检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Lindenbaum, Ofir Stanley, Jay S. Wolf, Guy Krishnaswamy, Smita Department of Genetics Yale University New HavenCT United States Applied Mathematics Program Yale University New HavenCT United States Computational Biology & Bioinformatics Program Yale University New HavenCT United States Department of Computer Science Yale University New HavenCT United States

We propose a new type of generative model of high-dimensional data that learns a manifold geometry of the data, rather than density, and can generate points evenly along this manifold. This is in contrast to existing generative models that represent data density, and are strongly affected by noise and other artifacts of data collection. We demonstrate how this approach corrects sampling biases and artifacts, and improves several downstream data analysis tasks such as clustering and classification. Finally, we demonstrate that this approach is especially useful in biology where, despite the advent of single-cell technologies, rare subpopulations and gene-interaction relationships are affected by biased sampling. We show that SUGAR can generate hypothetical populations and reveal intrinsic patterns and mutual-information relationships between genes on a single cell dataset of hematopoiesis. Copyright © 2018, The Authors. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Inventory control systems with safety stock and reorder point approach 1

Inventory control systems with safety stock and reorder poin...

引用

1st International Conference on Information and Communications Technology, ICOIACT 2018

作者： Efrilianda, Devi Ajeng Mustafid Isnanto, R. Rizal Master Program of Information Systems School of Post Graduate Studies Diponegoro University Semarang Indonesia Department of Statistics Faculty of Science and Mathematics Diponegoro University Semarang Central Java Indonesia Department of Computer Systems Faculty of Engineering Diponegoro University Semarang Indonesia

ISBN: (纸本)9781538609545

The inventory control systems has an important role to monitor the condition of the goods at the supply chain stage of goods distribution from the central warehouse to retail in accordance with consumer demand. The research aims to develop inventory control systems on the supply chain distribution of goods from suppliers to retail through the central warehouse with minimal supply chain costs. Minimization of supply chain cost using martingale model of forecast evaluation, and the result as the basis for calculation of safety stock and reorder point. The results of research are the system that can be used to control inventory and renewal of goods in the central warehouse by calculating the minimization of supply chain cost based on consumer demand. Case studies were conducted on the supply chain distribution of goods from the central warehouse to the retail in Semarang. The observation data derived from the goods distribution from central warehouse to retail for certain products over 4 time periods. Through such inventory control system, can minimize supply chain cost, and product inventory level can be maintained in time and amount of inventory that must be fulfilled. © 2018 IEEE.

关键词： Supply chains

来源：评论

学校读者我要写书评

暂无评论

STRING-AVERAGING ALGORITHMS FOR CONVEX FEASIBILITY WITH INFINITELY MANY SETS

arXiv

引用

arXiv 2018年

作者： Kong, T. Yung Pajoohesh, Homeira Herman, Gabor T. Computer Science Department Queens College City University of New York FlushingNY11367 United States Mathematics Department Medgar Evers College City University of New York BrooklynNY11225 United States Computer Science Ph.D. Program The Graduate Center City University of New York New YorkNY10016 United States

Algorithms for convex feasibility find or approximate a point in the intersection of given closed convex sets. Typically there are only finitely many convex sets, but the case of infinitely many convex sets also has some applications. In this context, a string is a finite sequence of points each of which is obtained from the previous point by considering one of the convex sets. In a string-averaging algorithm, an iterative step from a first point to a second point computes a number of strings, all starting with the first point, and then calculates a (weighted) average of those strings’ end-points: This average is that iterative step’s second point, which is used as the first point for the next iterative step. For string-averaging algorithms based on strings in which each point either is the projection of the previous point on one of the convex sets or is equal to the previous point, we present theorems that provide answers to the following question: "How can the iterative steps be specified so that the string-averaging algorithm generates a convergent sequence whose limit lies in the intersection of the sets of a given convex feasibility problem?" This paper focuses on the case where the given collection of convex sets is infinite, whereas prior work on the same question that we are aware of has assumed the collection of convex sets is finite (or has been applicable only to a small subset of the algorithms we consider). The string-averaging algorithms that are shown to generate a convergent sequence whose limit lies in the intersection are also shown to be perturbation resilient, so they can be superiorized to generate sequences that also converge to a point of the intersection but in a manner that is superior with respect to some application-dependent criterion.46N10 46N40 47H09 47H10 47J25 47N10 65F10 65J99 65K10 90C25 90C30 Copyright © 2018, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

HCVMultiscaleFit: A Simulator For Parameter Estimation in Multiscale Models Of Hepatitis C Virus Dynamics

引用

AIP conference proceedings 2020年第1期2293卷 420028页

作者： Alexander Churkin Vladimir Reinharz Stephanie Lewkiewicz Harel Dahari Danny Barash Department of Software Engineering Sami Shamoon College of Engineering Beer-Sheva Israel. Center for Soft and Living Matter Institute for Basic Science Ulsan South Korea. Department of Mathematics University of California at Los Angeles Los Angeles California USA. The Program for Experimental and Theoretical Modeling Division of Hepatology Department of Medicine Stritch School of Medicine Loyola University Chicago Maywood Illinois USA. Department of Computer Science Ben-Gurion Universty Beer-Sheva Israel.

Callibration in mathematical models that are based on differential equations is known to be of fundamental importance. For sophisticated models such as age-structured models that simulate biological agents, parameter estimation or fitting (callibration) that solves all cases of data points available presents a formidable challenge, as efficiency considerations need to be employed in order for the method to become practical. In the case of multiscale models of hepatitis C virus dynamics that deal with partial differential equations (PDEs), a fully numerical parameter estimation method was developed that does not require an analytical approximation of the solution to the multiscale model equations, avoiding the necessity to derive the long-term approximation for each model. However, the method is considerably slow because of precision problems in estimating derivatives with respect to the parameters near their boundary values, making it almost impractical for general use. In order to overcome this limitation, two steps have been taken that significantly reduce the running time by orders of magnitude and thereby lead to a practical method. First, constrained optimization is used, letting the user add constraints relating to the boundary values of each parameter before the method is executed. Second, optimization is performed by derivative-free methods, eliminating the need to evaluate expensive numerical derviative approximations. These steps that were successful in significantly speeding up a highly non-efficient approach, rendering it practical, can also be adapted to multiscale models of other viruses and other sophisticated differential equation models. The newly efficient methods that were developed as a result of the above approach are described. Illustrations are provided using a user-friendly simulator that incorporates the efficient methods for multiscale models. We provide a simulator called HCVMultiscaleFit with a Graphical User Interface that applies these

关键词：

来源：评论

学校读者我要写书评

暂无评论

Control the Water wheel with the Internet of Things

引用

Journal of Physics: Conference Series 2019年第1期1361卷

作者： Zulfian Azmi Zarlis, Muhammad Efendi, Syahril Mawengkang, Herman Postgraduate Doctoral of Computer Science Universitas Sumatera Utara Indonesia Program Pasca Sarjana Doktoral Ilmu Komputer Universitas Sumatera Utara Padang Bulan USU Medan Indonesia Department Of Mathematics Universitas Sumatera Utara Indonesia

The waterwheel is a component of the spinning water that energizes the rotating axis. Waterwheel is a means to convert water energy into mechanical energy in the form of torque on the shaft of the mill. One of the functions of water is to improve water quality. But the use of waterwheels manually is inefficient, because the mill works continuously even though the water quality is good. So it takes intelligent algorithm to be able to produce waterwheels that can benefit the local community for the needs of high protein foods. By adjusting some variables in determining water quality to improve the water quality of shrimp habitat, consisting of: water pH, water temperature, disoolved oxygen and salinity. And in uncertainty input from existing parameters can form a probability distribution that determines water quality and the movement of the mill. The sensor reading results into a reference microcontroller in sending PWM signals on the boost converter as DC motor drivers to run waterwheels slowly or quickly based on inputs. And with the Internet of Things (IoT) technology will make it easier to control, more practical, effective and efficient.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ten quick tips for deep learning in biology

arXiv

引用

arXiv 2021年

作者： Lee, Benjamin D. Gitter, Anthony Greene, Casey S. Raschka, Sebastian Maguire, Finlay Titus, Alexander J. Kessler, Michael D. Lee, Alexandra J. Chevrette, Marc G. Stewart, Paul Allen Britto-Borges, Thiago Cofer, Evan M. Yu, Kun-Hsing Carmona, Juan Jose Fertig, Elana J. Kalinin, Alexandr A. Signal, Beth Lengerich, Benjamin J. Triche, Timothy J. Boca, Simina M. In-Q-Tel Labs School of Engineering and Applied Sciences Harvard University Department of Genetics Harvard Medical School United States Department of Biostatistics and Medical Informatics University of Wisconsin-Madison MadisonWI United States Morgridge Institute for Research MadisonWI United States Department of Systems Pharmacology and Translational Therapeutics Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States Department of Biochemistry and Molecular Genetics University of Colorado School of Medicine AuroraCO United States Center for Health AI University of Colorado School of Medicine AuroraCO United States Department of Statistics University of Wisconsin Madison United States Faculty of Computer Science Dalhousie University Canada University of New Hampshire Bioeconomy.XYZ United States Department of Oncology Johns Hopkins University United States Institute for Genome Sciences University of Maryland School of Medicine United States Genomics and Computational Biology Graduate Program University of Pennsylvania United States Department of Systems Pharmacology and Translational Therapeutics University of Pennsylvania United States Wisconsin Institute for Discovery Department of Plant Pathology University of Wisconsin-Madison United States Department of Biostatistics and Bioinformatics Moffitt Cancer Center TampaFL United States Section of Bioinformatics and Systems Cardiology Klaus Tschira Institute for Integrative Computational Cardiology University Hospital Heidelberg Germany University Hospital Heidelberg Germany Lewis-Sigler Institute for Integrative Genomics Princeton University PrincetonNJ United States Graduate Program in Quantitative and Computational Biology Princeton University PrincetonNJ United States Department of Biomedical Informatics Harvard Medical School United States Department of Pathology Brigham and Women's Hospital United States Philips Healthcare CambridgeMA United States Philips Research

Machine learning is a modern approach to problem-solving and task automation. In particular, machine learning is concerned with the development and applications of algorithms that can recognize patterns in data and use them for predictive modeling. Artificial neural networks are a particular class of machine learning algorithms and models that evolved into what is now described as deep learning. Given the computational advances made in the last decade, deep learning can now be applied to massive data sets and in innumerable contexts. Therefore, deep learning has become its own subfield of machine learning. In the context of biological research, it has been increasingly used to derive novel insights from high-dimensional biological data. To make the biological applications of deep learning more accessible to scientists who have some experience with machine learning, we solicited input from a community of researchers with varied biological and deep learning interests. These individuals collaboratively contributed to this manuscript's writing using the GitHub version control platform and the Manubot manuscript generation toolset. The goal was to articulate a practical, accessible, and concise set of guidelines and suggestions to follow when using deep learning. In the course of our discussions, several themes became clear: the importance of understanding and applying machine learning fundamentals as a baseline for utilizing deep learning, the necessity for extensive model comparisons with careful evaluation, and the need for critical thought in interpreting results generated by deep learning, among others. © 2021, CC BY.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Modeling global dynamics from local snapshots with deep generative neural networks

arXiv

引用

arXiv 2018年

作者： Gigante, Scott Van Dijk, David Moon, Kevin R. Strzalkowski, Alexander Wolf, Guy Krishnaswamy, Smita Computational Biology and Bioinformatics Program Yale University New HavenCT United States Department of Genetics Yale University New HavenCT United States Department of Computer Science Yale University New HavenCT United States Department of Mathematics and Statistics Utah State University LoganUT United States Department of Computer Science Princeton University PrincetonNJ United States Department of Mathematics and Statistics Universitéde Montreacuteal MontéalQC Canada

Complex high dimensional stochastic dynamic systems arise in many applications in the natural sciences and especially biology. However, while these systems are difficult to describe analytically, "snapshot" measurements that sample the output of the system are often available. In order to model the dynamics of such systems given snapshot data, or local transitions, we present a deep neural network framework we call Dynamics Modeling Network or DyMoN. DyMoN is a neural network framework trained as a deep generative Markov model whose next state is a probability distribution based on the current state. DyMoN is trained using samples of current and nextstate pairs, and thus does not require longitudinal measurements. We show the advantage of DyMoN over shallow models such as Kalman filters and hidden Markov models, and other deep models such as recurrent neural networks in its ability to embody the dynamics (which can be studied via perturbation of the neural network) and generate longitudinal hypothetical trajectories. We perform three case studies in which we apply DyMoN to different types of biological systems and extract features of the dynamics in each case by examining the learned model. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Increasing accuracy of classification physical activity based on smartphone using ensemble logistic regression with boosting method

引用

Journal of Physics: Conference Series 2019年第4期1341卷

作者： Lawi, A Aziz, F Wungo, S L Department of Computer Science Universitas Hasanuddin Makassar Indonesia. 90245 Faculty of Mathematics and Natural Sciences Universitas Pancasakti Makassar Indonesia. 90132 Program Study Informatics Engineering STMIK Kreatindo Monokwari Indonesia. 98300

At present, the smartphone is equipped with several sensors such as Accelerometer, Gravity sensor, and Gyroscope which can be used to recognize human physical activities such as walking upstair and walking downstairs etc. Machine learning is needed to group data and get information. Statistical methods have poor performance in classifying because procedures must be met. To overcome this, an ensemble technique was used. This study proposes the application of the gradientboost ensemble method to classify walking upstair and walking downstairs. The *** system is designed for data retrieval using a smartphone. Then, the dataset will be partitioned into 70% training data and 30% test data. The results show that the performance of the ensemble boosting method produces 81.82% accuracy, 86.11% sensitivity and 77.50% specificity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BTEX exposure and its body burden pose differential risks for asthma and its phenotypic clusters

引用

Allergy 2023年第7期78卷 2036-2040页

作者： Yuan-Ting Hsu Chao-Chien Wu Chin-Chou Wang Wen-Yu Chung Chau-Chyun Sheu Yi-Hsin Yang Ming-Yen Cheng Ruay-Sheng Lai Sum-Yee Leung Chi-Cheng Lin Yu-Feng Wei Ching-Hsiung Lin Sheng-Hao Lin Jeng-Yuan Hsu Wei-Chang Huang Chia-Cheng Tseng Yung-Fa Lai Meng-Hsuan Cheng Huang-Chi Chen Chih-Jen Yang Chian-Heng Su Chien-Jen Wang Shih-Chang Hsu Chih-Hsing Hung Chon-Lin Lee Ming-Shyan Huang Shau-Ku Huang National Institute of Environmental Health Sciences National Health Research Institutes Miaoli Taiwan. Department of Internal Medicine Division of Pulmonary and Critical Care Medicine Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine Kaohsiung Taiwan. Department of Public Health Kaohsiung Medical University Kaohsiung Taiwan. Department of Computer Science and Information Engineering National Kaohsiung University of Science and Technology Kaohsiung Taiwan. Department of Internal Medicine Division of Pulmonary and Critical Care Medicine Kaohsiung Medical University Hospital Kaohsiung Medical University Kaohsiung Taiwan. Department of Internal Medicine School of Medicine College of Medicine Kaohsiung Medical University Kaohsiung Taiwan. National Institute of Cancer Research National Health Research Institutes Tainan Taiwan. Department of Mathematics Hong Kong Baptist University Hong Kong China. Division of Chest Medicine Kaohsiung Veterans General Hospital Kaohsiung Taiwan. Department of Internal Medicine Chest Division Antai Medical Care Cooperation Antai Tian-Sheng Memorial Hospital Pingtung Taiwan. Department of Internal Medicine E-Da Cancer Hospital I-Shou University Kaohsiung Taiwan. Department of Internal Medicine Division of Chest Medicine Changhua Christian Hospital Changhua Taiwan. Institute of Genomics and Bioinformatics National Chung Hsing University Taichung Taiwan. Department of Recreation and Holistic Wellness MingDao University Changhua Taiwan. Department of Medical Research Division of Clinical Research Taichung Veterans General Hospital Taichung Taiwan. Department of Internal Medicine Division of Chest Medicine Taichung Veterans General Hospital Taichung Taiwan. Department of Medical Technology Jen-Teh Junior College of Medicine Nursing and Management Miaoli Taiwan. School of Medicine Chung Shan Medical University Taichung Taiwan. Ph.D. Program in Translational Medicine National Chung Hsing Universi

来源：评论

学校读者我要写书评

暂无评论

A large-scale ENIGMA multisite replication study of brain age in depression

引用

Neuroimage: Reports 2022年第4期2卷 100149-100149页

作者： Han, Laura K.M. Dinga, Richard Leenings, Ramona Hahn, Tim Cole, James H. Aftanas, Lyubomir I. Amod, Alyssa R. Besteher, Bianca Colle, Romain Corruble, Emmanuelle Couvy-Duchesne, Baptiste Danilenko, Konstantin V. Fuentes-Claramonte, Paola Gonul, Ali Saffet Gotlib, Ian H. Goya-Maldonado, Roberto Groenewold, Nynke A. Hamilton, Paul Ichikawa, Naho Ipser, Jonathan C. Itai, Eri Koopowitz, Sheri-Michelle Li, Meng Okada, Go Okamoto, Yasumasa Churikova, Olga S. Osipov, Evgeny A. Penninx, Brenda W.J.H. Pomarol-Clotet, Edith Rodríguez-Cano, Elena Sacchet, Matthew D. Shinzato, Hotaka Sim, Kang Stein, Dan J. Uyar-Demir, Aslihan Veltman, Dick J. Schmaal, Lianne Centre for Youth Mental Health The University of Melbourne Parkville VIC Australia Orygen Parkville VIC Australia Department of Cognitive Science & Artificial Intelligence Tilburg University Tilburg Netherlands Institute for Translational Psychiatry University of Münster Münster Germany Faculty of Mathematics and Computer Science University of Münster Münster Germany Centre for Medical Image Computing Department of Computer Science University College London United Kingdom Dementia Research Centre Queen Square Institute of Neurology University College London United Kingdom Scientific Research Institute of Neuroscience and Medicine Novosibirsk Russian Federation Novosibirsk State University Novosibirsk Russian Federation Department of Psychiatry & Mental Health Neuroscience Institute University of Cape Town South Africa Department of Psychiatry and Psychotherapy Jena University Hospital Jena Germany Service Hospitalo-Universitaire de Psychiatrie de Bicêtre Mood Center Paris Saclay Assistance Publique-Hôpitaux de Paris Hôpitaux Universitaires Paris-Saclay Hôpital de Bicêtre Le Kremlin Bicêtre F-94275 France MOODS Team INSERM 1018 CESP (Centre de Recherche en Epidémiologie et Santé des Populations) Université Paris-Saclay Faculté de Médecine Paris-Saclay Le Kremlin Bicêtre F-94275 France Sorbonne Université Institut du Cerveau - Paris Brain Institute - ICM CNRS Inria Inserm AP-HP Hôpital de La Pitié Salpêtrière Paris F-75013 France Institute for Molecular Bioscience The University of Queensland St Lucia 4072 QLD Australia FIDMAG Hermanas Hospitalarias Research Foundation Barcelona Spain CIBERSAM Barcelona Spain SoCAT Lab Department of Psychiatry School of Medicine Ege University Izmir Turkey Department of Psychology Stanford University Stanford CA United States Laboratory of Systems Neuroscience and Imaging in Psychiatry (SNIP-Lab) University Medical Center Göttingen Göttingen Germany Center for Social and Affective Neuroscience Department o

Background: Several studies have evaluated whether depressed persons have older appearing brains than their nondepressed peers. However, the estimated neuroimaging-derived “brain age gap” has varied from study to study, likely driven by differences in training and testing sample (size), age range, and used modality/features. To validate our previously developed ENIGMA brain age model and the identified brain age gap, we aim to replicate the presence and effect size estimate previously found in the largest study in depression to date (N = 2126 controls & N = 2675 cases;+1.08 years [SE 0.22], Cohen's d = 0.14, 95% CI: 0.08–0.20), in independent cohorts that were not part of the original study. Methods: A previously trained brain age model (***/enigma_brainage) based on 77 FreeSurfer brain regions of interest was used to obtain unbiased brain age predictions in 751 controls and 766 persons with depression (18–75 years) from 13 new cohorts collected from 20 different scanners. Meta-regressions were used to examine potential moderating effects of basic cohort characteristics (e.g., clinical and scan technical) on the brain age gap. Results: Our ENIGMA MDD brain age model generalized reasonably well to controls from the new cohorts (predicted age vs. age: r = 0.73, R² = 0.47, MAE = 7.50 years), although the performance varied from cohort to cohort. In these new cohorts, on average, depressed persons showed a significantly higher brain age gap of +1 year (SE 0.35) (Cohen's d = 0.15, 95% CI: 0.05–0.25) compared with controls, highly similar to our previous finding. Significant moderating effects of FreeSurfer version 6.0 (d = 0.41, p = 0.007) and Philips scanner vendor (d = 0.50, p < 0.0001) were found, leading to more positive effect size estimates. Conclusions: This study further validates our previously developed ENIGMA brain age algorithm. Importantly, we replicated the brain age gap in depression with a comparable effect size. Thus, two large-s

关键词： Biological aging Brain age Depression ENIGMA consortium Replication study

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：