检索结果-内蒙古大学图书馆

Investigations on optimizing performance of the distributed computing in heterogeneous environment using machine learning technique for large scale data set

引用

Materials Today: Proceedings 2023年 80卷 2976-2982页

作者： Pandey, Rajeev Silakari, Sanjay Department of Computer Science & Engineering University Institute of Technology RGPV Madhya Pradesh Bhopal India

Enforcing admired machine learning approaches to huge data enhanced novel issues for researchers. Conventional libraries could not suitably fulfil the requirement of complex model with wide variety of data and system parameters. Therefore new methodologies are required performing the computation on more than one machine over distributed environment. Some distributed frameworks on huge data such as MapReduce and TensorFlow have been deployed to solve various machine learning problems in heterogeneous distributed environment. The objective of this paper is providing a wide variety of useful information about platforms, approaches, problems, datasets, and optimization approaches in distributed systems. So researchers have been used the beneficial information to develop new approaches for efficient machine learning. This paper also covers the various formats of data like structured, semi structured and unstructured big data. A brief review of previous works is also represented in text and tabular format to provide motivation to the researchers for developing new paradigm of distributed computing environment. © 2021

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Grid-Side Current Improvement With Direct Digital Control and Capacitor Voltage Feedforward to Mitigate Distorted Grid Currents for 3Φ3W LCL Grid-Connected Inverter Under Distorted Grid Voltages

IEEE Open Journal of Power Electronics

引用

IEEE Open Journal of Power Electronics 2024年 5卷 37-49页

作者： Wu, Tsai-Fu Chan, Ching-Chih Chang, Yun-Hsiang Chiu, Jui-Yang Hung, Chien-Chih Chuang, Tzu-Hsien National Tsing Hua University Department of Electrical Engineering Hsinchu300044 Taiwan National Tsing-Hua University College of Electrical Engineering and Computer Science Hsinchu300044 Taiwan

A three-phase three-wire LCL grid-connected inverter is usually used as an interface between renewable-energy sources and grid. However, grid voltage is always distorted and results in grid-current distortion when there is no control at the filter-capacitor current. This article presents the grid-current improvement with inverter-side-current direct digital control and capacitor voltage feedforward (CVF) for the grid-connected inverter under distorted grid voltages. With the inverter-side current feedback, the simple direct digital control can cover inductance variation and determine the control laws to track inverter-side inductor current, achieving robustness. A hysteresis repetitive predictor with finite impulse response low-pass filter and compensator term is introduced to the CVF loop which can stabilize the system and compensate the distorted grid current. The virtual impedance method is adopted to confirm the stability when the filter inductances drop and control parameters vary with the inductor current. Simulated and experimental results from 12 kW inverter are used to verify the theoretical analyses and discussions. © 2020 IEEE.

关键词： Inductance

来源：评论

学校读者我要写书评

暂无评论

Skin Cancer Classification Using a Quad Ensemble 2

Skin Cancer Classification Using a Quad Ensemble

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Blaise, Don Bosco Manoj Kumar, G. Jeswanth, S. Bhuvaneswari, G. Rajesh, C. Bharathi, A. Saveetha Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India Saveetha Engineering College Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India

ISBN: (纸本)9798331505745

Skin cancer is a highly prevalent form of cancer that frequently arises from the proliferation of abnormal cells on the skin. Early detection is crucial for effective treatment and better prognosis. Traditional diagnostic methods face challenges in accuracy and timeliness, making automated techniques a valuable tool in disease identification. This article proposes a deep learning framework based on an ensemble, aimed at enhancing the detection and classification of various types of cancer on the skin. The approach integrates four optimized Convolutional Neural Networks (CNNs) using a weighted average ensemble technique. This model addresses common challenges in data preparation, model selection, and overfitting through comprehensive preprocessing and hyperparameter tuning, resulting in improved accuracy and robustness compared to existing systems. © 2025 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 Compact Home-Based Training System for Preventing Frailty Using a Mapping Model and Cross-Dataset Transfer Learning

IEEE Journal of Selected Areas in Sensors

引用

IEEE Journal of Selected Areas in Sensors 2025年 2卷 1-8页

作者： Liu, Lizheng Hu, Hsuan Yeh, Shih-Ching Wu, Eric Hsiao-Kuang Chen, Chun-Chuan Fudan University Department of Academy of Engineering and Technology Shanghai200437 China National Central University Department of Computer Science and Information Engineering Taoyuan320 Taiwan National Central University Department of Biomedical Sciences and Engineering Taoyuan320 Taiwan

Frailty is becoming a more serious issue as the population ages. Numerous studies have shown that exercise can effectively slow the development of frailty. Compared with vigorous exercise, Baduanjin (BDJ), a kind of traditional Chinese Qigong with eight simple movements, is more suitable for frailty patients. BDJ has been used to train frailty patients by physical therapists. To provide an enhanced training method, we designed a lightweight family-based frailty training system via a virtual BDJ coach. To achieve a compact system, we use a webcam as the main device. The system also supports the Kinect framework. We use pose estimation and motion recognition methods to analyze the user's movements. In addition, a novel transfer learning method is proposed. We designed a mapping model called "Skeleton Mapnet" to convert skeletal data from different frameworks. This method enables datasets from different frameworks to share classification models. It can also mix skeletal data from different frameworks to solve the lack of webcam datasets. Such a design allows the system to be easily ported into other platforms. In addition, the system is also suitable for the use of the artificial intelligence of things. Our design ensures that frailty patients can easily learn and operate the system. © 2024 The Authors.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Impact of IoT Data Integration on Real-Time Analytics for Smart City Management 10

Impact of IoT Data Integration on Real-Time Analytics for Sm...

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Lakshmi, D. Jeyarani, J. Suguna, R. Muneeshwari, P. Valantina, G.Mary Jayaraman, Suganya Panimalar Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India Care College of Engineering Department of Electronics and Communication Engineering Tamil Nadu Trichy India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai Tamil Nadu Avadi India Rajalakshmi Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Computer Science and Engineering Tamil Nadu Chennai India Adhiparasakthi Engineering College Department of Electronics and Communication Engineering Tamil Nadu Melmaruvathur India

ISBN: (纸本)9798350353068

The paper in illustration will emphasize the necessity for an IoT big data and analytics on time fusion as a futuristic smart city management approach. The framework deals with the main problems observed in data assimilation, analytics, security and scalability. As a result, cities will enjoy the services and operations utilization of the urban data with the precision. Our approach is based upon the data collection with the use of the edge technologies, preprocessing, integration, and analysis of the data resulting in the creation of the tools of machine learning and the adoption of interoperability standards. The results have especially brought to the limelight the fantastic performance of the live analytics pipeline when considered as a whole, and the impressive throughput of 5,000 events per second alongside the very low latency of 50 milliseconds, indicating how the urban information flow is processed in the blink of an eye. With AI therein creating the precision rate of 88.7%-95.2%, which therefore means this level of an urban situation can pronounce a traffic congestion and air quality fluctuations. The situation where security systems that involve encryption, access controls, and privacy-preserving protocols, among other mechanisms, have been used for the management of urban data in a safe manner, away from any unauthorized people and hackers, is factual. For the sake of achieving scalability, the replacement of certain bottlenecks is applied in the system by means of horizontal scaling and optimal performance procedures assisting smart cities handle their increasing quantity of data. Usually the results are factorized to bring out the fact that the particular methodology is strong and thus can be used in real practice to transform and enhance urban resilience level. © 2024 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

New Radio-Frequency Liquid Permittivity Measurement System Using Filter-Based Microfluidic Sensor

引用

IEEE Sensors Journal 2023年第12期23卷 12785-12795页

作者： Nguyen, Tuan-Khanh Tseng, Chao-Hsiung National Taiwan University of Science and Technology Department of Electronic and Computer Engineering Taipei106335 Taiwan

A new radio-frequency (RF) liquid permittivity measurement system using a filter-based microfluidic sensor is proposed in this article. Integrating the filter-based sensor with an RF source, a power divider, and a gain/phase detector (GPD) can form a new permittivity measurement system without using a bulky and expensive vector network analyzer (VNA) to acquire measured data. Since two coupled resonators with a strong coupling synthesize the filter-based sensor, it can provide a stronger electric-field concentration in the sensing area and improve the sensor's sensitivity. The 8- μ L water-ethanol mixtures with ethanol volume fractions (EVF) ranging from 10% to 90% in 10% increments are used as the test liquids to evaluate the proposed sensor and system. Compared with the measured results using the commercial dielectric probe kit, the maximum errors of r' and r using the filter-based sensor with a VNA are -4.34% and 13.24%, respectively. At the same time, r' andr errors are 8.28% and 14%, respectively, using the proposed permittivity measurement system. Since the proposed permittivity measurement system can flexibly synthesize the sensing area size, control the electric-field intensity, and get rid of a VNA, it makes it easier to satisfy the requirements of various microfluidic sensing scenarios. © 2001-2012 IEEE.

关键词： Microfluidics

来源：评论

学校读者我要写书评

暂无评论

Migraine Categorization using the Scatter Search and Random Forest Classifier

Migraine Categorization using the Scatter Search and Random ...

引用

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

作者： Mary Litta David, K. Sharmili, Vengala Venkata Sai Babu, Tina Nair, Rekha R Dayananda Sagar University School of Engineering Department of Computer Science & Engineering Bengaluru India Alliance University Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350313413

Migraine attacks manifest through recurring episodes of intense headaches accompanied by autonomic nervous system dysfunction indicators, leading to various symptoms. Automatic classification of various classes of migraine is very much essential for the secondary opinion. This study categorizes a migraine dataset into seven distinct classes using features obtained through scatter search. To address the class balance issue, Synthetic Minority Oversampling Technique (SMOTE) was applied. Further, the optimal features were selected using Scatter Search. Subsequently, classification was executed using the Random Forest (RF) classifier. The proposed model was tested on a migraine dataset containing 400 instances and 24 features, resulting in a feature reduction of around 50%. Remarkably, the achieved accuracy of 98.26% surpassed that of the raw dataset. As a result, the proposed model outperforms existing methodologies, potentially offering an additional perspective for medical professionals. © 2023 IEEE.

关键词： classification feature reduction migraine search

来源：评论

学校读者我要写书评

暂无评论

An Eco-Friendly Approach for Reducing Carbon Emissions in Cloud Data Centers

引用

computers, Materials & Continua 2022年第8期72卷 3175-3193页

作者： Mohammad Aldossary Hatem A.Alharbi Department of Computer Science College of Arts and SciencePrince Sattam bin Abdulaziz UniversityAl-KharjSaudi Arabia Department of Computer Engineering College of Computer Science and EngineeringTaibah UniversityMadinahSaudi Arabia

Based on the Saudi Green initiative,which aims to improve the Kingdom’s environmental status and reduce the carbon emission of more than 278 million tons by 2030 along with a promising plan to achieve netzero carbon by 2060,NEOM city has been proposed to be the“Saudi hub”for green energy,since NEOM is estimated to generate up to 120 Gigawatts(GW)of renewable energy by ***,the Information and Communication Technology(ICT)sector is considered a key contributor to global energy consumption and carbon *** data centers are estimated to consume about 13%of the overall global electricity demand by ***,reducing the total carbon emissions of the ICT sector plays a vital factor in achieving the Saudi plan to minimize global carbon ***,this paper aims to propose an eco-friendly approach using a Mixed-Integer Linear Programming(MILP)model to reduce the carbon emissions associated with ICT infrastructure in Saudi *** approach considers the Saudi National Fiber Network(SNFN)as the backbone of Saudi Internet ***,we compare two different scenarios of data center *** first scenario considers a traditional cloud data center located in Jeddah and Riyadh,whereas the second scenario considers NEOM as a potential cloud data center new location to take advantage of its green energy ***,we calculate the energy consumption and carbon emissions of cloud data centers and their associated energy *** that,we optimize the energy efficiency of different cloud data centers’locations(in the SNFN)to reduce the associated carbon emissions and energy *** results show that the proposed approach can save up to 94%of the carbon emissions and 62%of the energy cost compared to the current cloud physical *** savings are achieved due to the shifting of cloud data centers from cities that have conventional energy sources to a city that has rich in renewable energy ***,we

关键词： Cloud computing carbon emissions energy efficiency energy consumption energy costs eco-friendly data center

来源：评论

学校读者我要写书评

暂无评论

Virtual Reality Applications for Social Anxiety Treatment: A Comprehensive Literature Review 2

Virtual Reality Applications for Social Anxiety Treatment: A...

引用

2nd International Conference on Computational Intelligence and Network Systems, CINS 2024

作者： Agarwal, Prerna Arya, Pradeep Kumar Gupta, Bharat Shrivastava, Pranav Tuli, Kareena Hussain, Saquib School of Computer Science Engineering and Technology Bennett University UP Greater Noida201310 India Department of Computer Science & Engineering Galgotias College of Engineering and Technology Greater Noida India

ISBN: (纸本)9798331504106

Social anxiety is a psychological disorder distinguished by a profound apprehension of social environments, leading to irrational anxiety among individuals. This excessive fear of social situations affects a considerable number of young people worldwide. This comprehensive literature analysis investigates the remedy of social anxiety with help of virtual reality (VR) in. It explores the extent and limitations of gamifying treatment solutions for social anxiety. This approach enables individuals to engage in social exposure therapy conveniently. It assists in enhancing their home-based exercise routine and reducing the likelihood of relapses. A detailed assessment of the frequency of social anxiety disorder, common therapeutic approaches, and the limitations associated with these conventional treatments is provided. Subsequently, the prospective applications of VR-based exposure therapy to improve social competencies among individuals suffering from social anxiety are detailed. The review places particular emphasis on the Indian demographic. This focus aims to address the distinctive challenges and prospects within this population due to the extensive cultural diversity. ©2024 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Prediction of Coronary Artery Calcium with CT-Images using Deep Learning

Prediction of Coronary Artery Calcium with CT-Images using D...

引用

2024 International Conference on Integration of Emerging Technologies for the Digital World, ICIETDW 2024

作者： Parameswari, R. Prasad, Mudarakola Lakshmi Balamurugan, M. Babu, Ch Ramesh Sreenivasulu, Meruva Reddy, Pundru Chandra Shaker Sathyabama Institute of Science and Technology Department of Mathematics Tamil Nadu Chennai India Institute of Aeronautical Engineering Computer Science and Engineering Telangana Hyderabad India Sri Sairam Engineering College Computer Science and Engineering Tamil Nadu Chennai India Matrusri Engineering College Department of Information Technology Telangana Hyderabad India Matrusri Engineering College Computer Science and Engineering Telangana Hyderabad India SR University School of Computer Science and Artificial Intelligence Telangana Warangal India

ISBN: (纸本)9798331541170

The coronary-artery-calcium(CAC)-score of CT is a popular tool for recognition of coronary-artery disease. Nevertheless, the present diagnostic approach utilizing CAC-score CT is laborious, since the radiologist needs to meticulously examine each CT image individually and verify the precise range. This research applies three convolutional neural network (CNN) models to 1200 CT scans of the cardiovascular system, including both normal and calcium-containing scans. As part of our experimental test, we categorize the CT-image data into three different sets: original CAC-score CT, cardiac-segmented, and cardiac-cropped images. The former set includes the entire rib cage, while the latter two sets exclude all but the heart region. The investigational test for determining the incidence of calcium in a CT-picture utilizing the Inception ResnetV2, VGG, and Resnet50 are yielded the best results with a 98.52% accuracy rate when the Resnet 50 model was applied to cardiac cropped image data. As a result, the authors of this work hope that future studies will pave the way for automated calcium study scores for each CAC-score CT as well as for the detection of calcium alone. © 2024 IEEE.

关键词： computerized tomography

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：