检索结果-内蒙古大学图书馆

Caco-2 Cell-Derived Biomimetic Electrochemical Biosensor for Cholera Toxin Detection

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Kim, Yonghwan Lee, Dongtak Seo, Youngjun Jung, Hyo Gi Jang, Jae Won Park, Dongsung Kim, Insu Lee, Gyudo Hwang, Kyo Seon Kim, Seung-Hyun Lee, Sang Won Lee, Jeong Hoon Yoon, Dae Sung School of Biomedical Engineering Korea University Seoul02841 Korea Republic of Interdisciplinary Program in Precision Public Health Korea University Seoul02841 Korea Republic of Department of Clinical Pharmacology and Therapeutics College of Medicine Kyung Hee University Seoul02447 Korea Republic of Department of Biotechnology and Bioinformatics Korea University Sejong30019 Korea Republic of Interdisciplinary Graduate Program for Artificial Intelligence Smart Convergence Technology Korea University Sejong30019 Korea Republic of School of Engineering Brown University ProvidenceRI02912 United States Department of Electrical Engineering and Computer Science University of California IrvineCA92697 United States Department of Electrical Engineering Kwangwoon University Seoul01897 Korea Republic of Astrion Inc Seoul02841 Korea Republic of

Cholera is a highly contagious and lethal waterborne disease induced by an infection with Vibrio cholerae (V. cholerae) secreting cholera toxin (CTx). Cholera toxin subunit B (CTxB) from the CTx specifically binds with monosialo-tetra-hexosyl-ganglioside (GM1) found on the exterior cell membrane of an enterocyte. Owing to the pathological process of CTx, a biomimetic electrochemical biosensor (CCB) was developed by applying GM1-expressing Caco-2 cell membrane (CCM) on the electrode surface of the biosensor for CTx detection. Briefly, the electrode surface was functionalized with CCM using the vesicle fusion method. The specific binding between GM1 and CTxB on the electrode surface was verified using confocal laser scanning microscopy and atomic force microscopy. The CTxB detection performances of the CCB, including sensitivity, selectivity, and long-term stability, were determined using electrochemical impedance spectroscopy (EIS). Based on the results, the CCB had an excellent limit of detection of ~11.46 nM and a detection range spanning 100 ng/mL - 1 mg/mL. Further, the CCB had high selectivity for the CTxB compared to different interfering molecules, which are abundant constituents of intestinal fluid and fecal matter in the human body. The long-term stability of the CCBs was also verified for 3 weeks using EIS. Overall, the CCB was found to have an excellent potential for application to point-of-care and cost-effective testing for CTxB detection in developing countries. © 2022, The Authors. All rights reserved.

关键词： Electrochemical impedance spectroscopy

DRStageNet: Deep Learning for Diabetic Retinopathy Staging from Fundus Images

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Men, Yevgeniy Fhima, Jonathan Celi, Leo Anthony Ribeiro, Lucas Zago Nakayama, Luis Filipe Behar, Joachim A. The Andrew and Erna Viterbi Faculty of Electrical & Computer Engineering The Faculty of Biomedical Engineering Technion Israel Institute of Technology Haifa3200003 Israel The Department of Applied Mathematics The Biomedical Engineering Faculty Technion Israel Institute of Technology Haifa3200003 Israel The Laboratory for Computational Physiology Massachusetts Institute of Technology CambridgeMA02139 United States The Division of Pulmonary Critical Care and Sleep Medicine Beth Israel Deaconess Medical Center BostonMA02215 United States The Department of Biostatistics Harvard T.H. Chan School of Public Health BostonMA02115 United States The Ophthalmology department São Paulo Federal University São Paulo Brazil The Institute for Medical Engineering and Science Massachusetts Institute of Technology CambridgeMA United States The Department of Ophthalmology São Paulo Federal University São Paulo Brazil The Faculty of Biomedical Engineering Technion Israel Institute of Technology Haifa3200003 Israel

Diabetic retinopathy (DR) is a prevalent complication of diabetes associated with a significant risk of vision loss. Timely identification is critical to curb vision impairment. Algorithms for DR staging from digital fundus images (DFIs) have been recently proposed. However, models often fail to generalize due to distribution shifts between the source domain on which the model was trained and the target domain where it is deployed. A common and particularly challenging shift is often encountered when the source- and target-domain supports do not fully overlap. In this research, we introduce DRStageNet, a deep learning model designed to mitigate this challenge. We used seven publicly available datasets, comprising a total of 93,534 DFIs that cover a variety of patient demographics, ethnicities, geographic origins and comorbidities. We fine-tune DINOv2, a pretrained model of self-supervised vision transformer, and implement a multi-source domain fine-tuning strategy to enhance generalization performance. We benchmark and demonstrate the superiority of our method to two state-of-the-art benchmarks, including a recently published foundation model. We adapted the gradrollout method to our regression task in order to provide high-resolution explainability heatmaps. The error analysis showed that 59% of the main errors had incorrect reference labels. DRStageNet is accessible at URL [upon acceptance of the manuscript]. © 2023, CC BY.

关键词： Error analysis

Prediction of Occupational Physical Activities using Inertial Measurement Units and Deep Learning Models

学校读者我要写书评

暂无评论

Proceedings of the Human Factors and Ergonomics Society Annual Meeting 2021年第1期64卷 879 - 881页

作者： Yishu Yan Hao Fan Yibin Li Elias Hoeglinger Alexander Wiesinger Alan Barr Carisa Harris Adamson Department of Mechanical Engineering University of California Berkeley Department of Industrial Design Northwestern Polytechnic ChinaDepartment of Medicine University of California San Francisco Department of Electrical Engineering and Computer Science University of California Berkeley University of Applied Sciences Upper Austria Linz AustriaSchool of Public Health University of California Berkeley Department of Medicine University of California San Francisco Department of Medicine University of California San FranciscoSchool of Public Health University of California Berkeley

Many workers engaged in manual material handling (MMH) jobs experience high physical demands that are associated with work-related musculoskeletal disorders (WMSD). Quantifying the physical demands of a job is an important legal requirement in the US that is used by human resources in the job hiring process. Most physical demands analysis (PDA) are performed using observational and semi-quantitative methods. The lack of accuracy and reliability of these methods can create problems when assigning acceptable tasks to an injured worker. In this study, various deep learning models were applied to data from eight inertial measurement units (IMUs) to predict 15 occupational physical activities (OPA). Overall, a 95% accuracy was reached by convolutional neural network (CNN) for predicting occupational physical activities when performed in isolation. More work is needed to estimate the accuracy of the model when OPA elements are combined into a more complex task.

关键词：

An end-to-end food image analysis system

学校读者我要写书评

暂无评论

arXiv 2021年

作者： He, Jiangpeng Mao, Runyu Shao, Zeman Wright, Janine L. Kerr, Deborah A. Boushey, Carol J. Zhu, Fengqing School of Electrical and Computer Engineering Purdue University West LafayetteIN United States School of Public Health Curtin University PerthWA Australia Cancer Epidemiology Program University of Hawaii Cancer Center HonoluluHI United States

Modern deep learning techniques have enabled advances in image-based dietary assessment such as food recognition and food portion size estimation. Valuable information on the types of foods and the amount consumed are crucial for prevention of many chronic diseases. However, existing methods for automated image-based food analysis are neither end-to-end nor are capable of processing multiple tasks (e.g., recognition and portion estimation) together, making it difficult to apply to real life applications. In this paper, we propose an image-based food analysis framework that integrates food localization, classification and portion size estimation. Our proposed framework is end-to-end, i.e., the input can be an arbitrary food image containing multiple food items and our system can localize each single food item with its corresponding predicted food type and portion size. We also improve the single food portion estimation by consolidating localization results with a food energy distribution map obtained by conditional GAN to generate a four-channel RGB-Distribution image. Our end-to-end framework is evaluated on a real life food image dataset collected from a nutrition feeding study. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

Towards learning food portion from monocular images with cross-domain feature adaptation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Shao, Zeman Fang, Shaobo Mao, Runyu He, Jiangpeng Wright, Janine Kerr, Deborah Boushey, Carol Jo Zhu, Fengqing School of Electrical and Computer Engineering Purdue University West LafayetteIN United States School of Public Health Curtin University PerthWA Australia Cancer Epidemiology Program University of Hawaii Cancer Center HonoluluHI United States

We aim to estimate food portion size, a property that is strongly related to the presence of food object in 3D space, from single monocular images under real life setting. Specifically, we are interested in end-to-end estimation of food portion size, which has great potential in the field of personal health management. Unlike image segmentation or object recognition where annotation can be obtained through large scale crowd sourcing, it is much more challenging to collect datasets for portion size estimation since human cannot accurately estimate the size of an object in an arbitrary 2D image without expert knowledge. To address such challenge, we introduce a real life food image dataset collected from a nutrition study where the groundtruth food energy (calorie) is provided by registered dietitians, and will be made available to the research community. We propose a deep regression process for portion size estimation by combining features estimated from both RGB and learned energy distribution domains. Our estimates of food energy achieved state-of-the-art with a MAPE of 11.47%, significantly outperforms non-expert human estimates by 27.56%. Copyright © 2021, The Authors. All rights reserved.

关键词： Large dataset

Assessing gender fairness in EEG-based machine learning detection of Parkinson’s disease: A multi-center study

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Kurbatskaya, Anna Jaramillo-Jimenez, Alberto Ochoa-Gomez, John Fredy Brønnick, Kolbjørn Fernandez-Quilez, Alvaro Department of Electrical Engineering and Computer Science University of Stavanger Stavanger Norway Stavanger University Hospital Stavanger Norway Department of Public Health Faculty of Health Sciences University of Stavanger Stavanger Norway Grupo de Neurociencias de Antioquia Universidad de Antioquia School of Medicine Medellín Colombia Grupo Neuropsicología y Conducta Universidad de Antioquia School of Medicine Medellín Colombia Department of Radiology Stavanger University Hospital Stavanger Norway

As the number of automatic tools based on machine learning (ML) and resting-state electroencephalography (rs-EEG) for Parkinson’s disease (PD) detection keeps growing, the assessment of possible exacerbation of health disparities by means of fairness and bias analysis becomes more relevant. Protected attributes, such as gender, play an important role in PD diagnosis development. However, analysis of sub-group populations stemming from different genders is seldom taken into consideration in ML models’ development or the performance assessment for PD detection. In this work, we perform a systematic analysis of the detection ability for gender sub-groups in a multi-center setting of a previously developed ML algorithm based on power spectral density (PSD) features of rs-EEG. We find significant differences in the PD detection ability for males and females at testing time (80.5% vs. 63.7% accuracy) and significantly higher activity for a set of parietal and frontal EEG channels and frequency sub-bands for PD and non-PD males that might explain the differences in the PD detection ability for the gender subgroups. © 2023, CC BY.

关键词： Electroencephalography

An integrated system for mobile image-based dietary assessment

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Shao, Zeman Han, Yue He, Jiangpeng Mao, Runyu Wright, Janine Kerr, Deborah Boushey, Carol Zhu, Fengqing School of Electrical and Computer Engineering Purdue University West LafayetteIN United States School of Public Health Curtin University PerthWA Australia Cancer Epidemiology Program University of Hawaii Cancer Center HonoluluHI United States

Accurate assessment of dietary intake requires improved tools to overcome limitations of current methods including user burden and measurement error. Emerging technologies such as image-based approaches using advanced machine learning techniques coupled with widely available mobile devices present new opportunities to improve the accuracy of dietary assessment that is cost-effective, convenient and timely. However, the quality and quantity of datasets are essential for achieving good performance for automated image analysis. Building a large image dataset with high quality groundtruth annotation is a challenging problem, especially for food images as the associated nutrition information needs to be provided or verified by trained dietitians with domain knowledge. In this paper, we present the design and development of a mobile, image-based dietary assessment system to capture and analyze dietary intake, which has been deployed in both controlled-feeding and community-dwelling dietary studies. Our system is capable of collecting high quality food images in naturalistic settings and provides groundtruth annotations for developing new computational approaches. Copyright © 2021, The Authors. All rights reserved.

关键词： Image analysis

Ultra Low Voltage Variable Gain Cherry-Hooper Amplifier with 1MHz Constant Bandwidth, 1.7μW Power Dissipation and ±0.2V Supply 62

学校读者我要写书评

暂无评论

Ultra Low Voltage Variable Gain Cherry-Hooper Amplifier with...

62nd IEEE International Midwest Symposium on Circuits and Systems, MWSCAS 2019

作者： Rico-Aniles, Hector Daniel Ramirez-Angulo, Jaime Lopez-Martin, Antonio J. Rocha, Jose Miguel DIaz-Sanchez, Alejandro Carvajal, Ramon G. VLSI Laboratory Klipsch School of Electrical and Computer Engineering Las Cruces United States Dept. of Electrical and Electronics Engineering Public Univerity of Navarra Navarra Spain Electronics Engineering Department Universidad de Sevilla Seville Spain

ISBN: (纸本)9781728127880

An ultra-low-voltage low-power amplifier is introduced. The design is based on the Cherry-Hooper architecture and operates with a ±0.2V supply and ±190mV linear input range. It has an approximately constant bandwidth of 1MHz with a power consumption of 1.7μW. The low-voltage operation is achieved using floating batteries that keep the gates of all differential pairs at a constant value close to the upper rail with large input signal variations. It has a figure of merit of 2.61 MHzpF/μW for a nominal gain A=15.6. © 2019 IEEE.

关键词： Bandwidth

Transatlantic partnership on artificial intelligence: realities, perceptions and future implications

学校读者我要写书评

暂无评论

Global Affairs 2020年第4-5期6卷 537-557页

作者： Muhammed Can Halid Kaplan a Department of International Relations and Public Administration University of Minho Braga Portugal b Department of Electrical and Computer Engineering University of Texas at San Antonio San Antonio USA

ABSTRACTABSTRACTRecent confrontation between China and the US laid bare underlying factors that might accelerate decoupling in different realms. Technology is one of the main factors of recent rift. Specific to AI, democratic countries are striving for finding common ground to counter diffusion of authoritarian technologies. In this paper we argue that future AI alliance/partnership has to find a solution in three distinct political obstacles. Firstly, future alliance/partnership bear in mind the crumbling the US leadership. The US leadership is must, for the future of alliance/partnership due to its economic and technological prowess. Secondly, the EU's fragmentation in deploying Chinese technology and their dependency towards China not only technologically but also economically will be determinative factor for the success of alliance/partnership. Finally, democratic partners and allies should focus on creating mechanisms to offer AI-based technologies to both offset authoritarian counterparts and to become more competitive.

关键词： Artificial intelligence AI policy alliances technology policy US foreign policy the EU fragmentation