Electronics Science Technology and Application

Research on the application of rural publicity design from the perspective of artificial intelligence: A case study of Panjin

Yiran Yang — Fri, 18 Apr 2025 09:19:37 +0800

This paper focuses on the current booming AIGC technology, aiming at the current situation of Panjin visual publicity, and discusses the application strategy and practical path of artificial intelligence technology in rural publicity design. Explore the activation and promotion of rural publicity design under the background of the era of digital intelligence. It aims to provide emerging productivity for the design field through the application of AIGC technology, improve the efficiency and quality of rural publicity design, and promote the deep integration of digital technology and rural revitalization with artificial intelligence technology.

Predictive analysis in computer information management driven by artificial intelligence

Yihan Wang, Juan Cao — Fri, 18 Apr 2025 09:19:40 +0800

In the era of information explosion, traditional computer information management methods are difficult to extract effective information from massive data to support forward-looking decision-making. Artificial Intelligence (AI) technology provides a scientific basis for organisational decision-making by predictive analysis and mining the potential patterns and trends of data. This paper systematically discusses the application of AI in predictive analysis for computer information management, covering key technologies such as machine learning and deep learning, and combining cases such as system performance prediction, user behaviour analysis and market trend prediction to demonstrate the practical effects of AI in improving reliability, conversion rate and return on investment. At the same time, the article points out the challenges of data quality, model interpretability and privacy security, and looks forward to the future development direction of the integration with IoT, big data and other technologies.

New energy vehicle motor computer control system design

Tuo Zheng — Fri, 18 Apr 2025 09:19:43 +0800

This paper introduces new energy vehicles and carries out corresponding control and analysis based on the relevant principles of new energy vehicles. As a remote monitoring and regulation port, drivers supported by new energy vehicles and corresponding automation equipment need to be further connected and communicated. The monitoring network of new energy vehicles includes multi-level management control and data acquisition functions, including communication drive management, PLC process management and automation equipment process. Through the real-time data recording and alarm, the motor control can be effectively set up to ensure the safe operation of the motor control system.

Application research of image signal processing based on deep learning in security monitoring

Xintian Wang — Fri, 18 Apr 2025 09:19:45 +0800

With the growing demand for security monitoring, traditional image signal processing methods are facing challenges in terms of accuracy and efficiency. The development of deep learning technology has brought new opportunities for the application of image signal processing in security monitoring. This paper deeply studies the application of deep learning in signal processing of security monitoring images, including target detection, behavior recognition, image enhancement and so on. This paper analyzes the advantages of deep learning algorithm in processing security monitoring images, such as adaptability to complex scenes and efficient processing of large amounts of data. At the same time, it also discusses the problems it faces, such as data privacy, computing resource consumption, etc., and looks forward to the future development trend.

Research on AI optimization of intelligent manufacturing strategies to enhance shipbuilding efficiency

Yihe Zhao — Fri, 18 Apr 2025 09:19:48 +0800

Shipbuilding is a complex and resource-intensive industry that requires high efficiency and precision. With the advancement of artificial intelligence (AI) and intelligent manufacturing technologies, there is a growing opportunity to optimize shipbuilding strategies. This paper explores the application of AI in enhancing shipbuilding efficiency through intelligent manufacturing, focusing on key areas such as predictive maintenance, process automation, quality control, and supply chain optimization. By integrating AI-driven techniques such as machine learning, computer vision, and digital twin technology, the shipbuilding industry can significantly reduce costs, improve production accuracy, and accelerate delivery times. This research provides an overview of existing AI methodologies, discusses their potential benefits, and outlines the challenges and future directions of AI-optimized intelligent manufacturing in shipbuilding.

A method of data supplementing Global PBL SO2 based on OMI

Chongyang Kang, Xiaofang Yang, Zhuoying He, Kedi Mi, Jie Hu, Xiaorong Yu — Fri, 18 Apr 2025 09:19:50 +0800

Sulfur dioxide(SO2) is an important pollutant gas that affects environment of our lives. Although we had made lots of detections, but still can not receive the distribution of SO2 in the world. Compared with great success in UV-vis spectrometers from remote sensing in OMI and OMPS, can provide SO2 data in a huge range and daily, but cannot receive data as there is no sunshine, this is difficult for researchers to do their study in global or area in high latitudes. In this paper, we tried to supplement the PBL SO2 in the whole world, based on the data of OMISO2, by the function derivative algorithm to segment approximation, and verified the method in the area, where OMI SO2 data are complete. The results show that the spatial distribution of SO2 in the global atmospheric boundary layer is obviously latitudinal zonality. SO2 columns and its variation trend are the same or similar in the same latitude during the year. Through verification we found that the partition below 5° latitude seldom affect the estimation, The accuracy is good in the region where there is no SO2 columns mutation, more than 90% of the grids which differences between the estimation and the truth are in a range of [-0.2DU, 0.2DU], less than the multi-day OMI monthly error of 0.2DU, the function is suitable in this situation, and the estimation will be biased in the region where the volcanic eruption, causes the monthly average SO2 columns mutation, but choosing data from the month nearby with no volcanic eruption can helps to eliminate the effects of volcanic eruptions and also can estimate the areas affected by volcanic eruptions.

Exploration of the connection and effective management utilization between smart home systems and renewable energy devices

Bo Huang, Yanni Hu — Fri, 18 Apr 2025 09:19:53 +0800

This paper explores the connection and effective management of smart home systems with renewable energy devices. Analyzing the current status of connections and existing issues, it proposes effective management strategies such as energy monitoring and data analysis, energy storage system management, and device operation control. Through two practical case studies, the paper validates the feasibility and benefits of the collaborative application of smart homes and renewable energy devices. Research indicates that by unifying communication protocols, applying middleware, and leveraging Internet of Things (IoT) technologies, combined with intelligent management strategies, the utilization efficiency of renewable energy in smart homes can be significantly improved, achieving energy-saving and environmental protection goals. Finally, the paper looks ahead to future development trends, pointing out that the deeper integration of artificial intelligence technologies and the improvement of industry standards will further promote the integrated development of smart homes and renewable energy.

Digital platform empowerment in urban community governance consortium: Implementation mechanisms of the "Xiaowu life" platform from China

Yuqing Sun — Fri, 18 Apr 2025 09:19:55 +0800

Community is the foundation of urban governance. Digital technology has become central to modernizing China’s grassroots governance. This study examines the “Xiaowu Life” platform in Wuhou District, Chengdu, revealing how it integrates community resources and fosters collaborative governance. By forming an organizational community linking government and residents, a value community with shared goals, an action community with coordinated efforts, and an interest community balancing diverse needs, the platform drives governance innovation. Future research should explore deeper digital integration to enhance efficiency, collaboration, and sustainability in urban community governance.

From “Cultural aphasia” to “Global Voice”: Artificial intelligence facilitating the international dissemination of Chinese excellent traditional culture

Jin Zhang — Fri, 18 Apr 2025 09:19:58 +0800

Against the backdrop of the globalization era, cross - cultural communication is not only a current economic and social necessity but also an inherent need for the dissemination of Chinese culture. At present, the international dissemination of Chinese excellent traditional culture faces the dilemma of “cultural aphasia”, and this paper explores the role of artificial intelligence (AI) technology in breaking this situation. Firstly, it deeply analyzes the applicability of core AI technologies such as machine learning, deep learning, natural language processing, and computer vision in cultural dissemination. Secondly, in combination with the actual situation, it discusses the challenges in terms of technical performance, technology update, and talent adaptation during the process of AI - powered cultural dissemination, and proposes targeted countermeasures. This paper provides certain theoretical support and practical guidance for the transformation of Chinese excellent traditional culture from “cultural aphasia” to “global voice”.

The Exploration of context sensitivity in large language models — A Comparative study of translation practice with Tencent Hunyuan and ChatGPT 4 as examples

Bo Han, Hua Zhu — Fri, 18 Apr 2025 09:20:00 +0800

This research compares Tencent Hunyuan and ChatGPT 4 in translation. While these models excel in long-text processing and multilingual translation, they still struggle with capturing deeper meanings, tones, and culturally specific expressions. Context sensitivity affects translation accuracy and fluency, and each model has pros and cons in complex contexts. The study offers references for improving model translation and understanding language - processing mechanisms.

Deep integration and application of electronic science and technology in power system automation control of smart substations

ZheMing Xing — Fri, 18 Apr 2025 09:20:02 +0800

With the rapid advancement of electronic science and technology, the automation control of smart substations has become increasingly intelligent and efficient. This paper explores the deep integration of electronic science and technology in power system automation, focusing on key technologies such as advanced sensors, digital signal processing, artificial intelligence (AI), and the Internet of Things (IoT). Through extensive data analysis, case studies, and experimental evaluation, this research demonstrates how these technologies enhance power system automation, improve grid stability, optimize energy management, and address existing challenges in power distribution.

Research on the impact of quantum computing on the security of financial data encryption

Wuyun Zhaola — Fri, 18 Apr 2025 09:20:06 +0800

This paper introduces the impact of quantum computing on the security of financial data encryption and analyzes the potential threats that quantum computing may pose to traditional encryption algorithms. Firstly, the basic principles and advantages of quantum computing were briefly described, especially its potential to crack classical encryption algorithms such as RSA and ECC and improve computational efficiency. Secondly, the impact of quantum computing on financial transactions, payment systems, privacy protection, and identity authentication was explored, and the security risks faced by financial data were pointed out. Finally, countermeasures were proposed, including post quantum encryption technology, quantum key distribution (QKD), and cross domain cooperation, aimed at improving the security of the financial system. Although quantum computing brings challenges, the financial industry can address this emerging threat and ensure data security through technological innovation and strategic deployment.

Rolling bearing fault diagnosis based on WOA-VMD-YOLOv8

Zihui Ding, Chenyang Wang, Di Zhang, Xin Hu, Jin Wang, Sheng Chen — Fri, 18 Apr 2025 09:20:08 +0800

Rolling bearings are often in a state of high-speed operation, making them highly susceptible to failure. To address this issue, the WOA-VMD-YOLOv8 fault diagnosis model was designed by combining the advantages of Whale optimization algorithm (WOA), variational mode decomposition (VMD) and YOLOv8. The bearing vibration signals collected by Case Western Reserve University were used as experimental data. WOA was applied to optimize the VMD parameters, and the time-frequency diagrams of the WOA-VMD output signals were used as the dataset for YOLOv8. The experimental results show that, compared to the Wavelet Transform(WT)-YOLOv8, the WOA-VMD-YOLOv8 achieves better predictive performance for bearing faults, with Recall rate of 99.7%, mAP@0.5 of 99.5%, and mAP@0.5-0.95 of 99.4%. Therefore, the WOA-VMDYOLOv8 demonstrates practical value in bearing fault detection technology.

Research on the optimization of computer vision algorithms for large - scale models

Haolan Li — Fri, 18 Apr 2025 09:20:11 +0800

This paper delves into the optimization of computer vision algorithms for large - scale models. With the rapid development of deep learning in computer vision, large - scale models have shown remarkable performance in various tasks. However, their high computational demands and memory requirements pose significant challenges. This research explores techniques such as model compression, acceleration strategies, and efficient data handling to optimize these algorithms. Through the analysis, it demonstrates the effectiveness of these optimization methods in improving the efficiency and performance of large - scale computer vision models, making them more applicable in real - world scenarios.

Optimization of YOLO for real-time object detection in robotic applications

Ran Wang — Fri, 18 Apr 2025 09:20:14 +0800

With the rapid development of robotics technology, real-time object detection has become increasingly crucial in robotic application scenarios. YOLO (You Only Look Once), as an efficient object detection algorithm, has been widely applied in the field of robotics. However, in practical applications, it still faces issues such as the balance between speed and accuracy, and poor performance in detecting small objects. This paper delves deeply into the optimization strategies for YOLO real-time object detection in robotic applications. By improving the network structure, optimizing the training algorithm, and adopting multi-modal data fusion and other methods, it aims to enhance the performance of the YOLO algorithm in robotic applications, providing strong support for robots to achieve accurate perception and decision-making in complex environments.

Research on feature selection techniques in software defect prediction

Zijie Zhou — Fri, 18 Apr 2025 09:20:17 +0800

This paper aims to study the application of feature selection technology in software defect prediction, explore the influence of different feature selection methods on the performance of prediction model, and then improve the accuracy and efficiency of software defect prediction. Three common feature selection methods were used: information gain, chi-square test and recursive feature elimination (RFE), and experimental validation was conducted using support Vector Machine (SVM), decision tree, random forest and logistic regression. The experimental results show that the combination of random forest with recursive feature elimination (RFE) method shows optimal performance on multiple indicators, with accuracy of 0.89, precision of 0.84, recall of 0.91, F1 value of 0.87 and AUC value of 0.93, which are better than the other combinations. The junction feature selection can significantly improve the accuracy and efficiency of the model in the software defect prediction. Through the appropriate feature selection methods, it can effectively reduce the redundant features, reduce the model complexity, and improve the prediction accuracy.

Dynamic modeling and motion control strategy simulation analysis of robots

Dajun Tao — Fri, 18 Apr 2025 09:20:20 +0800

Objective: This paper investigates the methods for robotic dynamic modeling and evaluates the performance of motion control strategies, focusing on accuracy, stability, and real-time capabilities in complex trajectory tracking. The aim is to provide theoretical support for optimizing motion control strategies. Methods: A six-degree-of-freedom robotic manipulator dynamic model is established based on the Lagrangian method. Three control strategies—PID control, sliding mode control (SMC), and model predictive control (MPC)— are implemented for simulation experiments. Their performance is compared in terms of trajectory error, torque fluctuation, and computational cost. Results: The experiments demonstrate that MPC achieves the highest trajectory accuracy (RMS error: 0.009 m) and the lowest torque fluctuation (0.14 Nm), but has a longer computation time (4.3 ms/step). Sliding mode control exhibits strong robustness with moderate computational efficiency, while PID control provides the best real-time performance but with relatively larger errors (0.018 m). Conclusion: MPC is suitable for high-precision and complex tasks, sliding mode control is appropriate for scenarios requiring strong robustness, and PID control is more suitable for industrial environments with high realtime demands. This study provides a reference for the application of dynamic modeling and control strategies.

Chip design requirements for building a comprehensive low altitude flight safety protection system

Feifei Zhang, Linying Cai — Fri, 18 Apr 2025 09:20:23 +0800

With the rapid advancement of drone and low altitude aircraft technology, it is particularly important to establish a comprehensive low altitude flight safety guarantee system. The article focuses on the key requirements of chip design in this context, aiming to improve the safety, reliability, and efficiency of flight. Firstly, the current technological challenges were analyzed, including high-precision positioning and navigation, real-time data processing capabilities, low energy consumption, and security guarantees. To address these issues, requirements are proposed in terms of hardware to improve integration, optimize signal processing units, and power management strategies; At the software level, the importance of developing lightweight operating systems and optimizing algorithms is emphasized. By comprehensively considering these factors, specific suggestions are provided for the design of low altitude aircraft chips, aiming to promote the industry’s development towards a safer and more efficient direction.

Feature extraction and analysis of ultra-high-frequency signals for partial discharges in power transformers

Zeyu Cui — Fri, 18 Apr 2025 09:20:25 +0800

In the power system, the local discharge of electrical signal of power transformer are rich and complex, easy to noise interference, and the traditional analysis method has obvious limitations. To this end, the author innovatively puts forward the time frequency analysis and machine learning technology fusion of local discharge electrical signal diagnosis method, through the short Fourier transform and wavelet transform capture high frequency signal component, reuse support vector machine machine learning methods, greatly improve detection accuracy and reliability, provide scientific basis for power equipment on-line monitoring and fault early warning.

AI-powered solutions for network traffic optimization

Ming Tang — Fri, 18 Apr 2025 09:20:28 +0800

With the explosion and increasing complexity of network traffic, management faces various technical challenges. Artificial intelligence (AI) technologies, including machine learning, deep learning, reinforcement learning and big data analysis, are used for traffic feature analysis, prediction, dynamic scheduling and optimization strategy formulation. The proposed optimization scheme is based on these techniques, including architecture construction and data processing.

Analysis of global cybercrimes using the fuzzy analytic hierarchy process and multiple regression model summary

Yanan Song, Xirui Jin — Fri, 18 Apr 2025 09:20:32 +0800

The popularization of the Internet has promoted globalization, but it has also increased the risk of cybercrime. Cybercrime is difficult to combat due to its cross - border nature, and many institutions choose not to disclose attack incidents to avoid damage to their reputations. To address this challenge, countries have formulated cybersecurity policies, while the International Telecommunication Union (ITU) plays a leading role in setting standards, promoting cooperation, and assessing global cybersecurity. After researching this issue, our team believes that the core of the problem should focus on three aspects: the distribution and pattern recognition of global cybercrime, the evaluation of policy effectiveness, and the correlation analysis of demographic data. Therefore, this paper analyzes the core issues based on VCDB data and provides effective suggestions for the development and improvement of national cybersecurity policies and laws.

The practical application of “signals and systems” from the perspective of artificial intelligence

Jie Fang, Xiaoshu Wang, Ping Wu — Fri, 18 Apr 2025 09:20:34 +0800

This paper explores the importance of the “Signals and Systems” course in practical applications and its integration with artificial intelligence (AI) technologies from an AI perspective. By analyzing the fundamental concepts and theories of signals and systems, along with examples of AI applications in signal processing, it demonstrates how AI enhances the performance of signal processing systems and discusses future development directions. Research shows that AI technologies bring new opportunities and challenges to the field of signals and systems, driving innovation and progress in this domain.

Time of arrival estimation with DLC receivers for IEEE 802.15.4a UWB systems

Taijung Huang — Fri, 18 Apr 2025 09:20:37 +0800

: In many conditions, it is necessary for a node in a WSN to be aware of its location in the physical world. If tracking or event-detection functions are not useful if the WSN cannot provide any information where the event has happened. Some location procedures have been proposed in the IEEE 802.15.4a standard, including the TOA estimation, the location estimation, and network location algorithms. In this paper, we discuss an effective TOA estimation scheme with the DLC receiver [7], which employs impulse radio UWB signals compliant with the IEEE 802.15.4a standard. By modifying the synchronization algorithm with the DLC receiver, the TOA can be obtained straightly.

Research on taxonomies, security risks and policies of digital currency: Based on the perspective of literature review

Shanshan Wu, Yuda Wang — Fri, 18 Apr 2025 09:20:39 +0800

This paper systematically composes the domestic and international research literature on digital currencies, summarizes the origin and related concepts of digital currencies, and elaborates on the classification of digital currencies. Based on the development status of digital currency in recent years, we have deeply studied the technical principles, key technologies and operating modes of digital currencies, analyzed the risk challenges in terms of cyber security, cryptographic security, data security and personal information protection. Finally, this paper provides an expectation on the future development of digital currencies and proposes suggestions for further research in cross-border payment and cyber security.

Collaborative integration and innovation and optimization of cruise liner embedded multimedia entertainment system based on artificial intelligence interaction technology driven by big data

Yangchun Shi — Fri, 18 Apr 2025 09:20:42 +0800

With the booming development of the cruise industry, passengers’ requirements for the cruise ship interior installed multimedia entertainment system are increasingly diversified and personalized. This study focuses on how to realize the collaborative integration and innovative optimization of the multimedia entertainment system installed in cruise ships with the help of big data and artificial intelligence interaction technology. Through in-depth study of relevant cutting-edge technologies and analysis of practical cases, a complete system architecture and optimization strategy are designed to improve the entertainment experience of passengers, enhance the efficiency of cruise operation, and promote the upgrading of the cruise industry towards the direction of intelligence.

Timing synchronization of ultra-wideband systems using delay line combination receivers

Taijung Huang — Fri, 18 Apr 2025 09:20:45 +0800

This paper proposes a novel non-data aided timing synchronization algorithm designated as ”timing with delay line combination” (TDLC), to improve the synchronization speed of differential impulse radio ultrawideband systems. Continuously integrating the combinative output signal provided by the proposed ”framedifferential delay line” (FDL), it is found that the integration output exhibits a sharp rising or falling transition at the moment that the first signal per symbol arrives. By accurately detecting the time of the rising or falling edge, the symbol boundary can be simply derived. The proposed scheme achieves timing synchronization within a single symbol duration.

The research on beidou satellite navigation technology for marine personal rescue system

Daihao Zhou, Jianxin Chen, Ruihan Zhang — Fri, 18 Apr 2025 09:20:48 +0800

The marine environment is complex and dynamic, and maritime operations and related offshore projects face numerous safety risks. During offshore operations or the boarding and disembarking process, manoverboard incidents frequently occur. Rapid and timely emergency response and rescue measures are crucial to ensuring the safety of maritime operations. The maritime personal search and rescue system based on the Beidou Satellite Navigation System provides precise positioning and alarm services, enabling efficient distress alerts, self-rescue, and mutual rescue capabilities. Moreover, this system can serve as a vital complement to the global maritime distress and safety system, offering technological support to enhance maritime safety

On the implication of new quality productivity empowering urban-rural integrated development

Zhengquan Liu — Fri, 18 Apr 2025 09:20:52 +0800

To promote the high synchronization and deep integration of new urbanization and rural revitalization, it is inseparable from the integration of urban and rural development empowered by new quality productivity. Urban-rural relations are the most basic form of relations in the process of social development. Urban-rural integration should include the integration of space, industry and social services. The integrated development of urban and rural areas is a new historical stage that must be experienced in the development and evolution of China’s urban-rural relations, a practical path for the Party to lead the people to get rid of poverty and promote the realization of common prosperity in the initial stage of socialism, and an important theoretical achievement of the sinicization of the Marxist theory of urban-rural relations. Promoting the integrated development of urban and rural areas and making systematic institutional arrangements has become a requirement of the times.

Innovative maintenance strategies for X- ray in a complex international environment

Baodong Ma — Fri, 18 Apr 2025 09:20:54 +0800

X-ray technology plays a crucial role across healthcare, industrial, and security sectors, but managing equipment globally presents challenges due to technological disparities, regulatory differences, and supply chain issues. This paper examines innovative maintenance strategies, focusing on preventive maintenance, predictive analytics, and IoT integration. Case studies demonstrate how these approaches improve equipment lifespan, reduce downtime, and enhance performance. The study also emphasizes the need for balancing standardized maintenance protocols with localized adaptations to ensure global efficiency. Advancements in AI and remote monitoring are transforming maintenance practices, offering cost savings and improved reliability

Optimizing meal kit delivery: A system analysis of Hellofresh’s supply Chain

Rong Pei — Fri, 18 Apr 2025 09:20:56 +0800

According to Miller and Kelekian (2015), meal kits are considered a transformative technology as they disrupt the traditional grocery supply chain, fundamentally changing how food is sourced, distributed, and consumed. This article analyzes HelloFresh, a leading representative of the meal kit industry, to demonstrate its efficiency and effectiveness. Through a data-driven approach, HelloFresh ensures operational efficiency while delivering high-quality, fresh meal kits to its customers.

A Study of Students’ Subjective Perspectives on Visual Behavior in AR learning environments

Jing Huang — Fri, 18 Apr 2025 09:20:59 +0800

Augmented reality (AR) technology, with its unique composite of real and imaginary, threedimensional visualization, and deep immersion, has injected new vitality and change into traditional classroom teaching models and learning styles. This study examines the literature to determine the applications of AR in education, which include empowering subject teaching, integrating educational games, and inventing topic teaching materials. Several studies have shown that AR has a positive effect on student learning. However, the majority of current research focuses on the objective effect evaluation of AR applications and does not examine students’ visual patterns and behavior paths in AR learning environments from a subjective perspective. Given the relevance of this perspective, the study recommends a research route for students’ visual behavior in an AR education environment based on existing research.

Synchronization scheme for FD-IR-UWB receiver

Taijung Huang — Fri, 18 Apr 2025 09:21:02 +0800

Synchronization poses a major of challenge in UWB systems because low duty cycles in UWB. This research develops an better synchronization scheme for FD-IR- UWB receivers to improve the synchronization speed.The mechanism reduces the search durarion of the symbol boundaries to only a single frame duration. Moreover,delay element is needed in each branch, since a SLD is also proposed to lower complexity of the parallel search mechanism. performance analysis and simutaitons show that the proposed scheme achieves a lower MSE and a higher PD than other alternatives.

On the performance of a fast synchronization scheme for IR-UWB receivers

TaiJung Huang — Fri, 18 Apr 2025 09:21:07 +0800

Because of the norrow signal duty cycles, SYNC is the most critical issue in UWB-IR systems. Some synchronization schemes like a SD-IR-UWB receiver have been proposed to synchronize received signals rapidly. Yet, SD IR-UWB receiver is not suitable for operation in multi-user stiution because of MAI. By taking advantage of FD-IR-UWB receivers, we propose a PFD-IR-UWB receiver to do so. Our proposed PFD IRUWB receiver manifests better immunity against message passing interface and MAI than the SD IR-UWB. Based on this PFD IR-UWB receiver, search regions are limited to one frame duration without any symbol-level synchronization sheme. Performance of PFD and SD receivers are compared by simulations, showing that the proposed PFD receiver not only achieves significantbit error rate performance but also better and more robust results than the SD receiver in this paper

A two-stage strategy image segmentation algorithm based on deep plug and play

Qin Yaping, Liu Hongjian — Fri, 18 Apr 2025 09:21:10 +0800

Image segmentation is a fundamental and challenging task in the field of image processing. This article proposes a two-stage strategy image segmentation algorithm based on deep plug and play. By conducting numerical experiments on pyCharm and MATLAB, we have verified the robustness and superiority of our proposed algorithm.

Artificial intelligence and electroencephalogram analysis: Innovative methods for optimizing anesthesia depth

Ke Hu — Fri, 18 Apr 2025 09:21:13 +0800

The purpose of this paper is to explore the potential of artificial intelligence and electroencephalogram (EEG) analysis in optimizing anesthesia depth monitoring. research methods include data collection and quality improvement, multimodal data fusion, algorithm generalization and robustness enhancement, and model interpretability improvement. The results show that the combination of AI and EEG significantly improves precision monitoring of anesthesia depth and personalized anesthesia management, reduces postoperative complications, and improves patient safety. The study shows that AI and EEG analysis have great potential for use in deep anesthesia monitoring, but further research and validation are needed in key areas such as data quality, algorithm generalization, and ethical safety. In the future, increasing the interpretability of models through multimodal data fusion is expected to further advance the widespread use of AI in anesthesia medicine to improve clinical outcomes and patient safety.

Integration and application of intelligent optical cable laying and low voltage electrical engineering from the perspective of environmental sustainability

Xiuan Fu — Fri, 18 Apr 2025 09:21:15 +0800

Environmental sustainability has become a global concern, and the integrated application of intelligent optical cable laying and low voltage electrical engineering technology, as a key link in the construction of modern information and communication infrastructure, is of great significance in promoting the process of social informatization and facilitating green and low-carbon development. This paper deeply explores the connotation and current situation of intelligent optical cable laying technology and low voltage electrical engineering technology, analyzes the main problems and challenges faced by the integrated application of the two, proposes targeted countermeasures, and demonstrates the effectiveness of the integrated application through practical cases. Research shows that the integrated application of intelligent optical cable laying and low voltage electrical engineering technology not only improves construction efficiency and quality, reduces energy consumption and emissions, but also promotes the green development of the information and communication industry, providing strong support for achieving environmental sustainability goals.

A simple advertisement image recommendation system based on user profiles

Enhui Yu — Fri, 18 Apr 2025 09:21:18 +0800

The purpose of this paper is to design and implement a simple advertisement image recommendation system based on user profiles. The system constructs a user profile by analyzing the user’s historical behavior, interests and preferences, and makes use of advanced machine learning models for personalized recommendation of advertising images. This paper firstly introduces the theoretical and technical background of the recommendation system, and then elaborates the requirements, outline design and detailed design of the system. In order to improve the recommendation effect, this paper also explores the click rate prediction method based on Z-NFFM (a kind of improved neural network factorization machine) model and the advertisement cold start strategy based on LightGBM-LR (Light Gradient Boosting Machine combined with logistic regression) model. The experimental results show that the system can effectively improve the click-through rate of advertisements, optimize the user experience, and bring higher conversion efficiency for advertisers.

Research on artificial intelligence-assisted software defect prediction and repair techniques

Yin Zheng — Fri, 18 Apr 2025 09:21:21 +0800

In this paper, the application of artificial intelligence technology in software defect prediction and repair is studied with respect to the shortcomings of traditional software defect prediction models in terms of interpretability and robustness. Focusing on the modeling method of Bayesian network in the field of software defect prediction, a software defect prediction model based on Bayesian network is established through data discretization, Bayesian network structure learning algorithm, and probabilistic inference technology. Further, this paper integrates Bayesian network with common predictors such as K-nearest neighbor, decision tree, logistic regression and so on in a soft-voting manner to construct an integrated software defect prediction model. Experimental simulations are carried out on six publicly available software defect datasets, and the results show that the integrated model based on Bayesian network significantly outperforms the traditional integrated model in terms of evaluation indexes such as F1, Recall, and G-Mean.

Research on the teaching reform of “Internet application and development technology” under the mode of applied talents training

Yan Li, Hongxiu Duan, Genjuan Ma, Wenting Ding, Yongyi Lin — Fri, 18 Apr 2025 09:21:24 +0800

Internet Application Development Technology" is an important professional course of computer science in colleges and universities. This paper aims to discuss the teaching reform of "Internet application development technology" under the applied talent training mode. The paper first analyzes the current existing problems in the independent undergraduate course teaching, and then puts forward a series of targeted teaching reform measures. These measures include the optimization of course content, the innovation of teaching methods, the strengthening of practical teaching and the improvement of assessment and evaluation. Finally, this paper also verifies the effectiveness of these reform measures through empirical research, in order to provide useful reference for the teaching reform of relevant courses. In order to improve students' professional knowledge and practical ability, to meet the needs of talents, students with the ability of applied talents.

AIoT-based indoor fire inspection and early warning system

Yan Li, Yanbin Bu, Long Zhang, Yuhao Gou, Xinyue Cheng, Renqin He, Huiting Zhang — Fri, 18 Apr 2025 09:21:27 +0800

This paper analyzes an AIoT-based indoor fire inspection and early warning system that utilizes a layered architecture to achieve multi-source data collection and fusion. The system integrates IoT technology, big data analysis, and artificial intelligence algorithms to build an intelligent fire warning model. Through three major functional modules - real-time monitoring, intelligent analysis, and remote management - the system achieves precise identification and early warning of fire risks, providing reliable theoretical support for indoor fire safety.

A review on advances in design methodologies for integrated circuits

Qingye Wei — Fri, 18 Apr 2025 09:21:29 +0800

The field of integrated circuit (IC) design has witnessed remarkable advancements driven by the need for higher performance, reduced chip size, and enhanced energy efficiency. This review explores state-ofthe-art methodologies in IC design, with a focus on layout optimization and the application of metaheuristic algorithms such as simulated annealing and genetic algorithms. It also examines novel representation techniques like sequence pair, B*-tree, and corneal block sequences that address layout complexity. Furthermore, the study proposes integrating machine learning, reinforcement learning, and predictive models to enhance the adaptability and efficiency of design processes. By offering a comprehensive overview and presenting forward-looking perspectives, this review aims to contribute to the development of next-generation ICs, addressing scalability challenges and ensuring improved performance for advanced electronic systems.

Parallel signal acquisition time with timing with dirty templates in ultra-wideband systems using delay-hopping-transmitted reference receiver

Taijung Huang — Fri, 18 Apr 2025 09:21:32 +0800

Synchronization poses a major challenge to UWB systems due to the low acquisition time in UWB. This study develops an Shared Loopded Delay -Line for FD-IR-UWB receivers to improve the synchronization performance. The proposed parallel search architecture reduces the search time of the symbol boundaries. Moreover, one branch needs a time delay element, since SDL was proposed to lower the implementation complexity of the parallel search architecture. Finally, simulations and theoretical analysis show that the proposed architecture obtains a lower MSE and a higher PD than other alternatives.