检索结果-内蒙古大学图书馆

International Conference on Green engineering Technology and Applied Computing 2019, IConGETech2 019 and International Conference on Applied Computing 2019, ICAC 2019

作者： Akma Abu Bakar, Noor Abdul Majid, Mazlina Adam, Khalid Faculty of Computer Systems and Software Engineering Universiti Malaysia Pahang Malaysia Faculty of Electric and Electronic Engineering Universiti Malaysia Pahang Malaysia

The operational research (OR) become one of emerging areas and significance and its relevance to be used in the simulation and modelling. To simulating and modelling the crowd evacuation, the most important elements to have in a realistic model is the appropriate simulation technique. To simulate the evacuee's movement in crowd is still in research and challenge because of the emergence and become a complex task and dangerous for the real and actual case. The computational simulation technique is required in order to model the crowd evacuation as one part of OR and become a solution to represent the fire crowd evacuation in the closed space e.g. Building relates to human movement and its states. The theories and concept of computational method allows for creating, analysing and experimentation. The techniques;Agent-Based Simulation (ABS), Social Force Model (SFM) and the hybrid SFM/ABS has been proposed for this research work. SFM is the well-known and popular technique for crowd evacuation while ABS is best-known, intelligent and appropriate to imitate the human movement. This paper provides a review of this research work from an OR perspective and the outcomes of a review of the computational simulation techniques literature are presented, using a proposed conceptual model will be valuable for future researchers, and modellers alike. © 2019 Published under licence by IOP Publishing Ltd.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

FEDCSD: A FEDERATED LEARNING BASED APPROACH FOR CODE-SMELL DETECTION

arXiv

引用

arXiv 2023年

作者： Alawadi, Sadi Alkharabsheh, Khalid Alkhabbas, Fahed Kebande, Victor Awaysheh, Feras M. Palomba, Fabio Awad, Mohammed Center for Applied Intelligent Systems Research School of Information Technology Halmstad University Halmstad Sweden Department of Software Engineering Prince Abdullah bin Ghazi Faculty of Information and Communication Technology Al-Balqa Applied University Jordan Internet of Things and People Research Center Malmö University Sweden Department of Computer Science Blekinge Institute of Technology Sweden Institute of Computer Science Delta Research Centre University of Tartu Estonia SeSa Lab University of Salerno Italy Arab American University Palestine Palestine

software quality is critical, as low quality, or "Code smell," increases technical debt and maintenance costs. There is a timely need for a collaborative model that detects and manages code smells by learning from diverse and distributed data sources while respecting privacy and providing a scalable solution for continuously integrating new patterns and practices in code quality management. However, the current literature is still missing such capabilities. This paper addresses the previous challenges by proposing a Federated Learning Code Smell Detection (FedCSD) approach, specifically targeting "God Class," to enable organizations to train distributed ML models while safeguarding data privacy collaboratively. We conduct experiments using manually validated datasets to detect and analyze code smell scenarios to validate our approach. Experiment 1, a centralized training experiment, revealed varying accuracies across datasets, with dataset two achieving the lowest accuracy (92.30%) and datasets one and three achieving the highest (98.90% and 99.5%, respectively). Experiment 2, focusing on cross-evaluation, showed a significant drop in accuracy (lowest: 63.80%) when fewer smells were present in the training dataset, reflecting technical debt. Experiment 3 involved splitting the dataset across 10 companies, resulting in a global model accuracy of 98.34%, comparable to the centralized model’s highest accuracy. The application of federated ML techniques demonstrates promising performance improvements in code-smell detection, benefiting both software developers and researchers. Copyright © 2023, The Authors. All rights reserved.

关键词： computer software selection and evaluation

来源：评论

学校读者我要写书评

暂无评论

BigData: Issues, Challenges, Technologies and Methods 1

引用

2nd International Conference on Advanced Data and Information engineering, DaEng 2015

作者： Adam, Khalid Fakharaldien, Mohammed Adam Ibrahim Zain, Jasni Mohamed Majid, Mazlina Abdul Noraziah, Ahmad Faculty of Computer Systems and Software Engineering University Malaysia Pahang Gambang KuantanPahang26300 Malaysia

ISBN: (数字)9789811317996

ISBN: (纸本)9789811317972

With dramatically increase of emerging applications such as social media, sensors, videos and digital pictures data is become generating from everywhere. Due to characteristic of big data it becomes very difficult to manage, analysis, store, transport, and process the data using the existing traditional techniques. This paper introduces several Big Data, technologies and methods. First, we introduce the Big Data and its problem, important of Big Data, technologies and methods of Big Data management, and analyzed includes the Distributed File System, NOSQL Database, Hadoop/MapReduce. Next, we present the Big Data model;and discuss the Big Data security challenges. Finally, we present the future work and the conclusion. © Springer Nature Singapore Pte Ltd. 2019.

关键词： MapReduce

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Behavior Modelling for Demand Side Recommender System in Solar Microgrid Applications Using Multi Agent Reinforcement Learning Model

SSRN

引用

SSRN 2022年

作者： Onile, Abiodun Emmanuel Belikov, Juri Levron, Yoash Petlenkov, Eduard Department of Software Science Tallinn University of Technology Akadeemia tee 15a Tallinn12618 Estonia The Andrew and Erna Viterbi Faculty of Electrical Engineering Technion—Israel Institute of Technology Haifa3200003 Israel Department of Computer Systems Tallinn University of Technology Akadeemia tee 15a Tallinn12618 Estonia

Electricity consumers are often faced with challenges relating the choice of optimal energy saving plan, increasing integration of transient’s renewable sources of energy promises tantalizing solution which also constitutes emerging stability challenges for the electricity Grid. Demand side management using Battery storage as grid balancing measures are crucial towards extending physical limits of existing electricity grid. On the one hand, battery storage is assuming a critical role in decarbonization efforts partly due to its tendencies to store excess electricity obtained via renewable energy sources thus enabling unlimited potentials for seasonal storage. On the other hand, while solving the identified problem, other problems relating consumer behavior towards adoption of energy/battery efficiency technologies, consumers comfort-feedback and control loop integration exist. In this study, we presented electricity energy storage (EES) technologies which are embedded into the grid and further enhanced with the use of Reinforcement learning control and recommendation system technologies for improving the grid management, the grid reliability and sustainability, mitigated operational issues, improved BESS utilization and attain self-consumption goals. The result of the study shows that operating the BESS using the multi-agent RL control strategy achieved a maximum peak load reduction of about 24.5% alongside 94% comfort improvements in certain loads. © 2022, The Authors. All rights reserved.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Unified resilience model using deep learning for assessing power system performance

引用

Heliyon 2025年第4期11卷 e42802页

作者： Artemchuk, Volodymyr Garbuz, Iurii Jamil Alsayaydeh, Jamil Abedalrahim Shkarupylo, Vadym Oliinyk, Andrii Bin Yusof, Mohd Faizal Herawan, Safarudin Gazali Department of Mathematical and Econometric Modelling G.E. Pukhov Institute for Modelling in Energy Engineering of the NAS of Ukraine Kyiv Ukraine Department of Environmental Protection Technologies and Radiation Safety Center for Information-analytical and Technical Support of Nuclear Power Facilities Monitoring of the NAS of Ukraine Kyiv Ukraine Department of Іnformation Systems in Economics Kyiv National Economic University Named After Vadym Hetman Kyiv Ukraine Department of Computerized Control System National Aviation University Kyiv Ukraine Department of Engineering Technology Fakulti Teknologi Dan Kejuruteraan Elektronik Dan Komputer (FTKEK) Universiti Teknikal Malaysia Melaka (UTeM) Melaka 76100 Malaysia Department of Computer Systems Networks and Cybersecurity of the National University of Life and Environmental Sciences of Ukraine Kyiv Ukraine Department of Software Tools Faculty of Computer Science and Technology Zaporizhzhia Polytechnic National University Zaporizhzhia Ukraine Research Section Faculty of Resilience Rabdan Academy Abu Dhabi United Arab Emirates Industrial Engineering Department Faculty of Engineering Bina Nusantara University Jakarta 11480 Indonesia

Energy resilience in renewable energy sources dissemination components such as batteries and inverters is crucial for achieving high operational fidelity. Resilience factors play a vital role in determining the performance of power systems, regardless of their operating environment and interruptions. This article introduces a Unified Resilience Model (URM) using Deep Learning (DL) to enhance power system performance. The proposed model analyzes environmental factors impacting the resilience of batteries and energy storage devices. This deep learning approach trains performance-impacting factors using previously known low resilience drain data. The learning output is utilized to augment various strengthening factors, thereby improving resilience. Drain mitigation and performance improvements are combined for direct impact verification. This process validates the model's fidelity in enhancing power system performance, with a specific focus on the impact of weather factors. © 2025 The Authors

关键词： Deep learning Energy resilience Fidelity Weather impact

来源：评论

学校读者我要写书评

暂无评论

BG-GAN: Generative AI Enable Representing Brain Structure-Function Connections for Alzheimer's Disease

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Zhou, Tong Ding, Chen Jing, Changhong Liu, Feng Hung, Kevin Pham, Hieu Mahmud, Mufti Lyu, Zhihan Qiao, Sibo Wang, Shuqiang Tsang, Kim-Fung Chinese Academy of Sciences Shenzhen Institutes of Advanced Technology Shenzhen518055 China University of Chinese Academy of Sciences Beijing100864 China Stevens Institute of Technology Department of Systems and Enterprises United States Hong Kong Metropolitan University School of Science and Technology Hong Kong Hong Kong VinUniversity College of Engineering and Computer Science VinUni-Illinois Smart Health Center Viet Nam King Fahd University of Petroleum and Minerals Interdisciplinary Research Center for Biosystems and Machines Department of Information and Computer Science SDAIA-KFUPM Joint Research Center for AI Dhahran Saudi Arabia Uppsala University Department of Game Design Faculty of Arts Sweden Tiangong University School of Software Tianjin300387 China

The relationship between brain structure and function is critical for revealing the pathogenesis of brain disorders, including Alzheimer's disease (AD). However, mapping brain structure to function connections is a very challenging task. In this work, a bidirectional graph generative adversarial network (BG-GAN) is proposed to represent brain structure-function connections. Specifically, by designing a module incorporating inner graph convolution network (InnerGCN), the generators of BG-GAN can employ features of direct and indirect brain regions to learn the mapping function between the structural domain and the functional domain. Besides, a new module named Balancer is designed to counterpoise the optimization between generators and discriminators. By introducing the Balancer into BG-GAN, both the structural generator and functional generator can not only alleviate the issue of mode collapse but also learn complementarity of structural and functional features. Experimental results using Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset show that both generated structure and function connections can improve the identification accuracy of AD. The experimental findings suggest that the relationship between brain structure and function is not a complete one-to-one correspondence. They also suggest that brain structure is the basis of brain function, and the strong structural connections are majorly accompanied by strong functional connections. © 2025 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Pl-Densenet: Enhancing Disease Classification in Pear Leaves Using Deep Learning

SSRN

引用

SSRN 2023年

作者： Gulzar, Yonis Ünal, Zeynep Ayoub, Shahnawaz Wani, Sharyar Mir, Mohammad Shuaib Soomro, Arjumand Bano Department of Management Information Systems College of Business Administration King Faisal University Al-Ahsa31982 Saudi Arabia Department of Biosystem Engineering Niğde Ömer Halisdemir University Central Campus Türkiye Niğde51240 Turkey Mirzapur Pole U.P. Saharanpur247121 India Department of Computer Science Kulliyyah of Information and Communication Technology International Islamic University Malaysia Kuala Lumpur53100 Malaysia Department of Software Engineering Faculty of Engineering and Technology University of Sindh Sindh Pakistan

Over the past two decades, climate changes have negatively impacted agriculture. It hasn’t left any stage of production unaffected. These noticeable changes have left formers no choice but to adopt new technological measures to tackle such changes. Deep learning has played a great role in improving decision-making in agriculture. This research introduces a novel deep learning model, PL-DenseNet, designed to accurately identify various disease types present in pear leaves. The PL-DenseNet model is an adaptation of the original DenseNet architecture, incorporating significant modifications to enhance its disease classification capabilities. The modifications involve replacing the classification layer of the DenseNet with three additional layers: Global Average Pooling 2D, Batch Normalization, and Dropout layers. Moreover, the final layer of the PL-DenseNet model comprises four nodes dedicated to classifying pear leaf diseases. The integration of these modifications aims to improve disease identification accuracy and enhance overall classification performance within the context of pear leaf diseases. The PL-DenseNet model also incorporated transfer learning and data augmentation to increase the variety and quantity of training data. The model's performance was evaluated on the DiaMOS Plant dataset, which comprises four different pear leaf diseases under real field conditions with varying brightness, disease similarity, complex background, and multiple leaves. Experimental evaluation reveals that the proposed PL-DenseNet model achieves notable advancements compared to the baseline model. It demonstrates higher accuracy (99.18%), precision (98.83), recall (99.06), and F1-score (93.58). Additionally, the proposed model surpasses other state-of-the-art models, including EfficientNetB0, InceptionV2, MobileNetV2, ResNet50, and VGG16, underscoring its superior performance in disease classification. Moreover, this research demonstrates how transfer learning and data augmentati

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Quantum-optimal Frequency Estimation of Stochastic AC Fields

arXiv

引用

arXiv 2024年

作者： Dey, Anirban Mouradian, Sara Lupo, Cosmo Huang, Zixin School of Mathematical and Physical Sciences Macquarie University NSW2109 Australia ARC Centre of Excellence for Engineered Quantum Systems Macquarie University NSW2109 Australia Department of Electrical and Computer Engineering University of Washington 98195 United States Dipartimento Interateneo di Fisica Politecnico di Bari Bari70126 Italy Dipartimento Interateneo di Fisica Università di Bari Bari70126 Italy INFN Sezione di Bari Bari70126 Italy Centre for Quantum Software and Information Faculty of Engineering and Information Technology University of Technology SydneyNSW2007 Australia

Classically, measurement bandwidth limits the achievable frequency resolution of stochastic time-dependent fields. We frame the problem of frequency measurement as the estimation of the noise parameter of a dephasing quantum channel. Using this framework, we find an exact upper bound for estimating frequency centroids and separations. In particular, given two closely separated frequencies with separation ωr, the quantum Fisher information (QFI) upper bound is approximately 2/ωr2, inversely proportional to the separation parameter. We show that this is achievable with a superposition of Dicke states, and show that GHZ states improve precision over unentangled states, achieving Heisenberg scaling in the low-bandwidth limit. This work established a robust framework for stochastic AC signal sensing and can be extended to an arbitrary number of frequencies. Copyright © 2024, The Authors. All rights reserved.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Short-time simulation of quantum dynamics by Pauli measurements

arXiv

引用

arXiv 2024年

作者： Faehrmann, Paul K. Eisert, Jens Kieferová, Mária Kueng, Richard Dahlem Center for Complex Quantum Systems Freie Universität Berlin Berlin14195 Germany Institute for Integrated Circuits and Quantum Computing Johannes Kepler University Linz Austria Helmholtz-Zentrum Berlin für Materialien und Energie Hahn-Meitner-Platz 1 Berlin14109 Germany Fraunhofer Heinrich Hertz Institute Berlin10587 Germany Centre for Quantum Software and Information School of Computer Science Faculty of Engineering & Information Technology University of Technology SydneyNSW2007 Australia

Simulating the dynamics of complex quantum systems is a central application of quantum devices. Here, we propose leveraging the power of measurements to simulate short-time quantum dynamics of physically prepared quantum states in classical post-processing using a truncated Taylor series approach. While limited to short simulation times, our hybrid quantum-classical method is equipped with rigorous error bounds. It is extendable to estimate low-order Taylor approximations of smooth, time-dependent functions of tractable linear combinations of measurable operators. These insights can be made use of in the context of Hamiltonian learning and device verification, short-time imaginary time evolution, or the application of intractable operations to sub-universal quantum simulators in classical post-processing. © 2024, CC BY.

关键词： Hamiltonians

来源：评论

学校读者我要写书评

暂无评论

FeSiCr添加对羰基铁磁粉心磁性能与温度稳定性的影响

引用

磁性材料及器件 2024年

作者：王雨孙小龙杨陆董鑫武文杰陈劲松邬传健曾涛李子鸣西南应用磁学研究所四川省磁性材料工程技术研究中心电子科技大学材料与能源学院 Faculty of Software Engineering and Computer Systems， ITMO University

以羰基铁粉为基体添加不同比例的FeSiCr软磁粉末，添加固定比例的酚醛树脂进行有机绝缘包覆，然后将其制备成羰基铁/FeSiCr复合磁粉心材料。研究了FeSiCr粉末添加量对磁粉心材料微观形貌、致密性、技术磁化性能、高频软磁性能以及磁导... 详细信息

以羰基铁粉为基体添加不同比例的FeSiCr软磁粉末，添加固定比例的酚醛树脂进行有机绝缘包覆，然后将其制备成羰基铁/FeSiCr复合磁粉心材料。研究了FeSiCr粉末添加量对磁粉心材料微观形貌、致密性、技术磁化性能、高频软磁性能以及磁导率温度稳定性等性能的影响。结果表明，羰基铁/FeSiCr复合磁粉心的密度、比饱和磁化强度和磁导率温度系数随着FeSiCr粉末添加添加量提升发生了显著改善，而高频磁导率、矫顽力以及Q值未随FeSiCr粉末添加得到优化。当FeSiCr为25%时，羰基铁/FeSiCr复合磁粉心综合性能最优，此时复合磁粉心磁导率为12.5(@1 MHz)、比饱和磁化强度为196.17 emu/g、Q最大值为176.64(@3 MHz)以及磁导率温度系数为72.95 ppm/℃。

关键词：羰基铁粉 FeSiCr粉添加复合磁粉心高频软磁性能磁导率温度系数

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：