检索结果-内蒙古大学图书馆

Organic and Hybrid Sensors and Bioelectronics XIV 2021

作者： Castillo, D. Sánchez, A. González, J. Chamba, C. Lakshminarayanan, Vasudevan Chemistry Department Universidad Tecnica Particular de Loja Ap. 11-01-608 Loja Ecuador Theoretical and Experimental Epistemology Lab School of Optometry and Vision Science University of Waterloo ON Canada Departments of Physics Electrical and Computer Engineering and Systems Design Engineering University of Waterloo ON Canada

ISBN: (数字)9781510644595

ISBN: (纸本)9781510644588

The ultraviolet (UV) index is an international standard measure of the strength of solar ultraviolet radiation on the earth's surface at a specific place and time. Solar radiation with a high UV index can produce damage to the skin and eye (photoaging and photokeratitis). The levels of UV radiation are commonly detected using silicon-based optoelectronic sensors, which can be expensive. Here we propose a way to measure the UV index using natural organic pigments which fluoresce when exposed to UV radiation. In combination with an optical fiber, we have built a prototype sensor based on the pigment of turmeric or "Curcuma Longa". Curcuma longa fluoresces in the range of 500 to 680 nm when exposed to UV radiation. The system uses a filter to isolate the sunlight UV component. The sensor measures the variation in fluorescence intensity using a light dependent resistor to determine radiation levels and correlate it with the UV index. The sensor has been tested in Loja, Ecuador which is located at the equator (UV levels can reach up to 20.0 at the equator). When compared to a standard commercially available sensor (ML8511/LAPIS Semiconductor) this prototype has an error of ± 2.8%. We will describe the optical design and present measurements made with this novel inexpensive sensor. © 2021 SPIE.

关键词： Fluorescence

来源：评论

学校读者我要写书评

暂无评论

Assessment of Serum Creatinine and Serum Sodium Prognostic Potential in Heart Failure Patients Using Machine Learning 46

Assessment of Serum Creatinine and Serum Sodium Prognostic P...

引用

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

作者： Alyounis, Sona Khandoker, Ahsan Stefanini, Cesare Hadjileontiadis, Leontios Scuola Superiore Sant'Anna Creative Engineering Design Lab The BioRobotics Institute Pontedera Italy Khalifa University of Science and Technology Healthcare Engineering Innovation Center Department of Biomedical Engineering P.O. Box 127788 Abu Dhabi United Arab Emirates Aristotle University of Thessaloniki Department of Electrical and Computer Engineering Thessaloniki Greece

ISBN: (纸本)9798350371499

Heart failure (HF) is the leading etiology for hospital admissions and ranks among the foremost contributors to mortality. This complex clinical syndrome with various phenotypes is categorized by left ventricle ejection fraction levels (LVEF), namely preserved (HFpEF), mid-range (HFmEF), and reduced (HFrEF). This study investigates the prognostic impact of serum creatinine and serum sodium levels in HF patients across these three classes using machine learning tools. A comprehensive dataset of HF patients' medical records including serum sodium and serum creatinine was utilized. Machine learning regression models were employed to predict the LVEF levels. Additionally, classification models were implemented to categorize patients into HFpEF, HFmEF, and HFrEF classes. Regression analyses revealed the predictive capabilities of serum sodium and serum creatinine in estimating the progression of HF severity. Furthermore, classification models successfully differentiated between the three EF classes, providing valuable insights into the classification patterns of HF patients based on these biomarkers. The results demonstrated the significance of serum sodium serum creatinine as prognostic markers in HF, and this contributes to a more nuanced approach to HF management, paving the way for targeted interventions and improved patient outcomes. Moreover, this study highlights the potential of machine learning techniques to enhance risk stratification and classification in HF patients, enabling personalized prognostication and treatment strategies. © 2024 IEEE.

关键词： Creatinine

来源：评论

学校读者我要写书评

暂无评论

GitFL: Uncertainty-Aware Real-Time Asynchronous Federated Learning Using Version Control 44

GitFL: Uncertainty-Aware Real-Time Asynchronous Federated Le...

引用

44th IEEE Real-Time Systems Symposium, RTSS 2023

作者： Hu, Ming Xia, Zeke Yan, Dengke Yue, Zhihao Xia, Jun Huang, Yihao Liu, Yang Chen, Mingsong School of Computer Science and Engineering Nanyang Technological University Singapore MoE Engineering Research Center of SW/HW Co-Design Tech. and App. East China Normal University China East China Normal University Moe International Joint Lab of Trustworthy Software China

ISBN: (纸本)9798350328578

As a promising distributed machine learning paradigm that enables collaborative training without compromising data privacy, Federated Learning (FL) has been increasingly used in large-scale A IoT (Artificial Intelligence of Things) system design. However, due to the lack of efficient management of straggling devices, existing FL methods greatly suffer from the problems of long response time (e.g., training and communication latency) and low inference accuracy. Things become even worse when taking various uncertain factors (e.g., network delays, performance variances caused by process variation) existing in AIoT scenarios into account. To address this issue, this paper proposes a novel asynchronous FL framework named GitFL, whose implementation is inspired by the famous version control system Git. Unlike traditional FL, the cloud server of GitFL maintains a master model (i.e., the global model) together with a set of branch models indicating the trained local models committed by selected devices, where the master model is updated based on both all the pushed branch models and their version information, and only the branch models after the pull operation are dispatched to devices. By using our proposed Reinforcement Learning (RL)-based device selection mechanism, a pulled branch model with an older version will be more likely to be dispatched to a faster and less frequently selected device for the next round of local training. In this way, GitFL enables both effective controls of model staleness and adaptive load balance of versioned models among straggling devices, thus avoiding performance deterioration while ensuring real-time performance. Comprehensive experimental results on well-known models and datasets show that, compared with state-of-the-art asynchronous and synchronous FL methods, GitFL can achieve up to 2.64X training acceleration and 7.88 % inference accuracy improvements in various uncertain scenarios. © 2023 IEEE.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Development of a Carbon Fiber Knitted Capacitive Touch Sensor

Development of a Carbon Fiber Knitted Capacitive Touch Senso...

引用

作者： Vallett, Richard Young, Ryan Knittel, Chelsea Kim, Youngmoo Dion, Genevieve Shima Seiki Haute Tech Lab at ExCITe Drexel University PhiladelphiaPA United States ExCITe Center Drexel University PhiladelphiaPA United States Mechanical Engineering and Mechanics College of Engineering Drexel University PhiladelphiaPA United States Department of Computer Science College of Computing and Informatics Drexel University PhiladelphiaPA United States Materials Science and Engineering College of Engineering Drexel University PhiladelphiaPA United States Electrical and Computer Engineering College of Engineering Drexel University PhiladelphiaPA United States Department of Design Westphal College of Media Arts and Design Drexel University PhiladelphiaPA United States

Textiles, in combination with advances in materials and design, offer exciting new possibilities for human and environmental interaction, including biometric and touch-based sensing. Previous fabric-based or flexible touch sensors have generally required a large number of sensing electrodes positioned in a dense XY grid configuration and a multitude of wires. This paper investigates the design and manufacturing of a planar (two-dimensional, XY location) touch fabric sensor with only two electrodes (wires) to sense both planar touch and pressure, making it ideal for applications with limited space/complexity for wiring. The proposed knitted structure incorporates a supplementary method of sensing to detect human touch on the fabric surface, which offers advantages over previous methods of touch localization through an efficient use of wire connections and sensing materials. This structure is easily manufactured as a single component utilizing flatbed knitting techniques and electrically conductive yarns. The design requires no embedded electronics or solid components in the fabric, which allows the sensor to be flexible and resilient. This paper discusses the design, fabrication, sensing methods, and applications of the fabric sensor in robotics and human-machine interaction, smart garments, and wearables, as well as the highly transdisciplinary approach pursued in developing medical textiles and flexible embedded sensors. Copyright © Materials Research Society 2016.

关键词： Wire

来源：评论

学校读者我要写书评

暂无评论

How effective is human video surveillance performance?

How effective is human video surveillance performance?

引用

International Conference on Pattern Recognition

作者： Noah Sulman Thomas Sanocki Dmitry Goldgof Rangachar Kasturi Vision Cognition Design Lab Department of Psychology University of South Florida Computer Science and Engineering College of Engineering University of South Florida

ISBN: (纸本)9781424421749

In surveillance situations, computer vision systems are often deployed to help humans perform their tasks more effectively. In a typical installation human observers are required to simultaneously monitor a number of video signals. Psychophysical research indicates that there are severe limitations in the ability of humans to monitor simultaneous signals. Do these same limitations extend to surveillance? We present a method for evaluating human surveillance performance in a situation that mimics demands of real world surveillance. A single computer monitor contained either nine display cells or four display cells. Each cell contained a stream of 2 to 4 moving objects. Observers were instructed to signal when a target event occurred - - when one of the objects entered a small square ldquoforbiddenrdquo region in the center of the display. Target events could occur individually or in groups of 2 or 3 temporally close events. The results indicate that the observers missed many targets (60%) when required to monitor 9 displays and many fewer when monitoring 4 displays (20%). Further, there were costs associated with target events occurring in close temporal succession. Understanding these limitations would help computer visions researchers to design algorithms and human-machine interfaces that result in improved overall performance.

关键词： Humans Video surveillance computerized monitoring computer displays Costs computer vision Cognition Psychology Algorithm design and analysis Educational institutions

来源：评论

学校读者我要写书评

暂无评论

Turning to Information Theory to Bring in-Memory Computing into Practice

IEEE BITS the Information Theory Magazine

引用

IEEE BITS the Information Theory Magazine 2023年第3期3卷 64-77页

作者： Dupraz, Elsa Leduc-Primeau, Francois Cai, Kui Dolecek, Lara Lab-STICC UMR CNRS IMT Atlantique Brest29238 France Polytechnique Montreal Department of Electrical Engineering MontrealQCH3T 1J4 Canada Singapore University of Technology and Design Science Mathematics and Technology Cluster Singapore487372 Singapore UCLA Department of Electrical and Computer Engineering Los AngelesCA90095 United States

This article explores the emerging field of in-memory computing, which has the potential to significantly improve energy efficiency in many signal processing and machine learning applications. In-memory computing systems are impacted by various sources of noise and perturbations that can affect their computation accuracy. Therefore, this article aims to identify the key challenges to be addressed from an information-theoretic point of view in this area. It first identifies relevant computation structures and noise models from the literature of hardware implementation, and then reviews existing works in information theory and error-correction for in-memory computing. Finally, it identifies key open avenues for establishing information-theoretic foundations of in-memory computing systems, and for providing insightful design rules leading to highly energy-efficient computing systems. © 2021 IEEE.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

A 2-channel time-to-digital converter with 20-ps resolution for pico-second timing application 11

A 2-channel time-to-digital converter with 20-ps resolution ...

引用

11th IEEE Global Conference on Consumer Electronics, GCCE 2022

作者： Du, Zhouji Ke, Qin Yu, Hang Li, Yan Ge, Binjie Yong, Shanshan Cheng, Yonghong Shenzhen Laboratory of IC Design for IOT College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Lab. of IC Design for IOT College of CS & SE Shenzhen University Shenzhen China Dept. of Electronics and Computer Engineering SHENZHEN MCU-BIT University Shenzhen China Peking University Shenzhen Graduate School Shenzhen China Hubble Sensor Solution Shenzhen Co. LTD Shenzhen China

ISBN: (纸本)9781665492324

Time-to-Digital Converter (TDC) provides picosecond accuracy timing and is widely used in many applications such as Light Detection and Ranging (LIDAR), 3-D vision, and ultrasonic flow sensors. This paper introduces a 2-channel TDC with two-level resolution control architecture. designed in a 180 nm CMOS process, the TDC occupies an area of 2.3 mm ×1.3 mm and achieves 20 ps resolution at 2 Msps measurement rate. © 2022 IEEE.

关键词： Frequency converters

来源：评论

学校读者我要写书评

暂无评论

A Configurable Architecture for a Visual Saliency System and Its Application in Retail

A Configurable Architecture for a Visual Saliency System and...

引用

Annual IEEE Symposium on Field-Programmable Custom Computing Machines (FCCM)

作者： Nandhini Chandramoorthy Siddarth Advani Kevin M. Irick Vijaykrishnan Narayanan Microsystems Design Lab (MDL) Department of Computer Science & Engineering Pennsylvania State University University Park PA USA

Summary form only given. The objective of this paper is to present a configurable architecture for a visual saliency model based on AIM. It presents algorithmic enhancements to AIM that facilitates the design of a performance-efficient hardware architecture that offers tradeoffs between accuracy, resource utilization and latency. The AIM computational model involves (1) extraction of a set of coefficient features for each local patch in an image, (2) estimation of probability density for each coefficient with respect to its local surround, (3) computation of their product to give a joint likelihood and (4) computation of the self information of each pixel from its log likelihood. Calculation of likelihood with respect to each pixel individually in a local surround is computationally expensive. It proposes to approximate the contribution of pixels in the surround in terms of “cells” grouped further into “support zones”, whose widths are configurable. This approximation leads to nearly a 10x reduction in the number of multipliers, a critical resource, for a 41x41 surround size.

关键词： computer architecture Microprocessors Visualization Computational modeling Pipelines Feature extraction Routing

来源：评论

学校读者我要写书评

暂无评论

Data Reconstruction from Gradient Updates in Federated Learning 4th

Data Reconstruction from Gradient Updates in Federated Lea...

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Zhang, Xiaoxue Li, Junhao Zhang, Jianjie Yan, Jijie Zhu, Enmin Chen, Kongyang School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China Institute of Artificial Intelligence and Blockchain Guangzhou University Guangzhou China Pazhou Lab Guangzhou China Jiangsu Key Laboratory of Media Design and Software Technology Jiangnan University Wuxi China

ISBN: (纸本)9783031200953

Federated learning has become an emerging technology to protect data privacy in the distributed learning area, by keeping each client user’s data locally. However, recent work shows that client users’ data might still be stolen (or reconstructed) directly from gradient updates. After exploring the attack and defense techniques of these data reconstruction methods, we discover that the attacker cannot steal the victim’s data unless it has prior knowledge about the victim’s data size. Thus, the attacker can hardly reconstruct any useful information without these prior knowledge. In this paper, we provide a novel data reconstruction method to obtain a high-dimensional compressed data from the gradient updates, without these prior knowledge. Experiment results show that our reconstructed data can be used to attack the model, with high attack accuracy. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Attention-Enhanced Lightweight Hourglass Network for Human Pose Estimation

Attention-Enhanced Lightweight Hourglass Network for Human P...

引用

2024 Australasian Conference on Robotics and Automation, ACRA 2024

作者： Kappan, Marsha Mariya Sandoval, Eduardo Benitez Meijering, Erik Cruz, Francisco School of Computer Science and Engineering University of New South Wales Sydney Australia School of Art and Design Creative Robotics Lab. University of New South Wales Sydney Australia Escuela de Ingeniería Universidad Central de Chile Santiago Chile

Pose estimation is a critical task in computer vision with a wide range of applications from activity monitoring to human-robot interaction. However, most of the existing methods are computationally expensive or have complex architecture. Here we propose a lightweight attention based pose estimation network that utilizes depthwise separable convolution and Convolutional Block Attention Module on an hourglass backbone. The network significantly reduces the computational complexity (floating point operations) and the model size (number of parameters) containing only about 10% of parameters of original eight stack Hourglass network. Experiments were conducted on COCO and MPII datasets using a two stack hourglass backbone. The results showed that our model performs well in comparison to six other lightweight pose estimation models with an average precision of 72.07. The model achieves this performance with only 2.3M parameters and 3.7G FLOPs. © 2024 Australasian Robotics and Automation Association. All rights reserved.

关键词： Convolution

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：