检索结果-内蒙古大学图书馆

On the usage of average hausdorff distance for segmentation performance assessment: hidden bias when used for ranking

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Aydin, Orhun Utku Taha, Abdel Aziz Hilbert, Adam Khalil, Ahmed A. Galinovic, Ivana Fiebach, Jochen B. Frey, Dietmar Madai, Vince Istvan Charité Lab for AI in Medicine Charité Universitätsmedizin Berlin Germany Research Studio Data Science Research Studios Austria Salzburg Austria Centre for Stroke Research Berlin Charité Universitätsmedizin Berlin Germany Department of Neurology Max Planck Institute for Human Cognitive and Brain Sciences Leipzig Germany School of Computing and Digital Technology Faculty of Computing Engineering and the Built Environment Birmingham City University United Kingdom

Average Hausdorff Distance (AVD) is a widely used performance measure to calculate the distance between two point sets. In medical image segmentation, AVD is used to compare ground truth images with segmentation results allowing their ranking. We identified, however, a ranking bias of AVD making it less suitable for segmentation ranking. To mitigate this bias, we present a modified calculation of AVD that we have coined balanced AVD (bAVD). To simulate segmentations for ranking, we manually created non-overlapping segmentation errors common in cerebral vessel segmentation as our use-case. Adding the created errors consecutively and randomly to the ground truth, we created sets of simulated segmentations with increasing number of errors. Each set of simulated segmentations was ranked using AVD and bAVD. We calculated the Kendall-rank-correlation-coefficient between the segmentation ranking and the number of errors in each simulated segmentation. The rankings produced by bAVD had a significantly higher average correlation (0.969) than those of AVD (0.847). In 200 total rankings, bAVD misranked 52 and AVD misranked 179 segmentations. Our proposed evaluation measure, bAVD, alleviates AVDs ranking bias making it more suitable for rankings and quality assessment of segmentations. Copyright © 2020, The Authors. All rights reserved.

关键词： Geometry

Generalised linear models for prognosis and intervention: Theory, practice, and implications for machine learning

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Arnold, Kellyn F. Davies, Vinny De Kamps, Marc Tennant, Peter W.G. Mbotwa, John Gilthorpe, Mark S. Leeds Institute for Data Analytics University of Leeds Leeds United Kingdom School of Medicine University of Leeds Leeds United Kingdom School of Computing Science University of Glasgow Glasgow United Kingdom School of Computing University of Leeds Leeds United Kingdom Alan Turing Institute London United Kingdom

In health research, machine learning (ML) is often hailed as the new frontier of data analytics which, combined with big data, will purportedly revolutionise delivery of healthcare and ultimately lead to more informed public health policy and clinical decision-making. However, much of the promise of ML is predicated on prediction, which is fundamentally distinct from causal inference. Nevertheless, these two concepts are often conflated in practice. We briefly consider the sources of this conflation, and the implications it has for modelling practices and subsequent interpretation, in the context of generalised linear models (GLMs). We then go on to consider the implications for ML methods (which are typically applied to prediction tasks), and offer lessons for researchers seeking to use ML for both prediction and causal inference. Our primary aim is to highlight the key differences between models for prediction and causal inference in order to encourage the critical and transparent application of ML to problems in health research. Copyright © 2019, The Authors. All rights reserved.

关键词： data Analytics

Innovative informatics methods for process mining in health care

学校读者我要写书评

暂无评论

Journal of Biomedical Informatics 2020年 109卷 103551-103551页

作者： Munoz-Gama, Jorge Martin, Niels Fernandez-Llatas, Carlos Johnson, Owen Sepúlveda, Marcos Department of Computer Science School of Engineering Pontificia Universidad Católica de Chile Santiago Chile Research Group Business Informatics Hasselt University Hasselt Belgium Data Analytics Laboratory Vrije Universiteit Brussel Brussels Belgium ITACA Institute – Process Mining 4 Health Lab Universitat Politècnica de Valencia Valencia Spain Karolinska Institutet Stockholm Sweden School of Computing Leeds University Leeds United Kingdom

A survey on graph processing accelerators: Challenges and opportunities

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Gui, Chuang-Yi Zheng, Long He, Bing-Sheng Liu, Cheng Chen, Xin-Yu Liao, Xiao-Fei Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China School of Computing National University of Singapore 117418 Singapore

Graph is a well known data structure to represent the associated relationships in a variety of applications, e.g., data science and machine learning. Despite a wealth of existing efforts on developing graph processing systems for improving the performance and/or energy efficiency on traditional architectures, dedicated hardware solutions, also referred to as graph processing accelerators, are essential and emerging to provide the benefits significantly beyond those pure software solutions can offer. In this paper, we conduct a systematical survey regarding the design and implementation of graph processing accelerator. Specifically, we review the relevant techniques in three core components toward a graph processing accelerator: preprocessing, parallel graph computation and runtime scheduling. We also examine the benchmarks and results in existing studies for evaluating a graph processing accelerator. Interestingly, we find that there is not an absolute winner for all three aspects in graph acceleration due to the diverse characteristics of graph processing and complexity of hardware configurations. We finially present to discuss several challenges in details, and to further explore the opportunities for the future research. Copyright © 2019, The Authors. All rights reserved.

关键词： Energy efficiency

Extending the Chemical Reach of the H3 Survey: Detailed Abundances of the Dwarf-galaxy Stellar Stream Wukong/LMS-1★

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Limberg, Guilherme Ji, Alexander P. Naidu, Rohan P. Chiti, Anirudh Rossi, Silvia Usman, Sam Ting, Yuan-Sen Zaritsky, Dennis Bonaca, Ana Borbolato, Lais Speagle, Joshua S. Chandra, Vedant Conroy, Charlie Universidade de São Paulo IAG Departamento de Astronomia São PauloSP 05508-090 Brazil Department of Astronomy & Astrophysics University of Chicago 5640 S Ellis Avenue ChicagoIL60637 United States Kavli Institute for Cosmological Physics University of Chicago ChicagoIL60637 United States Department of Physics Kavli Institute for Astrophysics and Space Research Massachusetts Institute of Technology CambridgeMA02139 United States Research School of Astronomy & Astrophysics Australian National University Weston CanberraACT2611 Australia School of Computing Australian National University Acton CanberraACT2601 Australia Department of Astronomy The Ohio State University 140 West 18th Avenue ColumbusOH43210 United States Steward Observatory University of Arizona 933 N. Cherry Ave. TucsonAZ85721-0065 United States Observatories of the Carnegie Institution for Science 813 Santa Barbara Street PasadenaCA91101 United States Department of Statistical Sciences University of Toronto TorontoONM5G 1Z5 Canada David A. Dunlap Department of Astronomy & Astrophysics University of Toronto TorontoONM5S 3H4 Canada Dunlap Institute for Astronomy & Astrophysics University of Toronto TorontoONM5S 3H4 Canada Data Sciences Institute University of Toronto TorontoONM5G 1Z5 Canada Center for Astrophysics Harvard & Smithsonian 60 Garden Street CambridgeMA02138 United States

We present the first detailed chemical-abundance analysis of stars from the dwarf-galaxy stellar stream Wukong/LMS-1 covering a wide metallicity range (−3.5 +0.7 and [Fe/H] ∼ −2.9) in Wukong/LMS-1 with strong enhancements in Sr, Y, and Zr, which is peculiar given its solar-level [Ba/Fe]. Wukong/LMS-1 stars have high abundances of α elements up to [Fe/H] −2, which is expected for relatively massive dwarfs. Towards the high-metallicity end, Wukong/LMS-1 becomes α-poor, revealing that it probably experienced fairly standard chemical evolution. We identified a pair of N- and Na-rich stars in Wukong/LMS-1, reminiscent of multiple stellar populations in globular clusters. This indicates that this dwarf galaxy contained at least one globular cluster that was completely disrupted in addition to two intact ones previously known to be associated with Wukong/LMS-1, which is possibly connected to similar evidence found in Indus. From these ≥3 globular clusters, we estimate the total mass of Wukong/LMS-1 to be ≈1010M☉, representing ∼1% of the present-day Milky Way. Finally, the [Eu/Mg] ratio in Wukong/LMS-1 continuously increases with metallicity, making this the first example of a dwarf galaxy where the production of r-process elements is clearly dominated by delayed sources, presumably neutron-star mergers. © 2023, CC BY.

关键词： Stars

DeepPurpose: A deep learning based drug repurposing toolkit

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Huang, Kexin Fu, Tianfan Xiao, Cao Glass, Lucas M. Sun, Jimeng Health Data Science Harvard T.H. Chan School of Public Health Harvard University BostonMA02115 United States College of Computing Georgia Institute of Technology AtlantaGA30332 United States Analytic Center of Excellence IQVIA CambridgeMA02139 United States Department of Computer Science University of Illinois at Urbana-Champaign UrbanaIL61801 United States

We present DeepPurpose, a deep learning toolkit for simple and efficient drug repurposing. With a few lines of code, DeepPurpose generates drug candidates based on aggregating five pretrained state-of-the-art models while offering flexibility for users to train their own models with 15 drug/target encodings and 50+ novel architectures. We demonstrated DeepPurpose using case studies, including repurposing for COVID-19 where promising candidates under trials are ranked high in our results. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

Joint segmentation and deformable registration with the presence of the noise using active contour and linear curvature

学校读者我要写书评

暂无评论

AIP Conference Proceedings 2024年第1期3150卷

作者： Nurul Asyiqin Mohd Fauzi Mazlinda Ibrahim Hoo Yann Seong Abdul Kadir Jumaat Lavdie Rada Faculty of Defence Science and Technology National Defence University of Malaysia 57000 Kuala Lumpur Malaysia Centre for Defence Foundation Studies National Defence University of Malaysia 57000 Kuala Lumpur Malaysia School of Mathematical Sciences College of Computing Informatics and Media Universiti Teknologi MARA (UiTM) 40450 Shah Alam Selangor Malaysia Institute for Big Data Analytics and Artificial Intelligence (IBDAAI) Universiti Teknologi MARA (UiTM) 40450 Shah Alam Selangor Malaysia Biomedical Engineering Department Bahcesehir University Besiktas Istanbul Turkey

Medical image processing requires image segmentation and image registration as important diagnostic tools. Image segmentation aims to split structures of interest into distinct components. Meanwhile, image registration finds an ideal transformation between given images. Despite their interrelationship, both tasks are often performed separately. As a result, it faces several problems when undertaken independently. Therefore, the joint models between segmentation and registration have advantages over the separate tasks, particularly when dealing with noisy images. This paper reviewed and compared three existing variational joint segmentation and registration (JSR) models based on active contour without edges and linear curvature. The models are tested on 2D mono-modal and multi-modal images with the presence of white Gaussian noise. The Dice coefficient metric and the registration performance measure are used to evaluate the performance of the models. Numerical results showed that the JSR model using the modified sum of the squared difference outperformed the other two JSR models for noisy mono-modal images. However, the JSR model using the modified normalized gradient fields performed better than the JSR model based on the modified mutual information for noisy multi-modal images.

关键词：

Intelligent identification of two-dimensional nanostructures by machine-learning optical microscopy

学校读者我要写书评

暂无评论

Nano Research 2018年第12期11卷 6316-6324页

作者： Xiaoyang Lin Zhizhong Si Wenzhi Fu Jianlei Yang Side Guo Yuan Cao Jin Zhang Xinhe Wang Peng Liu Kaili Jiang Weisheng Zhao Fert Beijing Research Institute School ofMicroelectronics & Beijing Advanced Innovation Center for Big Data and Brain Computing (BDBC)Beihang UniversityBeijing 100191China Beihang-GoertekJoint Microelectronics Institute Qingdao Research InstituteBeihang UniversityQingdao 266000China Fert Beijing Research Institute School of Computer Science and Engineering & Beijing Advanced Innovation Center for Big Data and Brain Computing (BDBC)Beihang UniversityBeijing 100191China State Key Laboratory of Low-Dimensional Quantum Physics Department of Physics & Tsinghua-Foxconn Nanotechnology Research CenterCollaborative Innovation Center of Quantum MatterTsinghua UniversityBeijing 100084China

Two-dimensional (2D) materials and their heterostructures, with wafer-scale synthesis methods and fascinating properties, have attracted significant interest and triggered revolutions in corresponding device applications. However, facile methods to realize accurate, intelligent, and large-area characterizations of these 2D nanostructures are still highly desired. Herein, we report the successful application of machine-learning strategy in the optical identification of 2D nanostructures. The machine-learning optical identification (MOI) method endows optical microscopy with intelligent insight into the characteristic color information of 2D nanostructures in the optical photograph. The experimental results indicate that the MOI method enables accurate, intelligent, and large-area characterizations of graphene, molybdenum disulfide, and their heterostructures, including identifications of the thickness, existence of impurities, and even stacking order. With the convergence of artificial intelligence and nanoscience, this intelligent identification method can certainly promote fundamental research and wafer-scale device applications of 2D nanostructures.

关键词： machine-learning optical identification two-dimensional (2D) material heterostructure artificial intelligence

The importance of environmental factors in forecasting Australian power demand

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Eshragh, Ali Ganim, Benjamin Perkins, Terry Bandara, Kasun School of Information and Physical Sciences University of Newcastle NSW Australia International Computer Science Institute BerkeleyCA United States School of Computing and Information Systems Melbourne Centre for Data Science University of Melbourne VIC Australia

We develop a time series model to forecast weekly peak power demand for three main states of Australia for a yearly time-scale, and show the crucial role of environmental factors in improving the forecasts. More precisely, we construct a seasonal autoregressive integrated moving average (SARIMA) model and reinforce it by employing the exogenous environmental variables including, maximum temperature, minimum temperature, and solar exposure. The estimated hybrid SARIMA-regression model exhibits an excellent mean absolute percentage error (MAPE) of 3.41%. Moreover, our analysis demonstrates the importance of the environmental factors by showing a remarkable improvement of 46.3% in MAPE for the hybrid model over the crude SARIMA model which merely includes the power demand variables. In order to illustrate the efficacy of our model, we compare our outcome with the state-of-the-art machine learning methods in forecasting. The results reveal that our model outperforms the latter *** Codes 62M10, 97K80 Copyright © 2019, The Authors. All rights reserved.

关键词： Electric power utilization