检索结果-内蒙古大学图书馆

11th IEEE International Conference on Healthcare Informatics, ICHI 2023

作者： Guo, Jiaqi Aqeel, Marah M. Lin, Luotao Gelfand, Saul B. Eicher-Miller, Heather A. Bhadra, Anindya Hennessy, Erin Richards, Elizabeth A. Delp, Edward J. Purdue University School of Electrical and Computer Engineering West LafayetteIN United States Purdue University Department of Nutrition Science West LafayetteIN United States Purdue University Department of Statistics West LafayetteIN United States Tufts University Friedman School of Nutrition Science and Policy BostonMA United States Purdue University School of Nursing West LafayetteIN United States

ISBN: (纸本)9798350302639

Physical activity (PA) is known to be a risk factor for obesity and chronic diseases such as diabetes and metabolic syndrome. Few attempts have been made to pattern the time of physical activity while incorporating intensity and duration in order to determine the relationship of this multi-faceted behavior with health. In this paper, we explore a distance-based approach to cluster the daily physical activity time series from the National Health and Nutrition Examination Survey 2003-2006 (NHANES). The clusters are used to find temporal physical activity patterns among US adults. A number of distance measures and distance-based clustering methods are investigated and compared using various metrics. These metrics include the Silhouette and the Dunn Index (internal criteria), and the associations of the clusters with health status indicators (external criteria). Our experiments indicate that using a distance-based cluster analysis approach to estimate temporal physical activity patterns through the day, has the potential to describe the complexity of behavior rather than characterizing physical activity patterns solely by sums or labels of maximum activity levels. © 2023 IEEE.

关键词： Nutrition

来源：评论

学校读者我要写书评

暂无评论

GSLB: The Graph Structure Learning Benchmark 37

GSLB: The Graph Structure Learning Benchmark

引用

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Li, Zhixun Wang, Liang Sun, Xin Luo, Yifan Zhu, Yanqiao Chen, Dingshuo Luo, Yingtao Zhou, Xiangxin Liu, Qiang Wu, Shu Yu, Jeffrey Xu Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Department of Automation University of Science and Technology of China China School of Cyberspace Security Beijing University of Posts and Telecommunications China Department of Computer Science University of California Los Angeles United States Heinz College of Information Systems and Public Policy Machine Learning Department School of Computer Science Carnegie Mellon University United States

ISBN: (纸本)9781713899921

Graph Structure Learning (GSL) has recently garnered considerable attention due to its ability to optimize both the parameters of Graph Neural Networks (GNNs) and the computation graph structure simultaneously. Despite the proliferation of GSL methods developed in recent years, there is no standard experimental setting or fair comparison for performance evaluation, which creates a great obstacle to understanding the progress in this field. To fill this gap, we systematically analyze the performance of GSL in different scenarios and develop a comprehensive Graph Structure Learning Benchmark (GSLB) curated from 20 diverse graph datasets and 16 distinct GSL algorithms. Specifically, GSLB systematically investigates the characteristics of GSL in terms of three dimensions: effectiveness, robustness, and complexity. We comprehensively evaluate state-of-the-art GSL algorithms in node- and graph-level tasks, and analyze their performance in robust learning and model complexity. Further, to facilitate reproducible research, we have developed an easy-to-use library for training, evaluating, and visualizing different GSL methods. Empirical results of our extensive experiments demonstrate the ability of GSL and reveal its potential benefits on various downstream tasks, offering insights and opportunities for future research. The code of GSLB is available at: https://***/GSL-Benchmark/GSLB. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Object Detection for Vehicles with Yolo

Object Detection for Vehicles with Yolo

引用

International Symposium on Applied Machine Intelligence and Informatics (SAMI)

作者： Pouria Maleki Abbas Ramazani Hassan Khotanlou Sina Ojaghi Milad Mousavi Alexey Kalinin Amir Mosavi Department of Electrical Engineering Bu-Ali Sina University Hamedan Iran Department of Computer Engineering Bu-Ali Sina University Hamedan Iran School of Computer and Electrical Engineering University of Tehran Tehran Iran K. N. Toosi University of Technology Tehran Iran Abylkas Saginov Karaganda Technical University Kazakistan John von Neumann Faculty of Informatics Obuda University Budapest Hungary Ludovika University of Public Service Budapest Hungary

The rapid urban population growth has intensified the challenges associated with urban and suburban traffic, necessitating effective traffic control and management. The efficient movement of emergency vehicles, particularly ambulances and fire trucks, has emerged as a critical concern. This article presents the Vehicle Dataset, a comprehensive benchmark for object detection, encompassing seven vehicle classes, including cars, motorcycles, buses, trucks, vans, ambulances, and fire trucks. The dataset, includes 29,759 meticulously labeled images obtained from freely available online sources, enables the identification of traffic patterns through deep neural networks. Notably, the dataset emphasizes the facilitation of emergency vehicle movement. The Vehicle Dataset in this study is divided into three subsets, with 25,369 images assigned for training, 2,896 for validation, and 1,494 for testing. Through the utilization of the dataset, object detection algorithms based on YOLO versions 5, 6, and 7 have been trained. Remarkably, YOLO version 7 has yielded outstanding results, achieving a final precision of 85% and a mAP of 85% at an IoU threshold of 0.5. Moreover, at IoU thresholds ranging from 0.5 to 0.9, a mAP of 64% has been attained. The Vehicle Dataset represents significant resource for researchers and practitioners in the transportation and traffic management field. Its inclusion of emergency vehicles such as ambulances and fire trucks contribute to its unique value. This article presents a detailed exploration of the dataset, underscoring its significance in advancing object detection methodologies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

As an AI Language Model, "Yes I Would Recommend Calling the Police": Norm Inconsistency in LLM Decision-Making

arXiv

引用

arXiv 2024年

作者： Jain, Shomik Calacci, D. Wilson, Ashia Institute for Data Systems and Society Massachusetts Institute of Technology United States Center for Information Technology Policy Princeton University United States Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology United States

We investigate the phenomenon of norm inconsistency: where LLMs apply different norms in similar situations. Specifically, we focus on the high-risk application of deciding whether to call the police in Amazon Ring home surveillance videos. We evaluate the decisions of three state-of-the-art LLMs – GPT-4, Gemini 1.0, and Claude 3 Sonnet – in relation to the activities portrayed in the videos, the subjects’ skin-tone and gender, and the characteristics of the neighborhoods where the videos were recorded. Our analysis reveals significant norm inconsistencies: (1) a discordance between the recommendation to call the police and the actual presence of criminal activity, and (2) biases influenced by the racial demographics of the neighborhoods. These results highlight the arbitrariness of model decisions in the surveillance context and the limitations of current bias detection and mitigation strategies in normative decision-making. © 2024, CC BY.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Deterministic-Based 5G mmWave Propagation Characterization in Urban Environments

Deterministic-Based 5G mmWave Propagation Characterization i...

引用

2021 IEEE International Symposium on Antennas and Propagation and North American Radio Science Meeting, APS/URSI 2021

作者： Azpilicueta, L. Rodriguez-Corbo, F.A. Celaya-Echarri, M. Lopez-Iturri, P. Michelson, David G. Falcone, F. School of Engineering and Sciences Tecnologico de Monterrey Monterrey Mexico Public University of Navarre Electric Electronic and Communication Engineering Dept. Pamplona Spain Institute of Smart Cities Public University of Navarre Pamplona Spain Department of Electrical and Computer Engineering University of British Columbia Vancouver Canada

ISBN: (纸本)9781728146706

The new requirements of context aware environments within the framework of Smart Cities and Smart Regions come with the implementation of the Fifth-Generation (5G) wireless technology and the use of millimeter-wave (mmWave) frequency bands. However, signal propagation at these frequency bands also comes with different channel impairments that needs to be completely understood before the design and implementation of a wireless communication system. Therefore, in this work, the spatial and temporal channel characteristics of a typical urban environment have been identified for wireless networks in 30 and 70 GHz frequency bands by means of an in-house deterministic approach. © 2021 IEEE.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

The motivated can encrypt (Even with PGP)

arXiv

引用

arXiv 2021年

作者： Borradaile, Glencora Kretschmer, Kelsy Gretes, Michele LeClerc, Alexandria School of Electrical Engineering and Computer Science School of Public Policy Oregon State University

Existing end-to-end-encrypted (E2EE) email systems, mainly PGP, have long been evaluated in controlled lab settings. While these studies have exposed usability obstacles for the average user and offer design improvements, there exist users with an immediate need for private communication, who must cope with existing software and its limitations. We seek to understand whether individuals motivated by concrete privacy threats, such as those vulnerable to state surveillance, can overcome usability issues to adopt complex E2EE tools for long-term use. We surveyed regional activists, as surveillance of social movements is well-documented. Our study group includes individuals from 9 social movement groups in the US who had elected to participate in a workshop on using Thunderbird+Enigmail for email encryption. These workshops tool place prior to mid-2017, via a partnership with a non-profit which supports social movement groups. Six to 40 months after their PGP email encryption training, more than half of the study participants were continuing to use PGP email encryption despite intervening widespread deployment of simple E2EE messaging apps such as Signal. We study the interplay of usability with social factors such as motivation and the risks that individuals undertake through their activism. We find that while usability is an important factor, it is not enough to explain long term use. For example, we find that riskiness of one's activism is negatively correlated with long-term PGP use. This study represents the first long-term study, and the first in-the-wild study, of PGP email encryption adoption. © 2021, CC BY.

关键词： Usability engineering

来源：评论

学校读者我要写书评

暂无评论

Radiative energy band gap of nanostructures coupled with quantum emitters around the epsilon-near-zero frequency

引用

Physical Review B 2022年第8期106卷 085422-085422页

作者： Tao Gong Iñigo Liberal Miguel Camacho Benjamin Spreng Nader Engheta Jeremy N. Munday Department of Electrical and Computer Engineering University of California 95616 Davis California USA Department of Materials Science and Engineering University of California 95616 Davis California USA Institute of Smart Cities Public University of Navarre 31006 Pamplona Spain Department of Electronics and Electromagnetism University of Seville 41012 Seville Spain Department of Electrical and Systems Engineering University of Pennsylvania Philadelphia 19104 Pennsylvania USA

Epsilon-near-zero (ENZ) materials have been demonstrated to exhibit unique electromagnetic properties. Here we propose the concept of a radiative energy band gap for an ENZ nanoparticle coupled with a quantum emitter (QE). The radiative emission of the coupled QE–nanoparticle can be significantly suppressed around the ENZ frequency and substantially enhanced otherwise, yielding an effective energy band gap for radiation. This suppression is effectively invariant with respect to particle size and is therefore an intrinsic property of the ENZ material. Our concept also heralds an alternative pathway to quench the emission from a QE, which may find potential application in quantum information storage.

关键词： Mie scattering Permittivity Photoemission Plasmonics Spontaneous emission Nanostructures

来源：评论

学校读者我要写书评

暂无评论

5G Multi-BS Positioning: A Decentralized Fusion Scheme

arXiv

引用

arXiv 2023年

作者： Saleh, Sharief Bader, Qamar Elhabiby, Mohamed Noureldin, Aboelmagd The Department of Electrical and Computer Engineering Queen’s University KingstonONK7L 3N6 Canada Lab Department of Electrical and Computer Engineering Royal Military Collage of Canada KingstonONK7K 7B4 Canada Micro Engineering Tech. Inc the Public Works Department Ain Shams University Cairo11566 Egypt

Fifth-generation (5G) networks are expected to provide high-precision positioning estimation utilizing mmWave signals in urban and downtown areas. In such areas, 5G base stations (BSs) will be densely deployed, allowing for line-of-sight (LOS) communications between the user equipment (UE) and multiple BSs at the same time. Having access to a plethora of measurement sources grants the need for optimal integration between the BSs to have an accurate and precise positioning solution. Traditionally, 5G multi-BS fusion is conducted via an extended Kalman filter (EKF), that directly utilizes range and angle measurements in a centralized integration scheme. Such measurements have a non-linear relationship with the positioning states of the filter, giving rise to linearization errors. Counter to the common belief, an unscented Kalman filter (UKF) will fail to totally eradicate such linearization errors. In this paper, we argue that a decentralized integration between 5G BSs would fully avoid linearization errors within the filter and significantly enhance the positioning performance. This is done by fusing position measurements instead of directly fusing range and angle measurements, which inherently leads to a linear measurement model by design. The proposed decentralized KF method was evaluated in a quasi-real simulation setup provided by Siradel using a real trajectory in Downtown Toronto. The experiments compared the performance of decentralized KF integration to that of centralized EKF and UKF integration schemes. It was shown that the proposed method outperformed both UKF and EKF implementations in multiple scenarios as it significantly decreased the RMS and maximum 2D positioning errors, achieving decimeter-level accuracy for 93.9% of the time. © 2023, CC BY.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

electrically switchable Casimir forces using transparent conductive oxides

引用

Physical Review A 2022年第6期106卷 062824-062824页

作者： Tao Gong Benjamin Spreng Miguel Camacho Iñigo Liberal Nader Engheta Jeremy N. Munday Department of Electrical and Computer Engineering University of California Davis California 95616 USA Department of Materials Science Engineering University of California Davis California 95616 USA Department of Electronics and Electromagnetism University of Seville Sevilla 41012 Spain Institute of Smart Cities Public University of Navarre Pamplona 31006 Spain Department of Electrical and Systems Engineering University of Pennsylvania Philadelphia Pennsylvania 19104 USA

Casimir forces between charge-neutral bodies originate from quantum vacuum fluctuations of electromagnetic fields, which exhibit a critical dependence on material's electromagnetic properties. Over the years, in situ modulation of a material's optical properties has been enabled through various means and has been widely exploited in a plethora of applications such as electro-optical modulation, transient color generation, bio- or chemical sensing, etc. Yet Casimir force modulation has been hindered by difficulty in achieving high modulation signals due to the broadband nature of the Casimir interaction. Here we propose and investigate two configurations that allow for in situ modulation of Casimir forces through electrical gating of a metal-insulator-semiconductor junction comprised of transparent conductive oxide (TCO) materials. By switching the gate voltage on and off, a force modulation of >400 pN is predicted due to substantive charge carrier accumulation in the TCO layer, which can be easily measured using state-of-the-art force measurement techniques in an atomic force microscope. We further examine the influence of the oxide layer thickness on the force modulation, suggesting the importance of the fine control of the oxide layer deposition. Our work provides a promising pathway for modulating the Casimir effect in situ with experimentally measurable force contrast.

关键词： Casimir effect Casimir effect & related phenomena Light-matter interaction Optical materials & elements Transparent conducting oxides

来源：评论

学校读者我要写书评

暂无评论

Robust Multimodal Cough and Speech Detection using Wearables: A Preliminary Analysis 46

Robust Multimodal Cough and Speech Detection using Wearables...

引用

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

作者： Chen, Yuhan Barahona, Jeffrey Eldho, Iype Yu, Yanbing Muhammad, Riyaz Kutsche, Bill Hernandez, Michelle L. Carpenter, Delesha Bozkurt, Alper Lobaton, Edgar North Carolina State University Department of Electrical and Computer Engineering RaleighNC27695 United States Murata Electronics North America Inc. SmyrnaGA30080-7604 United States University of North Carolina at Chapel Hill School of Medicine Department of Pediatrics Chapel HillNC27559 United States University of North Carolina at Chapel Hill Division of Pharmaceutical Outcomes and Policy Eshelman School of Pharmacy Chapel HillNC27559 United States

ISBN: (纸本)9798350371499

Cough detection is a crucial tool for long-term monitoring of respiratory illnesses. While clinical methods are accurate, they are not available in a home-based setting. In contrast, wearable devices offer a more accessible alternative, but face challenges in ensuring user speech privacy and detecting coughs accurately in real-world settings due to potential poor audio quality and background noise. This study addresses these challenges by developing a small-size multimodal cough and speech detection system, enhanced with an Out-of-Distribution (OOD) detection algorithm. Through our analyses, we demonstrate that combining transfer learning, a multimodal approach, and OOD detection techniques significantly improves system performance. Without OOD inputs, the system shows high accuracies of 92.59% in the in-subject setting and 90.79% in the cross-subject setting. With OOD inputs, it still maintains overall accuracies of 91.97% and 90.31% in these respective settings by incorporating OOD detection, despite the number of OOD inputs being twice that of In-Distribution (ID) inputs. This research are promising towards a more efficient, user-friendly cough and speech detection method suitable for wearable devices. © 2024 IEEE.

关键词： Audio signal processing

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：