检索结果-内蒙古大学图书馆

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Hao Yang Haoying Zhou Gregory S. Fischer Jie Ying Wu Department of Computer Science Vanderbilt University TN USA Department of Robotics Engineering Worcester Polytechnic Institute MA USA

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Haptic feedback to the surgeon during robotic surgery would enable safer and more immersive surgeries but estimating tissue interaction forces at the tips of robotically controlled surgical instruments has proven challenging. Few existing surgical robots can measure interaction forces directly and the additional sensor may limit the life of instruments. We present a hybrid model and learning-based framework for force estimation for the Patient Side Manipulators (PSM) of a da Vinci Research Kit (dVRK). The model-based component identifies the dynamic parameters of the robot and estimates free-space joint torque, while the learning-based component compensates for environmental factors, such as the additional torque caused by trocar interaction between the PSM instrument and the patient’s body wall. We evaluate our method in an abdominal phantom and achieve an error in force estimation of under 10% normalized root-mean-squared error. We show that by using a model-based method to perform dynamics identification, we reduce reliance on the training data covering the entire workspace. Although originally developed for the dVRK, the proposed method is a generalizable framework for other compliant surgical robots. The code is available at https://***/vu-maple-lab/dvrk_force_estimation.

关键词： Learning systems Torque Medical robotics Instruments Force Dynamics Estimation Surgery Robot sensing systems Trajectory optimization

来源：评论

学校读者我要写书评

暂无评论

On Neural Collapse in Contrastive Learning with Imbalanced Datasets

On Neural Collapse in Contrastive Learning with Imbalanced D...

引用

IEEE Workshop on Machine Learning for Signal Processing

作者： Thuan Nguyen Ruijie Jiang Shuchin Aeron Prakash Ishwar D. Richard Brown Department of Engineering Engineering Technology and Surveying East Tennessee State University Department of Electrical and Computer Engineering Tufts University Medford Department of Electrical and Computer Engineering Boston University Boston MA Department of Electrical and Computer Engineering Worcester Polytechnic Institute Worcester MA

ISBN: (数字)9798350372250

ISBN: (纸本)9798350372267

Neural collapse is a phenomenon in neural networks where all the samples from the same class collapse to their class mean and the class means have a specific geometric structure called Equiangular Tight Frame (ETF). Recent studies have empirically and theoretically confirmed that neural collapse solutions attain a global minimum of Contrastive Learning (CL) losses if the class distribution is uniform (balanced classes). This paper investigates the neural collapse phenomenon in Contrastive Learning for imbalanced datasets. We show that even if the classes are imbalanced, global minima of Contrastive Learning losses include solutions in which all samples from the same class collapse to their class mean. However, the geometric structure of the class means is, in general, different from an ETF. In addition, we show that under certain conditions the optimal geometry of the class means can be found by solving a convex optimization problem. We provide a program based on the CVX package to find these optimal class means.

关键词： Geometry Conferences Neural networks Contrastive learning Machine learning Signal processing Convex functions

来源：评论

学校读者我要写书评

暂无评论

Ishikawa, JESS, and Visual Analytics for engineering

Ishikawa, JESS, and Visual Analytics for Engineering

引用

2022 IEEE International Conference on Big Data, Big Data 2022

作者： Varde, Aparna S. Liang, Jianyu Yang, Zhaotong Sisson, Richard D. Montclair State University Department of Computer Science NJ United States Worcester Polytechnic Institute Mechanical and Materials Engineering MA United States

ISBN: (纸本)9781665480451

Domain-specific big data poses issues in knowledge discovery and decision support given its many Vs such as volume, variety, and visualization. In this work, we propose solutions via Ishikawa diagrams, JESS (Java Expert System Shell) with rule discovery, as well as visual analytics. We deploy data science and domain models, targeting engineering and scientific domains. Our results yield high accuracy, efficiency and cost-effectiveness. © 2022 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

ImpedanceVerif: On-Chip Impedance Sensing for System-Level Tampering Detection

IACR Transactions on Cryptographic Hardware and Embedded Sys...

引用

IACR Transactions on Cryptographic Hardware and Embedded Systems 2022年第1期2023卷 301-325页

作者： Mosavirik, Tahoura Schaumont, Patrick Tajik, Shahin Department of Electrical and Computer Engineering Worcester polytechnic Institute WorcesterMA United States

Physical attacks can compromise the security of cryptographic devices. Depending on the attack’s requirements, adversaries might need to (i) place probes in the proximity of the integrated circuits (ICs) package, (ii) create physical connections between their probes/wires and the system’s PCB, or (iii) physically tamper with the PCB’s components, chip’s package, or substitute the entire PCB to prepare the device for the attack. While tamper-proof enclosures prevent and detect physical access to the system, their high manufacturing cost and incompatibility with legacy systems make them unattractive for many low-cost scenarios. In this paper, inspired by methods known from the field of power integrity analysis, we demonstrate how the impedance characterization of the system’s power distribution network (PDN) using on-chip circuit-based network analyzers can detect various classes of tamper events. We explain how these embedded network analyzers, without any modifications to the system, can be deployed on FPGAs to extract the frequency response of the PDN. The analysis of these frequency responses reveals different classes of tamper events from board to chip level. To validate our claims, we run an embedded network analyzer on FPGAs of a family of commercial development kits and perform extensive measurements for various classes of PCB and IC package tampering required for conducting different side-channel or fault attacks. Using the Wasserstein Distance as a statistical metric, we further show that we can confidently detect tamper events. Our results, interestingly, show that even environment-level tampering activities, such as the proximity of contactless EM probes to the IC package or slightly polished IC package, can be detected using on-chip impedance sensing. © 2022, Ruhr-University of Bochum. All rights reserved.

关键词： Probes

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study of Domain Adaptation: Are We Really Learning Transferable Representations?

An Empirical Study of Domain Adaptation: Are We Really Learn...

引用

IEEE International Conference on Big Data

作者： Nicholas Josselyn Biao Yin Ziming Zhang Elke Rundensteiner Department of Data Science Worcester Polytechnic Institute Worcester MA Department of Electrical and Computer Engineering Worcester Polytechnic Institute Worcester MA Department of Computer Science Worcester Polytechnic Institute Worcester MA

ISBN: (纸本)9781665480468

Deep learning often relies on the availability of a large amount of high-quality labeled data, which can be very limited in novel domains. To address such data scarcity, domain adaptation is one promising approach that allows for deep networks to leverage large amounts of available data from a source domain to enhance the model’s efficacy on the target domain of interest. However, while there is a plethora of alternate models for domain adaptation proposed over many years in the literature, there is a dearth of studies that objectively compare the relative effectiveness of these models in a rigorous, empirical study. To fill this gap, we provide a thorough, unbiased, empirical study of five state-of-the-art (SOTA) deep domain adaptation models proposed over the past 6 years whose codes are publicly available. Models are evaluated on the complex and diverse domain adaptation tasks featured in the DomainNet benchmark dataset as well as the popular Office-31 dataset. Our results suggest that (1) all 5 models perform similarly, on average, and do not even significantly beat the oldest model, and (2) counter to their intended purpose, the transfer loss functions in the literature do not contribute significantly to learning transferable representations. Our observations suggest that domain adaptation research needs to more thoroughly compare newly proposed models against existing works, along with assessing their loss functions’ utility thoroughly. Our code and data splits are made public for reproducibility of results by the community.

关键词： Deep learning Adaptation models Codes Big Data Benchmark testing Reproducibility of results Data models

来源：评论

学校读者我要写书评

暂无评论

Latent Dynamical Model to Characterize Brain Network-Level Rhythmic Dynamics

Latent Dynamical Model to Characterize Brain Network-Level R...

引用

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

作者： Reza Saadati Fard Navid Ziaei Ali Yousefi Department of Computer Science Worcester Polytechnic Institute Worcester MA USA Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan Iran

Characterizing network-level rhythmic dynamics over multiple spatio-temporal scales can significantly advance our understanding of brain cognitive function and information processing. In this research, we propose a new switching state space model called latent dynamical coherence model or briefly LDCM. In the LDCM, we develop model inference and parameter estimation solutions that facilitate studying network-level rhythmic dynamics at scales. In the proposed framework, we incorporate both continuous and discrete state processes, helping us to capture dynamics of functional connectivity at various rates, such as slow, rapid, or a combination of both. We then demonstrate an application of our model in characterizing circuit dynamics of the anesthetic state in a sample data set, recorded from a patient under anesthesia using 64-channel EEG over the course of two hours.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On Rejecting Low Quality Images to Improve Deep Smartphone Wound Assessment

On Rejecting Low Quality Images to Improve Deep Smartphone W...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Apiwat Ditthapron Emmanuel O. Agu Peder Pedersen Clifford Lindsay Bengisu Tulu Diane Strong Computer Science Dept. Worcester Polytechnic Institute (WPI) Worcester MA Electrical and Computer Engineering Dept. Worcester Polytechnic Institute (WPI) Worcester MA Department of Radiology Univ. Massachusetts Medical School Worcester MA Foisie Business School Worcester Polytechnic Institute (WPI) Worcester MA

Automatic assessment of wounds using smartphones can facilitate the tracking of healing progress outside the clinic. Prior work proposed SS-PMG-EfficientNets, a state-of-the-art, multi-scale, convolutional neural network architecture for accurate wound assessment. However, the model was previously only trained and evaluated on high-quality wound images captured in controlled environments. This study systematically evaluated the effects of low-quality images on SS-PMG-EfficientNets, finding that the model's performance and consistency are reduced when input wound images are blurry or captured in adverse lighting (too bright or too dark), two factors previously identified as the most prevalent issues in crowdsourced images. Specifically, SS-PMG-EfficientNet was first trained on three high-quality wound datasets containing images labeled with Photographic Wound Assessment Tool (PWAT) wound healing scores, stages of pressure injury wounds, and wound types, respectively. The model was then evaluated on a test wound dataset that was augmented with real-world image luminance, blur, and image compression effects and found that wound assessment accuracy decreased by up to 27%. To improve model performance, we propose a method for instant image quality assessment on the smartphone, enabling low-quality wound images to be rejected immediately after image capture so that the nurse or patient can be prompted to recapture the image. Our evaluation of the proposed image quality assessment and rejection method showed that it increases average accuracy from 73 % to 87%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Language Anchor-Guided Method for Robust Noisy Domain Generalization

arXiv

引用

arXiv 2025年

作者： Dai, Zilin Wang, Lehong Lin, Fangzhou Wang, Yidong Li, Zhigang Yamada, Kazunori D. Zhang, Ziming Lu, Wang Department of Computer Science Worcester Polytechnic Institute WorcesterMA01609 United States Department of Electrical Engineering Worcester Polytechnic Institute WorcesterMA01609 United States Department of Robotics Engineering Worcester Polytechnic Institute WorcesterMA01609 United States Carnegie Mellon University PittsburghPA15213 United States Tohoku University Sendai980-8572 Japan Tsinghua University Beijing100190 China Peking University Beijing100871 China

Real-world machine learning applications are often hindered by two critical challenges: distribution shift and label noise. Networks inherently tend to overfit to redundant, uninformative features present in the training distribution, which undermines their ability to generalize effectively to the target domain’s distribution. The presence of noisy data further exacerbates this issue by inducing additional overfitting to noise, causing existing domain generalization methods to fail in effectively distinguishing invariant features from spurious ones. To address these challenges, we propose Anchor Alignment and Adaptive Weighting (A3W), a novel algorithm based on sample reweighting guided by natural language processing (NLP) anchors that seeks to extract representative features. In particular, A3W leverages semantic representations derived from natural language models to serve as a source of domain-invariant prior knowledge. We also introduce a weighted loss function that dynamically adjusts the contribution of each sample based on its distance to the corresponding NLP anchor, thereby improving the model’s resilience to noisy labels. Extensive experiments on benchmark datasets demonstrate that A3W outperforms state-of-the-art domain generalization methods, yielding significant improvements in both accuracy and robustness across various datasets and noise levels. © 2025, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Physics of Graphene Dirac Plasmons and their Terahertz Device Applications

Physics of Graphene Dirac Plasmons and their Terahertz Devic...

引用

International Conference on Applied Electromagnetics and Communications (ICECom)

作者： Taiichi Otsuji Akira Satou Victor Ryzhii Maxim Ryzhii Vladimir Mitin Michael S. Shur Research Institute of Electrical Communication Tohoku University Sendai Japan Department of Computer Science and Engineering University of Aizu Aizuwakamatsu Japan Department of Electrial and Electronic Engineering University at Buffalo SUNY Buffalo NY USA Department of Electrial Computer and Electronic Engineering Rensellaer Polytechnic Institute Troy NY USA

This paper revies recent advances in the research of graphene Dirac plasmons (GDPs) for THz device applications particularly focusing on THz laser transistors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Gradient Boosting Decision Trees on Medical Diagnosis over Tabular Data

arXiv

引用

arXiv 2024年

作者： Yıldız, A. Yarkın Kalayci, Asli Department of Electrical and Computer Engineering Northeastern University BostonMA United States School of Business Worcester Polytechnic Institute WorcesterMA United States

Medical diagnosis is a crucial task in the medical field, in terms of providing accurate classification and respective treatments. Having near-precise decisions based on correct diagnosis can affect a patient’s life itself, and may extremely result in a catastrophe if not classified correctly. Several traditional machine learning (ML), such as support vector machines (SVMs) and logistic regression, and state-of-the-art tabular deep learning (DL) methods, including TabNet and TabTransformer, have been proposed and used over tabular medical datasets. Additionally, due to the superior performances, lower computational costs, and easier optimization over different tasks, ensemble methods have been used in the field more recently. They offer a powerful alternative in terms of providing successful medical decision-making processes in several diagnosis tasks. In this study, we investigated the benefits of ensemble methods, especially the Gradient Boosting Decision Tree (GBDT) algorithms in medical classification tasks over tabular data, focusing on XGBoost, CatBoost, and LightGBM. The experiments demonstrate that GBDT methods outperform traditional ML and deep neural network architectures and have the highest average rank over several benchmark tabular medical diagnosis datasets. Furthermore, they require much less computational power compared to DL models, creating the optimal methodology in terms of high performance and lower complexity. Copyright © 2024, The Authors. All rights reserved.

关键词：

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：