检索结果-内蒙古大学图书馆

Advances in Industrial Control 2019年 v-vi页

作者： Ferrara, Antonella Department of Electrical Computer and Biomedical Engineering University of Pavia Via Ferrata 1 Pavia27100 Italy

来源：评论

学校读者我要写书评

暂无评论

Coderiu: a cloud platform for computer programming e-learning

Coderiu: a cloud platform for computer programming e-learnin...

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Guido Benetti Gianluca Roveda Davide Giuffrida Tullio Facchinetti Dept. of Electrical Computer and Biomedical Engineering University of Pavia Pavia (Italy)

The need for powerful and flexible platforms for teaching and learning computer programming concepts is increasing due to the growing number of interested attendees. Although implementing a complete platform from scratch would achieve the best flexibility in terms of possible features, it also requires a huge time-consuming effort. This paper proposes Coderiu, a platform built on top of Free and Open Source Software (FOSS) packages suitably integrated to implement the desired learning platform. Such features include platform independence of code editing, which is achieved by leveraging a web-based Integrated Development Environment (IDE). The environment is extended with custom features to enable the automated testing of the solutions and the automatic remote backup of the working directories. Moreover, the architecture was made suitable to be used in classroom exams, which require a controlled environment. A critical aspect of the Coderiu platform, beside the integration of its components and modules, is represented by the scalability. The Coderiu platform is used by hundreds of students in case of courses in relatively small classes, while it is ready to serve a larger user base in the future. For this reason, requirements and performance are studied on a pilot installation to derive insights regarding the resources required for larger deployments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Contrastive learning-based pretraining improves representation and transferability of diabetic retinopathy classification models

arXiv

引用

arXiv 2022年

作者： Alam, Minhaj Nur Yamashita, Rikiya Ramesh, Vignav Prabhune, Tejas Lim, Jennifer I. Chan, Rvp Hallak, Joelle Leng, Theodore Rubin, Daniel Department of Biomedical Data Science Stanford University School of Medicine StanfordCA94305 United States Department of Electrical and Computer Engineering University of North Carolina at Charlotte CharlotteNC28223 United States Department of Ophthalmology and Visual Sciences University of Illinois at Chicago ChicagoIL60612 United States Department of Ophthalmology Stanford University School of Medicine StanfordCA94305 United States Department of Radiology Stanford University School of Medicine StanfordCA94305 United States

Importance: Self-supervised contrastive learning (CL) based pretraining allows development of robust and generalized deep learning (DL) models with small, labeled datasets, reducing the burden of label generation. Application of CL in diabetic retinopathy (DR) diagnosis requires further investigation. Objective: To evaluate the effect of CL-based pretraining on the performance of referrable vs non referrable diabetic retinopathy (DR) classification. Design, Setting, and Participants: CL is a form of self-supervision that can leverage unlabeled data to produce pretrained models. We have developed a CL-based framework with neural style transfer (NST) augmentation to produce models with better representations and initializations for the detection of DR in color fundus images. We compare our model (FundusNet – a ResNet50 architecture pretrained with NST integrated CL framework) performance with two state-of-the-art baseline models (ResNet50 and InceptionV3 architectures pretrained with Imagenet weights). We further investigate the model performance with reduced labeled training-data (down to 10%) to test the robustness of the model when trained with small, labeled datasets. The model is trained and validated on the EyePACS dataset and tested independently on clinical data from the University of Illinois,Chicago (UIC). Exposure: CL pretrained DL algorithm. Main outcomes and measures: The sensitivity, specificity, and area under the receiver-operating-characteristic (ROC) curve (AUC) of the algorithm (95% confidence interval, CI) for detecting referable DR have been generated based on the reference labels created by an ophthalmologist panel. Results: The validation data from EyePACS consists of 88,692 images from 44,346 individuals. After data-curation, the dataset contains 57,722 non-referrable-DR and 13,247 referrable-DR images. The independent UIC dataset contains 2500 images from 1250 patients (500 referrable and 750 non-referrable DR). Compared to baseline models, ou

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Weakly supervised deep learning for detecting and counting dead cells in microscopy images 18

Weakly supervised deep learning for detecting and counting d...

引用

18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019

作者： Chen, Siteng Li, Ao Lasick, Kathleen Huynh, Julie Powers, Linda Roveda, Janet Paek, Andrew Electrical and Computer Engineering University of Arizona Tucson United States Molecular and Cellular Biology University of Arizona Tucson United States BIO5 Institute University of Arizona Tucson United States Biomedical Engineering University of Arizona Tucson United States

ISBN: (纸本)9781728145495

Counting dead cells is a key step in evaluating the performance of chemotherapy treatment and drug screening. Deep convolutional neural networks (CNNs) can learn complex visual features, but require massive ground truth annotations which is expensive in biomedical experiments. Counting cells, especially dead cells, with very few ground truth annotations remains unexplored. In this paper, we automate dead cell counting using a weakly supervised strategy. We took advantage of the fact that cell death is low before chemotherapy treatment and increases after treatment. Motivated by the contrast, we first design image level supervised only classification neural networks to detect dead cells. Based on the class response map in classification networks, we calculate a Dead Confidence Map (DCM) to specify confidence of each dead cell. Associated with peak clustering, local maximums in the DCM are used to count the number of dead cells. In addition, a biological experiment based weakly supervised data preparation strategy is proposed to minimize human intervention. We show classification performance compared to general purpose and cell classification networks, and report results for the image-level supervised counting task. © 2019 IEEE.

关键词： Cell death

来源：评论

学校读者我要写书评

暂无评论

Protein secondary structure analysis in the cloud 2018

Protein secondary structure analysis in the cloud

引用

6th International Workshop on Parallelism in Bioinformatics, PBio 2018, held as part of EuroMPI 2018

作者： Ferretti, Marco Santangelo, Luigi Department of Electrical Computer and Biomedical Engineering University of Pavia Italy

ISBN: (纸本)9781450365314

Many biological problems, such finding recurring geometrical patterns in the secondary structures of protein pairs, are often solved by using parallel applications running on HPC systems that, thanks to their powerful architecture and high number of CPUs, can yield good performance. Recently cloud computing is emerging as a convenient environment to deploy certain types of parallel applications. This work examines Cross Motif Search, an application that has been successfully executed in parallel on on-premise clusters and HPC systems, and studies its porting in a cloud environment. The work uses profiling and analytical modelling to predict communication overhead. While profiling gives unreliable estimates, model-based predictions and actual data are in good match, thanks to the simple pattern of communication embedded in the application. Overall, Cross Motif Search has a viable implementation in the cloud. © 2018 ACM.

关键词： Parallel architectures

来源：评论

学校读者我要写书评

暂无评论

Advancing Italian biomedical Information Extraction with Large Language Models: Methodological Insights and Multicenter Practical Application

SSRN

引用

SSRN 2023年

作者： Crema, Claudio Buonocore, Tommaso Mario Fostinelli, Silvia Parimbelli, Enea Verde, Federico Fundarò, Cira Manera, Marina Ramusino, Matteo Cotta Capelli, Marco Costa, Alfredo Binetti, Giuliano Bellazzi, Riccardo Redolfi, Alberto Laboratory of Neuroinformatics Italy Molecular Markers Laboratory IRCCS Istituto Centro San Giovanni di Dio Fatebenefratelli Brescia Italy Dept. of Electrical Computer and Biomedical Engineering University of Pavia Pavia Italy Department of Neurology and Laboratory of Neuroscience IRCCS Istituto Auxologico Italiano Milan Italy Department of Pathophysiology and Transplantation Dino Ferrari Center Università degli Studi di Milano Milan Italy Neurophysiopatology Unit Italy Psychology Unit IRCCS Istituti Clinici Scientifici Maugeri Pavia Italy Unit of Behavioral Neurology IRCCS Mondino Foundation Pavia Dept. of Brain and Behavioral Sciences University of Pavia Pavia Italy

The introduction of computerized medical records in hospitals has reduced burdensome activities like manual writing and information fetching. However, the data contained in medical records are still far underutilized, primarily because extracting data from unstructured textual medical records takes time and effort. Information Extraction, a subfield of Natural Language Processing, can help clinical practitioners overcome this limitation by using automated text-mining pipelines. In this work, we created the first Italian neuropsychiatric Named Entity Recognition dataset, PsyNIT, and used it to develop a Large Language Model for this task. Moreover, we collected and leveraged three external independent datasets to implement an effective multicenter model, with overall F1-score 84.77%, Precision 83.16%, Recall 86.44%. The lessons learned are: (i) the crucial role of a consistent annotation process and (ii) a fine-tuning strategy that combines classical methods with a "few-shot" approach. This allowed us to establish methodological guidelines that pave the way for Natural Language Processing studies in less-resourced languages. © 2023, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Glassy carbon microelectrode arrays enable voltage-peak separated simultaneous detection of dopamine and serotonin using fast scan cyclic voltammetry

arXiv

引用

arXiv 2020年

作者： Castagnola, Elisa Thongpang, Sanitta Hirabayashi, Mieko Nava, Giorgio Nimbalkar, Surabhi Nguyen, Tri Lara, Sandra Oyawalea, Alexis Bunnella, James Moritz, Chet Kassegne, Sam NanoFAB. SDSU Lab Department of Mechanical Engineering San Diego State University San DiegoCA United States University of Washington Departments of Electrical & Computer Engineering Rehabilitation Medicine and Physiology & Biophysics SeattleWA United States Department of Biomedical Engineering Faculty of Engineering Mahidol University Nakorn Pathom Thailand Department of Mechanical Engineering University of California Riverside RiversideCA United States Bill & Melinda Gates Center for Computer Science & Engineering SeattleWA98195 United States

Progress in real-time, simultaneous in vivo detection of multiple neurotransmitters will help accelerate advances in neuroscience research. The need for development of probes capable of stable electrochemical detection of rapid neurotransmitter fluctuations with high sensitivity and selectivity and sub-second temporal resolution has, therefore, become compelling. Additionally, a higher spatial resolution multi-channel capability is required to capture the complex neurotransmission dynamics across different brain regions. These research needs have inspired the introduction of glassy carbon (GC) microelectrode arrays on flexible polymer substrates through carbon MEMS (C-MEMS) microfabrication process followed by a novel pattern transfer technique. These implantable GC microelectrodes offer unique advantages in electrochemical detection of electroactive neurotransmitters through the presence of active carboxyl, carbonyl, and hydroxyl functional groups. In addition, they offer fast electron transfer kinetics, capacitive electrochemical behavior, and wide electrochemical window. Here, we combine the use of these GC microelectrodes with the fast scan cyclic voltammetry (FSCV) technique to optimize the co-detection of dopamine and serotonin in vitro and in vivo. We demonstrate that using optimized FSCV triangular waveform at scan rates ≤ 700 V/s and holding and switching at potentials of 0.4 and 1V respectively, it is possible to discriminate voltage reduction and oxidation peaks of serotonin and dopamine, with serotonin contributing distinct multiple oxidation peaks. Taken together, our results present a compelling case for a carbon-based MEA platform rich with active functional groups that allows for repeatable and stable detection of electroactive multiple neurotransmitters at concentrations as low as 10 nM. © 2020, CC-BY.

关键词： Carbon

来源：评论

学校读者我要写书评

暂无评论

Informing the development of assistive technologies for persons with dementia by connecting financial measures of wealth to perceptions of task dependence

引用

Technology and Disability 2019年第1-2期31卷 39-49页

作者： Czarnuch, Stephen Ricciardelli, Rose Mihailidis, Alex Department of Electrical and Computer Engineering Faculty of Engineering and Applied Science/Discipline of Emergency Medicine Faculty of Medicine Memorial University of Newfoundland St. John's NL Canada Department of Sociology Memorial University of Newfoundland St John's NL Canada Department of Occupational Science and Occupational Therapy Institute of Biomaterials and Biomedical Engineering University of Toronto Toronto ON Canada

BACKGROUND: Older adults with dementia have been targeted toward the development of assistive technologies intended to facilitate aging in place. Researchers have documented financial and occupation strain for the caregiver and the financial limitations experienced by persons with dementia. These factors constitute a potential hindrance to the use and applicability of assistive technologies;technologies that may reduce caregiver burden, allow more time for paid work, and, in consequence, reduce occupational strain. OBJECTIVE: To unpack how financial burden, operationalized as direct (e.g., income) and indirect (e.g., caregiver education, employment status) measures of wealth and assets, affect the perceived independence of people with dementia. METHODS: We draw on data collected through a cross-Canada survey of caregivers to develop a set of predictive models of care-recipient task independence. RESULTS: Our findings suggest that said measures of wealth can predict task independence, and more complicated or instrumental daily tasks (e.g., shopping, driving) are perceived as being those with which care recipients need most assistance. CONCLUSIONS: Considering the economical and emotional obstacles that affect both the caregiver and the care recipient, the development of assistive technologies that would be both financially realistic and assistive for this population in these instrumental daily tasks is warranted. © 2019 - IOS Press and the authors. All rights reserved.

关键词： Assistive technology caregiver dementia financial strain financial wealth independence

来源：评论

学校读者我要写书评

暂无评论

Predictive Protective Control for Flexible Energy System

引用

IFAC-PapersOnLine 2018年第6期51卷 1-6页

作者： Ozana, S. Pies, M. Department of Cybernetics and Biomedical Engineering Faculty of Electrical Engineering and Computer Science VSB-Technical University of Ostrava 17.listopadu 15 Ostrava Czech Republic

The paper deals with the predictive control applied to flexible cogeneration energy system (FES). The FES was designed and developed by the VITKOVICE POWER engineering joint-stock company and represents a new solution of decentralized cogeneration energy sources. In FES, the heating medium is flue gas generated by combustion of a solid fuel. The heated medium is power gas, which is a gas mixture of air and water steam. Power gas is superheated in the main heat exchanger and led to gas turbines. To protect the main heat exchanger against damage by overheating, the novel predictive protective control based on the mathematical model of exchanger was developed. The paper describes the principle, the design and simulation of the predictive protective method applied to main heat exchanger of FES. © 2018

关键词： Gases Cogeneration plants Fuels Gas turbines Heat exchangers Design and simulation Distributed parameter Energy systems Heating medium Joint stock companies Power engineering Predictive control simulation

来源：评论

学校读者我要写书评

暂无评论

BPS2025 - Rapid and accurate transepithelial resistance measurement of bronchiolar epithelium using impedance spectroscopy and RCRC model

引用

Biophysical Journal 2025年第3期124卷 296a-297a页

作者： Athena Chien Colby Lewallen Guiying Cui Analia Vazquez Cegla Erica Lull Hanna Khor Nael A. McCarty Craig Forest Walter H. Coulter Department of Biomedical Engineering Georgia Institute of Technology and Emory University Atlanta GA USA National Eye Institute National Institutes of Health Bethesda MD USA Department of Pediatrics Emory University Atlanta GA USA Department of Pharmacology Emory University Atlanta GA USA School of Mechanical Engineering Georgia Institute of Technology Atlanta GA USA School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA USA Picture Archives Communication System Emory University School of Medicine Atlanta GA USA

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：