检索结果-内蒙古大学图书馆

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

作者： Hemanth, S.V. Kirubha, D. Reddy, Sheri Ramchandra Chelladurai, T. Soundari, A. Gnana Amirthayogam, G. Hyderabad Institute of Technology and Management Department of Computer Science and Engineering Telangana Hyderabad501401 India Rajarajeswari College of Engineering Department of Computer Science and Engineering Karnataka Bangalore560074 India Telangana Hyderabad501401 India Psna College of Engineering and Technology Department of Electronics and Communication Engineering Tamil Nadu Dindigul624622 India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Thandalam600124 India Department of Information Technology Tamilnadu Chennai603103 India

ISBN: (纸本)9798350375190

Cloud Computing (CC) is a powerful paradigm for accessing IT services over the internet, allowing multiple consumers to share resources. Therefore, it requires task scheduling, allocating, and gradually releasing resources. Hence, efficient Task Scheduling (TS) and Resource Allocation (RA) in cloud systems is crucial to optimize resource usage and ensure timely completion. Assigning computing tasks in a cloud environment is a multifaceted process affected by numerous factors, including network bandwidth availability, completion time, and cost considerations. Traditional scheduling models based on heuristic algorithms have limitations in complex in cloud environments. To tackle these issues, we introduce Multi objective Ant Colony Optimization (MACO) and Adaptive Sequence Dynamic Allocation (ASDA) techniques for TS and RA in the cloud environment. Initially, the tasks submitted globally are divided into long and short queues. After that, the MACO algorithm schedules the task based on queues. Subsequently, the proposed ASDA algorithm efficiently allocates the most appropriate Virtual Machine (VM). If a VM is already occupied, the proposed method promptly chooses the next available VM based on the progress of the work completion process. According to the experimental results, the proposed algorithm achieves significant cost savings compared to other algorithms. © 2024 IEEE.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

Framework for Assessment of Bitcoin Price Prediction Using Ensembling Machine Learning Approach 3

Framework for Assessment of Bitcoin Price Prediction Using E...

引用

3rd International Conference on Pervasive Computing and Social Networking, ICPCSN 2023

作者： Shimpi, Amisha Gambhir, Rohan Diwate, Abhishek Udawant, Sahil Siddiqui, N.Y. William, P. Sanjivani College of Engineering Sppu Department of Electronics and Computer Engineering Maharashtra Pune India Sanjivani College of Engineering Sppu Department of Information Technology Maharashtra Pune India

ISBN: (纸本)9798350322842

As crypto market knowledge is not widely available to new investors;this problem may lead to wrong investments and financial losses. Inadequate understanding of the elements that have a significant impact on the price of bitcoin might potentially result in poor investing decisions. Now, there are more than $230 billion worth of openly traded cryptocurrencies on the market. The main purpose of Bitcoin, the most valuable cryptocurrency, which also has the best price predictability, is to act as a digital store of wealth. Bitcoin is a digital currency that is used all over the world for advanced payments or mostly for speculation. For instance, Bitcoin is decentralized because no one owns it. Bitcoin exchanges are easy since they are not tied to any one country. This research study employs a variety of machine learning approaches to predict Bitcoin values. Accurate price prediction is crucial for making wise investing decisions nowadays because of its high volatility feature. The price of bitcoin is initially divided into daily and high-frequency categories in this study. A collection of high-dimensional characteristics and fundamental trading features are used, respectively, for its daily and price forecast. Next, we see that while sophisticated machine learning algorithms like SVM accurately forecast pricing, statistical approaches like linear regression do not. The significance of sample dimensions in machine learning techniques is acknowledged in this study on predicting Bitcoin values. © 2023 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Integrating Informatics and Business Administration: Bridging the Gap for Developed Organizational Performance

Integrating Informatics and Business Administration: Bridgin...

引用

2024 International Conference on Decision Aid Sciences and Applications, DASA 2024

作者： Qader Ismail Alnajem, Ahmed Abdel Abdulrazak Al-Kubaisi, Abdulrazak A. Mahfuri, Mahmoud Radhi, Ahmed Dheyaa Abdulrahman, Mayasa M. Almajed, Rasha Baghdad College of Economic Sciences Business Administration Department Iraq International University for Science and Technology Computer and Information Technology Department Syria College of Pharmacy University of Al-Ameed Iraq College of Engineering Computer Engineering Department University of Baghdad Baghdad Iraq College of Engineering Abu Dhabi University United Arab Emirates

ISBN: (纸本)9798350369106

In today's business environment, organizations face the twin challenge of managing large amounts of data to ensure effective and strategic decision making. This paper addresses the problem of integrating information science and business management, which is particularly challenging due to the specific nature of these industries. The main objective of this study is to investigate the interplay between AI Solutions and business processes and to show how their integration can enhance organizational performance. This paper tests the issues, key elements, and basic principles of marketing management in practice, by adopting company and By Analysis of training programs and the concept of reporting steps. The contributions of these studies are twofold. Firstly, it affords empirical proof helping theoretical fashions like Socio-Technical Systems (STS) theory, the technology Acceptance Model (TAM), and Contingency Theory, thereby improving the instructional expertise of informatics and commercial enterprise management integration. Secondly, it gives realistic suggestions for corporations in search of to acquire stepped forward decision-making, operational efficiency, and innovation via integration. The consequences show that corporations that efficaciously combine informatics and commercial enterprise management can acquire great benefits, which includes a 15% discount in operational costs, a 25% growth in patron satisfaction, and a 30% development in danger evaluation accuracy. These findings underscore the significance of strategic planning, cross-purposeful collaboration, and non-stop ability improvement in using hit integration and improving organizational performance. © 2024 IEEE.

关键词： Informatics

来源：评论

学校读者我要写书评

暂无评论

Exploring the Use of Machine Learning Techniques for Enhancing Real-Time Data Access 3

Exploring the Use of Machine Learning Techniques for Enhanci...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Rampal, Sourav Shreenidhi, H.S. Shrivastava, Manish Singh, Akhilendra Pratap Reena, R. Kumar, Santosh D. Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Computer Science and Engineering Faculty of Engineering and Technology Karnataka Bangalore India Vivekananda Global University Department of Computer Science & Engineering Jaipur India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Prince Shri Venkateshwara Padmavathy Engineering College Department of Computer Science and Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India

ISBN: (纸本)9798350319125

Actual-time statistics to date has updated, increasingly vital as the quantity of virtual information maintains updated growth. Effective choice-making depends on the capability to update access and analyze records. Device up-to-date techniques provide the capacity up-to-date enhance actual-time statistics up-to-date by using offering insights from disparate pieces of information. This paper addresses the potential benefits of using a system with date knowledge and updated, up-to-date strategies to broaden extra clever statistics up to date updated systems. It summarizes the contemporary nation of the art and highlights studies in machine learning and up-to-date imaginative and prescient real-time information up-to-date. It additionally discusses present-day challenges and shows viable instructions for future studies. The studies network up-to-date recall how gadgets are up to date know that updated strategies may be used to facilitate real-time get entry updated the maximum precious pieces of facts. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

End-to-End Congestion Avoidance Scheme for Underwater High Speed Communication Networks 3

End-to-End Congestion Avoidance Scheme for Underwater High S...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Shivank Jain, Romil Reena, R. Kadam, Prema S. Das, Sunanda Singh, Swati Vivekananda Global University Department of Computer Science & Engineering Jaipur India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Prince Shri Venkateshwara Padmavathy Engineering College Department of Computer Science and Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Computer Science and Engineering Faculty of Engineering and Technology Karnataka Bangalore India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India

ISBN: (纸本)9798350319125

The cease-to-give up Congestion Avoidance Scheme for Underwater high pace verbal exchange Networks, commonly known as E2E-UCAN, is a critical technique for lowering plausible throughput by using efficiently warding off congestion inside a community. E2E-UCAN is a disbursed congestion control mechanism which uses statistics obtained from cease-to-end feedbacks to regulate sending prices on the give up systems. By means of monitoring the differences among expected network overall performance and actual performance, E2E-UCAN is able to pick out congestion stages inside the device, and is therefore able to regulate to prevent congestion before it happens. This enables to improve the stableness of the community and to increase the throughput of a network. Moreover, E2E-UCAN is likewise capable of efficaciously coping with queuing, avoiding packet loss in non-uniform networks, and in preferred, permitting applications to maximize performance. © 2023 IEEE.

关键词： Community Congestion Lowering Mechanism Performance

来源：评论

学校读者我要写书评

暂无评论

Distributed and Cooperative Security Mechanisms for Networked Applications 5th

Distributed and Cooperative Security Mechanisms for Networke...

引用

5th International Conference on Data Science, Machine Learning and Applications, ICDSMLA 2023

作者： Kamalraj, R. Singh, Vaishali Bhambu, Pawan Wadhwa, Bhawna Karnataka Bangalore India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Department of Computer Science and Engineering Vivekananda Global University Jaipur India Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India

ISBN: (纸本)9789819780426

Cutting-edge applications rely heavily on conversation via PC networks to provide improved functionality, multiplied interactivity, and more to get admission to sources. Cozy verbal exchange and gain control access should be enforced to shield information and different assets. Distributed and cooperative protection mechanisms enable exceptional components of a networked utility to collaborate for you to get the right of entry to resources responsibly, proportion records securely, and authenticate customers. Such mechanisms are regularly designed to offer automated authorization and authentication, secure conversation channels, and a cozy records garage. In addition, they usually include additives, which have users, roles, and permissions to assist in controlling access. Utility developers and IT directors can ensure that networked packages remain cozy no matter the ever-converting safety landscape by adopting allotted and cooperative safety mechanisms. Distributed and Cooperative security Mechanisms (DCSM) are community security mechanisms designed to provide a layered method to defend in opposition to cyber-attacks on networked applications. The use of DCSM permits a shift from traditional networks to an agile and resilient system structure that can react speedily to a capacity chance, mitigating the damaging effect of malicious attacks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： computer viruses

来源：评论

学校读者我要写书评

暂无评论

Predicting Blood Glucose Levels in Type 1 Diabetes Using Deep Learning and Regression Techniques

Predicting Blood Glucose Levels in Type 1 Diabetes Using Dee...

引用

2025 International Conference on Intelligent Control, Computing and Communications, IC3 2025

作者： Singh, Jagendra Singh, Brijendra Pratap Dandotiya, Monika Ekvitayavetchanukul, Pongkit Rana, Manoj Singh, Bakshish School of Computer Science Engineering & Technology Bennett University Greater Noida India Poornima University Department of Computer Science & Engineering Jaipur India The Board of Khonkaen University Affaneirs Khonkaen University Thailand Teerthanker Mahaveer University Cdoe Moradabad India Raj Kumar Goel Institute of Technology Department of Information Technology Ghaziabad India

ISBN: (纸本)9798331527495

Accurate blood glucose prediction is very critical for the effective management of Type 1 Diabetes as it allows timely interventions and prevents fluctuations in blood sugar levels. Due to such shortcomings, the traditional methods of monitoring that are followed are consistently unable to provide real-time insights and often cannot inform the patients about the stable levels of their glucose. This research studies advanced deep learning applications based on Long Short-Term Memory (LSTM), Gated recurrent unit (GRU), Autoregressive Integrated Moving Average (ARIMA), and linear regression models to predict blood glucose levels in terms of insulin intake dosage, consumption of carbohydrates, level of physical activity, and sleep patterns. The model performances with respect to Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean absolute percentage error (MAPE), and accuracy are deployed for training and performance evaluation. Results were obtained, which show that LSTM performed well in comparison to others with an accuracy of 97.68%, followed by ARIMA (92.23%), GRU (91.23%), and Linear Regression at an accuracy of 89.45%. Real-time testing also gave the results consistent with the above, showing accuracy at close par with the glucose values. Therefore, LSTM in diabetes management systems may allow for blood glucose monitoring in real-time and customised intervention. This research contributes towards developing intelligent systems with the capacity to predict problems and enhance patient outcomes and quality of life for those with Type 1 Diabetes by embedding deep learning models into predictive accuracy and timeliness. © 2025 IEEE.

关键词： Linear regression

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for MRI-Based Brain Tumour Identification and Classification 1

引用

8th International Conference on Data Management, Analytics and Innovation, ICDMAI 2024

作者： Jareena Begum, D. Chokkalingam, S.P. Sundaravadivazhagan, B. Department of Computer Science and Engineering Amrita School of Computing Chennai Amrita Vishwa Vidyapeetham Chennai India Department of Computer Science and Engineering Amrita School of Computing Chennai Amrita Vishwa Vidyapeetham Chennai India Department of Information Technology University of Technology and Applied Sciences University of Technology and Applied Sciences Al Mussana Oman

ISBN: (数字)9789819732456

ISBN: (纸本)9789819732449

Radiology tumour spotting is complicated and requires medical knowledge. Thus, a lack of doctors should not delay cancer detection programmes. Biomedical image processing software helps find brain tumours in MRI data. This study segmented and detected brain tumours using MRI sequence images. This process is complicated by the similarity of normal tissues and the wide range of tumour tissues in different patients. Brain tumour detection is the main goal. Brain tumour diagnosis requires precise tumour size and position. This paper presents a deep learning-based brain tumour MRI segmentation and classification method. We preprocessed the photos with the Gaussian blur filter and image enhancement tool. Binary thresholding segments. Morphological methods reveal traits. CNN will assess brain MRI regularity. This study uses the Kaggle Dataset. We train with 255 brain MRIs, 155 with tumours and 98 normal, and achieve 97% accuracy. We test the model using Kaggle brain MR datasets. Brain tumour detection, segmentation, and categorization;medical image processing. This study proposed an easy-to-implement way for identifying and classifying bone tumours. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Ensemble knowledge distillation for collaborative pseudo-label refinement in unsupervised domain adaptation for person re-identification

引用

Optik 2025年 328卷

作者： Samanta, Sidharth Jena, Debasish Rup, Suvendu Department of Computer Science and Engineering International Institute of Information Technology Bhubaneswar India Department of Information Technology National Institute of Technology Raipur India

In open-world person re-identification, obtaining annotated ground truth for every deployment environment is infeasible which necessitates the exploration of unsupervised domain adaptation methods. The Pseudo-label guided approaches leverage clustering methodologies for the generation of pseudo-labels to facilitate model retraining on the unlabeled target domain. However, the robustness of these methodological approaches is vulnerable in the presence of label noise, which is generated due to the domain shift, specifically, the interplay of intra-domain similarity within the source domain and the inter-domain dissimilarity between the source and target domains. This study introduces a novel learning scheme to enhance the robustness of such cross-domain re-identification models by minimizing the label noise through collaborative refinement utilizing the amalgamation of multiple teacher outputs and subsequent network training with the refined pseudo-labels. To obtain diverse perspectives, domain-adapted teacher networks of varying types and sizes are employed, and subsequently, their outcomes are amalgamated through a dynamic averaging method to yield a refined representation. A comprehensive set of ablation studies systematically analyzes the contributions of each component, highlighting the vital roles of clustering, knowledge distillation, collaborative refinement, and optimal ensemble size. Furthermore, the proposed model undergoes rigorous evaluation on widely used datasets, such as Market1501, DukeMTMC, and MSMT17, demonstrating superior performance compared to existing state-of-the-art methods. The mean Average Precision (mAP) and Rank-1 (R1) scores showcase notable improvements, with results indicating an enhanced performance in Duke to Market (mAP: 81.04, R1: 90.84) and Market to Duke (mAP: 76.24, R1: 86.27) scenarios. © 2025 Elsevier GmbH

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Transforming Online Learning with CNN and NLP: Personalized Education 14

Transforming Online Learning with CNN and NLP: Personalized ...

引用

14th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2023

作者： Lathaharan, Abilash Ravendran, Danushan Varatharasa, Agash Thayaparan, Abinaya Kasthuriarachchi, Sanvitha Rajendran, Karthiga Sri Lanka Institute of Information Technology Department of Computer Science & Software Engineering New Kandy Road Malabe Sri Lanka SSri Lanka Institute of Information Technology Department of Information Technology New Kandy Road Malabe Sri Lanka

ISBN: (纸本)9798350304138

In the rapidly evolving landscape of online education, ensuring easy and healthy learning experiences has become paramount. This research paper presents 'Sparkle Edu,' an innovative application that integrates multiple components to address the unique challenges of online learning. The components include stress detection through facial emotions and drowsiness analysis, facial authentication with personalized course recommendations, an AI-powered mental health therapist utilizing voice-to-text input, and document reconstruction for damaged images to predict missing letters and words. Through the implementation of these components, Sparkle Edu aims to create an engaging and supportive platform that prioritizes students' well-being and promotes effective learning. This research contributes valuable insights into the advancement of online education, fostering a brighter and more accessible future for learners worldwide. © 2023 IEEE.

关键词： 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：