检索结果-内蒙古大学图书馆

4th International Symposium on Artificial Intelligence and Intelligent Manufacturing, AIIM 2024

作者： Huang, Juan Tang, Jinghua Tang, Dan Cai, Hongliang Yu, Hongzhou School of Software Engineering Chengdu University of Information Technology Sichuan Province Engineering Technology Research Center of Support Software of lnformatization Application Sichuan Provincial Big Data Technical Service Center Chengdu China

ISBN: (纸本)9798331541729

To address the problem of low repair efficiency of single- and double-disk of localized horizontal array code, this paper retains the original advantages of horizontal array code, transforms it on the basis of RDP 2D array code, and proposes a 2D array code model based on nested structure - NRDP (Nested Rows Diagonal Parity Code). The overall layout of the NRDP code is the same as that of the RDP code. However, when deploying data columns, the NRDP code deploys the RDP code of one prime number level smaller as a whole in the data columns of the NRDP code, forming a nested relationship. The increased redundant data reduce the repair overhead and error recovery time. Through theoretical analysis, NRDP has good compiled code complexity, improves the problem of uneven reading and writing during disk repair, and reduces the total amount of data that needs to be read during single- and double-disk failures, improving the success rate of single- and double-disk repair. The experimental results show that compared with RDP, LRRDP, and DRDP, NRDP can save 7.03%-30.01% of the single-disk failure repair time and 14.79%-26.51% of the dual-disk repair time. © 2024 IEEE.

关键词： Codes (symbols)

来源：评论

学校读者我要写书评

暂无评论

Scalable Motion Estimation and Temporal Context Reinforcement for Video Compression Using RGB Sensors

引用

IEEE Sensors Journal 2025年第10期25卷 18323-18333页

作者： Huang, Qian Lu, Hao Liu, Wenting Wang, Yiming Hohai University College of Computer Science and Software Engineering Nanjing211100 China Jiangsu Engineering Research Center of Digital Twinning Technology for Key Equipment in Petrochemical Process Changzhou213164 China

We propose a novel deep learned video compression technique, named scalable motion estimation (SME), which is designed for video data generated by sensor systems in smart devices. These devices face unique challenges due to limited bandwidth, constrained computational resources, and the complexity of real-world scenarios. Existing learned video compression methods primarily rely on optical flow for motion estimation;however, optical flow often suffers from inaccuracies and displacement errors, resulting in imprecise motion vectors, and the increasing complexity of models further limits their deployment in resource-constrained environments. To address these issues, the SME framework introduces a hierarchical motion vector enhancement strategy that progressively optimizes motion information in video captured by sensors. In addition, we propose the temporal context reinforcement (TCR) module, which partitions high-dimensional contextual information into three components. Compared to direct context encoding methods, the TCR module optimizes bit allocation, achieving a more balanced distribution of high- and low-frequency information. Extensive experiments on benchmark datasets demonstrate that the SME framework substantially enhances the efficiency and performance of video compression systems on RGB sensor-captured videos, making it particularly suitable for video applications. © 2001-2012 IEEE.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Static Code Analysis of IEC 61131-3 ST Programs via Symbolic Execution

Static Code Analysis of IEC 61131-3 ST Programs via Symbolic...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Zhao, Mengyan Huang, Yanhong Shi, Jianqi Chen, Yinghao Yang, Yang East China Normal University Shanghai China National Trusted Embedded Software Engineering Technology Research Center Shanghai China Hardware/Software Co-Design Technology and Application Engineering Research Center Shanghai China

ISBN: (纸本)9781665410205

A Programmable Logic Controller (PLC) is an essentially domain-specific computer used to control physical equipment and is widely used in industrial control fields. It plays a crucial role in automating complex processes for industrial automation systems, requiring high reliability as code vulnerabilities can potentially lead to disasters. Therefore, vulnerability detection in PLC programs is of significant importance. However, the availability of tools supporting vulnerability detection in PLC programming languages is limited. This paper attempts to improve industrial security from the perspective of code security and proposes a static code analysis approach specifically designed for IEC 61131-3 Structured Text (ST) programs. This approach uses structural pattern matching and symbolic execution technology to identify program defects and improve quality by detecting problematic code structures and potential issues early in the development process, thereby reducing the debugging effort required during developments. Considering the characteristic of periodic loop execution in PLCs, we introduce the loop unwinding technique to collect constraints from subsequent execution cycles for detection purposes. Based on the aforementioned approach, we implement a static code analysis tool, ST-Checker and make a series of evaluations. The experimental results show that this method is feasible and can detect potential defects that existing PLC compilers cannot detect, improving the precision of defect detection with data dependencies. © 2024 IEEE.

关键词： Programmable logic controllers

来源：评论

学校读者我要写书评

暂无评论

Masked hybrid attention with Laplacian query fusion and tripartite sequence matching for medical image segmentation

引用

Neural Computing and Applications 2025年第8期37卷 5891-5911页

作者： Ekong, Favour Yu, Yongbin Patamia, Rutherford Agbeshi Sarpong, Kwabena Ukwuoma, Chiagoziem C. Wang, Xiangxiang Ukot, Akpanika Robert Cai, Jingye School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu610059 China Sichuan Engineering Technology Research Center for Industrial Internet Intelligent Monitoring and Application Chengdu University of Technology Sichuan Chengdu610059 China

Medical image segmentation is pivotal in computer-aided diagnosis systems, demanding high precision and contextual understanding. Vision Transformer-based approaches have gained much attention recently due to their excellent performance and ability to capture long-range dependencies in medical images. However, research shows they suffer from inadequate multi-scale feature integration, poor object localization, and inconsistent mask predictions, leading to sub-optimal segmentation performance. This paper addresses these challenges by redefining semantic medical image segmentation through learnable object queries within an enhanced transformer framework with a masked hybrid attention querying mechanism, optimizing multi-scale feature fusion, object localization, and instance-specific segmentation. First, this study presents a novel transformer-based masked hybrid attention mechanism using Laplacian query fusion on learnable query features and incorporating a novel tripartite sequence matching technique as part of the enhanced decoder block to improve the consistency of mask predictions and optimize decoder queries. The designed hybrid multi-head self- and cross-attention mechanisms aim to selectively integrate multi-scale features, ensuring optimal feature combinations for precise segmentation. Secondly, multiple class tokens are incorporated to improve object localization and capture class-specific characteristics within the transformer framework, leveraging the transformer decoders’ ability to learn distinct instance representations. Experimental results and extensive ablation studies demonstrate the effectiveness of the proposed approach on three publicly available datasets, obtaining better segmentation results compared to various state-of-the-art approaches using various evaluation metrics. Specifically, the proposed model achieves a Dice Score of 95.25%, 92.75%, and 85.25% on LUNA, ISIC, and DRIVE datasets, respectively. © The Author(s), under exclusive licence

关键词： Laplace transforms

来源：评论

学校读者我要写书评

暂无评论

Research on a High Efficiency Work Flow for Automated Mail Sending 19th

Research on a High Efficiency Work Flow for Automated Mail S...

引用

19th EAI International Conference on Heterogeneous Networking for Quality, Reliability, Security and Robustness, QShine 2023

作者： Tan, Zhongbing Luo, Huibin Beijing Institute of Technology ZhuHai Zhuhai China Software Engineering Technology Research Center Zhuhai ZhuHai China

ISBN: (纸本)9783031651229

In the daily work of enterprises, there is a large amount of complex and repetitive labor. Rapid customization of automated work flows to automate repetitive work for enterprises through low code development has attracted increasing attention from enterprises. This article introduces the the design and implementation of an work flow by Power Automate, which can run automatically to check certificates of power plant equipment, and which can further send an email automatically to the equipment owner at a specified time if the certificate of the equipment will be expired. The work flow effectively helps users in enterprises automate repetitive tasks that were originally manually completed, which greatly improves work efficiency. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering 2024.

关键词： Electric power plant equipment

来源：评论

学校读者我要写书评

暂无评论

MQTT Subscription Tree Optimization and Performance Analysis 7

MQTT Subscription Tree Optimization and Performance Analysis

引用

7th IEEE Advanced Information technology, Electronic and Automation Control Conference, IAEAC 2024

作者： Li, Aodong Beijing University of Technology Beijing Engineering Research Center for IoT Software and Systems Beijing China

ISBN: (纸本)9798350339161

With the continuous development of the Internet of Things (IoT) technology, the large number of messages generated by the increasing number of IoT devices has brought new challenges to MQTT servers. Due to the need for timely forwarding of MQTT messages, the latency of message reception and forwarding will also increase when there are too many clients connected to the server and message publishing and subscription activities are too frequent. In response to this issue, this paper proposes an MQTT subscription tree optimization method that combines hash tables and trie trees. Then, this method is used to implement the subscription tree module of a simple MQTT server, and its performance is compared and analyzed with several other subscription tree implementation methods. The final experimental results show that when a large number of clients connect to the server and frequently publish messages or subscribe to topics, the method proposed in this paper can reduce message forwarding latency, achieve fast message routing, and improve the efficiency of server message forwarding. © 2024 IEEE.

关键词： Data structures

来源：评论

学校读者我要写书评

暂无评论

Joint data augmentation and attention mechanism for occluded human pose estimation 7

Joint data augmentation and attention mechanism for occluded...

引用

7th IEEE Advanced Information technology, Electronic and Automation Control Conference, IAEAC 2024

作者： Pan, Xuelun Li, Da Huang, Zhangqin Yang, Huapeng Beijing University of Technology Beijing Engineering Research Center for IoT Software and Systems Beijing China

ISBN: (纸本)9798350339161

Human pose estimation technology has important applications in many fields. Existing research mainly focuses on precise localization of human key points in unobstructed situations but neglects the common occlusion problem in daily environments. Occlusion can disrupt the correlation between key points in the human body, causing a decrease in model accuracy. In response to the above issues, this article proposes a joint data augmentation and attention mechanism for occluded human pose estimation. This article focuses on training human key points in images, generating a specific number and size of occluded areas to simulate scenarios where human key points are occluded. To further enhance the model's ability to extract feature information, this method considers the global context of feature and integrates the GC Block attention mechanism into the human pose network structure, enabling the network to focus on the human body regions in the image. This method has been experimentally validated on the OCHuman dataset, and the results show that it can effectively improve the accuracy of joint localization in human pose estimation. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Edge Computing-enabled Network Architecture Design for Space-Air-Ground Integrated Network 7

Edge Computing-enabled Network Architecture Design for Space...

引用

7th IEEE Advanced Information technology, Electronic and Automation Control Conference, IAEAC 2024

作者： Zhang, Xiaobo Huang, Zhangqin Huang, Ling Yang, Huapeng Beijing University of Technology Beijing Engineering Research Center for IoT Software and Systems Beijing China

ISBN: (纸本)9798350339161

The space-air-ground integrated network (SAGIN) has become important research content for the next generation of 6G communication networks. Considering the difficulties in network resource management, complex network service configuration, network collaboration and security sharing pressure in network construction. A novel edge computing-enabled network architecture is proposed. On this basis, key technologies such as software defined network (SDN), network slicing and blockchain are used to solve the difficulties in network system construction. Then, the proposed architecture is designed and described in detail. Furthermore, the key technical challenges in the practical application and implementation of the proposed architecture are further explored, providing a fundamental reference for further in-depth research. Finally, simulation experiments verify that the proposed architecture achieves significant improvements in terminal devices' task processing energy consumption and latency compared to network architecture with other studies. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Facial expression recognition method based on dual-branch fusion network with noisy labels 7

Facial expression recognition method based on dual-branch fu...

引用

7th IEEE Advanced Information technology, Electronic and Automation Control Conference, IAEAC 2024

作者： Lv, Zhenhuai Beijing University of Technology Beijing Engineering Research Center for IoT Software and Systems Beijing China

ISBN: (纸本)9798350339161

As an important problem in the field of computer vision, facial expression recognition has been widely used in many fields such as human-computer interaction and emotion recognition. This paper proposes a dual-branch parallel facial expression recognition network that integrates Convolutional Neural Network (CNN) and Transformer. By consolidating local and global information obtained from the dual branches, the network effectively combines subtle local variations and overall contextual features of facial expressions. The fused feature representation demonstrates enhanced representativeness and discriminative power, leading to a notable improvement in facial expression recognition accuracy. In addressing the challenges posed by inter-class similarity and annotation ambiguity, the Erasing Attention Consistency (EAC) mechanism is employed. This mechanism effectively prevents the model from memorizing noisy samples, thereby enhancing robustness against noisy labels. Additionally, the focal loss function is utilized to rectify imbalances within data samples. Experiments conducted on RAF-DB datasets with labels containing noise reveal that the proposed methodology achieves accuracies of 87.65% and 86.05% at 10% and 20% noise rate, respectively. This substantiates the effectiveness of the proposed approach. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Multidimensional data processing and estimation algorithm for pipeline settlement measurement 4

Multidimensional data processing and estimation algorithm fo...

引用

4th International Conference on Artificial Intelligence, Robotics, and Communication, ICAIRC 2024

作者： Zhang, Xialu Huang, Zhangqin Beijing University of Technology Beijing Engineering Research Center for IoT Software and Systems Beijing China

ISBN: (纸本)9798331531225

With the rapid development of our country's economy, the density of urban pipe network has increased continuously. These pipeline lines operate in the environment of long transportation distance, large span and complex geological conditions. Due to the complexity of the environment, they are easily affected by geological disasters, and the settlement or even damage of pipelines may lead to direct and indirect secondary disasters, which will bring great impact on society and economy. The application of RFID based IoT sensing system in underground pipeline management realizes real-time monitoring of pipeline settlement displacement by burying devices carrying RFID tags underground, preventing economic losses and social disasters. Combined with BeiDou positioning technology, the system provides high-precision positioning and deformation monitoring, making positive contributions to the safe operation of urban infrastructure. The technology is expected to become an important tool for underground pipeline management and promote social stability and sustainable development. © 2024 IEEE.

关键词： Urban transportation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：