检索结果-内蒙古大学图书馆

A bio-inspired metaheuristic approach for cloud task scheduling using lateral hyena based particle swarm optimization

引用

Multimedia Tools and Applications 2025年第18期84卷 20023-20046页

作者： Malik, Meena Nandan, Durgesh Prabha, Chander Uddin, Mueen Acharya, Biswaranjan Hu, Yu-Chen Chandigarh University Mohali India School of CS & AI SR University Warangal506371 India Chitkara University Institute of Engineering and Technology Chitakara University Rajpura India College of Computing and IT University of Doha for Science & Technology Doha Qatar Department of Computer Engineering AI & BDA Marwadi University Gujarat Rajkot India Department of Computer Science Tunghai University No. 1727 Sec. 4 Boulevard Xitun District Taichung City407224 Taiwan

Being a rapidly emerging field, cloud computing encourages the rapid growth of all the essential internet services. One major challenge in a cloud computing environment is balancing the load among various machines to optimize the appropriate workload, thereby providing efficient task scheduling. Various studies have been proposed and implemented for task scheduling to provide a fair load balance among all the available virtual machines on the cloud. This research work targets the optimization of virtual machines by Lateral Hyena -Particle Swarm Optimization (LH-PSO) algorithm. Our main motivation is to push parallel task scheduling proficiently, producing low response time and rapid results for all the assigned tasks. This work attempts to optimize virtual machines by proposing a Lateral Hyena-based solution and parallel task scheduling. The proposed solution provides a flexible system where virtual machines will be load-balanced by serving equal tasks. The proposed solution attempts to optimize a fitness function based on the velocity and position value of particles mapped to the characteristics of incoming requests. The practice aims to find optimized virtual machines solving tasks with an optimal solution. The performance is analyzed using the Cloudsim simulator to assess all parameters such as load distribution, average response time, memory utilization, processor utilization, and average turnaround time. The analytical conclusions represent an enhancement over the existing schemes compared to the above-mentioned parameters. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

Scalable Efficient Training of Large Language Models with Low-dimensional Projected Attention

Scalable Efficient Training of Large Language Models with Lo...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Lv, Xingtai Ding, Ning Zhang, Kaiyan Hua, Ermo Cui, Ganqu Zhou, Bowen Department of Electronic Engineering Tsinghua University China Shanghai AI Laboratory China Department of Computer Science and Technology Tsinghua University China

ISBN: (纸本)9798891761643

Improving the effectiveness and efficiency of large language models (LLMs) simultaneously is a critical yet challenging research goal. In this paper, we find that low-rank pre-training, normally considered as efficient methods that will compromise performance, can be scalably effective when reduced parameters are precisely targeted. Specifically, applying the low-dimensional module only to the attention layer - resolves this issue and enhances both effectiveness and efficiency. We refer to this structure as Low-dimensional Projected Attention (LPA) and provide an explanatory analysis. Through extensive experimentation at parameter scales of 130M, 370M, and scaling up to 3B, we have validated the effectiveness and scalability of LPA. Our results show that LPA model can save up to 12.4% in time while achieving an approximate 5% improvement in test perplexity (ppl) and on downstream tasks compared with the vanilla Transformer. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

IoT-Based Power Metering Automation for Improving data Integrity and Reliability in Power Marketing Meters

IoT-Based Power Metering Automation for Improving data Integ...

引用

2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Samreen, Sumaiya Chanti, Yerrolla Mounika, P. Mandava, Manjusha Kruthika, C.G. Malla Reddy Engineering College for Women It Department Hyderabad India Sr University School of Computer Science & Artificial Intelligence Warangal India Hyderabad India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Vaadeswaram India Nitte Meenakshi Institute of Technology Department of Ai and Ml Bengaluru India

ISBN: (纸本)9798350313413

The goal of this paper is to provide an internet of things (IoT)-based approach for automated electricity metering. When measuring power using standard methods, inaccuracies and erroneous readings are possible, putting the data's integrity and authenticity at risk. The suggested method employs sensors linked to the internet of things (IoT) and machine learning algorithms to detect abnormalities and inconsistencies in real-time energy use statistics. This was evident during the testing phase. The proposed method offers several benefits over the present standard of power metering systems in use. The testing findings demonstrated that the proposed system is more reliable and effective in terms of 0.957 success rate, 0.943 accuracy, 0.967 recall, 0.956 F1 score and 0.982 AUC. © 2023 IEEE.

关键词： Anomaly detection Cloud-based data storage and analysis platform Internet of Things (IoT) Machine learning algorithm Power metering Real-time data analysis User interface

来源：评论

学校读者我要写书评

暂无评论

Ensemble Techniques for the Prediction of Heart Disease with Reduced Entropy 2

Ensemble Techniques for the Prediction of Heart Disease with...

引用

2nd IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2024

作者： Mahesh, T.R. Mohamed Musthafa, M. Rahman, A.M.J.Md. Zubair Viswanath, J. Vanitha, K. Vinoth Kumar, V. Department of Computer Science and Engineering Bangalore India Tamil Nadu Erode India Al- Ameen Engineering College Department of Computer Science and Engineering Tamil Nadu Erode India Madanapalle Institute of Technology & Science Department of Ai Andhra Pradesh India Department of Computer Science and Engineering Coimbatore India Vit University School of Information Technology and Engineering Tamil Nadu Vellore India

ISBN: (纸本)9798350360523

Healthcare industry generates a vast amount of data, the majority of which is sophisticated and massive in size. This information, however, is not "extracted"in order to uncover hidden facts for effective decision-making. Diagnosing heart disease, a noncommunicable disease, is one of the more difficult problems in medicine because it entails the patient's past health history. An accurate and effective automated system can be quite beneficial in detecting cardiac problems. Modern data mining techniques may be able to solve this issue. In the healthcare industry, various information-extracting technologies such as association rule mining, classification, and clustering are used to forecast cardiac disease. In order to address this issue, the research investigates the use of machine learning methods for cardiac disease prediction, including Naive Bayes (NB), logarithmic regression (LR), Support Vector Machine (SVM), the Decision Tree (DT), Random Forests (RF), and the k-nearest-neighbor algorithm (KNN). The Random Forest ensemble technique outperforms with 99% accuracy. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

EAP Based Certificateless Authentication Technique to Access Cloud Services in Openstack 8th

EAP Based Certificateless Authentication Technique to Access...

引用

8th International Conference on Cognition and Recognition, ICCR 2021

作者： Raghavendra, K. Ramesh, B. Chandrika, J. Computer Science and Engineering AI-ML Department Dayananda Sagar University Kudlu Gate Hosur Main Road Karnataka Bangalore560068 India Department of Computer Science and Engineering Malnad College of Engineering Karnataka Hassan India

ISBN: (纸本)9783031224041

Nowadays cloud services have gained more interest. The main advantage of the cloud is, it reduces management costs and efficient usage of resources. The major role of efficient authentication means not only providing authentication but it should also reduce the authentication traffic and provide security. There are many authentication mechanisms most of them were only for a web application. Here in this paper, we focus on both web and non-web applications authentication in cloud environment to access SaaS service. For non-web application services of cloud, ABFAB has created an architecture. ABFAB also defines how to use existing EAP/AAA and GSS-EAP for both web and non-web-based applications. In this paper, we mainly focus on efficient AAA to access cloud services. To demonstrate the proposed system, we use the moonshot from Github, freeradius an opensource, and Openstack for cloud service with our proposed authentication method. We have done the performance analysis of our authentication method compared with the other authentication mechanism to access cloud services. This analysis shows a significant reduction in the computation time required for authentication and reduction in the authentication traffic. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Examination System Automation Using Natural Language Processing

Examination System Automation Using Natural Language Process...

引用

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： R Praveen Kumar N. Muthukumaran Cheruku Hanisha Pohar Rithvik M.Saipavan Goud Department of Computer Science and Engineering (AI&ML) Vignan Institute of Technology and Science Department of ECE Centre for Computational Imaging and Machine Vision Sri Eshwar College of Engineering Coimbatore Tamil Nadu India

Numerous examination portals have been created and distributed over several servers for a number of objectives, including the administration of tests in connection withadmission exams, Olympic competitions at national and worldwide levels, and the administration of placement tests. It turns out that practically all portals are set up for multiple-choice examinations, as we found. Our goal here is not to work on current technology, but rather to work on technology that is very uncommon. The descriptive online examination method is discussed here. Simple to use, multiple choice questions are composed of a question, many possible answers to the same question as well as a field to record the correct response in the database. Descriptive queries, on the other hand, do not fall within this category. To award marks to replies, it incorporates or employs Natural Language Processing (NLP) ideas. The model's responsibility is to lead procedure on the response string so it can give the right stamps to the examinee's responses. The data is generally assembled utilizing an enlightening web-based appraisal procedure. It is likewise inspected, and the made model honors right stamps to the inquiry's answers. With respect to the front-end, HTml 5, CS S 3, Bootstrap, and JavaS cript are utilized. The back-end was created in Python using Django, NLTK for Natural Language Processing, and SQLite version 3 as the database.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MedLogic-AQA: Enhancing Medical Question Answering with Abstractive Models Focusing on Logical Structures

MedLogic-AQA: Enhancing Medical Question Answering with Abst...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Zafar, aizan Mishra, Kshitij Ekbal, Asif Department of Computer Science and Engineering Indian Institute of Technology Patna India School of AI and Data Science Indian Institute of Technology Jodhpur India

ISBN: (纸本)9798891761681

In Medical question-answering (QA) tasks, the need for effective systems is pivotal in delivering accurate responses to intricate medical queries. However, existing approaches often struggle to grasp the intricate logical structures and relationships inherent in medical contexts, thus limiting their capacity to furnish precise and nuanced answers. In this work, we address this gap by proposing a novel Abstractive QA system MEDLOGIC-AQA that harnesses First Order Logic (FOL) based rules extracted from both context and questions to generate well-grounded answers. Through initial experimentation, we identified six pertinent first-order logical rules, which were then used to train a Logic-Understanding (LU) model capable of generating logical triples for a given context, question, and answer. These logic triples are then integrated into the training of MEDLOGIC-AQA, enabling effective and coherent reasoning during answer generation. This distinctive fusion of logical reasoning with abstractive QA equips our system to produce answers that are logically sound, relevant, and engaging. Evaluation with respect to both automated and human-based demonstrates the robustness of MEDLOGIC-AQA against strong baselines. Through empirical assessments and case studies, we validate the efficacy of MEDLOGIC-AQA in elevating the quality and comprehensiveness of answers in terms of reasoning as well as informativeness. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

ABLE: Personalized Disability Support with Politeness and Empathy Integration

ABLE: Personalized Disability Support with Politeness and Em...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Mishra, Kshitij Burja, Manisha Ekbal, Asif Department of Computer Science and Engineering Indian Institute of Technology Patna India School of AI and Data Science Indian Institute of Technology Jodhpur India

ISBN: (纸本)9798891761643

In today's dynamic world, providing inclusive and personalized support for individuals with physical disabilities is imperative. With diverse needs and preferences, tailored assistance according to user personas is crucial. In this paper, we introduce ABLE (Adaptive, Bespoke, Listen and Empathetic), a Conversational Support System for Physical Disabilities. By tracking user personas, including gender, age, and personality traits based on the OCEAN model, ABLE ensures that support interactions are uniquely tailored to each user's characteristics and preferences. Moreover, integrating politeness and empathy levels in responses enhances user satisfaction and engagement, fostering a supportive and respectful environment. The development of ABLE involves compiling a comprehensive conversational dataset enriched with user profile annotations. Leveraging reinforcement learning techniques and diverse reward mechanisms, ABLE trains a model to generate responses aligned with individual user profiles while maintaining appropriate levels of politeness and empathy. Based on rigorous empirical analysis encompassing automatic and human evaluation metrics based on persona-consistency, politeness accuracy, empathy accuracy, perplexity, and conversation coherence, the efficacy of ABLE is assessed. Our findings underscore ABLE's success in delivering tailored support to individuals grappling with physical disabilities. To the best of our knowledge, this is the very first attempt towards building a user's persona-oriented physical disability support system. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Fusion of Convolutional Neural Networks and Random Forests for Accurate Potato Leaf Disease Detection

Fusion of Convolutional Neural Networks and Random Forests f...

引用

Applied Intelligence and Computing (aiC), IEEE World Conference on

作者： Durgunala Ranjith Bhargav Somisetty Sallauddin Mohmmad P Ramana Jayapal Lande School of Computer Science and Artificaial Intelligence SR University Warangal Telangana India Department of CSE(AI&ML) CVR College of Engineerning Hyderabad Telangana India Computer Science and Engineering Hyderabad Institute of Technology and Management Hyderabad Telangana India

ISBN: (数字)9798350384598

ISBN: (纸本)9798350384604

In order to classify potato leaf diseases, this work suggests a hybrid model that combines a Random Forest classifier for sample class classification with a CNN for image feature extraction. The dataset obtained from Kaggle includes 1885 samples of different potato leaf illnesses caused by fungi, viruses, pests, bacteria, Phytophthora, nematodes, and healthy leaves. Thorough preprocessing entails dividing the dataset into equal training, testing, and validation sets and downsizing photos to a standard dimension. The CNN model uses ReLU activation for normalization and softmax activation for classification. It has five layers with progressively larger filter sizes. For the final label classification, features taken from the CNN are fed into a Random Forest classifier consisting of 100 decision trees. The suggested model shows promise in terms of performance and accuracy in classifying diseases. The hybrid model suggested for classifying diseases affecting potatoes shows encouraging results; it has an overall accuracy rate of 77% and a precision range of 44% to 96% for various disease categories.

关键词： Training Accuracy Computational modeling Crops Convolutional neural networks Random forests Standards Optimization Diseases Testing

来源：评论

学校读者我要写书评

暂无评论

Assessing Secure Cloud Information Sharing Through Authentication and Encoded Indexing 8

Assessing Secure Cloud Information Sharing Through Authentic...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Pandiaraja, P. Karthik, K. Rajesh Kanna, P. Ushapriya, C. Mahesh, P.C.Senthil Muthumanickam, K. Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology School of Computing Department of Computer Science and Engineering Chennai600 062 India M. Kumarasamy College of Engineering Department of Computer Science and Engineering Karur Tamilnadu Thalavapalayam639113 India Bannari Amman Institute of Technology Department of Computer Science and Engineering Tamilnadu Erode638401 India St. Martin's Engineering College Department of Ai & Ml Telangana Secunderabad500100 India Excel Engineering College Department of Computer Science and Engineering Tamilnadu Komarapalayam637303 India Kongunadu College of Engineering and Technology Department of Information Technology Tamil Nadu Trichy621215 India

ISBN: (纸本)9798350376425

The high usage of storage in cloud, ensuring the privacy and security of information stored in the cloud has come up with a difficult concern. One approach to address this issue is the use of techniques which are encrypted, where data is already encrypted being uploaded to the storage of cloud. However, traditional encryption methods hinder the ability to find and retrieve particular information from the secured information, as the information needs to be decrypted first. This limitation hampers the usability and efficiency of storage of cloud systems. To overcome the challenge, this research says a novel approach for keyword search on secured information in storage of cloud using an AES approach. The algorithm of AES is a maximum adopted symmetric encryption method familiar for efficiency and robustness. By leveraging the AES encryption approach, the solution assures the confidentiality of information stored while enabling efficient keyword-based search operations without the need for decryption. The proposed approach utilizes a combination of cryptographic techniques such as AES encryption and index structures to access efficient information findings on the secured information. A secure index is created during encryption process that enables for potent retrieval of encrypted data related to specific keywords. The encrypted data remains confidential, as only authorized users possess the necessary decryption keys to retrieve the plaintext information. During data outsourcing, data owner can set the access permission based on their user identity. Users should have specific identity with decryption key for accessing data from cloud. Here data manager can also provide particular period for accessing information from cloud. The results demonstrate that the keyword findings on secured information in storage of using the AES approach achieve a balance between data privacy and search functionality. The solution offers an effective means to securely store and retrieve data

关键词： Cloud storage

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：