检索结果-内蒙古大学图书馆

IEEE Cool Chips

作者： Ziquan Qin Kaijie Wei Hideharu Amano Kazuhiro Nakadai Dept. of Information and Computer Science Keio University Yokohama Japan Dept. of Systems and Control Engineering Tokyo Institute of Technology Tokyo Japan

Open source software for robot audition called HARK aims to make “OpenCV” in audio signal processing, providing comprehensive functions from multichannel audio input to sound localization, sound source separation, and au-tomatic speech recognition. Since each of these HARK modules takes considerable energy when executed on PC, we propose to implement each module on an FPGA board called M-KUBOS connected. Here, we focus on the most computationally expensive function of HARK; the sound source separation, and implement it on a Zynq Ultrascale+ board. More than twice a performance improvement was achieved by using the sound frequency level parallelization in the HLS description compared to the software execution on the Ryzen 3990X64-core server. Power evaluation of the real board showed that the energy consumption is only 1/23.4 of the server.

关键词： Location awareness Energy consumption Source separation Power demand Speech recognition Parallel processing Servers

来源：评论

学校读者我要写书评

暂无评论

Deep-Learning-based VCSEL transmitter emulator

Deep-Learning-based VCSEL transmitter emulator

引用

2023 Conference on Lasers and Electro-Optics Europe and European Quantum Electronics Conference, CLEO/Europe-EQEC 2023

作者： Deligiannidis, Stavros Argyris, Nikos Dris, Stefanos Kalavrouziotis, Dimitrios Bakopoulos, Paraskevas Mesaritakis, Charis Bogris, Adonis Department of Informatics and Computer Engineering University of West Attica Aghiou Spiridonos Egaleo Athens12243 Greece NVIDIA Ermou 56 Athens10563 Greece University of the Aegean Dept. Information and Communication Systems Engineering Palama 2 str. Samos Karlovasi83200 Greece

ISBN: (纸本)9798350345995

The design of photonic/opto-electronic structures is a crucial field of research due to the wide range of applications in which these devices are utilized, such as communications, sensing and imaging. The traditional approach to design, which involves numerical simulation and iterative adjustments, is both time-consuming and computationally intensive. The ability to design-emulate photonic structures quickly and efficiently could bring new technologies to market at a faster pace and can also facilitate the process of extracting critical performance metrics from complex fabricated devices. The Vertical Cavity Surface Emitting Laser (VCSEL) and its use as a transmitter broadly used in data center interconnects is an example of a rather complex nonlinear system also exhibiting bandwidth limitation mechanisms attributed to its frequency response and parasitic effects, and thus its numerical simulation based on conventional rate equations can only partially approximate its behavior. When it comes to modelling fabricated devices, such physical models are notoriously difficult to parameterize in order to fit to observed laboratory data;in contrast, the emulation of the experimentally recorded behavior with the use of nonlinear models based on neural networks provides a much more efficient path to modelling, and with potentially higher prediction accuracy [1]. In this work, two types of bidirectional recurrent neural networks (RNN), namely Long Short-Term Memory (bi-LSTM) and Vanilla (bi-VRNN) were used to simulate the dynamic behavior of an experimentally characterized VCSEL-based, PAM-4 transmitter, exhibiting a high prediction accuracy approaching 100%. © 2023 IEEE.

关键词： Frequency response

来源：评论

学校读者我要写书评

暂无评论

VECOM: Variation-Resilient Encoding and Offset Compensation Schemes for Reliable ReRAM-Based DNN Accelerator

VECOM: Variation-Resilient Encoding and Offset Compensation ...

引用

IEEE International Conference on computer-Aided Design

作者： Je-Woo Jang Thai-Hoang Nguyen Joon-Sung Yang School of Electrical and Electronic Engineering Dept. of Semiconductor Systems Engineering Yonsei University Seoul South Korea Dept. of Electrical and Computer Engineering Sungkyunkwan University Suwon South Korea

Resistive Random-Access Memory (ReRAM)-based Processing In-Memory (PIM) Accelerator has emerged as a promising computing architecture for memory-intensive applications, such as Deep Neural Networks (DNNs). However, due to its immaturity, ReRAM devices often suffer from various reliability issues, which hinder the practicality of the PIM architecture and lead to a severe degradation in DNN accuracy. Among various reliability issues, device variation and offset current from High Resistance State (HRS) cell have been considered as major problems in a ReRAM-based PIM architecture. Due to these problems, the throughput of the ReRAM-based PIM is reduced as fewer wordlines are activated. In this paper, we propose VECOM, a novel approach that includes a variation-resilient encoding technique and an offset compensation scheme for a robust ReRAM-based PIM architecture. The first technique (i.e., VECOM encoding) is built based on the analysis of the weight pattern distribution of DNN models, along with the insight into the ReRAM's variation property. The second technique, VECOM offset compensation, tolerates offset current in PIM by mapping the conductance of each Multi-level Cell (MLC) level added with a specific offset conductance. Experimental results in various DNN models and datasets show that the proposed techniques can increase the throughput of the PIM architecture by up to 9.1 times while saving 50% of energy consumption without any software overhead. Additionally, VECOM is also found to endure low R-ratio ReRAM cell (up to 7) with a negligible accuracy drop.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Localization of Dengue Virus Likelihood Using Image Processing Technique

Localization of Dengue Virus Likelihood Using Image Processi...

引用

Emerging Smart Computing and Informatics (ESCI), Conference on

作者： Md. Mahbub Hosen Md. Rahatul Islam Faria Tabassum Syeda Thamina Tonni Malik Mohammad Nafiur Noor Shahid Rahman Dept. of Computer Science & Engineering Northern University of Bangladesh Dhaka Bangladesh Dept. of Human Intelligence Systems Kyushu Institute of Technology Wakamatsu Kitakyushu Japan Dept. of Computer Science & Engineering Bangladesh University of Engineering and Technology Dhaka Bangladesh Human Intelligence Lab Bangladesh Advance Robotics Research Center Dhaka Bangladesh Dept. of Electrical & Electronic Engineering Canadian University of Bangladesh Dhaka Bangladesh

The Aedes mosquito, found in tropical areas, transmits, and causes dengue fever. The spread of the dengue fever virus from an infected Aedes mosquito bite typically takes between three and fifteen days to manifest itself clinically as dengue fever symptoms. Early and automated detection of this illness will reduce the occurrence of outbreaks and facilitate the digitization of the system. Our primary objective is to identify regions at high risk for dengue fever using limited image data through the utilization of sophisticated machine learning and image processing methods. This work showcases the application of transfer learning algorithms for the timely identification of regions at risk for dengue mosquito infestation, particularly in situations where obtaining early data on dengue outbreaks is challenging. The experiments included images of 2150 dengue-positive data sets and 1440 dengue-negative data sets. We used AI and image classifiers Yolo V4 Tin, Tensor Flow, Google Colab, etc. for the training data set, and the system makes predictions with a 99.63% accuracy rate. Our system has some unique attributes; it not only detects the percentage of dengue probability but also the specific dengue-prone location on the submitted image.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Photonic Spiking Convolutional Neural Networks for High-Speed Image Processing

Photonic Spiking Convolutional Neural Networks for High-Spee...

引用

2021 IEEE Photonics Society Summer Topicals Meeting Series, SUM 2021

作者： Skontranis, Menelaos Sarantoglou, George Bogris, Adonis Mesaritakis, Charis Dept. Information and Communication Systems Engineering School of Engineering University of the Aegean Samos Greece Dept. Informatics and Computer Engineering University of West Attica Aigaleo Greece

ISBN: (纸本)9781665416009

A multi-layer photonic spiking convolutional neural network is presented, based on miniaturized VCSELs, targeting image classification. Spatial information is encoded using a time multiplexing scheme providing a radical reduction of physical neuron-count. Hardware-friendliness is enhanced by exploiting unsupervised spike-timing dependent plasticity. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Performance of Bifacial Solar System for 1MW grid-connected solar power plant in Mashhad, Iran: Design, Simulation and Economic Analysis 9

Performance of Bifacial Solar System for 1MW grid-connected ...

引用

9th International Conference on Technology and Energy Management, ICTEM 2024

作者： Eidiani, Mostafa Zeynal, Hossein Ghavami, Afrooz Zakaria, Zuhaina Energy Security and Sustainable Energy Institute Modarres 4P.C.: *** Mashhad Iran Buein Zahra Technical University Buein Zahra Dept. of Electrical and Computer Eng Qazvin Iran Electrical Engineering-Energy Systems Planning and Management Researcher Esfarayen Iran Universiti Teknologi MARA School of Electrical Engineering College of Engineering Shah Alam40450 Malaysia

ISBN: (纸本)9798350329797

In this paper, a 1 MW solar power plant has been designed by bifacial panels in Mashhad and from an economic and environmental perspective, it examined the issue. Determining the distance of the panels from each other, the appropriate angle of the panels has been checked to estimate the optimal efficiency of the system. In addition to producing 1812 megawatt hours per year, the system has a Performance Ratio (PR) of 93.42%, and the return on investment (ROI) and Net Present Cost (NPC) are respectively 31.4% and 7'892'184.18 h-t. As a result, a bifacial solar module's energy output is affected by a number of factors: the installation height of the solar module, the reflection coefficient of the surface below the module, tilt angles and pitch. Therefore, in this project, the performance of each of these parameters has been investigated and evaluated for different values in the power plant. Pvsyst is used as simulation software to design and simulate PV systems. © 2024 IEEE.

关键词： Solar power plants

来源：评论

学校读者我要写书评

暂无评论

Derivation of Aggregated Equivalent Models for the Steady-State Analysis of Active Distribution Networks Operated Under Voltage Control Schemes

SSRN

引用

SSRN 2024年

作者： Pasiopoulou, Ioanna D. Kontis, Eleftherios O. Papadopoulos, Theofilos A. Papagiannis, Grigoris K. Power Systems Laboratory School of Electrical and Computer Engineering Aristotle University of Thessaloniki GR Thessaloniki54124 Greece Department of Electrical and Computer Engineering University of Thessaly Volos Greece Power Systems Laboratory Dept. of Electrical and Computer Engineering Democritus University of Thrace XanthiGR 67100 Greece

To facilitate the coordination between transmission and distribution system operators, accurate equivalent models of power system components are required. Towards this objective, in this paper, a blackbox model is proposed for developing steady-state reduced-order equivalents of active distribution networks (ADNs) that host converter-interfaced renewable energy sources (CI-RES) and operate under various voltage control schemes. Droop-based and traditional voltage control schemes, such as on-load tap changer (OLTC) control strategies and the use of shunt capacitors, are considered. The performance of the proposed model is evaluated via simulations considering various load types and CI-RES penetration levels. Comparisons against the conventional polynomial and exponential models are also conducted, demonstrating the superior performance of the proposed black-box model. © 2024, The Authors. All rights reserved.

关键词： Electric power distribution

来源：评论

学校读者我要写书评

暂无评论

Performance of Monofacial and Bifacial Solar System for 5MW grid-connected solar power plant with Fixed Tilt and Tracking: Design, Simulation and investigating the effect of temperature 28

Performance of Monofacial and Bifacial Solar System for 5MW ...

引用

28th International Electrical Power Distribution Conference, EPDC 2024

作者： Eidiani, Mostafa Ghavami, Afrooz Zeynal, Hossein Zakaria, Zuhaina Energy Security and Sustainable Energy Institute Modarres 4 MashhadP.C.: *** Iran Master of Electrical Engineering-Energy Systems Planning and Management Researcher Esfarayen Iran Buein Zahra Technical University Buein Zahra Dept. of Electrical and Computer Eng Qazvin Iran Universiti Teknologi Mara School of Electrical Engineering College of Engineering Shah Alam40450 Malaysia

ISBN: (纸本)9798350385502

In this paper, a 5000 kW grid-connected photovoltaic system of Haft-Hoze Natural Park, 7 km southeast of Mashhad City, has been designed and simulated. This power plant is for two monofacial and bifacial systems in both fixed and tilted planes and trackers modes in PVSYST software. It is simulated and designed and the simulation data is compared in both cases. In this paper, the effect of temperature on solar panel performance is investigated first. This work has been done in three stages. At first, by keeping the solar radiation constant, the effect of temperature on the output performance of the panel. In the next step, the P-V curves at different ambient temperatures and changes in solar radiation have been investigated. In the following, it shows the effect of PV panel temperature on PV panel output performance at different intensities of solar radiation. The simulation results of the 5000 kW solar power plant, in a fixed tilted plane for the monofacial system, energy injected into the grid and performance ratio are 8291 MWh and 0.850. The bifacial system, energy injected into the grid, and performance ratio are 8730 MWh and 0.896. In the Trackers mode, for the monofacial system, energy injected to the grid and performance ratio are 9558 MWh and 0.838. For the bifacial system, energy injected into the grid and performance ratio are 10025 MWh and 0.880. © 2024 IEEE.

关键词： Solar power plants

来源：评论

学校读者我要写书评

暂无评论

Heart Failure: Machine Learning Prediction Within a 5-Year Framework 24

Heart Failure: Machine Learning Prediction Within a 5-Year F...

引用

24th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2024

作者： Tsarapatsani, Konstantina-Helen Tsakanikas, Vasilios D. Sakellarios, Antonis Trampisch, Hans J. Karapintzou, Efterpi Rudolf, Henrik Matsopoulos, George K. Fotiadis, Dimitrios I. Biomedical Research Institute Foundation for Research and Technology-Hellas Ioannina Greece Ruhr University Bochum Department of Medical Informatics Biometry and Epidemiology Bochum Germany University of Ioannina Unit of Medical Technology and Intelligent Information Systems Dept. of Materials Science and Engineering Greece Institute for Biostatistics and Informatics in Medicine and Ageing Research University Medical Center Rostock Germany School of Electrical and Computer Engineering National Technical University of Athens Athens Greece University of Ioannina and Biomedical Research Institute-FORTH Unit of Medical Technology and Intelligent Information Systems Dept. of Materials Science and Engineering Ioannina Greece

ISBN: (纸本)9798331518622

Heart failure (HF) is a complex syndrome that is affected by many factors and causes. It is crucial to early recognize the disease subtypes and the unidentified clinical pathways that give rise to it. Machine learning (ML) is the tool that assist to deal with these challenges and improve the prediction of HF. In this work, the HF risk prediction was implemented by employed ML classifiers, such as Random Forest (RF), Extreme Grading Boosting (XGBoost) and Light Gradient-Boosting Machine (LGBM). We utilized the data from the German epidemiological trial on ankle brachial index - getABI cohort, which includes 6,454 patients. The performance of classifiers was estimated by Accuracy (ACC), Sensitivity, Specificity and the area under the receiver operating characteristic curve (AUC) in mean values for each ML classifier. The results were also interpreted using the Explainable artificial intelligence (XAI) approach, the Shapley Additive exPlanations (SHAP) values. Our work reveals that LGBM classifier predict the HF risk within 5 years follow-up in general population with 68 % accuracy. Moreover, the N-terminal pro-B-type natriuretic peptide (NT-proBNP) was identified as the most important feature for HF risk prediction. © 2024 IEEE.

关键词： Risk perception

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Traffic-Aware Dynamic TDD Configuration in B5G Networks

AI-Driven Traffic-Aware Dynamic TDD Configuration in B5G Net...

引用

IEEE Symposium on Network Operations and Management

作者： Sanguk Jeong Dahyun Mok Gyurin Byun Lusungu J. Mwasinga Hyunseung Choo R&D Team Networks Samsung Electronics Suwon S. Korea Dept. of Digital Media and Communications Engineering Sungkyunkwan University Suwon South Korea Dept. of Electrical and Computer Engineering Sungkyunkwan University Suwon South Korea Dept. of AI Systems Engineering Sungkyunkwan University Suwon South Korea Dept. of Computer Science and Engineering Sungkyunkwan University Suwon South Korea

ISBN: (数字)9798350327939

ISBN: (纸本)9798350327946

The advent and anticipated evolution of Beyond Fifth Generation (B5G) networks raise critical issues for the static Time Division Duplex (TDD) radio resource allocation technique. In Static TDD, the fixed allocation of uplink and downlink resources leads to poor resource utilization, with uplink channels often congested and downlink channels underutilized. This study addresses static TDD limitations by proposing a novel TDD configuration called Traffic-Aware Dynamic TDD (TA-TDD), aiming to satisfy the high-speed and low-latency communication requirements of various applications. Specifically, the proposed TA-TDD utilizes Convolutional Long Short-Term Memory (ConvLSTM) model to predict traffic before allocation of uplink and downlink resource. This method effectively manages uplink-centric traffic in wireless networks, to improve both network quality and user experience. Compared to static TDD, the proposed TA-TDD notably improves network throughput by as much as 20% in scenarios with high uplink demand. The findings demonstrate that dynamic TDD configurations significantly enhance network throughput compared to static setups, which offers an effective solution for network management.

关键词： Wireless networks Predictive models Downlink Throughput User experience Resource management Uplink

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：