检索结果-内蒙古大学图书馆

VisioSLR: A Vision Data-Driven Framework for Sign Language Video Recognition and Performance Evaluation on Fine-Tuned YOLO Models

引用

Procedia Computer Science 2025年 257卷 85-92页

作者： Leila Ismail Nada Shahin Henok Tesfaye Alain Hennebelle Intelligent Distributed Computing and Systems (INDUCE) Lab Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University United Arab Emirates Independent Researcher

With the emergence of AI for good, there has been an increasing interest in building computer vision data-driven deep learning inclusive AI solutions. Sign language Recognition (SLR) has gained attention recently. It is an essential component of a sign-to-text translation system to support the deaf and hard-of-hearing population. This paper presents a computer VISIOn data-driven deep learning framework for Sign Language video Recognition (VisoSLR). VisioSLR provides a precise measurement of translating signs for developing an end-to-end computational translation system. Considering the scarcity of sign language datasets, which hinders the development of an accurate recognition model, we evaluate the performance of our framework by fine-tuning the very well-known YOLO models, which are built from a signs-unrelated collection of images and videos, using a small-sized sign language dataset. Gathering a sign language dataset for signs training would involve an enormous amount of time to collect and annotate videos in different environmental setups and multiple signers, in addition to the training time of a model. Numerical evaluations of VisioSLR show that our framework recognizes signs with a mean average precision of 97.4%, 97.1%, and 95.5% and 11, 12, and 12 milliseconds of recognition time on YOLOv8m, YOLOv9m, and YOLOv11m, respectively.

关键词： Artificial intelligence Computer vision Deep learning Fine-tuning Machine translation Neural machine translation Sign language Sign language recognition Transfer learning YOLO

来源：评论

学校读者我要写书评

暂无评论

Application of Neural Networks for Network Traffic Monitoring and Analysis 8

Application of Neural Networks for Network Traffic Monitorin...

引用

8th International Symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2024

作者： Kushnerov, Oleksandr Murr, Pierre Herasymov, Serhii Milevskyi, Stanislav Melnyk, Marharyta Golovashych, Sergii Sumy State University Department of Economic Cybernetics Sumy Ukraine International University of Science and Technology in Kuwait Computer Engineering Department Kuwait Kuwait 'Kharkiv polytechnic institute' Cybersecurity department National Technical University Kharkiv Ukraine Set University Department of Cyber Security and information protection Kyiv Ukraine National Technical University 'Kharkiv polytechnic institute' Department of Software Engineering and Management Intelligent Technologies Kharkiv Ukraine

ISBN: (纸本)9798350354423

Monitoring and analyzing network traffic are critically important tasks in the context of increasing cyber threats. Traditional data processing methods often struggle to handle the large volumes and complexity of modern network traffic, necessitating the use of advanced technologies such as neural networks and machine learning. This article demonstrates the application of neural networks for monitoring and analyzing network traffic, highlighting their ability to learn from large datasets to detect complex patterns and anomalies. Using TensorFlow, we developed a neural network model based on an autoencoder that effectively identifies and classifies anomalies in network traffic. The model's effectiveness was validated using a synthetic dataset from Kaggle, showing high accuracy on both training and testing data. Our approach significantly improves the efficiency and accuracy of threat detection compared to traditional methods, making it a valuable tool for enhancing cybersecurity. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

State-based Sandbox Tool for Distributed Malware Detection with Avoid Techniques 13

State-based Sandbox Tool for Distributed Malware Detection w...

引用

13th International Conference on Dependable Systems, Services and Technologies, DESSERT 2023

作者： Rehida, Pavlo Markowsky, George Sachenko, Anatoliy Savenko, Oleg Khmelnytskyi National University Department of Computer Engineering and Information Systems Khmelnytskyi Ukraine Kennesaw State University Department of Software Engineering and Game Development Marietta United States Kazimierz Pulaski University of Technology and Humanities Department of Informatics Radom Poland Research Institute for Intelligent Computer Systems West Ukrainian National Unversity Ternopil Ukraine

ISBN: (纸本)9798350396119

This paper deals with the problem of detecting the malware by using emulation approach. Modern malware include various avoid techniques, to hide its anomaly actions. Advantages of using sandbox and emulation technologies are described. Various anti-emulation techniques that are used in modern malware considered. Obfuscation as one primary approach to hide malware malicious actions described and discussed. State of emulator is presented, and the advantages of its usage are covered. Distributed model for malware detection is considered. Basic emulator and its current capabilities presented. Prepared files that represent malware are described. Experimental results for developed files that differs with included avoid techniques are presented. Disadvantages of proposed approach is described. Future research and sandbox improvement are described. © 2023 IEEE.

关键词： anti-emulation techniques malware detection obfuscation techniques sandbox

来源：评论

学校读者我要写书评

暂无评论

LV-Mamba: Integrating Denoising Mechanism with Mamba for Improved Segmentation of the Pediatric Echocardiographic Left Ventricle 5th

LV-Mamba: Integrating Denoising Mechanism with Mamba for Imp...

引用

5th International Conference on Medical Imaging and Computer Aided Diagnosis, MICAD 2024

作者： Chen, Tianxiang Chang, Zeyu Wang, Fangyijie Wang, Ziyang Ye, Zi University of Science and Technology of China Hefei China School of Biomedical Engineering and Imaging Sciences King’s College London London United Kingdom School of Medicine University College Dublin Dublin Ireland Department of Computer Science University of Oxford Oxford United Kingdom Institute of Intelligent Software Guangzhou China

ISBN: (纸本)9789819638628

In pediatric cardiology, the accurate and immediate assessment of cardiac function through echocardiography is crucial since it can determine whether urgent intervention is required in many emergencies. However, echocardiography is characterized by ambiguity and heavy background noise interference, causing more difficulty in accurate segmentation. Present methods lack efficiency and are prone to mistakenly segmenting some background noise areas, such as the left ventricular area, due to noise disturbance. We introduce LV-Mamba for efficient pediatric echocardiographic left ventricular segmentation to relieve the two issues. Specifically, we turn to the recently proposed vision mamba layers in our vision mamba encoder branch to improve our model’s computing and memory efficiency while modeling global dependencies. In the other DWT-based PMD encoder branch, we devise DWT-based Perona-Malik Diffusion (PMD) Blocks that utilize PMD for noise suppression while preserving the left ventricle’s local shape cues. Leveraging the strengths of both encoder branches, LV-Mamba achieves superior accuracy and efficiency to established models, such as vision transformers with quadratic and linear computational complexity. This innovative approach promises significant advancements in pediatric cardiac imaging and beyond. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Pediatrics

来源：评论

学校读者我要写书评

暂无评论

A Data-Driven Approach Towards software Regression Testing Quality Optimization 25

A Data-Driven Approach Towards Software Regression Testing Q...

引用

25th International Arab Conference on Information technology, ACIT 2024

作者： Moubayed, Abdallah Alhindawi, Nouh Alsakran, Jamal Injadat, MohammadNoor Kanan, Mohammad King Fahd University of Petroleum & Minerals Computer Engineering Department Interdisciplinary Research Center for Intelligent Secure Systems Dhahran Saudi Arabia Arizona State University School of Computing and Augmented Intelligence GilbertAZ United States Jadara University Department of Software Engineering Irbid Jordan Fairleigh Dickinson University Canada Zarqa University Data Science & Artificial Intelligence Department Zarqa Jordan University of Business and Technology Department of Industrial Engineering Jeddah Saudi Arabia

ISBN: (纸本)9798331540012

software testing is very important in software development to ensure its quality and reliability. As software systems have become more complex, the number of test cases has increased, which presents the challenge of executing all the tests in a limited time frame. Various test case prioritization techniques have been introduced to solve this problem. These methods aim to identify and implement the most critical tests first. In this paper, we propose an implementation of a dynamic test case prioritization strategy to improve software quality by increasing code coverage with special attention to edge case handling. Edge case test prioritization is a technique that improves test efficiency by selecting extreme case scenarios that can reveal critical bugs or unexpected behavior early in development, improving overall software reliability and dependability. In order to prioritize test cases, this paper presents a regression-based method that makes use of machine learning algorithms. The approach leverages previous performance data to optimize regression testing efficiency by examining variables like test time and execution status. Performance evaluations, when compared against industry standards and cutting-edge techniques, show how effective these algorithms are at correctly prioritizing test cases and identifying faults. This study offers simplified yet reliable solutions for regression testing optimization by shedding light on the efficacy of regression algorithms, such as Random Forest and decision trees. © 2024 IEEE.

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

?-net: Dual supervised medical image segmentation with multi-dimensional self-attention and diversely-connected multi-scale convolution

引用

NEUROCOMPUTING 2022年 500卷 177-190页

作者： Xu, Zhenghua Liu, Shijie Yuan, Di Wang, Lei Chen, Junyang Lukasiewicz, Thomas Fu, Zhigang Zhang, Rui State Key Laboratory of Reliability and Intelligence of Electrical Equipment Hebei University of Technology China Tianjin Key Laboratory of Bioelectromagnetic Technology and Intelligent Health Hebei University of Technology China College of Computer Science and Software Engineering Shenzhen University China Department of Computer Science University of Oxford United Kingdom Department of Health Management Center 983 Hospital of Joint Logistics Support Force China www.ruizhang.info

Although U-Net and its variants have achieved some great successes in medical image segmentation tasks, their segmentation performances for small objects are still unsatisfactory. Therefore, in this work, a new deep model, co-Net, is proposed to achieve more accurate medical image segmentations. The advancements of co-Net are mainly threefold: First, it incorporates an additional expansive path into U-Net to import an extra supervision signal and obtain a more effective and robust image segmentation by dual supervision. Then, a multi-dimensional self-attention mechanism is further developed to highlight salient features and suppress irrelevant ones consecutively in both spatial and channel dimensions. Finally, to reduce semantic disparity between the feature maps of the contracting and expansive paths, we further propose to integrate diversely-connected multi-scale convolution blocks into the skip connections, where several multi-scale convolutional operations are connected in both series and parallel. Extensive experimental results on three abdominal CT segmentation tasks show that (i) co-Net greatly outperforms the state-of-the-art image segmentation methods in medical image segmentation tasks;(ii) the proposed three advancements are all effective and essential for co-Net to achieve the superior performances;and (iii) the proposed multi-dimensional self-attention (resp., diversely-connected multi scale convolution) is more effective than the state-of-the-art attention mechanisms (resp., multi-scale solutions) for medical image segmentations. The code will be released online after this paper is formally accepted. (c) 2022 Elsevier B.V. All rights reserved.

关键词： Medical image segmentation Dual supervision Multi-dimensional self-attention Diversely-connected multi-scale convolution

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Deep Learning Based Approach for Plant Disease Recognition

An End-to-End Deep Learning Based Approach for Plant Disease...

引用

International Conference on Communications, Information System and Computer engineering (CISCE)

作者： Mingyue Guo Qiutong Li Deyu Liu Department of Intelligent Science and Technology Chengdu Neusoft University Chengdu China Department of Network Engineering Chengdu Neusoft University Chengdu China Department of Software Engineering Chengdu Neusoft University Chengdu China

ISBN: (数字)9798350353174

ISBN: (纸本)9798350353181

The agricultural industry is essential in providing high-quality food and plays a significant role in growing economies and populations. Plant diseases can cause severe losses in food production and eliminate species diversity. Using automated detection techniques for diagnosing plant diseases can enhance food productivity and minimize economic losses in the early stage. Recent advancements in Deep Neural Networks have significantly enhanced the accuracy of object recognition systems. In this paper, we present an end-to-end deep learning based methodology to recognise different diseases of plants, not limited to specific plant species. We investigate the efficiency of different Visual Transformer models with the transfer learning strategy. The AI Challenger 2018 Crop Disease Detection and PlantVillage datasets are used for training and evaluation. Experimental results indicate the efficacy of our proposed approach in accurately recognizing various plant diseases.

关键词： Deep learning Industries Plant diseases Analytical models Visualization Biological system modeling Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Automated Classification of Medical Images Using Convolutional Neural Networks 15

Automated Classification of Medical Images Using Convolution...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Pillai, N. Muthuvairavan Manimala, S. Rongali, Aruna Sri Gugnani, Anchit Kumar, Senthil A. Sriramakrishnan, G.V. Computer Science and Business Systems R.M.D Engineering College Thiruvallur district Kavarapettai India Computer science and engineering University SJCE JSS Science and technology University Karnataka Mysore India Sr. Software Engineer Department Information Technology Emphasis/Information Technology Ph.D University The country University of The Cumberlands United States Physiotherapy Amity University Rajasthan Jaipur India Artificial Intelligent department Shri Vishnu Engineering College for Women AP Bhimavaram India Tamilnadu Chennai India

ISBN: (纸本)9798350370249

Medical imagery has been increasingly used in diagnosing and treating various diseases, leading to advances in healthcare. While humans usually lead the qualitative interpretation of visual features, Automated Classification of Medical Images Using Convolution Neural Networks (CNNs) has gained traction for accurate image classification. CNNs are a type of deep learning algorithm that attempts to mimic the structure of the human brain and are ideal for image classification due to their convolution layers that can detect patterns within the image. These convolution layers enable the networks to learn the characteristics of the data through a series of convolution and pooling operations. Additionally, they can rapidly identify relationships and patterns within the dataset and extract features from the input image, thus allowing a more accurate classification. With the increasing availability of medical imaging data, advancements in the field of ML/AI has enabled the use of CNNs for automated medical image classification, helping clinicians to diagnose diseases accurately with less time and effort. ©2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Automated Area Based Explosive Trace Detection System

Automated Area Based Explosive Trace Detection System

引用

Science, engineering and Business for Sustainable Development Goals (SEB-SDG), International Conference on

作者： Monday F. Ohemu Ambrose A. Azeta Ibrahim A. Adeyanju Nuradeen Maidoki Department of Artiftial Intelligent ACETEL-National Open University of Nigria Nigeria Department of Software Engineering Namibia University of Science and Technology Namibia Department of Computer Engineering Federal University Oye-Ekiti Nigeria Natview Technology Abuja Nigeria

ISBN: (数字)9798350358155

ISBN: (纸本)9798350358162

Explosive based attacks on people and sensitive places in the form of terrorism has become a global challenge that is making organizations such as airports, train station, security agencies and the government to do anything possible to secure the lives of people and some essential infrastructures. Several approaches have been adopted to prevent its occurrence that ranges from the use of animals, analytical means and sensor based approach to manual screaming by human personnel. With the development in the field of Artificial intelligent, efforts are being made to deploy Sensor base system that leverage of machine learning technology to make the system highly accurate and sensitive in detection of explosive trace within an environment. This study presents the architecture of area base explosive trace detection utilizing deep learning model. The experiment shows the concept of area based explosive trace detection from trace properties of Carbon, Nitrogen, Oxygen and Hydrogen (CNOH). The deep leaning model recorded an accuracy of 98% on the explosive trace data. The system uses this information to detect the presence of explosion within an area.

关键词： Wireless sensor networks Accuracy Oxygen Terrorism Explosives Data models Real-time systems

来源：评论

学校读者我要写书评

暂无评论

LinNet: Linear Network for Efficient Point Cloud Representation Learning 38

LinNet: Linear Network for Efficient Point Cloud Representat...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Deng, Hao Jing, Kunlei Cheng, Shengmei Liu, Cheng Ru, Jiawei Bo, Jiang Wang, Lin State-Province Joint Engineering and Research Center of Advanced Networking and Intelligent Information Services School of Information Science and Technology Northwest University China Shaanxi Key Laboratory of Higher Education Institution of Generative Artificial Intelligence and Mixed Reality China School of Software Engineering Xi'an Jiaotong University China Department of Computing The Hong Kong Polytechnic University Hong Kong

Point-based methods have made significant progress, but improving their scalability in large-scale 3D scenes is still a challenging problem. In this paper, we delve into the point-based method and develop a simpler, faster, stronger variant model, dubbed as LinNet. In particular, we first propose the disassembled set abstraction (DSA) module, which is more effective than the previous version of set abstraction. It achieves more efficient local aggregation by leveraging spatial anisotropy and channel anisotropy separately. Additionally, by mapping 3D point clouds onto 1D space-filling curves, we enable parallelization of downsampling and neighborhood queries on GPUs with linear complexity. LinNet, as a purely point-based method, outperforms most previous methods in both indoor and outdoor scenes without any extra attention, and sparse convolution but merely relying on a simple MLP. It achieves the mIoU of 73.7%, 81.4%, and 69.1% on the S3DIS Area5, NuScenes, and SemanticKITTI validation benchmarks, respectively, while speeding up almost 10x times over PointNeXt. Our work further reveals both the efficacy and efficiency potential of the vanilla point-based models in large-scale representation learning. Our code will be available at https://***/DengH293/LinNet. © 2024 Neural information processing systems foundation. All rights reserved.

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：