检索结果-内蒙古大学图书馆

IEEE International Conference on System engineering and Technology

作者： Adi Novitarini Putri Carmadi Machbub Dimitri Mahayana Egi M. Idris Hidayat Control and Computer System Research Group School of Electrical Engineering and Informatics Institut Teknologi Bandung Indonesia

ISBN: (纸本)9798350319842

A problem arises when implementing the control scheme into a system, the limitation of the number of sensors used causes not all state information from the plant can be obtained. In addition, the data measurement process also often contains noise. Therefore, implementing the optimal control scheme directly becomes difficult. The status estimation method proposed in this study utilizes the use of an Artificial Neural Network (ANN) as a function approximation. On the other hand, the development of optimal control implementation has also experienced a fairly massive increase. Some of the existing optimal control solutions can only be carried out offline and depend on the dynamics' model of the system to be controlled. The combination of KalmanNet and the Value Iteration (VI) algorithm is used to adapt the role of the Linear Quadratic Gaussian (LQG) method in designing control procedures to produce high performance. Tests were carried out on a cart-pole system in a discrete-time domain. The use of the combination of these methods could make the closed loop system towards a value of 0 and the evolution of the estimator gain is smoother, namely with the norm of 2.33S4E-04.

关键词： Optimal control Artificial neural networks Reinforcement learning Nonlinear filters Systems engineering and theory Sensor systems Trajectory

来源：评论

学校读者我要写书评

暂无评论

Geometric Parameterized Macromodel of Uniaxial Capacitance Accelerometer Based on Modal Superposition 16

Geometric Parameterized Macromodel of Uniaxial Capacitance A...

引用

16th IEEE International Scientific and Technical Conference Actual Problems of Electronic Instrument engineering, APEIE 2023

作者： Gridchin, Aleksandr V. Koleda, Aleksei N. Barbin, Evgenii S. Nesterenko, Tamara G. Kolchuzhin, Vladimir A. Department of Semiconductor Devices and Microelectronics Novosibirsk State Technical University Novosibirsk Russia Department of Electronic Engineering National Research Tomsk Polytechnic University Tomsk Russia Laboratory of Intelligent Computer Systems Tomsk State University of Control Systems and Radioelectronics Tomsk Russia Advanced Cellular Group Qorvo Munich GmbH Munich Germany

ISBN: (纸本)9798350330885

The paper presents a piecewise geometric parameterization method and a parametric analysis of uniaxial capacitance accelerometer using a reduced model formulated on the modal superposition method. The extraction of parameters for the macromodel such as modal frequencies, modal masses, modal stiffnesses, strain energy, and capacitances are described. The reduced model consists of the two modes: torsion mode, and transversal mode, three electrodes in the electrostatic domain, and eight master nodes in the geometrical domain located at the edges of the plate. The generation of the discrete macromodels is executed using commercial software. The thickness of the plate has been selected as a design parameter. Linear piecewise interpolation is used for macromodel parameterization which have been done inside VHDL-AMS code. The accelerometer's dynamic response simulated using of parametrized macromodel considering the mechanical contact phenomena and the nonlinear electrostatic interaction are presented and discussed. The developed approach can be applied for fast system level simulations in view of the variation of the geometric parameters. © 2023 IEEE.

关键词： Capacitance

来源：评论

学校读者我要写书评

暂无评论

State Derivative Normalization for Continuous-Time Deep Neural Networks

arXiv

引用

arXiv 2024年

作者： Weigand, Jonas Beintema, Gerben I. Ulmen, Jonas Görges, Daniel Tóth, Roland Schoukens, Maarten Ruskowski, Martin Chair of Machine Tools and Control Systems RPTU Kaiserslautern The German Research Center for Artificial Intelligence Kaiserslautern Germany Group The Department of Electrical Engineering Eindhoven University of Technology Netherlands The Systems and Control Laboratory The Institute for Computer Science and Control Budapest Hungary Institute for Electromobility RPTU Kaiserslautern Germany

The importance of proper data normalization for deep neural networks is well known. However, in continuous-time state-space model estimation, it has been observed that improper normalization of either the hidden state or hidden state derivative of the model estimate, or even of the time interval can lead to numerical and optimization challenges with deep learning based methods. This results in a reduced model quality. In this contribution, we show that these three normalization tasks are inherently coupled. Due to the existence of this coupling, we propose a solution to all three normalization challenges by introducing a normalization constant at the state derivative level. We show that the appropriate choice of the normalization constant is related to the dynamics of the to-be-identified system and we derive multiple methods of obtaining an effective normalization constant. We compare and discuss all the normalization strategies on a benchmark problem based on experimental data from a cascaded tanks system and compare our results with other methods of the identification literature. © 2024, CC BY-SA.

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

Composite DC-DC Converter with Bipolar/bidirectional Current-Fed Push-pull Voltage Regulator 16

Composite DC-DC Converter with Bipolar/bidirectional Current...

引用

16th Brazilian Power Electronics Conference, COBEP 2021

作者： Klein Faistel, Tiago Miguel Jank, Henrique Ribeiro, Gustavo Colpes Da Silva Martins, Mario Lucio Correa Lopes, Luiz Antonio Power Electronics and Control Research Group Federal University of Santa Maria Santa Maria Brazil Concordia University Department of Electrical and Computer Engineering Montreal Canada

ISBN: (纸本)9781665421294

This paper presents a power converter to interface an extra low voltage bus, ELV (48 V) and a low voltage bus, LV (380 V) in a residential dc-dc nanogrid of 1.2 kW. The proposed converter makes use of a composite structure where a DC transformer (DCX converter) handles the major amount of the processed power between the DC buses. DCX is design to operate at a fixed duty-cycle where the transformer turns-ratio is optimized to ensure the lowest conduction losses. To provide voltage regulation to ELV bus, a parallel voltage regulator (DCR) is employed. The power handled by the DCR is proportional to its input voltage across capacitor $C$ 1.1 Results from a 1.2 kW laboratory prototype confirm the feasibility of the proposed composite converter and reveals that it is a strong candidate for DC-DC applictations with a narrow volage regulation range. © 2021 IEEE.

关键词： Voltage regulators

来源：评论

学校读者我要写书评

暂无评论

MARS: Multi-Agent Deep Reinforcement Learning for Real-Time Workflow Scheduling in Hybrid Clouds with Privacy Protection

MARS: Multi-Agent Deep Reinforcement Learning for Real-Time ...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Long Cheng Haoyang He Yan Gu Qingzhi Liu Zhiming Zhao Fang Fang State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Control and Computer Engineering North China Electric Power University Beijing China Information Technology Group Wageningen University and Research Netherlands Research Group of Multi-Scale Networked Systems University of Amsterdam Netherlands

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

Scheduling workflows in hybrid cloud environments presents significant challenges due to the inherent complexity of workflows and the dynamic nature of cloud resources. This complexity is further increased when attempting to balance workflow performance with privacy protection. Recent efforts have leveraged deep reinforcement learning (DRL) to address these challenges. However, most of these approaches rely on single-agent models, which can lead to security issues and scalability problems due to their centralized processing. Specifically, the properties of workflows are transferred to the single agent, which risks leaking privacy information. Our paper addresses these issues by introducing MARS, a real-time workflow scheduling method that prioritizes privacy protection in hybrid clouds. MARS leverages multi-agent deep reinforcement learning (MADRL) to optimize the workflow scheduling of cloud virtual machines (VMs). The benefit of our solution is that it relies on the collaborative learning of multi-agents on multiple VMs, which could assign user data to specific cloud servers for privacy protection while sharing training experiences between agents. In our implementation, MARS aims to reduce workflow completion time and operational costs while complying with strict privacy protection guidelines. The experimental results demonstrate that MARS can significantly surpass existing methods, reducing makespan by an average of $53.18 \%$ and costs by $61.98 \%$ compared to basic techniques, and achieving $20.26 \%$ and $25.71 \%$ improvements over the latest advanced methods, respectively.

关键词： Training Cloud computing Privacy Costs Scalability Deep reinforcement learning Dynamic scheduling Real-time systems Complexity theory Protection

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Reliability of Stream Sparse Matrix-Vector Multiplication Accelerators: A High-Level Approach

Analyzing the Reliability of Stream Sparse Matrix-Vector Mul...

引用

Latin American Test Workshop, LATW

作者： María L. Pinto-Salamanca Josie E. Rodriguez Condia José A. Hidalgo-López Wilson J. Pérez-Holguín GIRA Research Group Universidad Pedagógica y Tecnológica de Colombia (UPTC) Departamento de Electrónica Universidad de Málaga Department of Control and Computer Engineering (DAUIN) Politecnico di Torino

ISBN: (数字)9798350365559

ISBN: (纸本)9798350365566

1 Today, advances in scientific and embedded computing and the incredible proliferation of machine learning algorithms take advantage of specialized hardware accelerators to provide exceptional performance and good accuracy. In some safety-critical applications like autonomous robotics, healthcare, and automotive, crucial mathematical operations such as convolutions are often efficiently mapped in hardware as Matrix-Vector(MxV) and Matrix-Matrix (MxM) multiplications. Moreover, sophisticated sparsity algorithms aim to improve performance and power consumption. Unfortunately, technology scaling trends may increase the proliferation of faults on hardware during the in-field operation, so there is a rising interest in the reliability assessment and analysis of sparsity-based accelerators. This work evaluates the impact of soft errors (bit-flips) on sparse-matrix dense-vector multiplication (SpMV) cores for safety-critical tactile sensing applications by resorting to a High-Level Synthesis (HLS) strategy. The experiments are performed on an open-source streaming SpMV core using the Compressed Sparse Row (CSR) format when processing characteristic medium-size sparse matrices (100x100 and 494x494). Our results indicate that data-path pipeline registers in the (SpMV) core are resilient to transient faults (< 1.3% of observed corruption effects), while large magnitude errors can be associated with the type of sparse matrix describing the system (e.g., number of non-zero values) and the type and features of the input vector sensor.

关键词： Machine learning algorithms Power demand Pipelines Robot sensing systems Vectors Sensors Registers

来源：评论

学校读者我要写书评

暂无评论

PV powered neuromorphic sensors with optical connectivity

PV powered neuromorphic sensors with optical connectivity

引用

Communications and Networking (BalkanCom), International Balkan Conference on

作者： George-Iulian Uleru Alexandru Barleanu Mircea Hulea Zabih Ghassemlooy Faculty of Automatic Control and Computer Engineering Gheorghe Asachi Technical University of Iasi Iasi Romania Photonics Technology Laboratory Optical Communications Research Group. FEE Northumbria University Newcastle upon Tyne United Kingdom

ISBN: (数字)9798350365955

ISBN: (纸本)9798350365962

The spiking neural networks (SNN) benefits from low power consumption, very good signal-to-noise ratio and the ability to model rigorously the physiology of the biological neural areas. In robotics, the SNN can be used in different applications including motion control where the neural module drives the actuators based on the information from sensors. The most suitable type of sensing devices in biomimetic robotics are the neuromorphic sensors (NS) with spiking output which can include an optical transmitter for wireless connectivity. Considering that the reduced energy consumption is a critical characteristic for the SNN, in this work we evaluate the possibility of using photovoltaic (PV) panels to power the NS with optical output. The focus is on the recently introduced type of NS with integrated force sensing resistor (FSR) that uses a module based on a light emitting diode (LED) to generate optical pulses. We measured the responses of this NS with the load mass when it is powered by a PV panel, and the results show that the NS operates in nominal conditions despite the slight variations of the used supply voltage. Moreover, the NS is able to transmit optical pulses which frequency depends on the load mass.

关键词： Biomedical optical imaging Neuromorphics Robot sensing systems Optical network units Optical receivers Sensors Optical sensors

来源：评论

学校读者我要写书评

暂无评论

Enabling Self-Powered Analog Voice Communication with Photovoltaic Cells and Optical Wireless Links Communication

Enabling Self-Powered Analog Voice Communication with Photov...

引用

International Symposium on Communication Systems, Networks and Digital Signal Processing, CNSDSP

作者： Mircea Hulea George-Iulian Uleru Alexandru Barleanu Othman Isam Younus Faculty of Automatic Control and Computer Engineering Gheorghe Asachi Technical University of Iasi Iasi Romania Photonics Technology Laboratory Optical Communications Research Group. FEE Northumbria University Newcastle upon Tyne United Kingdom

ISBN: (数字)9798350348743

ISBN: (纸本)9798350348750

The growing demand for energy-efficient communication systems has triggered the interest in using photovoltaic (PV) panels to power optical receivers in Visible Light Communication (VLC) systems. While this approach offers the enticing advantage of self-powered operation, it comes with a significant drawback of limited bandwidth. This limitation severely restricts the maximum data rate achievable through VLC channels, especially when compared to digital audio transmission which requires high bandwidth due to sampling and resolution needs. Therefore, a key challenge lies in finding a balance between the energy-harvesting benefits of PV receivers and the need for a sufficient data rate for specific VLC applications. This work evaluates experimentally the possibility to transmit using VLC the voice in the analogue domain when the transmission of the digital conversion of limited by the bandwidth of the PV-based receiver. The results show that speech can be received properly in analogue domain when the transmission of the digital conversion is not possible due to limited bandwidth of the PV panel. The results show that the PV panel is able to receive speech with cross-correlation factors above 0.94. On the other hand, a 128 KHz digital signal, that is transmitted over the same optical channel, is not visible at the receiver side.

关键词： Wireless communication Photovoltaic systems Stimulated emission Bandwidth Optical receivers Stability analysis Real-time systems

来源：评论

学校读者我要写书评

暂无评论

VLC with PV-Based Optical Receiver for Motion Tolerant Optical Axon

VLC with PV-Based Optical Receiver for Motion Tolerant Optic...

引用

International Symposium on Communication Systems, Networks and Digital Signal Processing, CNSDSP

作者： George-Iulian Uleru Mircea Hulea Zabih Ghassemlooy Faculty of Automatic Control and Computer Engineering Gheorghe Asachi Technical University of Iasi Iasi Romania Photonics Technologt Lab Optical Communications Research Group. FEE Northumbria University Newcastle upon Tyne United Kingdom

ISBN: (数字)9798350348743

ISBN: (纸本)9798350348750

Optical axons with visible light communication (VLC) can be used to connect areas of spiking neurons that are in relative motion to each other. In electro-optical-based spiking neural network the parallel transmission of the spikes generated by many neurons is achieved by multiplexing of optical signals. Alternatively, serial transmission of the optical pulses is possible if the activation rate of the neurons permits additional delays. In low-speed VLC systems, an energy efficient photovoltaic panels (PVs) could be used for energy harvesting and data reception (i.e., photodetectors). In this work, we report a multi-input optical axon VLC link with PV -based receiver and evaluate its performance in terms of the bit error ratio (BER) when PV panel powers the SOMAs of the neurons at the transmitter side. The results show that with power harvesting BER varies between 16% and ~40% when the channel length and misalignment are in the ranges 5 - 15 cm, and 0 - 60 degree, when the ambient light is around 280 lux. In the dark these parameters, when the ambient light is below 10 lux, BER drops under 10% for line of sight and distances up to 5 m.

关键词： Axons Neurons Optical computing Optical fiber networks Optical receivers Adaptive optics Optical transmitters

来源：评论

学校读者我要写书评

暂无评论

Leveraging protein-protein interactions in phenotype prediction through graph neural networks 21

Leveraging protein-protein interactions in phenotype predict...

引用

21st IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2024

作者： Smeriglio, Riccardo Rosell-Mirmi, Joana Radeva, Petia Abante, Jordi Universitat de Barcelona Dpt. of Physics Spain Politecnico di Torino Control and Computer Engineering Dpt. Turin Italy Headache Research Group Vall d'Hebron Institut de Recerca Catalonia Barcelona Spain Universitat de Barcelona Institute of Neurosciences Dpt. of Mathematics & Computer Science Catalonia Barcelona Spain Laboratory of Stem Cells & Regenerative Medicine Creatio Production & Validation Center of Advanced Therapies Spain Universitat de Barcelona Institute of Neurosciences Dpt. of Biomedical Sciences Spain Dpt. of Mathematics & Computer Science Catalonia Barcelona Spain

ISBN: (纸本)9798350356632

Current genotype-to-phenotype models, such as polygenic risk scores, only account for linear relationships between genotype and phenotype and ignore epistatic interactions, limiting the complexity of the diseases that can be properly characterized. Protein-protein interaction networks have the potential to improve the performance of the models. Moreover, interactions at the protein level can have profound implications in understanding the genetic etiology of diseases and, in turn, for drug development. In this article, we propose a novel approach for phenotype prediction based on graph neural networks (GNNs) that naturally incorporates existing protein interaction networks into the model. As a result, our approach can naturally discover relevant epistatic interactions. We assess the potential of this approach using simulations and comparing it to linear and other non-linear approaches. We also study the performance of the proposed GNN-based methods in predicting Alzheimer's disease, one of the most complex neurodegenerative diseases, where our GNN approach outperform state of the art methods. In addition, we show that our proposal is able to discover critical interactions in the Alzheimer's disease. Our findings highlight the potential of GNNs in predicting phenotypes and discovering the underlying mechanisms of complex diseases. © 2024 IEEE.

关键词： Prediction models

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：