检索结果-内蒙古大学图书馆

Computational Optical Sensing and Imaging, COSI 2024 - Part of Optica Imaging Congress

作者： Markley, Eric Kabuli, Leyla Chien, Tiffany Pinkard, Henry Waller, Laura UCB/UCSF Joint Graduate Program in Bioengineering University of California Berkeley United States Department of Electrical Engineering and Computer Sciences University of California Berkeley United States

We present a technique for information-theoretic optimization of computational imaging systems demonstrated in snapshot 3D microscopy. By directly evaluating measurement quality and decoupling optimization from downst... 详细信息

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Fast non-iterative algorithm for 3D point-cloud holography

引用

Optics Express 2023年第22期31卷 36468-36485页

作者： Ersaro, Nathan Tessema Yalcin, Cem Murray, Liz Kabuli, Leyla Waller, Laura Muller, Rikky Graduate Program in Bioengineering University of California Berkeley and University of California San Francisco BerkeleyCA94720 United States Department of Electrical Engineering and Computer Sciences University of California Berkeley BerkeleyCA94720 United States

Recently developed iterative and deep learning-based approaches to computer-generated holography (CGH) have been shown to achieve high-quality photorealistic 3D images with spatial light modulators. However, such approaches remain overly cumbersome for patterning sparse collections of target points across a photoresponsive volume in applications including biological microscopy and material processing. Specifically, in addition to requiring heavy computation that cannot accommodate real-time operation in mobile or hardware-light settings, existing sampling-dependent 3D CGH methods preclude the ability to place target points with arbitrary precision, limiting accessible depths to a handful of planes. Accordingly, we present a non-iterative point cloud holography algorithm that employs fast deterministic calculations in order to efficiently allocate patches of SLM pixels to different target points in the 3D volume and spread the patterning of all points across multiple time frames. Compared to a matched-performance implementation of the iterative Gerchberg-Saxton algorithm, our algorithm’s relative computation speed advantage was found to increase with SLM pixel count, reaching >100,000x at 512 × 512 array format. © 2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Hybrid 1D and 2D CNN-Transformer Architectures for Multilabel 12-Lead EKG Anomaly Detection

Hybrid 1D and 2D CNN-Transformer Architectures for Multilabe...

引用

Annual Conference on Information Sciences and Systems (CISS)

作者： Ian DeTore John Samsundar Cleon Davis Electrical and Computer Engineering Program Johns Hopkins University Baltimore MD USA Electrical and Computer Engineering Program Johns Hopkins University Laurel MD USA

ISBN: (数字)9798331513269

ISBN: (纸本)9798331513276

This study introduces two novel hybrid machine-learning architectures for multilabel anomaly detection in electrocardiograms (EKGs): a 1D modified ResNet combined with a transformer encoder and an equivalent 2D ResNet-Transformer hybrid. This work is among the first to utilize two separate CNN-transformer architectures tailored specifically for temporal and spatial features in multilabel EKG data. Our models address the challenges of imbalanced data and multilabel classification by leveraging the PTB-XL dataset, containing over 21,000 annotated samples across five diagnostic superclasses, namely myocardial infarction, conduction disturbances, hypertrophy, ST-T wave changes, and normal EKGs. We applied advanced data augmentation techniques to mitigate class imbalance, including the Multilabel Synthetic Minority Over-Sampling Technique (ML-SMOTE). Additionally, we employed digital signal processing to denoise the EKG signals and convert time-series data into time-frequency representations for 2D modeling. Experimental results demonstrate the effectiveness of our approach, with the 1D model achieving an area under the curve (AUC) of 91.5% and the 2D model achieving an AUC of 87.2%. These findings demonstrate the potential of specialized architectures for comprehensive multilabel EKG anomaly detection.

关键词： Time-frequency analysis Multi label classification Machine learning Electrocardiography Myocardium Brain modeling Transformers Data models Electromyography Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Neurocognitive assessment under various human-robot teaming environments 46

Neurocognitive assessment under various human-robot teaming ...

引用

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

作者： Packy, Anna L. Jayahankar, Jayesh Teymourlouei, Arya Stone, Joshua Oh, Hyuk Katz, Garrett E. Reggia, James A. Gentili, Rodolphe J. University of Maryland Neuroscience and Cognitive Science Program College Park United States University of Maryland Department of Computer Science College Park United States University of Maryland Department of Electrical & Computer Engineering College Park United States University of Maryland Department of Kinesiology College Park United States Syracuse University Department of Electrical Engineering & Computer Science Syracuse United States

ISBN: (纸本)9798350371499

Human-robot teaming has become increasingly important with the advent of intelligent machines. Prior efforts suggest that performance, mental workload, and trust are critical elements of human-robot dynamics that can be altered by the robot's behavior. Most prior human-robot teaming studies used behavioral analyses, but a limited number used neural markers, without the use of physical robots and complex tasks. Here we combine behavioral and EEG cortical dynamics to examine cognitive-motor processes when individuals complete a complex task under various team environments with a robot. The results revealed that altering the robot quality affected both behavioral and EEG dynamics. Task completion with an experienced robot led to greater team performance and human trust along with lower mental workload compared to an inexperienced teammate or when individuals performed alone. EEG changes suggest that different attentional processes were engaged when humans worked with the robot and performed alone, and that visual processing was more prominent when teaming with an inexperienced teammate. This work can inform human cognitive-motor processes and the design of robotic controllers in human-robot teams. © 2024 IEEE.

关键词： Man machine systems

来源：评论

学校读者我要写书评

暂无评论

Textual Training for the Hassle-Free Removal of Unwanted Visual Data: Case Studies on OOD and Hateful Image Detection 38

Textual Training for the Hassle-Free Removal of Unwanted Vis...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Lee, Saehyung Mok, Jisoo Park, Sangha Shin, Yongho Jung, Dahuin Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Qualcomm Korea YH Seoul Korea Republic of School of Computer Science and Engineering Soongsil University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

In our study, we explore methods for detecting unwanted content lurking in visual datasets. We provide a theoretical analysis demonstrating that a model capable of successfully partitioning visual data can be obtained using only textual data. Based on the analysis, we propose Hassle-Free Textual Training (HFTT), a streamlined method capable of acquiring detectors for unwanted visual content, using only synthetic textual data in conjunction with pre-trained vision-language models. HFTT features an innovative objective function that significantly reduces the necessity for human involvement in data annotation. Furthermore, HFTT employs a clever textual data synthesis method, effectively emulating the integration of unknown visual data distribution into the training process at no extra cost. The unique characteristics of HFTT extend its utility beyond traditional out-of-distribution detection, making it applicable to tasks that address more abstract concepts. We complement our analyses with experiments in out-of-distribution detection and hateful image detection. Our codes are available at https://***/Saehyung-Lee/HFTT. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Boost DC-DC Converter with Non-dissipative Snubber

引用

IEEJ Transactions on electrical and Electronic engineering 2024年第11期19卷 1858-1878页

作者： Yau, Yeu-Torng Department of Ph.D. Program Prospective Technology of Electrical Engineering and Computer Science National Chin-Yi University of Technology Taichung No.57 Sec. 2 Zhongshan Rd. Taiping Dist Taichung41170 Taiwan

To provide a hold-up time function in DC-DC supplies for cell site stations or data centers, using a boost converter with a bulk output capacitor as a front-end converter stage is a simple and highly cost-effective solution. However, conventional boost converters with a hard-switching operation result in low conversion efficiency and increased electromagnetic interference emissions. In this paper, a boost converter with a new non-dissipative snubber is proposed that only requires two additional diodes, an inductor, and a multilayer ceramic capacitor. The main feature of the proposed snubber is that the components are not located on the main power processing path. This means they only require low ratings, improving cost-effectiveness. A prototype converter is analyzed, realized, and applied to a 300 W redundant DC-DC power supply module for a 5G cell base station. © 2024 The Author(s). IEEJ Transactions on electrical and Electronic engineering published by Institute of electrical Engineers of Japan and Wiley Periodicals LLC. © 2024 The Author(s). IEEJ Transactions on electrical and Electronic engineering published by Institute of electrical Engineers of Japan and Wiley Periodicals LLC.

关键词： Boost converter

来源：评论

学校读者我要写书评

暂无评论

Seafloor Imaging Maps by Incorporating Side Scan Sonar Technology on Hybrid Autonomous Underwater Glider 6

Seafloor Imaging Maps by Incorporating Side Scan Sonar Techn...

引用

6th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2023

作者： Atmaja, Ardian Budi Kusuma Hidayat, Egi Muhammad Idris Riyanto Trilaksono, Bambang Siregar, Simon habibullah, Natsir School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia Institut Teknologi Bandung Telkom University Doctoral Program of Electrical Engineering Department Computer Engineering Faculty of Applied Science Indonesia

ISBN: (纸本)9798350358346

This research aims to construct a two-dimensional image to represent an underwater geometry map with a Side Scan Sonar (SSS) mounted on a Hybrid Autonomous Underwater Glider (HAUG). Building the underwater map has two stages of the process. The first stage is preprocessing which includes Time-varying gains (TVG), slant range correction, and ground range correction. The second is HAUG navigation, the movement of HAUG orientation to the angle and distance of SSS readings and plotting the geometry of the grid map. With these two stages, a two-dimensional grid map will be formed. Meanwhile, the 3D plot utilizes slant range and ground range correction to obtain the surface height of the bottom of the pool. From the experiments conducted to conduct mapping in the pool, two-dimensional and three-dimensional visual forms of the pool floor and pool walls were produced. The results of the estimated measurement of the width of the pool obtained 14.05 meters and the height of the pool 3.199 meters with an SSS beam angle of 58 degrees. © 2023 IEEE.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

ReMP: Reusable Motion Prior for Multi-domain 3D Human Pose Estimation and Motion Inbetweening

ReMP: Reusable Motion Prior for Multi-domain 3D Human Pose E...

引用

2025 IEEE/CVF Winter Conference on Applications of computer Vision, WACV 2025

作者： Jang, Hojun Kim, Young Min Seoul National University Dept. of Electrical and Computer Engineering Korea Republic of Interdisciplinary Program in Artificial Intelligence and Inmc Seoul National University Korea Republic of

ISBN: (纸本)9798331510831

We present Reusable Motion prior (ReMP), an effective motion prior that can accurately track the temporal evolution of motion in various downstream tasks. Inspired by the success of foundation models, we argue that a robust spatio-temporal motion prior can encapsulate underlying 3D dynamics applicable to various sensor modalities. We learn the rich motion prior from a sequence of complete parametric models of posed human body shape. Our prior can easily estimate poses in missing frames or noisy measurements despite significant occlusion by employing a temporal attention mechanism. More interestingly, our prior can guide the system with incomplete and challenging input measurements to quickly extract critical information to estimate the sequence of poses, significantly improving the training efficiency for mesh sequence recovery. ReMP consistently outperforms the baseline method on diverse and practical 3D motion data, including depth point clouds, LiDAR scans, and IMU sensor data. Project page is available in https://***/ReMP. © 2025 IEEE.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

Optimized Instruction Set Architecture for programmable Memory Test Pattern Generation 21

Optimized Instruction Set Architecture for Programmable Memo...

引用

21st International System-on-Chip Design Conference, ISOCC 2024

作者： Park, Seokmin Park, Jewoo Lee, Young-Woo Inha University School of Electrical and Computer Engineering Incheon Korea Republic of Inha University Program in Semiconductor and Device Korea Republic of Hyundai Motor Company Hwaseong Korea Republic of

ISBN: (纸本)9798350377088

Continuous progress in memory semiconductor manufacturing technology has significantly increased capacities, densities, and operating frequencies. However, these developments have also increased the probability of memory defects, consequently diminishing yield rates. To overcome this issue, various memory test pattern algorithms have been devised to identify the type of memory defect, primarily categorized into linear and nonlinear patterns. This paper presents an instruction-based approach for efficiently generating diverse nonlinear patterns. The proposed instruction set architecture (ISA) provides flexibility in generating both linear and intricate nonlinear patterns, while also ensuring a compact memory test setup cycle, regardless of the memory cell size. © 2024 IEEE.

关键词： Cost reduction

来源：评论

学校读者我要写书评

暂无评论

High impedance fault classification in microgrids using a transformer-based model with time series harmonic synchrophasors under data quality issues

引用

Neural Computing and Applications 2024年第23期36卷 14017-14034页

作者： Cieslak, Dionatan A. G. Moreto, Miguel Lazzaretti, André E. Macedo-Júnior, José R. PPGEEL - Graduate Program in Electrical Engineering Federal University of Santa Catarina UFSC R. Eng. Agronômico Andrei Cristian Ferreira s/n Santa Catarina Florianópolis88040-900 Brazil CPGEI - Graduate Program in Electrical and Computer Engineering Federal University of Technology - Paraná UTFPR Av. Sete de Setembro 3165 Paraná Curitiba80230-901 Brazil PPGEELT - Graduate Program in Eletrical Engineering Federal University of Uberlândia UFU Av. João Naves de Ávila 2121 Minas Gerais Uberlândia38408-100 Brazil

Recent advances in distribution networks, driven by the integration of renewable energy sources, have spurred the emergence of microgrids, elevating concerns regarded reliability and stability. In this context, precise monitoring of events, particularly those elusive to detection like high-impedance faults (HIFs), becomes imperative. The development of phasor measurement units (PMUs) with their harmonic synchronized measurements has enhanced the monitoring task and fostering the application of synchrophasors even on microgrids. This work introduces a novel method for event classification in microgrids, utilizing combined low-rate PMU data and harmonic synchrophasor time series. Central to our approach is the usage of a state-of-the-art transformer neural network, based on the attention mechanism, to effectively discern HIFs from other faulty and non-fault events. Notably, this methodology accounts for prevalent PMU data quality issues, including noise, missing data, and synchronism errors. Results from real-world HIF data demonstrate a robust performance, with an accuracy rate of approximately 98% in event classification. This harmonic synchrophasor-based strategy showcases promise as an original approach for handling commercial PMU data, offering sufficient robustness for deployment in real-world applications. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Phasor measurement units

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：