检索结果-内蒙古大学图书馆

SSRN 2025年

作者： Zhang, Wenyong Xia, Dawen Chang, Guoyan Zheng, Zhiquan Hu, Yang Huo, Yujia Wang, Ziqiang Feng, Fujian Li, Yantao Li, Huaqing College of Data Science and Information Engineering Guizhou Minzu University Guiyang550025 China School of Computer Science and Engineering South China University of Technology Guangzhou510006 China Engineering Research Center of Micro-nano and Intelligent Manufacturing Ministry of Education Kaili University Kaili556011 China Affiliated Hospital of Guizhou Medical University Guiyang550001 China State Key Laboratory of Public Big Data Guizhou University Guiyang550008 China College of Computer Science Chongqing University Chongqing400044 China College of Electronic and Information Engineering Southwest University Chongqing400715 China

Accurate and timely air quality prediction is important for supporting daily activities and safeguarding respiratory health. However, the complex aerodynamic properties of air pollutants pose significant challenges to accurate air quality prediction. Most existing spatiotemporal prediction models extract spatial features in a coarse-grained manner, which cannot fully utilize the spatial feature data, resulting in poor prediction accuracy. To this end, we propose a novel air quality prediction method based on a Spatiotemporal Transformer with a Kolmogorov-Arnold Network (ST-KAN-Former). Specifically, in the temporal dimension, we use the wavelet transform, KAN, and ProbAttention network to construct the temporal feature extraction model. Based on this, the temporal dimension data are decomposed into high-frequency and low-frequency components, and then feature extraction is performed for fine-grained acquisition of temporal dimension features. Then, in the spatial dimension, we divide the spatial region into four subregions according to the distance parameter between the master site and the slave site and build a spatial feature extraction model for each subregion using KAN and ProbAttention networks. Next, we simulate the attenuation of pollutants during their dispersion to introduce the concept of diffusion coefficients. This approach allows us to apply diffusion processing to data from each subregion, enabling a finer granularity in capturing spatial characteristics. Finally, we employ the KAN and ProbAttention networks to construct a spatiotemporal feature fusion model that integrates temporal and spatial characteristics. Extensive experiments on the Beijing dataset demonstrate that ST-KAN-Former achieves better results compared with the other 11 benchmarks. © 2025, The Authors. All rights reserved.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Dynamic Graph Message Passing Networks for Visual Recognition

arXiv

引用

arXiv 2022年

作者： Zhang, Li Chen, Mohan Arnab, Anurag Xue, Xiangyang Torr, Philip H.S. The School of Data Science Fudan University China Google Research School of Computer Science Fudan University China The Department of Engineering Science University of Oxford United Kingdom

Modelling long-range dependencies is critical for scene understanding tasks in computer vision. Although convolution neural networks (CNNs) have excelled in many vision tasks, they are still limited in capturing long-range structured relationships as they typically consist of layers of local kernels. A fully-connected graph, such as the self-attention operation in Transformers, is beneficial for such modelling, however, its computational overhead is prohibitive. In this paper, we propose a dynamic graph message passing network, that significantly reduces the computational complexity compared to related works modelling a fully-connected graph. This is achieved by adaptively sampling nodes in the graph, conditioned on the input, for message passing. Based on the sampled nodes, we dynamically predict node-dependent filter weights and the affinity matrix for propagating information between them. This formulation allows us to design a self-attention module, and more importantly a new Transformer-based backbone network, that we use for both image classification pretraining, and for addressing various downstream tasks (e.g. object detection, instance and semantic segmentation). Using this model, we show significant improvements with respect to strong, state-of-the-art baselines on four different tasks. Our approach also outperforms fully-connected graphs while using substantially fewer floating-point operations and parameters. Code and models will be made publicly available at https://***/fudan-zvg/DGMN2. © 2022, CC BY.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

Goods Anomaly Detection Based on Multi-Branch Feature Extraction and Foreground Mining

Goods Anomaly Detection Based on Multi-Branch Feature Extrac...

引用

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Zhiqian Jia Wei Li Zuoyong Li Zhipeng Mu Lihui Lin Shenghua Teng College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao China Xiamen Air Traffic Management Station of CAAC Xiamen China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Data Science MinjiangUniversity Fuzhou China Fujian Key Laboratory of Big Data Application and Intellectualization for Tea Industry School of Mathematics and Computer Science Wuyi University Fujian China

ISBN: (数字)9798350356670

ISBN: (纸本)9798350356687

In recent years, significant advancements have been made in the field of anomaly detection. Expanding anomaly detection tasks to new scenarios has become a development avenue. Anomaly detection for the outer packaging of supermarket goods is a challenging task due to the diversity of goods’ appearances, which results in some detection methods suffering from limited sensitivity to anomalies and inadequate target mining. To address these issues, we propose a novel unsupervised anomaly detection method based on multi-branch feature extraction and foreground cosine structure mining strategy. Firstly, we use anomaly synthesis technique to enhance the model’s perception of anomalies and construct more precise decision boundaries in the feature space. Secondly, a multi-branch feature extractor extracts and integrates multi-level and multi-scale features, providing rich texture and semantic information to improve the model’s adaptability in real-world scenarios. Finally, the foreground cosine loss focuses on target mining while supplementing local structural information, further enhancing the model’s ability to detect subtle anomalies. To validate the effectiveness of the proposed method, extensive experiments were conducted on the GoodsAD dataset, sampled from supermarket scenarios. Experimental results show that this method achieves significant performance in image-level detection and pixel-level localization.

关键词： Location awareness Adaptation models Sensitivity Semantics Education Packaging Feature extraction Information technology Anomaly detection Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Extensive Analysis of IoT Assisted Fake Currency Detection using Novel Learning Scheme

Extensive Analysis of IoT Assisted Fake Currency Detection u...

引用

Augmented Intelligence and Sustainable Systems (ICAISS), International Conference on

作者： K. Sundravadivelu P. Gururama Senthilvel N. Duraimutharasan Hannah Rose Esther T Rajesh Kumar. K Department of Computer Science School of Information Technology Madurai Kamaraj University Madurai Tamil Nadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Chennai Department of Information Technology AMET University Kanathur Tamil Nadu Department of Artificial Intelligence and Data Science Velammal Engineering College Chennai Department of Electronics and Communication Engineering Chendu College of Engineering Madurantakam Tamil Nadu India

A person with normal vision can readily read and differentiate between different banknotes, while a person with visual impairment or blindness would have a far more difficult time doing the same. Any person who is blind or visually impaired must have the ability to recognize and identify banknotes in real time since money is so central to our daily lives and is necessary for any business transaction. To do this, deep learning systems were integrated with the Internet of Things (IoT) model. In particular, this study has investigated the feasibility of applying pre-trained deep learning models, namely CNN and CNNXGB for currency categorization and fake currency detection. Pre-trained deep learning models perform well as they require less data to run when compared to newly-trained models. After testing the method on about 4002 photos representing four different denominations of Indian rupees (10, 50, 100, and 500), this study found that the proposed method has performed well. Deep Learning (DL) has recently shown remarkable performance in solving the image classification challenges. Several performance metrics are analyzed to determine the accuracy of the proposed method. The experimental findings result in a training accuracy of 97.12% and a validation accuracy of 96.34%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on data Link State Awareness Based on Buried Point 2

Research on Data Link State Awareness Based on Buried Point

引用

2nd International Conference on Electronics, Communications and Information Technology, CECIT 2021

作者： Yingjie, Ren Zhongyi, Shang Chang, Yang Lisa, Wu Haifeng, Liu Ling, Nie Bowen, Shao Technical Support Center State Grid Corporation Big Data Center Beijing China Beijing China-power Information Technology Co. Ltd. Data Application Research Division Beijing China School of Control and Computer Engineering Data North China Electric Power University Beijing China

ISBN: (纸本)9781665437578

With the construction of the two-level data center of the State Grid, there is a lack of awareness of the data link status of the two-level data center. This paper presents a research on data link state perception based on buried points. First, the data link information is collected through the buried point probe, and the link information is reported by the buried point, combined with random forest regression to analyze the network abnormality, and complete the current link state perception. © 2021 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Design of Intelligent Detection and Alarm System for Accident Anti-collision Based on ARM Technology 5th

Design of Intelligent Detection and Alarm System for Acciden...

引用

5th International Conference on Smart Computing and Communication, SmartCom 2020

作者： Tan, Minfu Hong, Yujie Quan, Guiyan Lin, Yinhua Xi, Erhui Zhang, Shiwen Huang, Weihong Big Data Development and Research Center Guangzhou College of Technology and Business Guangzhou528138 China College of Computer Science and Electronic Engineering Hunan University Changsha410000 China Department of Computer Science and Engineering Guangzhou College of Technology and Business Guangzhou528138 China School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan411201 China

ISBN: (纸本)9783030747169

With the increase of social transportation, traffic accidents are not uncommon, and various disputes often arise in accident responsibility. Law enforcement agencies can only understand the situation at the scene of the accident through the two parties who caused the accident, and the two sides of the accident often have their own opinions. This article designs an anti-collision intelligent detection and alarm system. When cars collide, the collision video recorded during driving can be used as direct evidence, saving a lot of time for both sides of the accident and law enforcement agencies, and improving the efficiency of law enforcement. This article first introduces the research significance of the ARM-based accident collision detection and alarm system, and then deeply analyzes the key technologies used in the system, including the main control A10, embedded system Melis, bus I2C and acceleration sensor BMA250. Then analyze the entire hardware module of the system. After that, it analyzes in detail the initialization and control of the acceleration sensor BMA250 in the software, and the alarm processing process when an accident occurs. Finally, we summarized the design and research of the entire system, analyzed the system's shortcomings, and looked forward to the work that needs to be improved in the future. © 2021, Springer Nature Switzerland AG.

关键词： Alarm systems

来源：评论

学校读者我要写书评

暂无评论

BNIS- Bot Node Isolation Strategy to Prevent DoS Attacks: An Improved Overhearing Solution

TechRxiv

引用

TechRxiv 2023年

作者： Mishra, Satyam Van Tanh, Nguyen Phuc, Vu Minh Informatics and Computer Engineering International School Vietnam National University Hanoi Viet Nam Faculty of Applied Sciences International School Vietnam National University Hanoi Viet Nam Business and Data Analytics International School Vietnam National University Hanoi Viet Nam

This research addresses the issue of information security in the RPL routing protocol against denial of service (DoS) attacks in wireless sensor networks. Our study proposes solutions to detect and prevent DoS attacks using the Contiki operating system to simulate illustrated scenarios and conduct tests on real sensor environments with a network model basis. This helps to demonstrate the impact of DoS attacks on IoT networks and the effectiveness of the proposed security mechanism. The solution proposed involves improving the overhearing mechanism based on a proposed algorithm of listening around to detect which node is performing the attack. The attacking node is then blacklisted and isolated to prevent it from affecting data exchange throughout the network, thereby limiting heavy damage from denial-of-service attacks on low-resource IoT environments. Simulation experiments and real device models demonstrate that implementing the improved overhearing solution can detect the attacking node in a short time with a relatively simple algorithm. Isolating the attacking node has a positive effect, reducing damage in DoS attacks. The proposed solution has the advantage of minimizing energy consumption when compared to previous proposals of the same nature, making it suitable for wireless sensor networks of small and medium scale with limited resources. Additionally, this solution incorporates a Bot node isolation plan to maintain the normal operation of the WSN network while ensuring that Bot infection is avoided, thereby limiting the harm of DoS attacks. © 2023, CC BY.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

Using Arduino Iot Modules As A Low Cost Environmental Research Monitoring System 1

Using Arduino Iot Modules As A Low Cost Environmental Resear...

引用

1st International Conference on computer Science and Emerging Technologies, CSET 2023

作者： Magableh, Murad Marie, Ziyad Mohamed, Rajina R. Bin Ibrahim, Mohd Hafizuddin Jusoh, Julaily Aida Kumar, Rohit Irbid National University Faculty of Business and Financial Science MIS BI and Data Analysis Department Irbid Jordan Al-Istiqlal University Faculty of Administrative Sciences and Informatics Public Administration Department Palestine College of Computing Dan Informatics Universiti Tenaga Nasional Malaysia Politeknik Kuala Terenngganu Department of Electrical Engineering Kuala Terengganu20200 Malaysia UniSZA Faculty of Informatics and Computing Malaysia School of Computer Science and Engineering Jain Deemed to Be University Bangalore India

ISBN: (纸本)9798350341737

Environmental monitoring plays a crucial role in understanding the impact of human activities on our ecosystems. However, the cost and complexity of traditional monitoring systems often hinder widespread deployment, especially in resource-constrained regions. This research paper explores the feasibility and effectiveness of employing Arduino Internet of Things (IoT) modules as a low-cost alternative for environmental research monitoring. The study focuses on designing and implementing an Arduino-based environmental monitoring system capable of gathering real-time data on key environmental parameters, such as temperature, humidity, air quality, and soil moisture. The hardware setup comprises Arduino microcontrollers interfaced with a range of environmental sensors and connectivity modules for data transmission. To assess the system's reliability and accuracy, a series of field experiments were conducted in diverse environmental settings, including urban areas, agricultural zones, and natural habitats. The collected data was compared against measurements from conventional monitoring equipment to validate the Arduino-based system's performance. The research demonstrates that the Arduino IoT modules can effectively monitor and transmit environmental data with a reasonable level of accuracy and stability, making them suitable for various environmental research applications. The low-cost nature of Arduino components and the open-source ecosystem facilitate customization and scalability, enabling researchers and organizations to develop tailored monitoring solutions for specific environmental contexts. Additionally, the paper discusses the challenges and limitations encountered during the deployment of Arduino-based monitoring systems, including power constraints, sensor calibration, and data processing techniques. Furthermore, it explores potential avenues for improvement and optimization to enhance the system's capabilities and data accuracy. In conclusion, this research

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

SELF-TRANSRIBER: FEW-SHOT LYRICS TRANSCRIPTION WITH SELF-TRAINING

arXiv

引用

arXiv 2022年

作者： Gao, Xiaoxue Yue, Xianghu Li, Haizhou Department of Electrical and Computer Engineering National University of Singapore Singapore Shenzhen Research Institute of Big Data Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen China

The current lyrics transcription approaches heavily rely on supervised learning with labeled data, but such data are scarce and manual labeling of singing is expensive. How to benefit from unlabeled data and alleviate limited data problem have not been explored for lyrics transcription. We propose the first semi-supervised lyrics transcription paradigm, Self-Transcriber, by leveraging on unlabeled data using self-training with noisy student augmentation. We attempt to demonstrate the possibility of lyrics transcription with a few amount of labeled data. Self-Transcriber generates pseudo labels of the unlabeled singing using teacher model, and augments pseudo-labels to the labeled data for student model update with both self-training and supervised training losses. This work closes the gap between supervised and semi-supervised learning as well as opens doors for few-shot learning of lyrics transcription. Our experiments show that our approach using only 12.7 hours of labeled data achieves competitive performance compared with the supervised approaches trained on 149.1 hours of labeled data for lyrics transcription. © 2022, CC BY-NC-ND.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Enhancing Online Teaching Effectiveness Through Hand-Raising Detection

Enhancing Online Teaching Effectiveness Through Hand-Raising...

引用

Information Science and Education (ICISE-IE), International Conference on

作者： Xiaoke Zhu Zhiwei Dong Xiaopan Chen Yufeng Shi Henan Engineering Research Center of Intelligent Technology and Application Henan University Kaifeng China School of Computer and Information Engineering Henan University Kaifeng China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China

After the outbreak of the COVID-19 pandemic, online teaching has gradually emerged as an indispensable component of education. Despite its convenience, online education lacks the immediate interactive experience inherent in traditional classrooms. This paper presents a meticulously designed DS-YOLOv8 network model, specifically tailored for real-time recognition of students raising their hands under cameras. On our proprietary dataset, this network model exhibits exceptional accuracy in hand-raising detection, showcasing a 1.3% improvement in the AP50 index compared to the baseline YOLOv8 model. Our focus lies on the application of hand-raising detection within online classrooms with an objective to provide enhanced support for teachers by promptly identifying students raising their hands and thereby improving teaching efficiency while enriching the interactive experience of students in virtual learning environments.

关键词：

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：