检索结果-内蒙古大学图书馆

6th International Conference on Smart Computing and Informatics, SCI 2024

作者： Sulaie, Saleh Al Laxmi Lydia, E. Vijaya Kumar, K. Rao, Kommu Gangadhara Department of Mechanical and Industrial Engineering College of Engineering and Computing in Al-Qunfudah Umm Al-Qura University Makkah Saudi Arabia Department of Computer Science and Engineering GMR Institute of Technology Rajam India Department of Computer Science Engineering GITAM School of Technology Gitam University Visakhapatnam India Department of IT Chaitanya Bharathi Institute of Technology Hyderabad India

ISBN: (纸本)9789819619801

Hospital systems are currently dealing with a large patient influx brought on by a number of circumstances, including seasonal flows or epidemic-related health problems. Hospital facilities, especially emergency departments (EDs), have to admit people for medical care regardless of the severity of the care requirements. However, the large patient volume frequently results in longer length of stay (LOS) for patients and causes issues with congestion in emergency departments. Hospital administrators must forecast the patient’s length of stay (LOS), as this is a crucial metric for evaluating ED congestion and the utilization of medical resources (allocation, planning, and utilization rates). Thus, to enhance ED management, precise LOS prediction is required. In this study, a logistic regression algorithm (LRA) model-based method for forecasting patient length of stay (LOS) in the ED is proposed. Without making any presumptions about the distribution of the data, it flexibly learns pertinent information from linear and nonlinear processes and greatly improves prediction accuracy. In order to facilitate decision-making and avoid crowding, we also categorized the anticipated patients’ length of stay (LOS) based on the amount of time they spent in the pediatric emergency department (PED). The PED provided real data that was used in the trials. We compared the LRA results with those from other models. The results show that LRA performs better than the other models and attest to the models’ suitability for forecasting patient length of stay. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

EDRLNet: privacy preservation in online social networks via deep reinforcement learning and graph convolutional networks

引用

International Journal of Information Technology (Singapore) 2025年 1-10页

作者： Gowda, Nithish Ranjan Venkatesh Venugopal, K.R. Department of Computer Science and Engineering University Visvesvaraya College of Engineering Bangalore University Bengaluru India Associate Professor Department Computer Science and Engineering University Visvesvaraya College of Engineering Bangalore University Bangalore India University Visvesvaraya College of Engineering Bangalore University Bangalore India

Online social networks (OSN) have become extremely popular in the past few decades. Prominent OSN companies, such as Facebook and Twitter, control a huge amount of information on its users as well as interactions that may cause people to have major privacy concerns. The OSN information is combined with other online sources to reveal sensitive information. As a result, there is a great need to anonymize the OSN data before providing it to a third party. Thus, in this study, we propose a Deep Reinforcement Learning (DRL)-based rewiring operation that entails changing the relationships (edges) between nodes (users) without changing their degree to protect users’ privacy. To accomplish this, we introduce a novel technique for Enhanced DRL Networks called “EDRLNet” which combines an Optimized Policy Network (OPN) and Graph Convolutional Network (GCN) that preserves the essential characteristics of OSN data while anonymizing it to prevent privacy breaches. This approach employs a GCN to extract embeddings (features) from the edges and nodes. Furthermore, OPN applies the graph feature representation learned by the GCN model to policy learning. Additionally, the hyperparameters of OPN are optimized by using the Addax optimization algorithm (AOA). The suggested scheme’s performance is assessed using PageRank with mean-squared error (MSE), Root mean-squared error (RMSE), mean absolute error (MAE), Privacy score, Utility Score, Clustering coefficient, privacy and information loss. © Bharati Vidyapeeth's Institute of computer Applications and Management 2025.

关键词： Addax optimization algorithm Anonymization Deep reinforcement learning Graph convolutional network Online social network Privacy preservation

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Mastery in Cardiovascular Risk Assessment 1

Machine Learning Mastery in Cardiovascular Risk Assessment

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Gandhimathi, Suma Kamalesh Rajesh, S.M. Ghamya, K. Lohitha, A. Lakshmi Vinitha, A. Reddy, C. Surya Prakash VIT-AP University School of Computer Science and Engineering Amaravathi India GITAM University-Bengaluru Campus GITAM School of Technology Department of CSE Bengaluru India Tirupati India Sree Vidyanikethan Engineering College Department of CSE Tirupati India

ISBN: (纸本)9798350356816

Coronary illness stays a basic general well-being concern, requiring progressed prescient instruments for opportune determination and intercession. It is the maincause of death universally, liable for almost 18million passings every year. Early recognition and intercession are significant for lessening CVD mortality. AI has arisen as an integral asset for anticipating coronary illness risk, offering expected benefits for customized medication and further developed medical service results. Data preprocessing, feature selection, model training, and evaluation are all covered in this review of ML-based heart disease prediction systems. We talk about the logistic regression, decision trees, random forests, support vector machines (SVMs), naive Bayes, k-means, and artificial neural networks (ANNs) ML algorithms used to predict heart disease. We additionally feature the significance of interpretability and logic in ML models for clinical navigation. At last, we talk about future directions in ML-based coronary illness expectation, accentuating the capability of deep learning and hybrid models for upgrading prescient precision and clinical importance. © 2024 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

A Review towards Fault-Tolerable Load Balancing in Cloud Computing

A Review towards Fault-Tolerable Load Balancing in Cloud Com...

引用

2023 International Conference on Intelligent Systems for Communication, IoT and Security, ICISCoIS 2023

作者： Siruvoru, Vahini Aparna, S. Vijaykumar, Nampally Siruvoru, Vahini GITAM Deemed to Be University Department of Computer Science and Engineering Hyderabad India Medak India Medak India

ISBN: (纸本)9798350335835

In cloud computing, load-balancing is essential for maximising workload distribution and utilising available resources, which in turn reduces the system's overall reaction time. In order to deal with load balancing-related problems such work scheduling, migration, resource utilisation, and others, a number of strategies and approaches have been presented. The essential issue of load-balancing in cloud computing was addressed in this study in a variety of ways. By contrasting the approaches proposed by researchers during the previous six years., the challenges associated with load-balancing have been examined. Numerous methods have been suggested, however some problems, such VM migration and unresolved fault tolerance problems, still exist in the cloud environment. © 2023 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Lightweight Privacy Preserving Framework at Edge Layer in IoT 1

引用

10th International Conference on Frontiers of Intelligent Computing: Theory and Applications, FICTA 2022

作者： Agrawal, Kavita Chittineni, Suresh Reddy, P. V. G. D. Prasad Subhadra, K. Diaz, Elizabeth D. Department of Computer Science and Engineering Chaitanya Bharathi Institute of Technology Hyderabad India Department of Computer Science and Engineering GITAM Deemed to be University Vishakhapatnam India Department of Computer Science and Systems Engineering Andhra University Vishakhapatnam India Department of Computer Science and Engineering University of Texas Arlington United States

ISBN: (数字)9789811975240

ISBN: (纸本)9789811975233

The Internet of Things is helping us to make our lives comfortable. IoT devices used here are resource-constrained in terms of memory and CPU as well as they lack basic security design. When everyone is using IoT, there are high chances of their personal data getting exposed to the outside world. For real-time application, data need to be processed at the edge layer directly instead of doing the entire processing and analysis at cloud. Privacy preserving at the edge layer in the Internet of Things is a challenging task. We proposed a lightweight privacy preserving framework that uses the concept of blockchain, zero knowledge proof algorithm, principal component analysis, and digital signatures. Here for the mining process in blockchain, Trust concept is being used instead of Proof of Work (POW) and Proof of Stake (POS) as it consumes fewer resources and our edge layer is resource constrained. This could be a feasible solution and can be deployed at the edge layer in the Internet of Things for preserving privacy. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Blockchain in Evolving Computing Paradigms: A Beginner's Guide for Review and Future Directions 11

Blockchain in Evolving Computing Paradigms: A Beginner's Gui...

引用

11th IEEE Region 10 Humanitarian Technology Conference, R10-HTC 2023

作者： Mahapatra, Abhijeet Mishra, Kaushik Majhi, Santosh Kumar Pradhan, Rosy Veer Surendra Sai University of Technology Department of Computer Science and Engineering Odisha Burla India GITAM Deemed to be University Department of Computer Science and Engineering Andhra Pradesh Visakhapatnam India

ISBN: (纸本)9798350326147

The evolvement of different computing paradigms as complementary to Cloud computing has transfigured the world into a smarter place. This extension of Cloud computing has been believed as cutting-edge technology to improve the processing power of the resource constraint computing nodes. However, due to location unawareness, the security of the data plays a significant role both for the service provider and consumers. This challenge led to the development of blockchain technology as a prominent solution for providing security and privacy. This paper aims to briefly survey blockchain technology and its application as a solution in evolving computing paradigms. In addition, a secured task offloading framework using blockchain in the loT-Fog-Cloud paradigm has also been proposed. Furthermore, this paper investigates some of the open issues and challenges in the aforementioned computing paradigms and proposes future scope for the above challenges. This survey elucidates the vision of blockchain technology in these paradigms and would be a helping hand for researchers and academicians for a transparent picture of this newer technology. © 2023 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

MOPSO-driven optimization for sustainable retrofitting: balancing time, cost, and environmental impacts

引用

Asian Journal of Civil engineering 2025年第5期26卷 2165-2178页

作者： Singh, Rekha Sangeeta, Viswanadham Manjunath, T.C. Singh, Prachi Bishoyi, Sasanka Sekhar Pati, Aditya Kumar Department of Civil Engineering Raj Kumar Goel Institute of Technology Ghaziabad India Computer Science and Engineering GITAM Deemed to Be University Visakhapatnam India Department of Computer Science & Engineering Rajarajeswari College of Engineering Bengaluru India Department of Civil Engineering Madhav Institute of Technology and Science Gwalior India Department of Mathematics NIST University Berhampur India Department of Mathematics Centurion University of Technology and Management Gajapati R. Sitapur India

Retrofitting projects play a critical role in enhancing the sustainability of existing structures, yet balancing time, cost, and environmental impact remains a significant challenge for decision-makers. This study introduces a Multi-Objective Particle Swarm Optimization (MOPSO) approach to achieve optimal trade-offs among these competing objectives. By leveraging MOPSO’s capability to explore Pareto-efficient solutions, the research provides a robust framework for sustainable decision-making in retrofitting projects. The model evaluates project scenarios based on key metrics such as time efficiency, cost minimization, and reduced carbon emissions. Through the application of MOPSO, the study generates a range of viable solutions, enabling project managers to make informed decisions tailored to specific sustainability goals. A case study is conducted to validate the model’s effectiveness, comparing its performance with conventional optimization techniques. The results demonstrate that MOPSO excels in balancing multiple objectives, delivering superior outcomes in sustainability metrics. This research contributes to the advancement of sustainable construction practices by offering a practical tool for optimizing retrofitting projects in alignment with environmental and economic priorities. The findings provide valuable insights for practitioners seeking to integrate sustainability into decision-making processes, addressing the pressing need for environmentally conscious infrastructure development. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： MOPSO Multi Objective optimization Sustainable construction practices Sustainable retrofitting Time-cost-environmental trade-off

来源：评论

学校读者我要写书评

暂无评论

Twitter sentiment analysis using conditional generative adversarial network

引用

International Journal of Cognitive Computing in engineering 2024年第1期5卷 161-169页

作者： Mahalakshmi, V. Shenbagavalli, P. Raguvaran, S. Rajakumareswaran, V. Sivaraman, E. Department of Information Technology Sengunthar College of Engineering Tiruchengode Tiruchengode637205 India Assistant Professor Karunya Institute of Technology and Sciences Coimbatore India Assistant Professor Department of Computational Intelligence School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur Kanchipuram Chennai Tamil Nadu 603203 India Assistant Professor Department of Computer Science and Design Erode Sengunthar Engineering College Tamil Nadu Thuduppathi India Department of Electrical and Computer Engineering Curtin University Miri Malaysia

Sentiment analysis, which aims to extract information from textual data indicating people's ideas or attitudes about a particular problem, has developed into one of the most exciting study issues in natural language processing (NLP) with the development of social media. Twitter is a social network with an extensive audience that expresses their thoughts and opinions clearly and readily. Due to the prevalence of slang phrases and incorrect spellings in short phrase styles, Twitter data analysis is more challenging than data analysis from other social networks. Automated feature selection still has several limitations, such as higher computing costs that rise with the number of characteristics. Deep learning, which is self-learned and more accurate at processing vast amounts of data, is utilized to overcome these challenges. This paper introduces a conditional generative adversarial network (GAN) for Twitter sentiment analysis, whereas a convolutional neural network (CNN) has been used to extract traits from Twitter data. Compared to existing works, the proposed work has outperformed in accuracy, recall, precision, and F1 score. The suggested method is the most accurate, with a classification accuracy of 93.33 %. © 2024

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

An Automated Sleep Stage Classification for Healthcare Monitoring by using Single Channel EEG Signal

An Automated Sleep Stage Classification for Healthcare Monit...

引用

2023 IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2023

作者： Kumar Gurumoorthy, Sasi Chethana, D.T. Ramesh, M. Upendra Roy, B.P. Sapna Kumari, C. J.J.College of Engineering and Technology Department of Computer Science and Engineering Trichy India Gitam School of Technology Gitam University Department of Computer Science & Engineering India K L University Department of Computer Science & Engineering Vadeeshwaram Vijayawada India Channabasaveshwara Institute of Technology Department of Electronics and Communication Engineering Tumkur India Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India

ISBN: (纸本)9798350398465

It is well-established that biomedical signals convey crucial data regarding the functioning of living systems. The physiological and clinical information included in these signals can be improved with adequate processing. Modern qualitative and quantitative analyses of physiological systems and events rely on digital signal processing and pattern recognition methods. Analysis and interpretation of a medical practitioner's signal carry the weight of the analyst's knowledge and expertise, yet such analysis is inherently subjective. If done logically, computer analysis of biomedical information might provide credibility to the expert's interpretation by providing an objective second opinion. Furthermore, it allows for enhanced diagnosis and online monitoring of critically ill patients. The current research intends to develop effective methods for utilizing sleep-monitoring health gadgets. When it comes to handling complex classification or pattern recognition issues, the Support Vector Machine (SVM) is the instrument of choice. In this article, we focus on using support vector machines (SVMs) to identify and categorize apnea. When compared to other methods of categorization, such as sophisticated statistical approaches, SVM performed better. Both an adaptive classification model and a novel approach to merging the decisions of ensemble-based classification models are proposed in the work. The current method relies on an ensemble classifier system and a huge number of features, making it both effective and trustworthy. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

An Advanced Intrusion Detection Solution for Networks based on Honeypot Servers 6

An Advanced Intrusion Detection Solution for Networks based ...

引用

6th International Conference on Inventive Computation Technologies, ICICT 2023

作者： Veena, K. Meena, K. Mercy Theresa, M. Hemalatha, C. Rajalakshmi, D. Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai600119 India Department of Computer Science and Engineering GITAM School of Technology GITAM Bangalore561203 India Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai603203 India Computer Science and Engineering Sri Sairam Institute of Technology Chennai India

ISBN: (纸本)9798350398496

Network security is a critical issue in modern technology. Honey pot-based intrusion detection methods provide an additional layer of security and enhance network performance by analyzing hacker behaviour and detecting unauthorized clients. IP validation and vulnerability detection are used to ensure authorized customer access and prevent illegal client activity. A voice recognition system detects malicious attacks in stage two. If authorized, packets are passed to the server, otherwise, they are delivered to honeypot servers. Using Naive Bayes algorithm, the detection rate is 85.06% with an accuracy of 98.18% and a false alarm rate of 0.15 seconds. © 2023 IEEE.

关键词： Network security

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：