检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhou, Haoying Yang, Hao Deguet, Anton Fichera, Loris Wu, Jie Ying Kazanzides, Peter Department of Robotics Engineering Worcester Polytechnic Institute MA United States Laboratory for Computational Sensing and Robotics JHU MD United States Department of Computer Science Vanderbilt University TN United States Department of Computer Science Johns Hopkins University MD United States

The da Vinci Research Kit (dVRK, also known as dVRK Classic) is anopen-source teleoperated surgical robotic system whose hardware is obtainedfrom the first generation da Vinci Surgical System (Intuitive, Sunnyvale, CA,USA). The dVRK has greatly facilitated research in robot-assisted surgery overthe past decade and helped researchers address multiple major challenges inthis domain. Recently, the dVRK-Si system, a new version of the dVRK which usesmechanical components from the da Vinci Si Surgical System, became available tothe community. The major difference between the first generation da Vinci andthe da Vinci Si is in the structural upgrade of the Patient Side Manipulator(PSM). Because of this upgrade, the gravity of the dVRK-Si PSM can no longer beignored as in the dVRK Classic. The high gravity offset may lead to relativelylow control accuracy and longer response time. In addition, althoughsubstantial progress has been made in addressing the dynamic modelidentification problem for the dVRK Classic, further research is required onmodel-based control for the dVRK-Si, due to differences in mechanicalcomponents and the demand for enhanced control performance. To address theseproblems, in this work, we present (1) a novel full kinematic model of thedVRK-Si PSM, and (2) a gravity compensation approach based on the dynamic modelidentification. © 2025, CC BY.

关键词： Surgical equipment

来源：评论

学校读者我要写书评

暂无评论

AdaER: An Adaptive Experience Replay Approach for Continual Lifelong Learning

arXiv

引用

arXiv 2023年

作者： Li, Xingyu Tang, Bo Li, Haifeng The Department of Electrical and Computer Engineering Mississippi State University Mississippi StateMS39762 United States The Department of Electrical and Computer Engineering Worcester Polytechnic Institute WorcesterMA01609 United States The School of Geosciences and fInfo-Physics Central South University Changsha410083 China

Continual lifelong learning is an machine learning framework inspired by human learning, where learners are trained to continuously acquire new knowledge in a sequential manner. However, the non-stationary nature of streaming training data poses a significant challenge known as catastrophic forgetting, which refers to the rapid forgetting of previously learned knowledge when new tasks are introduced. While some approaches, such as experience replay (ER), have been proposed to mitigate this issue, their performance remains limited, particularly in the class-incremental scenario which is considered natural and highly challenging. In this paper, we present a novel algorithm, called adaptive-experience replay (AdaER), to address the challenge of continual lifelong learning. AdaER consists of two stages: memory replay and memory update. In the memory replay stage, AdaER introduces a contextually-cued memory recall (C-CMR) strategy, which selectively replays memories that are most conflicting with the current input data in terms of both data and task. Additionally, AdaER incorporates an entropy-balanced reservoir sampling (E-BRS) strategy to enhance the performance of the memory buffer by maximizing information entropy. To evaluate the effectiveness of AdaER, we conduct experiments on established supervised continual lifelong learning benchmarks, specifically focusing on class-incremental learning scenarios. The results demonstrate that AdaER outperforms existing continual lifelong learning baselines, highlighting its efficacy in mitigating catastrophic forgetting and improving learning performance. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

AdaER: An Adaptive Experience Replay Approach for Continual Lifelong Learning

arXiv

引用

arXiv 2023年

作者： Li, Xingyu Tang, Bo Li, Haifeng Department of Electrical and Computer Engineering Mississippi State University Mississippi StateMS39762 United States Department of Electrical and Computer Engineering Worcester Polytechnic Institute WorcesterMA01609 United States School of Geosciences and fInfo-Physics Central South University Changsha410083 China

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Importance of considering microscopic structures in modeling brain stimulation

引用

Brain Stimulation 2025年第4期18卷 1150-1152页

作者： Zhen Qi Gregory M. Noetscher Alton Miles Konstantin Weise Thomas R. Knösche Cameron R. Cadman Alina R. Potashinsky Kelu Liu William A. Wartman Guillermo Nunez Ponasso Marom Bikson Hanbing Lu Zhi-De Deng Aapo Nummenmaa Sergey N. Makaroff Electrical and Computer Engineering Department Worcester Polytechnic Institute Worcester MA USA Max Planck Institute for Human Cognitive and Brain Sciences Leipzig Germany Leipzig University of Applied Sciences (HTWK) Faculty of Engineering Leipzig Germany Department of Biomedical Engineering The City College of New York New York NY USA Neuroimaging Research Branch NIDA Intramural Research Program National Institutes of Health Baltimore MD USA Computational Neurostimulation Research Program Noninvasive Neuromodulation Unit Experimental Therapeutics and Pathophysiology Branch NIMH National Institutes of Health Baltimore MD USA Massachusetts General Hospital Harvard Medical School Boston MA USA Department of Mathematical Sciences Worcester Polytechnic Institute Worcester MA USA

来源：评论

学校读者我要写书评

暂无评论

Robust 3D Point Clouds Classification based on Declarative Defenders

arXiv

引用

arXiv 2024年

作者： Li, Kaidong Zhang, Tianxiao Zhong, Chuncong Zhang, Ziming Wang, Guanghui Department of Electrical Engineering & Computer Science University of Kansas 1520 West 15th St. LawrenceKS66045 United States Department of Electrical & Computer Engineering Worcester Polytechnic Institute 100 Institute Rd. WorcesterMA01609 United States Department of Computer Science Toronto Metropolitan University 350 Victoria Street TorontoONM5B 2K3 Canada

3D point cloud classification requires distinct models from 2D image classification due to the divergent characteristics of the respective input data. While 3D point clouds are unstructured and sparse, 2D images are structured and dense. Bridging the domain gap between these two data types is a non-trivial challenge to enable model interchangeability. Recent research using Lattice Point Classifier (LPC) highlights the feasibility of cross-domain applicability. However, the lattice projection operation in LPC generates 2D images with disconnected projected pixels. In this paper, we explore three distinct algorithms for mapping 3D point clouds into 2D images. Through extensive experiments, we thoroughly examine and analyze their performance and defense mechanisms. Leveraging current large foundation models, we scrutinize the feature disparities between regular 2D images and projected 2D images. The proposed approaches demonstrate superior accuracy and robustness against adversarial attacks. The generative model-based mapping algorithms yield regular 2D images, further minimizing the domain gap from regular 2D classification tasks. The source code is available at https://***/KaidongLi/***. © 2024, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

An Analog Front-End for a Photoplethysmography Patch to Monitor Respiratory Rate

An Analog Front-End for a Photoplethysmography Patch to Moni...

引用

2020 IEEE MIT Undergraduate Research Technology Conference, URTC 2020

作者： Elokda, Mona Jiang, Jiayi Mandile, Chloe Adler Guler, Ulkuhan Worcester Polytechnic Institute Department of Electrical and Computer Engineering WorcesterMA United States

ISBN: (纸本)9781728175713

This paper proposes the design of an analog frontend to be used in a photoplethysmography application to detect respiration rate and transmit the information using an RF antenna. This signal can then be processed off-chip to extract respiratory rate (RR). The chip is powered using wireless power transfer through the same antenna. The design includes an RF-to-DC converter, an LED driver, a transimpedence amplifier, a low-pass filter, a programmable gain amplifier, and a voltage controlled oscillator. The chip is designed in TSMC 0.18 μ$m$ CMOS process. The overall power consumption is 2.46 mW from a 3.3/1.8 V source. The input RF power signal, transmitted at a frequency of 13.56 MHz, is converted to a DC voltage using a passive rectifier with a power conversion efficiency of 73.6 %. The TIA has a gain of 113 dB and a bandwidth of 663 kHz. The achieved cutoff frequency of the filter is 5 Hz. © 2020 IEEE.

关键词： Cutoff frequency

来源：评论

学校读者我要写书评

暂无评论

An Analog Front-End for a Noninvasive Core Body Temperature Sensor

An Analog Front-End for a Noninvasive Core Body Temperature ...

引用

2020 IEEE MIT Undergraduate Research Technology Conference, URTC 2020

作者： Baccei, Eric MacOrri, Eric Guler, Ulkuhan Worcester Polytechnic Institute Department of Electrical and Computer Engineering WorcesterMA United States

ISBN: (纸本)9781728175713

Core body temperature falls under the list of vitals that must be closely monitored in many settings, such as a patient going through surgery or a soldier in the battlefield. Although the importance is major, there is' an abundance of devices that can do this remotely and in a noninvasive manner. This paper presents the design of an integrated analog front-end for noninvasive monitoring of core body temperature. This analog front-end was designed in the TSMC 0.18 ${\mu}$ m 3.3 V and 1.8 V CMOS process. The overall system consists of a voltage regulator, a constant current source, bias circuits, an operational amplifier, and a filter. Specifications achieved include an amplifier with open-loop gain of 84.4 dB, a filter with a cut off frequency of 0.4 Hz, and a total power consumption of 181.2 ${\mu}$ W. This was achieved with a total layout area of 0.027 mm 2. © 2020 IEEE.

关键词： Voltage regulators

来源：评论

学校读者我要写书评

暂无评论

A Photoplethysmography Wearable with Long-term Heart Rate Variability Detection Algorithm

A Photoplethysmography Wearable with Long-term Heart Rate Va...

引用

2020 IEEE MIT Undergraduate Research Technology Conference, URTC 2020

作者： Chieng, Bill Kavassalis, Fivos Baudino, Franco Guler, Ulkuhan Worcester Polytechnic Institute Department of Electrical and Computer Engineering WorcesterMA United States

ISBN: (纸本)9781728175713

This paper presents a wearable device that extracts and utilizes a photopfethysmogram waveform to measure and estimate various vital signs via a mobile application's custom-designed algorithms. These vital signs include peripheral oxygen saturation, heart rate, respiratory rate, and short/fong term heart rate variability. The device wirelessly transmits accumulated data to a mobile phone and a personal computer over Bluetooth Low Energy. Moreover, this paper explores the proposed device as an emerging technology with the Coronavirus Disease 19 (COVID-19) pandemic's contemporary concerns. The peripheral oxy gen saturation measurements would give an early indicator of degrading respiratory health before the apparent manifestation of symptoms. The convenient use of this device in a mobile setting is especially relevant to current isolation precautions in place and its critical role in improving at-risk patients' care. © 2020 IEEE.

关键词： Wearable technology

来源：评论

学校读者我要写书评

暂无评论

Adaer: An Adaptive Experience Replay Approach for Continual Lifelong Learning

SSRN

引用

SSRN 2023年

作者： Tang, Bo Li, Xingyu Li, Haifeng Department of Electrical and Computer Engineering Mississippi State University Mississippi StateMS39762 United States Department of Electrical and Computer Engineering Worcester Polytechnic Institute WorcesterMA01609 United States School of Geosciences and Info-Physics Central South University Hunan Changsha410083 China

Continual lifelong learning is an machine learning framework inspired by human learning, where learners are trained to continuously acquire new knowledge in a sequential manner. However, the non-stationary nature of streaming training data poses a significant challenge known as catastrophic forgetting, which refers to the rapid forgetting of previously learned knowledge when new tasks are introduced. While some approaches, such as experience replay (ER), have been proposed to mitigate this issue, their performance remains limited, particularly in the class-incremental scenario which is considered natural and highly challenging. In this paper, we present a novel algorithm, called adaptive-experience replay (AdaER), to address the challenge of continual lifelong learning. AdaER consists of two stages: memory replay and memory update. In the memory replay stage, AdaER introduces a contextually-cued memory recall (C-CMR) strategy, which selectively replays memories that are most conflicting with the current input data in terms of both data and task. Additionally, AdaER incorporates an entropy-balanced reservoir sampling (EBRS) strategy to enhance the performance of the memory buffer by maximizing information entropy. To evaluate the effectiveness of AdaER, we conduct experiments on established supervised continual lifelong learning benchmarks, specifically focusing on class-incremental learning scenarios. The results demonstrate that AdaER outperforms existing continual lifelong learning baselines, highlighting its efficacy in mitigating catastrophic forgetting and improving learning performance. © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Effects of Interference on Beamforming-Enabled Vehicular Networks in Multipath Propagation Environments 91

Effects of Interference on Beamforming-Enabled Vehicular Net...

引用

91st IEEE Vehicular Technology Conference, VTC Spring 2020

作者： Kanthasamy, Nivetha Wyglinski, Alexander M. Cowlagi, Raghvendra Worcester Polytechnic Institute Department of Electrical and Computer Engineering WorcesterMA United States

ISBN: (纸本)9781728152073

This paper characterizes the impact of interference on vehicular communications employing beamforming links between transmitters and receivers operating within a multipath propagation environment. Different road scenarios, such as an intersection and a roundabout are considered to determine the performance characteristics of the vehicle communication link. By employing the results for different antenna array elements and by varying distance, we analyse the bit error rate (BER) of vehicles operating in multipath propagation environments with an interferer within the vicinity of an communication link. © 2020 IEEE.

关键词： Multipath propagation

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：