检索结果-内蒙古大学图书馆

Unlocking the potential of RNN and CNN models for accurate rehabilitation exercise classification on multi-datasets

Multimedia Tools and Applications 2025年第3期84卷 1261-1301页

作者： Zaher, Moamen Ghoneim, Amr S. Abdelhamid, Laila Atia, Ayman Software Engineering Program Faculty of Computers & Artificial Intelligence—Helwan University Cairo Ain Helwan11795 Egypt Computer Science Department Faculty of Computers & Artificial Intelligence—Helwan University Cairo Ain Helwan11795 Egypt Information System Department Faculty of Computers & Artificial Intelligence—Helwan University Cairo Ain Helwan11795 Egypt Cairo Ain Helwan11795 Egypt Giza October12451 Egypt

Physical rehabilitation is crucial in healthcare, facilitating recovery from injuries or illnesses and improving overall health. However, a notable global challenge stems from the shortage of professional physiotherapists, particularly acute in some developing countries, where the ratio can be as low as one physiotherapist per 100,000 individuals. To address these challenges and elevate patient care, the field of physical rehabilitation is progressively integrating computer Vision and Human Activity Recognition (HAR) techniques. Numerous research efforts aim to explore methodologies that assist in rehabilitation exercises and evaluate patient movements, which is crucial as incorrect exercises can potentially worsen conditions. This study investigates applying various deep-learning models for classifying exercises using the benchmark KIMORE and UI-PRMD datasets. Employing Bi-LSTM, LSTM, CNN, and CNN-LSTM, alongside a Random Search for architectural design and Hyper-parameter tuning, our investigation reveals the (CNN) model as the top performer. After applying cross-validation, the technique achieves remarkable mean testing accuracy rates of 93.08% on the KIMORE dataset and 99.7% on the UI-PRMD dataset. This marks a slight improvement of 0.75% and 0.1%, respectively, compared to previous techniques. In addition, expanding beyond exercise classification, this study explores the KIMORE dataset’s utility for disease identification, where the (CNN) model consistently demonstrates an outstanding accuracy of 89.87%, indicating its promising role in both exercises and disease identification within the context of physical rehabilitation. © The Author(s) 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Tutorial on Cybersecurity in Quantum Computing Paradigm

TechRxiv

引用

TechRxiv 2023年

作者： Ghosh, Uttam Das, Debashis Chatterjee, Pushpita The Department of Computer Science and Data Science Meharry Medical College TN United States The Department of Computer Science and Engineering University of Kalyani Kalyani India The Department of Electrical Engineering and Computer Science and Engineering Howard University WashingtonDC United States Howard University United States

Quantum computing has the potential to revolutionize computing by solving problems that classical computers cannot solve efficiently. However, it also poses a significant threat to cybersecurity. Quantum computers can break many of the encryption methods that are currently used to protect sensitive information. This includes breaking public-key encryption, decrypting symmetric keys, forging digital signatures, and stealing private keys. To mitigate this threat, efforts are underway to develop new encryption methods that are resistant to quantum attacks. Cybersecurity is a constantly evolving field, and as quantum computing continues to develop, new strategies and tools will be needed to defend against cyber threats. By staying informed and proactive, individuals and organizations can help ensure the security of their digital assets in the face of this new paradigm. In this paper, we will explain what quantum computing is and look at how it might be used in cybersecurity. Quantum computing could make cybersecurity less safe, so we talk about cybersecurity threats to learn more about them. We also introduce several quantum attacks and their countermeasures. Finally, we provide quantum approaches to cybersecurity concerns. © 2023, CC BY.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Automated Waste Classification using Convolutional Neural Network

Automated Waste Classification using Convolutional Neural Ne...

引用

International Conference on Software Technology and Engineering (ICSTE)

作者： Rajermani Thinakaran J. Somasekar Vikram Neerugatti P. Guru Saran Faculty of Data Science and Information Technology INTI International University Negeri Sembilan Malaysia Department of Computer Science and Engineering Jain (Deemed-to-be University) Banglore Karnataka India

ISBN: (数字)9798350378955

ISBN: (纸本)9798350378962

Efficient waste management relies on precise waste classification, which facilitates recycling, composting, and appropriate disposal. Conventional waste classification methods often involve manual sorting or simple rule-based systems, which are labor intensive and prone to errors. This study investigates the application of Convolutional Neural Networks (CNNs) for automated waste classification using image data. CNNs have shown significant success in various image classification tasks due to their ability to learn hierarchical features directly from pixel values. The methodology outlined covers data collection, preprocessing, model architecture design, and training procedures for the CNN model. Experimental results demonstrate the effectiveness of the CNN approach in accurately categorizing various waste types. Additionally, we discuss the practical implications of CNN-based waste classification systems for real-world waste management applications. By leveraging CNNs, waste management processes can be optimized, leading to better resource utilization and environmental sustainability. The authors also highlight potential avenues for future research, including exploring advanced CNN architectures and integrating emerging technologies like Internet of Things (IoT) sensors for improved waste management solutions. Overall, this study emphasizes the potential of CNNs to transform waste classification practices and enhance the efficiency of waste management systems.

关键词： Waste management Training computer architecture Transforms data models Software Sensors Convolutional neural networks Internet of Things Sorting

来源：评论

学校读者我要写书评

暂无评论

Adaptive and frugal BDDC coarse spaces for virtual element discretizations of a Stokes problem with heterogeneous viscosity

arXiv

引用

arXiv 2024年

作者： Bevilacqua, Tommaso Klawonn, Axel Lanser, Martin Center for Data and Simulation Science University of Cologne Germany Department of Mathematics and Computer Science Division of Mathematics University of Cologne Weyertal 86-90 Cologne50931 Germany

The virtual element method (VEM) is a family of numerical methods to discretize partial differential equations on general polygonal or polyhedral computational grids. However, the resulting linear systems are often ill-conditioned and robust preconditioning techniques are necessary for an iterative solution. Here, a balancing domain decomposition by constraints (BDDC) preconditioner is considered. Techniques to enrich the coarse space of BDDC applied to a Stokes problem with heterogeneous viscosity are proposed. In this framework a comparison between two adaptive techniques and a computationally cheaper heuristic approach is carried out. Numerical results computed on a physically realistic model show that the latter approach in combination with the deluxe scaling is a promising *** Codes 65F08, 65N30, 65N55 Copyright © 2024, The Authors. All rights reserved.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Battle Royale Optimization-Based Resource Scheduling Scheme for Cloud Computing Environment

引用

computer Systems science & Engineering 2023年第9期46卷 3925-3938页

作者： Lenin Babu Russeliah R.Adaline Suji D.Bright Anand Data Scientist Conversight.aiIndianaUSA Department of Computer Science and Engineering KIT-KalaignarKarunanidhi Institute of TechnologyCoimbatore641402India Department of Computer Science and Engineering Narayana Engineering CollegeGudur524101Andhra PradeshIndia

Cloud computing(CC)is developing as a powerful and flexible computational structure for providing ubiquitous service to *** receives interrelated software and hardware resources in an integrated manner distinct from the classical computational *** variation of software and hardware resources were combined and composed as a resource *** software no more resided in the single hardware environment,it can be executed on the schedule of resource pools to optimize resource *** energy consumption in CC environments is the question that allows utilizing several energy conservation approaches for effective resource *** study introduces a Battle Royale Optimization-based Resource Scheduling Scheme for Cloud Computing Environment(BRORSS-CCE)*** presented BRORSS-CCE technique majorly schedules the available resources for maximum utilization and effectual *** the BRORSS-CCE technique,the BRO is a population-based algorithm where all the individuals are denoted by a soldier/player who likes to go towards the optimal place and ultimate *** BRORSS-CCE technique can be employed to balance the load,distribute resources based on demand and assure services to all *** experimental validation of the BRORSS-CCE technique is tested under distinct *** experimental outcomes indicated the enhancements of the BRORSS-CCE technique over other models.

关键词： Cloud computing resource scheduling battle royale optimization makespan resource utilization

来源：评论

学校读者我要写书评

暂无评论

A Synchronous Parallel Method with Parameters Communication Prediction for Distributed Machine Learning 19th

A Synchronous Parallel Method with Parameters Communication...

引用

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Zeng, Yanguo Xue, Meiting Xu, Peiran Shi, Yukun Zeng, Kaisheng Zhang, Jilin Yue, Lupeng School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China Key Laboratory for Modeling and Simulation of Complex Systems Ministry of Education Hangzhou310018 China Data Security Governance Zhejiang Engineering Research Center Hangzhou310018 China National University of Defense Technology Changsha China School of Cyberspace HangZhou Dianzi University Hangzhou China Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9783031545306

With the development of machine learning technology in various fields, such as medical care, smart manufacturing, etc., the data has exploded. It is a challenge to train a deep learning model for different application domains with large-scale data and limited resources of a single device. The distributed machine-learning technology, which uses a parameter server and multiple clients to train a model collaboratively, is an excellent method to solve this problem. However, it needs much communication between different devices with limited communication resources. The stale synchronous parallel method is a mainstream communication method to solve this problem, but it always leads to high synchronization delay and low computing efficiency as the inappropriate delay threshold value set by the user based on experience. This paper proposes a synchronous parallel method with parameters communication prediction for distributed machine learning. It predicts the optimal timing for synchronization, which can solve the problem of long synchronization waiting time caused by the inappropriate threshold settings in the stale synchronous parallel method. Moreover, it allows fast nodes to continue local training while performing global synchronization, which can improve the resource utilization of work nodes. Experimental results show that compared with the delayed synchronous parallel method, the training time and quality, and resource usage of our method are both significantly improved. © ICST Institute for computer sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Universal Low Bit-Rate Speech Steganalysis Integrating Domain-specific and Domain-shared Knowledge

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Tian, Hui Qiu, Yiqin Li, Haizhou Zhang, Xinpeng Vasilakos, Athanasios V. National Huaqiao University College of Computer Science and Technology Xiamen361021 China Xiamen Key Laboratory of Data Security and Blockchain Technology Xiamen361021 China School of Data Science Chinese University of Hong Kong Shenzhen518172 China National University of Singapore Department of Electrical and Computer Engineering 119077 Singapore Fudan University School of Computer Science Shanghai200433 China University of Agder Center for AI Research Grimstad4879 Norway

Universal low bit-rate speech steganalysis is a cutting-edge research task addressing real-world application needs and has garnered significant attention recently. However, the existing methods are still inadequate in extracting available information from various steganographic domains and fail to deliver interpretable forensic results for specific steganographic domains containing embedded information. In view of this, we present a novel universal low bit-rate speech steganalysis approach that seamlessly combines domain-specific and domain-shared information, enabling comprehensive and effective speech steganography detection. This approach comprises two vital components: the Matching Identification Network (MIN) and the Content Alignment Network (CAN). The MIN incorporates three effective separable backbones for capturing informative domain-specific embeddings, inherently unveiling local and global dependencies. In this network, we also design a cross-domain matching module to establish correlations among steganographic domains, thereby enhancing detection performance through multi-domain collaboration and facilitating effective forensics for the embedded domains. Moreover, the CAN acquires more informative domain-shared embeddings by using a metric learning-based Siamese architecture to process pairs of naive and recompressed speech samples. Experimental results demonstrate that the presented method not only significantly surpasses the existing universal steganalysis methods, but also competes with or even surpasses dedicated steganalysis methods in certain cases. In addition, our method can provide accurate forensic results regarding the existence of hidden information within each steganographic domain without relevant supervisory information, marking a significant milestone in pursuit of speech steganalysis. The source code for this work will be publicly available on GitHub. © 2004-2012 IEEE.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Few-shot Prompting for Pairwise Ranking: An Effective Non-Parametric Retrieval Model

arXiv

引用

arXiv 2024年

作者： Sinhababu, Nilanjan Parry, Andrew Ganguly, Debasis Samanta, Debasis Mitra, Pabitra Centre for Computational and Data Sciences IIT Kharagpur India School of Computing Science University of Glasgow United Kingdom Department of Computer Science and Engineering IIT Kharagpur India

A supervised ranking model, despite its advantage of being effective, usually involves complex processing - typically multiple stages of task-specific pre-training and fine-tuning. This has motivated researchers to explore simpler pipelines leveraging large language models (LLMs) that are capable of working in a zero-shot manner. However, since zero-shot inference does not make use of a training set of pairs of queries and their relevant documents, its performance is mostly worse than that of supervised models, which are trained on such example pairs. Motivated by the existing findings that training examples generally improve zero-shot performance, in our work, we explore if this also applies to ranking models. More specifically, given a query and a pair of documents, the preference prediction task is improved by augmenting examples of preferences for similar queries from a training set. Our proposed pairwise few-shot ranker demonstrates consistent improvements over the zero-shot baseline on both in-domain (TREC DL) and out-domain (BEIR subset) retrieval benchmarks. Our method also achieves a close performance to that of a supervised model without requiring any complex training pipeline. © 2024, CC BY.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Algorithms for Deep Learning in Secure Network Environments

Evolutionary Algorithms for Deep Learning in Secure Network ...

引用

2024 IEEE International Conference on Intelligent Systems and Advanced Applications, ICISAA 2024

作者： Seva, Banothu Jain, Ratnesh Khare, Neha Choudhury, Hussain Ahmed Chakravarthi, M Ayyappa Tomer, Nitin MLR Institute of Technology Dept. of CSE Telangana Hyderabad India GGITS Dept of Computer Science & Design M.P Jabalpur India IES Institute of Technology and Management IES University Department of Computer Science & Engineering M.P Bhopal462044 India Barak Valley Engineering College Department of CSE Assam Karimganj India KKR & KSR Institute of Technology and Sciences Dept. of CSE - Data Science AP Guntur India GGITS Cyber Security & Blockchain Dept of IOT M.P. Jabalpur India

ISBN: (纸本)9798331539948

Hackers are getting better at breaking into protected networks, making network security an arms race. Today, combining EAs with DL to combat these risks is cuttingedge. This research illustrates how EAs and DL may enhance network security in a shifting threat environment. This blend outperforms traditional techniques in many critical security measures, according to our study. Network safety in deep learning involves improving model architecture, hyperparameters, and adaptive strategies. These variables affect how successfully a model detects unexpected activity while limiting false positives. We propose rethinking how these settings are fine-tuned and modified to create a larger digital asset security strategy. This technique integrates EAs with DL. Evolutionary algorithms, based on natural selection and genetic variety, solve large problem areas well. With DL, these approaches speed up the construction of cutting-edge safety tools. These approaches allow us to find model designs, modify hyperparameters, and update trained models, which we like. Our experiment illuminated the topic. The recommended method routinely outperforms established methods in terms of discovery rate. In network security, the detection rate indicates how successfully a system can identify and react to malicious conduct. Our approach can protect digital products due to their greater detection rate. Security specialists celebrate any modest finding in their never-ending battle against nefarious actors. Network security professionals must monitor false positives to avoid too many false alarms. New dangers may be stopped before they do harm. Evolutionary algorithms and deep learning in secure networks give new perspectives. Empirical evidence reveals that our method is more efficient, versatile, and finds things better. Because digital threats change, our strategy strengthens our defenses to protect critical networks and digital assets. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Survey of Online Exam Proctoring Model to Detect Cheating Behavior based on Face Recognition

Survey of Online Exam Proctoring Model to Detect Cheating Be...

引用

International Conference on Systems and Informatics (ICSAI)

作者： Sucianna Ghadati Rabiha Iman Herwidiana Kartowisastro Reina Setiawan Widodo Budiharto Computer Science Department BINUS Graduate Program – Computer Science. Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program – Computer Science. Computer Engineering Department Faculty of Engineering Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program – Computer Science. Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9781665474498

Exams are an important component of any educational program, including online education. In any test, there is a possibility of cheating, so its detection and prevention is important. This study aims to conduct an in-depth study of the online exam monitoring model approach based on facial recognition used to detect cheating. Based on the inclusion and exclusion criteria designed, 13 selected studies were obtained. From these studies, we conducted further analysis regarding the Face Detection Method, Face Recognition Method, Initial Feature, Behavior Analysis and Evaluation Metrics used in each study so as to provide answers to research questions. the most frequently used Face detection method was Viola-Jones with a presentation of 20%, then CNN and MTCNN with a total presentation of 21%. The most widely used face recognition method in selected studies is CNN and metrics Accuracy is one of the most frequently used evaluations with a percentage of 33%. While the features that are usually used to detect cheating during online exams include facial motion and head pose which occupies the first position. The second is eye movement, then multiple faces gaze estimation and facial expression is in third place. Other features that also play a role in analyzing cheating behavior are mouth detection, facial vector, landmark location, gesture and posture.

关键词： Measurement Analytical models Face recognition Mouth Estimation Feature extraction Behavioral sciences

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：