检索结果-内蒙古大学图书馆

Computing, Sciences and Communications (ICCSC), International Conference on

作者： Mohammad Bdair E D Kanmani Ruby Prachi Juyal Rakheeba Taseen A. Abirami A Soujanya School of Architecture Computing & Engineering University of East London London UK Department of ECE Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Allied Science (Mathematics) Graphic Era (Deemed to be University) Dehradun Uttarakhand India School of computer science and Engineering Presidency university Bangalore India Department of Mathematics Sona College of Technology Salem Tamil Nadu India Department of Computer Science and Engineering CVR College of Engineering Ibrahimpatnam (M) Telangana India

ISBN: (数字)9798350353648

ISBN: (纸本)9798350353655

Lung cancer must be detected as early as possible, but it may be difficult with existing methods since they often depend on human judgment and outdated image processing. These techniques take a lot of time and are prone to errors, which produces uneven outcomes. The research provides a unique deep learning-based method for classifying lung nodules from CT images using convolutional neural networks (CNNs). By automating feature extraction and categorization, the suggested technique greatly increases diagnostic precision. The result shows superior performance over existing systems is demonstrated by evaluation measures such as AUC-ROC, accuracy, sensitivity, and specificity. With a training duration of 12 hours, an AUC-ROC of 0.95, accuracy of 92%, sensitivity of 94%, specificity of 90%, and inference speed of 0.5 seconds per scan, the results demonstrate notable improvements in diagnostic efficiency and accuracy. Deep learning has the potential to revolutionize the diagnosis of lung cancer and enhance patient care, as demonstrated by the study.

关键词： Training Accuracy Lungs Computed tomography Lung cancer Sensitivity and specificity Feature extraction Data models Stability analysis Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Critical Analysis on the Application of Next-Generation Internet of Things (Iot) for Building Efficient Energy Systems for Improved Temperature Control and Better Energy Consumption 2nd

A Critical Analysis on the Application of Next-Generation In...

引用

2nd International Conference on Mechanical and Energy Technologies , ICMET 2021

作者： Veeraiah, Vivek Shaikh, Naim Narasima Venkatesh, A. Thailand, Korakod Kousalyadevi, G. Shanmugasundaram, V. Department of R&D Computer Science Adichunchanagiri University Karnataka Mandya India Global Business School and Research Centre Dr. D.Y. Patil Vidyapeeth Pune Tathawade India MBA-Department of Human Resource Management RV Institute of Management Karnataka Bangalore India Faculty of Law Thaksin University Muang Songkhla District Thailand Department of Architecture Mohamed Sathak Engineering College Kilakarai India Department of Electrical and Electronics Engineering Sona College of Technology Tamil Nadu Salem636005 India

ISBN: (纸本)9789811901072

This research article is focused on analyzing the application of next-generation Internet of Things (IoT) in creating energy-efficient systems so as to improvise the temperature and manage the energy consumption effectively. The term IoT is a new concept that has been growing imminently due to growing needs and requirements of government, individuals, corporations, etc. The IoT is mainly stated as a critical system of computing machines that possess better and enhanced connection so as to automate various aspects of the routine needs of the individuals, it also assists in creating better information approach for evaluation and implementation of different approaches for sustainable living. The IoT system connects the different smart devices and senses through cloud-based controllers, the sensors in the building can enable in collecting and transmitting the real-time data on the environment, this information is then used by the controller’s team to offer quick responses on the temperature control ana management. The systems enable in applying predictive and adaptive algorithms which will enable in executing the real-time operational responses, like turning on or switching off the lights based on the signals from in-room occupancy and turning on the air conditioning based on the level of occupancy in the building, this enables in optimizing the heating, ventilation and air-conditioning system so as to enhance better energy consumption. This article presents a critical analysis of the usage of IoT in enhancing the energy-efficient system in the building for improved temperature control and enhanced energy consumption. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Automated resource management system based on kubernetes technology 18

Automated resource management system based on kubernetes tec...

引用

18th International Conference on Electrical Engineering/Electronics, computer, Telecommunications and Information technology, ECTI-CON 2021

作者： Sithiyopasakul, Jirayus Archevapanich, Tuanjai Purahong, Boonchana Sithiyopasakul, Paisan Benjangkaprasert, Chawalit King Mongkut's Institute of Technology Ladkrabang School of Engineering Bangkok Thailand Rajamagala University of Technology Suvarnabhumi Faculty of Engineering and Architecture Department of Electronics and Communication Engineering Nonthaburi Thailand King Mongkut's Institute of Technology Ladkrabang School of Engineering Department of Computer Engineering Bangkok Thailand

ISBN: (纸本)9780738111278

The purpose of this research is intended to study and analyze the Kubernetes technology using the processes of performance evaluation by inspecting how many requests and responses could the server handle. According to the ability of Kubernetes technology, there is no systematic measure of performance despite the Kubernetes is currently in use broadly. Therefore, this paper proposed to test out the system by measuring the effectiveness according to a structured process by studying such measurement variables including the number of requests per second, number of responses to requests, and resource extension period with Kubernetes technology. Which from the testing and analysis of all three variables as mentioned, it is possible to know the efficiency of the Kubernetes technology in such a similar environment. Moreover, the testing experiment could display a piece of information on the dashboard for visualization and analytic purposes. © 2021 IEEE.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Rolling Stock Shunt Operation Planning in Urban Rail Transit Depots

SSRN

引用

SSRN 2024年

作者： Wang, Dian Yao, Ling D'Ariano, Andrea Zhan, Shuguang Wang, Lisha School of Automotive and Transportation Engineering Hefei University of Technology Anhui Hefei230009 China Department of Civil Computer Science and Aeronautical Technologies Engineering Roma Tre University Rome00146 Italy School of Architecture and Urban Planning Chongqing University Chongqing400030 China

This study investigates daily rolling stock shunt operation planning in an urban rail transit depot. Given the layout of a depot and the rolling stocks (that arrive at and depart from this depot within an operation day) with given maintenance schedule, the studied problem lies in determining: 1) the position where each rolling stock stops to be parked, outside washed, and/or maintained, and 2) the conflict-free shunting plan of rolling stocks to move within depot. We transform the studied depot into different multiple-layer directed graphs (to represent the infrastructures in a microscope perspective) based on depot’s layout and maintenance schedule of rolling stocks, to illustrate the specific shunting processes of each rolling stock. By means of these resulting graphs, we formulate the studied problem as a mixed integer linear programming model by incorporating several additional requirements (that are not or rarely considered in previous related works) and a specific situation of Chinese urban rail transit system, to increase the attractiveness of our solutions for rail dispatchers. We also introduce a logic-based Benders decomposition algorithm to efficiently solve real-life problem instances, where three groups of customized acceleration mechanisms (including strengthening the bounds of variables, reducing total numbers of variables and constraints involved, and designing additional feasibility cuts) are explored to improve solution performance of our algorithm. Finally, a set of realistic and realworld instances with different scales, derived from the largest depot of Chongqing Rail Transit Line 3 in China, are investigated to demonstrate the efficiency and effectiveness of our model and algorithm. Computational results reveal that our algorithm solves a real-life instance in approximately 8 seconds which is considerably shorter than the time of dispatchers to solve the studied problem manually, thus our approach can provide strong automatical computer-aided d

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

Coupled Swmm-Moea/D for Multi-Objective Optimization of Low Impact Development in Urban Stormwater Systems

SSRN

引用

SSRN 2024年

作者： Javan, Kazem Nazari, Amirhossein Roozbahani, Abbas Darestani, Mariam Hossieni, Hanieh Banihashemi, Saeed The Department of Civil and Environmental Engineering Western Sydney University Australia Faculty of Agricultural Technology College of Agriculture and Natural Resources University of Tehran Tehran Iran Ås Norway The Department of Computer and Electrical Engineering Sistan and Baluchestan University Iran School of Built Environment Faculty of Design Architecture and Building University of Technology Sydney Australia Tehran University Iran

The escalating challenge of unsustainable urban development worldwide has precipitated changes in land usage, contributing to increased impermeability of the urban landscape. This phenomenon exacerbates urban runoff, a critical environmental concern. In response, Low Impact Development (LID) techniques, recognized for their environmental efficacy, have emerged as pivotal in mitigating urban runoff. However, transforming the hydrological dynamics of urban watersheds into a more sustainable state necessitates substantial financial commitments from relevant authorities. Consequently, strategic LID planning becomes essential to maximize effectiveness while minimizing costs. This research introduces a novel, hybrid modeling strategy that integrates the Storm Water Management Model (SWMM) with the MOEA/D optimization algorithm. This approach aims to concurrently minimize runoff volume, peak flow rate, and implementation expenses. Focusing on a segment of Tehran Municipality's urban stormwater system in District 11, the study evaluates four distinct LID scenarios. These scenarios encompass various configurations of rain barrels (RB), bioretention cells (BC), green roofs (GR), and porous pavements (PP). Utilizing the TOPSIS method for comparative analysis, the study results identify the most efficacious scenario, S2_1, including RB and BC, which achieves a 19.34% reduction in runoff volume and a 46.53% decrease in peak flow rate, all at the implementation cost of 123,169 US$. A close second, scenario S3_1 incorporating RB and PP, demonstrates a 17% and 46.55% reduction in runoff volume and peak flow at an expenditure of 107,017 US$, respectively. The proposed SWMM-MOEA/D model, in conjunction with TOPSIS, presents a valuable tool for LID planning and optimization, offering decision-makers and relevant entities a pragmatic approach to address the challenges of urban runoff management. © 2024, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

TensorHive: management of exclusive GPU access for distributed machine learning workloads

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2021年第1期22卷 9766-9770页

作者： Paweł Rościszewski Michał Martyniak Filip Schodowski Department of Computer Architecture Faculty of Electronics Telecommunications and Informatics Gdańsk University of Technology Gdańsk Poland

TensorHive is a tool for organizing work of research and engineering teams that use servers with GPUs for machine learning workloads. In a comprehensive web interface, it supports reservation of GPUs for exclusive usage, hardware monitoring, as well as configuring, executing and queuing distributed computational jobs. Focusing on easy installation and simple configuration, the tool automatically detects the available computing resources and monitors their utilization. Reservations granted on the basis of flexible access control settings are protected by pluggable violation hooks. The job execution module includes auto-configuration templates for distributed neural network training jobs in frameworks such as TensorFlow and PyTorch.

关键词： GPU reservation access control hardware monitoring job orchestration

来源：评论

学校读者我要写书评

暂无评论

Enhancing Local Feature Learning for 3D Point Cloud Processing using Unary-Pairwise Attention 32

Enhancing Local Feature Learning for 3D Point Cloud Processi...

引用

32nd British Machine Vision Conference, BMVC 2021

作者： Xiu, Haoyi Liu, Xin Wang, Weimin Kim, Kyoung-Sook Shinohara, Takayuki Chang, Qiong Matsuoka, Masashi Department of Architecture and Building Engineering Tokyo Institute of Technology Tokyo Japan Artificial Intelligence Research Center AIST Tokyo Japan DUT-RU International School of Information Science and Engineering Dalian University of Technology Dalian China Department of Computer Science Tokyo Institute of Technology Tokyo Japan

We present a simple but effective attention named the unary-pairwise attention (UPA) for modeling the relationship between 3D point clouds. Our idea is motivated by the analysis that the standard self-attention (SA) that operates globally tends to produce almost the same attention maps for different query positions, revealing difficulties for learning query-independent and query-dependent information jointly. Therefore, we reformulate the SA and propose query-independent (Unary) and query-dependent (Pairwise) components to facilitate the learning of both terms. In contrast to the SA, the UPA ensures query dependence via operating locally. Extensive experiments show that the UPA outperforms the SA consistently on various point cloud understanding tasks including shape classification, part segmentation, and scene segmentation. Moreover, simply equipping the popular PointNet++ method with the UPA even outperforms or is on par with the state-of-the-art attention-based approaches. In addition, the UPA systematically boosts the performance of both standard and modern networks when it is integrated into them as a compositional module. © 2021. The copyright of this document resides with its authors.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Athletes movement tracking device for soccer players 18

Athletes movement tracking device for soccer players

引用

18th International Conference on Electrical Engineering/Electronics, computer, Telecommunications and Information technology, ECTI-CON 2021

作者： Archevapanich, Tuanjai Sithiyopasakul, Jirayus Sithiyopasakul, Jiran Sithiyopasakul, Paisan Anuwongpinit, Thanavit Purahong, Boonchana Rajamagala University of Technology Suvarnabhumi Faculty of Engineering and Architecture Department of Electronics and Communication Engineering Nonthaburi Thailand King Mongkut's Institute of Technology Ladkrabang School of Engineering Bankok Thailand King Mongkut's Institute of Technology Ladkrabang School of Engineering Department of Computer Engineering Bankok Thailand

ISBN: (纸本)9780738111278

This article presents the design and development of real-time tracking system using GPS for soccer players. The tracking system is separated into two parts including hardware and software sections. The hardware uses NodeMCUV3 which is connected to the GPS module that can receive a current position data of soccer players. After that, it processes and records the position data into the MicroSD card module. In the software section can display the heat map results from recorded data of soccer players. The main user is a soccer club manager which is responsible for monitoring the data that tested on the movement of the soccer player. For the experimental results, a device is tested, and the movement data is collected. Also, it is found that the tracking device could track the athlete's movements successfully. © 2021 IEEE.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

Keyword extraction based on semantic similarity metric and multi-feature computing 7

Keyword extraction based on semantic similarity metric and m...

引用

7th International Conference on Big Data Computing and Communications, BigCom 2021

作者： Kang, Hui Sun, Xin Feng, Tie Lin, Shuhang Jilin University College of Computer Science and Technology Changchun China Jilin University College of Software Changchun China Beijing ByteDance Technology Co. Ltd. Department of Product R&D and Engineering Architecture Beijing China

ISBN: (纸本)9781665442527

Keyword extraction is an effective method to extract keywords from a text which can express the main content of the text. However, it is difficult to extract useful information quickly from a large number of documents. In this paper, a semantic similarity metric and multi-feature computing based keyword extraction algorithm is presented. First, a semantic similarity algorithm based on WordNet semantic dictionary toward distance, information and property (SSDIPA) is proposed, which quantifies the degree of association between words. Then, a multi-feature tuple (word frequency, word length, word span, word position, semantic similarity) based computing method is presentssd to score the candidate keywords. Finally, the feature decision tree is used to adjust the proportional relationship among the features so that the keyword extraction results can meet the use's subjective preferences. The result shows that the proposed algorithm outperforms other comparison algorithms, and the multi-feature computing based keywords extraction algorithm can improve the accuracy. © 2021 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Reachability Analysis for Piecewise Affine System

arXiv

引用

arXiv 2025年

作者： Xie, Peng Betz, Johannes Raimondo, Davide M. Alanwar, Amr TUM School of Computation Information and Technology Department of Computer Engineering Technical University of Munich Heilbronn74076 Germany TUM School of Engineering and Design Department of Autonomous Vehicles Systems Technical University of Munich Garching85748 Germany School of Automatic Control Department of Engineering and Architecture University of Trieste Via Valerio 10 Trieste34127 Italy

Hybrid systems play a crucial role in modeling real-world applications where discrete and continuous dynamics interact, including autonomous vehicles, power systems, and traffic networks. Safety verification for these systems requires determining whether system states can enter unsafe regions under given initial conditions and uncertainties—a question directly addressed by reachability analysis. However, hybrid systems present unique difficulties because their state space is divided into multiple regions with distinct dynamic models, causing traditional data-driven methods to produce inadequate over-approximations of reachable sets at region boundaries where dynamics change abruptly. This paper introduces a novel approach using hybrid zonotopes for data-driven reachability analysis of piecewise affine systems. Our method addresses the boundary transition problem by developing computational algorithms that calculate the family of set models guaranteed to contain the true system trajectories. Additionally, we extend and evaluate three methods for set-based estimation that account for input-output data with measurement noise. © 2025, CC BY.

关键词： Convergence of numerical methods

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：