检索结果-内蒙古大学图书馆

Yoga with Deep Learning: Linking Mind and Machine

SN computer Science 2024年第4期5卷 427页

作者： Sakshi Saini, Sandeep Department of Electronics and Communication Engineering The LNM Institute of Information Technology Rajasthan Jaipur 302031 India

Health and fitness play a crucial role in every aspect of an individual’s life. In an era where well-being is an absolute target, Yoga is one of the most straightforward ways to remain healthy and achieve mental focus, breath control and body balance without undergoing useless expenditures. The motive of this study is to combine the knowledge of Yoga with the continuously developing power of deep learning. In this study, we observe yoga pose estimation along with breath control and focus instructions for 10 different poses with the help of deep learning and Mediapipe. The proposed work predicts pose and instructions through model matching with landmark extraction done by obtaining keypoints on the pose by initializing the Mediapipe pose model. Here, a hybrid model is created using ANN with existing state-of-the-art models to achieve the pose estimation. The maximum accuracy achieved during the model implementation was around 93.43%. Later, when the model was deployed on Raspberry Pi-4 hardware, the maximum accuracy achieved was around 90.9%. The user also gets guidance on breath and focus control during a particular pose. Integration with deep learning and data science is seen to have created a whole new personalized Yoga experience with on-demand posture monitoring, customized feedback, and global access while creating future scopes for risk analysis and injury prevention. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Data-driven precision Holistic analysis Pose perfection Smartyoga

来源：评论

学校读者我要写书评

暂无评论

Detecting Android Botnet Applications Using Convolution Neural Network

引用

computers, Materials & Continua 2023年第11期77卷 2123-2135页

作者： Mamona Arshad Ahmad Karim Salman Naseer Shafiq Ahmad Mejdal Alqahtani Akber Abid Gardezi Muhammad Shafiq Jin-Ghoo Choi Department of Information Technology Bahauddin Zakariya UniversityMultan60000Pakistan Department of Information Technology University of the Punjab Gujranwala CampusGujranwala52250Pakistan Industrial Engineering Department College of EngineeringKing Saud UniversityP.O.Box 800Riyadh11421Saudi Arabia Department of Computer Science COMSATS University IslamabadIslamabad45550Pakistan Department of Information and Communication Engineering Yeungnam UniversityGyeongsan38541Korea

The exponential growth in the development of smartphones and handheld devices is permeated due to everyday activities i.e.,games applications,entertainment,online banking,social network sites,etc.,and also allow the end users to perform a variety of *** of activities,mobile devices attract cybercriminals to initiate an attack over a diverse range of malicious activities such as theft of unauthorized information,phishing,spamming,Distributed Denial of Services(DDoS),and malware *** applications are a type of harmful attack that can be used to launch malicious activities and has become a significant threat in the research area.A botnet is a collection of infected devices that are managed by a botmaster and communicate with each other via a command server in order to carry out malicious *** the rise in malicious attacks,detecting botnet applications has become more ***,it is essential to investigate mobile botnet attacks to uncover the security issues in severe financial and ethical damages caused by a massive coordinated command *** state of the art,various solutions were provided for the detection of botnet applications,but in general,the researchers suffer various techniques of machine learning-based methods with static features which are usually ineffective when obfuscation techniques are used for the detection of botnet *** this paper,we propose an approach by exploring the concept of a deep learning-based method and present a well-defined Convolutional Neural Network(CNN)*** the visualization approach,we obtain the colored images through byte code files of applications and perform an *** analysis of the results of an experiment,we differentiate the performance of the model from other existing research ***,our method outperforms with 94.34%accuracy,92.9%of precision,and 92%of recall.

关键词： CNN botnet applications machine learning image processing

来源：评论

学校读者我要写书评

暂无评论

Improved clustering techniques for paediatric cerebral palsy gait assessment during rehabilitation

引用

International Journal of information technology (Singapore) 2024年 1-18页

作者： Singhal, Prateek Yadav, Rakesh Kumar Department of Computer Science and Engineering Maharishi University of Information Technology Lucknow India

The gait abnormality may be the cause of various diseases like foot drop, lower back trembling, and osteoarthritis in the human body. The causes may affect body performance. The problem may be solved if we notice it between the ages of 2 and 20. Today's medical research struggles to identify normality and abnormality in children at a young age. The gait abnormalities depend on a complex neurological condition called cerebral palsy. The article proposes an improved fuzzy C-mean-PSO technique and also defines selection criteria for gait patterns, such as optimal number identification gait profiles, mean square error, silhouette coefficient, and Dunn index. The researcher used 156 patients’ data from the available O’Malley gait dataset for experimental purposes. We partitioned 156 patients into 5 different combinations. In the first two combinations, we applied conventional methods, and the next three employed proposed methods. Finally, we found the 91.6% CPI (Cluster Purity Index), that is greater than existing techniques. In the future, we can perform the proposed methods on various datasets. The findings indicate that employing clustering-based gait profiles improved fuzzy C-mean-PSO optimised using these methods can aid in measuring clinical rehabilitation for children with cerebral palsy. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Gait analysis Gauss Cuckoo search IPSOFCM PSO Rehabilitation

来源：评论

学校读者我要写书评

暂无评论

A robust visual information hiding framework based on HVS pixel adaptive alpha blending (HPAAB) technique

引用

Multimedia Tools and Applications 2025年第14期84卷 13959-13982页

作者： Panda, Bishwabara Nayak, Manas Ranjan Mallick, Pradeep Kumar Basu, Abhishek School of Computer Engineering KIIT Deemed to be University Bhubaneswar India Department of ECE RCC Institute of Information Technology Kolkata India

The popularity of the Internet and digital consumer gadgets has fundamentally changed our society and daily lives by making digital data collection, transmission, and storage exceedingly easy and convenient. However, protecting these data and preventing unauthorized changes is an important task. This challenge has arisen in several domains, including copyright protection, content authentication, information concealment, and protected communications. Several academics have developed digital watermarking algorithms to solve this issue, aiming to implant hidden data (a watermark) in digital material to affix a mark on or seal the digital data content. The proposed approach builds a spatial domain image watermarking approach using entropy, a spectral residual pixel-based saliency map, and alpha blending. This method states that the value of entropy improves the concealing capacity. To increase imperceptibility, a spectral residual-based saliency map is used to discover less visible portions of the input images and progressively incorporate more information based on entropy data. Any modifications made other than those detectable regions will be less noticeable to viewers since they result from saliency, which decides which elements of an image are the most visible from a visual perspective. Lastly, utilizing the quality criteria, the mechanism's capability is analyzed for numerous existing frameworks. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Federated Multitask Learning for Complaint Identification Using Graph Attention Network

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第3期5卷 1277-1286页

作者： Singh, Apoorva Chandrasekar, Siddarth Sen, Tanmay Saha, Sriparna Department of Computer Science and Engineering Indian Institute of Technology Patna Patna801106 India Department of Electronics and Communication Engineering Iiitdm Kancheepuram600127 India Ericsson Kolkata700135 India

Prior study on automatically identifying complaints on social media has relied on extensive feature engineering in centralized settings, with no consideration for the decentralized, nonidentically independently distributed (Non-IID), and privacyconscious aspect of complaints, which can hinder data collection, distribution, and learning. In this work, we propose a graph attention network (GAT)-based multitask framework that intends to learn two closely related tasks, complaint detection (primary task) and sentiment classification (auxiliary task), simultaneously in federated learning scenarios. We propose the Federated Combination (FedComb) algorithm, a two-sided adaptive optimization technique that simultaneously optimizes global and local models. The proposed methodology outperforms several baselines for the intended task of recognizing complaints in decentralized settings, according to quantitative and qualitative studies on two benchmark datasets. Impact Statement-Automatic complaint identification is crucial to organizations as they provide insights to meet the customers' requirements, including handling and addressing the complaints. Unlike standard technologies developed using data stored in the cloud, a federated learning model allows businesses to learn complaint detection models without sharing their training data spread on their local databases with third-party cloud services. In this work, we propose a GAT-based sentiment-aided complaint identification in federated learning settings. The proposed FedComb algorithm integrates local and global model optimization, making it efficient compared to existing federated algorithms. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Red deer algorithm to detect the secret key of the monoalphabetic cryptosystem

引用

Soft Computing 2024年第17-18期28卷 10569-10582页

作者： Jain, Ashish Bansal, Sulabh Das, Nripendra Narayan Gupta, Shyam Sunder Department of Information Technology School of Information Security and Data Science Manipal University Jaipur Jaipur303007 India Department of Computer Science and Engineering Amity School of Engineering and Technology Amity University Madhya Pradesh Gwalior474005 India

Encryption of a plaintext involves a secret key. The secret key of classical cryptosystems can be successfully determined by utilizing metaheuristic techniques. Monoalphabetic cryptosystem is one of the famous classical cryptosystems. In this paper, we determine the secret key of the monoalphabetic cryptosystem using a recently proposed metaheuristic technique, namely, red deer algorithm. The existing red deer algorithm framework has been tailored to solve the above considered problem. Performance of the developed red deer algorithm is compared with the following metaheuristic techniques: tabu search, genetic algorithm, and cuckoo search using three criteria, namely, effectiveness, efficiency, and accuracy. The results obtained show that the proposed red deer algorithm can compete with all the above three algorithms with respect to all the criteria. This signifies the importance of the proposed red deer algorithm is that it can be utilized to solve the similar problems effectively, efficiently, and with more accuracy. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Tabu search

来源：评论

学校读者我要写书评

暂无评论

The use of multi-task learning in cybersecurity applications: a systematic literature review

引用

Neural Computing and Applications 2024年第35期36卷 22053-22079页

作者： Ibrahim, Shimaa Catal, Cagatay Kacem, Thabet Department of Computer Science and Engineering Qatar University 2713 Doha Qatar Department of Computer Science and Information Technology University of the District of Columbia WashingtonDC20008 United States

Cybersecurity is crucial in today’s interconnected world, as digital technologies are increasingly used in various sectors. The risk of cyberattacks targeting financial, military, and political systems has increased due to the wide use of technology. Cybersecurity has become vital in information technology, with data protection being a major priority. Despite government and corporate efforts, cybersecurity remains a significant concern. The application of multi-task learning (MTL) in cybersecurity is a promising solution, allowing security systems to simultaneously address various tasks and adapt in real-time to emerging threats. While researchers have applied MTL techniques for different purposes, a systematic overview of the state-of-the-art on the role of MTL in cybersecurity is lacking. Therefore, we carried out a systematic literature review (SLR) on the use of MTL in cybersecurity applications and explored its potential applications and effectiveness in developing security measures. Five critical applications, such as network intrusion detection and malware detection, were identified, and several tasks used in these applications were observed. Most of the studies used supervised learning algorithms, and there were very limited studies that focused on other types of machine learning. This paper outlines various models utilized in the context of multi-task learning within cybersecurity and presents several challenges in this field. © The Author(s) 2024.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Artificial neural networks and noncontact microwave NDT for evaluation of polypropylene fiber concrete

引用

Asian Journal of Civil engineering 2025年第1期26卷 273-292页

作者： Nimer, Hamsa Ismail, Rabah Al-Mattarneh, Hashem Khodier, Mohanad Jaradat, Yaser Rawashdeh, Adnan Rawashdeh, Mohammad Civil Engineering Department Yarmouk University Irbid Jordan Civil Engineering Department Jadara University Irbid Jordan Computer Science & amp Information Technology Yarmouk University Irbid Jordan Communication Engineering Department Yarmouk University Irbid Jordan

Polypropylene fibers are extensively incorporated into reinforced concrete to enhance performance aspects such as crack resistance, flexural and tensile strength, fire resistance, and overall durability. However, current methods for evaluating factors like fiber inclusion percentage, distribution, and orientation within the concrete matrix are often limited, destructive, and time-consuming. This study explores developing and applying a non-contact microwave non-destructive method (NMNDT) for assessing polypropylene fiber-reinforced concrete. The NMNDT system measures the reflection and transmission characteristics of microwave signals through the concrete, correlating these properties with the physical and mechanical characteristics of the material. Key findings indicate a strong correlation between microwaves’ reflection and transmission properties, the quality of fiber distribution, and the fiber content within the concrete. For instance, the study found that the reflection coefficient (S₁₁) increased from 0.36 to 0.39, with fiber content varying from 0.5 to 1.5 kg/m³, while the transmission coefficient (S₂₁) decreased from 0.46 to 0.38 over the same range. The compressive strength of fiber-reinforced concrete was predicted with a correlation coefficient (R) of 0.98 using artificial neural networks (ANN). These microwave properties can predict mechanical properties such as tensile and compressive strength, with the ANN model achieving more than 97% accuracy. The study highlights the innovative potential of microwave technology as a non-invasive evaluation technique for polypropylene fiber-reinforced concrete, offering a promising avenue for rapid and non-destructive quality control and performance assessment. The integration of ANN further enhances the predictability of the strength properties of polypropylene fiber-reinforced concrete, significantly contributing to advancements in the field of fiber-reinforced concrete evaluation and quality

关键词： Artificial neural network (ANN) Concrete technology Mechanical properties Nondestructive Polypropylene fibers concrete

来源：评论

学校读者我要写书评

暂无评论

Intelligent Decision-Making in Cybersecurity Using Machine Learning 12th

Intelligent Decision-Making in Cybersecurity Using Machine L...

引用

12th International Conference on Frontiers of Intelligent Computing: Theory and Applications, FICTA 2024

作者： Sakhare, Nitin N. Maruthi Shankar, B. Kalnawat, Aarti Sharma, Abha Rege, P.R. Wagh, Kapil Adhar Department of Computer Engineering BRACT’s Vishwakarma Institute of Information Technology Maharashtra Pune India Department of Electronics and Communication Engineering Sri Krishna College of Engineering and Technology Tamil Nadu Coimbatore India Pune India Electronics and Communication Engineering Arya College of Engineering Rajasthan Jaipur India Department of Computer Engineering Vishwakarma Institute of Information Technology Maharashtra Pune India Nutan Maharashtra Institute of Engineering and Technology Maharashtra Pune India

ISBN: (纸本)9789819601462

In the constantly changing field of cybersecurity, the need for advanced decision-making tools is more crucial than ever. This study explores machine learning in order to introduce an innovative method for strengthening cybersecurity protocols. The methodology involves combining Random Forests (RF) and Support Vector Machines (SVM) using the AdaBoost algorithm in an ensemble framework. The ensemble model is intricately crafted to address the complexities of intrusion detection, utilizing the combined capabilities of Random Forest’s data handling and Support Vector Machine’s pattern discrimination. AdaBoost enhances the ensemble’s predictive abilities by iteratively adjusting weights to focus more on misclassified instances. This adaptive learning process enables the model to constantly develop and adjust to new cyber threats. Validation against benchmark datasets demonstrates an impressive accuracy rate of 97.78%, highlighting the strength of the ensemble methodology. The True Positive Rate (TPR) of 98.33% demonstrates the ensemble’s effectiveness in accurately detecting and responding to potential cyber threats. The results demonstrate the superior performance of the proposed ensemble method and highlight its ability to achieve a balance between accuracy and adaptability. This research significantly advances intelligent decision-making in cybersecurity by introducing a potent ensemble approach that smoothly integrates various machine learning algorithms. The method’s proven accuracy and sensitivity make it a powerful tool in combating the increasing complexity of cyber threats. The combination of RF, SVM, and AdaBoost sets a standard for future research in strengthening digital defenses and ensuring the resilience of critical information systems. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Side-Channel Attack Detection for Mobile Devices Security in 5G Networks

引用

清华大学学报自然科学版（英文版） 2025年第3期30卷 1012-1026页

作者： Amjed A.Ahmed Mohammad Kamrul Hasan Ali Alqahtani Shayla Islam Bishwajeet Pandey Leila Rzayeva Huda Saleh Abbas Azana Hafizah Mohd Aman Nayef Alqahtani Center for Cyber Security Faculty of Information Science and TechnologyUniversiti Kebangsaan MalaysiaBangi 43600Malaysia Imam Alkadhim University College Department of Computer Techniques EngineeringBaghdad 10066Iraq Center for Cyber Security Faculty of Information Science and TechnologyUniversiti Kebangsaan MalaysiaBangi 43600Malaysia Department of Networks and Communications Engineering College of Computer Science and Information SystemsNajran UniversityNajran 61441Saudi Arabia Institute of Computer Science and Digital Innovation UCSI UniversityKuala Lumpur 56000Malaysia Department of Intelligent Systems and Cyber Security Astana IT UniversityAstana 20000Kazakstan Department of Computer Science College of Computer Science and EngineeringTaibah UniversityMadinah 42353Saudi Arabia Department of Electrical Engineering College of EngineeringKing Faisal UniversityAl-Hofuf 31982Saudi Arabia

Mobile devices within Fifth Generation(5G)networks,typically equipped with Android systems,serve as a bridge to connect digital gadgets such as global positioning system,mobile devices,and wireless routers,which are vital in facilitating end-user communication ***,the security of Android systems has been challenged by the sensitive data involved,leading to vulnerabilities in mobile devices used in 5G *** vulnerabilities expose mobile devices to cyber-attacks,primarily resulting from security ***-permission apps in Android can exploit these channels to access sensitive information,including user identities,login credentials,and geolocation *** such attack leverages"zero-permission"sensors like accelerometers and gyroscopes,enabling attackers to gather information about the smartphone's *** underscores the importance of fortifying mobile devices against potential future *** research focuses on a new recurrent neural network prediction model,which has proved highly effective for detecting side-channel attacks in mobile devices in 5G *** conducted state-of-the-art comparative studies to validate our experimental *** results demonstrate that even a small amount of training data can accurately recognize 37.5％of previously unseen user-typed ***,our tap detection mechanism achieves a 92％accuracy rate,a crucial factor for text *** findings have significant practical implications,as they reinforce mobile device security in 5G networks,enhancing user privacy,and data protection.

关键词： Fifth Generation(5G)networks smartphone information leakage Side-Channel Attack(SCA) deep learning

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：