检索结果-内蒙古大学图书馆

International Workshop on Wearable and Implantable Body Sensor Networks (BSN)

作者： Lohith Chatragadda Adrian Valdez Franco Kunal Mankodiya Matthew J. Delmonico Dhaval Solanki Interdisciplinary Neuroscience Program University of Rhode Island Kingston RI USA Department of Kinesiology University of Rhode Island Kingston RI USA Department of Electrical Computer and Biomedical Engineering University of Rhode Island Kingston RI USA

An increasing number of people are being diagnosed with neurodegenerative diseases every year. One of the aims of digital health is to provide innovative solutions for rehabilitation or pre-diagnosis of these diseases. In this vein, e-textiles can allow for the construction of flexible and comfortable devices to record biosignals and develop novel rehabilitation platforms. In this study, an e-textile forearm band was constructed to acquire an electromyogram (EMG: a muscle response to a nerve’s stimulation of the muscle) from the flexor muscles of the hand to detect hand grips/squeezes. A light and portable data acquisition module, as well as a computer-based virtual reality game (controlled by the acquired EMG signal) were designed. Our pilot study showed that the system is reliable in detecting hand squeezes in both 6 healthy participants (F-score: 0.88) and 6 participants with Parkinson’s disease (F-score: 0.88). Participants also rated the system to be enjoyable, comfortable, and easy to use.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Diversity and Suitability of the State-of-the-Art Wearable and Wireless EEG Systems Review

引用

IEEE Journal of biomedical and Health Informatics 2023年第8期27卷 3830-3843页

作者： He, Congying Chen, Yu-Yi Phang, Chun-Ren Stevenson, Cory Chen, I-Ping Jung, Tzyy-Ping Ko, Li-Wei Institute of Bioinformatics and Systems Biology National Yang Ming Chiao Tung University Hsinchu30010 Taiwan Institute of Applied Arts National Yang Ming Chiao Tung University Hsinchu30010 Taiwan International Ph.D. Program in Interdisciplinary Neuroscience National Yang Ming Chiao Tung University Hsinchu30010 Taiwan Institute for Neural Computation and Institute of Engineering in Medicine University of California San DiegoCA90093 United States National Yang Ming Chiao Tung University Hsinchu30010 Taiwan Institute of Electrical and Control Engineering Department of Electronics and Electrical Engineering Department of Biological Science and Technology National Yang Ming Chiao Tung University Hsinchu30010 Taiwan Department of Biomedical Science and Environment Biology Drug Development and Value Creation Research Center Kaohsiung Medical University Kaohsiung80708 Taiwan

Wireless electroencephalography (EEG) systems have been attracting increasing attention in recent times. Both the number of articles discussing wireless EEG and their proportion relative to general EEG publications have increased over years. These trends indicate that wireless EEG systems could be more accessible to researchers and the research community has recognized the potential of wireless EEG systems. To explore the development and diverse applications of wireless EEG systems, this review highlights the trends in wearable and wireless EEG systems over the past decade and compares the specifications and research applications of the major wireless systems marketed by 16 companies. For each product, five parameters (number of channels, sampling rate, cost, battery life, and resolution) were assessed for comparison. Currently, these wearable and portable wireless EEG systems have three main application areas: consumer, clinical, and research. To address this multitude of options, the article also discussed the thought process to find a suitable device that meets personalization and use cases specificities. These investigations suggest that low-price and convenience are key factors for consumer applications, wireless EEG systems with FDA or CE-certification may be more suitable for clinical settings, and devices that provide raw EEG data with high-density channels are important for laboratory research. This article presents an overview of the current state of the wireless EEG systems specifications and possible applications and serves as a guide point as it is expected that more influential and novel research will cyclically promote the development of such EEG systems. © 2023 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Reduction of Reflected Light on Fluorescence Emission for Indocyanine Green

引用

Journal of engineering and Science in Medical Diagnostics and Therapy 2022年第1期5卷 011004页

作者： Kwon, So Yoon Yoon, Ki-Cheol Kim, Kwang Gi Interdisciplinary Program in Bioengineering Seoul National University Seoul08826 Korea Republic of Medical Devices R&D Center Gachon University Gil Medical Center 774 beon-gil Namdong-daero Namdong-gu Incheon21565 Korea Republic of Department of Biomedical Engineering College of Medicine Gachon University 38-13 Dokjom-ro 3 Namdong-gu Incheon21565 Korea Republic of Department of Biomedical Engineering College of Health Science Gachon University 191 Hambakmoero Yeonsu-gu Incheon21936 Korea Republic of Gachon University 38-13 3 Dokjom-ro Namdong-gu Incheon21565 Korea Republic of

Inside the brain tumor, the blood vessels are intricately composed, and the tumors and blood vessels are similar in color. Therefore, when observing tumors and blood vessels with the naked eye or a surgical microscope, it is difficult to distinguish between tumors and blood vessels. Fluorescence staining with indocyanine green (ICG) is performed to distinguish between brain tumors and blood vessels using a surgical microscope. However, when observing the blood circulation state of a tumor or blood vessel through a surgical microscope, light reflection occurs from the camera. In the process of observing the state of the blood vessel, due to the occurrence of light reflection, an obstruction phenomenon in which the observation field is blocked by the blood vessel of the object to be observed occurs. Therefore, it is difficult to diagnose the vascular condition. In this experiment, the 780 nm light-emitting diode (LED) was irradiated to the ICG phantom, and then, when the fluorescence expression image was observed, the polarizing filter such as circular polarized light (CPL) filter and linear polarized light (LPL) filter was inserted into the camera, and the reflected light was reduced. Therefore, it is possible to reduce the reflected light from the fluorescence expression image by using a polarizing filter, and it is expected to be applicable to surgery and diagnostic fields of cancer such as surgery. Copyright © 2022 by ASME.

关键词： Microscopes

来源：评论

学校读者我要写书评

暂无评论

AI In Healthcare: Using Bayesian Networks To Predict Response To Immune Checkpoint Blockades

AI In Healthcare: Using Bayesian Networks To Predict Respons...

引用

National Conference on Radio Science (NSRC)

作者： Ahmed H. Saadawy Aly F. Hissam Eman Badr Omar M. Fahmy Biomedical Sciences Program Zewail City of Science and Technology Giza Egypt Faculty of Computers and Artificial Intelligence Cairo University Giza Egypt Omar Mamdouh Fahmy Electrical Engineering Dept. Badr University in Cairo Giza Egypt

Cancer remains a leading cause of death worldwide, with its heterogeneous and patient-specific nature complicating treatment. Immunotherapy, especially immune checkpoint blockades (ICB), shows promising potential by reactivating the immune system to detect and destroy cancer cells. However, their effectiveness largely depends on the patient’s clinical and molecular characteristics, making them unsuitable for everyone. This highlights the importance of developing predictive and interpretable models that could distinguish potential responders from non-responders. This study aims to utilize gene expression data to predict patients’ responses to ICB and identify key genes whose expression is associated with treatment outcome using probabilistic Bayesian networks (BNs). To address the high-dimensional nature of gene expression data, we propose and compare the use of machine learning-based feature selection (FS) and clustering by weighted gene co-expression network analysis (WGCNA). To our knowledge, this is the first study to apply BNs along with FS and WGCNA dimensionality reduction techniques to tackle ICB response using transcriptomic data. We achieved a maximal classification accuracy of 75% and identified eight genes and two gene clusters directly influencing ICB response. These results may offer more biological insights and mechanisms underlying ICB response. The proposed pipeline will contribute to guiding treatment decisions, minimizing harmful side effects, and reducing the financial costs associated with ineffective treatments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DiffEGG: Diffusion-Driven Edge Generation as a Pixel-Annotation-Free Alternative for Instance Annotation

arXiv

引用

arXiv 2025年

作者： Jo, Sanghyun Lee, Ziseok Lee, Wooyeol Kim, Kyungsu OGQ Seoul Korea Republic of Department of Biomedical Sciences Seoul National University Seoul Korea Republic of Department of Computer Science and Engineering Seoul National University Seoul Korea Republic of School of Transdisciplinary Innovations Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of

Achieving precise panoptic segmentation heavily relies on pixel-wise instance annotations, but obtaining such datasets is costly. Unsupervised instance segmentation (UIS) eliminates annotation requirements but struggles with adjacent instance merging and single-instance fragmentation, largely due to the limitations of DINO-based backbones, which lack strong instance separation cues. Weakly-supervised panoptic segmentation (WPS) reduces annotation costs by using sparse labels (e.g., points, boxes), yet these annotations remain expensive and introduce human bias and boundary errors, limiting performance. To address these challenges, we propose DiffEGG (Diffusion-Driven EdGe Generation), a fully annotation-free method that extracts instance-aware features from pretrained diffusion models to generate precise instance edge maps. DiffEGG fundamentally differs from prior UIS and WPS approaches by leveraging pretrained diffusion models as a backbone. Unlike DINO-based UIS methods, diffusion models inherently capture fine-grained, instance-aware features, enabling more precise boundary delineation. DiffEGG further enhances edge connectivity through self-supervised fine-tuning, progressively improving instance separation. For WPS, DiffEGG completely eliminates annotation costs and human bias by operating without any form of manual supervision, addressing the key limitations of prior best methods. Additionally, we introduce RIP, a post-processing technique that fuses DiffEGG’s edge maps with segmentation masks in a task-agnostic manner. This broad applicability allows DiffEGG to be seamlessly integrated into various segmentation frameworks. When applied to UIS, DiffEGG and RIP achieve an average +4.4 AP improvement over prior best UIS methods. When combined with weakly-supervised semantic segmentation (WSS), DiffEGG enables WPS without instance annotations, outperforming prior best point-supervised WPS methods by +1.7 PQ. These results demonstrate that DiffEGG’s edge maps serv

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Few-cycle THz wave manipulation with a high degree of freedom via f-t modulation

引用

Optics Letters 2023年第4期48卷 1016-1019页

作者： Wei, Hao-Keng Ito, Hironori Huang, Wei-Hong Chen, Zai-Wen Ko, Ying-Kuan Tu, Chien-Ming Yabushita, Atsushi Misawa, Kazuhiko Luo, Chih-Wei Department of Electrophysics National Yang Ming Chiao Tung University Hsinchu30010 Taiwan Graduate Faculty of Interdisciplinary Research Faculty of Engineering University of Yamanashi 4-3-11 Takeda Kofu Yamanashi400-8511 Japan Department of Applied Physics Tokyo University of Agriculture and Technology 2-24-16 Naka-cho Koganei Tokyo184-8588 Japan Department of Biomedical Engineering Tokyo University of Agriculture and Technology 2-24-16 Naka-cho Koganei Tokyo184-8588 Japan National Science and Technology Council Taiwan Institute of Physics Center for Emergent Functional Matter Science National Yang Ming Chiao Tung University 30010 Taiwan National Synchrotron Radiation Research Center Hsinchu30076 Taiwan Department of Physics University of Washington SeattleWA98195 United States

THz waves have been intensively applied in many fields, e.g., spectroscopy, imaging, and communications. However, owing to the rarity of available techniques for manipulating circularly polarized few-cycle THz waves on picosecond time scales, most of the current studies are conducted with linearly polarized THz waves. Here we demonstrate circularly polarized (CP) THz (dual) pulses generated by a polarization-twisting pulse/dual pulse (PTP/PTDP). The polarization-twisting optical dual pulses can be generated via a modified Michelson interferometer (MI) system, which provides the ability to control the frequency, helicity, and time interval of the dual pulses arbitrarily and individually. Such a novel, to the best of our knowledge, modulation technique shows huge potential for applications, not only in imaging and spectroscopy but also in next-generation communications. © 2023 Optica Publishing Group.

关键词： Degrees of freedom (mechanics)

来源：评论

学校读者我要写书评

暂无评论

Meaningful human control: actionable properties for AI system development

引用

AI and Ethics 2022年第1期3卷 241-255页

作者： Cavalcante Siebert, Luciano Lupetti, Maria Luce Aizenberg, Evgeni Beckers, Niek Zgonnikov, Arkady Veluwenkamp, Herman Abbink, David Giaccardi, Elisa Houben, Geert-Jan Jonker, Catholijn M. van den Hoven, Jeroen Forster, Deborah Lagendijk, Reginald L. AiTech Interdisciplinary Research Program on Meaningful Human Control Delft University of Technology Delft The Netherlands Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft The Netherlands Faculty of Industrial Design Engineering Delft University of Technology Delft The Netherlands Faculty of Mechanical Maritime and Materials Engineering Delft University of Technology Delft The Netherlands Faculty of Technology Policy and Management Delft University of Technology Delft The Netherlands

How can humans remain in control of artificial intelligence (AI)-based systems designed to perform tasks autonomously? Such systems are increasingly ubiquitous, creating benefits - but also undesirable situations where moral responsibility for their actions cannot be properly attributed to any particular person or group. The concept of meaningful human control has been proposed to address responsibility gaps and mitigate them by establishing conditions that enable a proper attribution of responsibility for humans; however, clear requirements for researchers, designers, and engineers are yet inexistent, making the development of AI-based systems that remain under meaningful human control challenging. In this paper, we address the gap between philosophical theory and engineering practice by identifying, through an iterative process of abductive thinking, four actionable properties for AI-based systems under meaningful human control, which we discuss making use of two applications scenarios: automated vehicles and AI-based hiring. First, a system in which humans and AI algorithms interact should have an explicitly defined domain of morally loaded situations within which the system ought to operate. Second, humans and AI agents within the system should have appropriate and mutually compatible representations. Third, responsibility attributed to a human should be commensurate with that human’s ability and authority to control the system. Fourth, there should be explicit links between the actions of the AI agents and actions of humans who are aware of their moral responsibility. We argue that these four properties will support practically minded professionals to take concrete steps toward designing and engineering for AI systems that facilitate meaningful human control.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LoraMap: Harnessing the Power of LoRA Connections

arXiv

引用

arXiv 2024年

作者： Park, Hyeryun Kwak, Jeongwon Jang, Dongsuk Park, Sumin Choi, Jinwook Interdisciplinary Program for Bioengineering Graduate School Seoul National University Korea Republic of Integrated Major in Innovative Medical Science Graduate School Seoul National University Korea Republic of Department of Biomedical Engineering College of Medicine Seoul National University Korea Republic of Medical Research Center Institute of Medical and Biological Engineering Seoul National University Korea Republic of

Fact-checking techniques can mitigate hallucinations in Large Language Models (LLMs), a prominent issue in specialized domains. As parameter-efficient techniques such as Low-Rank Adaptation (LoRA) can overcome substantial computational overhead, some studies have explored the integration of multiple LoRAs. While previous studies focus on parallel integration, this paper investigates methods to establish connections among multiple LoRAs. We create three reasoning datasets tailored to fact-checking and fine-tune individual LoRAs, allowing them to view and reason from diverse perspectives. Then, we explore strategies for allocating these reasoning LoRAs and introduce LoraMap, an approach to map connections between them. The results of the fact-checking task demonstrate that the performance of LoraMap is superior to LoraHub, an existing method for integrating LoRAs. LoraMap also outperforms with significantly fewer trainable parameters than LoraConcat, which concatenates LoRAs and further fine-tunes them. Copyright © 2024, The Authors. All rights reserved.

关键词： Problem oriented languages

来源：评论

学校读者我要写书评

暂无评论

Gamma-ray Probe Endoscope using Phoswich structure & Pulse Shape Discrimination system

Gamma-ray Probe Endoscope using Phoswich structure & Pulse S...

引用

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： M. Park H. Lee S. Song J. Hwang C. Park K. Lee J.-Y. Yeom Department of Bioengineering Korea University Seoul Republic of Korea Interdisciplinary Program in Precision Public Health Korea University Seoul Republic of Korea Global Health-Tech Research Center Korea University Seoul Republic of Korea School of Biomedical Engineering Korea University Seoul Republic of Korea

ISBN: (数字)9798350388152

ISBN: (纸本)9798350388169

This study focuses on separation of gamma-ray signals, when a high density BGO is used in place of a light guide. The purpose of utilizing BGO instead of the light guide is to shield the GAGG scintillator from background radiation while also acting as a light guide. By using a 1.5mm BGO scintillator, over 87% of side/rear gamma rays were found to interact with BGO rather than GAGG. Gamma radiation interacting with GAGG from the front and the signals interacting with BGO from the side/rear can be separated using our pulse shape discrimination (PSD) method. In addition, unlike the conventional gamma-ray PSD method that processes with raw signals, our method can separate signals processed through CSA using rising time discrimination. By shielding side/rear gamma rays, the structural/spatial limitations of detectors such as the 3 mm diameter flexible gamma probe endoscope being developed by our research team, which limits the use shielding materials, can be overcome.

关键词： Microwave integrated circuits Scintillators Shape Endoscopes Semiconductor detectors Gamma-rays Probes

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Cs3Cu2I5 Perovskite Scintillator Grown by Seedless SEST Method

Performance Evaluation of Cs3Cu2I5 Perovskite Scintillator G...

引用

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： S. Song J. Seo M. Park J.-Y. Yeom Department of Bioengineering Korea University Seoul Republic of Korea Interdisciplinary Program in Precision Public Health Korea University Seoul Republic of Korea Department of Health and Safety Convergence Science Korea University Seoul Republic of Korea School of Biomedical Engineering Korea University Seoul Republic of Korea

ISBN: (数字)9798350388152

ISBN: (纸本)9798350388169

In this study, we utilized the seedless Slow evaporation solution growth technique (SEST) method to grow Cs 3 Cu 2 I 5 , a 0-D perovskite scintillator material, at room temperature. The growth was conducted under conditions of 23°C temperature and 40% humidity for 10 days, resulting in obtaining multiple crystals of 5 mm in size. Using single crystal Cs 3 Cu 2 I 5 detectors grown in our lab, we evaluated its performance using radioactive isotopes ${ }^{137} \mathrm{Cs},{ }^{241} \mathrm{Am},{ }^{54} \mathrm{Mn},{ }^{60} \mathrm{Co},{ }^{22} \mathrm{Na}$, and ${}^{57}\mathrm{Co}$, and acquired energy resolutions of 8.55%, 23.35%, 7.59%, 6.49%, 9.38%, and 16.8%, respectively. In comparison with polycrystalline counterparts, single crystal Cs 3 Cu 2 I 5 exhibited superior performance, although both demonstrated excellent characteristics. By comparison, measurement using GAGG:Ce as a reference scintillator with the same setup showed an energy resolution of 10.00 %.

关键词： Temperature measurement Performance evaluation Semiconductor device measurement Microwave integrated circuits Scintillators Temperature Semiconductor detectors

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：