检索结果-内蒙古大学图书馆

Malaysian Conference in Software engineering (MySEC)

作者： Adil A. A. Saed Wan M. N. Wan Kadir Faculty of Computer Science & Information Systems Department of Software Engineering Universiti Teknologi Malaysia Skudai Johor Malaysia

Component-Based System (CBS) is an approach to build applications from deployed components. It provides efficiency, reliability, maintainability. The challenge of interpreting the results of performance analysis and generate alternative design to build component system is quite critical in the software performance domain. Although, many approaches have been proposed and were successfully applied to predict software performance, still span of design space hinder the selection of the appropriate design alternative. Meta-heuristics such as Genetic Algorithms (GA) methods have proven its usefulness to solve the problem even with multi-degree of freedom. But, in recent investigations Particle Swarm Optimization (PSO), an alternative search technique, often outperformed GA when applied to various problems. In this paper we describe performance prediction approach based on PSO for component-Based system development. The proposed approach aids developers to effectively trades-off between architectural designs alternatives. Boundary search technique and PSO are used to provoke more efficient results. To the best of our knowledge we are the first who employ PSO in software performance prediction. Outlines of our approach are presented and a case study applied using GA is described to be used by our approach for validation. This paper has concluded that, PSO technique can be used to effectively generate alternatives in spanned design space and facilitate the design decision during the development process.

关键词： Genetic algorithms computer architecture Software performance Optimization Search problems Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Experimentation of measuring three dimensional ultrasound resolution

Experimentation of measuring three dimensional ultrasound re...

引用

2013 World Congress on engineering and computer science, WCECS 2013

作者： Rahmat, Rahmita W. Abboud, Anas A. Kadiman, Suhaini Bin Dimon, Mohd Z. Nurliyana, Lili Saripan, M. Iqbal Khaleel, Hasan H. Department of Computer Science and Information Technology UPM 43400 Serdang Malaysia No 145 Jalan Tun Razak 50400 Kuala Lumpur Malaysia Heart and Lung Centre National University of Malaysia Medical Centre HUKM 56000 Cheras Kuala Lumpur Malaysia Department of Computer and Communication Systems Engineering Faculty of Engineering UPM 43400 Serdang Malaysia

ISBN: (纸本)9789881925169

The quantification of the ultrasound images requires resolution of the ultrasound probe and image knowledge. However, only little information are available for ultrasound resolution where most of the publications used the physical information (frequency, band width and velocity of sound in tissue) to estimate the resolution. In this work, the experiment has been conducted to estimate the real size of objects acquired by three dimensional ultrasound imaging system. Then the predicated resolution has been used as a factor to measure heart ventricle stroke volume acquired using real time 3D echocardiography imaging system (ie33 Philips, X7-2t transducer) with the absence of the probe's physical information. Results: the results were validated by experts and the successful rates were acceptable with high accuracy. The finding of this experiment is useful for the researchers, where they can estimate the real size of any object (organ) acquired by 3D ultrasound X7-2t transducer, as it used as tool in our research to measure the ventricle volume.

关键词： Echocardiography

来源：评论

学校读者我要写书评

暂无评论

Demand Response Estimation based on Aggregate Data from Heterogeneous Users

Demand Response Estimation based on Aggregate Data from Hete...

引用

Mediterranean Conference on Control and Automation

作者： Donatello Materassi Mardavij Roozbehani Munther A. Dahleh Department of Electrical Engineering and Computer Science University of Tennessee Laboratory for Information and Decision Systems is with Massachusetts Institute of Technology

ISBN: (纸本)9781467383479

The article presents methodologies for the pre-diction of the aggregate consumption of a large number of heterogeneous energy users with deferrable loads. It is assumed that the users respond to an identical coordinating signal (e.g. a price) broadcast by the system operator. The main contributions of the article are two: (i) the presence of heterogeneous users is explicitely addressed by considering the possibility of several "classes" of consumers;(ii) the described methodologies provide predictions and estimates that have the advantage of making use of aggregate data only. When a dynamic response mechanism is implemented, the presence of consumers with deferrable loads introduces memory in the system in the form of the backlogged demand that has to be satisfied in the near future. From the perspective of the system operator, an accurate estimate of the current backlogged demand is of paramount importance, since it allows one to better predict what the aggregate consumption will be for a given coordinating signal. Thus, mathematical models need to be derived in order to predict future aggregate consumption using the accessible information. Unfortunately, consumers tends to be highly heterogeneous, depending on several factors including individual preferences, the interrupt-ability or the criticality of the tasks and the presence of hard deadlines. These factors can not be measured directly. Indeed, both privacy issues and practical constraints on processing and communicating data are likely to prevent utility companies and system operators from collecting and using measurements at the individual user level. Thus, methodologies for predicting aggregate demand response from aggregate data, such as the ones suggested in the article, can help overcome all these challenges.

关键词： Aggregates Load management Markov processes Mathematical model Data privacy Probabilistic logic Optimization

来源：评论

学校读者我要写书评

暂无评论

A Reputation-Aware Randomization Consensus Algorithm for Performance Optimization in Blockchain systems

A Reputation-Aware Randomization Consensus Algorithm for Per...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Jingyu Zhang Yongtao Sun Zhennan Zhang Weifeng Ren Lailong Luo School of Computer and Communication Engineering Changsha University of Science and Technology Changsha China Science and Technology on Information Systems Engineering Laboratory School of Systems Engineering National University of Defense Technology Changsha China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Blockchain technology, due to its decentralized, traceable, and tamper-resistant characteristics, has been applied in a wide range of collaborative computing scenarios, including smart grid, industrial production, and smart cities. Consensus algorithm, as the key blockchain technology, plays a decisive role in terms of performance, security, and scalability, ensuring that system nodes reach consensus on transaction data. However, with the increase of user nodes and the diversity of application scenarios, existing consensus algorithms face some performance and security challenges. To overcome these challenges, this article proposes a novel blockchain consensus mechanism, namely the Reputation-Aware Randomization Consensus Algorithm (RRCA). The proposed mechanism first constructs a dynamic reputation evaluation model to divide nodes into ordinary ones and candidate ones. Secondly, a selection model is constructed for candidate nodes to select consensus nodes, which run the consensus algorithm. Finally, a random selection mechanism for the leader node of the proposed consensus algorithm is constructed to ensure the unpredictability and reduce the probability of the leader node being subjected to malicious attacks. Theoretical analysis and experimental results indicate that the RRCA can significantly reduce consensus latency and increase the unpredictability of the leader node, which improves the performance and security of blockchain systems.

关键词： Smart cities Federated learning Scalability Evaluation models Consensus algorithm Production Blockchains

来源：评论

学校读者我要写书评

暂无评论

BTDFS: B+ Tree-Based Distributed File Storing Mechanism for Improving Small File Storage

BTDFS: B+ Tree-Based Distributed File Storing Mechanism for ...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Jingyu Zhang Jiachen Tian Lailong Luo School of Computer & Communication Engineering Changsha University of Science & Technology Changsha China Science and Technology on Information Systems Engineering Laboratory School of Systems Engineering National University of Defense Technology Changsha China

Hadoop is currently the most popular big data processing architecture, which provides a processing framework for managing and analyzing massive data. Hadoop Distributed File System (HDFS) is the core component for storing data in the Hadoop systems. It performs well when storing and managing large-sized files. However, it shows extremely bad performance when dealing with a large number of small files, which is reflected in the consumption of a large amount of memory space of the NameNode node and the low efficiency of accessing small files. Archive file is proposed to solve this problem. It combines small files into larger merged files for storage, and uses index files to record the relevant information of small files in the merged files. However, archive files (e.g., Hadoop Archive, MapFile) all require additional processing and multiple I/O operations to obtain index information before actually accessing the file content, which reduces the efficiency of file access. This paper proposes a novel distributed file storing mechanism called B+ Tree-Based Distributed File Storing mechanism (BTDFS), which combines a large number of small files into a merged file, records the index information of the small files in the merged file, and organizes the index information into a B+ tree for storage. Using BTDFS, while reducing the metadata consumption of the NameNode node, improves the access performance of a single small file with additional abilities, which provides convenience for analyzing a large number of small files. Finally, this paper designs corresponding experiments for the proposed BTDFS, and tests and analyzes the memory usage in N ameN ode and the access performance of small files. The experimental results show that the proposed BTDFS can effectively reduce the memory usage of the NameNode, and the efficiency of accessing small files is improved compared with state-of-the-art methods.

关键词： File systems Memory management Distributed databases Big Data Metadata Indexing

来源：评论

学校读者我要写书评

暂无评论

A Novel Technique to Parameterize Congestion Control in 6TiSCH IIoT Networks

arXiv

引用

arXiv 2024年

作者： Chakraborty, Kushal Dutta, Aritra Kumar Hussain, Mohammad Avesh Mohiuddin, Syed Raafay Choudhury, Nikumani Matam, Rakesh Mukherjee, Mithun Dept. of Computer Science & Information Systems Birla Institute of Technology & Science Hyderabad Pilani India Dept. of Computer Science & Engineering Indian Institute of Information Technology Guwahati India Nanjing University of Information Science and Technology Nanjing China

The Industrial Internet of Things (IIoT) refers to the use of interconnected smart devices, sensors, and other technologies to create a network of intelligent systems that can monitor and manage industrial processes. 6TiSCH (IPv6 over the Time Slotted Channel Hopping mode of IEEE 802.15.4e) as an enabling technology facilitates low-power and low-latency communication between IoT devices in industrial environments. The Routing Protocol for Low power and lossy networks (RPL), which is used as the de-facto routing protocol for 6TiSCH networks is observed to suffer from several limitations, especially during congestion in the network. Therefore, there is an immediate need for some modifications to the RPL to deal with this problem. Under traffic load which keeps on changing continuously at different instants of time, the proposed mechanism aims at finding the appropriate parent for a node that can forward the packet to the destination through the least congested path with minimal packet loss. This facilitates congestion management under dynamic traffic loads. For this, a new metric for routing using the concept of exponential weighting has been proposed, which takes the number of packets present in the queue of the node into account when choosing the parent at a particular instance of time. Additionally, the paper proposes a parent selection and swapping mechanism for congested networks. Performance evaluations are carried out in order to validate the proposed work. The results show an improvement in the performance of RPL under heavy and dynamic traffic loads. © 2024, CC BY.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Physics-Informed Neural Networks for Solving Blood Flows

Physics-Informed Neural Networks for Solving Blood Flows

引用

International Conference on Advanced Communication Technology (ICACT)

作者： Yao-Chung Chang Yu-Shan Lin Jeu-Jiun Hu Department of Computer Science and Information Engineering National Taitung University Taitung Taiwan Department of Information Science and Management Systems University Rd. Taitung Taiwan

The Physics-informed Neural Networks Deep Learning (PINN) framework has been introduced with the primary objective of advancing the field of blood flow simulations. PINN Deep Learning involves data-driven training for flow prediction and can incorporate the understanding of physical laws described by partial differential equations (PDEs). This paper employs the PINN Method for simulating blood flows. Multiple test cases will be computed and compared with other numerical and experimental results to validate the approach. The results demonstrate that the PINN method functions as expected, and validation against experimental and other researchers' results ensures the generation of meaningful output data and the prudent selection of parameters.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implementing Deep Learning Techniques into Healthcare System Improvement 2

Implementing Deep Learning Techniques into Healthcare System...

引用

2nd International Conference on Electronics and Renewable systems, ICEARS 2023

作者： Kochhar, Harmeet Kaur Kilaru, Mrudula Aljohani, Nasser Goyal, Himanshu Rai Singh, Devendra Saini, DilipKumar Jang Bahadur Chandigarh University University Institute of Media Studies India Velagapudi Ramakrishna Siddhartha Engineering College India Islamic University of Madinah Information Systems Department Madinah Saudi Arabia Graphic Era Deemed to Be University Department of Computer Science and Engineering Uttarakhand Dehradun248002 India Uttaranchal University Uttaranchal Institute of Technology Uttarakhand Dehradun India Sawmi Rama Himalayan University Department of Computer Science and Engineering Dehradun India

ISBN: (纸本)9798350346640

Artificial intelligence (AI) has the potential to transform clinical decision-making and assistance. In any case, the utilization of current AI methods remains only as a supportive solution to make clinical decisions. The existing methodologies fail to perform in-depth analysis to deliver accurate predictions. This study reviews the integration of advanced technologies AutoML in healthcare sector by considering the data privacy, heterogeneity and interpretability. This review will be a useful resource for medical practitioners interested in applying information science methods to their field of study. © 2023 IEEE.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Towards Perso-Arabic Urdu Language Hate Detection Using Machine Learning: A Comparative Study Based on a Large Dataset and Time-Complexity 22

Towards Perso-Arabic Urdu Language Hate Detection Using Mach...

引用

Proceedings of the 26th Pan-Hellenic Conference on Informatics

作者： Mohsan Ali Ali Muhammad Muhammad Asad Makhdoom Sajawal Charalampos Alexopoulos Yannis Charalabidis Department of Information and Communications Systems Engineering University of the Aegean Greece Department of Computer Science Air University Pakistan

ISBN: (纸本)9781450398541

Social media users are growing daily, with hundreds of millions of active users per month on certain networking sites. For any administrative institution, the manual method for regulating user content is challenging. There are hundreds of languages through which you can direct your attention on the web. The Urdu language is among the most widely utilized languages in the world. We have proposed a quick way of detecting the content of Urdu language hate using machine learning models. We used the open data set and manually created instances to make this investigation viable on a balanced data set. Our experimental set-up has demonstrated that support vector machine in the detection of Urdu hatred detection is 81.87% accurate. The training time, testing time, and accuracy helped us select the best model for Urdu hate detection on social media sites. We also compared the training and testing times of various methods. Additionally, we demonstrated k and stratified folding via indexing to provide a better understanding of folding in machine learning. Finally, we compared our findings to those of previously published works in the field of Urdu hate detection.

关键词： Machine Learning Natural Language Processing Hatred Content Detection Urdu Speech

来源：评论

学校读者我要写书评

暂无评论

Domain Transfer SVM for video concept detection

Domain Transfer SVM for video concept detection

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Lixin Duan Ivor W. Tsang Dong Xu Stephen J. Maybank School of Computer Engineering Nanyang Technological University Singapore School of Computer Science and Information Systems Birkbeck College University of London UK

Cross-domain learning methods have shown promising results by leveraging labeled patterns from auxiliary domains to learn a robust classifier for target domain, which has a limited number of labeled samples. To cope with the tremendous change of feature distribution between different domains in video concept detection, we propose a new cross-domain kernel learning method. Our method, referred to as Domain Transfer SVM (DTSVM), simultaneously learns a kernel function and a robust SVM classifier by minimizing both the structural risk functional of SVM and the distribution mismatch of labeled and unlabeled samples between the auxiliary and target domains. Comprehensive experiments on the challenging TRECVID corpus demonstrate that DTSVM outperforms existing cross-domain learning and multiple kernel learning methods.

关键词： Support vector machines Kernel Support vector machine classification Learning systems Robustness Testing Training data Multimedia communication Broadcasting Humans

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：