检索结果-内蒙古大学图书馆

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Abbas, Momin Kar, Koushik Chen, Tianyi Rensselaer Polytechnic Institute Department of Electrical Computer and Systems Engineering TroyNY United States

ISBN: (纸本)9798350351255

Deep neural networks (DNNs) have made significant strides in tackling challenging tasks in wireless systems, especially when an accurate wireless model is not available. However, when available data is limited, traditional DNNs often yield subpar results due to underfitting. At the same time, large language models (LLMs) exemplified by GPT-3, have remarkably showcased their capabilities across a broad range of natural language processing *** whether and how LLMs can benefit challenging non-language tasks in wireless systems is *** this work, we propose to leverage the in-context learning ability (a.k.a. prompting) of LLMs to solve wireless tasks in the low data regime without any training or fine-tuning, unlike DNNs which require training. We further demonstrate that the performance of LLMs varies significantly when employed with different prompt templates. To solve this issue, we employ the latest LLM calibration methods. Our results reveal that using LLMs via ICL methods generally outperforms traditional DNNs on the symbol demodulation task and yields highly confident predictions when coupled with calibration techniques. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Contrastive Self-Supervised Speaker Embedding With Sequential Disentanglement

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2024年 32卷 2704-2715页

作者： Tu, Youzhi Mak, Man-Wai Chien, Jen-Tzung Hong Kong Polytechnic University Department of Electrical and Electronic Engineering Hong Kong SAR999077 Hong Kong National Yang Ming Chiao Tung University Institute of Electrical and Computer Engineering Hsinchu30010 Taiwan

Contrastive self-supervised learning has been widely used in speaker embedding to address the labeling challenge. Contrastive speaker embedding assumes that the contrast between the positive and negative pairs of speech segments is attributed to speaker identity only. However, this assumption is incorrect because speech signals contain not only speaker identity but also linguistic content. In this paper, we propose a contrastive learning framework with sequential disentanglement to remove linguistic content by incorporating a disentangled sequential variational autoencoder (DSVAE) into the conventional contrastive learning framework. The DSVAE aims to disentangle speaker factors from content factors in an embedding space so that the speaker factors become the main contributor to the contrastive loss. Because content factors have been removed from contrastive learning, the resulting speaker embeddings will be content-invariant. The learned embeddings are also robust to language mismatch. It is shown that the proposed method consistently outperforms the conventional contrastive speaker embedding on the VoxCeleb1 and CN-Celeb datasets. This finding suggests that applying sequential disentanglement is beneficial to learning speaker-discriminative embeddings. © 2014 IEEE.

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

T-Scope: Side-channel Leakage Assessment with a Hardware-accelerated Online TVLA Test

T-Scope: Side-channel Leakage Assessment with a Hardware-acc...

引用

Midwest Symposium on Circuits and Systems (MWSCAS)

作者： Hao Wang Andrew Malnicof Patrick Schaumont Department of Electrical and Computer Engineering Worcester Polytechnic Institute Worcester MA USA

ISBN: (数字)9798350387179

ISBN: (纸本)9798350387186

Test vector leakage assessment (TVLA) is a generic and commonly-used approach to assessing a device's side-channel vulnerability based on measuring a large number power traces. However, the current use model of TVLA uses batch processing which separates trace acquisition from statistical analysis, making the method harder to use in online, continuous-monitoring scenarios. We propose T-scope, a TVLA optimized for online testing of real-time targets. We use a pipelined solution to efficiently store power traces in compact histogram structures, and then use FPGA-based hardware acceleration of Welch's t-test to compute the TVLA. By continuously updating the histograms with newly acquired power traces, T-scope visualizes real-time changes in the side-channel leakage characteristics of the target. Our FPGA-based hardware-accelerator, created using high-level synthesis, offers a 99.93X performance gain over a software-based solution. We present a hardware demonstrator of a real-time display of the TVLA assessment of a leaky implementation of the Advanced Encryption Standard.

关键词： Histograms Visualization Power measurement Statistical analysis Performance gain Real-time systems Vectors

来源：评论

学校读者我要写书评

暂无评论

A Miniaturized Transcutaneous Carbon Dioxide Monitor Based on Dual Lifetime Referencing

A Miniaturized Transcutaneous Carbon Dioxide Monitor Based o...

引用

2022 IEEE Biomedical Circuits and Systems Conference, BioCAS 2022

作者： Tufan, Tuna B. Guler, Ulkuhan Worcester Polytechnic Institute Electrical and Computer Engineering WorcesterMA01609 United States

ISBN: (数字)9781665469173

ISBN: (纸本)9781665469173

The ability to monitor blood gases, namely oxy-gen and carbon dioxide, in real-time is of critical importance to clinicians in diagnosing and treating respiratory disorders. Transcutaneous monitors measure the partial pressure of carbon dioxide diffused from the skin. These monitors are noninvasive and capable of continuously monitoring carbon dioxide. Conventional transcutaneous carbon dioxide monitors require a heating element and large calibration equipment for reliable measurements. We propose a miniaturized transcutaneous carbon dioxide monitor based on a luminescence sensing film and dual lifetime referencing technique to assess the partial pressure of carbon dioxide within the 0-75 mmHg range, covering the clinically relevant range for healthy humans, 35-45 mmHg. We measured the partial pressure of carbon dioxide with less than ~1.6% error in the given range without any post-processing and heating. © 2022 IEEE.

关键词： Carbon dioxide

来源：评论

学校读者我要写书评

暂无评论

Graph Coordinates and Conventional Neural Networks - An Alternative for Graph Neural Networks

Graph Coordinates and Conventional Neural Networks - An Alte...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Qin, Zheyi Paffenroth, Randy Jayasumana, Anura P. Colorado State University Electrical and Computer Engineering Fort Collins United States Worcester Polytechnic Institute Department of Data Science Program WorcesterMA United States

ISBN: (纸本)9798350324457

Graph-based data present unique challenges and opportunities for machine learning. Graph Neural Networks (GNNs), and especially those algorithms that capture graph topology through message passing for neighborhood aggregation, have been a leading solution. However, these networks often require substantial computational resources and may not optimally leverage the information contained in the graph's topology, particularly for large-scale or complex *** propose Topology Coordinate Neural Network (TCNN) and Directional Virtual Coordinate Neural Network (DVCNN) as novel and efficient alternatives to message passing GNNs, that directly leverage the graph's topology, sidestepping the computational challenges presented by competing algorithms. Our proposed methods can be viewed as a reprise of classic techniques for graph embedding for neural network feature engineering, but they are novel in that our embedding techniques leverage ideas in Graph Coordinates (GC) that are lacking in current *** results, benchmarked against the Open Graph Benchmark Leaderboard, demonstrate that TCNN and DVCNN achieve competitive or superior performance to message passing GNNs. For similar levels of accuracy and ROC-AUC, TCNN and DVCNN need far fewer trainable parameters than contenders of the OGBN Leaderboard. The proposed TCNN architecture requires fewer parameters than any neural network method currently listed in the OGBN Leaderboard for both OGBN-Proteins and OGBN-Products datasets. Conversely, our methods achieve higher performance for a similar number of trainable parameters. These results hold across diverse datasets and edge features, underscoring the robustness and generalizability of our methods. By providing an efficient and effective alternative to message passing GNNs, our work expands the toolbox of techniques for graph-based machine learning. A significantly lower number of tunable parameters for a given evaluation metric makes TCNN and DVCNN especiall

关键词： graph analytics graph coordinate graph embedding green AI network embedding

来源：评论

学校读者我要写书评

暂无评论

A Wearable Prototype Measuring PtcCO2 and SpO2

A Wearable Prototype Measuring PtcCO2 and SpO2

引用

IEEE Biomedical Circuits and Systems (BIOCAS)

作者： Kleo Golemi Evan Apinis Isil Isiksalan Vladimir Vakhter Ulkuhan Guler Department of Electrical and Computer Engineering Worcester Polytechnic Institute Worcester MA USA

ISBN: (数字)9798350354959

ISBN: (纸本)9798350354966

The proper functioning of the respiratory system is evaluated by monitoring the exchange of blood oxygen and carbon dioxide. While wearable devices for monitoring both blood oxygen and carbon dioxide are emerging, wearable carbon dioxide monitors remain relatively rare. This paper introduces a novel wearable prototype that integrates the measurement of transcutaneous carbon dioxide and peripheral blood oxygen saturation on a miniaturized custom-designed printed circuit board. The device employs a fluorescent sensing film consisting of two distinct luminophore types and utilizes the time-domain dual lifetime referencing technique to enhance measurement accuracy by mitigating the effects of confounding factors. Thorough testing on human subjects validated the prototype’s functionality, comparing its performance against commercial clinical devices. The prototype effectively tracked changes in transcutaneous carbon dioxide induced by hyperventilation, with a resolution as low as 1 mmHg. Additionally, blood oxygen saturation measurements were tested on human subjects to compare our prototypes’ performance to that of clinical devices. The results confirm the potential of the proposed novel wearable for prolonged use with minimal maintenance and underscore its significance in advancing wearable health monitoring technologies.

关键词： Performance evaluation Accuracy Prototypes Carbon dioxide Sensors Biomedical monitoring Wearable devices Time-domain analysis Monitoring Blood

来源：评论

学校读者我要写书评

暂无评论

Invited: Investigation of Motion Artifacts for Luminescence-Based Transcutaneous Oxygen Wearable Device

Invited: Investigation of Motion Artifacts for Luminescence-...

引用

Midwest Symposium on Circuits and Systems (MWSCAS)

作者： Olivia Kendzulak Naisargi Mehta Ryan McSweeney Parisa Saadatmand Hashemi Ulkuhan Guler Department of Electrical and Computer Engineering Worcester Polytechnic Institute Worcester MA USA

ISBN: (数字)9798350387179

ISBN: (纸本)9798350387186

Respiratory diseases are among the top causes of mortality globally, and their effective control frequently relies on accurate monitoring of oxygen levels. The home quarantines during the COVID-19 pandemic have underscored the need for miniaturized respiratory monitoring technologies, especially in remote patient care settings. This paper presents a study on quantifying motion artifacts in a novel, wearable, noninvasive sensor. This sensor is designed to monitor transcutaneous oxygen, a marker correlated with the partial pressure of oxygen in arteries and indicative of pulmonary disease progression. It utilizes a luminescent film whose emission properties inversely correlate with oxygen levels. This study was conducted to assess the impact of motion artifacts on the sensor's accuracy, evaluating its performance under various motion conditions through three tests: dual motion, single motion, and extended motion, involving a flexible prototype with an integrated sensor and accelerometer. The test data, with no post-signal processing, demonstrated min-imal impact on accuracy, with discrepancies not exceeding 0.8%. These findings highlight the wearable oxygen sensor's potential for reliable monitoring in dynamic environments, although future research could focus on solutions to further eliminate the minimal influence of motion artifacts identified in this study.

关键词： COVID-19 Accuracy Pulmonary diseases Prototypes Biomedical monitoring Wearable devices Monitoring

来源：评论

学校读者我要写书评

暂无评论

Optimizing Transcutaneous Carbon Dioxide Measurement Sites on Humans

Optimizing Transcutaneous Carbon Dioxide Measurement Sites o...

引用

IEEE MIT Undergraduate Research Technology Conference (URTC)

作者： Nilgun Duman Alper Y. Ozbey Isil Isiksalan Ulkuhan Guler Department of Electrical and Computer Engineering Worcester Polytechnic Institute Worcester MA USA

ISBN: (数字)9798331531003

ISBN: (纸本)9798331531010

This study explores the body sites for measuring transcutaneous carbon dioxide (CO 2 ) noninvasively using a miniaturized monitor that employs a technique known as timedomain dual lifetime referencing. Accurate measurement of CO 2 levels is crucial for patients with respiratory distress who need monitoring in both clinical and home care settings. We tested this novel monitor by calculating ratio values of luminescence light, indicative of CO 2 levels, at five d ifferent b ody locations: cheek, forearm, forehead, wrist, and fingertip, on f our subjects. We also conducted a repeatability analysis: we tested the sensor on one subject at the fingertip each day for three consecutive days. Our findings show that while all t ested s ites presented reliable data, the forehead and cheek yielded faster settling times, and the forearm, forehead, and wrist produced less variation in readings. The results highlight the significance of c hoosing e ffective sites for accurate transcutaneous CO 2 monitoring.

关键词： Wrist Forehead Accuracy Carbon dioxide Luminescence Sensors Reliability Biomedical monitoring Wearable devices Monitoring

来源：评论

学校读者我要写书评

暂无评论

Parasitic Circus: On the Feasibility of Golden-Free PCB Verification

Parasitic Circus: On the Feasibility of Golden-Free PCB Veri...

引用

International Symposium on Physical & Failure Analysis of Integrated Circuits

作者： Maryam Saadat Safa Patrick Schaumont Shahin Tajik Department of Electrical and Computer Engineering Worcester Polytechnic Institute Worcester MA USA

ISBN: (数字)9798350360608

ISBN: (纸本)9798350360615

Printed circuit boards (PCBs) are an integral part of electronic systems. Hence, verifying their physical integrity in the presence of supply chain attacks (e.g., tampering and counterfeiting) is of utmost importance. Recently, tamper detection techniques grounded in impedance characterization of PCB's Power Delivery Network (PDN) have gained prominence due to their global detection coverage, non-invasive, and low-cost nature. Similar to other physical verification methods, these techniques rely on the existence of a physical golden sample for signature comparisons. However, having access to a physical golden sample for golden signature extraction is not feasible in many real-world scenarios. In this work, we assess the feasibility of eliminating a physical golden sample and replacing it with a simulated golden signature obtained by the PCB design files. By performing extensive simulation and measurements on an in-house designed PCB, we demonstrate how the parasitic impedance of the PCB components plays a major role in reaching a successful verification. Based on the obtained results and using statistical metrics, we show that we can mitigate the discrepancy between collected signatures from simulation and measurements.

关键词： Measurement Integrated circuits Machine learning algorithms Impedance measurement Printed circuits Supply chains Impedance

来源：评论

学校读者我要写书评

暂无评论

Enhanced Vehicle Detection by Optimized Image Compression in NextG Wireless Network Autonomous Vehicles System 100

Enhanced Vehicle Detection by Optimized Image Compression in...

引用

100th IEEE Vehicular Technology Conference, VTC 2024-Fall

作者： Monir, Md Fahad Hossain, Md Junayed Barkatullah, Mohammad Hoque, Md Mozammal Hassan, Zoheb Ahmed, Tarem Virginia Polytechnic Institute and State University Department of Electrical and Computer Engineering United States Department of Computer Science & Engineering Bangladesh University of Houston Department of Engineering Technology United States Université Laval Department of Electrical and Computer Engineering Canada

ISBN: (纸本)9798331517786

Autonomous Vehicle System (AVS) is rapidly advancing and is expected to completely transform the transportation industry, bringing about a new era of mobility. As digital data proliferation strains network resources, the demand for performing resource-intensive edge-assisted Deep Learning tasks in AVS with limited computational resources becomes increasingly challenging. The advent of 5G and future cellular networks (NextG) offers the promise of facilitating the seamless execution of these tasks. This research aims to diminish dataset size, in harmony with the integration capabilities of the Semantic and Flexible Open Radio Access Network (SEMO-RAN) framework, which is anticipated to reduce latency and refine resource allocation in vehicle image processing. The focus of this study is on optimizing image compression without compromising the accuracy of vehicle classification, leveraging esteemed Convolutional Neural Network models like YOLOv5. By employing Generative Adversarial Network compression and Wavelet Image Compression methods, our study achieves an impressive 81.82% reduction in data size while maintaining a 96.97% accuracy in classification tasks. This underscores the potential for significant efficiency gains in AVS through improved data management, supported by Digital Twins (DT), Integrated Sensing and Communication (ISAC), and O-RAN. © 2024 IEEE.

关键词： Radio access networks

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：