检索结果-内蒙古大学图书馆

3rd International Congress of biomedical engineering and Bioengineering, CIIBBI 2024

作者： Rojas, Ivette Sierra, Katherin Tocora, Angelica Maria Rojas Calderon, Luis Buitrago, Natalia Orjuela-Canon, Alvaro D. Biomedical Engineering Program Universidad Del Rosario - Escuela Colombiana de Ingeniería Julio Garavito D.C. Bogota Colombia School of Medicine and Health Sciences Universidad Del Rosario D.C. Bogota Colombia

ISBN: (纸本)9798331532352

Colombian sign language (CSL) have shown different advances to automatize the translation and communication between deaf or disabling hearing people and speakers. However, these current efforts are oriented on classification of static signs, mainly. The present proposal implements the use a convolutional neural network (CNN) that also involves the use an architecture of the long short-term memory (LSTM) one. This allowed to include the time dependent information for dynamic signs like a sequence data. For this, a dataset was created with greetings for the CSL through the recording videos of signs. The methodology used the MediaPipe tool for feature extraction, which was used to represent relevant points from fingers articulation for frames of the videos. CNN-LSTM was applied with the joint points information for the classification. Results show that 71.50 % (+/-4.33%) for five greetings classification, employing a crossvalidation and early stopping criteria for the training of models. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Deep Learning for Final Infarct Prediction Using Acute Stroke CT Perfusion Data 4th

Spatio-Temporal Deep Learning for Final Infarct Prediction U...

引用

4th International Workshop on Imaging and Treatment Challenges, SWITCH 2024, and 6th International Challenge on Ischemic Stroke Lesion Segmentation Challenge, ISLES 2024, Held in Conjunction with Medical Image Computing and Computer Assisted Intervention, MICCAI 2024

作者： Amador, Kimberly Winder, Anthony J. Forkert, Nils D. Biomedical Engineering Graduate Program University of Calgary Calgary Canada Department of Radiology University of Calgary Calgary Canada Hotchkiss Brain Institute University of Calgary Calgary Canada Alberta Children’s Hospital Research Institute University of Calgary Calgary Canada

ISBN: (纸本)9783031811005

Accurate prediction of the tissue outcome is crucial for guiding treatment decisions in acute ischemic stroke (AIS). Spatio-temporal (4D) Computed Tomography Perfusion (CTP) provides detailed insights into cerebral blood flow dynamics, which are essential for predicting final infarct regions. However, its high-dimensional and noisy nature presents challenges for direct prediction. In this study, we evaluate a deep learning model that fully leverages 4D CTP data for predicting tissue outcomes. The model integrates a shared-weight convolutional neural network (CNN) encoder, a Transformer encoder, and a CNN decoder to capture both spatial and temporal dependencies within the data. We evaluated this approach on a multicenter dataset of 143 patients from the ISLES 2024 challenge. The results reveal a Dice score of 0.20, an absolute volume difference of 17 ml, a mean lesion count difference of 19, and a lesion-wise F1-Score of 0.02, underscoring both the potential and challenges of directly utilizing 4D CTP data for final infarct prediction. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Design and Validation of a Prosthetic Foot Adaptable to Sagittal Plane Ground Irregularity

Design and Validation of a Prosthetic Foot Adaptable to Sagi...

引用

3D Analysis of Human Movement (3DAHM), International Symposium on

作者： Marco Lagones Victoria E. Abarca Dante A. Elias Biomedical Engineering Program Pontificia Universidad Católica del Perú Biomedical Engineering Program Universidad Peruana Cayetano Heredia Lima Peru Biomechanics and Applied Robotics Research Laboratory Pontificia Universidad Católica del Perú Lima Peru

ISBN: (数字)9798331521738

ISBN: (纸本)9798331509842

Amputation involves the removal of a limb or part of it. In the case of the lower extremity, amputation affects the ankle joint and the metatarsophalangeal and intertarsal joints, improving the foot's adaptability on uneven terrain. Therefore, based on state-of-the-art technology that does not address the other joints of the foot to a large extent, a prosthetic foot has been developed that integrates the support structure of the foot through a foot arch with an extension analogous to the forefoot and an elastic element that mimics the plantar fascia that deforms against obstacles and provides stability to the prosthetic arch foot. The work addresses the design of the prosthetic foot from its design to its prototyping and validation, where the foot was shown to withstand the loads recommended for the P5 category of the ISO 22675 standard and to provide a return energy equal to 95.72%, 77.13%, and 90.21 %, in the heel strike, mid-stance, and toe-off stages, respectively. In addition to showing linear stiffness properties (66.95 kN /m) and torsional stiffness properties(2.05 kN.m/rad) in the forefoot analog element, values that are comparable with those recorded in commercial tests such as LP Variflex categories 7 and 8.

关键词： Three-dimensional displays Protocols Prototypes Amputation Stability analysis Standards Foot Prosthetics Load modeling Testing

来源：评论

学校读者我要写书评

暂无评论

Systematic designs of single metal compounds synthesized using ammonia fluoride-based complex as structure directing agents for energy storage

引用

Journal of Colloid and Interface Science 2023年第PartA期652卷 294-304页

作者： Kuo, Tsung-Rong Zher Yu, You Wu, Chung-Hsien Lee, Pin-Yan Kongvarhodom, Chutima Chen, Hung-Ming Husain, Sadang Yougbaré, Sibidou Lin, Lu-Yin International PhD Program in Biomedical Engineering College of Biomedical Engineering Taipei Medical University Taipei11031 Taiwan Graduate Institute of Nanomedicine and Medical Engineering College of Biomedical Engineering Taipei Medical University Taipei11031 Taiwan Department of Chemical Engineering and Biotechnology National Taipei University of Technology Taipei Taiwan Department of Chemical Engineering King Mongkut's University of Technology Thonburi 126 Pracha-u-thit Toong-kru Bangkok10140 Thailand Gingen technology Co. LTD. Rm. 7 10F. No.189 Sec. 2 Keelung Rd. Xinyi Dist. Taipei11054 Taiwan Department of Physics Faculty of Mathematics and Natural Science Lambung Mangkurat University Banjarmasin70124 Indonesia /Nanoro 03 B.P 7192 Ouagadougou 03 Burkina Faso

Tailoring morphology and composition of metal organic frameworks (MOF) can improve energy storage by establishing high surface area, large porosity and multiple redox states. Structure directing agents (SDA) is functional of designing surface properties of electroactive materials. Ammonium fluoride has functional abilities for designing MOF derivatives with excellent energy storage abilities. Systematic design of MOF derivatives using ammonia fluoride-based complex as SDA can essentially create efficient electroactive materials. Metal species can also play significant roles on redox reactions, which are the main energy storage mechanism for battery-type electrodes. In this work, 2-methylimidazole, two novel SDAs of NH4BF4 and NH4HF2, and six metal species of Al, Mn, Co, Ni, Cu and Zn are coupled to synthesize MOF derivatives for energy storage. Metal species-dependent compositions including hydroxides, oxides, and hydroxide nitrates are observed. The nickel-based derivative (Ni-HBF) shows the highest specific capacitance (CF) of 698.0F/g at 20 mV/s, due to multiple redox states and advanced flower-like surface properties. The diffusion and capacitive-control contributions of MOF derivatives are also analyzed. The battery supercapacitor hybrid with Ni-HBF electrode shows a maximum energy density of 27.9 Wh/kg at 325 W/kg. The CF retention of 170.9% and Coulombic efficiency of 93.2% are achieved after 10,000 cycles. © 2023 Elsevier Inc.

关键词： Supercapacitor

来源：评论

学校读者我要写书评

暂无评论

Coevolution of Myoelectric Hand Control under the Tactile Interaction among Fingers and Objects

引用

Cyborg and Bionic Systems 2022年第1期2022卷 285-302页

作者： Yuki Kuroda Yusuke Yamanoi Shunta Togo Yinlai Jiang Hiroshi Yokoi Joint Doctoral Program for Sustainability Research Graduate School of Informatics and Engineering The University of Electro-CommunicationsTokyoJapan Department of Mechan ical and Intelligent System Engineering Graduate School of Informatics and Engineering The University of Electro Communications TokyoJapan Center for Neuroscience and Biomedical Engineering The University of Electro Communications TokyoJapan Bejing Innovation Center for Inelligent Robots and Systems BeijingChina

The usability of a prosthetic hand difers significantly from that of a real ***,the complexity of manipulation increases as the number of degrees of freedom to be controlled increases,making manipulation with biological signals extremely *** overcome this problem,users need to select a grasping posture that is adaptive to the object and a stable grasping method that prevents the object from *** previous studies,these have been left to the operating skills of the user,which is extremely difficult to *** this study,we demonstrate how stable and adaptive grasping can be achieved according to the object regardless of the user's operation *** required grasping technique is achieved by determining the correlation bet ween the motor output and each sensor through the interaction between the prosthetic hand and the surrounding stimuli,such as myoelectricity,sense of touch,and grasping *** agents of the 16 DOF robot hand were trained with the myoelectric signals of six participants,including one child with a congenital forearm ***,each agent could open and close the hand in response to the myoeletric stimuli and could accomplish the object pickup *** the tasks,the agents successfully identified grasping patterns suitable for practical and stable positioning of the *** addition,the agents were able to pick up the object in a similar posture regardless of the partiipant,suggesting that the hand was optimized by evolutionary computation to a posture that prevents the object from being dropped.

关键词： robot Objects overcome

来源：评论

学校读者我要写书评

暂无评论

Stellate silicon microneedles for rapid point-of-care melanoma exosome isolation and detection via a lateral flow assay

引用

Biosensors and Bioelectronics 2025年 285卷 117560页

作者： Smith, Scott M. Kumari, Abha Marvar, Joseph P. Onukwugha, Nna-Emeka Kang, Yoon-Tae Nagrath, Sunitha Department of Chemical Engineering and Biomedical Engineering Biointerfaces Institute Translational Oncology Program University of Michigan Ann ArborMI48109 United States

Melanoma is the most aggressive type of skin cancer with high mortality rates. Early diagnosis is crucial because it significantly improves treatment outcomes, but conventional methods relying on dermoscopy and lesion biopsy have limitations in accuracy during early stages and are invasive. Liquid biopsies offer a minimally invasive alternative, particularly for routine screening. The abundance of cancer cell-driven extracellular vesicles in interstitial fluid can be utilized for point-of-care cancer diagnostics. Here, we developed a stellate silicon microneedle patch, the ExoPatch, coated with Annexin V functionalized hydrogel to isolate melanoma-specific exosomes. The ExoPatch captures exosomes directly from the skin, followed by dissolution of the hydrogel to release the exosomes, which are then detected using a lateral flow immunoassay specific to melanoma markers (MCAM and MCSP). After validating with cell line derived extracellular vesicles and testing with mouse tissue, the ExoPatch isolated 11.5 times more protein from melanoma tissue compared to healthy tissue. Additionally, the ExoPatch effectively distinguished between melanoma and healthy tissues, with its specificity confirmed through Western Blot and electron microscopy analysis. The ExoPatch with melanoma mouse samples produced a 3.5-fold higher signal in the lateral flow immunoassay compared to that of healthy controls. The ExoPatch presents a promising point-of-care diagnostic tool for melanoma, offering significant advantages in terms of rapidness, minimal invasiveness, and ease of use. It has the potential to enhance early detection and routine monitoring in melanoma patients, ultimately improving patient outcomes by reducing the reliance on traditional, invasive biopsies. © 2025

关键词： Biopsy

来源：评论

学校读者我要写书评

暂无评论

HIFU thermal lesion difference between simulated human phantom and tissue-mimicking phantom 24

HIFU thermal lesion difference between simulated human phant...

引用

24th International Congress on Acoustics, ICA 2022

作者： Kim, Seong Chan Choi, Min Joo Jeju National University Interdisciplinary Postgraduate Program of Biomedical Engineering Korea Republic of Jeju National University School of Medicine Korea Republic of

Most HIFU procedures use the thermal effect of ultrasound, and information about temperature is directly related to the effect and side effects of the procedure. In the case of the human body, there are complex structures including bones around the target tissue to be irradiated with ultrasound. Thermal lesions in human tissue differ from thermal lesions in ideal conditions due to the standing waves generated by the target tissue and surrounding structures. If a high temperature rise is induced at a location other than the focal point of the HIFU, side effects of the procedure and patient safety may be threatened. In this study, two conditions were simulated, a tissue-mimicking phantom and a human body, in order to compare differences in thermal lesions. In the simulation results, the shape of the thermal lesion generated in the two conditions was not the same, and there was a difference in the location where the temperature was increased. © ICA *** rights reserved

关键词： HIFU Human phantom Thermal lesion Tissue mimicking phantom

来源：评论

学校读者我要写书评

暂无评论

Using electroencephalography signals to explore the influence of Zentangle on meditation and mindfulness 9

Using electroencephalography signals to explore the influenc...

引用

9th International Conference on Applied System Innovation, ICASI 2023

作者： Usman, Muhammad Lin, Chun-Ling Ming Chi University of Technology International Ph.D Program in Innovative Technology of Biomedical Engineering and Medical Devices New Taipei City Taiwan Ming Chi University of Technology Department of Electrical Engineering New Taipei City Taiwan

ISBN: (纸本)9798350398380

Fifteen novices completed a Zentangle task while their brain activity was measured with electroencephalography (EEG) and their concentration emotional state, stress, and anxiety levels were evaluated with questionnaires. The study found increased activity in theta, alpha, beta, and gamma ranges associated with relaxation, focus, and mental activity. Participants reported improved concentration, emotional state, and reduced stress and anxiety levels after completing the task, suggesting the potential of Zentangle to enhance cognitive and emotional well-being. © 2023 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Spectral Learning of Shared Dynamics Between Generalized-Linear Processes 38

Spectral Learning of Shared Dynamics Between Generalized-Lin...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Oganesian, Lucine L. Sani, Omid G. Shanechi, Maryam M. Ming Hsieh Department of Electrical and Computer Engineering University of Southern California Los AngelesCA United States Ming Hsieh Department of Electrical and Computer Engineering Thomas Lord Department of Computer Science Alfred E. Mann Department of Biomedical Engineering Neuroscience Graduate Program University of Southern California Los AngelesCA United States

Generalized-linear dynamical models (GLDMs) remain a widely-used framework within neuroscience for modeling time-series data, such as neural spiking activity or categorical decision outcomes. Whereas the standard usage of GLDMs is to model a single data source, certain applications require jointly modeling two generalized-linear time-series sources while also dissociating their shared and private dynamics. Most existing GLDM variants and their associated learning algorithms do not support this capability. Here we address this challenge by developing a multi-step analytical subspace identification algorithm for learning a GLDM that explicitly models shared vs. private dynamics within two generalized-linear time-series. In simulations, we demonstrate our algorithm's ability to dissociate and model the dynamics within two time-series sources while being agnostic to their respective observation distributions. In neural data, we consider two specific applications of our algorithm for modeling discrete population spiking activity with respect to a secondary time-series. In both synthetic and real data, GLDMs learned with our algorithm more accurately decoded one time-series from the other using lower-dimensional latent states, as compared to models identified using existing GLDM learning algorithms. © 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

Possible solutions for oxygenation support in critically ill patients with COVID-19

引用

Research on biomedical engineering 2021年第2期37卷 389-402页

作者： de Souza, Daniel Baldoino de Oliveira Andrade, Adriano Milagre, Selma Terezinha Pereira, Adriano Alves Centre for Innovation and Technology Assessment in Health Postgraduate Program in Electrical and Biomedical Engineering Faculty of Electrical Engineering Federal University of Uberlândia Uberlândia Brazil

Purpose: Due to the large number of patients with respiratory deficiency during the COVID-19 pandemic, several governments and their respective health care services have been studying ways to complement the care provided by offering immediate solutions. In view of this, the aim of this study was to carry out a systematic review of the advantages and disadvantages of possible solutions in oxygenation support. Methods: This systematic review used the PRISMA-P methodology and sought to list alternatives in oxygenation support that are being applied and studied worldwide. A bibliographic search was conducted in the MEDLINE and Cochrane Central databases, using the keywords SARS-CoV-2, COVID19, or coronavirus;combined with extracorporeal membrane oxygenation (ECMO), mechanical ventilation, mechanical ventilation support, low-cost, anesthesia, anesthesia machine, and ventilation therapy. The records were also found in the gray literature. Results: The search found 85 publications of which 41 articles were considered after excluding duplicate articles, reading the title and summary, and reading the articles in full. The oxygenation supports identified in these publications were the following: ECMO, shared mechanical ventilator, fast or low-cost production equipment, high-flow nasal cannula (HFNC), non-invasive ventilation, and use of anesthesia equipment as a mechanical ventilator. Conclusion: This study demonstrated the importance of a trained clinical team in the application of technologies. The alternatives found for support oxygenation require a more robust clinical evaluation to demonstrate their efficacy and safety for the COVID-19 patient. © 2021, Sociedade Brasileira de Engenharia Biomedica.

关键词： Oxygenation

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：