检索结果-内蒙古大学图书馆

IEEE International Symposium on Applications of Ferroelectrics (ISAF)

作者： Jack Rothenberg Keshav Bimbraw Haichong Zhang Robotics and Biomedical Engineering Worcester Polytechnic Institute Worcester USA Robotics Engineering Worcester Polytechnic Institute Worcester USA

ISBN: (数字)9798350371901

ISBN: (纸本)9798350371918

Ultrasound images of the forearm can be used to classify hand gestures towards developing human machine interfaces. In our previous work, we have demonstrated gesture classification using ultrasound on a single subject without removing the probe before evaluation. This has limitations in usage as once the probe is removed and replaced, the accuracy declines since the classifier performance is sensitive to the probe location on the arm. In this paper, we propose training a model on multiple data collection sessions to create a generalized model, utilizing incremental learning through fine tuning. Ultrasound data was acquired for 5 hand gestures within a session (without removing and putting the probe back on) and across sessions. A convolutional neural network (CNN) with 5 cascaded convolution layers was used for this study. A pre-trained CNN was fine tuned with the convolution blocks acting as a feature extractor, and the parameters of the remaining layers updated in an incremental fashion. Fine tuning was done using different session splits within a session and between multiple sessions. We found that incremental fine tuning can help enhance classification accuracy with more fine tuning sessions. After 2 fine tuning sessions for each experiment, we found an approximate 10% increase in classification accuracy. This work demonstrates that incremental learning through fine tuning on ultrasound based hand gesture classification can be used improves accuracy while saving storage, processing power, and time. It can be expanded to generalize between multiple subjects and towards developing personalized wearable devices.

关键词： Hands Training Ultrasonic imaging Accuracy Incremental learning Feature extraction Data models Convolutional neural networks Probes Tuning

来源：评论

学校读者我要写书评

暂无评论

Multiview Compounding for Linear Array-Based 3D Photoacoustic Imaging

Multiview Compounding for Linear Array-Based 3D Photoacousti...

引用

Photons Plus Ultrasound: Imaging and Sensing 2023

作者： Garje, Yash Tang, Yichuan Jaupi, Enxhi Zhang, Haichong K. Robotics Engineering Department Worcester Polytechnic Institute 100 Institute Rd WorcesterMA01609 United States Biomedical Engineering Department Worcester Polytechnic Institute 100 Institute Rd WorcesterMA01609 United States Computer Science Department Worcester Polytechnic Institute 100 Institute Rd WorcesterMA01609 United States

ISBN: (纸本)9781510658639

Two-dimensional and three-dimensional photoacoustic (PA) visualization is an emerging diagnostic procedure for investigation and research in vascular studies. Current manual/mechanized target scanning techniques involve sweeping the target along the elevation to generate 3D visuals. However, since the linear array probes exhibit poor resolution along the direction orthogonal to its focal plane, these techniques are prone to miss out on the organic structures parallel to the lateral direction. This could result in a misrepresentation of the target and is a critical shortfall of the method. We propose a multiview scanning and compounding technique to overcome the directionality bias and obtain more accurate and isotropic imaging performance. Using electromechanical translatory and rotary stages for multiview data acquisition, we generate a unified 3D visualization. A data processing pipeline illustrates an axial implementation of the Hilbert transform followed by spatial integration of the volumetric data to obtain the output. A 6-directional scanning approach improves the completeness of the structural details. We validated the technique using sub-millimeter-sized balls and wire phantoms. We first observed an enhanced resemblance of the outcome with the actual target in the ball phantom. Secondly, we observed imaging quality improvement with isotropic intensity distribution prominently in the wire phantom. A comparative analysis showed around a 50% reduction in the standard deviation of intensity distribution as compared to conventional unidirectional 3D PA imaging. © 2023 SPIE.

关键词： Phantoms

来源：评论

学校读者我要写书评

暂无评论

Forearm Ultrasound Based Gesture Recognition on Edge

Forearm Ultrasound Based Gesture Recognition on Edge

引用

International Workshop on Wearable and Implantable Body Sensor Networks (BSN)

作者： Keshav Bimbraw Haichong K. Zhang Bashima Islam Robotics Engineering Worcester Polytechnic Institute Worcester USA Robotics Engineering and Biomedical Engineering Worcester Polytechnic Institute Worcester USA Electrical and Computer Engineering Worcester Polytechnic Institute Worcester USA

ISBN: (数字)9798331530143

ISBN: (纸本)9798331530150

Ultrasound imaging of the forearm has demon-strated significant potential for accurate hand gesture classification. Despite this progress, there has been limited focus on developing a stand -alone end-to-end gesture recognition system which makes it mobile, real-time and more user friendly. To bridge this gap, this paper explores the deployment of deep neural networks for forearm ultrasound-based hand gesture recognition on edge devices. Utilizing quantization techniques, we achieve substantial reductions in model size while maintaining high accuracy and low latency. Our best model, with Float16 quantization, achieves a test accuracy of 92% and an inference time of 0.31 seconds on a Raspberry Pi. These results demonstrate the feasibility of efficient, real-time gesture recognition on resource-limited edge devices, paving the way for wearable ultrasound-based systems.

关键词： Deep learning Ultrasonic imaging Accuracy Quantization (signal) Imaging Gesture recognition Real-time systems Biomedical monitoring Low latency communication Monitoring

来源：评论

学校读者我要写书评

暂无评论

Improving Intersession Reproducibility for Forearm Ultrasound based Hand Gesture Classification through an Incremental Learning Approach

arXiv

引用

arXiv 2024年

作者： Bimbraw, Keshav Rothenberg, Jack Zhang, Haichong K. Robotics Engineering Worcester Polytechnic Institute Worcester United States Robotics and Biomedical Engineering Worcester Polytechnic Institute Worcester United States

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Laparoscopic Photoacoustic Imaging System Integrated with the da Vinci Surgical System

Laparoscopic Photoacoustic Imaging System Integrated with th...

引用

Medical Imaging 2023: Image-Guided Procedures, Robotic Interventions, and Modeling

作者： Gao, Shang Wang, Yang Zhou, Haoying Yang, Kehan Jiang, Yiwei Lu, Liang Wang, Shiyue Ma, Xihan Nephew, Benjamin C. Fichera, Loris Fischer, Gregory S. Zhang, Haichong K. Robotics Engineering Worcester Polytechnic Institute 100 Institute Rd WorcesterMA01609 United States Computer Sciencev Biology & Biotechnology Worcester Polytechnic Institute 100 Institute Rd WorcesterMA01609 United States Neuroscience Worcester Polytechnic Institute 100 Institute Rd WorcesterMA01609 United States Biomedical Engineering Worcester Polytechnic Institute 100 Institute Rd WorcesterMA01609 United States Mechanical & Materials Engineering Worcester Polytechnic Institute 100 Institute Rd WorcesterMA01609 United States Electrical & Computer Engineering Worcester Polytechnic Institute 100 Institute Rd WorcesterMA01609 United States

ISBN: (纸本)9781510660373

This paper presents the design, fabrication, and experimental validation of a photoacoustic (PA) imaging probe for robotic surgery. PA is an emerging imaging modality that combines the high penetration of ultrasound (US) imaging with high optical contrast. When equipped with a PA probe, a surgical robot can provide intraoperative guidance to the operating physician, alerting them of the presence of vital substrate anatomy (e.g., nerves or blood vessels) invisible to the naked eye. Our probe is designed to work with the da Vinci surgical system to produce three-dimensional PA images: We propose an approach wherein the robot provides remote center-of-motion (RCM) scanning across a region of interest, and successive PA tomographic images are acquired and interpolated to produce a three-dimensional PA image. To demonstrate the accuracy of the PA guidance in scanning 3D tomography actuated by the robot, we conducted an experimental study that involved the imaging of a multi-layer wire phantom. The computed Target Registration Error (TRE) between the acquired PA image and the phantom was 1.5567±1.3605 mm. The ex vivo study demonstrated the function of the proposed laparoscopic device in 3D vascular detection. These results indicate the potential of our PA system to be incorporated into clinical robotic surgery for functional anatomical guidance. © 2023 SPIE.

关键词： Robotic surgery

来源：评论

学校读者我要写书评

暂无评论

Hand Gesture Classification Based on Forearm Ultrasound Video Snippets Using 3D Convolutional Neural Networks

arXiv

引用

arXiv 2024年

作者： Bimbraw, Keshav Talele, Ankit Zhang, Haichong K. Robotics Engineering Worcester Polytechnic Institute Worcester United States Robotics and Biomedical Engineering Worcester Polytechnic Institute Worcester United States

Ultrasound based hand movement estimation is a crucial area of research with applications in human-machine interaction. Forearm ultrasound offers detailed information about muscle morphology changes during hand movement which can be used to estimate hand gestures. Previous work has focused on analyzing 2-Dimensional (2D) ultrasound image frames using techniques such as convolutional neural networks (CNNs). However, such 2D techniques do not capture temporal features from segments of ultrasound data corresponding to continuous hand movements. This study uses 3D CNN based techniques to capture spatio-temporal patterns within ultrasound video segments for gesture recognition. We compared the performance of a 2D convolution-based network with (2+1)D convolution-based, 3D convolution-based, and our proposed network. Our methodology enhanced the gesture classification accuracy to 98.8 ± 0.9%, from 96.5 ± 2.3% compared to a network trained with 2D convolution layers. These results demonstrate the advantages of using ultrasound video snippets for improving hand gesture classification performance. © 2024, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Fluence Compensation for Linear Array-Based Photoacoustic Imaging System Using Geometrical Depth Mapping

Fluence Compensation for Linear Array-Based Photoacoustic Im...

引用

2023 IEEE International Ultrasonics Symposium, IUS 2023

作者： Tang, Yichuan Lesniak, Wojciech G. Pomper, Martin G. Zhang, Haichong K. Johns Hopkins University Department of Radiology and Radiological Science BaltimoreMD United States Worcester Polytechnic Institute Department of Robotics Engineering WorcesterMA United States Worcester Polytechnic Institute Department of Biomedical Engineering WorcesterMA United States

ISBN: (纸本)9798350346459

Linear array-based photoacoustic (PA) imaging has been applied in tissue imaging. Due to optical attenuation, deep tissue receives less optical energy compared to surface tissue and thus generates weaker acoustic signals. To compensate for fluence change along light penetration direction, methods have been proposed based on optical transport model or statistical learning. However, these methods either require knowledge about optical properties of the tissue or involve extensive computation. In this work, we propose a fluence compensation method based on geometrical depth mapping derived from outer contour of the tissue. Our method requires no information on optical properties and does not involve extensive computation. Validations were carried out in simulation and ex vivo experiment. Results show that image intensities in deep tissue are enhanced, and image intensity distribution is more homogenous along the light penetration depth after fluence compensation. The proposed method proved effective for fluence compensation in imaging ex vivo tissue with homogeneous optical properties. © 2023 IEEE.

关键词： Tissue

来源：评论

学校读者我要写书评

暂无评论

Hacking the Colony: On the Disruptive Effect of Misleading Pheromone and How to Defend Against It 21

Hacking the Colony: On the Disruptive Effect of Misleading P...

引用

21st International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2022

作者： Aswale, Ashay López, Antonio Ammartayakun, Aukkawut Pinciroli, Carlo Department of Robotics Engineering Worcester Polytechnic Institute WorcesterMA United States

ISBN: (纸本)9781713854333

Ants have evolved to seek and retrieve food by leaving trails of pheromones. This mechanism has inspired several approaches to decentralized multi-robot coordination. However, in this paper, we show that pheromone trails are a fragile mechanism for coordination, and can be sabotaged to starve the colony. We introduce detractors: malicious agents that leave a misleading, but indistinguishable, trail of food pheromone to distract and trap cooperator ants in the nest. We analyze the effectiveness of detractors with respect to parameters such as evaporation rate of misleading pheromone and fraction of detractors in the colony. In addition, we propose a countermeasure to this attack by introducing a new type of pheromone: the cautionary pheromone. Cooperator ants secrete this type of pheromone atop existing food trails as a warning. When the cautionary pheromone intensity exceeds the food pheromone intensity, cooperator ants ignore overlapping food pheromone. We show that, despite its simplicity, this defense mechanism can limit, but not nullify, the effect of detractors. Ultimately, our work shows that pheromone-based coordination, while effective, is also fragile. © 2022 International Foundation for Autonomous Agents and Multiagent Systems (***). All rights reserved

关键词： Swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

A System for Watering and Autonomously Monitoring Plants

A System for Watering and Autonomously Monitoring Plants

引用

IEEE Symposium on Systems and Information engineering Design, SIEDS

作者： E. Gutman L. Harrison J. Hart I. Lucas C. Mullane G. C. Lewin Department of Mechanical Engineering Worcester Polytechnic Institute Worcester Massachusetts Department of Robotics Engineering Worcester Polytechnic Institute Worcester Massachusetts

ISBN: (数字)9798331535759

ISBN: (纸本)9798331535766

To alleviate the challenges of plant care, the Great Roboticz Ladiez’ Plant Watering Robot (GRL PWR) team developed SWAMP, a mobile robotic System for Watering and Autonomously Monitoring Plants. SWAMP replicates the plant care a human provides with minimal user input and allows plant owners the freedom to keep their plants anywhere in their homes. From stakeholder analysis, the team categorized the main functionalities required to meet user needs into Customizing Plant Care, Accessing Plants, Assessing Plant Condition, Providing Water, and System Monitoring. The user can input unique watering instructions and plant characteristics. The robot uses a differential drive to autonomously navigate and localize within its environment while safely avoiding obstacles. The robot has an articulated arm to reach plants up to 24 -inches off the ground and set back no more than 2.5 -inches from the edge of the surface. These design choices allow SWAMP to accurately meet the watering needs of each plant, reducing the time commitment required from plant owners. GRL PWR will demonstrate the system in the WPI Gordon Library, providing a real-world environment to assess SWAMP’s ability to map its surroundings, navigate around obstacles, and accurately deliver water to plants.

关键词： Water Visualization Navigation Storage management Robot vision systems User interfaces Stakeholders Robots Monitoring Testing

来源：评论

学校读者我要写书评

暂无评论

Run-Time Task Composition with Safety Semantics 41

Run-Time Task Composition with Safety Semantics

引用

41st International Conference on Machine Learning, ICML 2024

作者： Leahy, Kevin Mann, Makai Serlin, Zachary Department of Robotics Engineering Worcester Polytechnic Institute LexingtonMA United States MIT Lincoln Laboratory LexingtonMA United States

Compositionality is a critical aspect of scalable system design. Here, we focus on Boolean composition of learned tasks as opposed to functional or sequential composition. Existing Boolean composition for Reinforcement Learning focuses on reaching a satisfying absorbing state in environments with discrete action spaces, but does not support composable safety (i.e., avoidance) constraints. We provide three contributions: i) introduce two distinct notions of compositional safety semantics;ii) show how to enforce either safety semantics, prove correctness, and analyze the trade-offs between the two safety notions;and iii) extend Boolean composition from discrete action spaces to continuous action spaces. We demonstrate these techniques using modified versions of value iteration in a grid world, Deep Q-Network (DQN) in a grid world with image observations, and Twin Delayed DDPG (TD3) in a continuous-observation and continuous-action Bullet physics environment. Copyright 2024 by the author(s)

关键词： Reinforcement learning

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：