检索结果-内蒙古大学图书馆

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

作者： Wang, Siyu Quinn, Kiara N. Slepyan, Ariel Qin, Lang Thakor, Nitish V. Johns Hopkins Whiting School of Engineering Department of Biomedical Engineering BaltimoreMD21218 United States Johns Hopkins Whiting School of Engineering Department of Electrical and Computer Engineering BaltimoreMD21218 United States

ISBN: (纸本)9798350371499

Both motor unit-based control algorithms and implantable interfaces are promising approaches to improve current prosthetic limbs by allowing control of more movements. However, combining the two methods poses a challenge due to the current wireless transmission capabilities which limits the amount of data that can be processed. Capturing the motor unit requires a higher sampling rate and higher channel counts. Thus, this paper investigates a data compression strategy comprised of two independent stages: recording data reduction by selecting fewer channels to be 'active' and minimization of the transmitting data through compression with wavelet transformation. We have demonstrated a promising wavelet compression pipeline using db4, which can compress the raw EMG signal 0.63% of its original size while maintaining low WMSE error (0.109) and high heatmap reconstruction correlation coefficient (0.9741±0.972). In addition, placing high-density electrodes along the muscle fibers during channel selection while utilizing wavelet transformation can compress 99.82% of transmitted data while preserving a MCC of 0.706 ± 0.169. © 2024 IEEE.

关键词： Data compression

来源：评论

学校读者我要写书评

暂无评论

Balancing Memorization and Generalization in RNNs for High Performance Brain-Machine Interfaces 37

Balancing Memorization and Generalization in RNNs for High P...

引用

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Costello, Joseph T. Temmar, Hisham Cubillos, Luis H. Mender, Matthew J. Wallace, Dylan M. Willsey, Matthew S. Patil, Parag G. Chestek, Cynthia A. Department of Electrical and Computer Engineering Biomedical Engineering Robotics and Neurosurgery University of Michigan Ann ArborMI United States

ISBN: (纸本)9781713899921

Brain-machine interfaces (BMIs) can restore motor function to people with paralysis but are currently limited by the accuracy of real-time decoding algorithms. Recurrent neural networks (RNNs) using modern training techniques have shown promise in accurately predicting movements from neural signals but have yet to be rigorously evaluated against other decoding algorithms in a closed-loop setting. Here we compared RNNs to other neural network architectures in real-time, continuous decoding of finger movements using intracortical signals from nonhuman primates. Across one and two finger online tasks, LSTMs (a type of RNN) outperformed convolutional and transformer-based neural networks, averaging 18% higher throughput than the convolution network. On simplified tasks with a reduced movement set, RNN decoders were allowed to memorize movement patterns and matched able-bodied control. Performance gradually dropped as the number of distinct movements increased but did not go below fully continuous decoder performance. Finally, in a two-finger task where one degree-of-freedom had poor input signals, we recovered functional control using RNNs trained to act both like a movement classifier and continuous decoder. Our results suggest that RNNs can enable functional real-time BMI control by learning and generating accurate movement patterns. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Mammals

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Commercially Available Fall Detection Systems

Evaluation of Commercially Available Fall Detection Systems

引用

17th International Conference of the Association for the Advancement of Assistive Technology in Europe, AAATE 2023

作者： Hrubý, Dan Černý, Martin Department of Cybernetics and Biomedical Engineering Faculty of Electrical Engineering and Computer Science Vsb - Technical University of Ostrava Czech Republic

ISBN: (纸本)9781643684222

Falls are a serious problem in the hospital setting and home environments. However, this problem does not only affect the elderly, but also people who have had surgery, have disabling problems, have associated diagnoses (such as poor eyesight, confusion, etc.) or are dizzy or have walking aids. The aim of research was to find, compare and implement fall detectors especially for the hospital environment. This paper summarizes possible fall detectors. Various technological solutions were selected for testing, including wearable technologies as well as contactless technologies based on PIR detectors and mmWave technologies. The selected fall detectors were tested in living laboratory of *** and then in Hospital AGEL Třinec - Podlesí. The best result of the testing was the use of two Vayyar Home Care devices in one room, thus achieving a detection accuracy of 92.50 % and a sensitivity of 92.50 %. © 2023 IOS Press. All rights reserved.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

In Search for Model-Driven eXplainable Artificial Intelligence 1

引用

10th IFIP International Workshop on Artificial Intelligence for Knowledge Management, AI4KMES 2023

作者： Ligęza, Antoni Sepiolo, Dominik Faculty of Electrical Engineering Automatics Computer Science and Biomedical Engineering Department of Applied Computer Science AGH University of Krakow al. Mickiewicza 30 Krakow30-059 Poland

ISBN: (数字)9783031610691

ISBN: (纸本)9783031610684

This paper reports on ongoing and innovative research in the area of eXplainable Artificial Intelligence (XAI). A classical XAI task is considered as finding an explanation of the model generated via Machine Learning by identifying the most influential variables for local decision-making. Such an approach suffers from severe limitations. The proposed approach moves the explanatory process to a new, knowledge-level dimension. It is oriented towards Model Discovery, i.e. the internal structure and functions of the components. The concept of Model-Driven XAI is put forward and explained with examples. An experiment on Function Discovery via Grammatical Evolution is reported in brief. © IFIP International Federation for Information Processing 2024.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Harnessing dielectric metasurfaces for light-matter interactions in the infrared region 15

Harnessing dielectric metasurfaces for light-matter interact...

引用

Photonic and Phononic Properties of Engineered Nanostructures XV 2025

作者： Biswas, Shovasis Kumar Adi, Wihan Beisenova, Aidana Rosas, Samir Arvelo, Eduardo Romero Yesilkoy, Filiz Department of Electrical and Computer Engineering University of Wisconsin-Madison MadisonWI53706 United States Department of Biomedical Engineering University of Wisconsin-Madison MadisonWI53706 United States

ISBN: (纸本)9781510685024

Resonant metasurfaces exhibit exceptional subwavelength light-trapping capabilities crucial for advanced biochemical sensors and surface-enhanced spectroscopy. While mid-infrared light-matter interactions have predominantly operated in the weak coupling regime, exploring the strong coupling regime—marked by hybrid polariton states—remains underexplored. Notably, low-loss dielectric metasurfaces with quasi-bound states in the continuum (q-BIC) offer ideal platforms for coherent energy exchange between their high-Q cavities and molecular resonances. This study delves into q-BIC resonances at mid-infrared wavelengths identifying key parameters governing the transition from weak to strong coupling. Moreover, we introduce a novel transitional coupling zone where polaritons are challenging to spectrally distinguish. Additionally, we analyze molecules' transition dipole strength, damping rate, and the total number of molecules coupled to a single cavity, offering insights to optimize dielectric metasurfaces for VSC. These findings provide crucial guidelines for enhancing VSC across diverse molecular transitions, anticipating transformative impacts on polaritonic chemistry. © 2025 SPIE.

关键词： Light sensitive materials

来源：评论

学校读者我要写书评

暂无评论

Arabic text sentiment analysis and emotion classification using transformers 11

Arabic text sentiment analysis and emotion classification us...

引用

11th International Japan-Africa Conference on Electronics, Communications, and Computations, JAC-ECC 2023

作者： Mossad, Nada Mohamed, Youssef Fares, A. Zaky, Ahmed B. Alexandria21934 Egypt Benha University The Computer Systems Engineering Program Faculty of Engineering at Shoubra The Department of Electrical Engineering Egypt

ISBN: (纸本)9798350369328

Sentiment analysis and emotion classification are two crucial components of natural language processing (NLP), which have been widely explored in recent years due to their broad applications. Sentiment analysis aims to identify the polarity of written texts, ranging from positive to negative. Meanwhile, emotion classification is focused on recognizing and categorizing the emotional states expressed in the text. To achieve a deeper understanding of sentiments and emotions, it's essential to utilize models like BERT transformers that can effectively interpret the context. The process begins with data preprocessing, including tokenization and noise removal, followed by fine-tuning techniques to adapt the BERT model to the proposed tasks. We employed the BERT model on four datasets obtained from various sources, including Twitter, news websites, and restaurant reviews, where each dataset represents a distinct Arabic dialect. Our proposed model outperforms commonly used techniques like LSTM and CNN, yielding superior results. Despite the progress made, there are still challenges to overcome, such as dealing with Arabic diacritics, the new Arabic Arabizi, which uses Latin characters, and handling Arabic idioms. Further research is required to address these challenges adequately. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Retinal Blood Vessel Tracking and Diameter Estimation via Gaussian Process With Rider Optimization Algorithm

引用

IEEE Journal of biomedical and Health Informatics 2024年第3期28卷 1173-1184页

作者： Ahmad, Nehal Lai, Kuan-Ting Tanveer, M. Indian Institute of Technology Indore Simrol Department of Mathematics Indore453552 India National Taipei University of Technology Department of International Program of Electrical Engineering and Computer Science Taipei106 Taiwan National Taipei University of Technology Department of Electronic Engineering Taipei106 Taiwan

Retinal blood vessels structure analysis is an important step in the detection of ocular diseases such as diabetic retinopathy and retinopathy of prematurity. Accurate tracking and estimation of retinal blood vessels in terms of their diameter remains a major challenge in retinal structure analysis. In this research, we develop a rider-based Gaussian approach for accurate tracking and diameter estimation of retinal blood vessels. The diameter and curvature of the blood vessel are assumed as the Gaussian processes. The features are determined for training the Gaussian process using Radon transform. The kernel hyperparameter of Gaussian processes is optimized using Rider Optimization Algorithm for evaluating the direction of the vessel. Multiple Gaussian processes are used for detecting the bifurcations and the difference in the prediction direction is quantified. The performance of the proposed Rider-based Gaussian process is evaluated with mean and standard deviation. Our method achieved high performance with the standard deviation of 0.2499 and mean average of 0.0147, which outperformed the state-of-the-art method by 6.32%. Although the proposed model outperformed the state-of-the-art method in normal blood vessels, in future research, one can include tortuous blood vessels of different retinopathy patients, which would be more challenging due to large angle variations. We used Rider-based Gaussian process for tracking blood vessels to obtain the diameter of retinal blood vessels, and the method performed well on the 'STrutred Analysis of the REtina (STARE) Database' accessed on Oct. 2020 (https://***/~ahoover/stare/). To the best of our knowledge, this experiment is one of the most recent analysis using this type of algorithm. © 2013 IEEE.

关键词： Blood vessels

来源：评论

学校读者我要写书评

暂无评论

NutriA: A Responsive Web App to Monitor Nutrition and Clinical Outcomes in Inflammatory Bowel Disease Patients

NutriA: A Responsive Web App to Monitor Nutrition and Clinic...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Petrini, Giorgia Pala, Daniele Lenti, Marco Vincenzo Lepore, Federica Bosoni, Pietro Quaglini, Silvana Lanzola, Giordano University of Pavia Department of Computer Electrical and Biomedical Engineering Pavia Italy University of Pavia First Department of Internal Medicine Pavia Italy

ISBN: (纸本)9798350386226

Inflammatory Bowel Disease (IBD) is a term that includes two chronic conditions characterized by inflammation of the gastrointestinal tract, i.e., Ulcerative Colitis and Crohn's Disease. IBD can be associated to symptoms that significantly reduce quality of life and can lead to serious complications, therefore proper disease monitoring and treatment is necessary. To this end, Telemedicine has been identified as a useful tool, since it can ease the patients' burden on the management of nutrition and pharmacological treatment, and can improve the connection with the physicians. In this paper, we present NutriA, a new responsive web application for the management of IBD patients in Italy, created to assist patients with diet, medications and symptoms monitoring, optimizing the follow-ups frequency and providing direct assistance by the doctors. Besides being useful to improve the patients' well-being, NutriA is also designed to be used in a new clinical study on the effects of malnutrition on IBD treatment. © 2024 IEEE.

关键词： Telemedicine

来源：评论

学校读者我要写书评

暂无评论

A Scattered Wireless EEG Recording System

A Scattered Wireless EEG Recording System

引用

2023 IEEE biomedical Circuits and Systems Conference, BioCAS 2023

作者： Han, Yiming Zhao, Linran Stephany, Raymond G Hsieh, Ju-Chun Wang, Huiliang Jia, Yaoyao The University of Texas at Austin Department of Electrical and Computer Engineering United States The University of Texas at Austin Department of Biomedical Engineering United States

ISBN: (纸本)9798350300260

This paper presents a scattered wirelessly powered Electroencephalographic (EEG) recording system with 32 standalone devices to enable untethered, continuous, long-term EEG recording. Each device incorporates a wireless low-power EEG recording ASIC, a receiver (Rx) coil, and a hydrogel electrode in a compact cube (1.2 cm × 1.2 cm × 0.5 cm). The 32 EEG devices are wirelessly powered by a transmitter (Tx) coil array, under the control of a central control unit, through an inductive link operating at 60 MHz. The 60 MHz carrier also serves as the data link, enabling forward data transmission of user commands from the central control unit to EEG devices and back data transmission from EEG devices to the central control unit. In each EEG device, the ASIC will decode the user commands that are loaded onto the inductive link carrier by a novel synchronized pulse width demodulator at a data rate of 4 Mbps to control the ASIC digitizing the EEG signal or transmitting the EEG data. The EEG analog frontend (AFE) with a gain of 45 dB, bandpass of 0.03 Hz to 800 Hz, and input-referred noise (IRN) of 4.5 μVrms amplifies and filters EEG signals. Then, the 10-bit successive approximation register analog-to-digital converter (SAR-ADC) with an effective number of bits (ENOB) of 9.6 bits digitizes the amplified EEG signals. The backscatter-based data Tx transfers the EEG data to the central control unit via load-shift-keying (LSK) modulation at a data rate of 3.75 Mbps. The overall ASIC and the prototype of the scattered wirelessly powered EEG recording system have been successfully evaluated on human subjects. © 2023 IEEE.

关键词： EEG recording inductive link scattered structure synchronized pulse width modulation

来源：评论

学校读者我要写书评

暂无评论

Detecting Cardiovascular Disease From PPG Signals using Machine Learning 4

Detecting Cardiovascular Disease From PPG Signals using Mach...

引用

4th IEEE International Multidisciplinary Conference on engineering Technology, IMCET 2023

作者： Sadek, Tamara Ahmad, Julia Khoury, Fadi Badawe, Heba Khraiche, Massoud American University of Beirut Department of Electrical and Computer Engineering Beirut Lebanon American University of Beirut Biomedical Engineering Department Beirut Lebanon

ISBN: (纸本)9798350313826

Cardiovascular diseases (CVD) are the leading cause of death worldwide. Early detection of CVD allows for the use of effective and inexpensive interventions. CVD prediction using machine learning has achieved high accuracy using multiple data types such as Photoplethysmography (PPG), Electrocardiogram (ECG), and Blood Pressure (BP). However, these biological signals cannot all be reliably collected in real-time from a single wearable device and necessitate patients to be equipped with several devices. In this work, we trained a machine learning model to predict CVD using only PPG data collected from wearable devices, achieving an accuracy of 88% along with an F1-score of 90%. The information that this system can provide the patients with regarding their health status would enable the early detection and management of CVD, eventually decreasing the risk of morbidity. © 2023 IEEE.

关键词： Photoplethysmography

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：