检索结果-内蒙古大学图书馆

Real-Time Challenges and Opportunities for an Effective Resource Management in Multi-cloud Environment

SN computer science 2024年第2期5卷 1-8页

作者： Basha, H. Anwar Anilkumar, B.H. Swetha, G. Reddy, Raghavendra Manoli, Sunil Department of Computer Science and Engineering Rajalakshmi Institute of Technology Tamilnadu Chennai India Department of Computer Science and Engineering Vidyavardhaka College of Engineering Mysuru India R R Institute of Technology Bengaluru India School of Computer Science and Engineering REVA University Bengaluru India

As the usage of multi-cloud setups grows, resource management will become a major concern. Because of the dynamic nature of these environments, as well as fluctuating workloads and service-level targets, an effective algorithm for real-time resource allocation and optimisation is required. The Adaptive Multi-Cloud Resource Management Algorithm (AMCRMA) is proposed in this study to handle the obstacles and capitalise on the benefits of resource management in a multi-cloud context. To ensure optimal resource utilisation, cost effectiveness, and service performance, AMCRMA incorporates real-time monitoring, workload prediction, and intelligent resource allocation. Experiment results show that AMCRMA is successful in adapting to changing situations and managing resources in real time, resulting in enhanced resource utilisation and overall performance in multi-cloud systems. © 2024, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： AMCRMA Cloud federation Cloud orchestration Data management Intelligent resource allocation Resource management

来源：评论

学校读者我要写书评

暂无评论

CAAM- CNN With Autoencoder Attention Mechanism for Recommendation System to Improve Trust in E-commerce Industry 2

CAAM- CNN With Autoencoder Attention Mechanism for Recommend...

引用

2nd IEEE International Conference for Women in Innovation, technology and Entrepreneurship, ICWITE 2024

作者： Sethi, Vikas Kumar, Rajneesh Mehla, Stuti Department of Computer Science and Engineering Ambala Mullana India Panipat Institute of Engineering and Technology Department of Computer Science and Engineering Panipat India

ISBN: (纸本)9798350383287

COVID-19 crisis expedited the spread of e-commerce, moving beyond luxury goods and services and towards new businesses, product categories and basic necessities that are important to many people. Customers can have access to a wide range of products from the comfort and security of their homes but still have trusting issues while purchasing online. Online feedback either comments or ratings given by customers, has the power to affect how consumers make purchasing decisions. This meteoric expansion of digitized information and number of users over internet brought the use of recommender systems as a significant solution by offering more proactive and individualized information services and enable users to quickly narrow their choices and make wise ***, the majority of existing recommendation models have poor accuracy issues as a result of data scarcity and cold start issues because recommender systems only have a limited amount of explicit data and this also lead to trust issue where users are fear of being taken advantage due to misleading information on the e-commerce websites. To solve this problem and provide quality recommendations, a new trust-based approach CNN with Autoencoder Attention Mechanism (CAAM) is proposed. CAAM uses static and dynamic trust combined with the user-item preferences and pass through the auto-encoder to reduce noise and make encoded features visible. After that convolution is used to combine encoded features with user and item features in latent space to provide nonlinear mapping and increase the reliability of features and to improve the recommendations which ultimately lead to improve the trust of people over *** Epinions dataset is used to evaluate the concept in a number of measures. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Advancing Smart Sensor Networks and Carbon-Based Biosensors Through Artificial Intelligence: A Deep Learning Approach to Optoelectronic Device Innovation

引用

IEEE Access 2025年 13卷 86083-86109页

作者： Luo, Keliang Universiti Putra Malaysia Faculty of Computer Science and Information Technology Software Engineering Department Kuala Lumpur43400 Malaysia

This research proposes a novel artificial decision-marking framework suitable for modern smart sensor networks and carbon-based biosensor systems which deals with uncertainty and the peculiarity of the data. To achieve the goals, the approach relies on the optoelectronic properties of carbon nanomaterials and already combines AI and deep learning. This raises the level of sensing, real-time data fusion, and adaptive decision-making within the environment to unprecedented levels. To enhance sensor evaluation in sensor manufacturing, we take a step further and implement Dombi Interval Valued Intuitionistic Fuzzy Sets (D-IVIFs) and work with Dombi Interval Valued Intuitionistic Fuzzy Dombi Bonferroni Mean (D-IVIFDBM) for hierarchical decision-making. Moreover, two Multi-Attribute Group Decision Making (MAGDM) methods IVIFWDBM and IVIFWDGBM are developed for expert evaluation aggregation in selection tasks of different criteria to enhance selection accuracy. These experiments did demonstrate improvements in decision accuracy as well as better overall performance than conventional models of comparison. The numerical experiments showed that these methods are more effective than traditional MAGDM models. Introducing such an advanced decision framework in deep learning systems enables improved adaptability, security, and resilience in next-generation sensor networks and biosensor devices. The new paradigm enables real-time signal interpretation and adaptive learning and provides effective solutions in harsh environments where severe fluctuations are common. This study assists in addressing the discrepancy between conceptual decision models and actual physical achievements in smart sensing, which will foster the development of more sophisticated and efficient optoelectronic devices. © 2013 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Design of a Multifactor Unidentified Remote End User Authentication Mechanism for IoT Network

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第10期49卷 191-204页

作者： Sharma, Neha Dhiman, Pankaj Department of Computer Science and Engineering Jaypee University of Information Technology Waknaghat H. P. Solan India

The rapid proliferation of Internet of Things (IoT) devices, coupled with the rollout of advanced 5G networks, has generated significant concerns regarding security breaches. These concerns stem from the expanded attack surfaces that come with improved connectivity, making IoT systems more vulnerable to malicious threats. A crucial strategy to counter these security challenges is the implementation of robust user authentication methods. Despite numerous proposals for multi-factor authentication mechanisms, many of these systems exhibit weaknesses, particularly in their susceptibility to user impersonation attacks and the risks posed by stolen mobile devices. Furthermore, several schemes fail to incorporate essential features such as session key agreements or backup solutions for instances of lost or stolen devices and compromised private keys. To address urgent security challenges in IoT environments, we developed a three-factor user authentication system tailored for low-cost IoT devices. This system tackles critical vulnerabilities while maintaining low computing and communication costs, enhancing security without compromising usability and efficiency. © 2025 Slovene Society Informatika. All rights reserved.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Path Selection Optimization Algorithms for Mobile Agent Based on Push-All-Data Strategy

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2025年第10期19卷 112-128页

作者： Alzyoud, Faisal Tarawneh, Monther Al-Shrouf, Faiz Almaghthawi, Ahmed Alrehaili, Meaad Kanaker, Hasan Department of Computer Science Isra University Amman Jordan Department of Information Technology College of Information Technology and Communications Tafila Technical University Tafila Jordan Department of Software Engineering Faculty of Information Technology Isra University Amman Jordan Department of Computer Science College of Science & Art at Mahayil King Khalid University Abha62529 Saudi Arabia Department of Computer Sciences and Artificial Intelligence Collège of Computer Science and Engineering University of Jeddah Jeddah Saudi Arabia Department of Information Security Faculty of Information Technology Petra University Amman Jordan

With the advent of 5G and 6G technologies and the growing ubiquity of the Internet, the Mobile Agent (MA) paradigm is increasingly seen as a promising alternative to the conventional client-server model. MAs, which are software entities capable of moving and processing data across different systems, offer potential efficiencies in data management. However, their operation in dynamic and mobile environments can lead to challenges, such as incomplete or delayed tasks. This study addresses these issues by focusing on reducing the relocation time of MAs. A numerical procedure and a streamlining strategy were developed to expedite the transfer of an agent from the source to the target hub. Utilizing the itinerary design pattern and the Ant Colony Optimization (ACO) algorithm, implemented via the Java Agent Development Framework (JADE), this study sought the most efficient path for the MA. The proposed algorithm demonstrated a significant improvement, selecting the optimal path in just 271.511 seconds. This performance represents a substantial enhancement over previous approaches using the master-slave design pattern with either the Genetic Algorithm (GA) or the Node Compression Algorithm (NCA). The implications of this improvement are far-reaching, potentially enhancing the efficiency and reliability of data management systems in a variety of applications. © 2025 by the authors of this article. Published under CC-BY.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Comprehensive insights into healthcare IoT: the role of machine learning and deep learning approaches

引用

Multimedia Tools and Applications 2025年 1-42页

作者： Kumar, Atul Dewang, Rupesh Kumar Computer Science and Engineering Department Motilal Nehru National Institute of Technology Allahabad Uttar Pradesh Prayagraj211004 India

Conventional healthcare systems have long struggled to address the varied needs of large patient populations, often leading to inefficiencies and less-than-optimal outcomes. Yet, the advent of machine learning (ML) and deep learning (DL) models has heralded a transformative shift toward value-based care, enabling healthcare providers to offer personalized and remarkably effective treatments. Contemporary medical equipment and devices are equipped with internal applications that gather and store extensive patient data, forming a valuable resource for ML-powered predictive *** have conducted a systematic literature review (SLR) which mainly focuses on Theoretical background, challenges, Application framework, Organization of IoT in healthcare and HIoT *** the SLR process some efficient methodologies has been used. In the SLR process we have conducted Quality metadata analysis (QMA) which provides the complete statistical analysis by considering different *** learning algorithms enable the analysis of the extensive data produced by IoT devices, uncovering patterns and irregularities that may escape human detection. Deep learning, leveraging sophisticated neural network models, enhances the accuracy of medical image interpretation, disease prognosis, and forecasting patient outcomes. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

GWO-CNN: Trust and Intelligent Recommendation system based model to improve marketing strategies on e-commerce 2

GWO-CNN: Trust and Intelligent Recommendation system based m...

引用

2nd IEEE International Conference for Women in Innovation, technology and Entrepreneurship, ICWITE 2024

作者： Sethi, Vikas Kumar, Rajneesh Mehla, Stuti Department of Computer Science and Engineering Mullana Ambala India Panipat Institute of Engineering and Technology Department of Computer Science and Engineering Panipat India

ISBN: (纸本)9798350383287

In 21st century, AI-based intelligent recommendation system uses rating predictions, which are frequently utilized and helps users swiftly filter down their options and make informed judgements from an abundance of material. Nevertheless, as recommender systems only contain a small number of explicit data and are subject to cold start and sparsity issues, the majority of existing recommendation models have poor accuracy. The majority of conventional algorithms used to make recommendations simply take into account the straight-forward connection among consumers and products, largely ignoring the interests, prospective employment factors, or other social aspects of the products being *** this study focus is on user preferences, as they are key to tailoring recommendations to individual needs. By combining trust values with user preferences, the system can recommend items that not only have a high trust value but also align with a user's individual tastes or needs. For this proposed model used feature matrix, Grey Wolf Optimizer (GWO) and Convolution Neural Network (CNN). GWO is an optimization algorithm used to find optimal weights or parameters for the recommendation system. Once the GWO has found optimal or near-optimal weights, they are integrated into the feature matrix. These weights can help prioritize or scale certain features to improve the recommendation quality. Then CNN will extract patterns and relationships from the feature matrix. Based on the processed feature matrix, the system predicts the top 'K' items to recommend to the user. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

LightSTATE: A Generalized Framework for Real-Time Human Activity Detection Using Edge-Based Video Processing and Vision Language Models

引用

IEEE Access 2025年 13卷 97609-97627页

作者： Debnath, Anik Kim, Yong-Woon Byun, Yung-Cheol Jeju National University Department of Computer Engineering Jeju-si63243 Korea Republic of Jeju National University Institute of Information Science & Technology Department of Computer Engineering Major of Electronic Engineering Jeju63243 Korea Republic of

Human activity detection plays a vital role in applications such as healthcare monitoring, smart environments, and security surveillance. However, traditional methods often rely on computationally intensive models, which are unsuitable for edge devices due to their limited resources and high latency. This research introduces a new approach named LightSTATE, a lightweight hybrid framework designed for real-time activity detection by integrating edge-based preprocessing with cloud-hosted Vision Language Models (VLMs). The system processes video streams through efficient frame extraction, edge detection and Root Mean Square Error (RMSE)-based frame filtering to identify significant motion events. These selected frames are transmitted to the cloud for semantic analysis and state recognition. The system utilizes GPT-4o as the vision-language model to generate rich, descriptive captions for human state understanding. LightSTATE was evaluated on a curated dataset of 9 real-world videos containing 634 frames, with 320 labeled frames used for testing. The framework demonstrated high accuracy in detecting predefined states, with an average precision of 0.98, an average recall of 0.98, and an average F1-score of 0.98. The experimental results confirm that the average frame processing time is approximately 0.8-0.9 seconds, ensuring suitability for real-time applications. Due to the scarcity of publicly accessible datasets, we compiled a custom dataset to effectively assess the performance of our proposed approach. The results validate the scalability and real-time capabilities of our proposed system, making it a promising solution for continuous monitoring applications. This study establishes LightSTATE as a scalable, efficient, and privacy-preserving framework for real-time human activity detection. Future work will focus on extending its applicability to dynamic and multi-person scenarios while enhancing system adaptability for diverse use cases. © 2013 IEEE.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning Techniques of Human Brain Tissue Segmentation and Tumor Localization in MRI Images 7th

Hybrid Deep Learning Techniques of Human Brain Tissue Segmen...

引用

7th International Conference on Soft Computing and Signal Processing, ICSCSP 2024

作者： Banu, Mohammed Razia Alangir Gupta, Arpita Banu, Athur Shaik Ali Gousia Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Telangana Hyderabad500075 India Department of Computer Science and Engineering Muffakham Jah College of Engineering & Technology Hyderabad India Department of Computer Science and and Information Technology Muffakham Jah College of Engineering & Technology Hyderabad India

ISBN: (纸本)9789819609239

MRI is important for diagnosing brain tumors due to its clear imaging. Manual brain tissue segmentation in MRI images is time- consuming and prone to errors. Deep learning can now automate this task effectively. Left4Dead team uses deep learning to segment brain tissues and identify tumor locations in MRI scans accurately. CNNs, RNNs, and other deep learning structures combined with traditional techniques enhance segmentation performance. Applying hybrid deep learning methods in medical imaging may improve brain tumor detection. Techniques like merging features on different scales and transfer learning can tackle obstacles in brain tissue segmentation and tumor detection. Integration of GANs and reinforcement learning can enhance data augmentation in this field. This review analyzes advanced techniques and challenges in previous research. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based human activity recognition using CNN, ConvLSTM, and LRCN

引用

International Journal of Cognitive Computing in engineering 2024年第1期5卷 259-268页

作者： Uddin, Md. Ashraf Talukder, Md. Alamin Uzzaman, Muhammad Sajib Debnath, Chandan Chanda, Moumita Paul, Souvik Islam, Md. Manowarul Khraisat, Ansam Alazab, Ammar Aryal, Sunil School of Information Technology Deakin University Waurn Ponds Campus Geelong Australia Department of Computer Science and Engineering International University of Business Agriculture and Technology Dhaka Bangladesh Department of Computer Science and Engineering Jagannath University Dhaka Bangladesh Centre for Artificial Intelligence and Optimization Torrens University Australia Department of Electrical and Computer Engineering University of Ottawa Canada

Human activity recognition (HAR) plays a crucial role in assisting the elderly and individuals with vascular dementia by providing support and monitoring for their daily activities. This paper presents a deep learning (DL)-based approach to HAR, leveraging convolutional neural network (CNN), convolutional long short-term memory (ConvLSTM), and long-term recurrent convolutional network (LRCN) architectures. These models are designed to extract spatial features and capture temporal dependencies in video data, enhancing the accuracy of activity classification. We conducted experiments on the UCF50 and HMDB51 video datasets, encompassing diverse human activities. Our evaluation demonstrates that the ConvLSTM model achieves an accuracy of 82% on UCF50 and 68% on HMDB51, while the LRCN model gives accuracies of 93.44% and 71.55%, respectively. Finally, the CNN model outperforms with an accuracy rate of 99.58% for the UCF50 and 92.70% for the HMDB51 datasets. These significant improvements showcase the effectiveness of integrating convolutional and recurrent neural networks for HAR tasks. Our research contributes to advancing HAR systems with potential applications in healthcare, assisted living, and surveillance. By accurately recognizing human activities, our models can assist in remote patient monitoring, fall detection, and public safety initiatives. These findings underscore the importance of DL in enhancing the quality of life and safety for individuals in various contexts. © 2024 The Authors

关键词： Long short-term memory

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：