检索结果-内蒙古大学图书馆

IEEE Transactions on Circuits and systems for Artificial Intelligence 2025年第2期2卷 114-125页

作者： Mikail Yayla Ming-Liang Wei Simon Thomann Albi Mema Chia-Lin Yang Jian-Jia Chen Hussam Amrouch Design Automation for Embedded Systems Group TU Dortmund University Dortmund Germany Lamarr Institute for Machine Learning and Artificial Intelligence Dortmund Germany Department of the Graduate Institute of Electronics Engineering National Taiwan University Taipei Taiwan Technical University of Munich (TUM) Munich Germany TUM School of Computation Information and Technology Chair of AI Processor Design Munich Institute of Robotics and Machine Intelligence Munich Germany Department of Computer Science and Information Engineering Graduate Institute of Electronics Engineering National Taiwan University Taipei Taiwan Department of Computer Science TU Dortmund University Dortmund Germany Lamarr Institute Dortmund Germany

Accelerating the immense workloads of Neural Networks (NNs) is a critical challenge, and analog computing-based approaches present a promising solution. Among these, the Integrate-and-Fire (IF) Spiking Neural Network (SNN) stands out for its potential in efficient neural computation. However, achieving high inference accuracy through precise multiply-accumulate (MAC) operations necessitates a large membrane capacitor—224 to 547 times larger than the synapse array at the 14nm technology node—resulting in prohibitive area costs. Additionally, the large capacitor size introduces higher energy consumption and longer access times. Thus, a key research challenge is maintaining accuracy while mitigating the costs associated with the large membrane capacitor. In this work, we propose a HW/SW Codesign method, called CapMin, for capacitor size minimization in analog computing IF-SNNs. CapMin minimizes the capacitor size by reducing the number of spike times needed for accurate operation of the HW, based on the absolute frequency of MAC level occurrences in the SW. To increase the operation of IF-SNNs to current variation, we propose the method CapMin-V, which trades capacitor size for protection based on the reduced capacitor size found in CapMin. In our experiments, CapMin achieves more than a 14 $\times$ reduction in capacitor size along with a 34% reduction in energy consumption over the state of the art, while CapMin-V achieves increased variation tolerance in the IF-SNN operation, requiring only a small increase in capacitor size.

关键词： Capacitors Circuits Accuracy Capacitance Micromechanical devices Costs Neurons Integrated circuit modeling Spiking neural networks Hardware

来源：评论

学校读者我要写书评

暂无评论

Assistive Technical Communication of Montenegrin eServices: a Case Study 27

Assistive Technical Communication of Montenegrin eServices: ...

引用

27th International Conference on Information Technology, IT 2023

作者： Simon, Aniko Lakovic, Luka Kovacevic, Pavle Kara, Peter A. Ognjanovic, Ivana Sendelj, Ramo Reich, Christoph Roganovic, Milovan Mantas, John Bokor, Laszlo Sigma Technology Budapest1093 Hungary University of Donja Gorica Faculty for Information Systems and Technologies Podgorica81000 Montenegro Budapest University of Technology and Economics Faculty of Electrical Engineering and Informatics Department of Networked Systems and Services Budapest1111 Hungary Kingston University Wireless Multimedia and Networking Research Group Department of Computer Science School of Computer Science and Mathematics Faculty of Science Engineering and Computing LondonKT1 2EE United Kingdom University of Donja Gorica Humanistic Studies Podgorica81000 Montenegro Furtwangen University Institute of Data Science Cloud Computing and It Security Furtwangen78120 Germany Clinical Centre of Montenegro Clinic for Neurology Podgorica81000 Montenegro National and Kapodistrian University of Athens Faculty of Nursing School of Health Sciences Goudi 11527 Greece

ISBN: (纸本)9798350397512

With the advancement of information technology in the recent decades, digital and online services have become essential components of everyday life in Europe. Montenegro is no different in this regard. However, as digital literacy in the country is still in a developing phase in comparison with most countries of the EU, a higher portion of its citizens may rely on assistive technical communication. In this paper, we provide a case study on the assistive technical communication of Montenegrin eServices. The work addresses the sectors of online banking, healthcare services, higher education, national administrative services, and utilities. Our findings highlight the diversity in terms of implemented assistive technical communication, and distinguish usage contexts on the level of adequacy. Yet as the functionalities of Montenegrin eServices are expected to gradually expand in the upcoming years, assistive technical communication must aim to handle the higher extents of service complexity. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimal Economic Dispatch of Power System Networks with Renewable Energy Sources

Optimal Economic Dispatch of Power System Networks with Rene...

引用

IEEE PES Conference on Innovative Smart Grid Technologies - Middle East (ISGT Middle East)

作者： Atif M. Mohammad Osama A. Alghamdi Abdullah Ali Alhusssainy Muhyaddin Rawa Abdullah M. Abusorrah Y. A. Al-Turki Department of Electrical and Computer Engineering King Abdulaziz University Jeddah Saudi Arabia Department of Electrical and Computer Engineering K. A. CARE Energy Research and Innovation Center King Abdulaziz University Jeddah Saudi Arabia Department of Electrical and Computer Engineering K. A. CARE Energy Research and Innovation Center Smart Grids Research Group Center of Research Excellence in Renewable Energy and Power Systems King Abdulaziz University Jeddah Saudi Arabia

This paper compares betwe!en different types of batteries of a grid-connected hybrid power system that utilizes renewable energy sources (PV and Wind Turbines). The hybrid system is located in Yanbu region in Saudi Arabia. Part of the vision of 2030 of Saudi Arabia is to use renewable energy sources to cover a portion of the total electricity production. The required energy to be produced by renewable energy sources is 850 MW for the vision of 2030. To meet such a requirement, a thorough study is carried out to investigate a potential solution. The purpose of this study is to design a hybrid system which contains battery storage and has the lowest cost. Ten different batteries were used for a comparison study to examine the hybrid system with the lowest cost. Hybrid Optimization of Multiple Energy Resources (HOMER) software was used to design the hybrid system. HOMER provides real time evaluation of power systems. The criteria used for decision making purpose are the net present cost (NPC), levelized cost of energy (COE), electricity production, initial capital cost, nominal battery capacity, and battery autonomy. The results indicate that the hybrid system with Zinc Bromine flow battery (electrochemical type) has the lowest cost.

关键词： Renewable energy sources Bromine Costs Production Software Hybrid power systems Batteries

来源：评论

学校读者我要写书评

暂无评论

Speech Separation for Low-Resource Languages

Speech Separation for Low-Resource Languages

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Marvin Borsdorf Zexu Pan Pascal Himmelmann Haizhou Li Tanja Schultz Machine Listening Lab University of Bremen Bremen Germany Alibaba Group Singapore Department of Mathematics and Computer Science FernUniversität in Hagen Hagen Germany School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China Department of Electrical and Computer Engineering National University of Singapore Singapore Cognitive Systems Lab University of Bremen Bremen Germany

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Speech separation aims to equip machines with the human ability of selective listening, i.e. to focus attention on specific information in spoken communication. Studies have shown that the language spoken in a cocktail party scenario matters. While the development of speech separation models can leverage extensive databases, for the majority of languages only very limited data is available. This work presents the very first study on speech separation for low-resource languages. We choose blind source separation as the task to be studied and analyze three strategies to overcome the data scarcity of two low-resource languages from the GlobalPhoneMS2 database. We show that data from other languages can be used to develop models that work for low-resource languages. Finetuning additionally boosts the performance, and training on multiple languages increases both performance and robustness. We show that dynamic mixing in the development helps to find a trade-off between performance and development time.

关键词： Training Measurement Databases Signal processing Data models Blind source separation Robustness Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

Direct Data-Driven State-Feedback Control of Linear Parameter-Varying systems

arXiv

引用

arXiv 2022年

作者： Verhoek, Chris Tóth, Roland Abbas, Hossam S. Control Systems group Dept. of Electrical Engineering Eindhoven University of Technology Eindhoven Netherlands Systems and Control Lab Institute for Computer Science and Control Budapest Hungary Institute for Electrical Engineering in Medicine Universität zu Lübeck Lübeck Germany

The framework of linear parameter-varying (LPV) systems has shown to be a powerful tool for the design of controllers for complex nonlinear systems using linear tools. In this work, we derive novel methods that allow to synthesize LPV state-feedback controllers directly from only a single sequence of data and guarantee stability and performance of the closed-loop system. We show that if the measured open-loop data from the system satisfies a persistency of excitation condition, then the full open-loop and closed-loop input-scheduling-state behavior can be represented using only the data. With this representation we formulate data-driven analysis and synthesis problems, where the latter yields controllers that guarantee stability and performance in terms of infinite horizon quadratic cost, generalized H2-norm and 2-gain of the closed-loop system. The controllers are synthesized by solving a semi-definite program. Additionally, we provide a synthesis method to handle noisy measurement data. Competitive performance of the proposed data-driven synthesis methods is demonstrated w.r.t. model-based synthesis in multiple simulation studies, including a nonlinear unbalanced disc system. © 2022, CC BY-NC-SA.

关键词： State feedback

来源：评论

学校读者我要写书评

暂无评论

Non-specificity-based Supervised Discretization for Possibilistic Classification 15th

Non-specificity-based Supervised Discretization for Possibi...

引用

15th International Conference on Scalable Uncertainty Management, SUM 2022

作者： Jenhani, Ilyes Khlifi, Ghaith Sidiropoulos, Panagiotis Jansen, Henk Frangou, George College of Computer Engineering and Science Prince Mohammad Bin Fahd University Al-Khobar31952 Saudi Arabia Massive Analytic Ltd. London United Kingdom Mullard Space Science Laboratory University College London London United Kingdom UCL Quantum Science & Technology Institute London United Kingdom Autonomous Systems Dynamics and Control Research Group Centre for Autonomous and Cyber Physical Systems Cranfield University Bedford United Kingdom

ISBN: (纸本)9783031188428

Data imperfection and information uncertainty are inevitable in many application domains, including medicine, finance, meteorology, cybersecurity, etc. Sources of uncertainty include the lack of information of the solicited experts, sensor unreliability for automatically collected data, conflicting information sources, etc. Classification techniques, such as the non-specificity based possibilistic decision trees (NSPDT) have been proposed to deal with such uncertainty. However, most of the introduced possibilistic methods are limited to categorical features, i.e. they can not process data input that is continuous. This paper address this limitation through a supervised possibilistic discretization method, which transforms continuous features into categorical features in datasets where class labels are imperfect and represented by possibility distributions. The proposed method can be used as a pre-processing step to make it possible to use methods such as NSPDT in datasets that initially have continuous features. The proposed non-specificity based discretization algorithm has provided good quality categorical features which have led to obtain NSPDT trees showing an accuracy higher than 80% in most cases. With original datasets, where the instances have certain (i.e. non-possibilistic) class labels, the proposed possibilistic discretization method has shown a robust performance compared to the standard discretization algorithm which is the default approach in this case. The difference in accuracy has not exceeded 5% for all used datasets and all tested classifiers, and in some cases, the possibilistic discretization outperformed the standard discretization. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Odour Localization in Neuromorphic systems

Odour Localization in Neuromorphic Systems

引用

IEEE International Symposium on Circuits and systems (ISCAS)

作者： Thorben Schoepe Damien Drix Franz Marcus Schüffny Rebecca Miko Samuel Sutton Elisabetta Chicca Michael Schmuker Peter Grünberg Institut 15 Forschungszentrum Jülich Aachen Germany Bio-Inspired Circuits and Systems Lab Zernike Institute for Advanced Materials University of Groningen Netherlands Groningen Cognitive Systems and Materials Center University of Groningen Netherlands Biocomputation Research Group University of Hertfordshire Hatfield United Kingdom Faculty of Electrical Engineering and Computer Science TU Dresden Dresden Germany

ISBN: (数字)9798350330991

ISBN: (纸本)9798350331004

Odour source localization is crucial in life-saving scenarios like pinpointing gas leaks, detecting explosives, searching for earthquake survivors, or locating fires at their origin. The turbulent character of natural environments makes this task very challenging. The absolute concentration of odour plumes carries little meaning and these plumes are only encountered in an intermittent, transient fashion. However, navigation algorithms that are driven by odour encounter events, can successfully find odour sources by extracting spatiotemporal information. The event driven nature of odour plumes motivates a fully event-driven sensing and processing pipeline for robot navigation. Hence, we developed a spiking neural network, implemented on neuromorphic hardware, that can successfully decode odour-puff direction from a pair of enose-systems. This is to our knowledge the first fully event driven neuromorphic system for odour localization.

关键词： Location awareness Neuromorphics Navigation Pipelines Green products Robot sensing systems Sensors

来源：评论

学校读者我要写书评

暂无评论

Exploring PEMFCs for Powering Untethered Small-Scale Robots

Exploring PEMFCs for Powering Untethered Small-Scale Robots

引用

IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob)

作者： Aiswarya Lakshmi Manikandan Berfin Gürboğa Niko Münzenrieder Akash Raman Han J. G. E. Gardeniers Arturo Susarrey-Arce Leon Abelmann Islam S. M. Khalil Faculty of Electrical Engineering Mathematics and Computer Science (EEMCS) University of Twente AE Enschede The Netherlands Faculty of Engineering Metallurgical and Materials Engineering Man-isa Celal Bayar University Manisa Türkiye Faculty of Engineering Free University of Bozen-Bolzano Bozen-Bolzano Italy Faculty of Science and Technology Mesoscale Chemical Systems Group MESA+ Institute for Nanotechnology University of Twente AE Enschede The Netherlands Department of Biomechanical Engineering University of Twente En-schede AE The Netherlands

ISBN: (数字)9798350386523

ISBN: (纸本)9798350386530

Magnetically guided untethered devices are used in a variety of medical applications. These devices are typically powered by onboard battery units. Hydrogen fuel cells (FC) are a promising alternative power source for such small-scale devices since they rely on a sustainable fuels which produce electric power from the redox reaction of hydrogen and oxygen across a proton exchange membrane (PEM). Understanding the impact of decreasing the active electrode area in FCs is crucial for deploying FCs in untethered devices and gaining insights into the challenges of downscaling the devices. This paper investigates the performance of PEM FCs (PEMFCs) when their active area is reduced, and when the FC is supplied with reactants at different flow rates from a PEM electrolyzer. PEMFCs with three active electrode areas, 3.5 × 3.5 cm 2 , 2.7×2.7 cm 2 , and 1.6×1.6 cm 2 were designed, fabricated, and characterised. Maximum fuel cell output powers of 0.3 W, 0.09 W, and 0.03 W (maximum power densities of 0.025 W/cm 2 , 0.012 W/cm 2 , and 0.013 W/cm 2 ) corresponding to the three aforementioned areas were achieved. Mathematical modeling of the PEMFC simulated the FC response, providing insights into the activation kinetics of the fuel cell. The smallest PEMFC with an active area of 1.6 × 1.6 cm 2 was used to power an inductor coil (rated 130 mA, 150 mH, 8 Ω). This study can guide the development of FCs to power untethered devices.

关键词： Coils Performance evaluation Power system measurements Fuel cells Magnetic moments Mathematical models Numerical models Inductors Robots Load modeling

来源：评论

学校读者我要写书评

暂无评论

QuIP: A P4 Quantum Internet Protocol Prototyping Framework

arXiv

引用

arXiv 2024年

作者： Kozlowski, Wojciech Kuipers, Fernando A. Smets, Rob Turkovic, Belma QuTech Delft University of Technology Delft2628 CD Netherlands The Networked Systems Group Department of Software Technology Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft2628 CD Netherlands SURF Utrecht3511 EP Netherlands TNO The Hague2595 DA Netherlands

Quantum entanglement is so fundamentally different from a network packet that several quantum network stacks have been proposed;one of which has even been experimentally demonstrated. Several simulators have also been developed to make up for limited hardware availability, and which facilitate the design and evaluation of quantum network protocols. However, the lack of shared tooling and community-agreed node architectures has resulted in protocol implementations that are tightly coupled to their simulators. Besides limiting their reusability between different simulators, it also makes building upon prior results and simulations difficult. To address this problem, we have developed QuIP: a P4-based Quantum Internet Protocol prototyping framework for quantum network protocol design. QuIP is a framework for designing and implementing quantum network protocols in a platform-agnostic fashion. It achieves this by providing the means to flexibly, but rigorously, define device architectures against which quantum network protocols can be implemented in the network programming language P416. QuIP also comes with the necessary tooling to enable their execution in existing quantum network simulators. We demonstrate its use by showcasing V1Quantum, a completely new device architecture, implementing a link- and network-layer protocol, and simulating it in the existing simulator NetSquid. © 2024, CC BY.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Reduced-Order Models of Static Power Grids Based on Spectral Clustering

Reduced-Order Models of Static Power Grids Based on Spectral...

引用

Annual North-American Power Symposium

作者： Mario D. Baquedano-Aguilar Sean Meyn Arturo Bretas Department of Electrical & Computer Engineering University of Florida Gainesville FL USA Distributed Systems Group Pacific Northwest National Laboratory Richland WA USA G2Elab Grenoble INP CNRS Université Grenoble Alpes Grenoble France

For large-scale interconnected power systems that cover large geographical areas, certain electrical studies are required so that appropriate decisions ensure system reliability and low cost. For such studies, it is often neither practical nor necessary to model in detail the entire power system, which is increasingly complex due to a more diverse range of grid assets to choose from in both short and long-term planning. The goal of this paper is to present a methodology to reduce the order of large-scale power networks based on spectral graph theory given that current methods for static network reduction are not scalable. A brief analysis of some spectral clustering properties to determine which graph Laplacian matrix should be used and why is included. The analysis shows that the utilization of the normalized graph Laplacian is more advantageous for clustering purposes. Techniques are proposed to approximate cost functions for the aggregated generators. This is done via linear regression. The reduced-order model obtained with the proposed methodology has an accuracy above 94% and solves the scalability issue commonly present in other reduction methods. If the utilization of the reduced-order model is either constrained to load levels above mid-peak demand, or cost functions of aggregated units are approximated via a piece-wise quadratic approach, then the error distribution is in the order of 10- 3 .

关键词：

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：