检索结果-内蒙古大学图书馆

UNCERTAINTY QUANTIFICATION FOR THE HOMOGENEOUS LANDAU-FOKKER-PLANCK EQUATION VIA DETERMINISTIC PARTICLE GALERKIN METHODS

引用

Multiscale Modeling and Simulation 2025年第2期23卷 687-710页

作者： Bailo, Rafael Carrillo, Jose A. Medaglia, Andrea Zanella, Mattia Centre for Analysis Scientific Computing and Applications Eindhoven University of Technology Netherlands Mathematical Institute University of Oxford United Kingdom Department of Mathematics ` University of Pavia Italy

We design a deterministic particle method for the solution of the spatially homogeneous Landau equation with uncertainty. The deterministic particle approximation is based on the reformulation of the Landau equation as a formal gradient flow on the set of probability measures, whereas the propagation of uncertain quantities is computed by means of a stochastic Galerkin (sG) representation of each particle. This approach guarantees spectral accuracy in uncertainty space while preserving the fundamental structural properties of the model: the positivity of the solution, the conservation of invariant quantities, and the entropy dissipation. We provide a regularity result for the particle method in the random space. We perform the numerical validation of the particle method in a wealth of test cases. © 2025 Authors.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

WeaponVision AI: a software for strengthening surveillance through deep learning in real-time automated weapon detection

引用

International Journal of Information technology (Singapore) 2025年第3期17卷 1717-1727页

作者： Yadav, Pavinder Gupta, Nidhi Sharma, Pawan Kumar Department of Computer Applications National Institute of Technology Haryana Kurukshetra 136119 India Mathematics and Scientific Computing National Institute of Technology HP Hamirpur India

During situations involving dangerous activities, such as armed robbery in public areas, surveillance systems often exhibit delays or inefficiencies in their prompt responding. To obviate the necessity for human involvement, there is a requirement for technology capable of autonomously detecting harmful objects, like firearms in surveillance footages. This article presents WeaponVision AI, an advanced software system that has the ability to accurately identify weapons in live feeds, recorded videos, and images. Moreover, this software has the capability to detect guns even under weak lighting circumstances. The deep learning architecture based on modified YOLOv7 was trained on a vast dataset assortment of 79,558 images of weapons, in developing the WeaponVision AI. The model exhibited satisfactory results following the training phase, achieving significant outcome metrics: a precision rate of 91.75% and a mean average precision of 92.15%. The efficacy of WeaponVision AI is showcased through its ability to accurately identify weapons across diverse environmental and visual conditions. © Bharati Vidyapeeth's Institute of Computer applications and Management 2025.

关键词： Computer vision Deep learning Machine learning Security and surveillance Surveillance system Weapon detection

来源：评论

学校读者我要写书评

暂无评论

Innovative Solutions for Sustainable IoT in Smart City Infrastructure 5

Innovative Solutions for Sustainable IoT in Smart City Infra...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Arul, S. Kavitha, P. Kamalakkannan, S. School of Computing Sciences Department of Computer Science Chennai Pallavaram India School of Computing Sciences Department of Computer Applications Chennai Pallavaram India School of Computing Sciences Department of Information Technology Chennai Pallavaram India

ISBN: (纸本)9798331504403

Smart cities are being created all over the world to enhance the safety and quality of life for their residents via the use of technology. Video surveillance, which includes placing cameras at key locations across the city to keep an eye on public areas and give law enforcement and other local authorities real-time access to recordings, is a crucial part of the architecture of smart cities. Cuttingedge technologies like deep learning, blockchain, edge computing, and cloud computing are used in modern video surveillance systems. This paper offers a comprehensive review of video surveillance systems for smart cities, examining both their benefits and drawbacks. In order to improve inhabitants' safety, security, and overall well-being, this article aims to show the benefits of video surveillance systems in smart cities and offers suggestions for their application. © 2024 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

YOLOv8: A Novel Object Detection Algorithm with Enhanced Performance and Robustness

YOLOv8: A Novel Object Detection Algorithm with Enhanced Per...

引用

2024 International Conference on Advances in Data Engineering and Intelligent computing Systems, ADICS 2024

作者： Varghese, Rejin Sambath, M. Hindustan Institute Of Technology And Science Department Of Computer Applications Chennai India School Of Computing Science Hindustan Institute Of Technology And Science Chennai India

ISBN: (纸本)9798350364828

In recent years, the You Only Look Once (YOLO) series of object detection algorithms have garnered significant attention for their speed and accuracy in real-time applications. This paper presents YOLOv8, a novel object detection algorithm that builds upon the advancements of previous iterations, aiming to further enhance performance and robustness. Inspired by the evolution of YOLO architectures from YOLOv1 to YOLOv7, as well as insights from comparative analyses of models like YOLOv5 and YOLOv6, YOLOv8 incorporates key innovations to achieve optimal speed and accuracy. Leveraging attention mechanisms and dynamic convolution, YOLOv8 introduces improvements specifically tailored for small object detection, addressing challenges highlighted in YOLOv7. Additionally, the integration of voice recognition techniques enhances the algorithm's capabilities for video-based object detection, as demonstrated in YOLOv7. The proposed algorithm undergoes rigorous evaluation against state-of-the-art benchmarks, showcasing superior performance in terms of both detection accuracy and computational efficiency. Experimental results on various datasets confirm the effectiveness of YOLOv8 across diverse scenarios, further validating its suitability for real-world applications. This paper contributes to the ongoing advancements in object detection research by presenting YOLOv8 as a versatile and high-performing algorithm, poised to address the evolving needs of computer vision systems. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Explainable Artificial Intelligence in Healthcare -A Review 7

Explainable Artificial Intelligence in Healthcare -A Review

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Ishwarya, S. Pillai, Anitha S. Hindustan Institute of Technology And Science Department of Computer Applications Chennai India Hindustan Institute of Technology And Science School of Computing Sciences Chennai India

ISBN: (纸本)9798350359299

This study focuses on the application of Explainable Artificial Intelligence (XAI) in Stroke, heart attack and cancer prediction, highlighting the importance of XAI. This technology helps users to clearly understand the reason behind detection, prediction and classification. XAI further enhances the capabilities of these models ensuring that their predictions are accurate but also transparent, interpretable, and actionable. This paper explores recent research and developments in XAI applications for three healthcare domains. It also examines the algorithm, datasets, and accuracy achieved, shedding light on how XAI has improved the accuracy and trustworthiness of predictive models. This study thoroughly analyses Explainable AI's effect on healthcare, delivering insightful information about how XAI is changing the field of predictive medicine and enhancing patient outcomes and healthcare decision-making. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Prediction of Cyber Attacks Utilizing Deep Learning Model using Network/Web Traffic Data 3

Prediction of Cyber Attacks Utilizing Deep Learning Model us...

引用

3rd International Conference on Applied Artificial Intelligence and computing, ICAAIC 2024

作者： Kannan, Balaji Sakthivanitha, M. Jayashree, S. Maruthi, R. School of Computing Science Department of Information Technology Tamil Nadu Chennai India Hindustan Institute of Technology and Science Department of Computer Applications Tamil Nadu Chennai India

ISBN: (纸本)9798350375190

Nowadays, cyber-attacks are growing predominantly due to the development of technologies. It will lead to financial losses to a company and the other problems related to attacks. It is very important to predict such attacks from outsiders to safeguard our networking systems to provide effective security. The Artificial Intelligence (AI), Machine Learning (ML) and Deep Learning (DL) techniques leverage enormous amounts of data to identify the cyber attacks. These learning approaches are used to identify a broad range of cyber-attacks by analyzing the web traffic or network traffic to identify potential threats such as malware, network intrusions and other types of attacks. The study demonstrates the various deep learning methods to predict the anomalies and other potential threats with more accuracy in real time. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence based System to Prevent Animal Accidents in the Railway Tracks 8

Artificial Intelligence based System to Prevent Animal Accid...

引用

8th International Conference on Inventive Systems and Control, ICISC 202

作者： Kannan, Balaji Lakshmi, R.Bagavathi Sakthivanitha, M. Maruthi, R. School of Computing Science Department of Information Technology Tamil Nadu Chennai India Hindustan Institute of Technology and Science Department of Computer Applications Tamil Nadu Chennai India

ISBN: (纸本)9798350386578

The wildlife population has been in danger due to frequent animal accidents on railway tracks. In India, animal train collisions cause an average of 20 elephant deaths every year all over the nation. At the same time railway departments are taking necessary steps to identify the cause and implement prevention methods. Despite this, lots of accidents are happening in the railway tracks near the forest areas. This problem has been addressed by proposing a well-defined technological mechanism to alert the animals to be away from the railway tracks to reduce the wildlife deaths. In this study, Machine Learning(ML) frameworks are employed to detect the animals that are coming near the railway tracks and the developed module will provide appropriate warning or signals to the animals as well as to the loco pilot. © 2024 IEEE.

关键词： Invertebrates

来源：评论

学校读者我要写书评

暂无评论

SV-HaRF: a scene representation method for sparse image view synthesis

SV-HaRF: a scene representation method for sparse image view...

引用

2023 International Conference on Computer Graphics, Artificial Intelligence, and Data Processing, ICCAID 2023

作者： Liu, Wei Zhang, Yu Zou, Xuechao Ma, Rui Tao, Pin Department of Computer Technology and Applications Qinghai University China Department of Computer Science and Technology Tsinghua University China Key Laboratory of Pervasive Computing Ministry of Education China

ISBN: (纸本)9781510677685

Existing view synthesis algorithms often require dozens or even hundreds of photographs taken from different angles to capture more intricate details in the resulting 3D model. While increasing the number of angles can yield better model parameters, it also significantly increases the training cost. Therefore, there is a need to reduce the quantity of input images with different angles while maintaining comparable results. In this paper, we propose SV-HaRF, which aims to reconstruct scenes by using a sparse set of angles (typically less than 100 but not less than 10) to ensure scene model integrity, as the original training sets often consist of over 100 angles. To address this issue, SV-HaRF employs hash encoding on the input sparse image resolutions to enhance the spatial constraint of these viewpoint positions during the scene reconstruction process, thereby improving the ability to restore scene information. SV-HaRF not only demonstrates outstanding performance in synthesizing sparse viewpoints for reducing model angles but also exhibits superior enhancement, compared to existing NeRF and its related variants, when the input image viewpoints remain unchanged. We conducted experiments on the NeRF Blender Synthetic dataset, showcasing significant improvements in scene synthesis achieved by SV-HaRF. © 2024 SPIE.

关键词： Image resolution

来源：评论

学校读者我要写书评

暂无评论

Analysis on Text Compression Algorithms 7

Analysis on Text Compression Algorithms

引用

7th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2023

作者： Aruna, P. Devi, L Yamuna Danusri, E. Pragathy, V.Y. Sri Jaya Vaishnavi, K.S. Coimbatore Institute of Technology Department of Computing Coimbatore India Coimbatore Institute of Technology Department of Computer Applications Coimbatore India Coimbatore India

ISBN: (纸本)9798350341485

In the rapidly evolving digital age, the exponential growth of data accumulation has become a ubiquitous challenge, necessitating efficient file compression techniques for optimized data handling, transmission, and storage. The fundamental concepts and advancements in file compression are explored, shedding light on its significance in today's data-driven world, especially in the field of cloud computing. Cloud computing demands resource efficiency and cost-effectiveness, making compression crucial for data management. Among these techniques, Huffman Coding (Statistical Algorithm) and LZ77 (Dictionary-Based Algorithm) are two prominent algorithms that have found widespread applications in various fields, ranging from data storage and communication to multimedia compression. Additionally, the combination of both Huffman Coding and LZ77 (Deflate Algorithm) are examined, which explores the hybrid compression techniques that harness the strengths of both algorithms. Overall, a comprehensive overview of file compression techniques and their applications are provided, making it a valuable resource for professionals and researchers seeking to optimize data management in the face of mounting data volumes and cloud-based demands. © 2023 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

DYTC:Dynamic Graph Triangle Counting on GPU 24

DYTC:Dynamic Graph Triangle Counting on GPU

引用

8th International Conference on Algorithms, computing and Systems, ICACS 2024

作者： Wang, Zhuo Li, Zhixiong Tu, Jinxing Huang, Jianqiang Department of Computer Technology and Applications Qinghai University Xining China Intelligent Computing and Application Laboratory of Qinghai Province Qinghai University Xining China

ISBN: (纸本)9798400718304

Triangle counting is a critical problem in graph theory and network analysis, with widespread applications in social network analysis, network science, and bioinformatics. Dynamic graphs are extensively utilized in various domains and are prevalent in real-world scenarios. Over time, dynamic graphs necessitate frequent updates, where vertices and edges are inserted, deleted, or modified. However, existing dynamic graph analysis methods often focus solely on the data structure of dynamic graphs, neglecting the algorithms for dynamic graph processing. Current triangle counting methods are typically designed for static graphs and are not suited for continuously updated dynamic graphs. In this paper, we propose an incremental triangle counting algorithm tailored for dynamic graphs, which only requires recomputing the affected subgraph caused by updated edges, rather than the entire graph. Consequently, in comparison to the previous algorithm, our algorithm is capable of attaining a maximum speedup of . © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Graph algorithms

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：