检索结果-内蒙古大学图书馆

SASWISE-UE: Segmentation and synthesis with interpretable scalable ensembles for uncertainty estimation

computers in Biology and Medicine 2025年 194卷 110258页

作者： Chen, Weijie McMillan, Alan B. Department of Electrical and Computer Engineering University of Wisconsin-Madison WI53705 United States Department of Radiology University of Wisconsin-Madison WI53705 United States Department of Medical Physics University of Wisconsin-Madison WI53705 United States Department of Biomedical Engineering University of Wisconsin-Madison WI53705 United States

This paper introduces an efficient sub-model ensemble framework aimed at enhancing the interpretability of medical deep learning models, thus increasing their clinical applicability. By generating uncertainty maps, this framework enables end-users to evaluate the reliability of model outputs. We developed a strategy to generate diverse models from a single well-trained checkpoint, facilitating the training of a model family. This involves producing multiple outputs from a single input, fusing them into a final output, and estimating uncertainty based on output disagreements. Implemented using U-Net and UNETR models for segmentation and synthesis tasks, this approach was tested on CT body segmentation and MR-CT synthesis datasets. It achieved a mean Dice coefficient of 0.814 in segmentation and a Mean Absolute Error of 88.17 HU in synthesis, improved from 89.43 HU by pruning. Additionally, the framework was evaluated under image corruption and data undersampling, maintaining correlation between uncertainty and error, which highlights its robustness. These results suggest that the proposed approach not only maintains the performance of well-trained models but also enhances interpretability through effective uncertainty estimation, applicable to both convolutional and transformer models in a range of imaging tasks. © 2025 Elsevier Ltd

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Guided Reinforcement Learning Control for Robotic Lower Limb Prosthesis

Knowledge-Guided Reinforcement Learning Control for Robotic ...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Xiang Gao Jennie Si Yue Wen Minhan Li He Helen Huang Department of Electrical Computer and Energy Engineering Arizona State University Tempe AZ USA Department of Biomedical Engineering North Carolina State University Raleigh NC USA

ISBN: (数字)9781728173955

ISBN: (纸本)9781728173962

Robotic prostheses provide new opportunities to better restore lost functions than passive prostheses for trans-femoral amputees. But controlling a prosthesis device automatically for individual users in different task environments is an unsolved problem. Reinforcement learning (RL) is a naturally promising tool. For prosthesis control with a user in the loop, it is desirable that the controlled prosthesis can adapt to different task environments as quickly and smoothly as possible. However, most RL agents learn or relearn from scratch when the environment changes. To address this issue, we propose the knowledge-guided Q-learning (KG-QL) control method as a principled way for the problem. In this report, we collected and used data from two able-bodied (AB) subjects wearing a RL controlled robotic prosthetic limb walking on level ground. Our ultimate goal is to build an efficient RL controller with reduced time and data requirements and transfer knowledge from AB subjects to amputee subjects. Toward this goal, we demonstrate its feasibility by employing OpenSim, a well-established human locomotion simulator. Our results show the OpenSim simulated amputee subject improved control tuning performance over learning from scratch by utilizing knowledge transfer from AB subjects. Also in this paper, we will explore the possibility of information transfer from AB subjects to help tuning for the amputee subjects.

关键词： Prosthetics Task analysis Impedance Knee Legged locomotion Tuning

来源：评论

学校读者我要写书评

暂无评论

Human Activity Recognition: From Sensors to Applications

Human Activity Recognition: From Sensors to Applications

引用

2020 International Conference on Omni-layer Intelligent Systems (COINS)

作者： Faeghe Fereidoonian Farshad Firouzi Bahar Farahani Biomedical Engineering Amirkabir University of technology Tehran Iran Electrical and Computer Engineering Duke University USA Cyberspace Research Institute Shahid Beheshti University Tehran Iran

ISBN: (数字)9781728163710

ISBN: (纸本)9781728163727

Human activity recognition (HAR) being a dynamic research topic in recent decades due to its high demand in countless applications, for instance, in healthcare, gaming, security and surveillance, and sports. Despite the amount of work contributed by the researcher to this well-researched field, there are still many challenging aspects and open issues that should be addressed in future works. In this paper, the current state-of-the-art in HAR from three holistic aspects is surveyed: sensors, models, and open challenges. First, we summarize the existing sensory systems, including sensor-based, vision-based sensors, and multimodal solutions. Next, the recent advances in HAR algorithms - from hierarchical fusion methods to handcrafted features to deep features, traditional machine learning algorithms to deep learning techniques - are discussed. Finally, the principal issues and challenges that should be addressed in future research are discussed.

关键词： Wearable sensors Accelerometers Cameras Activity recognition Biosensors biomedical monitoring

来源：评论

学校读者我要写书评

暂无评论

Interpretable Factorization for Neural Network ECG Models

arXiv

引用

arXiv 2020年

作者： Snyder, Christopher Vishwanath, Sriram Department of Biomedical Engineering University of Texas at Austin AustinTX United States Department of Electrical and Computer Engineering University of Texas at Austin AustinTX United States

The ability of deep learning (DL) to improve the practice of medicine and its clinical outcomes faces a looming obstacle: model interpretation. Without description of how outputs are generated, a collaborating physician can neither resolve when the model’s conclusions are in conflict with his or her own, nor learn to anticipate model behavior. Current research aims to interpret networks that diagnose ECG recordings, which has great potential impact as recordings become more personalized and widely deployed. A generalizable impact beyond ECGs lies in the ability to provide a rich test-bed for the development of interpretive techniques in medicine. Interpretive techniques for Deep Neural Networks (DNNs), however, tend to be heuristic and observational in nature, lacking the mathematical rigor one might expect in the analysis of math equations. The motivation of this paper is to offer a third option, a scientific approach. We treat the model output itself as a phenomenon to be explained through component parts and equations governing their behavior. We argue that these component parts should also be "black boxes" – additional targets to interpret heuristically with clear functional connection to the original. We show how to rigorously factor a DNN into a hierarchical equation consisting of black box variables. This is not a subdivision into physical parts, like an organism into its cells;it is but one choice of an equation into a collection of abstract functions. Yet, for DNNs trained to identify normal ECG waveforms on PhysioNet 2017 Challenge data, we demonstrate this choice yields interpretable component models identified with visual composite sketches of ECG samples in corresponding input regions. Moreover, the recursion distills this interpretation: additional factorization of component black boxes corresponds to ECG partitions that are more morphologically pure. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Computational Internal Model to Quantify the Effect of Sensorimotor Augmentation on Motor Output

A Computational Internal Model to Quantify the Effect of Sen...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Devon Dollahon Seok Chang Ryu Hangue Park Electrical & Computer Engineering Department Texas A&M University College Station USA Division of Mechanical and Biomedical Engineering Ewha Womans University Seoul South Korea

ISBN: (数字)9781728119908

ISBN: (纸本)9781728119915

The aging process, as well as neurological disorders, causes a decline in sensorimotor functions, which can often bring degraded motor output. As a means of compensation for such sensorimotor deficiencies, sensorimotor augmentation has been actively investigated. Consequently, exoskeleton devices or functional electrical stimulation could augment the muscle activity, while textured surfaces or electrical nerve stimulations could augment the sensory feedback. However, it is not easy to precisely anticipate the effects of specific augmentation because sensory feedback and motor output interact with each other as a closed-loop operation via the central and peripheral nervous systems. A computational internal model can play a crucial role in anticipating such an effect of augmentation therapy on the motor outcome. Still, no existing internal sensorimotor loop model has been represented in a complete computational form facilitating the anticipation. This paper presents such a computational internal model, including numerical values representing the effect of sensorimotor augmentation. With the existing experimental results, the model performance was evaluated indirectly. The change of sensory gain affects motor output inversely, while the change of motor gain did not change or minimally affects the motor *** Relevance- The presented computational internal model will provide a simple and easy tool for clinicians to design therapeutic intervention using sensorimotor augmentation.

关键词： Robot sensing systems Mathematical model Computational modeling Exoskeletons Muscles Numerical models Force

来源：评论

学校读者我要写书评

暂无评论

Identification of multi-temporal snow melting patterns with microwave radars

Identification of multi-temporal snow melting patterns with ...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Marco Pasian Pedro Fidel Espín-López Valentina Premier Claudia Notarnicola Carlo Marin Department of Electrical Computer and Biomedical Engineering University of Pavia Pavia Italy Eurac Research Institute for Earth Observation Bolzano Italy

ISBN: (数字)9788831299008

ISBN: (纸本)9781728137124

The amplitude of the backscattered signal collected by space-born radars, e.g., Sentinel-1, when illuminating snow-covered areas, is strongly dependent upon the conditions of the snow. In particular, there is a potential evidence of a relationship between the melting phases of the snowpack and the amplitude of the backscattered signal. However, the exact quantitative description of this phenomenon it is not fully determined. This paper proposes a first-order preliminary model, based on plane-wave incidence on stratified media, to describe the effect of several physical parameters of the snowpack (depth, liquid water content, density, snow water equivalent) on the amplitude of the backscattered signal. The model is tested against experimental data for a site in the Italian Alps (Malga Fadner), where data from Sentinel-1, as well as in-situ data about the composition of the snowpack, are available for entire winter season 2017/18, showing good general agreement.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Bit Incremental Converters with Optimal Power Consumption and Mismatch Error

Multi-Bit Incremental Converters with Optimal Power Consumpt...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： W. A. Qureshi A. Salimath E. Bonizzoni F. Maloberti Department of Electrical Computer and Biomedical Engineering University of Pavia Pavia - Italy STMicroelectronics Automotive & Discrete Group Cornaredo (MI) - Italy

ISBN: (数字)9781728133201

ISBN: (纸本)9781728133218

Multi-bit architectures of incremental converters are discussed. The use of a hybrid scheme and multi-rate operation reduces the consumed power. Methods for canceling or significantly reducing the error caused by the mismatch between unit capacitors are proposed. Behavioral simulation results prove the effectiveness of the solutions.

关键词： Clocks Capacitors Capacitance Power demand computer architecture Noise shaping Signal resolution

来源：评论

学校读者我要写书评

暂无评论

Staining and rinsing protocol in excised lymph node using paired-agent fluorescence imaging to detect micrometastases

Staining and rinsing protocol in excised lymph node using pa...

引用

Optical Molecular Probes, Imaging and Drug Delivery, OMP 2019

作者： Li, Chengyue Torres, Veronica C. Xu, Xiaochun Brankov, Jovan G. Tichauer, Kenneth M. Biomedical Engineering Illinois Institute of Technology ChicagoIL60616 United States Electrical and Computer Engineering Illinois Institute of Technology ChicagoIL60616 United States

Paired-agent fluorescence imaging could significantly improve the sensitivity of micrometastases detection for breast cancer sentinel lymph node biopsy and suggests that fewer than 1000 cells may be potentially observ... 详细信息

ISBN: (纸本)9781943580545

关键词： Fluorescence imaging

来源：评论

学校读者我要写书评

暂无评论

Decentralised Model Predictive Control with Integral Sliding Mode for Frequency Regulation in Power Grids

Decentralised Model Predictive Control with Integral Sliding...

引用

European Control Conference (ECC)

作者： Gianmario Rinaldi Antonella Ferrara Gianmario Rinaldi is with College of Engineering Mathematics and Physical Sciences University of Exeter Exeter United Kingdom Department of Electrical Computer and Biomedical Engineering University of Pavia Pavia Italy

ISBN: (数字)9783907144022

ISBN: (纸本)9781728188133

This paper proposes a decentralised Integral Sliding Mode (ISM) scheme coupled with a Model Predictive Control (MPC) architecture to control the frequency in power systems partitioned into control areas and characterised by unknown disturbances and unmodelled dynamics. The frequency and the total electrical active power exchanged are both locally measured in each area by Phasor Measurement Units (PMUs). A robust ISM control scheme with chattering alleviation is designed to compensate bounded uncertainties. Thanks to the achieved compensation, it is shown in the paper that a standard MPC control law for linear systems can be used in order to both regulate the frequency deviation and to minimise a quadratic cost function depending also on the cost of the generation. In addition, a method to locally and dynamically reconstruct the unknown disturbances exploiting ISM is designed. Numerical simulations are reported to verify and validate the formulated methodology.

关键词： Frequency control Power system dynamics Power system stability Frequency measurement Phasor measurement units Control systems Uncertainty

来源：评论

学校读者我要写书评

暂无评论

MagicHand: Context-Aware Dexterous Grasping Using an Anthropomorphic Robotic Hand

MagicHand: Context-Aware Dexterous Grasping Using an Anthrop...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Hui Li Jindong Tan Hongsheng He Department of Electrical Engineering and Computer Science Wichita State University Wichita KS USA Department of Mechanical Aerospace and Biomedical Engineering University of Tennessee Knoxville TN USA

ISBN: (数字)9781728173955

ISBN: (纸本)9781728173962

Understanding of characteristics of objects such as fragility, rigidity, texture and dimensions facilitates and innovates robotic grasping. In this paper, we propose a context- aware anthropomorphic robotic hand (MagicHand) grasping system which is able to gather various information about its target object and generate grasping strategies based on the perceived information. In this work, NIR spectra of target objects are perceived to recognize materials on a molecular level and RGB-D images are collected to estimate dimensions of the objects. We selected six most used grasping poses and our system is able to decide the most suitable grasp strategies based on the characteristics of an object. Through multiple experiments, the performance of the MagicHand system is demonstrated.

关键词： Grasping Three-dimensional displays Neurons Cameras Robot vision systems

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：