检索结果-内蒙古大学图书馆

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Wang, Jing Wang, Xiaoyang Guo, Jianxiong Tang, Zhiqing Ding, Xingjian Wang, Tian Advanced Institute of Natural Sciences Beijing Normal University Zhuhai China Guangdong Key Lab of AI and Multi-modal Data Processing Department of Computer Science BNU-HKBU United International College Zhuhai China Faculty of Information Technology Beijing University of Technology Beijing China

ISBN: (纸本)9789819615278

With the increasing concern for environmental protection and resource optimization, efficient waste sorting has become a serious challenge today. In this paper, we propose a new offloading control problem that aims to solve waste sorting in wireless bin communication networks. Due to limited computational power, bins belonging to embedded devices rely on simple classification models with varying accuracy. In this scenario, consider a network of intelligent bins, each acting as an independent agent capable of deciding to offload an image to the edge server with a more accurate but resource-intensive model when the local classification is deemed inaccurate. Thus, Our goal is to find a lightweight online offloading policy that can achieve the best possible sorting accuracy while balancing transmission traffic. The method utilizes a Deep Q-network algorithm that enables each intelligent bin to make image-processing decisions autonomously. In the experiment, we validate the effectiveness of improving the performance of waste classification compared with existing flow control methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Distributed Resource Allocation Intelligent Waste Management Waste Sorting Wireless Communication Network

来源：评论

学校读者我要写书评

暂无评论

Helmet wearing detection based on YOLOv5 3

Helmet wearing detection based on YOLOv5

引用

3rd International Conference on Artificial Intelligence, Automation, and High-Performance Computing, AIAHPC 2023

作者： Wu, Chao Wang, De-Yong Shi, Wen-Xi Fang, Jian Zhao, Xue-Yi Fu, Yan-Yun School of Information Science and Engineering Xinjiang University Urumqi830000 China XinJiang Lianhai INA-INT Information Technology Co. Ltd. Urumqi830000 China Key Laboratory of Big Data of Xinjiang Social Security Risk Prevention and Control Urumqi830000 China Beijing Academy of Science and Technology Beijing100035 China

ISBN: (数字)9781510666580

ISBN: (纸本)9781510666573

Complex environments, such as dense personnel and background interference, affect the detection accuracy of whether personnel wear helmets. To solve this problem, a new detection algorithm for helmets based on YOLOv5 is studied in this paper. Firstly, RepVGGblock is used to replace the common convolution in the network to effectively utilize the computing power of GPU. Secondly, the efficient channel attention mechanism is incorporated into the C3 module of the backbone network to enhance the feature identification ability of the backbone network for the hard hat. Then, the boundary box regression function is changed to SIoU to redefine the distance loss and improve the regression accuracy. Finally, the detection performance of multi-scale targets is improved by adding detection layers. The test results on the self-made safety helmet data set show that the average accuracy of the improved YOLOv5 model reaches 94.6%, which is 4.1% higher than that of the original model, and can meet the requirements of target detection. © 2023 SPIE.

关键词： Computing power

来源：评论

学校读者我要写书评

暂无评论

A Few-shot Classification Algorithm Based on Two-stream Frequency-Domain Information Networks

A Few-shot Classification Algorithm Based on Two-stream Freq...

引用

International Conference on Systems and Informatics (ICSAI)

作者： Siquan Hu Jun Jia Zhiguo Shi Jun Zhao School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China Beijing Big Data Center Beijing China

In the domain of few-shot learning, where the scarcity of training data poses a significant challenge, this paper introduces an innovative approach. We present a few-shot classification algorithm that utilizes the Two-Stream Frequency Domain Information Network. This algorithm delves deep into the efficacy of training different frequency components of images in the context of few-shot classification. It integrates filtered and enhanced image frequency domain information as supplementary data to be adaptively fused with the original image data, enhancing and augmenting the available information. Experimental results establish that the few-shot classification model, employing the Two-Stream Frequency Domain Information Network, outperforms leading algorithms in the field of few-shot learning. This enhancement is evidenced by an accuracy improvement of 1.06% and 0.93% on the miniImageNet and tiredImageNet datasets, respectively, when compared to the Meta-Baseline, illustrating the efficacy of this specialized approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Development in Solving Critical Medical Problems 6

Machine Learning Development in Solving Critical Medical Pro...

引用

6th International Conference on Inventive Computation Technologies, ICICT 2023

作者： Fatima, Shaista Sangeetha, G. Ponmurugan, P. Arularasan, A.N. Prabhu Chakkaravarthy, A. Denis, R. Chinnasamy, A. Department of Electronics and Communication Engineering MJ College Telangana Hyderabad500053 India Department of Artificial Intelligence and Data Science R.M.K College of Engineering and Technology Puduvoyal Tamil Nadu Thiruvallur India Department of Research Meenakshi Academy of Higher Education and Research Tamil Nadu Chennai600078 India Department of Artificial Intelligence and Data Science Panimalar Engineering College Poonamallee Tamil Nadu Chennai600123 India Department of Networking and Communications School of Computing College of Engineering and Technology Tamil Nadu Kattankulathur603203 India Department of Computer Science Mount Carmel College Autonomous Karnataka Bengaluru560052 India Department of Data Science and Business Systems School of Computing SRMIST Kattankulathur campus Tamil Nadu 603203 India

ISBN: (纸本)9798350398496

As a result of ML, the healthcare industry undergoes substantial innovation and improvement. As a result, data management, clinical operations, drug research, and surgery are all progressing more quickly. The healthcare sector is now required to use this cutting-edge technology because of the Covid-19 pandemic. More importantly, people stand to benefit the most from technology because it may improve their health outcomes by identifying the best treatment alternatives for them. Thanks to ML's enhanced early disease detection capabilities, the frequency of re-admissions to hospitals and clinics can be reduced. In this article, we'll look at the main applications of machine learning in healthcare as well as its exceptional benefits in changing the industry. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Transforming Education with data Mining: Opportunities, Applications, and Challenges 8

Transforming Education with Data Mining: Opportunities, Appl...

引用

8th International Conference on Inventive Computation Technologies, ICICT 2025

作者： Raut, Amey Hajare, Shital Department of Computer Science & Engineering Faculty of Engineering & Technology Datta Meghe Institute of Higher Education and Research Maharashtra Wardha India Department of Artificial Intelligence and Data Science Faculty of Engineering & Technology Datta Meghe Institute of Higher Education and Research Maharashtra Wardha India

ISBN: (纸本)9798331512248

Educational data Mining (EDM), a scientific subject that emphasizes employing data analysis to improve instruction and learning, was created because of the increased usage of data in education. Through the application of predictive analytics, clustering, and personalized learning systems EDM helps the educators to understand the student performance, interest and requirement. Identifying problem areas that require attention, allocating resources as efficiently as feasible, and developing learning experiences that are customized to each student's needs are all made possible by the data generated by EDM. Although EDM has the power to change the face of education for the better, there are issues such as data privacy, ethical issues and absence of guidelines that still pose a threat. These challenges may be hailed as future advancements in the fields of artificial intelligence, blockchain and other related technologies could also solve these challenges. With the growth of the digital education EDM is likely to transform the way teaching and learning is done by making it more customized, barrier free and effective in the near future. © 2025 IEEE.

关键词： Applications of data Mining in Education CHALLENGES and Future Directions CONCLUSION Enhancing Learning with Predictive Analytics Global Trends and OPPORTUNITIES References Techniques in Educational data MINING

来源：评论

学校读者我要写书评

暂无评论

Adaptive Split Balancing for Optimal Random Forest

arXiv

引用

arXiv 2024年

作者： Zhang, Yuqian Ji, Weijie Bradic, Jelena Institute of Statistics and Big Data Renmin University of China China School of Statistics and Management Shanghai University of Finance and Economics China Department of Mathematics and Halicioglu Data Science Institute University of California San Diego United States

In this paper, we propose a new random forest algorithm that constructs the trees using a novel adaptive split-balancing method. Rather than relying on the widely-used random feature selection, we propose a permutation-based balanced splitting criterion. The adaptive split balancing forest (ASBF), achieves minimax optimality under the Lipschitz class. Its localized version, which fits local regressions at the leaf level, attains the minimax rate under the broad Hölder class Hq,β of problems for any q ∈ N and β ∈ (0, 1]. We identify that over-reliance on auxiliary randomness in tree construction may compromise the approximation power of trees, leading to suboptimal results. Conversely, the proposed less random, permutation-based approach demonstrates optimality over a wide range of models. Although random forests are known to perform well empirically, their theoretical convergence rates are slow. Simplified versions that construct trees without data dependence offer faster rates but lack adaptability during tree growth. Our proposed method achieves optimality in simple, smooth scenarios while adaptively learning the tree structure from the data. Additionally, we establish uniform upper bounds and demonstrate that ASBF improves dimensionality dependence in average treatment effect estimation problems. Simulation studies and real-world applications demonstrate our methods' superior performance over existing random forests. Copyright © 2024, The Authors. All rights reserved.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Geotaggingofplantationinthecatchment Area of Hydro Project

Geotaggingofplantationinthecatchment Area of Hydro Project

引用

International Conference on Computer and Communications Technologies (ICCCT)

作者： S Mathupriya A Chinnasamy B Benisha K Kaviya U Kiruthika Department of CSE Sri Sairam Institute of Technology SRM Institute of Data Science and Business Systems Department of CSE Sri Saram Institute of Technology

ISBN: (数字)9798331537579

ISBN: (纸本)9798331537586

Geo-tagging of plantations within the catchment area of a hydro project is an essential process for effective environmental management and monitoring. This technique involves capturing the precise geographical coordinates of planted vegetation, coupled with detailed metadata, to support the assessment and management of reforestation or afforestation efforts. The process includes field surveys using GPS technology, data integration into Geographic Information Systems (GIS), and regular updates to track growth and ecological impact. By providing accurate spatial data, geo-tagging facilitates visualization of plantation distribution, supports compliance with environmental regulations, and aids in evaluating the effectiveness of conservation strategies. This approachnotonlyenhancesprojectmanagementbut also contributes to the sustainable development of hydro projectsby ensuring thehealth and impactof catchment area vegetation are systematically monitored and managed.

关键词： Surveys Plantations data integration Vegetation Spatial databases Regulation Sustainable development Monitoring Geographic information systems Global Positioning System

来源：评论

学校读者我要写书评

暂无评论

A location semantic privacy protection model based on spatial influence

引用

Scientific Reports 2025年第1期15卷 1-22页

作者： Kuang, Linghong Shi, Wenlong Chen, Xueqi Zhang, Jing Liao, Huaxiong School of Computer Science and Mathematics Fujian University of Technology Fuzhou 350118 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fuzhou 350118 China Faculty of Data Science City University of Macau 999078 Macao

The utilization of numerous location-based intelligent services yields massive traffic trajectory data. Mining such data unveils internal and external user features, offering significant application value across various domains. Nonetheless, while trajectory data mining enhances user convenience, it also exposes their privacy to potential breaches. To address the problem that existing traffic trajectory privacy protection methods rarely consider the location semantics and the spatial influence of interest points when constructing k-anonymity sets, which makes user trajectories vulnerable to attacks, a Location Semantic Privacy Protection Model based on Spatial Influence (LSPPM-SI) is proposed to resist semantic attacks. Firstly, a location semantic mining algorithm is proposed to classify the stopovers based on positional semantics, thereby simplifying the semantic information contained in user trajectories. Secondly, a diversified semantic dummy location selecting algorithm is proposed to resist semantic attacks. To enhance the availability of traffic trajectory data while safeguarding location semantics, a Hilbert curves is used to reduce the area of anonymous regions, and a diversified semantic anonymous set is constructed. Thirdly, the spatial influence of interest points is defined and used to verify the rationality of dummy trajectories within the anonymous trajectory set, thereby preventing attackers from identifying dummy trajectories. Finally, the problem of synthesizing dummy trajectories is transformed into a matching problem for directed bipartite graphs and the optimal k-anonymity set is obtained using the Kuhn Munkres algorithm. Experimental results demonstrate that the proposed model improves traffic trajectory data availability and semantic protection performance by 14% and 46.5%, respectively, compared to traditional models. © The Author(s) 2025.

关键词： Diversified semantic Dummy trajectory synthesis K-anonymity Semantic privacy Spatial influence

来源：评论

学校读者我要写书评

暂无评论

Secrecy Performance Analysis of Artificial Noise Assisted Secure Transmission for MISO systems with Multiple Eavesdroppers

Secrecy Performance Analysis of Artificial Noise Assisted Se...

引用

IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)

作者： Panpan Xu Weijie Tan Kun Niu Zhen Li Changgen Peng School of Mathematics and Statistics Guizhou University Guiyang China Key Laboratory of Advanced Manufacturing Technology of Ministry of Education Guizhou China Guizhou Big Data Academy Guizhou University Guiyang China State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China College of Big Data and Information Engineering Guizhou University Guiyang China

In the paper, we investigate the secure communication of multiple-input single-output (MISO) systems with multiple eavesdroppers. We jointly design the beamforming (BF) and the artificial noise (AN) in MISO systems with multiple eavesdroppers to enhance the secrecy rate. Furthermore, under the secrecy interrupt constraint, we obtain the calculation formulas of the secrecy interrupt probability and the optimal secrecy rate. The simulation results demonstrate that AN with a higher dimension can effectively obstruct eavesdroppers and enhance the system's optimal secrecy rate. In addition, it is proved that the 1/4 full-dimension AN's secrecy rate close to that of the full-dimension AN in the system with multiple eavesdroppers, allowing the trade-off between system secrecy performance and artificial noise design complexity to be realized.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Smart Farming: Intelligent Animal Detection Framework in Agriculture using IoT Sensors 2

Smart Farming: Intelligent Animal Detection Framework in Agr...

引用

2nd International Conference on Edge Computing and Applications, ICECAA 2023

作者： Priyanka, S. Suje, S.A. Selvapandian, D. Narasimharaj, V. Sns College of Engineering Department of Information Technology Coimbatore India Sns College of Engineering Department of Artificial Intelligence and Data Science Coimbatore India Karpagam Academy of Higher Education Department of Computer Science and Engineering Coimbatore India Sri Krishna College of Engineering and Technology Department of Mechatronics Engineering Coimbatore India

ISBN: (纸本)9798350347579

Agriculture, the study and practice of plant cultivation, is crucial to the development of a subsistence farming economy. In India, farming supports more than half of the population. The agricultural sector's expansion has been severely hampered by obstacles. Ineffective crop management and crop raiding by external sources, notably human-wildlife conflict, provide the greatest challenge to farmers. Intricately highlighted by means of integrated systems is a cumulative strategy that employs Internet-of-Things (IoT) and conventional farming practices, as well as barriers to prevent crop destruction. A device that can detect the occurrence of a little alive object using a PIR Sensor or an Ultrasonic Sensor, particularly creatures, fenced terrestrial to be cultivated, this module aims to make agriculture smart. This module also proposes smart irrigation control and real-time data analysis. The GSM Module can send this information as text messages, or the Blynk software can be used to visualize it. The suggested system includes animal identification and a laser security system to minimize noise pollution from animals. Multiple issues have been addressed to aid the farmer in fixing them all at once. © 2023 IEEE.

关键词： Internet of things

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：