检索结果-内蒙古大学图书馆

26th International Conference on computer and Information Technology, ICCIT 2023

作者： Rahman, Md Mokhlesur Abdulhamid, Alhassan Kabir, Sohag Military Institute of Science and Technology Department of Computer Science and Engineering Bangladesh University of Bradford School of Computer Science AI and Electronics United Kingdom

ISBN: (纸本)9798350359015

The Internet of Things (IoT) has improved our lives through various applications such as home automation, smart city monitoring, environmental monitoring, intelligent farming, and a host of others. IoT is increasingly being used for environmental monitoring to prevent fire incidents and other environmental hazards. However, for IoT systems to function effectively in preventing fire incidents, they must operate in a safe, reliable, and dependable manner. The intelligent sensors and devices that constitute the system are prone to different types of failures, which can lead to unsafe or dangerous conditions. Failure of a fire prevention system can pose significant risks to Health, Safety, and the Environment (HSE). To address these concerns, it is essential to understand how component failures can contribute to the overall system failure. This paper adopts Fault Tree Analysis, a widely used framework for failure behaviour analysis in other safety-critical domains, to qualitatively analyse an intelligent fire detection system in an industrial setting. The analysis outlines the ways in which the system can fail and the necessary prevention mechanism to guard against undesired system failure. © 2023 IEEE.

关键词： fault tree analysis Internet of Things smart fire control system system failure analysis

来源：评论

学校读者我要写书评

暂无评论

Impact of Engineers Without Borders on Students and Society

Impact of Engineers Without Borders on Students and Society

引用

2023 IEEE Technology and engineering Management Conference - Asia Pacific, TEMSCON-ASPAC 2023

作者： Pavani, Dhanni Reddy, Ch Pravalika Naik, Santosh Madeva Hyderabad Institute of Technology and Management Computer Science with Ai & Ml Hyderabad India Hyderabad Institute of Technology and Management Computer Science with Iot Hyderabad India Hyderabad Institute of Technology and Management Mechanical Engineering Hyderabad India

ISBN: (纸本)9798350384659

The largest and fastest expanding field is engineering. Engineers are regarded as the foundation of society. In the world of engineering, skills are essential. The Indo-Universal Collaboration for engineering Education (IUCEE) and Engineers without Borders (EWB) are non-profit organizations that have a significant impact on students' skill development. Both technical and non-technical skills are developed by IUCEE-EWB. The study presented in this paper focused on the members of the IUCEE-EWB HITAM student chapter. Under the umbrella of IUCEE-EWB, numerous activities are carried out to help students enhance their talents. Numerous projects, activities, and events are held to aid students in developing their talents. By participating in these activities actively, students can improve their skills. Students of the IUCEE EWB-HITAM student chapter are encouraged to take courses as well as to compete in a variety of local, national, and worldwide activities. With the abilities acquired through IUCEE-EWB, students excelled in numerous events and won praise from many. The IUCEE EWB helped students achieve new heights. © 2023 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Generalized Learning of Coefficients in Spectral Graph Convolutional Networks 15

Generalized Learning of Coefficients in Spectral Graph Convo...

引用

15th IEEE International Conference on Knowledge Graph, ICKG 2024

作者： Coskun, Mustafa Grama, Ananth Koyuturk, Mehmet Ankara University Department of Ai and Data Engineering Ankara Turkey Purdue University Department of Computer Science IN United States Case Western University Department of Data and Computer Science OH United States

ISBN: (纸本)9798331508821

Spectral Graph Convolutional Networks (GCNs) have gained popularity in graph machine learning applications due, in part, to their flexibility in specification of network propagation rules. These propagation rules are often constructed as polynomial filters whose coefficients are learned using label information during training. In contrast to learned polynomial filters, explicit filter functions are useful in capturing relationships between network topology and distribution of labels across the network. A number of algorithms incorporating either approach have been proposed;however the relationship between filter functions and polynomial approximations is not fully resolved. This is largely due to the ill-conditioned nature of the linear systems that must be solved to derive polynomial approximations of filter functions. To address this challenge, we propose a novel Arnoldi orthonormalization-based algorithm, along with a unifying approach, called G-Arnoldi-GCN that can efficiently and effectively approximate a given filter function with a polynomial. We evaluate G-Arnoldi-GCN in the context of multi-class node classification across ten datasets with diverse topological characteristics. Our experiments show that G-Arnoldi-GCN consistently outperforms state-of-the-art methods when suitable filter functions are employed. Overall, G-Arnoldi-GCN opens important new directions in graph machine learning by enabling the explicit design and application of diverse filter functions. Code link: https://***/mustafaCoskunAgu/GArnoldi-GCN © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

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

Methodological Insights Into Protein Clustering Using BERT & RoBERTa

Methodological Insights Into Protein Clustering Using BERT &...

引用

IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)

作者： Shashwat Saini Jayavrinda Vrindavanam Subhash Mondal Computer Science and Engineering (AI & ML) Dayananda Sagar University Bengaluru Karnataka India

ISBN: (数字)9798350385922

ISBN: (纸本)9798350385939

Proteins are present in all living organisms, and understanding their processes is vital. Protein databases such as SWISS-PROT include curated information on only 570,000 protein sequences, representing a fraction of the 250 million known evidential and predicted sequences; it becomes crucial to cluster proteins into similar groups. This research explores the application of two transformer architectures, BERT and RoBERTa in clustering proteins in the supervised prediction of Gene Ontology (GO) annotations. The detailed methodology for both the pre-training and fine-tuning processes, as well as results that showcase RoBERTa outperforming BERT in the context of protein clustering, on performance metrics of accuracy and loss. Operating under constrained computational resources, the deployed model exhibits strong performance and highlight the robustness of methodology in protein clustering within resource constraints. This study not only contributes to the understanding of protein clustering but also signifies the potential of transformer models to handle biological data.

关键词： Proteins Training Analytical models Annotations Biological system modeling Computational modeling Ontologies

来源：评论

学校读者我要写书评

暂无评论

Optimizing Regulatory Compliance in Supply Chains with Blockchain and Gaussian Process Regression 2

Optimizing Regulatory Compliance in Supply Chains with Block...

引用

2nd IEEE International Conference on IoT, Communication and Automation Technology, ICICAT 2024

作者： Tulasiram, D. Jebaseeli, S. Kanmani Adnan, Myasar M. Madhavi, Arelli Varshney, Neeraj Nandhini, T.J. CMR College of Engineering & Technology Department of CSE India New Prince Shri Bhavani College of Engineering and Technology Department of IT Tamil Nadu Chennai600073 India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq GRIET Bachupally Department of AI&ML Telangana Hyderabad India GLA University Department of Computer Engineering & Applications Mathura India Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350368109

Increased regulation of the supply chain is another important issue of concern to industries in distinct countries as they struggle to implement the regulation in a network setting. This paper aims to explore ways to improve regulatory compliance through the application of the blockchain and machine learning model, namely Gaussian process regression. Blockchain is an accurate and permanent record-keeping system that can be applied to track the flow of items and associated activities in the supply chain. Compliance can also be enforced, and through smart contracts, analyses of various parameters such as obligations can be monitored and adjusted automatically through GPR which involves the analysis of data from systems that use blockchain to model compliance risks and predict compliance issues. Thus, using the above-mentioned technologies, a company can prevent compliance failures, meet the necessary standards and set up a constant process of improvement in the supply chain area. This research specifically defines the theoretical foundations, application, and advantages of blockchain and GPR in enhancing the compliance of supply chains with the regulations in this work. In this approach, case-study and use of examples show how this approach works in handling compliance issues in several industries. © 2024 IEEE.

关键词： Smart contract

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

Enhancing Alzheimer's Disease Diagnosis Through Deep Learning-Leveraging VGG-16 Architecture and Adaptive Boosting 5

Enhancing Alzheimer's Disease Diagnosis Through Deep Learnin...

引用

5th International Conference on Image Processing and Capsule Networks, ICIPCN 2024

作者： Irrigisetty, Harshavelu Madhavi, K. Reddy Avanija, J. Thokala, Rishi Reddy Varma, K. S. S. Rishi Sree Vidyanikethan Engineering College Department of CSE Tirupati India Department of AI&ML Tirupati India School of Computing Tirupati India SRM Institute of Science and Technology Department of CSE Chennai India

ISBN: (纸本)9798350367171

The key to early intervention and patient care with Alzheimer's disease is early detection. The World Health Organization estimates that 50 million people worldwide suffer from dementia, with 60-70 % of cases being Alzheimer's disease (AD). Moreover, the WHO projects that the number of people affected by AD will be nearly tripled by the year 2050, thus, the development of effective detection and management strategies. Our Research suggests a complete method that combines Convolutional Neural Networks (CNNs) with transfer learning using the VGG16 architecture, on the one hand, and Adaptive Boosting on the other, in order to improve the accuracy. The dataset includes NonDemented, VeryMildDemented, MildDemented, and ModerateDemented classes which makes the VGG16 model suitable for extraction of features and classification after the preprocessing steps, such as image resizing, conversion to arrays and pixel value normalization, are performed. From the problems faced in the earlier AD detection methodologies we use CNNs, transfer learning and adaptive boosting to improve the task performance. In conclusion, the combination of automated computational methods and sophisticated algorithms such as CNNs and AdaBoost is a progressive approach in AD detection. It provides services like efficiency, consistency, and improved diagnosis that can be applied to the patient care and the healthcare management. © 2024 IEEE.

关键词： Convolutional neural networks

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：