检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Pasunuri, Raghunadh Bhukya, Sreedhar Shaik, Kashim Dept. of CSE AIML Malla Reddy Engineering College Secunderabad Hyderabad India Department of Computer Science and Engineering Sreenidhi Institute of Science and Technology Hyderabad Pakistan Department of Computer Science and Engineering Sreenidhi Institute of Science and Technology India

Cloud computing has revolutionized Information technology (IT) orientation and became preferred choice for enterprises across the globe. Cloud infrastructure is dynamically scalable and flexible in rendering computing resources in pay as you go fashion. Due to large workloads and consumer base across the globe, it is indispensable to optimize cloud resource utilization for efficiency. Balancing of workload through efficient scheduling can have huge impact on resource optimization. However, in presence of changing workloads, resource heterogeneity and Service Level Agreements (SLAs), the runtime of cloud infrastructure is very dynamic in nature. There are large number of scheduling algorithms found in the literature. However, existing methods largely focused on minimizing execution time of tasks. However, considering workload balancing along with efficient scheduling of tasks is the less explored area in cloud research. Besides, there is need for improving Quality of Service (QoS) of existing methods. Towards this end, we proposed a hybrid algorithm combining an evolutionary approach and fuzzy logic for efficient scheduling and load balancing in cloud environments. The algorithm is named Fuzzy Genetic Algorithm for Load Balancing (FGA-LB). It exploits fuzzy inference along with evolutionary approach for scheduling decision making. We have built a CloudSim based framework for empirical study. Experimental results revealed that the proposed algorithm minimizes task execution time and balances workload outperforming many existing methods. © 2023, The Authors. All rights reserved.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Biological age estimation from ECG using Artificial Intelligence approaches

Biological age estimation from ECG using Artificial Intellig...

引用

Biomedical engineering Conference (JIBEC), Jordanian International

作者： Jana Sleiman Mohamad Daher Mohamad Khalil Ahmad Diab Abdallah Kassem Computer and Communications Engineering Lebanese University Tripoli Lebanon Dep. of Computer Science/Dep. of Computer Science & Information Technology Faculty of Science/Faculty of Applied Sciences & Technology Tripoli Lebanon Electrical Engineering Lebanese University Tripoli Lebanon Biomedical Engineering Lebanese International University Beirut Lebanon ECCE Dept. Faculty Of Engineering Notre Dame University Zouk Mosbeh Lebanon

ISBN: (数字)9798331539542

ISBN: (纸本)9798331539559

This paper explores the application of Artificial Intelligence (AI) techniques in healthcare, specifically focusing on electrocardiogram (ECG) data analysis and biological age estimation. The study begins with an overview of ECG as a diagnostic tool and discusses the integration of Deep Learning (DL) models, particularly Convolutional Neural Networks (CNNs), in healthcare for various applications. Previous studies reviewed in this context consistently identify CNNs as the superior model for ECG analysis and prediction tasks. The primary research investigates the use of Machine Learning (ML) algorithms to estimate biological age from ECG data, employing metrics such as Mean Absolute Error (MAE) and variance to evaluate model performance. Subsequently, DL models are implemented and compared, demonstrating superior accuracy in estimating the biological age of new patients. While both ML and DL approaches were initially explored, this paper primarily focuses on deep learning methodologies due to their demonstrated superiority in healthcare applications. The findings highlight the efficacy of deep learning over traditional ML methods, underscoring its potential for enhancing diagnostic accuracy and personalized patient care. For instance, the most accurate deep learning model, the Convolutional Neural Network (CNN), achieved a Mean Absolute Error (MAE) of 1.49 and an R 2 score of 0.53, whereas the best-performing traditional ML model, Random Forest, achieved an MAE of 1.54 and an R 2 score of 0.55. These results clearly indicate the advantage of deep learning models in capturing complex patterns in ECG data, leading to more precise and reliable estimations of biological age.

关键词： Deep learning Maximum likelihood estimation Accuracy Data analysis Biological system modeling Medical services Electrocardiography Data models Convolutional neural networks Random forests

来源：评论

学校读者我要写书评

暂无评论

Bi-Core Photonic Crystal Fiber Based Chemical Sensor in THz Frequency Regime

Bi-Core Photonic Crystal Fiber Based Chemical Sensor in THz ...

引用

Workshop on Recent Advances in Photonics (WRAP)

作者： Vishal Chaudhary Kirti Dalal Asbah Masih Vijay Shanker Chaudhary Dept. of Electronics and Communication Engineering Delhi Technological University Delhi India Dept. of Computer Science and Engineering Galgotias College of Engineering and Technology UP India

ISBN: (数字)9798350340839

ISBN: (纸本)9798350340846

This study proposes a chemical sensor based on bi-core photonic crystal fiber (BC-PCF) in the terahertz (THz) frequency regime with a novel construction that has two solid cores separated apart by a vertical elliptical hole filled with various chemicals such as ethanol, benzene, and water. Because of the ability that BC-PCF has to transmit light across all wavelengths, the solid core architecture is chosen for this sensor. The proposed sensor is able to attain extraordinarily high sensitivity because of the unique arrangement of circular and elliptical holes, which offers a substantial advantage over existing structures. The principle on which the proposed chemical sensor operates involves the coupling of modes between the two fiber cores. The finite element method (FEM) based COMSOL Multiphysics software has been used to comprehensively analyse and simulate the sensor's performance. Remarkably, the sensor is able to achieve a high sensitivity of 725833.34 nm/RIU with a fiber length of 0.2 meter. The use of this BC-PCF chemical sensor in the industrial sector is mainly aimed at efficiently identifying and detecting toxic chemicals.

关键词： Couplings Optical fiber sensors Sensitivity Toxic chemicals Photonic crystals Solids Chemical and biological sensors Software Robustness Finite element analysis

来源：评论

学校读者我要写书评

暂无评论

Trusted Federated Learning Framework for Attack Detection in Edge Industrial Internet of Things

Trusted Federated Learning Framework for Attack Detection in...

引用

International Conference on Fog and Mobile Edge Computing (FMEC)

作者： Mahendra Pratap Singh Ashutosh Anand Lakshmi Aashish Prateek Janaswamy Sudarshan Sundarrajan Maanak Gupta Dept. of Computer Science and Engineering National Institute of Technology Karnataka Surathkal India Dept. of Computer Science Tennessee Technological University TN USA

The edge Industrial Internet of Things (IIoT) is highly vulnerable to attacks due to the vast number of connected devices and the lack of security features. Attacks in edge IIoT can lead to significant damage, including data theft, malfunctioning, and privacy breaches. Federated Learning (FL) is a promising approach to detecting attacks by utilizing edge devices' collective intelligence. FL allows devices to collaboratively learn from multiple devices' data without centralized sharing, which preserves data privacy and reduces communication costs. However, FL has vulnerabilities that can compromise model accuracy, privacy, and security. Trusted FL is essential for collaboration among multiple edge IIoT devices while preserving data privacy and security. Trust plays a critical role in the success of FL, as edge IIoT devices must trust that the models are accurately learning and that their data is protected. To address this, we propose an FL framework that uses Federated Averaging (FedAvg) and Convolutional Neural Network (CNN) to detect attacks in edge IIoT. We also propose a mechanism to calculate trust for appropriate edge IIoT device selection by measuring each device's (a.k.a client's) performance during model training. The proposed edge IIoT device selection method, client selection, can fairly select clients for model training and improve trust in the entire system. Although the proposed FL approach does not outperform the centralized ResNet-18 CNN model on experimental analysis, improving its performance can be a promising solution for detecting attacks in edge IIoT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Monitoring, Tracking and Fighting Pandemics using Drone-based Artificial Intelligence in IoT

Monitoring, Tracking and Fighting Pandemics using Drone-base...

引用

International Conference on Advanced Computing and Communication Systems (ICACCS)

作者： K. Praveen Kumar S. Sangeetha T Rajesh Kumar Bhuvaneswari R D. Rasi Mahaveerakannan R Department of Information Technology Kakatiya Institute of Technology and Science Warangal Dept. Of Information Technology Kakatiya Institute of Technology and Science Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Chennai Tamil Nadu Computer Science and Applications D. K. M. College for Women (Autonomous) Vellore Department of Computer Science and Engineering Sri Krishna College of Engineering and Technology Coimbatore

The world has altered since the World Health Organization (WHO) designated (COVID-19) a worldwide epidemic. Everything in society, from professions to routines, has shifted to accommodate the new reality. The World Health Organization warns that future pandemics of infectious diseases are likely and that people should be ready for the worst. Therefore, this study presents a framework for tracking and monitoring COVID-19 using a Deep Learning (DL) perfect. The suggested framework utilises UAVs (such as a quadcopter or drone) equipped with artificial intelligence (AI) and the Internet of Things (IoT) to keep an eye on and combat the spread of COVID-19. AI/IoT for COVID-19 nursing and a drone-based IoT scheme for sterilisation make up the bulk of the infrastructure. The proposed solution is based on the use of a current camera installed in a face-shield or helmet for use in emergency situations like pandemics. The developed AI algorithm processes the thermal images that have been detected using multi-scale similar convolution blocks (MPCs) and Res blocks that are trained using residual learning. When infected cases are detected, the helmet's embedded Internet of Things system can trigger the drone system to intervene. The infected population is eradicated with the help of the drone's sterilisation process. The developed system undergoes experimental evaluation, and the findings are presented. The developed outline delivers a novel and well-organized arrangement for monitoring and combating COVID-19 and additional future epidemics, as evidenced by the results

关键词： COVID-19 Head Pandemics Convolution Organizations Safety Internet of Things

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach for Recognizing Malayalam Sign Language Gestures

A Deep Learning Approach for Recognizing Malayalam Sign Lang...

引用

International Conference on ent Computing and Control Systems (ICICCS)

作者： Kevin Issac Esther Daniel Bright Gee Varghese Dept. of Computer Science & Engineering Karunya Institute of Technology and Sciences Coimbatore India Dept. of Computer Science Maharishi International University Fairfield USA

Communication involves the sharing or exchanging of information, ideas, and emotions, which requires a common language between individuals. For those with speech impairments, sign language serves as a means of communication. The lack of understanding of sign language can create difficulties in communication between individuals with speech impairments and those without, posing a significant challenge. One solution to this challenge is to create a machine learning-based model that recognizes various sign language motions and converts them into a shared language. This model can be trained to benefit those seeking to interact and communicate with individuals with speech impairments. Although Sign Language Recognition systems exist, they are limited in the number of languages that can be recognized. This article introduces a real-time Sign Language Recognition system that employs transfer learning with TensorFlow and utilizes a webcam for the purpose of detecting and interpreting sign language gestures specific to the Malayalam language.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Efficient Big Data Gathering in Wireless Sensor Network using Reconfigurable Node Distribution Algorithm 4

An Efficient Big Data Gathering in Wireless Sensor Network u...

引用

4th International Conference on Cognitive Computing and Information Processing, CCIP 2022

作者： Mallikarjunaswamy, S. Basavaraju, N.M. Sharmila, N. Mahendra, H.N. Pooja, S. Deepak, B.L. JSS Academy of Technical Education Dept of Electronics and Communication Engineering Bengaluru India JSS Academy of Technical Education Bengaluru India JSS Science and Technology University Mysuru India K S Insitute of Technoloy Dept of Electronics and Communication Engineering Bengaluru India R.L.Jalappa Institute of Technology Dept of Computer Science and Engineering Kodigehalli India

ISBN: (数字)9781665456487

ISBN: (纸本)9781665456487

In recent days, communication process is performed in wireless sensor networks (WSNs). The WSN is effectively reconstructed and accurately communicates the information to each corner of high-density nodes of cellular area. The main objective of this paper is to improve the data gathering of all sensor nodes and efficiently optimize the energy utilisation of each node in WSNs. The cluster head is identified in highly node distributed WSNs. The sink nodes during big data gathering are effectively utilized in WSNs with the help of Reconfigurable Node Distribution Algorithm (RNDA). The proposed algorithm procedure has been followed to address the big data gathering location in WSNs and mobilize the sink nodes in optimized location for proper communication in WSNs. The performance analysis and comparison between proposed and existing methods have been carried out with respect to energy efficiency, packet delivery ratio, packet ratio and transmission energy. The simulation result shows that the proposed method reduces energy consumption by 2 % in high density sensor node network communication process. The proposed method effectively selects the cluster head in WSNs to enhance the throughput packet delivery ratio and transmission energy. © 2022 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

How does promoting the minority fraction affect generalization? A theoretical study of the one-hidden-layer neural network on group imbalance

arXiv

引用

arXiv 2024年

作者： Li, Hongkang Zhang, Shuai Zhang, Yihua Wang, Meng Liu, Sijia Chen, Pin-Yu The Dept. of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute United States New Jersey Institute of Technology United States The Dept. of Computer Science and Engineering Michigan State University United States IBM Research United States

Group imbalance has been a known problem in empirical risk minimization (ERM), where the achieved high average accuracy is accompanied by low accuracy in a minority group. Despite algorithmic efforts to improve the minority group accuracy, a theoretical generalization analysis of ERM on individual groups remains elusive. By formulating the group imbalance problem with the Gaussian Mixture Model, this paper quantifies the impact of individual groups on the sample complexity, the convergence rate, and the average and group-level testing performance. Although our theoretical framework is centered on binary classification using a one-hidden-layer neural network, to the best of our knowledge, we provide the first theoretical analysis of the group-level generalization of ERM in addition to the commonly studied average generalization performance. Sample insights of our theoretical results include that when all group-level co-variance is in the medium regime and all mean are close to zero, the learning performance is most desirable in the sense of a small sample complexity, a fast training rate, and a high average and group-level testing accuracy. Moreover, we show that increasing the fraction of the minority group in the training data does not necessarily improve the generalization performance of the minority group. Our theoretical results are validated on both synthetic and empirical datasets, such as CelebA and CIFAR-10 in image classification. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Attacks Detection in 6G Wireless Networks using Machine Learning

Attacks Detection in 6G Wireless Networks using Machine Lear...

引用

International Conference on computer and Communication engineering, ICCCE

作者： Mamoon M. Saeed Rashid A. Saeed Abdulguddoos S. A. Gaid Rania A. Mokhtar Othman O. Khalifa Zeinab E. Ahmed Department of Communications and Electronics Engineering Faculty of Engineering University of Modern Sciences (UMS) Yemen Department of Computer Engineering College of Computers and Information Technology Taif University P.O. Box 11099 Taif Saudi Arabia Department of Communication & Computer Engineering Faculty of Engineering & Information Technology Taiz University Taiz Yemen Department of Electrical and Computer Engineering International Islamic University Malaysia Malaysia Libyan Center for Engineering Research and Information Technology Bani Waleed Libya Electrical and Computer Engineering Dept International Islamic University Malaysia Malaysia Computer Engineering Dept University of Gezira Sudan

Unlike the fifth generation (5G), which is well recognized for network cloudification with micro-service-oriented design, the sixth generation (6G) of networks is directly tied to intelligent network orchestration and management. The Attacks Detection in 6G (AD6Gs) wireless networks created by this research uses a Machine Learning (ML) algorithm. The pre-processing stage of the ML-AD6Gs process is the initial step. The second stage involves the feature selection approach. Correlation Feature Selection algorithm (CFS) is used to implement the suggested hybrid strategy. It selects the best subset feature and reduces dimensionality for each independent analyses of the dataset CICDDOS2019. The voting average method is used as an aggregation step, and two classifiers—Random Forest (RF) and Support Vector Machine (SVM)—are modified to be used as ML Algorithms. The proposed method shown an outperformed the existing classification method. The accuracy was 99.9%% for CICDDOS2019 dataset with a false alarm rate of 0.00102

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Graph-Generative Network-based PV Condition Monitoring Systems

Unsupervised Graph-Generative Network-based PV Condition Mon...

引用

IEEE General Meeting Power& Energy Society

作者： Sarah Allahmoradi Shahabodin Afrasiabi Xiaodong Liang Mousa Afrasiabi Jamshid Aghaei Chi Yung Chung Dept. Electrical and Computer Engineering University of Saskatchewan Saskatoon Canada Department of Electrical Engineering School of Energy Systems Lappeenranta University of Technology Lappeenranta Finland Department of Electrical and Computer Engineering The Hong Kong Polytechnique University Hong Kong China

ISBN: (数字)9798350381832

ISBN: (纸本)9798350381849

Condition monitoring plays a pivotal role in the photovoltaic (PV) system’s operation. To overcome issues in conventional PV condition monitoring, in this paper, an unsupervised graph-generative network-based PV condition monitoring system is proposed by considering Gaussian/non-Gaussian noises. The designed network has the ability to handle an imbalanced dataset and high dimensional signals, establish the correlation between time-varying signals in PV systems, and learn spatial-temporal features. The proposed system is validated through an experimental dataset by considering seven abnormal conditions, including PV array faults, PV control system faults, and grid faults. The proposed method appears to be effective under Gaussian/non-Gaussian noises with an accuracy higher than 98%. The superiority of the proposed graph-generative network is demonstrated by comparing with well-known deep- and shallow-based PV condition monitoring systems with 5%- 30% improvements in terms of accuracy and reliability.

关键词： Condition monitoring Photovoltaic systems Accuracy Correlation Noise Probabilistic logic Control systems Robustness Time-varying systems Monitoring

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：