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

A Predictive Study of Feature Encoding and Selection Methods on PTM Lysine Glutarylation Site Allocation

A Predictive Study of Feature Encoding and Selection Methods...

引用

International Conference on Electrical, computer & Telecommunication engineering (ICECTE)

作者： MD. Salahuddin Fahad Md. Nazrul Islam Mondal Anika Tabassum Era dept. of computer science & engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh

The post-translational modification, Lysine Glutarylation is an active outcome of protein acylation. To determine the functional behaviors at the molecular level, it is required to have a proper visualization of the translation sites of the PTM. In this regard, machine learning algorithms and methodologies play an inevitable role. A wide range of conventions in machine learning is constantly being used to determine the PTM sites. However, in this study, the incorporated feature encoding methods are CKSAAP (Composition of K-Spaced Amino Acid Pairs) and PseKRAAC (Pseudo K-tuple Reduced Amino Acid Composition). Specifically, the main intention of the study is to trial two feature extraction methods with two feature selection processes (RFECV and mRMR), so that better performance is gained regardless of other feature screening methods. Consequently, the sequence received, is likely to have more related information regarding the specified PTM. The approach implemented has 4 comparative combinations that are determined with the AUC (Area Under Curve). One of the conclusions is the combined prediction of CKSAAP and RFECV which derives an exceptional remark. Whereas, the merged case of PseKRAAC and RFECV through a noteworthy output of 0.908 AUC. The notable portion is that, when the RFECV is used in both cases (CKSAAP and PseKRAAC), the chances to have an outperformed prediction is achieved as RFECV extracts optimal features by cross val-idations. However, the mRMR selection method for CKSAAP results in 0.779 AUC, and PseKRAAC results in 0.786 AUC. So, the comparative study depicts that RFECV is more impactful than mRMR and more precisely, the achievable accuracy is for the combination of PseKRAAC and RFECV.

关键词： Proteins Visualization Machine learning algorithms Machine learning Feature extraction Amino acids Encoding

来源：评论

学校读者我要写书评

暂无评论

Sigmoid Functions Applied in Proportional + Resonant Reference for Current Harmonic Sharing

Sigmoid Functions Applied in Proportional + Resonant Referen...

引用

IEEE Annual Southern Power Electronics Conference (SPEC)

作者： Bruno Meneghel Zilli Lucas Jonys Ribeiro Silva Márcio Von Rondow Campos Cassius Rossi De Aguiar Ricardo Quadros Machado Dept. of Electr. & Comput. Engineering University of Sao Paulo Sao Carlos Brazil Dept. of Computer Engineering Federal University of Technology-Paraná Toledo Brazil

The concept of distributed generation and microgrids allowed different alternative of power sources to be integrated to the main grid, made possible due to the evolution and improvement of power converters, like DC-AC inverters. This paper proposes an alternative harmonic current sharing methodology without communication between the inverters in the microgrid. Sigmoid functions designed for each frequency in each inverter manage the amplitudes of currents references of PR controller, assigning the appropriate amount to each element taking into account the capacity and availability of each inverter. The grid connected system is composed by two VSIs operanting in parallel at the point of common coupling, as well as the non-linear load. The results presented a harmonic compensation evaluating VSIs with different power capacities. In a first scenario, the VSIs were designed for only supply active power, and in a second scenario, the converters provided almost all the harmonic needed for a non-linear load.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Squeeze-Excitation ResNet Approach for Effective Classification of Parasitic Eggs

A Squeeze-Excitation ResNet Approach for Effective Classific...

引用

2024 International Visualization, informatics and technology Conference, IVIT 2024

作者： Muthulakshm, M. Venkatesan, K. Rahayu, Syarifah Bahiyah Elangovan, Karthickeien Amrita School of Engineering Amrita Vishwa Vidyapeetham Dept. of Electronics and Communication Engineering Chennai India Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Chennai India National Defence University Malaysia Faculty of Defense Science and Technology Kuala Lumpur Malaysia National Defence University Malaysia Cyber Security and Digital Industrial Revolution Centre Kuala Lumpur Malaysia

ISBN: (纸本)9798350354447

The identification and classification of different kinds of parasite eggs in microscopic samples represent a critical challenge in the field of Soil-transmitted helminth infection diagnosis. Traditional methods are often labor-intensive and time-consuming. The emergence of deep learning models has shown promising results in automating this process by extracting intricate features from complex images. This study aims to develop an automated system for accurately classifying parasite egg types in microscopic images by leveraging the ability of squeeze excitation layers to learn the global information from the input. The proposed system employs features extracted by ResNet50 and ResNet101 with Squeeze Excitation (SE) layers for analysis. The extracted features are then input into a Support Vector Classifier. The study systematically evaluates the features extracted from ResNet50+SE and ResNet101+SE. Results from the evaluation demonstrate the efficacy of the ResNet50+SE in accurately classifying parasite egg types in microscopic images with an accuracy of 0.94. The study provides valuable insights into the choice of squeeze-excitation block added Resnet in the context of parasitology, contributing to the advancement of automated medical image analysis. The findings hold great potential for improving diagnostic processes and supporting epidemiological studies through efficient and accurate parasite detection. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Automated Diagnosis of brain tumor classification and segmentation of MRI Images

Automated Diagnosis of brain tumor classification and segmen...

引用

Confluence of Advancements in Robotics, Vision and Interdisciplinary technology Management (IC-RVITM), International Conference on th

作者： K Shanthala B M Chandrakala N Shobha Deepashree D Dept. of Mechanical Engineering RV Institute of Technology and Management Bengaluru India Dept. of Information scince Engineering Dayanand Sagar college of Engineering Bengaluru India Dept. of Computer scince and Engineering Dayanand Sagar college of Engineering Bengaluru India

Brain tumors are one of the most prevalent disorders of the central nervous system and are dangerous. For patients to receive the best treatment, early diagnosis is crucial. For radiologists to correctly detect brain tumor images, an automated approach is required. The identification procedure can be time-consuming and prone to mistakes. In this work, the issue of fully automated brain tumor classification and segmentation of Magnetic Resonance Imaging (MRI) including meningioma, glioma, pituitary and no tumor are taken into consideration. In this study, Convolutional Neural Network (CNN) and mask Region-based Convolutional Neural Network (R-CNN) are proposed for classification and segmentation problems respectively. This study employed 3,200 images as training set and the system achieved an accuracy of 96% for classifying the tumors and 94% accuracy in segmentation of tumors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mobile Health Intervention System in Optimizing Healthcare Delivery for Cardiac Patients

Mobile Health Intervention System in Optimizing Healthcare D...

引用

Advancements in Computing (ICAC), International Conference on

作者： R.P.K. Prabashana G.A.J.W. Nanayakkara W.K.D.C. Wanniachchi S.B.A.M.B.S. Arampath Samantha Rajapaksha S.M.B. Harshanath Dept. of Computer Systems Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka dept. of Information Technology Sri Lanka Institute of Information Technology Malabe Sri Lanka

The advent of mobile health (mHealth) technologies has ushered in a new era in healthcare delivery, transforming the way cardiac patients receive medical care and support. This research paper explores the role of a mobile health intervention system in optimizing healthcare delivery for cardiac patients. The prevalence of heart attacks has necessitated innovative solutions to enhance patient outcomes and reduce the burden on healthcare systems. The proposed mHealth intervention system leverages the ubiquity of mobile devices to provide real-time monitoring, personalized interventions with environment prediction, and seamless communication between patients and healthcare providers. Through a comprehensive review of existing literature and empirical studies, this paper examines the impact of the mHealth intervention system on patient engagement, adherence to treatment plans, early detection of cardiac events, and overall quality of care. The integration of wearable device, CardioCare mobile application, and telemedicine platforms creates a holistic approach to cardiac care, empowering patients to actively participate in their health management and enabling healthcare professionals to make informed decisions. The potential benefits, challenges, and ethical considerations surrounding the implementation of this system are discussed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DLT Based Smart Medical Ecosystem

DLT Based Smart Medical Ecosystem

引用

2023 IEEE International Conference on Network, Multimedia and Information technology, NMITCON 2023

作者： Puri, Vikram Kataria, Aman Rani, Sita Pareek, Piyush Kumar Duy Tan University Center of Visualization and Simulation Da Nang Viet Nam Amity Institute of Defence Technology Amity University Uttar Pradesh Noida India Guru Nanak Dev Engineering College Department of Computer Science and Engineering Ludhiana India Nitte Meenakshi Institute of Technology Dept. of Artificial Intelligence and Machine Learning Bengaluru India

ISBN: (纸本)9798350300826

The healthcare system has become more reliant on the data collection capabilities of fast evolving IoT devices. Patient healthcare records (PHR) now contain additional information as a result. However, securing identities and guaranteeing data security have emerged as critical challenges in the healthcare system. When it comes to regulating PHR, many of the centralized and decentralized methods now in use struggle difficulties such as single point of failure, high transaction fees, slow throughput, and excessive latency. To address these concerns, a distributed ledger technology (DLT)-based framework named IOTA rather than a blockchain-based platform such as Ethereum or Polygon is proposed. The proposed framework considered the example of a hospital with several patients on the same and various floors. Furthermore, the suggested approach employs a real-time experimental setup for calculating the time and power consumption of the devices. © 2023 IEEE.

关键词： Distributed ledger

来源：评论

学校读者我要写书评

暂无评论

Multichannel Polarization Fiber Optic Sensors Using Wavelength Multiplexing

Multichannel Polarization Fiber Optic Sensors Using Waveleng...

引用

2024 Latin America Optics and Photonics Conference, LAOP 2024

作者： Kyselak, Martin Vylezich, Zdenek Vavra, Jiri Grenar, David Slavicek, Karel Department of Electrical Engineering Faculty of Military Technology University of Defense Brno Czech Republic IT Infrastructure Division Institute of Computer Science Masaryk University Zerotinovo nam. 617/9 Brno Czech Republic Dept. of Telecommunications Faculty of Electrical Eng. and Comm. Brno University of Technology Antoninska 548/1 Brno Czech Republic

A novel approach for multichannel polarization fiber optic sensors using wavelength multiplexing. By exploiting the unique properties of polarization and multiplexing techniques, our system achieves enhanced sensitivi... 详细信息

关键词： Fiber optic sensors

来源：评论

学校读者我要写书评

暂无评论

Bangla Toxic Comment Classification and Severity Measure Using Deep Learning

Bangla Toxic Comment Classification and Severity Measure Usi...

引用

Recent Progresses in Science, engineering and technology (ICRPSET), International Conference on

作者： Naimul Haque Md. Bodrul Alam Abdullah Ath Towfiq Mehorab Hossain Dept. of Computer Science & Engineering Ahsanullah University of Science and Technology Dhaka Bangladesh Dept. of Computer Science & Engineering Manarat International University Dhaka Bangladesh

Online users nowadays leave a lot of comments on various social networks, news websites, and forums. Certain comments are harmful or abusive. Since it is impractical to manually monitor so many comments, the majority of systems employ some form of a machine learning model to automatically identify harmful content. Much of the work has been done for the English language. However, only a few approaches have been taken to classify toxic comments in the Bangla language. A multi-label classification technique for Bangla comments is offered in the study that follows to classify the numerous toxic comments into six categories: toxic, severe toxic, obscene, threat, insult, and identity hate, and also measure the severity of these comments. For the experiment, we compiled a dataset of 12634 comments from TikTok and other sources. By incorporating knowledge from earlier proposed studies, the proposed classification model was developed utilizing deep learning techniques, specifically Long Short-Term Memory (LSTM) and Long Short-Term Memory-Convolutional Neural Networks (LSTM-CNNs), as well as word embeddings and obtained a maximum accuracy of 83.66% and 1.61 MSE loss for the severity measure. 1 1 https://***/imbodrulalam/Toxic-Comment-Detection-BN

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Healthcare Delivery Through IoT Applications in Remote Patient Monitoring and Telemedicine 3

Enhancing Healthcare Delivery Through IoT Applications in Re...

引用

3rd IEEE North Karnataka Subsection Flagship International Conference, NKCon 2024

作者： Yogi, Kottala Sri Gowda V, Dankan Manoj Kumar, S.B. Nithya, R. Begum, A.Yasmine Suganthi.n Symbiosis Institute of Business Management Hyderabad Symbiosis International University Department of Operations Pune India Bms Institute of Technology and Management Department of Electronics and Communication Engineering Karnataka Bangalore India Bgsit Adichunchanagiri University Faculty of Engineering Management & Technology Dept. of Ece Karnataka 571448 India Vivekanandha College of Engineering for Women Department of Computer Science and Engineering Tamilnadu Namakkal India Mohan Babu University School of Engineering Department of Electronics and Communication Engineering Tirupati India Dayananda Sagar College of Engineering Department of Electrical and Electronics Engineering Karnataka Bangalore India

ISBN: (纸本)9798350364569

This paper presents how IoT plays a vital role in improving delivery of healthcare services especially through remote patient monitoring and telemedicine. The proposed system also employs IoT devices aimed at passing various health indicators like;pulse rate, blood glucose levels, blood pressure, and physical activity to continually and objectively provide real-time data in the body. This particular study, the participants with chronic diseases, normal population and elderly people also participated in the test of the system. Some of the findings include;it is possible to measure the daily steps corresponding to the a calorie expenditure, the sleep score ranging between 60-80 and oxygen saturation percentages ranging from 96%-99% in various postures. The system also proved the correlation between the percentage of variation in ambient temperature and the percentage of variation in the pulse rate which was quite sensitive to the changes in temperatures. Based on these observations, it is possible to conclude that IoT-based monitoring can improve patient's conditions as long as underlying issues will be detected at an early stage and necessary actions will be taken in time. The study also also demonstrates the application of telemedicine in making healthcare more accessible especially for the people from rural settings or in developing countries. The results show a good direction regarding the future of the system;however, security issues, privacy relating to data as well as integration are key hurdles in this connection. © 2024 IEEE.

关键词： Blood pressure

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：