检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Rabiei, Shima Mishra, Sandipan Paternain, Santiago Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute United States Department of Mechanical Aerospace and Nuclear Engineering Rensselaer Polytechnic Institute United States

This work considers the problem of transfer learning in the context of reinforcement learning. Specifically, we consider training a policy in a reduced order system and deploying it in the full state system. The motivation for this training strategy is that running simulations in the full-state system may take excessive time if the dynamics are complex. While transfer learning alleviates the computational issue, the transfer guarantees depend on the discrepancy between the two systems. In this work, we consider a class of cascade dynamical systems, where the dynamics of a subset of the state-space influence the rest of the states but not vice-versa. The reinforcement learning policy learns in a model that ignores the dynamics of these states and treats them as commanded inputs. In the full-state system, these dynamics are handled using a classic controller (e.g., a PID). These systems have vast applications in the control literature and their structure allows us to provide transfer guarantees that depend on the stability of the inner loop controller. Numerical experiments on a quadrotor support the theoretical findings. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Real-Time Multi-Class Infection Classification for Respiratory Diseases

引用

computers, Materials & Continua 2022年第11期73卷 4157-4177页

作者： Ahmed El.Shafee Walid El-Shafai Abdulaziz Alarifi Mohammed Amoon Aman Singh Moustafa H.Aly Department of Electrical Engineering Faculty of EngineeringAhram Canadian UniversityGizaEgypt Department of Electronics and Electrical Communications Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Department of Computer Science Community CollegeKing Saud UniversityRiyadh11437Saudi Arabia Higher Polytechnic School Universidad Europea del AtlánticoSantander39011Spain Electronics and Communications Engineering Department College of Engineering and TechnologyArab Academy for ScienceTechnology and Maritime TransportAlexandria1029Egypt

Real-time disease prediction has emerged as the main focus of study in the field of computerized *** disease identification framework can assist medical practitioners in diagnosing disease in a way that is reliable,consistent,and timely,successfully lowering mortality rates,particularly during endemics and *** prevent this pandemic’s rapid and widespread,it is vital to quickly identify,confine,and treat affected *** need for auxiliary computer-aided diagnostic(CAD)systems has *** recent studies have indicated that radiological pictures contained critical information regarding the COVID-19 *** advanced convolutional neural network(CNN)architectures in conjunction with radiological imaging makes it possible to provide rapid,accurate,and extremely useful susceptible *** research work proposes a methodology for real-time detection of COVID-19 infections caused by the Corona *** purpose of this study is to offer a two-way COVID-19(2WCD)diagnosis prediction deep learning system that is built on Transfer Learning Methodologies(TLM)and features customized fine-tuning on top of fully connected layered pre-trained CNN architectures.2WCD has applied modifications to pre-trained models for better *** is designed and implemented to improve the generalization ability of the classifier for binary and multi-class *** with the ability to differentiate COVID-19 and No-Patient in the binary class model and COVID-19,No-Patient,and Pneumonia in the multi-class model,our framework is augmented with a critical add-on for visually demonstrating infection in any tested radiological image by highlighting the affected region in the patient’s lung in a recognizable color *** proposed system is shown to be extremely robust and reliable for real-time COVID-19 diagnostic *** can also be used to forecast other lung-related *** the system can assist medical practitioner

关键词： COVID-19 real-time computerized disease prediction intelligent disease identification framework CAD systems X-rays CT-scans CNN real-time detection of COVID-19 infections

来源：评论

学校读者我要写书评

暂无评论

ARMAN: A Reconfigurable Monolithic 3D Accelerator Architecture for Convolutional Neural Networks

arXiv

引用

arXiv 2024年

作者： Sedaghatgoo, Ali Hajisadeghi, Amir M. Momtazpour, Mahmoud Bagherzadeh, Nader The Department of Computer Engineering Amirkabir University of Technology Tehran Polytechnic Iran The Department of Electrical Engineering and Computer Science University of California Irvine United States

The Convolutional Neural Network (CNN) has emerged as a powerful and versatile tool for artificial intelligence (AI) applications. Conventional computing architectures face challenges in meeting the demanding processing requirements of compute-intensive CNN applications, as they suffer from limited throughput and low utilization. To this end, specialized accelerators have been developed to speed up CNN computations. However, as we demonstrate in this paper via extensive design space exploration, different neural network models have different characteristics, which calls for different accelerator architectures and configurations to match their computing demand. We show that a one-size-fits-all fixed architecture does not guarantee optimal power/energy/performance trade-off. To overcome this challenge, this paper proposes ARMAN, a novel reconfigurable systolic-array-based accelerator architecture based on Monolithic 3D (M3D) technology for CNN inference. The proposed accelerator offers the flexibility to reconfigure among different scale-up or scale-out arrangements depending on the neural network structure, providing the optimal trade-off across power, energy, and performance for various neural network models. We demonstrate the effectiveness of our approach through evaluations of multiple benchmarks. The results demonstrate that the proposed accelerator exhibits up to 2x, 2.24x, 1.48x, and 2x improvements in terms of execution cycles, power, energy, and EDP respectively, over the non-configurable architecture. © 2024, CC BY.

关键词： Systolic arrays

来源：评论

学校读者我要写书评

暂无评论

Thermally robust compact single Bragg grating silicon modulator for photonic computing

引用

Applied Optics 2025年第16期64卷 4646-4653页

作者： Meng Zhang Nicholas Gangi Amir Begović Alexer Chen Bowen Liu Z Rena Huang Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute Troy New York 12180 USA Department of Physics Applied Physics and Astronomy Rensselaer Polytechnic Institute Troy New York 12180 USA

We report, to our knowledge, a novel compact, thermally operated optical modulator with 6-bit resolution. The device comprises a slow-light photonic structure, a Bragg grating with a footprint of $10\,\,{\unicode{x00B5}{\rm m}}$ by $50\,\,{\unicode{x00B5}{\rm m}}$ . This single Bragg-grating modulator (SBG-M) operates based on thermally induced band edge shift of the photonic stop band and demonstrates almost constant normalized mean square error (NMSE) lower than 0.001 from room temperature to ${40^\circ}{\rm C}$ , while maintaining thermal robustness up to ${65^\circ}{\rm C}$ limited by the Johnson noise of the on-chip photodetector. The clock frequency, computing accuracy, power consumption, thermal stability, and fabrication-induced spectrum non-ideality are thoroughly studied. The SBG-M achieves a measured lowest NMSE of $5.0 \times {10^{- 4}}$ , with an average power consumption of 5.29 mW. Compared to other optical devices such as micro-ring resonators and slow-light incorporated Mach–Zehnder modulators, the reported device demonstrates significant advantages in compactness, lower power consumption, and thermal robustness.

关键词： Optical computing Optical modulators Phase shift Quantum computation Silicon modulators Silicon photonics

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Network-Based Fingerprint Reformation for Minimizing Displacement 12

Deep Neural Network-Based Fingerprint Reformation for Minimi...

引用

12th International Conference on System Modeling and Advancement in Research Trends, SMART 2023

作者： Kumar, Munish Kumar, Sandeep Gulhane, Monali Beniwal, Rajender Kumar Nitin Choudhary, Shilpha Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Vaddeswaram India Department of Cse Pune India Electrical and Electronics Engineering Guru Jambheshwar University of Science and Technology Haryana Hisar India Govt. Polytechnic Department of Computer Engg. Haryana Hisar India Hyderabad India

ISBN: (纸本)9798350369861

In the realm of biometric authentication and forensic analysis, the accurate matching of fingerprints is paramount. Fingerprint displacement, caused by factors such as skin elasticity and pressure during touch, has been a significant challenge in achieving precise fingerprint recognition both during the enrollment and the authentication process. This research presents a technique to address this issue by leveraging Support Vector Machines (SVM) for fingerprint transformation and displacement minimization. The proposed methodology involves the extraction of distinctive fingerprint features and the application of SVM-based algorithms to realign and correct fingerprint distortions resulting from displacement. We analyze the effectiveness of SVM in reducing displacement-induced errors and improving matching accuracy. Experimental results demonstrate the potential of SVM-based fingerprint transformation techniques to significantly enhance the robustness and reliability of fingerprint recognition systems. This research contributes to the ongoing efforts in biometrics and forensic science by providing a practical solution to the problem of fingerprint displacement, with potential applications in identity verification, criminal investigations, and security systems. The findings of this study offer a promising avenue for further research and development in the field of biometric authentication, ultimately leading to more accurate and secure identification methods. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Design of Multi-Robotic System for Navigation in a Tomato Crop Field Using Human Robot Interaction, Robot Operating System and Gazebo

Design of Multi-Robotic System for Navigation in a Tomato Cr...

引用

electrical, computer and Energy Technologies (ICECET), International Conference on

作者： Balasubramaniyan Chandrasekaran Department of Electrical and Computer Engineering Florida Polytechnic University Lakeland FL

Robotics is an emerging field and finds application in various areas. For applications such as navigation and collecting information in a large agricultural field, it is important to use more than one robot for timely and efficient information gathering. In this paper, an architecture for multi-robot navigation in an agricultural field is presented and the system uses Robot Operating System and Gazebo. This is a work in progress.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A review of Multisensor Fusion techniques used in the development of Mobile Robotic Systems

A review of Multisensor Fusion techniques used in the develo...

引用

International Conference on Robotics and Automation engineering (ICRAE)

作者： Balasubramaniyan Chandrasekaran Department of Electrical and Computer Engineering Florida Polytechnic University Lakeland FL

Robotics is a multi-disciplinary field that involves the use of multiple sensors for the application. These sensors can be of the same type or different types and measure various attributes of the environment. In this paper, a review of some of the multi sensor fusion techniques used to combine the data from the sensors for the development of robotic systems is presented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Beamspace Channel Estimation for Wideband Millimeter-Wave MIMO: A Model-Driven Unsupervised Learning Approach

引用

IEEE Transactions on Wireless Communications 2023年第3期22卷 1808-1822页

作者： He, Hengtao Wang, Rui Jin, Weijie Jin, Shi Wen, Chao-Kai Li, Geoffrey Ye Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong Hong Kong The Hong Kong Polytechnic University Department of Electronic and Information Engineering Hong Kong Hong Kong Imperial College London Department of Electrical and Electronic Engineering LondonSW7 2BX United Kingdom Southeast University National Mobile Communications Research Laboratory Nanjing210096 China

Millimeter-wave (mmWave) communications have been one of the promising technologies for future wireless networks that integrate a wide range of data-demanding applications. To compensate for the large channel attenuation in mmWave band and avoid high hardware cost, a lens-based beamspace massive multiple-input multiple-output (MIMO) system is considered. However, the spatial-wideband effect in wideband mmWave systems makes channel estimation very challenging, especially when the receiver is equipped with a limited number of radio-frequency (RF) chains. Furthermore, the real channel data cannot be obtained before the mmWave system is used in a new environment, which makes it impossible to train a deep learning (DL)-based channel estimator using real data set beforehand. To solve the problem, we propose a model-driven unsupervised learning network, named learned denoising-based generalized expectation consistent (LDGEC) signal recovery network. By utilizing the Stein's unbiased risk estimator loss, the LDGEC network can be trained only with limited measurements corresponding to the pilot symbols, instead of the real channel data. Even if designed for unsupervised learning, the LDGEC network can be supervisingly trained with the real channel via the denoiser-by-denoiser way. The numerical results demonstrate that the LDGEC-based channel estimator significantly outperforms state-of-the-art compressive sensing-based algorithms when the receiver is equipped with a small number of RF chains and low-resolution ADCs. © 2002-2012 IEEE.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

A Hybrid based Kolmogorov-Arnold Network for Intrusion Detection Systems in IoT

A Hybrid based Kolmogorov-Arnold Network for Intrusion Detec...

引用

2024 IEEE Middle East Conference on Communications and Networking, MECOM 2024

作者： Amouri, Amar Rahhal, Mohamad Mahmoud Al Bazi, Yakoub Alaparthy, Vishwa Teja Fotopoulos, Georgios Abu Dhabi Polytechnic Academic Support Department Abu Dhabi United Arab Emirates King Saud University College of Computer & Information Science Riyadh Saudi Arabia University of South Florida Electrical Engineering Department TampaFL United States

ISBN: (纸本)9798350376715

In recent years, machine learning models have become increasingly prevalent across various fields, particularly in intrusion detection. This trend is especially noticeable in the Internet of Things (IoT) domain, where the intricate network of interconnected devices requires sophisticated defence mechanisms against potential threats. To tackle this challenge, researchers are turning to deep learning techniques, harnessing the power of artificial intelligence (AI) to secure IoT environments. We introduce a novel Intrusion Detection System (IDS) based on the Kolmogorov-Arnold Network (KAN). This system combines the efficiency of Long Short-Term Memory (LSTM) networks, which excel in handling time series data, with the adaptability of KAN, thanks to its learnable activation functions. To the best of the authors' knowledge, this is the 1st manuscript utilizing KANs as a core algorithm for intrusion detection. Our experimental results highlight the high detection accuracy of the hybrid IDS, achieving over 98% accuracy in distinguishing between malicious and normal instances. Additionally, we provide a comparative analysis with conventional Multi-Layer Perceptron (MLP) networks, evaluating performance metrics such as Precision, Recall, and F1-score. Our findings underscore the potential of a hybrid IDS approach in enhancing the security of IoT networks. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Investigation of a New Stator Permanent Magnet with the effects of Flux-Reversal and Flux-Switching

Investigation of a New Stator Permanent Magnet with the effe...

引用

Power Electronic and Drive Systems and Technologies Conference (PEDSTC)

作者： Mohammad Reza Sarshar Mohammad Amin Jalali Kondelaji Mojtaba Mirsalim Seyed Hamid Montazeri Department of Electrical Engineering Amirkabir University of Technology (Tehran Polytechnic) Tehran Iran Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology (MIT) Cambridge USA

ISBN: (数字)9798331533946

ISBN: (纸本)9798331533953

This article studies a new stator-permanent magnet (PM) motor with flux-switching (FS) and flux-reversal (FR) effects synergies. The proposed structure benefits from the splitting stator pole PMs and consequent-pole FRPM, which reduces the PM utilization compared to the conventional ones. Also, the proposed structure is optimized by a random search multiobjective algorithm to attain the structure with the highest output torque and minimum torque ripple. Additionally, the proposed motor is compared to a conventional FSPM to investigate the advantages of the main motor. Using finite element analysis (FEA) studies, the flux density distribution results show that the FR effect lowers the saturation risk compared to FSPM. Also, the back-EMF generation of the proposed motor has improved by 135% compared to its benchmark. Correspondingly, fullload results show that the proposed topology has enhanced the average torque by 75% and deteriorated the ripple by about 55% compared to FSPM. Therefore, the proposed structure offers a profitable for high torque density applications.

关键词： Magnetic flux Torque Switches Stators Motors Permanent magnets Power electronics Topology Torque measurement Saturation magnetization

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：