检索结果-内蒙古大学图书馆

Transferable individual brain regional atrophy progression prediction model using structural connectome

Alzheimer's & Dementia 2023年第S14期19卷

作者： Yu Xiao Joanna Su Xian Chong Bing Cai Kok Kwun Kei Ng Christopher Li-Hsian Chen Juan Helen Zhou Quantitative Biology and Medicine Program Duke-NUS Medical School Singapore Singapore Centre for Sleep and Cognition & Centre for Translational Magnetic Resonance Research Yong Loo Lin School of Medicine National University of Singapore Singapore Singapore Correspondece Department of Pharmacology Clinical Research Centre National University Health System National University of Singapore Singapore Singapore Memory Ageing and Cognition Centre National University Health System Singapore Singapore Electrical and Computer Engineering National University of Singapore Singapore Singapore Integrative Sciences and Engineering Programme (ISEP) NUS Graduate School National University of Singapore Singapore Singapore

Background Brain microstructure, as measured by diffusion MR imaging (dMRI), is an early biomarker of Alzheimer’s disease (AD) and has been previously demonstrated to predict whole brain atrophy and cognition. The network-based neurodegeneration hypothesis posits that the onset of AD occurs within key vulnerable regions, whose network connectivity guides the spread of atrophy into new regions. Graph convolutional network (GCN) models can mimic this spread through its convolution process. Here we present a GCN-based model to predict future individual nodal atrophy and disease progression across the AD spectrum using structural connectome. Method We analyzed 371 participants with baseline dMRI scans (154 cognitively normal (CN), 161 mild cognitive impairment (MCI), 56 AD) and longitudinal T1 scans (2.7±1.2 years) from the ADNI study. To predict annual nodal atrophy rates (126 nodes) from baseline structural connectivity (SC), we constructed a two-layer GCN followed by multilayer perceptron (GCN-MLP). Five-fold nested cross-validation and Optuna were used for hyperparameter tuning. We applied the trained GCN-MLP model to predict future disease progression via transfer learning. GNNExplainer was used to identify the predictive SC features for atrophy or cognition. The GCN-MLP model was validated in another independent dataset from Singapore (MACC) with 226 participants (61 CN, 112 MCI, 53 AD, follow-up period of T1 scans (3.1±1.3 years)) using transfer learning. Result The proposed GCN-MLP model predicted the annual rate of regional atrophy at the individual level in the main (R = 0.5407±0.0480; MAE = 0.0013±0.0001; EV = 0.2930±0.0516) and validation (R = 0.5323±0.0564; MAE = 0.0009±0.0001; EV = 0.2808±0.0559) datasets (Table 1; Figure 1). Graph edge SC of the target network contributed most to the atrophy prediction of its own network (Figure 2A&C). Nodal feature SC in hippocampus, striatum, and temporal network were major predictors of atrophy progression across all 1

关键词：

来源：评论

学校读者我要写书评

暂无评论

High Impedance Fault Detection based on Stockwell Transform

High Impedance Fault Detection based on Stockwell Transform

引用

IEEE/PES Transmission and Distribution Conference and Exposition: Latin America

作者： Erica Mangueira Lima Rodrigo de Almeida Coelho Nubia Silva Dantas Brito Benemar Alencar de Souza Electrical Engineering Post Graduate Program Federal University of Campina Grande Campina Grande Brazil

A high impedance fault (HIF) detection method is proposed in this paper. Several parameters are extracted using the Stockwell transform, which is a relatively new multi-resolution tool with the ability to provide good resolution on both time and frequency domain, simultaneously. Those parameters are used to identify a HIF occurrence and distinguish it from other common disturbances such as capacitor banks switching, feeder energizing and solid faults. Two databases are used to validate the method, one with simulated data and one with real HIF oscillographic records, obtained from field experiments. A brief analysis of parameters behavior is also presented, since it is necessary for method's development. Results show the method is able to detect HIF on both simulated and real data in viable time, using only the substation as observation point. Also it can distinguish the fault from other tested disturbances.

关键词： Frequency-domain analysis Transforms Harmonic analysis Capacitors Solids Databases Impedance

来源：评论

学校读者我要写书评

暂无评论

Two-dimensional pentagonal material Penta-PdPSe: A first-principle study

arXiv

引用

arXiv 2021年

作者： Bafekry, Asadolah Fadlallah, M.M. Faraji, M. Shafique, A. Jappor, H.R. Abdolhoseini Sarsari, I. Ang, Yee Sin Ghergherehchi, M. Department of Radiation Application Shahid Beheshti University Tehran*** Iran Department of Physics Faculty of Science Benha University Benha13518 Egypt Micro and Nanotechnology Graduate Program TOBB University of Economics and Technology Sogutozu Caddesi No 43 Sogutozu Ankara06560 Turkey Department of Physics Lahore University of Management Sciences Lahore Pakistan Department of Physics College of Education for Pure Sciences University of Babylon Hilla Iraq Department of Physics Isfahan University of Technology Isfahan84156-83111 Iran Cluster Singapore University of Technology and Design Singapore487372 Singapore Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Low-symmetry Penta-PdPSe with intrinsic in-plane anisotropy synthesized successfully [P. Li et al., Adv. Mater., 2102541 (2021)]. Motivated by this experimental discovery, we investigate the structural, mechanical, electronic, optical and thermoelectric properties of PdPSe monolayer via density functional theory calculations. The phonon dispersion, molecular dynamics simulation, the cohesive energy mechanical properties of the penta-PdPSe monolayer is verified to confirm its stability. The phonon spectrum represents a striking gap between the high-frequency and the low-frequency optical branches and an out-of-plane flexure mode with a quadratic dispersion in the long-wavelength limit. The Poisson’s ratio indicates that penta-PdPSe is a brittle monolayer. The pendaPdPSe monolayer is an indirect semiconductor with bandgap of 1.40 (2.07) eV using PBE (HSE06) functional. Optical properties simulation suggests that PdPSe is capable of absorbing a substantial range of visible to ultraviolet light. Band alignment analysis also reveals the compatibility of PdPSe for water splitting photocatalysis application. By combining the electrical and thermal transport properties of PdPSe, we show that a high PF is achievable at room temperature, thus making PdPSe a candidate material for thermoelectric application. Our findings reveal the strong potential of penta-PdPSe monolayer for a wide array of applications, including optoelectronic, water splitting and thermoelectric device applications. © 2021, CC BY.

关键词： Monolayers

来源：评论

学校读者我要写书评

暂无评论

Identifying irregularity electricity usage of customer behaviors using logistic regression and linear discriminant analysis 3

Identifying irregularity electricity usage of customer behav...

引用

3rd International Conference on Science in Information Technology, ICSITech 2017

作者： Lawi, Armin Wungo, Supriyadi La Manjang, Salama Department of Computer Science Post-graduate Program of Electrical Engineering Dept. Electrical Engineering Universitas Hasanuddin Makassar Indonesia

ISBN: (纸本)9781509058662

This study aims to implement a machine learning technique in identifying the irregularities of customer behavior on the use of prepaid electricity pulses. The methods used are Linear Discriminant Analysis and Logistic Regression. The performance of the classification system will be evaluated using the 10-fold cross-validation technique. Validation results are measured using accuracy, precision and recall values. In this research shows that the use of machine learning technique has a good performance in classification of electrical consumption behavior. Experimental results with the different amount of data testing indicate that Logistic Regression method has high accuracy, precision, and recall value when compared with Linear Discriminant Analysis that is 100%. This is due to Logistic Regression method can predict irregularities accurately because the addition of the amount of data does not affect the performance of the method. © 2017 IEEE.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Developing self-adaptive microservice systems: Challenges and directions

arXiv

引用

arXiv 2019年

作者： Mendonça, Nabor C. Jamshidi, Pooyan Garlan, David Pahl, Claus Post Graduate Program in Applied Informatics University of Fortaleza FortalezaCE Brazil Computer Science and Engineering Department University of South Carolina ColumbiaSC United States School of Computer Science Carnegie Mellon University PittsburghPA United States Faculty of Computer Science Free University of Bozen-Bolzano Bozen-Bolzano Italy

A self-adaptive system can dynamically monitor and adapt its behavior to preserve or enhance its quality attributes under uncertain operating conditions. This article identifies key challenges for the development of microservice applications as self-adaptive systems, using a cloud-based intelligent video surveillance application as a motivating example. It also suggests potential new directions for addressing most of the identified challenges by leveraging existing microservice practices and technologies. Copyright © 2019, The Authors. All rights reserved.

关键词： Adaptive systems

来源：评论

学校读者我要写书评

暂无评论

Instant Messaging as Information Goldmines to Digital Forensic: A Systematic Review 3

Instant Messaging as Information Goldmines to Digital Forens...

引用

3rd International Conference on Information Management and Technology, ICIMTech 2018

作者： Sihombing, Harry Chandra Fajar, Ahmad Nurul Utama, Ditdit Nugeraha Mercu Buana University Master of Electrical Engineering Jakarta Indonesia Information Systems Management Department Bina Nusantara University BINUS Graduate Program-Master of Information Systems Management Jakarta11480 Indonesia Computer Science Department Bina Nusantara University BINUS Graduate Program-Master of Computer Science Jakarta11480 Indonesia

ISBN: (纸本)9781538658215

The use of instant messaging (IM) application is very communal among smartphone users, as it delivers ease in interaction and communication. The speed at which technologies, growth, and expansion of networks infrastructure for high-speed data networks (e.g. wifi, 4G, etc.) are changing and the high number of IM applications are available. IM application usage is significantly escalating, also for doing illegitimate purposes, particularly to organize and coordinate criminal acts. They are practically exploited by the criminality groups involved when they target and interact with the victims, or try to run away from criminal occurrences. By systematically conducting a review to understand and to investigate IM applications topic coming from a number of scientific sources (e.g. manuscripts, metadata, files, etc.), a broader picture and opportunity to regain the valuable evidence in the investigation is academically provided. © 2018 IEEE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Benchmark problems for transcranial ultrasound simulation: Intercomparison of compressional wave models

arXiv

引用

arXiv 2022年

作者： Aubry, Jean-Francois Bates, Oscar Boehm, Christian Pauly, Kim Butts Christensen, Douglas Cueto, Carlos Gélat, Pierre Guasch, Lluis Jaros, Jiri Jing, Yun Jones, Rebecca Li, Ningrui Marty, Patrick Montanaro, Hazael Neufeld, Esra Pichardo, Samuel Pinton, Gianmarco Pulkkinen, Aki Stanziola, Antonio Thielscher, Axel Treeby, Bradley Van't Wout, Elwin Physics for Medicine Paris INSERM U1273 ESPCI Paris PSL University CNRS UMR 8063 France Department of Bioengineering Imperial College London Exhibition Road LondonSW7 2AZ United Kingdom Institute of Geophysics ETH Zürich Sonneggstrasse 5 Zürich8092 Switzerland Department of Radiology Stanford University StanfordCA United States Department of Biomedical Engineering Department of Electrical and Computer Engineering University of Utah United States Department of Surgical Biotechnology Division of Surgery and Interventional Science University College London LondonNW3 2PF United Kingdom Earth Science and Engineering Department Imperial College London London United Kingdom Centre of Excellence IT4Innovations Faculty of Information Technology Brno University of Technology Bozetechova 2 Brno612 00 Czech Republic Graduate Program in Acoustics The Pennsylvania State University University Park PA16802 United States Joint Department of Biomedical Engineering University of North Carolina at Chapel Hill North Carolina State University NC United States Department of Electrical Engineering Stanford University StanfordCA United States Zurich Switzerland Laboratory for Acoustics / Noise control Empa Swiss Federal Laboratories for Materials Science and Technology Dubendorf Switzerland Zurich Switzerland Radiology and Clinical Neurosciences Departments Cumming School of Medicine University of Calgary Canada Department of Applied Physics University of Eastern Finland Kuopio70211 Finland Department of Medical Physics and Biomedical Engineering University College London Gower Street LondonWC1E 6BT United Kingdom Technical University of Denmark Denmark Danish Research Center for Magnetic Resonance Copenhagen University Hospital Hvidovre Denmark Institute for Mathematical and Computational Engineering School of Engineering and Faculty of Mathematics Pontificia Universidad Catolica de Chile Santiago Chile

Computational models of acoustic wave propagation are frequently used in transcranial ultrasound therapy, for example, to calculate the intracranial pressure field or to calculate phase delays to correct for skull distortions. To allow intercomparison between the different modeling tools and techniques used by the community, an international working group was convened to formulate a set of numerical benchmarks. Here, these benchmarks are presented, along with intercomparison results. Nine different benchmarks of increasing geometric complexity are defined. These include a single-layer planar bone immersed in water, a multi-layer bone, and a whole skull. Two transducer configurations are considered (a focused bowl and a plane piston), giving a total of 18 permutations of the benchmarks. Eleven different modeling tools are used to compute the benchmark results. The models span a wide range of numerical techniques, including the finite-difference time-domain method, angular-spectrum method, pseudospectral method, boundary-element method, and spectral-element method. Good agreement is found between the models, particularly for the position, size, and magnitude of the acoustic focus within the skull. When comparing results for each model with every other model in a cross comparison, the median values for each benchmark for the difference in focal pressure and position are less than 10% and 1 mm, respectively. The benchmark definitions, model results, and intercomparison codes are freely available to facilitate further comparisons. Copyright © 2022, The Authors. All rights reserved.

关键词： Bone

来源：评论

学校读者我要写书评

暂无评论

Observation of topological polaritons and photonic magic angles in twisted van der Waals bi-layers

arXiv

引用

arXiv 2020年

作者： Alù, Andrea Krasnok, Alex Dai, Zhigao Wu, Jing Qiu, Cheng-Wei Wu, Yingjie Bao, Qiaoliang Si, Guangyuan Ou, Qingdong Hu, Guangwei Mazor, Yarden Zhang, Qing Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore Photonics Initiative Advanced Science Research Center City University of New York New YorkNY United States Monash University ClaytonVIC Australia Melbourne Centre for Nanofabrication Victorian Node of the Australian National Fabrication Facility ClaytonVIC Australia Singapore Singapore Faculty of Materials Science and Chemistry China University of Geosciences 388 Lumo Road Wuhan430074 China Department of Electrical and Computer Engineering University of Texas at Austin AustinTX United States Physics Program Graduate Center City University of New York New YorkNY United States

来源：评论

学校读者我要写书评

暂无评论

Ensembling Handcarafted Features to Representation Learning for Content Based Image Classification

Ensembling Handcarafted Features to Representation Learning ...

引用

IEEE Punecon

作者： Rik Das Khushbu Kumari P.K. Manjhi Sudeep D. Thepade Dept.of Post Graduate Program-Information Technology Xavier Institute of Social Service Ranchi Jharkhand India Dept.of Computer Applications Yogoda Satsanga Mahavidyalaya Ranchi Jharkhand India Dept.of Mathematics Vinoba Bhave University Hazaribag Jharkhand India Computer Engineering Dept. Pimpri Chinchwad College of Engineering Maharashtra India

ISBN: (数字)9781728119243

ISBN: (纸本)9781728119250

Content Based Image Classification (CBIC) has garnered massive interest within research community for it's applications and significances in multiple areas. This paper has explored a robust feature vector definition scheme based on fusion of handcrafted features to neural network based feature extraction, popularly known as representation learning. The extracted handcrafted features are primarily evaluated with classification results to identify the best color space for significant descriptor definition. Further, feature vector extraction using pre-trained Convolution Neural Network is exercised for evaluating classification performance with representation learning features. Finally, an early fusion of handcrafted feature and representation learning feature is accomplished to examine the classification performance of the model. The test bed is prepared using Wang dataset having 10 different categories of 1000 images. Six different color spaces are explored to finalize the best fit for feature extraction with the proposed handcrafted technique. Performance analyses of the proposed model have turned out to be superior compared to state-of-the-art techniques and have established the importance of fusion based approach in enhancing the accuracy of content based image classification.

关键词： Colour Intervals Color Space Hand-Crafted Features Representation Learning Fusion Classification color spaces Image classification Fusion reactions Fusion, biological Taxonomy FUSION fusion (melting) Feature extraction Learning based test bed Neural network Eigenvector

来源：评论

学校读者我要写书评

暂无评论

Big Data Governance for Building A Smart Cities

Big Data Governance for Building A Smart Cities

引用

International Conference on ICT For Smart Society (ICISS)

作者： Novan Zulkarnain Raymond Kosala Benny Ranti Suhono Harso Supangkat Computer Science Department BINUS Graduate Program Doctor of Computer Science Information Systems Department Bina Nusantara University Jakarta Indonesia Computer Science Department Bina Nusantara University Jakarta Indonesia Computer Science Department Universitas Indonesia Depok Indonesia School of Electrical and Informatics Engineering Institute of Technology Bandung Bandung Indonesia

There have been many studies conducted related to Smart City, IT Governance and Big Data. In this study aims to find out how the relationship between the three and how to form a framework to explain it. The methodology used is qualitative by looking for some literature on smart city framework, IT Governance framework, and a Big Data framework. From these results, an overall picture of the relationship between the three is concluded, where Big Data has a role in IT Governance. and also the relationship of IT Governance to the realization of Smart City. And the final results of this study produce a framework to explain the relationship between Smart City, IT Governance and Big Data.

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：