检索结果-内蒙古大学图书馆

International Conference on Ubiquitous Robots (UR)

作者： Damin Yeom Heejun Yoon Soyeon Lee Kahyun Lee Department of Electronic and Electrical Engineering Ewha Womans University Seoul South Korea Graduate Program in Smart Factory Ewha Womans University Seoul South Korea

The global personal mobility market has been rapidly expanding due to its convenience. However, the increasing number of accidents involving personal mobility devices has become a growing concern, including falls, collisions with objects, and riders being struck by moving vehicles or objects. In this paper, we propose a deep learning-based safe driving system that considers both user and road images to address this issue. Our system employs CNN-based models to detect whether the user is 1) wearing a helmet and 2) looking ahead in user-side images. At the same time, the roadside image recognizes whether the user is 3) driving on the sidewalk and 4) near the intersection. These tasks are simultaneously performed in parallel to identify the overall situation, which is done by determining the final speed as the minimum speed of speed values extracted from all tasks. Additionally, we employ knowledge distillation techniques to compress the models and enable real-time inference on edge devices, resulting in a fast and accurate system that is well-suited to the characteristics of personal mobility.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PA-2SBF: Pattern-Adaptive Two-Stage Bloom Filter for Run-Time Memory Diagnostic Data Compression in Automotive SoCs

PA-2SBF: Pattern-Adaptive Two-Stage Bloom Filter for Run-Tim...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Sunyoung Park Hyunji Kim Hana Kim Ji-Hoon Kim Department of Electronic and Electrical Engineering Ewha Womans University Seoul Republic of Korea Graduate Program in Smart Factory Ewha Womans University Seoul Republic of Korea

ISBN: (数字)9783981926385

ISBN: (纸本)9798350348606

In the realm of safety-critical Automotive System-on-Chip (SoC) design, memory functionality plays a crucial role in determining overall die yield due to its sizable footprint on the chip. Therefore, efficient methodologies for both post-manufacturing offline testing and real-time monitoring are essential to provide timely diagnostic feedback. This paper proses a real-time memory diagnostic data compression technique Pattern-Adaptive Two-Stage Bloom Filter (PA-2SBF) for automotive System-on-Chip (SoC) applications. PA-2SBF is designed to address the challenge of false positives incorporating frequently encountered failure patterns. Bloom filters, a probabilistic data structure renowned for their space-efficiency and quick approximate membership queries, are employed to expedite fault memory diagnosis information lookup and compression. Furthermore, failure patterns are considered to mitigate the false positive rate inherent in Bloom filters. The paper also presents a strategy for leveraging the compressed diagnostic information during run-time. Specifically, it exploits the quick lookup feature of Bloom filter to prohibit CPU access to defective memory regions, enhancing overall system reliability.

关键词： Memory management Data compression Information filters Probabilistic logic Data structures Real-time systems System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Dynamic Volumetric Video Coding with Tensor Decomposition

Dynamic Volumetric Video Coding with Tensor Decomposition

引用

IEEE Visual Communications and Image Processing (VCIP)

作者： Ju-Yeon Shin Yeoneui Kim Je-Won Kang Gun Bang Dept. of Electronic and Electrical Engineering and Graduate Program in Smart Factory Ewha Womans University Seoul South Korea Electronics and Telecommunications Research Institute Daejeon South Korea

ISBN: (数字)9798331529543

ISBN: (纸本)9798331529550

Recently, volumetric video coding based on neural radiance fields has gained significant attention for storing and transmitting three-dimensional (3D) scenes captured from multi-view video. Because the neural networks are trained to produce novel view synthesis of surrounding 3D scenes, compressing the model and then rendering the colors and geometry through the decompressed model can be utilized as a 3D video coding system. However, although this approach provides superior performance compared to conventional 3D video coding standards using depth video, challenges remain in reducing overall model sizes to improve coding efficiency. In this paper, we propose a novel dynamic volumetric video coding technique that employs a Group of Volume (GoV) to divide multi-view video sequences into smaller chunks, addressing complex temporal dynamics. Our method uses volumetric video features represented with 3D spatial and temporal tensor matrices and vectors and encodes them with the GoVs. The tensors are compressed by existing 2D video codec, allowing for fast rendering and easing deployment. Experimental results validate that our method not only reduces memory footprint but also maintains high-quality rendering as compared to state-of-the-art studies.

关键词： Video coding Solid modeling Three-dimensional displays Image coding Tensors Visual communication Video sequences Rendering (computer graphics) Video codecs Standards

来源：评论

学校读者我要写书评

暂无评论

Overview of Versatile Video Coding (H.266/VVC) and Its Coding Performance Analysis

引用

IEIE Transactions on smart Processing and Computing 2023年第2期12卷 122-154页

作者： Lee, Minhun Song, HyeonJu Park, Jeeyoon Jeon, Byeungwoo Kang, Jungwon Kim, Jae-Gon Lee, Yung-Lyul Kang, Je-Won Sim, Donggyu Department of Computer Engineering Kwangwoon University Seoul Korea Republic of Department of Computer Engineering Sejong University Seoul Korea Republic of Department of Electrical and Computer Engineering Sungkyunkwan University Kyunggi-do Korea Republic of Communication and Media Research Laboratory Electronics and Telecommunications Research Institute Deajeon Korea Republic of School of Electronics and Information Engineering Korea Aerospace University Kyunggi-do Korea Republic of Department of Electronic and Electrical Engineering Graduate Program in Smart Factory Ewha Womans University Seoul Korea Republic of

Versatile Video Coding (H.266/VVC) is the newest video coding standard jointly developed by the Joint Video Experts Team (JVET), which is organized by the ITU-T Video Coding Experts Group (VCEG) and the ISO/IEC Moving Picture Experts Group (MPEG). H.266/VVC provides about 40% bitrate reduction compared with High Efficiency Video Coding (H.265/HEVC) for the same visual quality. This paper introduces in detail the core structure of H.266/VVC by highlighting its features within block partitioning structure, intra/inter prediction, transform, quantization, and in-loop filtering, compared to its predecessor (H.265/HEVC). H.266/VVC yields significantly improved the coding performance, but it increased the computational complexity, particularly for the encoder side, which remains a problem to be tackled for successful commercialization in the future. This paper examined the statistical performance of H.266/VVC coding tools from the bitstreams encoded by the VVC test model (VTM12.0) encoder through rate-distortion optimization under the JVET common test conditions. In addition, the complexity and performance analyses are conducted on the block partitioning structure and group of picture structure. It is expected that an optimized H.266/VVC encoder can be designed and developed by minimizing the coding loss based on the analysis data. © 2023 Institute of Electronics and Information Engineers. All rights reserved.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Feasibility Study of a Teleoperation System With Haptics for Tip-Force Sensing Active Needles

Feasibility Study of a Teleoperation System With Haptics for...

引用

IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob)

作者： Sooyeon Kim Sujin Yu Yuri Lim Suhyun Lee Seok Chang Ryu Department of Mechanical and Biomedical Engineering BioRobotics Laboratory Graduate Program in Smart Factory Ewha Womans University Seoul South Korea Department of Mechanical and Biomedical Engineering BioRobotics Laboratory Ewha Womans University

ISBN: (数字)9798350386523

ISBN: (纸本)9798350386530

This paper presents the design of a teleoperation system with a haptic display for the active needles with tip-force sensing and tip-steering capabilities. The active needle design employs sensorized tendons by fiber Bragg gratings sensor (FBGs), while the teleoperation system combines a general haptic interface with electrical stimulation as its steering interface, delivering not only general force feedback but also tip-force information measured by the FBGs-based tendons to the operators. The essential features, such as tip-force sensing, teleoperation of the tip-joint, and human perception of the measured tip-force, were experimentally evaluated with their prototypes in tissue phantoms. Based on the results obtained, necessary follow-up studies were identified and suggested for the effective teleoperation of force-sensing steerable instruments in clinical environments. If successfully developed, such systems can enable surgeons to perceive clinical situations and perform operations more precisely and safely.

关键词： Instruments Surgery Prototypes Phantoms Biomedical measurement Robot sensing systems Needles Fiber gratings Sensors Tendons

来源：评论

学校读者我要写书评

暂无评论

Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives

arXiv

引用

arXiv 2022年

作者： Liu, Xiaofeng Yoo, Chaehwa Xing, Fangxu Oh, Hyejin El Fakhri, Georges Kang, Je-Won Woo, Jonghye Gordon Center for Medical Imaging Massachusetts General Hospital Harvard Medical School BostonMA United States Dept. of Electronic and Electrical Engineering Graduate Program in Smart Factory Ewha Womans University Seoul Korea Republic of

Deep learning has become the method of choice to tackle real-world problems in different domains, partly because of its ability to learn from data and achieve impressive performance on a wide range of applications. However, its success usually relies on two assumptions: (i) vast troves of labeled datasets are required for accurate model fitting, and (ii) training and testing data are independent and identically distributed. Its performance on unseen target domains, thus, is not guaranteed, especially when encountering out-of-distribution data at the adaptation stage. The performance drop on data in a target domain is a critical problem in deploying deep neural networks that are successfully trained on data in a source domain. Unsupervised domain adaptation (UDA) is proposed to counter this, by leveraging both labeled source domain data and unlabeled target domain data to carry out various tasks in the target domain. UDA has yielded promising results on natural image processing, video analysis, natural language processing, time-series data analysis, medical image analysis, etc. In this review, as a rapidly evolving topic, we provide a systematic comparison of its methods and applications. In addition, the connection of UDA with its closely related tasks, e.g., domain generalization and out-of-distribution detection, has also been discussed. Furthermore, deficiencies in current methods and possible promising directions are highlighted. © 2022, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional Variable Slab-Selective Projection Acquisition Imaging

arXiv

引用

arXiv 2023年

作者： Park, Jinil Shin, Taehoon Park, Jang-Yeon The Department of Intelligent Precision Healthcare Convergence Sungkyunkwan University Suwon Korea Republic of Division of Mechanical and Biomedical Engineering Graduate Program in Smart Factory Ewha Woman University Seoul Korea Republic of The Department of Biomedical Engineering Sungkyunkwan University Suwon Korea Republic of

Three-dimensional (3D) projection acquisition (PA) imaging has recently gained attention because of its advantages, such as achievability of very short echo time, less sensitivity to motion, and undersampled acquisition of projections without sacrificing spatial resolution. However, larger subjects require a stronger Nyquist criterion and are more likely to be affected by outer-volume signals outside the field of view (FOV), which significantly degrades the image quality. Here, we proposed a variable slab-selective projection acquisition (VSS-PA) method to mitigate the Nyquist criterion and effectively suppress aliasing streak artifacts in 3D PA imaging. The proposed method involves maintaining the vertical orientation of the slab-selective gradient for frequency-selective spin excitation and the readout gradient for data acquisition. As VSS-PA can selectively excite spins only in the width of the desired FOV in the projection direction during data acquisition, the effective size of the scanned object that determines the Nyquist criterion can be reduced. Additionally, unwanted signals originating from outside the FOV (e.g., aliasing streak artifacts) can be effectively avoided. The mitigation of the Nyquist criterion owing to VSS-PA was theoretically described and confirmed through numerical simulations and phantom and human lung experiments. These experiments further showed that the aliasing streak artifacts were nearly suppressed. © 2023, CC BY-NC-ND.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

Algorithm-Hardware Co-Design for Wearable BCIs: An Evolution from Linear Algebra to Transformers

Algorithm-Hardware Co-Design for Wearable BCIs: An Evolution...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Sunyoung Park Wooseok Byun Minkyu Je Ji-Hoon Kim Department of Electronic and Electrical Engineering Ewha Womans University Seoul Republic of Korea Graduate Program in Smart Factory Ewha Womans University Seoul Republic of Korea SAPEON Korea Inc Seongnam Republic of Korea School of Electrical Engineering KAIST Daejeon Republic of Korea

ISBN: (数字)9798350330991

ISBN: (纸本)9798350331004

Recent advancements in brain-computer interface (BCI) technology for steady-state visual evoked potential (SSVEP)-based target identification have shifted from traditional linear algebra (LA) techniques to more sophisticated neural network (NN) approaches, driven by their increased accuracy and consistent performance across different subjects. However, adopting NN-based algorithms has introduced complexities in wearable BCI systems, mainly due to their extensive parameter sets that demand significant memory capacity. Moreover, the computational intensity of these models requires reevaluating hardware architectures. Additionally, the advent of Transformer-based models has further advanced the state of the art, providing even higher accuracy and reduced variability in cross-subject performance, placing greater demands on hardware resources. This paper provides an overview of recent algorithmic progress in SSVEP-based target identification. Also, it proposes considerations for the hardware architecture needed to efficiently support the computation of cutting-edge Transformer-based models in wearable BCIs from the perspective of algorithm-hardware co-design.

关键词： Visualization Accuracy Computational modeling Computer architecture Artificial neural networks Linear algebra Transformers

来源：评论

学校读者我要写书评

暂无评论

Feasibility Study of Finger Interface for Miniature Surgical Instruments

Feasibility Study of Finger Interface for Miniature Surgical...

引用

Telepresence, IEEE Conference on

作者： Serin Cha Sebin Kim Seok Chang Ryu BioRobotics Laboratory Department of Mechanical and Biomedical Engineering Graduate Program in Smart Factory Ewha Womans University Seoul South Korea BioRobotics Laboratory Department of Mechanical and Biomedical Engineering Ewha Womans University Department of Mechanical and Biomedical Engineering BioRobotics Laboratory Ewha Womans University

ISBN: (数字)9798331528249

ISBN: (纸本)9798331528256

This paper presents a study on the design of a finger interface to improve the teleoperation of a miniaturized surgical instrument with a bendable distal section. A unique design principle employing the kinematic similarity between the human motion and the follower robot has been proposed for such instruments, which may result in embodied teleoperation, enhancing the overall telepresence experience. According to the principle, a design for an index finger interface was proposed, consisting of a sub-unit measuring finger motion and a handle. When the interface is connected to a robotic platform, it can control the entire tool motion in two separate ways: distal bending by the sub-unit and overall tool motion by the handle. A human subject test was conducted for trajectory-following tasks in a virtual environment, and their performance score was quantified for analysis of the learning curve. Based on the satisfactory learning rate of 75.78% for all nine subjects, the proposed finger interface could be a promising interface for a miniature surgical instrument with a long bendable section at the distal end.

关键词： Telepresence Instruments Fingers Virtual environments Kinematics Bending Motion measurement Robots

来源：评论

学校读者我要写书评

暂无评论

Real-time temperature correction for magnetoresistive biosensors integrated with temperature modulator

引用

Biosensors and Bioelectronics: X 2023年 14卷 100356页

作者： Kim, Songeun Wang, Shan X. Lee, Jung-Rok Division of Mechanical and Biomedical Engineering Ewha Womans University Seoul03760 Korea Republic of Graduate Program in Smart Factory Ewha Womans University Seoul03760 Korea Republic of Department of Materials Science and Engineering Stanford University StanfordCA93405 United States Department of Electrical Engineering Stanford University StanfordCA93405 United States

Magnetoresistance-based biosensors utilize changes in electrical resistance upon varying magnetic fields to measure biological molecules or events involved with magnetic tags. However, electrical resistance fluctuates with temperature. To decouple unwanted temperature-dependent signals from the signal of interest, various methods have been proposed to correct signals from magnetoresistance-based biosensors. Yet, there is still a need for a temperature correction method capable of instantaneously correcting signals from all sensors in an array, as multiple biomarkers need to be detected simultaneously with a group of sensors in a central laboratory or point-of-care setting. Here we report a giant magnetoresistive biosensor system that enables real-time temperature correction for individual sensors using temperature correction coefficients obtained through a temperature sweep generated by an integrated temperature modulator. The algorithm with individual temperature correction coefficients obviously outperformed that using the average temperature correction coefficient. Further, temperature regulation did not eliminate temperature-dependent signals completely. To demonstrate that the method can be used in biomedical applications where large temperature variations are involved, binding kinetics experiments and melting curve analysis were conducted with the temperature correction method. The method successfully removed all temperature-dependent artifacts and thus produced more precise kinetic parameters and melting temperatures of DNA hybrids. © 2023 The Authors

关键词： Kinetics

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：