检索结果-内蒙古大学图书馆

Frontiers in Biological Detection: From Nanosensors to Systems XVII 2025

作者： An, Huijin Laibinis, Paul E. Locke, Andrea K. Weiss, Sharon M. Interdisciplinary Material Science Program Vanderbilt University NashvilleTN37235 United States Department of Electrical and Computer Engineering Vanderbilt University NashvilleTN37235 United States Department of Chemical and Biomolecular Engineering Vanderbilt University NashvilleTN37235 United States Department of Chemistry Vanderbilt University NashvilleTN37235 United States Department of Biomedical Engineering Vanderbilt University NashvilleTN37235 United States

ISBN: (纸本)9781510684249

A paper-based biosensor integrating a functionalized porous silicon (PSi) membrane as the active sensing element for quantifiable protein detection has been developed. For similar short-time exposures to an analyte, improved molecular transport in PSi membranes when on paper leads to larger signal changes compared to traditional PSi films that remain on a silicon substrate. In this work, we discuss controlling the incubation time of the analyte and the overall testing time of the sensor by incorporating different combinations of wicking and absorbent paper beneath the PSi membrane. With this control, the PSi-on-paper sensor platform has the potential to serve as an effective low-cost rapid diagnostic test with highly sensitive, quantitative readout for a wide range of analytes. © 2025 SPIE.

关键词： Porous silicon

来源：评论

学校读者我要写书评

暂无评论

Effective Loss Function for Unbalanced Breast Thermal Image Segmentation

Effective Loss Function for Unbalanced Breast Thermal Image ...

引用

2021 International Conference on computer System, Information Technology, and electrical engineering, COSITE 2021

作者： Roslidar, Roslidar Saddami, Khairun Irhamsyah, Muhammad Arnia, Fitri Syukri, Maimun Munadi, Khairul Universitas Syiah Kuala Doctoral Program Post Graduate Program School of Engineering Banda Aceh23111 Indonesia Universitas Syiah Kuala Department of Electrical and Computer Engineering Banda Aceh23111 Indonesia Universitas Syiah Kuala Medical Faculty Banda Aceh23111 Indonesia

ISBN: (纸本)9781665425094

The convolutional neural network's ability to learn images has reigned in computer vision tasks of object detection, classification, and segmentation. In segmentation, the CNN architectures of U-Net and SegNet have shown a good performance;thus, we implemented these networks to take the region of interest (ROI) of the breast thermal images from database for mastology research (DMR). We fine-tuned the networks to find the optimal hyperparameter that can result in the best learning performance. The networks were trained using the stochastic gradient descent optimization algorithm, and weights were updated using the error backpropagation of the algorithm. To minimize the error, the loss function is applied to evaluate a candidate solution of the weights. Thus, we conducted a preliminary study on finding the optimal loss function for breast thermal image segmentation. We applied loss functions of cross-entropy, dice, and focal and figured out the one that provides the highest segmentation accuracy. Then, to evaluate the segmentation result, we calculated the pixel accuracy rate and the dice coefficient to obtain the overlapping index measuring the overlay area between ground truth and predicted output. The result shows that the SegNet model with cross-entropy loss function can take the ROI of breast thermal images at the highest pixel accuracy and optimum dice coefficient of 0.8845 and 0.7928, respectively. © 2021 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A model of indoor thermal condition based on traditional acehnese houses using artificial neural network

引用

Heliyon 2024年第23期10卷 e40644页

作者： Muslimsyah Munir, Abdul Away, Yuwaldi Abdullah Arif, Teuku Yuliar Novandri, Andri Doctoral Program School of Engineering Universitas Syiah Kuala Banda Aceh 23111 Indonesia Department of Architecture and Planning Universitas Syiah Kuala Banda Aceh 23111 Indonesia Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh 23111 Indonesia Department of Civil Engineering Universitas Syiah Kuala Banda Aceh 23111 Indonesia Department of Computer Engineering Universitas Serambi Mekkah Banda Aceh 23249 Indonesia

This paper examines the thermal condition aspects of traditional Acehnese houses (Rumoh Aceh) in Indonesia. This study highlights the importance of considering traditional architecture in achieving comfortable living conditions. Through the integration of cultural values, architectural design, and environmental factors, this research evaluates the prediction of thermal conditions within Rumoh Aceh based on building orientation and location, serving as guidelines for architects in designing buildings in the Aceh region. The study employs an ANN (Artificial Neural Network) algorithm to predict thermal condition parameters including indoor: temperature, humidity, and wind speed. The sample data used to train the ANN model consists of thermal data from five different rooms and meteorological data. The ANN model is employed to predict the thermal conditions in the Rumoh Aceh building based on its orientation and location. In this study, two models were developed, namely MODEL_01, for predicting indoor temperature and humidity, and MODEL_02, for predicting indoor wind speed. In MODEL_01, the error tolerance level obtained is ±1.05, and in MODEL_02, it is ±0.03. The prediction results based on the building orientation show the lowest average indoor temperature value of 29.19 °C, occurring at an angle of 292.19°. Furthermore, the lowest average indoor humidity value is 74.57 %, which also occurs at an angle of 292.19°. However, for indoor wind speed, the angle of 260° records the lowest average value of 0.125 m/s, while the highest average value is observed at 292.19°, at 0.132 m/s. The prediction results based on the building's location show the lowest average temperature value, which is 29.44 °C in the Aceh Besar region. Furthermore, the lowest average humidity value is 75.11 % in the North Aceh region. Meanwhile, the highest average wind speed value is 0.174 m/s in the Sabang region. This study reveals that at the orientation angle of 292.19° (the qibla direction), it pr

关键词： ANN Orientation Region Rumoh aceh Thermal condition

来源：评论

学校读者我要写书评

暂无评论

Surface engineering Towards Boosted Dielectric Properties for High-Temperature Polymers Under electrical Extremes

Surface Engineering Towards Boosted Dielectric Properties fo...

引用

Conference on electrical Insulation and Dielectric Phenomena, (CEIDP)

作者： Jierui Zhou Marina Dabaghian Anna Marie LaChance Jing Hao Wesley Zhong Luyi Sun Yang Cao Department of Electrical and Computer Engineering University of Connecticut Storrs CT USA Electrical Insulation Research Center Institute of Materials Science University of Connecticut Storrs CT USA Department of Chemical and Biomolecular Engineering University of Connecticut Storrs CT USA Polymer Program Institute of Materials Science University of Connecticut Storrs CT USA

Polymer-thin films are critical dielectric materials for capacitive energy storage in power and electronic systems. The rapid development of wide bandgap semiconductors urgently calls for polymers that can attain high energy density and high charge-discharge efficiency at elevated temperatures. However, high-temperature polymers usually suffer from compromised dielectric breakdown strength and soaring conduction loss due to the intrinsic constraint between their bandgaps and thermal stability. In this work, we propose a facile and high throughput interface engineering technique utilizing nanocoatings formed by montmorillonite (MMT) nanoclays, which can serve as an out-of-the-box solution to bypass this constraint. The highly ordered MMT-based nanocoatings with layered structure can significantly block the excessive charge injection at high electric fields and dissipate the charge carriers along the in-plane direction. The MMT-coated PI films exhibit improved breakdown strength, suppressed conduction loss, and boosted charging-discharging efficiency. This work holds the promise of improving the dielectric properties of polymers through surface engineering, enabling their application at concurrent electrical and thermal extremes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modeling functional cell types in spike train data

引用

PLoS Computational Biology 2023年第1 OCTOBER期19卷 e1011509页

作者： Zdeblick, Daniel N. Shea-Brown, Eric T. Witten, Daniela M. Buice, Michael A. Department of Electrical and Computer Engineering University of Washington SeattleWA United States Department of Applied Math University of Washington SeattleWA United States MindScope Program Allen Institute SeattleWA United States Department of Statistics and Biostatistics University of Washington SeattleWA United States

A major goal of computational neuroscience is to build accurate models of the activity of neurons that can be used to interpret their function in circuits. Here, we explore using functional cell types to refine single-cell models by grouping them into functionally relevant classes. Formally, we define a hierarchical generative model for cell types, single-cell parameters, and neural responses, and then derive an expectation-maximization algorithm with variational inference that maximizes the likelihood of the neural recordings. We apply this "simultaneous" method to estimate cell types and fit single-cell models from simulated data, and find that it accurately recovers the ground truth parameters. We then apply our approach to in vitro neural recordings from neurons in mouse primary visual cortex, and find that it yields improved prediction of single-cell activity. We demonstrate that the discovered cell-type clusters are well separated and generalizable, and thus amenable to interpretation. We then compare discovered cluster memberships with locational, morphological, and transcriptomic data. Our findings reveal the potential to improve models of neural responses by explicitly allowing for shared functional properties across neurons. Copyright: © 2023 Zdeblick et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Dynamics of COVID-19 Misinformation: An Analysis of Conspiracy Theories, Fake Remedies, and False Reports

Dynamics of COVID-19 Misinformation: An Analysis of Conspira...

引用

17th International Conference on Social Computing and Social Media, SCSM 2025, held as part of the 27th HCI International Conference, HCII 2025

作者： Thakur, Nirmalya Shao, Mingchen Knieling, Victoria Su, Vanessa Bian, Andrew Jeong, Hongseok Department of Electrical Engineering and Computer Science South Dakota School of Mines and Technology Rapid CitySD57701 United States Department of Computer Science Emory University AtlantaGA30322 United States Program in Linguistics Emory University AtlantaGA30322 United States Goizueta Business School Emory University AtlantaGA30322 United States

ISBN: (纸本)9783031935350

This paper makes four scientific contributions to the area of misinformation detection and analysis on digital platforms, with a specific focus on investigating how conspiracy theories, fake remedies, and false reports emerge, propagate, and shape public perceptions in the context of COVID-19. A dataset of 5,614 posts on the internet that contained misinformation about COVID-19 was used for this study. These posts were published in 2020 on 427 online sources (such as social media platforms, news channels, and online blogs) from 193 countries and in 49 languages. First, this paper presents a structured, three-tier analytical framework that investigates how multiple motives - including fear, politics, and profit - can lead to a misleading claim. Second, it emphasizes the importance of narrative structures, systematically identifying and quantifying the thematic elements that drive conspiracy theories, fake remedies, and false reports. Third, it presents a comprehensive analysis of different sources of misinformation, highlighting the varied roles played by individuals, state-based organizations, media outlets, and other sources. Finally, it discusses multiple potential implications of these findings for public policy and health communication, illustrating how insights gained from motive, narrative, and source analyses can guide more targeted interventions in the context of misinformation detection on digital platforms. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Enhanced Prognostics and Health Management in Automated Driving Systems: Using Graph Neural Networks to Recognize Operational Contexts

Enhanced Prognostics and Health Management in Automated Driv...

引用

Prognostics and System Health Management Conference (PHM)

作者： Peng Su Yeqi Wang Conglei Xiang Erik Wendel Madhav Mishra DeJiu Chen Department of Engineering Design Mechatronics Division KTH Royal Institute of Technology Stockholm Sweden Embedded Systems Master Program of Electrical Engineering and Computer Science (EECS) School KTH Royal Institute of Technology Stockholm Sweden Digital Systems Division RISE Research Institutes of Sweden Gothenburg Sweden

ISBN: (数字)9798350360585

ISBN: (纸本)9798350360592

Prognostics and health management (PHM) is an engineering discipline that aims to maintain system behaviour and function and ensure mission success, safety and effectiveness. Addressing the challenges in prognostics and health management for modern intelligent systems, especially automated driving systems, is complex due to the contextual nature of faults. This complexity necessitates a thorough understanding of spatial, and temporal conditions, and relationships within operational scenarios and life-cycle stages. This paper introduces a framework designed to automatically recognize driving scenarios in automated driving systems using graph neural networks (GNNs). The framework extracts relational data from image frames, constructing graph-based models and transforming unstructured sensory data into structured data with diverse node types and relationships. A specific graph neural network processes the graph model to reveal and detect operational conditions and relationships. The proposed framework is evaluated using the KITTI dataset, demonstrating superior performance compared to conventional feed-forward networks such as MLP, particularly in handling relational data.

关键词： Graph neural networks Data models Safety Complexity theory Data mining Prognostics and health management Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Optical spectroscopy of excitons in ReS2 monolayers grown by chemical vapor deposition

arXiv

引用

arXiv 2024年

作者： Ojo, Solomon Onasanya, Juwon Benamara, Morad Hamad, Bothina Manasreh, M.O. Material Science and Engineering program University of Arkansas FayettevilleAR72701 United States Institute of nanotechnology University of Arkansas FayettevilleAR72701 United States Physics Department University of Arkansas FayettevilleAR72701 United States Department of Electrical Engineering and Computer Science University of Arkansas FayettevilleAR72701 United States

Monolayers of ReS2 were grown by a chemical vapor deposition technique on SiO2/Si substrates and investigated at room temperature by using μ-Raman, μ-photoluminescence (PL) and absorbance spectroscopies. The Raman scattering spectrum exhibits several phonon modes that were confirmed by the computation analysis based on the density functional theory. The ReS2 structural integrity was confirmed by using the XRD and the energy dispersion spectroscopy that was obtained by the scanning electron microscopy. Photoluminescence spectra show excitons related to interband transition in thin monolayer flakes and bulk-like structures. Additionally, a sharp PL line located at 1.2620 eV with a second harmonic peak at 2.5420 eV were observed and explained in terms of interband excitonic transitions originated within the rhenium 5d orbit. An optical absorbance spectrum with an exciton peak around 1.4660 eV was obtained for an assembly of ReS2 flakes grown on silica substrate. Copyright © 2024, The Authors. All rights reserved.

关键词： Scanning electron microscopy

来源：评论

学校读者我要写书评

暂无评论

Gene Name Recognition in Gene Pathway Figures Using Siamese Networks

Gene Name Recognition in Gene Pathway Figures Using Siamese ...

引用

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Micheal Olaolu Arowolo Muhammad Azam Fei He Mihail Popescu Dong Xu Department of Public Health Sciences Health Informatics Program Xavier University of Louisiana New Orleans Louisiana USA Department of Electrical Engineering and Computer Science Bond Life Sciences Center University of Missouri Columbia Missouri USA Department of Health Management and Informatics University of Missouri Columbia Missouri USA

ISBN: (数字)9798350377613

ISBN: (纸本)9798350377620

The number of scientific papers related to biology is rapidly increasing, and with it, the number of pathway figures containing crucial biological information. However, manually annotating these figures is a time-consuming process, and current optical character recognition (OCR) methods are not effective in identifying gene names within these figures. To improve gene name recognition from pathway figures, we utilized a Siamese network that maps image segments to a library of pictures containing known gene name, like object recognition in many photo applications. We combined the triplet convolution neural network and the spatial pyramid pooling (TSPP-Net) to create a CNN triple loss function. We trained and tested the developed TSPP-Net network using 563 gene images from 45 pathway pictures, 1000 images of alphanumeric characters and gene names from HUGO and KEGG. To benchmark against major available OCR technologies, we used 20 randomly selected curated pathway genes. Additionally, we compared several models, such as VGG19, VGG16, Resnet-50 Resnet-18, Densnet-121, and Xception for the Siamese backbone network model. VGG16 achieved the best performance with an accuracy of 93%, which is much higher than the results obtained using OCR. Our code is publicly available at https://***/MuhammadAzam636/Siamese-Network.

关键词： Image recognition Accuracy Sensitivity Text recognition Biological system modeling Optical character recognition Neural networks Libraries Object recognition Biological information theory

来源：评论

学校读者我要写书评

暂无评论

Dynamics of COVID-19 Misinformation: An Analysis of Conspiracy Theories, Fake Remedies, and False Reports

arXiv

引用

arXiv 2025年

关键词：

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：