检索结果-内蒙古大学图书馆

Metadata Concepts for Advancing the Use of Digital Health Technologies in Clinical Research

学校读者我要写书评

暂无评论

Digital Biomarkers 2019年第3期3卷 116-132页

作者： Badawy, Reham Hameed, Farhan Bataille, Lauren Little, Max A. Claes, Kasper Saria, Suchi Cedarbaum, Jesse M. Stephenson, Diane Neville, Jon Maetzler, Walter Espay, Alberto J. Bloem, Bastiaan R. Simuni, Tanya Karlin, Daniel R. School of Computer Science University of Birmingham Birmingham United Kingdom Digital Medicine and Pfizer Innovation Research Lab Early Clinical Development Pfizer Inc. CambridgeMA United States College of Computer and Information Science Northeastern University BostonMA United States Analytics Informatics and Business Intelligence Chief Digital Office Pfizer Inc. New YorkNY United States Michael J. Fox Foundation for Parkinson's Research New YorkNY United States Media Lab Massachusetts Institute of Technology CambridgeMA United States UCB Biopharma Brussels Belgium Machine Learning and Healthcare Laboratory Departments of Computer Science Statistics and Health Policy Malone Center for Engineering in Healthcare Armstrong Institute for Patient Safety and Quality Johns Hopkins University BaltimoreMD United States Biogen CambridgeMA United States Critical Path Institute TucsonAZ United States Clinical Data Interchange Standards Consortium AustinTX United States Department of Neurology Christian Albrecht University Kiel Germany James J. and Joan A. Gardner Family Center for Parkinson's Disease and Movement Disorders University of Cincinnati CincinnatiOH United States Department of Neurology Donders Institute for Brain Cognition and Behavior Radboud University Medical Center Nijmegen Netherlands Department of Neurology Gardner Center for Parkinson's Disease and Movement Disorders UC Gardner Neuroscience Institute University of Cincinnati CincinnatiOH United States Tufts University School of Medicine BostonMA United States HealthMode New YorkNY United States School of Engineering and Applied Science Aston University BirminghamB47ET United Kingdom

Digital health technologies (smartphones, smartwatches, and other body-worn sensors) can act as novel tools to aid in the diagnosis and remote objective monitoring of an individual's disease symptoms, both in clinical care and in research. Nonetheless, such digital health technologies have yet to widely demonstrate value in clinical research due to insufficient data interpretability and lack of regulatory acceptance. Metadata, i.e., data that accompany and describe the primary data, can be utilized to better understand the context of the sensor data and can assist in data management, data sharing, and subsequent data analysis. The need for data and metadata standards for digital health technologies has been raised in academic and industry research communities and has also been noted by regulatory authorities. Therefore, to address this unmet need, we here propose a metadata set that reflects regulatory guidelines and that can serve as a conceptual map to (1) inform researchers on the metadata they should collect in digital health studies, aiming to increase the interpretability and exchangeability of their data, and (2) direct standard development organizations on how to extend their existing standards to incorporate digital health technologies. The proposed metadata set is informed by existing standards pertaining to clinical trials and medical devices, in addition to existing schemas that have supported digital health technology studies. We illustrate this specifically in the context of Parkinson's disease, as a model for a wide range of other chronic conditions for which remote monitoring would be useful in both care and science. We invite the scientific and clinical research communities to apply the proposed metadata set to ongoing and planned research. Where the proposed metadata fall short, we ask users to contribute to its ongoing revision so that an adequate degree of consensus can be maintained in a rapidly evolving technology landscape. © 2019 The Author(s

关键词： Metadata

Towards an Integrated Approach to Simultaneously Estimating the Frequency and Amplitude Modulations of SSVEP Signals from Consumer-grade EEG

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Autthasan, Phairot Du, Xiangqian Perera, Maneesha Lamyai, Sirakorn Itthipuripat, Sirawaj Yagi, Tohru Manoonpong, Poramate Wilaiprasitporn, Theerawit Rayong Thailand Department of Psychology Vanderbilt University Tennessee and Neurosciences Graduate Program University of California California USA and Learning Institute King Mongkuts University of Technology Thonburi Bangkok Thailand BRAIN Lab IST VISTEC Rayong Thailand Embodied AI & Neurorobotics Centre for BioRobotics Msk McKinney Mller Institute University of Southern Denmark Odense MDK-5230 Denmark Yagi Lab Department of Mechanical Engineering Tokyo Institute of Technology Tokyo Japan Data Analysis and Knowledge Discovery Laboratory Department of Computer Engineering Kasetsart University Bangkok Thailand department of Computer Engineering Sirindhorn International Institute of Technology Pathum Thani Thailand

For several decades, researchers have sought several solutions for helping patients who suffer from neuromuscular disorders. One of a few promising approaches is to invent brain-computer interfaces (BCIs) in which brain signals could be used to control computers and prosthetics. Due to their high signal-to-noise ratio, steady-state visually evoked potentials (SSVEPs) or electrical brain signals that oscillate at the same frequency as the frequency of a flickering visual stimulus on the computer screen has been widely used to build BCIs. While researchers have focused on developing frequency recognition algorithms for SSVEP-based BCIs, these algorithms do not precisely predict the modulation of SSVEP amplitude, known to change as a function of stimulus luminance contrast. Thus, in the present study we aimed to develop an integrated approach to simultaneously estimating the frequency and contrast-related amplitude modulations of the SSVEP signal. To do so, we developed a behavioral task in which human participants looked at a visual target flicking at a 7.5 Hz. Critically, across different experimental conditions, the luminance contrast of the visual target could change across time in several ways (i.e., the luminance contrast remained constant, increased gradually, decreased gradually, or increased and then decreased). SSVEPs were measured via an open-source and low-cost consumer-grade EEG device, namely OpenBCI, placed at the central occipital site. Our results displayed that the filter bank canonical correlation analysis (FBCCA) performed generally well in SSVEP frequency recognition, while support vector regression (SVR) outperformed the other supervised machine learning algorithms in predicting the contrast-dependent amplitude modulations of the SSVEP signal. These results demonstrated the applicability and efficiency of our integrated method at simultaneously predicting both frequency and amplitude of visually evoked signals in the human brain, proven useful for

关键词： Brain computer interface

Author Correction: Opportunities and challenges of single-cell and spatially resolved genomics methods for neuroscience discovery

学校读者我要写书评

暂无评论

Nature neuroscience 2025年第1期28卷 216页

作者： Boyan Bonev Gonçalo Castelo-Branco Fei Chen Simone Codeluppi M Ryan Corces Jean Fan Myriam Heiman Kenneth Harris Fumitaka Inoue Manolis Kellis Ariel Levine Mo Lotfollahi Chongyuan Luo Kristen R Maynard Mor Nitzan Vijay Ramani Rahul Satijia Lucas Schirmer Yin Shen Na Sun Gilad S Green Fabian Theis Xiao Wang Joshua D Welch Ozgun Gokce Genevieve Konopka Shane Liddelow Evan Macosko Omer Ali Bayraktar Naomi Habib Tomasz J Nowakowski Helmholtz Pioneer Campus Helmholtz Zentrum München Neuherberg Germany. Physiological Genomics Biomedical Center Ludwig-Maximilians-Universität München Munich Germany. Laboratory of Molecular Neurobiology Department of Medical Biochemistry and Biophysics Karolinska Institutet Stockholm Sweden. The Broad Institute of MIT and Harvard Cambridge MA USA. Moleculent Stockholm Sweden. Gladstone Institute of Neurological Disease San Francisco CA USA. Gladstone Institute of Data Science and Biotechnology San Francisco CA USA. Department of Neurology University of California San Francisco San Francisco CA USA. Department of Biomedical Engineering Johns Hopkins University Baltimore MD USA. Department of Brain and Cognitive Sciences MIT Cambridge MA USA. The Picower Institute for Learning and Memory MIT Cambridge MA USA. UCL Queen Square Institute of Neurology University College London London UK. Institute for the Advanced Study of Human Biology (WPI-ASHBi) Kyoto University Kyoto Japan. Computer Science and Artificial Intelligence Lab Massachusetts Institute of Technology Cambridge MA USA. Spinal Circuits and Plasticity Unit National Institute of Neurological Disorders and Stroke Bethesda MD USA. Institute of Computational Biology Helmholtz Center Munich - German Research Center for Environmental Health Neuherberg Germany. Wellcome Sanger Institute Wellcome Genome Campus Cambridge UK. Department of Human Genetics University of California Los Angeles Los Angeles CA USA. Lieber Institute for Brain Development Baltimore MD USA. Department of Psychiatry Johns Hopkins School of Medicine Baltimore MD USA. Department of Neuroscience Johns Hopkins School of Medicine Baltimore MD USA. School of Computer Science and Engineering The Hebrew University of Jerusalem Jerusalem Israel. Racah Institute of Physics The Hebrew University of Jerusalem Jerusalem Israel. Faculty of Medicine The Hebrew University of Jerusalem Jerusalem Israel. Department of Biochemis

Author Correction: Federated learning enables big data for rare cancer boundary detection

学校读者我要写书评

暂无评论

Nature communications 2023年第1期14卷 436页

作者： Sarthak Pati Ujjwal Baid Brandon Edwards Micah Sheller Shih-Han Wang G Anthony Reina Patrick Foley Alexey Gruzdev Deepthi Karkada Christos Davatzikos Chiharu Sako Satyam Ghodasara Michel Bilello Suyash Mohan Philipp Vollmuth Gianluca Brugnara Chandrakanth J Preetha Felix Sahm Klaus Maier-Hein Maximilian Zenk Martin Bendszus Wolfgang Wick Evan Calabrese Jeffrey Rudie Javier Villanueva-Meyer Soonmee Cha Madhura Ingalhalikar Manali Jadhav Umang Pandey Jitender Saini John Garrett Matthew Larson Robert Jeraj Stuart Currie Russell Frood Kavi Fatania Raymond Y Huang Ken Chang Carmen Balaña Jaume Capellades Josep Puig Johannes Trenkler Josef Pichler Georg Necker Andreas Haunschmidt Stephan Meckel Gaurav Shukla Spencer Liem Gregory S Alexander Joseph Lombardo Joshua D Palmer Adam E Flanders Adam P Dicker Haris I Sair Craig K Jones Archana Venkataraman Meirui Jiang Tiffany Y So Cheng Chen Pheng Ann Heng Qi Dou Michal Kozubek Filip Lux Jan Michálek Petr Matula Miloš Keřkovský Tereza Kopřivová Marek Dostál Václav Vybíhal Michael A Vogelbaum J Ross Mitchell Joaquim Farinhas Joseph A Maldjian Chandan Ganesh Bangalore Yogananda Marco C Pinho Divya Reddy James Holcomb Benjamin C Wagner Benjamin M Ellingson Timothy F Cloughesy Catalina Raymond Talia Oughourlian Akifumi Hagiwara Chencai Wang Minh-Son To Sargam Bhardwaj Chee Chong Marc Agzarian Alexandre Xavier Falcão Samuel B Martins Bernardo C A Teixeira Flávia Sprenger David Menotti Diego R Lucio Pamela LaMontagne Daniel Marcus Benedikt Wiestler Florian Kofler Ivan Ezhov Marie Metz Rajan Jain Matthew Lee Yvonne W Lui Richard McKinley Johannes Slotboom Piotr Radojewski Raphael Meier Roland Wiest Derrick Murcia Eric Fu Rourke Haas John Thompson David Ryan Ormond Chaitra Badve Andrew E Sloan Vachan Vadmal Kristin Waite Rivka R Colen Linmin Pei Murat Ak Ashok Srinivasan J Rajiv Bapuraj Arvind Rao Nicholas Wang Ota Yoshiaki Toshio Moritani Sevcan Turk Joonsang Lee Snehal Prabhudesai Fanny Morón Jacob Mandel Konstantinos Kamnitsas Ben Glocker Luke V M Dixon Matthew Williams Peter Zamp Center for Biomedical Image Computing and Analytics (CBICA) University of Pennsylvania Philadelphia PA USA. Department of Radiology Perelman School of Medicine University of Pennsylvania Philadelphia PA USA. Department of Pathology and Laboratory Medicine Perelman School of Medicine University of Pennsylvania Philadelphia PA USA. Department of Informatics Technical University of Munich Munich Bavaria Germany. Intel Corporation Santa Clara CA USA. Department of Neuroradiology Heidelberg University Hospital Heidelberg Germany. Clinical Cooperation Unit Neuropathology German Cancer Consortium (DKTK) within the German Cancer Research Center (DKFZ) Heidelberg Germany. Department of Neuropathology Heidelberg University Hospital Heidelberg Germany. Division of Medical Image Computing German Cancer Research Center Heidelberg Germany. Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Heidelberg Germany. Neurology Clinic Heidelberg University Hospital Heidelberg Germany. Department of Radiology & Biomedical Imaging University of California San Francisco San Francisco CA USA. Symbiosis Center for Medical Image Analysis Symbiosis International University Pune Maharashtra India. Department of Neuroimaging and Interventional Radiology National Institute of Mental Health and Neurosciences Bangalore Karnataka India. Department of Radiology School of Medicine and Public Health University of Wisconsin Madison WI USA. Department of Medical Physics School of Medicine and Public Health University of Wisconsin Madison WI USA. Leeds Teaching Hospitals Trust Department of Radiology Leeds UK. Department of Radiology Brigham and Women's Hospital Harvard Medical School Boston MA USA. Athinoula A. Martinos Center for Biomedical Imaging Massachusetts General Hospital Charlestown MA USA. Catalan Institute of Oncology Badalona Spain. Consorci MAR Parc de Salut de Barcelona Catalonia Spain. Department of Radiology (IDI

Brain-computer interface with corrupted EEG data: A tensor completion approach

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Solé-Casals, J. Caiafa, C.F. Zhao, Q. Cichocki, A. University of Vic Central University of Catalonia Data and Signal Processing Research Group Vic Catalonia Spain - CCT-La Plata CONICET CICPBA Villa Elisa Buenos Aires Argentina Department of Psychological and Brain Sciences Indiana University BloomingtonIN United States Tensor Learning Unit RIKEN Center for Advanced Intelligence Tokyo Japan School of Automation Guangdong University of Technology China Skolkovo Institute of Science and Technology Moscow Russia Department of Informatics Nicolaus Copernicus University Torun87-100 Poland College of Computer Science Hangzhou Dianzi University Hangzhou310018 China

Background / Introduction: One of the current issues in Brain-Computer Interface (BCI) is how to deal with noisy Electroencephalography (EEG) measurements organized as multidimensional datasets (tensors). On the other hand, recently, significant advances have been made in multidimensional signal completion algorithms that exploit tensor decomposition models to capture the intricate relationship among entries in a multidimensional signal. We propose to use tensor completion applied to EEG data for improving the classification performance in a motor imagery BCI system with corrupted measurements. Noisy measurements (electrode misconnections, subject movements, etc.) are considered as unknowns (missing samples) that are inferred from a tensor decomposition model (tensor completion). Methods: We evaluate the performance of four recently proposed tensor completion algorithms, CP-WOPT (Acar et al, 2011), 3DPB-TC (Caiafa et al, 2013), BCPF (Zhao et al, 2015) and HaLRT (Liu et al. (2013), plus a simple interpolation strategy, first with random missing entries and then with missing samples constrained to have a specific structure (random missing channels), which is a more realistic assumption in BCI applications. Results: We measured the ability of these algorithms to reconstruct the tensor from observed data. Then, we tested the classification accuracy of imagined movement in a BCI experiment with missing samples. We show that for random missing entries, all tensor completion algorithms can recover missing samples increasing the classification performance compared to a simple interpolation approach. For the random missing channels case, we show that tensor completion algorithms help to reconstruct missing channels, significantly improving the accuracy in the classification of motor imagery (MI), however, not at the same level as clean data. Summarizing, compared to the interpolation case, all tensor completion algorithms succeed to increase the classification performance by

关键词： Electroencephalography

The higher education space, connecting degree programs from individuals' choices

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Candia, Cristian Encarnacaõ, Sara Pinheiro, Flávio L. Facultad de Gobierno Universidad Del Desarrollo Santiago Chile MIT Media Lab Collective Learning Group Massachusetts Institute of Technology Department of Networks and Data Science Central European University Budapest Hungary Interdisciplinary Centre of Social Sciences [CICS.NOVA Universidade Nova de Lisboa Lisboa Portugal Applications of Theoretical Physics Group Porto Salvo Portugal Universidade Nova de Lisboa Lisboa Portugal

Is it possible to derive organizing principles of higher education systems from the applicants' choices Here, we introduce the Higher Education Space (HES) as a way to describe the complex relationship between degree programs. The HES is based on the application of methods from network science to data on the revealed preferences of applicants to the higher education systems of Chile and Portugal. Our work reveals: 1) the existence of a positive assortment of features-such as gender balance, application scores, unemployment levels, demand-supply ratio, etc- A long the network structure of the HES;2) that the decaying of the prevalence level of a feature from a focal degree program extends beyond the dyadic relationships captured by the HES;3) temporal variations in different features do not spillover/propagate throughout the system in the same way;4) differences in unemployment levels reported among pairs of degree programs are minimized when taking into consideration the connectivity structure of the HES, largely outperforming the differences in matched pairs using traditional similarity measures;and 5) grouping of degree programs based in the network structure of the HES provides an applicant perspective that complements existing classification systems. Our findings support the HES as a multi-dimensional framework that can effectively contribute to the governance of higher education systems. Copyright © 2018, The Authors. All rights reserved.

关键词： Employment

Recurrent Neural Networks on Drifting Time-of-Flight Measurements

学校读者我要写书评

暂无评论

Recurrent Neural Networks on Drifting Time-of-Flight Measure...

International Conference on Indoor Positioning and Indoor Navigation (IPIN)

作者： Tobias Feigl Thorsten Nowak Michael Philippsen Thorsten Edelhäußer Christopher Mutschler Programming Systems Group (Informatics II) Friedrich-Alexander University Erlangen-Nürnberg Erlangen Germany Institute of Information Technology (Comm. Electronics) Friedrich-Alexander University Erlangen-Nürnberg Erlangen Germany Precise Positioning and Analytics Department Fraunhofer Institute for Integrated Circuits IIS Nürnberg Nürnberg Germany Machine Learning and Data Analytics Lab Friedrich-Alexander University Erlangen-Nürnberg Erlangen Germany

Kalman filters (KFs) are popular methods to estimate position information from a set of time-of-flight (ToF) values in radio frequency (RF)-based locating systems. Such filters are proven to be optimal under zero-mean Gaussian error distributions. In presence of multipath propagation ToF measurement errors drift due to small-scale motion. This results in changing phases of the multipath components (MPCs) which cause a drift on the ToF measurements. Thus, on a short-term scale the ToF measurements have a non-constant bias that changes while moving. KFs cannot distinguish between the drifting measurement errors and the true motion of the tracked object. Hence, very rigid motion models have to be used for the KF which commonly causes the filters to diverge. Therefore, the KF cannot resolve the short-term errors of consecutive measurements and the long-term motion of the tracked object. This paper presents a data-driven approach that uses training sequences to derive a near-optimal position estimator. A Long Short-Term Memory (LSTM) Recurrent Neural Network (RNN) learns to interpret drifting errors in ToF measurements of a tracked dynamic object directly from raw ToF data. Our evaluation shows that our approach outperforms state-of-the-art KFs on both synthetically generated and real-world dynamic motion trajectories that include drifting ToF measurement errors.

关键词： Trajectory Hidden Markov models Tracking Measurement uncertainty Neural networks Position measurement Dynamics

Global tracking of marine megafauna space use reveals how to achieve conservation targets

学校读者我要写书评

暂无评论

Science (New York, N.Y.) 2025年第6751期388卷 1086-1097页

作者： Ana M M Sequeira Jorge P Rodríguez Sarah A Marley Hannah J Calich Mirjam van der Mheen Michelle VanCompernolle Lucy M Arrowsmith Lauren R Peel Nuno Queiroz Marisa Vedor Ivo da Costa Gonzalo Mucientes Ana Couto Nicolas E Humphries Sara Abalo-Morla Francisco J Abascal Debra L Abercrombie Katya Abrantes F Alberto Abreu-Grobois André S Afonso Pedro Afonso Heidi Ahonen Susanne Åkesson Joanna Alfaro-Shigueto Russel D Andrews Frédéric Angelier Marina Antonopoulou Javier A Arata Gonzalo Araujo Randall Arauz José Manuel Arcos Igor Arregui Haritz Arrizabalaga Marie Auger-Méthé Steffen Bach Fred Bailleul Robin W Baird George H Balazs Susan G Barco Adam Barnett Warren Baverstock Alastair M M Baylis Annalea Beard Juan Bécares Eduardo J Belda Ian Bell Ashley Bennison Scott R Benson Diego Bernal Michael L Berumen Sandra Bessudo Natalia P A Bezerra Antonin V Blaison Gabriela S Blanco Barbara A Block Mark Bolton Mark E Bond Ramón Bonfil Camrin D Braun Annette C Broderick Michael de L Brooke Annabelle M L Brooks Edward J Brooks Ignacio M Bruno Jennifer M Burns Michael E Byrne Steven E Campana Hamish A Campbell Richard A Campbell Aaron Carlisle Ruth H Carmichael Gemma Carroll Paolo Casale Filipe R Ceia Demian D Chapman Taylor K Chapple Jean-Benoit Charrassin Andre Chiaradia John Chisholm Christopher R Clarke Thomas A Clay Christophe Cleguer Elizabeth Clingham Eric E G Clua Jesse E M Cochran Rochelle Constantine Robert W Cooper Estelle Crochelet Michelle Cronin Eduardo Cuevas Kayla P DaCosta Laurent Dagorn Ryan Daly Randall W Davis P J Nico de Bruyn Carlos Delgado-Trejo Thomas Dellinger Solène Derville Stella Diamant Andrew DiMatteo Kara L Dodge Philip D Doherty Michael C Double Alistair D M Dove Thomas K Doyle Michael J Drew Lindsay L Dubbs Clinton A J Duffy Peter H Dutton Ewan W J Edwards Luke D Einoder Mark V Erdmann Eduardo Espinoza Nicole Esteban Ana Isabel Fagundes Chris Feare Steven H Ferguson Luciana C Ferreira Francesco Ferretti John Filmalter Brittany Finucci G Chris Fischer Richard J Fitzpatrick Jorge Fontes Angela Formia Division of Ecology and Evolution Research School of Biology The Australian National University Canberra (Australian Capital Territory) Australia. UWA Oceans Institute and the School of Biological Sciences The University of Western Australia Perth (Western Australia) Australia. Instituto de Física Interdisciplinar y Sistemas Complejos (IFISC) CSIC-UIB Palma de Mallorca Spain. Instituto Mediterráneo de Estudios Avanzados (IMEDEA) CSIC-UIB Esporles Illes Balears Spain. C.A. Illes Balears Universidad Nacional de Educación a Distancia (UNED) Palma Spain. Delegación Territorial en Illes Balears Agencia Estatal de Meteorología (AEMET) Muelle de Poniente s/n Palma Spain. Scotland's Rural College (SRUC) Craibstone Estate Bucksburn Aberdeen UK. Oceans Graduate School and the UWA Oceans Institute The University of Western Australia Perth (Western Australia) Australia. School of Engineering and the UWA Oceans Institute The University of Western Australia Perth (Western Australia) Australia. Department of Biodiversity Conservation and Attractions Biodiversity and Conservation Science Kensington (Western Australia) Australia. Save Our Seas Foundation Geneva Switzerland. The Manta Trust Catemwood House Norwood Lane Corscombe Dorset UK. Centro de Investigação em Biodiversidade e Recursos Genéticos (CIBIO) InBIO Laboratório Associado Campus de Vairão Universidade do Porto Vairão Portugal. BIOPOLIS Program in Genomics Biodiversity and Land Planning Campus de Vairao Vairão Portugal. Instituto de Investigaciones Marinas Consejo Superior de Investigaciones Científicas (IIM-CSIC) Vigo Pontevedra Spain. School of Biological Sciences University of Aberdeen Aberdeen UK. Biomathematics and statistics Scotland The kings building Edinburgh Scotland. Marine Biological Association (MBA) The Laboratory Citadel Hill Plymouth UK. Instituto de Investigación para la Gestión Integrada de Zonas Costeras Universitat Politècnica de València Gandia València Spain. Instituto Español de O

The recent Kunming-Montreal Global Biodiversity Framework (GBF) sets ambitious goals but no clear pathway for how zero loss of important biodiversity areas and halting human-induced extinction of threatened species will be achieved. We assembled a multi-taxa tracking dataset (11 million geopositions from 15,845 tracked individuals across 121 species) to provide a global assessment of space use of highly mobile marine megafauna, showing that 63% of the area that they cover is used 80% of the time as important migratory corridors or residence areas. The GBF 30% threshold (Target 3) will be insufficient for marine megafauna's effective conservation, leaving important areas exposed to major anthropogenic threats. Coupling area protection with mitigation strategies (e.g., fishing regulation, wildlife-traffic separation) will be essential to reach international goals and conserve biodiversity.

关键词：

An online-learning approach to inverse optimization

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Bärmann, Andreas Martin, Alexander Pokutta, Sebastian Schneider, Oskar Lehrstuhl für Wirtschaftsmathematik Department Mathematik Friedrich-Alexander-Universität Erlangen-Nürnberg Cauerstraße 11 Erlangen91058 Germany Laboratory for Interactive Optimization and Learning School of Industrial & Systems Engineering Georgia Institute of Technology Ferst Drive 755 NW AtlantaGA United States Gruppe Data Science and Optimization Fraunhofer Arbeitsgruppe für Supply-Chain Services SCS Fraunhofer Institut für Integrierte Schaltungen IIS Nordostpark 93 Nürnberg90411 Germany

In this paper, we demonstrate how to learn the objective function of a decision-maker while only observing the problem input data and the decision-maker's corresponding decisions over multiple rounds. Our approach is based on online learning and works for linear objectives over arbitrary feasible sets for which we have a linear optimization oracle. As such, it generalizes previous approaches based on KKT-system decomposition and dualization. The two exact algorithms we present - based on multiplicative weights updates and online gradient descent respectively - converge at a rate of O(1/√T) and thus allow taking decisions which are essentially as good as those of the observed decision-maker already after relatively few observations. We also discuss several useful generalizations, such as the approximate learning of non-linear objective functions and the case of suboptimal observations. Finally, we show the effectiveness and possible applications of our methods in a broad computational study.68Q32, 68T05, 90C90, 90C11 Copyright © 2018, The Authors. All rights reserved.

关键词： Gradient methods