depth research on the quality and
safety of the power grid. This study uses images 1 and 2 of the sample PG route as infrared technology data, and performs noise reduction and feature extraction on the images, analyzing the role of sensor technology in PG job safety detection. To calculate the PG quality safety IR test results, this study sets the parameters to a total of 500 rounds every 50 times. The experimental results show that the node energy L of neural networks, genetic algorithms, and decision tree algorithms is totally consumed by the 600th iteration, while simulated annealing is completely consumed by the 550th iteration. This indicates that the combination of image recognition technology with sensor technology can efficiently monitor in real-time the quality and safety of the power grid, which helps to provide effective support for the safe and stable operation of the power grid.

Keywords: Image recognition technology, artificial intelligence, power grid system, sensor technology, power grid quality safety

Cite As

Z. Liu, Y. Bai, B. Hou, K. Ning, X. Liu, J. Zhang, "Investigation of AI-based Image Recognition
Technology Combined with Sensor Technology for Power Grid Quality and Safety", Engineering
Intelligent Systems, vol. 32 no. 5, pp. 533-542, 2024.

Optimal Scheduling Model of Power System Based on Multi-Objective Evolutionary Algorithm

Zhenyuan Zhang — 2024-09-01

In today’s increasingly prosperous society, almost every industry requires electricity to support its operations, and whether the power system can operate stably and safely has been closely related to the steady development of the economy. Optimal scheduling research plays a decisive role in power system operation and control. In order to ensure reliable power supply and power quality, it is important to optimize the operational efficiency of the power system, so that the system can provide greater economic benefits. Traditional multi-objective optimization methods have major shortcomings, and multi-objective optimization methods based on traditional mathematical planning principles usually have certain vulnerabilities in terms of practical engineering optimization problems, so there is a need for in-depth research on efficient and practical multi-objective optimization
algorithms and theories. In this paper, the modeling technology of the power information-physical system is studied and the multi-objective scheduling optimization of power system is explored using a multi-objective evolutionary algorithm. The algorithm analysis results showed that compared with the traditional dispatching model, the proposed multi-objective evolutionary algorithm not only improved the optimization effect of the power system by about 8.95%, but also offered decision makers guidance on dispatching, with good convergence speed and accuracy compared with previous optimization methods and solutions.

Keywords: Power system, multi-objective evolutionary computation, physical communication, scheduling model

Cite As

Z. Zhang, "Optimal Scheduling Model of Power System Based on Multi-Objective Evolutionary Algorithm",
Engineering Intelligent Systems, vol. 32 no. 5, pp. 543-552, 2024.

Research on Big Data and AI in an Interactive Visual Design System

Tian Tian — 2024-09-01

The development, retention and consistency of an item’s aesthetic quality are the main goals of visual design. An in-depth familiarity with these components and their respective guidelines is essential for creating a successful visual design for any product. The integration of big data and artificial intelligence technology is essential so as to address the industry-wide problems of low demand and productivity in visual design systems and to alleviate the burden placed on visual designers by the need to meet simultaneous demands for technical design creations of relatively low quality and high volume. Users can now quickly and easily absorb massive amounts of complicated data with the help of big data visualization tools, thus eliminating the need for time-consuming in-depth data analysis. This is generally done by means of interactive, visually-presented interfaces. However,
Artificial Intelligence helps UX/UI designers build and enhance user-centric designs, reducing the amount of energy and time required. While AI can adapt to human experience, develop and create better outcomes, and implement improvement measures, machines still cannot do so. Hence, this article proposes a Deep Learning Enabled Intelligent Visual Design System (DL-IVDS) to investigate the feasibility of integrating AI technology and big data into visual design in order to assist graphic communication designers. Intelligent systems that generate visual design require high-quality, high-efficiency, and high-quantity visual designs. Researchers will seek ways to combine AI and big data into the design process and then construct a model with complementing benefits. Finally, the component design process illustrates the system’s operating premise, and application processes can
be expanded. A collection of neural intelligence systems in several settings and an aggregation of different configurations, form the basis of a feasible computational collaboration visual aesthetics production system.

Keywords: Intelligent design system, artificial intelligence, big data, visual designing, deep learning, neural networks.

Cite As

T. Tian, "Research on Big Data and AI in an Interactive Visual Design System",
Engineering Intelligent Systems, vol. 32 no. 5, pp. 553-567, 2024.