Intelligent Decision Technologies - Volume 18, issue 4

Authors: Li, Haiqiang | Ling, Zhimei | Yang, Chaoyi

Article Type: Research Article

Abstract: With the digital transformation of information technology and industry, the applicability scenarios of edge intelligent terminals are expanding. AI chips have become one of the mainstream core devices of edge terminals. How to select suitable AI chips according to application scenarios through systematic analysis has become an urgent problem to be solved. This paper first provides a comparative analysis of the technical architecture and advantages and disadvantages of AI chips; then proposes a low implementation complexity, multi-code rate fusion LDPC parallel coding structure, and an encoder chip design scheme using this structure for high-speed digital transmission applications. Based on the …TSMC 130 nm CMOS standard cell library, the encoder chip can achieve a throughput rate of 1.6 Gbps at 200 MHz clock and consume only 184.3 m W. Compared with the LDPC encoder chip with the same throughput rate designed in the conventional architecture, this solution can reduce the storage space requirement to 18.52% of the conventional architecture. The proposed encoding chip design solution not only maintains high performance but also significantly reduces the demand for storage space, making it a good choice for resource-constrained environments. Show more

Keywords: AI chip, edge intelligence, LDPC encoder, multi-code rate fusion, integrated chip design

DOI: 10.3233/IDT-240112

Citation: Intelligent Decision Technologies, vol. 18, no. 4, pp. 3259-3276, 2024

Authors: Li, Xingdong | Hu, Shengwu

Article Type: Research Article

Abstract: In order to obtain the rigorous accuracy of any point on the straight line element, based on existing research, this article considers the error of the straight line element and the error of any point to its end point of the straight line element, attempts to discuss the accuracy calculation of any point on the straight line element in three different situations, and through case analysis, compares the position covariance matrix of any point on the straight line element in three situations and draws its error ellipse using MATLAB programming. Finally, different accuracy sizes and different error ellipses are obtained. …This research has certain guiding significance and role for error calculation in precision engineering measurement, such as large bridges or large through projects. Show more

Keywords: Rigorous accuracy, linear element, covariance matrix, error ellipses, MATLAB

DOI: 10.3233/IDT-230751

Citation: Intelligent Decision Technologies, vol. 18, no. 4, pp. 3277-3284, 2024

Authors: Yu, Yue | Li, Qiang | Duan, Maojun | Yuan, Minxi | Song, Ziheng

Article Type: Research Article

Abstract: Traditional data storage models are inadequate in the face of the growing demand for big data in transportation and transportation management. Its poor horizontal scalability makes it difficult to deal with the growth of massive data; on the other hand, its complex management makes it challenging to achieve unified management and effective resource utilization due to the differences in equipment from different manufacturers. In order to effectively store and manage this huge amount of information, it is urgent to rely on advanced technical tools. In this context, while ensuring data security and simplifying data management, it is also necessary to …meet the terminal’s demand for high real-time performance, and these factors jointly promote the continuous attention and improvement of data storage terminal performance. This paper proposes a Hadoop solution based on distributed computing. As a distributed system infrastructure, Hadoop allows users to develop distributed programs without a deep understanding of distributed details, fully using the high-speed computing and storage capabilities of Hadoop clusters, which is especially suitable for big data processing tasks on the Internet of Things (IoT) platform. The experimental results show that for a 10 GB data file, the traditional terminal (Terminal 1) can store 7.8 GB, while the Hadoop-based terminal (Terminal 2) can store 9.9 GB. For 50 GB of data files, Terminal 1 and Terminal 2 can store 40.4 GB and 49.8 GB of data respectively. These results show that Hadoop terminals have significant advantages in processing large-scale data, especially in terms of data storage efficiency, and can use storage resources more effectively to meet the high-performance requirements of traffic and transportation management for data storage terminals. Show more

Keywords: Internet of Things, distributed computing, transportation management, data storage terminal, data transfer, data management

DOI: 10.3233/IDT-240196

Citation: Intelligent Decision Technologies, vol. 18, no. 4, pp. 3285-3299, 2024

Authors: Zhu, Yidong | Zhang, Zhe | Liu, Hengyu | Zhao, Bo | Wang, Tong

Article Type: Research Article

Abstract: Load access point planning based on network security is the open capacity assessment for distributive networks to reduce power loss. Distribution network operators must meet consumers’ qualitative and statistical power demands and ensure their satisfaction. The distribution network function aims to minimize power loss by determining the network’s maximum power supply capacity while considering parameters like power flow dispersion, node voltage, line capability, and other limitations. The emergence of new flexible loads presents opportunities and challenges. The study suggested Open Capacity Distribution Network solutions incorporating Distributed Power Supply and Network Reconfiguration (OCDN-DPS and NR). The paper proposes a novel technique …to optimize distribution networks’ open capacity, addressing the issues faced by the expanding use of distributed energy sources. The proposed study produces a rise of 18% in inaccessible capacity and a decrease in power losses by combining distributed electrical power and reconfiguration of network approaches, demonstrating the efficacy of the presented methodologies. The study uses second-order cone relaxing theory to estimate the distribution of the system’s power supply capability on typical days, taking uncertainty into account to satisfy optimization goals. Comparative analysis indicates the unique approach’s superiority, stressing its significance in promoting sustainable energy options in distribution system optimization while maintaining consumer happiness and network security. Show more

Keywords: Distributed power supply, network reconfiguration, open capacity of distribution network, second-order cone relaxation theory

DOI: 10.3233/IDT-240219

Citation: Intelligent Decision Technologies, vol. 18, no. 4, pp. 3301-3322, 2024

Authors: Lin, Shuang | Huang, Jianye | Lin, Chenxiang | Zheng, Zhou | He, Deming | Ma, Teng | Wu, Xinxin

Article Type: Research Article

Abstract: The multi-scale object detection algorithm based on deep learning is a common method for safety monitoring in current power operation scenarios, which is of great significance to ensuring the safety of power operations. For certain power applications with high real-time requirements, the computational complexity of deep learning models may become a bottleneck. Deploying deep learning models requires high-performance hardware support, such as GPUs, which might not be easily achievable in some power field environments. According to the characteristics of common safety monitoring tasks in power operation scenarios, this paper proposes an automatic structured pruning method for multi-scale object detection algorithms. …This method is designed for the safety monitoring of single and fixed-scale targets, effectively reducing the complexity of inference calculations and improving the frames per second (FPS) of real-time object detection without compromising accuracy. Furthermore, the proposed method can adaptively perform automatic structured pruning for targets of different scales. Experiments conducted using the YOLOv5 model demonstrate that the proposed method improves inference speed by approximately 20% for safety monitoring tasks without reducing detection accuracy. Show more

Keywords: Power scene, multi-scale object detection, automatic structured pruning, model optimization

DOI: 10.3233/IDT-240255

Citation: Intelligent Decision Technologies, vol. 18, no. 4, pp. 3323-3332, 2024

Authors: Huang, Cong | Nong, Liyong | Nong, Yingxiong | Lu, Ying | Chen, Zhibin | Li, Zhe

Article Type: Research Article

Abstract: This paper studies the detection model of network access data tampering attack based on blockchain technology to solve the problem of over-dependence on central server and easy data tampering in traditional network environment. The model uses decentralization and encryption technology to monitor user behavior in real time through smart contracts, enhances data protection with SHA-256 hash algorithm, and combines consensus algorithm to ensure data consistency and security. The experimental results show that the model performs well in detecting multiple attack types with an accuracy of 99.51% and an F1 score of 0.98, far exceeding traditional methods and other deep learning …techniques. The model shows good robustness under multi-node attacks, even with 200 attack nodes, the recognition accuracy is still close to 90%, and the response time is less than 3 seconds. Cross-platform testing showed that the model quickly and consistently detected tampering on both Ethereum and Hyperledger, with an average detection time between 0.33 and 0.47 seconds.The hardware acceleration test further shows that the processing speed and hardware utilization of TPU and GPU have been improved, with TPU processing speed reaching 135 MB/s and GPU 122 MB/s. This study will provide a theoretical basis for improving the security, effectiveness and reliability of current network systems, and also lay a solid theoretical and technical foundation for network applications in future network environments. Show more

Keywords: Blockchain technology, central server, data tampering attack detection, convolutional neural network, hash algorithm

DOI: 10.3233/IDT-240176

Citation: Intelligent Decision Technologies, vol. 18, no. 4, pp. 3333-3345, 2024

Authors: Zhang, Zongju

Article Type: Research Article

Abstract: As electronic information technology continuously develops, it has gradually been applied to various industries and plays a vital role in the Internet of Things (IoT). The electronic communication positioning system is an interrelated aggregate or component composed of combining electronic science and technology with information science and technology to determine the spatial position. The current electronic communication positioning system has low positioning accuracy in indoor environments and is easily affected by obstacles such as building structures and walls, making it difficult to achieve accurate positioning. This paper integrated the IoT technology into the design and simulation experiment of the electronic …communication system, aiming to improve the stability and accuracy of the positioning system and improve the quality of the location information service in the current stage of the market. This paper first introduced the architecture of the IoT, including RFID technology analysis and ZigBee technology analysis. Then it studied the classification of common positioning algorithms, and finally conducted a simulation test on the electronic communication positioning system based on the IoT technology in the experimental part. Compared with the traditional electronic communication positioning system, the tested results show that the minimum error of the electronic communication positioning system based on the IoT technology can reach 0.102. The maximum time accuracy can reach 95.34%, proving its effectiveness. In practical application, its error and time accuracy can achieve the required level of location information service. This article provided a brief explanation of the application of electronic information technology in the IoT system to assist in the further development of the IoT. Show more

Keywords: Internet of things technology, electronic communication technology, system design, simulation test

DOI: 10.3233/IDT-240184

Citation: Intelligent Decision Technologies, vol. 18, no. 4, pp. 3347-3363, 2024

Authors: Wu, Jian | Xu, Liang | Chen, Qi | Ye, Zhihui

Article Type: Research Article

Abstract: In the development of automation and intelligent systems, multi-sensor data fusion technology is crucial. However, due to the uncertainty and incompleteness of sensor data, how to effectively fuse these data has always been a challenge. To solve this problem, the study combines fuzzy theory and neural networks to study the process of multi-sensor data transmission and data fusion. Sensor network clustering algorithms based on whale algorithm optimized fuzzy logic and neural network data fusion algorithms based on sparrow algorithm optimized were designed respectively. The performance test results showed that the first node death time of the data fusion algorithm is …delayed to 1122 rounds, which is 391 rounds and 186 rounds later than the comparison algorithm, respectively. In the same round, the remaining energy was always greater than the comparison algorithm, and the difference gradually increased. The results indicate that the proposed multi-sensor data fusion path combining fuzzy theory and neural networks has successfully improved network efficiency and node energy utilization, and extended network lifespan. Show more

Keywords: SSA, BP, fuzzy logic, neural networks, data fusion

DOI: 10.3233/IDT-240316

Citation: Intelligent Decision Technologies, vol. 18, no. 4, pp. 3365-3378, 2024

Authors: Wang, Yongqiang | Yang, Li

Article Type: Research Article

Abstract: Faced with the situation that the elderly people at home have dangerous behaviors, the study explores various aspects of motion target detection, real-time target tracking and behavioral pose recognition and classification, using behavioral poses in videos as samples. To tackle the challenges in detecting motion targets, a target detection method based on Gaussian mixture model (GMM) and four frame difference method is proposed; A tracking technique incorporating Kalman filter (KF) is investigated to trail the behavioral changes of the elderly in actual time. A seven-layer convolutional neural network (CNN) is constructed to face the problem of inaccurate behavioral pose recognition. …Through relevant experimental analyses, the outcomes show that the increased GMM detection way has a complete profile and the accuracy is significantly improved. The KF target tracking technique can trail the object trajectory in actual time and steadily, with the smallest trailing error value of 0.19. The classification accuracy of the CNN pose recognition model is 95.87%, and the pose classification time is 27 seconds. Its performance is superior to the mean shift algorithm, particle filter algorithm, and Cam Shift algorithm in all aspects. When applied in practice, it can accurately identify whether the elderly’s behavior is abnormal and ensure their daily health. Show more

Keywords: Abnormal poses, target tracking, convolutional neural networks, gaussian mixture models, kalman filtering

DOI: 10.3233/IDT-230375

Citation: Intelligent Decision Technologies, vol. 18, no. 4, pp. 3379-3394, 2024

Authors: Tang, Hui | Yan, Jie | Pan, Deng | Chen, Yu

Article Type: Research Article

Abstract: This paper analyzes the healthcare level and the evolution of spatial and temporal pattern of each district and county in Changsha City by using the entropy value method based on the statistics of the number of healthcare facilities, beds, and health technicians in Changsha City from 2010 to 2018, and evaluates the fairness and trend of healthcare resource distribution in Changsha City over the years in terms of per capita level through the calculation of the Gini coefficient. The results show that the medical level in the southern part of Changsha City is better, the medical level in the northern …part is weaker, there are significant differences in the healthcare level between districts and counties and the differences between districts and counties are decreasing year by year; there is a lack of fairness in the level of healthcare technicians in each district and counties in comparison with the level of the number of health care institutions and beds. In this regard, suggestions are made to improve the level of protection of health technical personnel, to equalize the distribution of the internal components of health care, and to improve the construction of the health care system and resource sharing. Show more

Keywords: Health equality, medical health resource allocating, gini coefficient, Changsha City

DOI: 10.1177/18724981241295933

Citation: Intelligent Decision Technologies, vol. 18, no. 4, pp. 3395-3404, 2024

Authors: Zhang, Pengcheng | Yu, Hao | Wang, Wei | Su, Tao | Zhu, Min | Jin, Xin | Huang, Ying

Article Type: Research Article

Abstract: With the rapid development of global navigation satellite system (GNSS) technology, IGS signals play a crucial role in many fields such as positioning, navigation, and time synchronization. Nevertheless, the multipath error problem seriously affects the performance of IGS signals in practical applications. In this paper, the multipath error problem of IGS signals is studied in depth, and an improvement method based on a digital filtering technique is proposed. The article first provides a comprehensive analysis of the impact of multipath error and identifies the shortcomings of existing studies, thus clarifying the motivation of this study. Subsequently, this paper uses digital …filtering techniques to estimate the multipath error accurately and designs a corresponding improvement strategy. Through experimental verification, this paper demonstrates the significant effect of the improved method in improving signal quality and positioning accuracy. Finally, the article summarises the research results. It discusses their potential promotion value in IGS signal reception and related applications, which provides important theoretical support and practical guidance for future technology development and applications. Show more

Keywords: Digital filtering techniques, IGS signals, multipath error estimation, error improvement

DOI: 10.3233/IDT-240242

Citation: Intelligent Decision Technologies, vol. 18, no. 4, pp. 3405-3421, 2024

Authors: Liu, Xin

Article Type: Research Article

Abstract: In film and television production, efficient and precise image processing is vital for achieving realistic visual effects. Therefore, exploring and applying advanced image processing technologies has become an essential method for elevating the production quality of film and television projects. This work investigates the application of artificial intelligence (AI) technology in the processing and production of animated images in film and television scenarios. By comparing the performance of standard Generative Adversarial Network (GAN), DenseNet, and CycleGAN models under different noise conditions, it is found that CycleGAN performs the best in image denoising and detail restoration. Experimental results demonstrate that CycleGAN …achieves a Peak Signal-to-noise Ratio (PSNR) of 30.1dB and a Structural Similarity Index Measure (SSIM) of 0.88 under Gaussian noise conditions. Moreover, CycleGAN achieves a PSNR of 29.5dB and an SSIM of 0.85 under salt-and-pepper noise conditions. It outperforms the other models in both conditions. Additionally, CycleGAN’s mean absolute error is significantly lower than that of the other models. This work demonstrates that CycleGAN can more effectively handle complex noise and generate high-quality images under unsupervised learning conditions. These findings provide new directions for future image processing research and offer important references for model selection in practical applications. This work not only offers new perspectives on the development of animation image processing technology but also establishes a theoretical foundation for applying advanced AI techniques in film and television production. Through comparative analysis of various deep learning models, this work highlights the superior performance of CycleGAN under complex noise conditions. This advancement not only drives progress in image processing technology but also provides effective solutions for efficient production and quality enhancement of future film and television works. Show more

Keywords: High-performance calculation, Zhongying⋅Shensi, film and television images, artificial neural network

DOI: 10.3233/IDT-240577

Citation: Intelligent Decision Technologies, vol. 18, no. 4, pp. 3423-3436, 2024

Authors: Wang, Honglv | Shi, Dingke | Zhang, Chengting | Ding, Nanzhe | Cheng, Chao

Article Type: Research Article

Abstract: Industry 4.0 is reshaping conventional factories into “smart factories” via the widespread use of IoT-enabled networks of linked devices, sensors, and software for process optimization and monitoring. Intelligent manufacturing facilities may employ IoT-based predictive maintenance to reduce downtime, increase equipment longevity, and avoid machine problems. Manufacturers may get real-time insights into energy consumption patterns, which is a major concern in the business. The primary objective is to optimize energy use during part manufacturing. Hence, this paper proposes the Internet of Things- Low-Power Wide-Area Network Model (IoT-LPWM) to monitor manufacturing and reduce energy consumption. The proposed method’s production status component uses …visual Knowledge Map Analysis loaded with data from the edge device. A Low-power wide-area network (LPWAN) is the fundamental component of the suggested approach to industrial wireless communication. Using edge computing technology in LPWAN helps reduce computational complexity by shifting high-intensity processing to the periphery, where devices with computing resources are more readily available. Both the energy needed to process and store massive data and the likelihood of cyberattacks may be decreased with this method. The experimental results show that the IoT-LPWM provides useful information to help them make decisions and reduce energy consumption. The experimental results show that our proposed method IoT-LPWM achieves a high performance ratio of 97%, attack prevention ratio of 96.3%, energy management ratio of 93.8%, and data transmission ratio of 98.1% compared to other methods. Show more

Keywords: Intelligent factory, internet of things (IoT), knowledge map (KM), edge computing(EC), sensors

DOI: 10.3233/IDT-240251

Citation: Intelligent Decision Technologies, vol. 18, no. 4, pp. 3437-3451, 2024