检索结果-内蒙古大学图书馆

2023 IEEE Biomedical Circuits and Systems Conference, BioCAS 2023

作者： Isiksalan, Isil Worcester Polytechnic Institute Dept. of Electrical and Computer Engineering Worcester United States

ISBN: (纸本)9798350300260

In this paper, we present MedicaLog, a novel health data platform designed to tackle key challenges in contemporary healthcare. A significant global deficiency in shared health data repositories has impeded efficient health management, leaving nearly 3.5 billion individuals without basic health services. [1] MedicaLog employs exponential technologies like wearable electronics and IoT to continuously gather and process diverse health *** detail the primary challenges in the existing healthcare domain, underscoring the need for a tailored, proactive healthcare strategy. Our market analysis delves into the prospects and obstacles of this pioneering solution. The financial blueprint underscores MedicaLog's feasibility and its vast potential for *** main focus explores MedicaLog's evolution, embracing solution design and prototype creation. Our iterative innovation approach ensures a compelling user experience. The journey provides insights, emphasizing user engagement and AI-driven digital twin *** conclusion, MedicaLog proposes a groundbreaking, integrated, and patient-oriented healthcare paradigm. This paper outlines MedicaLog's development and its prospective role in reshaping global health. © 2023 IEEE.

关键词： exponential technologies healthcare innovation design

来源：评论

学校读者我要写书评

暂无评论

PFAS Incineration: Known Unknowns, Reaction Simulation, and ML to Predict Product Properties

PFAS Incineration: Known Unknowns, Reaction Simulation, and ...

引用

2023 IEEE MIT Undergraduate Research Technology Conference, URTC 2023

作者： Soiffer, Duncan Pyorre, Tuomas Kenney, David Teixeira, Andrew Worcester Polytechnic Institute Department of Computer Science and Mathematical Sciences WorcesterMA United States Worcester Polytechnic Institute Department of Robotics Engineering WorcesterMA United States Worcester Polytechnic Institute Department of Chemical Engineering WorcesterMA United States

ISBN: (纸本)9798350308600

Per- and polyfluoroalkyl substances (PFAS) are a group of chemicals used for their impressive stability, a property which has also led them to be found polluting virtually every sector of the environment-including our own bodies. Presently, our ability to destroy PFAS is limited largely to incineration, whose products and side effects are poorly understood. Research on PFAS incineration is constrained by high experimental costs and difficulty in accurately measuring reaction products. This presents an opportunity for computer simulation and machine learning to provide valuable assistance. In this study, three kinds of thermal PFAS decomposition are simulated. Further, to broaden physical understanding of PFAS incineration products, a recent in-house machine learning model for predicting the octanol-water partition coefficient (LogP) of chemicals is improved and applied to simulation results. A decrease in LogP is observed in all treatments, with the most dramatic effect (-2 average LogP) observed in oxidative pyrolysis. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

On Contrastive Learning for Domain Generalization 23

On Contrastive Learning for Domain Generalization

引用

23rd IEEE International Conference on Machine Learning and Applications, ICMLA 2024

作者： Nguyen, Thuan Brown, D. Richard East Tennessee State University Department of Engineering Engineering Technology and Surveying TN United States Worcester Polytechnic Institute Department of Electrical and-Computer Engineering WorcesterMA United States

ISBN: (纸本)9798350374889

Given the training data and labels from several seen domains, Domain Generalization (DG) aims to learn models that generalize well on unlabeled data from unseen domains. Due to the distribution of data and/or labels may vary between domains, current DG methods are mainly based on the theme of domain-invariant representation learning which decomposes the learning process into two steps: (1) finding a representation function from the input space to the representation/feature space to learn the so-called domain-invariant features, i.e., the features that are statistically stable between domains, and (2) designing a classifier on top of these domain-invariant features which is mutually optimal for all domains. Recent works on DG show that Contrastive Learning (CL) which was originally proposed to learn a representation function such that similar samples are pulled closer while dissimilar samples are pushed far away in the representation/feature space, appears as a promising solution for domain-invariant features learning. In this paper, we first establish the fundamental theory to justify why CL might be a potential approach for DG by showing that CL, under particular settings, allows a mechanism to minimize a loss function that enforces an optimal classifier for all training domains. Based on these foundations, we revisit the recent works that apply CL for DG to indicate their limitations and suggest a modification by combining the CL method with current DG methods for better out-of-domain generalization. Our numerical results point out that our proposed algorithm can achieve state-of-the-art performance on multiple DG benchmark datasets. © 2024 IEEE.

关键词： Contrastive Learning

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

引用

Neural Computing and Applications 2025年第3期37卷 1209-1221页

作者： Li, Kaidong Zhang, Tianxiao Zhong, Cuncong 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/***. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

IC Backside Tamper Detection using Impedance Sensing

引用

IEEE Access 2025年 13卷 90706-90725页

作者： Mosavirik, Tahoura Tajik, Shahin Worcester Polytechnic Institute Electrical and Computer Engineering Department WorcesterMA01609 United States

The expansion of flip-chip technologies and lack of backside protection made integrated circuits (ICs) vulnerable to certain classes of physical attacks mounted from the IC’s backside, including laser-assisted probing, electromagnetic side-channel analysis, body biasing injection (BBI), and focused ion beam (FIB) editing. Existing countermeasures are expensive, incompatible with standard IC fabrication, and unsuitable for legacy systems such as field-programmable gate arrays (FPGAs), which are widely used in industrial and defense systems. In this paper, we demonstrate how impedance monitoring of the printed circuit board (PCB) and the IC package’s power distribution network (PDN) using on-chip circuit-based network analyzers can detect IC backside tampering. Our method is based on the fact that any attempt to expose the backside silicon substrate, such as the removal of the fan and heatsinks, or polishing it, leads to changes in the equivalent impedance of the package’s PDN, and hence scanning the package impedance will reveal if the package integrity has been violated. To validate our claims, we deployed an on-FPGA network analyzer on an AMD Zynq UltraScale+ MPSoC (16 nm), which is part of a multi-PCB *** performed a series of backside tamper attacks, including the removal of cooling components and IC backside silicon milling/polishing, across different temperatures, and evaluated detection effectiveness leveraging the difference of means as the statistical metric. © 2013 IEEE.

关键词： Focused ion beams

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

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

Optimizing Magnetic Induction Sensors for Non-Obtrusive Vital Signs Monitoring: Impact of Current Control on Operational Quality 46

Optimizing Magnetic Induction Sensors for Non-Obtrusive Vita...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Momeni, Mahdi Radomski, Adrian Guler, Ulkuhan Teichmann, Daniel University of Southern Denmark Sdu Health Informatics and Technology The Maersk Mc-Kinney Moller Institute Denmark Worcester Polytechnic Institute Department of Electrical and Computer Engineering WorcesterMA United States

ISBN: (纸本)9798350371499

This paper investigates the advancement of magnetic induction-based heart and respiration rate sensing by actively controlling the coil current. This is realized through the implementation of a current-starved inverter mechanism. Experiments show a notable level of accuracy of the proposed circuit in measuring heart and respiration activity when compared to a reference sensor. The direct manipulation of current levels was found to have a direct impact on the signal strength. Incrementing the overall current within the proposed circuit from 60 mA to 100 mA resulted in an augmentation of the output amplitude of the heart rate signal from 8.5 mV to 27 mV, accompanied by a marginal enhancement in beat-to-beat interval accuracy. Moreover, the proposed sensor demonstrates noteworthy precision in monitoring the respiratory rate when compared with the reference sensor under different current values, exhibiting the same trend in signal strength. This finding offers valuable insight for the development of future power-optimized magnetic induction sensors with enhanced robustness. © 2024 IEEE.

关键词： Contact sensors

来源：评论

学校读者我要写书评

暂无评论

FairCIM: Fair Interference Mitigation by DNN Switching for Latency-Sensitive Inference Jobs

FairCIM: Fair Interference Mitigation by DNN Switching for L...

引用

2024 IEEE International Conference on Autonomic Computing and Self-Organizing Systems, ACSOS 2024

作者： Nabavinejad, Seyed Morteza Reda, Sherief Guo, Tian Worcester Polytechnic Institute Computer Science Department WorcesterMA United States Brown University School of Engineering ProvidenceRI United States

ISBN: (纸本)9798350363876

It is a common practice to co-locate several jobs, such as DNN inference ones, on a single machine to improve resource utilization, energy efficiency, and overall performance. However, individual job performance might degrade when these jobs compete for shared resources. This degradation can in particular affect latency-sensitive jobs bound by Service Level Agreements (SLA), and result in SLA violations. To tackle this issue and mitigate the impact of interference on latency, we design a system called FairCIM. For certain applications such as image classification, various DNNs with varying accuracy and computational complexity are proposed. Upon detection of SLA violations, FairCIM dynamically switches between those DNNs to maintain the latency in the presence of co-location interference. To ensure fairness, FairCIM selects the jobs for DNN switching based on their resource utilization. We conduct experiments using diverse DNNs, datasets, and hardware platforms to evaluate the FairCIM effectiveness. Compared to another approach that uses a resource exchange mechanism, FairCIM's flexibility achieved by DNN switching substantially reduces SLA violations and improves the effective accuracy by up to 244%. © 2024 IEEE.

关键词： Energy efficiency

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

2022 IEEE International Conference on Big Data, Big Data 2022

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

ISBN: (纸本)9781665480451

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. © 2022 IEEE.

关键词： Deep 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：