检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Liu, Yanqi Calderoni, Giuseppe Bahar, R. Iris Dept.of Computer Science Brown University ProvidenceRI United States Dept.of Automation and Informatics Politecnico di Torino Torino Italy School of Engineering Dept. of Computer Science Brown University ProvidenceRI United States

Algorithms based on Monte-Carlo sampling have been widely adapted in robotics and other areas of engineering due to their performance robustness. However, these sampling-based approaches have high computational requirements, making them unsuitable for real-time applications with tight energy constraints. In this paper, we investigate 6 degree-of-freedom (6DoF) pose estimation for robot manipulation using this method, which uses rendering combined with sequential Monte-Carlo sampling. While potentially very accurate, the significant computational complexity of the algorithm makes it less attractive for mobile robots, where runtime and energy consumption are tightly constrained. To address these challenges, we develop a novel hardware implementation of Monte-Carlo sampling on an FPGA with lower computational complexity and memory usage, while achieving high parallelism and modularization. Our results show 12X–21X improvements in energy efficiency over low-power and high-end GPU implementations, respectively. Moreover, we achieve real time performance without compromising accuracy. Copyright © 2020, The Authors. All rights reserved.

关键词： Robotics

来源：评论

学校读者我要写书评

暂无评论

Task Scheduling in Cloud Environment Using Enhanced Resource Monitor and Scheduler Algorithm 8

Task Scheduling in Cloud Environment Using Enhanced Resource...

引用

8th International Conference on Computation of Power, Energy, Information and Communication, ICCPEIC 2019

作者： Seethalakshmi, V. Govindasamy, V. Akila, V. Iyswarya Saradha, N. Hari Haran, J. Vigneshwaran, G. Pondicherry Engineering College Dept.of Computer Science and Engineering Puducherry India Pondicherry Engineering College Department of Information Technology Puducherry India

ISBN: (数字)9781728108377

ISBN: (纸本)9781728108377

Cloud Computing is a concept for virtualized resources. It is a technology which delivers plenty of services to service users through internet. It takes users request as input and delivers the service in good manner. Cloud computing manages the numerous variety of virtualized resources and user request which makes scheduling an important one in order to manage it effectively. For every task thousands of virtualized assets are used. Task scheduling in cloud computing is the process of organizing the user task and allocating it with the suitable and available resources so that the available resources will be properly used and scheduling will be done effectively. There are numerous task scheduling techniques. This paper presents an alternative approach to task scheduling problem. It mainly focused on the time utilization and resource monitoring. The proposed method is Enhanced Resource Monitor and Scheduler (ERMS) which focus on both monitoring of available resources and scheduling of user *** push action method is used to get the status of virtual machine. The fitness value is calculated and scheduling is done. The process is implemented using ClouldSim 3.0 Simulator in NetBeans IDE. © 2019 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Simulating Spiking Neural Networks with Timed Dataflow Graphs

Simulating Spiking Neural Networks with Timed Dataflow Graph...

引用

IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS)

作者： Lei Pan Francois Christophe Tommi Mikkonen Zhu Li Shuvra S. Bhattacharyya Dept.of ECE and UMIACS University of Maryland College Park Maryland USA HAMK Tech HAMK University of Applied Sciences Hämeenlinna Finland Dept.of Computer Science University of Helsinki Helsinki Finland Dept.of Computer Science and Electrical Engineering University of Missouri Kansas City Missouri USA

ISBN: (数字)9781728149226

ISBN: (纸本)9781728149233

This article presents a novel approach for simulating Spiking Neural Networks (SNNs) that is based on timed dataflow graphs. Whereas conventional SNN simulators compute changes in spiking neuron variables at each time step, the proposed simulation approach focuses on evaluating spike timings. This focus on evaluating when a dataflow actor (spiking neuron) reaches a new spike contributes to making spike evaluation an event-driven computation. The resulting event-driven simulation approach avoids unnecessary computations at time steps that lie between spiking events. This optimization is achieved while avoiding the large overheads associated with lookup tables that are incurred in existing event-driven approaches. Our results show identical spiking behavior compared to simulation using a conventional (time-based) simulator while providing significant improvement in execution time.

关键词： Neurons Computational modeling Biological system modeling Biological neural networks Tools Indexes Integrated circuit modeling

来源：评论

学校读者我要写书评

暂无评论

Educational Matlab Tool for Evaluating Liver Tumors Using Ultrasound

Educational Matlab Tool for Evaluating Liver Tumors Using Ul...

引用

International Symposium on Electronics and Telecommunications (ISETC)

作者： Denisa Alexandra Veres Dumitru Daniel Bonciog Damian Olei Daniela Cîrnatu Daniel Iacob Goje David Comaniciu Liliana Mâtiu Iovan Mihaela Ruxandra Lascu Valentin Laurenşiu Ordodi Dept. of Computer and Information Technology University Politehnica Timişoara Timişoara Romania Dept. of Measurements and Optical Electronics University Politehnica Timişoara Timişoara Romania National Institute of Public Health Timisoara Regional Centre Timişoara Romania Dept.of Internal medicine I. “Victor Babes” University of Medicine and Phanmacy Timişoara Timişoara Romania Dept. of Biochemistry.“Victor Babes” University of Medicine and Phanmacy Timişoara Timişoara Romania Dept. of Applied Chemistry Engineering of Organic and Natural Compounds University Politehnica Timişoara Timisoara Romania Dept. of Functional Science “Victor Babes” University of Medicine and Phanmacy Timişoara Timisoara

ISBN: (数字)9798350390865

ISBN: (纸本)9798350390872

This paper aims to develop a Matlab application for computer-assisted learning in the evaluation of liver tumors using ultrasound. Diagnosing liver tumors detected during standard ultrasound exams is challenging for doctors, often requiring detailed investigations for accurate diagnosis and effective treatment. computerized analysis of ultrasound images can significantly aid doctors in interpreting these images and formulating accurate diagnoses. The Matlab programming environment provides various tools for processing biomedical images. In this study, Histogram and Entropy functions were utilized to accurately differentiate between malignant and benign liver tumors. Additionally, Matlab App Designer was used to create a user-friendly interface for doctors. This application is also beneficial for students, offering a valuable tool for self-testing and skill development in clinical ultrasound courses and practical sessions. The proposed Matlab application employs classic image processing tools and serves as useful software for students learning liver ultrasound techniques.

关键词： Ultrasonic imaging Accuracy Liver Medical services Software Telecommunications MATLAB Standards Tumors Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Prediction of Soil Wind Erodibility Using Rfe-Based Ensemble Modelling

SSRN

引用

SSRN 2022年

作者： Roy, Bishwajit Malviya, Lokesh Mal, Sandip Kumar, Amrendra Kumar, Radhikesh Jahed Armaghani, Danial Kumar, Deepak Banerjee, Avishek School of Computer Science UPES Uttarakhand Dehradun248007 India School of SCSE VIT MP Bhopal466114 India Dept.of CE RIT UK Roorkee247667 India Dept. of CSE NIT Bihar Patna800001 India Department of Urban Planning Engineering Networks and Systems Institute of Architecture and Construction South Ural State Universit 76 Lenin Pros ect Chelyabinsk454080 Russia Dept. of CE NIT Bihar Patna800001 India Department of CSBS Asansol Engineering College Asansol713305 India

Due to the intricate nature of erodibility, sensitivity of soil particles and limited amount of data, the consequent modelling of soil wind erodibility is a challenging task for researchers. Therefore, the robust prediction of soil wind erodibility along with the sensitive factors is often an indispensable task. This study analyses portable wind tunnel-based measured wind erosion rate (gm −2 s −1 ) from 118 sites in Kerman Province, southeast Iran where 17 different predictors were considered for each site. This paper investigates the importance of a set of predictors which are most affected by soil erosion rate. Furthermore, this study proposes a novel an optimum feature selection-based heterogeneous ensemble meta-estimator (voting ensemble (VE)) for predicting wind erosion rate. A linear regression-based recursive feature elimination technique with 2-fold cross validation is used to identify the 7significant important predictors, called i) VFS (very fine sand), ii) CS (coarse sand), iii) VCS (very coarse sand), iv) GC (gravel coverage), v) MWD (mean weight diameter), vi) surface crust, and vii) moisture, that affects the soil erodibility rate. Then, a VE with 3 unfitted estimators is proposed, which averages the predictions of singleton estimators to enhance the prediction accuracy. The 3 singleton unfitted estimators, called support vector machine (linear kernel), random forest and gradient boosting machine, are used with grid search approach. The investigation identifies the surface crust as the most effective parameter in predicting soil erosion rate. © 2022, The Authors. All rights reserved.

关键词： Soils

来源：评论

学校读者我要写书评

暂无评论

A Learning Performance Assessment Model Using Neural Network Classification Methods of e-Learning Activity Log Data 2

A Learning Performance Assessment Model Using Neural Network...

引用

2nd International Conference on Smart Systems and Inventive Technology, ICSSIT 2019

作者： Arumugam, S. Kovalan, A. Narayanan, A.E. Dept. of Computer Science and Applications Periyar Maniammai Institute of Science and Technology Thanjavur India Dept.of Computer Science VSB College of Arts and Science VSB Group of Institutions Karur India Department. of Computer Science Engineering Periyar Maniammai Institute of Science and Technology Thanjavur India

ISBN: (纸本)9781728121192

Interactive learning and computed aided learning methods increased a lot of developments in Learning Systems. It results a collection of log data of learning activities increased. Machine Learning(ML) based Data Mining(DM) is used to find some meaningful information from huge and complex datasets. Learning behavior of the students can be accessed by using ML based data mining techniques on the log data of the students' activity. It helps to Even there are possibilities to recognize the performance of the students before the examination. Time-series students log data during their lab section is taken from the UCI dataset. The modified numeric data file is taken and applied classification techniques to predict the performance of the students. Among the implemented models J48, Random Tree, Multilayer Perceptran Neural Network(MLPNN), Radial Basis Neural Network(RBFNN), the RBFNN based classification is better than other classification techniques to predict the students' grades. © 2019 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey of machine learning based mobile data traffic prediction models for 5G cellular networks

引用

AIP Conference Proceedings 2024年第1期2816卷

作者： R. Raj Mohan K. Vijayalakshmi P. John Augustine R. Venkatesh M. Gomathy Nayagam B. Jegajohi Dept.of Electronics and Communication Science Agurchand Manmull Jain College Meenambakkamchennai Tamil Nadu India Computer Science and Engineering Sri Sai Ram Institute of Technology Sai Leo Nagar west Tambaram chennai India Department of Information Technology Sri Eshwar College of Engineering Kondampatti Coimbatore Tamil Nadu India Computer Science and Engineering Ramco Institute of Technology North Venganallur Village Rajapalayam Virudhunagar Tamil Nadu India Sri Venkateswara College of engineering Sriperumbudur chennai Tamil Nadu India

The advanced progression of mobile technology leads to a dramatic expansion in cellular data traffic (DT). Especially, the development of precise time series model in a 5G cellular network, becomes indispensable to increase the quality of services (QoS) and forecast cellular DT. The cellular DT predictive models allow the operator in adapting to the traffic demand of the networks with user experience and better resource usage. Furthermore, owing to the characteristics of the higher heterogeneities amongst a number of base stations with traffic load, the cellular DT predictive model becomes challenging. Thus, the study develops a detailed analysis of artificial intelligence (AI) based techniques to predict mobile DT. An extensive analysis of existing ML model has been presented for the cellular DT prediction in 5G network. Additionally, a wide-ranging description of the advancement of mobile networks is provided. Likewise, the present approaches are studied in different ways including underlying methodologies, merits, major objectives, performance measures, and inferences. Also, wide-ranging experimental analyses of the surveyed methods have been taking place for recognizing the exclusive features of all approaches. Lastly, an overview of future directions and challenging issues are extensively discussed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Spatial Data Management Systems Using GeoSpark

Performance Evaluation of Spatial Data Management Systems Us...

引用

International Conference on Big Data and Smart Computing (BIGCOMP)

作者： Hansub Shin Kisung Lee Hyuk-Yoon Kwon Dept.of Industrial and Systems Engineering Seoul National University of Science and Technology Seoul Republic of Korea Division of Computer Science and Engineering Louisiana State University Louisiana Baton Rouge U.S.

ISBN: (数字)9781728160344

ISBN: (纸本)9781728160351

In this paper, We evaluate the performance of spatial data management systems in distributed computing environments. Given that GeoSpark outperforms other spatial systems in many scenarios as reported in several studies, we choose spatial data management systems using GeoSpark for this evaluation. Even though GeoSpark supports various storage engines as its underlying data store, the effects of the storage engines for spatial data processing have not been well studied. To address this limitation, we evaluate the performance of GeoSpark using two underlying data stores: 1) HDFS and 2) MongoDB. We first design and build distributed experimental environments based on Amazon EC2 and EMR using up to 10 nodes. Through the extensive experiments on three synthetic and real data sets, we show that the overall performance of both HDFS-and MongoDB-based GeoSpark improves as we increase the number of nodes. We also show that HDFS-based GeoSpark generally outperforms MongoDB-based GeoSpark, especially for large-scale data sets. In addition, we demonstrate that the proper use of caching on HDFS-based GeoSpark can improve the overall query processing performance by up to three orders of magnitude.

关键词： Spatial databases Indexes Distributed databases Data processing Connectors Performance evaluation

来源：评论

学校读者我要写书评

暂无评论

New Method of POS based on Artificial Intelligence and Cloud Computing

New Method of POS based on Artificial Intelligence and Cloud...

引用

2019 International Conference on Recent Advances in Energy-efficient Computing and Communication, ICRAECC 2019

作者： Dey, Arnab Jain, Sudhanshu Nandi, Shovan Bengal Institute of Technology Dept. of Computer Science and Engineering Kolkata700150 India Chitkara Institute of Engineering and Technology Dept.of Master of Computer Applications Punjab140401 India Bengal Institute of Technology Dept. of Electronics and Communication Engineering Kolkata700150 India

ISBN: (纸本)9781538694824

Point of Sale systems have been rapidly getting advanced and powerful. In recent times, we can see credit and debit card based POS systems apart from traditional cash POS with manual entry. POS systems with Barcode readers are also developed. What we must recognize is that still many fraud and security issues are present. POS system that we have proposed, is based on new age technology that is 'AI subset based POS' which is a new method. We can find POS system with face recognition and Card swipe system at few places. Considering that the security problems still exists with the current system. We have proposed face recognition along with password as a method of payment making POS systems both card less and cashless. Cloud Computing technology is suggested way of implementation to make solution overall energy efficient as well. © 2019 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Magnetic field sensors using arrays of electrospun magnetoelectric Janus nanowires

引用

Microsystems & Nanoengineering 2018年第1期4卷 24-35页

作者： Matthew J.Bauer Xiao Wen Prabal Tiwari David P.Arnold Jennifer S.Andrew Dept.of Materials Science and Engineering University of FloridaGainesvilleFL 32611-6400USA Dept.of Electrical and Computer Engineering University of FloridaGainesvilleFL 32611-6200USA

The fabrication and characterization of the first magnetoelectric sensors utilizing arrays of Janus magnetoelectric composite nanowires composed of barium titanate and cobalt ferrite are *** utilizing magnetoelectric nanowires suspended across electrodes above the substrate,substrate clamping is reduced when compared to layered thin-film architectures;this results in enhanced magnetoelectric *** magnetoelectric nanowires are fabricated by sol–gel electrospinning,and their length is controlled through the electrospinning and calcination *** a directed nanomanufacturing approach,the nanowires are then assembled onto pre-patterned metal electrodes on a silicon substrate using *** this process,functional magnetic field sensors are formed by connecting many nanowires in *** observed magnetic field sensitivity from the parallel array of nanowires is 0.514±.027mV Oe^(−1) at 1 kHz,which translates to a magnetoelectric coefficient of 514±27mV cm^(−1) Oe^(−1).

关键词： nanowires composite utilizing

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：