检索结果-内蒙古大学图书馆

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Nikolaos Efkarpidis Martin Geidl Chen-Wei Yang Andrija Goranović Stefan Wilker Thilo Sauter Ingo Herbst Institute of Electric Power Systems University of Applied Sciences and Arts Northwestern Switzerland Windisch Switzerland Department of Computer Science Electrical and Space Engineering Lule&#x00E5 University of Technology TU Wien Institute of Computer Technology Department of Smart Infrastructure Siemens Switzerland

ISBN: (数字)9781665482400

ISBN: (纸本)9781665482417

Nowadays, an increasing focus is placed on the development of smart energy systems (SESs) that combine a variety of heterogeneous sub-systems with largely varying applications. Due to their multidisciplinary nature, there are no universally accepted standards assessing their performance. Previous efforts typically define Key Performance Indicators (KPIs) only for specific SES types and application areas. This paper presents a robust KPI framework that can be applied to any SES type regardless of the application area. The proposed framework consists of four layers following the top-down approach. The layers define the application area, SES requirements, main stakeholders involved specifying their objectives and finally, the KPIs for each of the stakeholders' objectives. The proposed KPI framework is applied on the use cases of a European research project with different application areas showing its features.

关键词： Industrial electronics Key performance indicator Europe Stakeholders Standards

来源：评论

学校读者我要写书评

暂无评论

Utilizing Artificial Intelligence for Plant Phenotyping in Soilless Farming: An Innovative Deep Learning Approach on a Unique Dataset

Utilizing Artificial Intelligence for Plant Phenotyping in S...

引用

Smart Power Control and Renewable Energy (ICSPCRE), IEEE International Conference on

作者： D Jaya Narayana Reddy Krishna Priya R J. Arun Kumar P. Dharani Prasad Mustafa Nawaz Nookala Venu G Pullaiah College of Engineering and Technology Research and Consultancy Department University of Technology and Applied Sciences Governorate of Musandam Sultanate of Oman Department of ECE Vel Tech Rangarajan Sagunthala R&D Institute of Science and Technology Dept of Pharmacology Mohan Babu University MB School of Pharmaceutical sciences (Erstwhile Sree Vidyaniketan College of Pharmacy) Tirupati Department of Computer Science and Engineering Sri Sairam Institute of Technology Centre for IoT Madhav Institute of Technology & Science (MITS) (A Govt. Aided UGC Autonomous Institute) Gwalior Madhya Pradesh India

ISBN: (数字)9798350377002

ISBN: (纸本)9798350377019

In the dynamic landscape of agriculture, the convergence of technological advancements and sustainable practices has become imperative. The emergence of soilless farming, driven by hydroponics and aeroponics, presents a promising solution to address food security challenges while mitigating environmental concerns. Central to the success of soilless farming is efficient plant phenotyping, which traditionally relies on labour-intensive methodologies. However, this paradigm is shifting with the integration of Artificial Intelligence (AI) and Deep Learning techniques. This research endeavours to pioneer an innovative approach to plant phenotyping in soilless farming by harnessing the power of AI. Leveraging a unique dataset meticulously curated from controlled hydroponic and aeroponic environments, our study aims to redefine the boundaries of agricultural research and practice. By employing state-of-the-art Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), we dissect complex phenotypic traits encompassing leaf morphology, biomass accumulation, and physiological responses. Through iterative model refinement and validation, we strive to develop a robust framework capable of real-time phenotypic assessment across diverse plant species and growth stages. By synthesizing diverse environmental conditions and perturbations, we augment the original dataset, enhancing model generalization and adaptability. Moreover, through transfer learning techniques, Furthermore, the scalability and accessibility of AI technologies pave the way for democratizing agricultural innovation, fostering inclusive growth and resilience in the face of global challenges.

关键词： Deep learning Technological innovation Recurrent neural networks Plants (biology) Biological system modeling Scalability Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Explainable Artificial Intelligence to Detect Image Spam Using Convolutional Neural Network

Explainable Artificial Intelligence to Detect Image Spam Usi...

引用

Cyber Resilience (ICCR), International Conference on

作者： Zhibo Zhang Ernesto Damiani Hussam Al Hamadi Chan Yeob Yeun Fatma Taher Department of Electrical Engineering and Computer Science C2PS Khalifa University Abu Dhabi United Arab Emirates Department of Computing and Applied Technology Zayed University Dubai United Arab Emirates

ISBN: (数字)9781665461221

ISBN: (纸本)9781665461238

Image spam threat detection has continually been a popular area of research with the internet's phenomenal expansion. This research presents an explainable framework for detecting spam images using Convolutional N eural Network (CNN) algorithms and Explainable Artificial Intelligence (XAI) algorithms. In this work, we use CNN model to classify image spam respectively whereas the post-hoc XAI methods including Local Interpretable Model Agnostic Explanation (LIME) and Shapley Additive Explanations (SHAP) were deployed to provide explanations for the decisions that the black-box CNN models made about spam image detection. We train and then evaluate the performance of the proposed approach on a 6636 image dataset including spam images and normal images collected from three different publicly available email corpora. The experimental results show that the proposed framework achieved satisfactory detection results in terms of different performance metrics whereas the model-independent XAI algorithms could provide explanations for the decisions of different models which could be utilized for comparison for the future study.

关键词： Measurement Additives Unsolicited e-mail Closed box Classification algorithms Convolutional neural networks Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

An electrical model characterization of an electronic nose chemical sensor using a programmable system-on-a-chip based AFE

An electrical model characterization of an electronic nose c...

引用

2022 International Young Engineers Forum in Electrical and computer engineering, YEF-ECE 2022

作者： Santos, Joao J.M. Palma, Susana I.C.J. Esteves, Carina Gamboa, Hugo Oliveira, Joao Pedro Roque, Ana C.A. Department of Electrical and Computer Engineering Nova School of Science and Technology Nova University of Lisbon Caparica2829-516 Portugal Associate Laboratory i4HB Institute for Health and Bioeconomy Nova School of Science and Technology Nova University of Lisbon Caparica2829-516 Portugal Ucibio Applied Molecular Biosciences Unit Department of Chemistry Nova School of Science and Technology Nova University of Lisbon Caparica2829-516 Portugal LIBPhys - Laboratory for Instrumentation Biomedical Engineering and Radiation Physics Nova School of Science and Technology Nova University of Lisbon Caparica2829-516 Portugal Uninova Nova School of Science and Technology Nova University of Lisbon Caparica2829-516 Portugal

ISBN: (纸本)9781665467315

The diagnosis of many diseases involves invasive detection methods, which are both painful and stressing for patients. In the last decades, the ever-growing development in electronic nose (E-Nose) technology made them great candidates for non-invasive disease detection methods. Such devices mimic the human olfactory system through a set of sensors which produce signals that can be associated with diseases. Recently, a class of low-cost and innovative ionogel sensors, developed by our group demonstrated their full applicability in E-Nose systems, opening a new and promising approach to the field. However, the operation of such sensor needs a background calibration phase which relies on the correct characterization and parameterization of the corresponding electrical sensor *** paper proposes a model characterization methodology based on a set of frequency responses acquisitions of the sensor, under several humidity conditions. To obtain a flexible acquisition tool capable of acquiring accurate results, an analog front-end (AFE) circuit to interface with the interdigitated electrode (IDE) sensors is presented. Such AFE circuit is fully implemented using a programmable system-on-a-chip (PSoC), helping to reduce system size and cost. Lastly, a comparison between the electrical model and data acquired with the proposed system is presented. © 2022 IEEE.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Multi-GeV Electron Bunches from an All-Optical Laser Wakefield Accelerator

引用

Physical Review X 2022年第3期12卷 031038-031038页

作者： B. Miao J. E. Shrock L. Feder R. C. Hollinger J. Morrison R. Nedbailo A. Picksley H. Song S. Wang J. J. Rocca H. M. Milchberg Institute for Research in Electronics and Applied Physics and Department of Physics University of Maryland College Park Maryland 20742 USA Department of Electrical and Computer Engineering Colorado State University Fort Collins Colorado 80523 USA John Adams Institute for Accelerator Science and Department of Physics University of Oxford OX1 3RH United Kingdom Physics Department Colorado State University Fort Collins Colorado 80523 USA Department of Electrical and Computer Engineering University of Maryland College Park Maryland 20742 USA

We present the first demonstration of multi-GeV laser wakefield acceleration in a fully optically formed plasma waveguide, with an acceleration gradient as high as 25 GeV/m. The guide was formed via self-waveguiding of <15 J, 45 fs (<∼ 300 TW) pulses over 20 cm in a low-density hydrogen gas jet, with accelerated electron bunches driven up to 5 GeV in quasimonoenergetic peaks of relative energy width as narrow as ∼15%, with divergence down to ∼1 mrad and charge up to tens of picocoulombs. Energy gain is inversely correlated with on-axis waveguide density in the range Ne0=(1.3–3.2)×1017 cm−3. We find that shot-to-shot stability of bunch spectra and charge are strongly dependent on the pointing of the injected laser pulse and gas jet uniformity. We also observe evidence of pump depletion-induced dephasing, a consequence of the long optical guiding distance.

关键词： Laser driven electron acceleration Laser wakefield acceleration

来源：评论

学校读者我要写书评

暂无评论

Robust, High-Rate Trajectory Tracking on Insect-Scale Soft-Actuated Aerial Robots with Deep-Learned Tube MPC

arXiv

引用

arXiv 2022年

作者： Tagliabue, Andrea Hsiao, Yi-Hsuan Fasel, Urban Kutz, J. Nathan Brunton, Steven L. Chen, YuFeng How, Jonathan P. Department of Aeronautics and Astronautics Massachusetts Institute of Technology United States Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology United States Department of Aeronautics Imperial College London United Kingdom Department of Applied Mathematics University of Washington United States Department of Mechanical Engineering University of Washington United States

Accurate and agile trajectory tracking in subgram Micro Aerial Vehicles (MAVs) is challenging, as the small scale of the robot induces large model uncertainties, demanding robust feedback controllers, while the fast dynamics and computational constraints prevent the deployment of computationally expensive strategies. In this work, we present an approach for agile and computationally efficient trajectory tracking on the MIT SoftFly [1], a sub-gram MAV (0.7 grams). Our strategy employs a cascaded control scheme, where an adaptive attitude controller is combined with a neural network policy trained to imitate a trajectory tracking robust tube model predictive controller (RTMPC). The neural network policy is obtained using our recent work [2], which enables the policy to preserve the robustness of RTMPC, but at a fraction of its computational cost. We experimentally evaluate our approach, achieving position Root Mean Square Errors (RMSEs) lower than 1.8 cm even in the more challenging maneuvers, obtaining a 60% reduction in maximum position error compared to [3], and demonstrating robustness to large external disturbances. © 2022, CC BY.

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

IoT Edge and Fog Computing Architecture for Educational Systems in Universities

IoT Edge and Fog Computing Architecture for Educational Syst...

引用

Current Development in engineering and Technology (CCET), IEEE International Conference on

作者： Shams Tabrez Siddiqui Md Oqail Ahmad Alighazi Siddiqui Haneef Khan Mohammad Rafeek Khan Ashjan Hamad Alsabhan Department of Computer Science College of CS & IT Jazan University Jazan Saudi Arabia Department of Computer Applications B.S Abdur Rahman Crescent Institute of Science and Technology Chennai Tamilnadu India Department of Computer and Network Engineering College of CS & IT Jazan University Jazan Saudi Arabia CST Department Applied College University of Hafr Al Batin Hafar al-Batin Saudi Arabia

Smart lights, ovens, and industrial data-gathering equipment are all instances of internet-connected gadgets. With 41.6 billion IoT devices being used, 79.4 ZB of data will be generated by 2025, according to research firm IDC. The earliest IoT gadgets sent information to the cloud for analysis. When sending many billions of gigabytes to the cloud, the data pipeline clogs up. With computing at the edge, IoT gadgets can analyze data without transferring it to a remote server. Data is handled locally, at the “edge” of your network, rather than being transmitted elsewhere. Technology's malleability makes it a valuable tool in the field of education. The specifications for edge computing in IoT networks vary from those of other networks. At the edge, well-suited setting to handle the massive volumes of devices and data generated by the Internet of Things. Several tasks can be moved to the device's edge, which can help keep costs down. The importance of IoT edge computing architecture in education has grown as a result of its deployment in real-time applications. The research simplifies the process of analyzing the structural layout of educational systems by proposing a framework for Internet of Things (IoT) Edge computing in the field of education. There will be a focus on concerns and issues with the IoT that will be brought out by the framework. In this research, potential and pitfalls of using IoT edge computing in education institutions is explored. In addition to this, the research article analyzes the effectiveness of edge computing for Internet of Things applications in an educational environment.

关键词： Productivity Cloud computing Education computer architecture Real-time systems Internet of Things Servers

来源：评论

学校读者我要写书评

暂无评论

Investigation and Countermeasure toward Unintentional Access to Docker Container

Investigation and Countermeasure toward Unintentional Access...

引用

Cybersecurity Conference (SVCC), Silicon Valley

作者： Yueyang Li Luyi Li Ruxue Luo Yuzhen Chen Arijet Sarker Sang-Yoon Chang Wenjun Fan School of Advanced Technology Xi’an Jiaotong-Liverpool University Suzhou Jiangsu P.R.China Computer Science Department College of Engineering and Applied Science University of Colorado Colorado Springs Colorado Springs CO United States Silicon Valley Cybersecurity Institute (SVCSI)

Due to the ease of management and the high performance of the containerization, many services have been deployed on container, e.g., Web server running in Docker. However, the Docker implementation suffers several fatal loopholes. In this paper, we perform a study on a persistent security problem of Docker, i.e., the port mapping statement results in a wrong IPTABLES rule, which has been disclosed for a while but is still not solved. Therefore, we are motivated to investigate and articulate this vulnerability with a technical explanation. Nevertheless, we proposed several solutions to address the problem. Further, we applied our network testbed for demonstrating the loophole and the effectiveness of the security solutions. We tested the performance of both attack and defense prototyping. The experimental results show that our approach not only increase the time cost for the attacker to identify the target but also bring negligible overhead for deploying the countermeasures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intra-Datacenter Load Balancing in a Federated Cloud with Throttled Algorithm

Intra-Datacenter Load Balancing in a Federated Cloud with Th...

引用

science, engineering and Business for Sustainable Development Goals (SEB-SDG), International Conference on

作者： Damola Gideon Akinola Emmanuel Adetiba Abdultaofeek Abayomi Uche Nnaji Surendra Thakur Sibusiso Moyo Department of Electrical and Information Engineering Covenant Applied Informatics and Communications African Center of Excellence Covenant University Ota Nigeria HRA Institute for Systems Science Durban University of Technology Durban South Africa Department of Information and Communication Technology Mangosuthu University of Technology Durban South Africa Dept. of Computer and Information Science Covenant Applied Informatics and Communications African Center of Excellence Covenant University Ota Nigeria KZN e-Skills CoLab Durban University of Technology Durban South Africa School for Data Science and Computational Thinking and Department of Mathematical Sciences Stellenbosch University Stellenbosch South Africa

ISBN: (数字)9798350358155

ISBN: (纸本)9798350358162

The emergence of cloud computing technology has motivated a very high number of users in different organizations to access its services in running and delivering their various operations and services. However, this surge of cloud users has led to the problem of uneven load sharing among the cloud computing infrastructures. As a result, federated cloud infrastructure was initiated to provide more cloud computing resources to accommodate more cloud users’ requests and also to provide equal requests mapping with the available cloud resources. Nevertheless, the issue of unequal allocation of requests within the datacenter(s) that makes up the federated cloud environment still persists. This research work presents an intra-datacenter load balancing algorithm in a federated cloud environment named; the intra-balancer adapted throttled algorithm to evenly distribute requests in each datacenter that formulate the federated cloud infrastructures. The simulation of the intra-balancer was carried out in CloudAnalyst, the results of the implementation showed that the intra-balancer outperformed the Round-Robin and ESCE with 98.93ms and 2.26ms for the response and processing time respectively. The results assert that the intra-balancer algorithm provides a better load balancing solution in a federated cloud environment.

关键词： computers Cloud computing Organizations Load management Resource management Time factors Task analysis

来源：评论

学校读者我要写书评

暂无评论

Spatial Attention Cooperative-Based Graph Convolutional Model for Person Re-Identification

SSRN

引用

SSRN 2023年

作者： Xiong, Mingfu Xiong, Jiefan Wang, Zhongyuan Chen, Jia Hu, Ruimin Ser, Javier Del Muhammad, Khan Xiong, Zixiang School of Computer Science and Artificial Intelligence Wuhan Textile University Wuhan430200 China School of Cyber Science and Engineering Wuhan University Wuhan430072 China Department of Applied Artificial Intelligence School of Convergence College of Computing and Informatics Sungkyunkwan University Seoul03063 Korea Republic of Derio48160 Spain Bilbao48013 Spain The Department of Electrical and Computer Engineering Texas A&M University College StationTX7784 United States

Recently, person re-identification (person Re-ID) equipped with an attention mechanism has gradually emerged as one of the most active areas of study in the field of computer vision and neural processing. Despite the upsurge in related research, existing attention-based methods still face two major challenges when recognizing different persons with similar appearances in unpredictable realistic environments: (1) the adaptability of a single local salient feature to hostile scenes cannot be guaranteed, and (2) most existing methods originating from attention features usually find a simple linear transformation or implement variation strategies, which makes it difficult to discriminate different pedestrians with similar appearance attributes. To address these issues, this paper proposes a spatial attention cooperative-based graph convolutional model (SACGCM) to examine the relevance of local body regions for individuals. The proposed framework encompasses a multi-dimensional attention model (MAM) and spatial adaptive graph convolutional model (SAGCM). In particular, the MAM comprises a dual-attention (local and global) module and feature channel-attention stage, which are used to capture multiple key points for each person. Then, SAGCM is used to construct spatial nonlinear transformation relationships among the various body regions for each person using graph optimization. Extensive experiments were conducted using public person Re-ID datasets (Market-1501, DukeMTMC-reid, and CUHK-03). The results demonstrate that the performance of the proposed approach is superior to that of state-of-the-art methods by between 2 and 10\% at Rank-1 (mAP). © 2023, The Authors. All rights reserved.

关键词： Linear transformations

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：