检索结果-内蒙古大学图书馆

Extracting human emotions at different places based on facial expressions and spatial clustering analysis

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Kang, Yuhao Jia, Qingyuan Gao, Song Zeng, Xiaohuan Wang, Yueyao Angsuesser, Stephan Liu, Yu Ye, Xinyue Fei, Teng Geospatial Data Science Lab Department of Geography University of Wisconsin Madison United States School of Resources and Environmental Sciences Wuhan University Wuhan China College of Urban and Environment Sciences Peking University Beijing China Institute of Remote Sensing and Geographical Information Systems Peking University Beijing China Urban Informatics and Spatial Computing Lab Department of Informatics New Jersey Institute of Technology Newark United States

The emergence of big data enables us to evaluate the various human emotions at places from a statistic perspective by applying affective computing. In this study, a novel framework for extracting human emotions from large-scale georeferenced photos at different places is proposed. After the construction of places based on spatial clustering of user generated footprints collected in social media websites, online cognitive services are utilized to extract human emotions from facial expressions using state-of-the-art computer vision techniques. And two happiness metrics are defined for measuring the human emotions at different places. To validate the feasibility of the framework, we take 80 tourist attractions around the world as an example and a happiness ranking list of places is generated based on human emotions calculated over 2 million faces detected out from over 6 million photos. Different kinds of geographical contexts are taken into consideration to find out the relationship between human emotions and environmental factors. Results show that much of the emotional variation at different places can be explained by a few factors such as openness. The research may offer insights on integrating human emotions to enrich the understanding of sense of place in geography and in place-based GIS. Copyright © 2019, The Authors. All rights reserved.

关键词： Big data

Ordered magnetic fields around the 3C 84 central black hole

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Paraschos, Georgios Filippos Kim, J.-Y. Wielgus, M. Röder, J. Krichbaum, T.P. Ros, E. Agudo, I. Myserlis, I. Moscibrodzka, M. Traianou, E. Zensus, J.A. Blackburn, L. Chan, C.-K. Issaoun, S. Janssen, M. Johnson, M.D. Fish, V.L. Akiyama, K. Alberdi, A. Alef, W. Algaba, J.C. Anantua, R. Asada, K. Azulay, R. Bach, U. Baczko, A.-K. Ball, D. Baloković, M. Barrett, J. Bauböck, M. Benson, B.A. Bintley, D. Blundell, R. Bouman, K.L. Bower, G.C. Boyce, H. Bremer, M. Brinkerink, C.D. Brissenden, R. Britzen, S. Broderick, A.E. Broguiere, D. Bronzwaer, T. Bustamante, S. Byun, D.-Y. Carlstrom, J.E. Ceccobello, C. Chael, A. Chang, D.O. Chatterjee, K. Chatterjee, S. Chen, M.T. Chen, Y. Cheng, X. Cho, I. Christian, P. Conroy, N.S. Conway, J.E. Cordes, J.M. Crawford, T.M. Crew, G.B. Cruz-Osorio, A. Cui, Y. Dahale, R. Davelaar, J. De Laurentis, M. Deane, R. Dempsey, J. Desvignes, G. Dexter, J. Dhruv, V. Doeleman, S.S. Dougal, S. Dzib, S.A. Eatough, R.P. Emami, R. Falcke, H. Farah, J. Fomalont, E. Ford, H.A. Foschi, M. Fraga-Encinas, R. Freeman, W.T. Friberg, P. Fromm, C.M. Fuentes, A. Galison, P. Gammie, C.F. García, R. Gentaz, O. Georgiev, B. Goddi, C. Gold, R. Gómez-Ruiz, A.I. Gómez, J.L. Gu, M. Gurwell, M. Hada, K. Haggard, D. Haworth, K. Hecht, M.H. Hesper, R. Heumann, D. Ho, L.C. Ho, P. Honma, M. Huang, C.L. Huang, L. Hughes, D.H. Ikeda, S. Impellizzeri, C.M.V. Inoue, M. James, D.J. Jannuzi, B.T. Jeter, B. Jaing, W. Jiménez-Rosales, A. Jorstad, S. Joshi, A.V. Jung, T. Karami, M. Karuppusamy, R. Kawashima, T. Keating, G.K. Kettenis, M. Kim, D.-J. Kim, J. Kim, J. Kino, M. Koay, J.Y. Kocherlakota, P. Kofuji, Y. Koch, P.M. Koyama, S. Kramer, C. Kramer, J.A. Kramer, M. Kuo, C.-Y. La Bella, N. Lauer, T.R. Lee, D. Lee, S.-S. Leung, P.K. Levis, A. Li, Z. Lico, R. Lindahl, G. Lindqvist, M. Lisakov, M. Liu, J. Liu, K. Liuzzo, E. Lo, W.-P. Lobanov, A.P. Max-Planck-Institut für Radioastronomie Auf dem Hügel 69 BonnD-53121 Germany Department of Astronomy and Atmospheric Sciences Kyungpook National University Daegu702-701 Korea Republic of Institute of Physics Silesian University in Opava Bezručovo nám. 13 OpavaCZ-746 01 Czech Republic Instituto de Astrofísica de Andalucía-CSIC Glorieta de la Astronomía s/n GranadaE-18008 Spain Avenida Divina Pastora 7 Local 20 GranadaE-18012 Spain Radboud University P.O. Box 9010 Nijmegen6500 GL Netherlands Black Hole Initiative Harvard University 20 Garden Street CambridgeMA02138 United States Center for Astrophysics Harvard & Smithsonian 60 Garden Street CambridgeMA02138 United States Steward Observatory Department of Astronomy University of Arizona 933 N. Cherry Ave. TucsonAZ85721 United States Data Science Institute University of Arizona 1230 N. Cherry Ave. TucsonAZ85721 United States Program in Applied Mathematics University of Arizona 617 N. Santa Rita TucsonAZ85721 United States NASA Hubble Fellowship Program Einstein Fellow United States Massachusetts Institute of Technology Haystack Observatory 99 Millstone Road WestfordMA01886 United States National Astronomical Observatory of Japan 2-21-1 Osawa Mitaka Tokyo181-8588 Japan Department of Physics Faculty of Science Universiti Malaya Kuala Lumpur50603 Malaysia Department of Physics & Astronomy The University of Texas at San Antonio One UTSA Circle San AntonioTX78249 United States Institute of Astronomy and Astrophysics Academia Sinica 11F of Astronomy-Mathematics Building AS/NTU No. 1 Sec. 4 Roosevelt Rd. Taipei10617 Taiwan Departament d’Astronomia i Astrofísica Universitat de València C. Dr. Moliner 50 Burjassot ValènciaE-46100 Spain Observatori Astronòmic Universitat de València C. Catedrático José Beltrán 2 València PaternaE-46980 Spain Department of Space Earth and Environment Chalmers University of Technology Onsala Space Observatory OnsalaSE-43992 Sweden Yale C

Context. 3C 84 is a nearby radio source with a complex total intensity structure, showing linear polarisation and spectral patterns. A detailed investigation of the central engine region necessitates the use of very-long-baseline interferometry (VLBI) above the hitherto available maximum frequency of 86 GHz. Aims. Using ultrahigh resolution VLBI observations at the currently highest available frequency of 228 GHz, we aim to perform a direct detection of compact structures and understand the physical conditions in the compact region of 3C 84. Methods. We used Event Horizon Telescope (EHT) 228 GHz observations and, given the limited (u, v)-coverage, applied geometric model fitting to the data. Furthermore, we employed quasi-simultaneously observed, ancillary multi-frequency VLBI data for the source in order to carry out a comprehensive analysis of the core structure. Results. We report the detection of a highly ordered, strong magnetic field around the central, supermassive black hole of 3C 84. The brightness temperature analysis suggests that the system is in equipartition. We also determined a turnover frequency of νm = (113 ± 4) GHz, a corresponding synchrotron self-absorbed magnetic field of BSSA = (2.9 ± 1.6) G, and an equipartition magnetic field of Beq = (5.2 ± 0.6) G. Three components are resolved with the highest fractional polarisation detected for this object (mnet = (17.0 ± 3.9)%). The positions of the components are compatible with those seen in low-frequency VLBI observations since 2017-2018. We report a steeply negative slope of the spectrum at 228 GHz. We used these findings to test existing models of jet formation, propagation, and Faraday rotation in 3C 84. Conclusions. The findings of our investigation into different flow geometries and black hole spins support an advection-dominated accretion flow in a magnetically arrested state around a rapidly rotating supermassive black hole as a model of the jet-launching system in the core of 3C 84. However,

关键词： Magnetic fields

Presenting unbinned differential cross section results

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Arratia, Miguel Butter, Anja Campanelli, Mario Croft, Vincent Gillberg, Dag Ghosh, Aishik Lohwasser, Kristin Malaescu, Bogdan Mikuni, Vinicius Nachman, Benjamin Rojo, Juan Thaler, Jesse Winterhalder, Ramon Department of Physics and Astronomy University of California RiversideCA92521 United States Thomas Jefferson National Accelerator Facility Newport NewsVA23606 United States Institut für Theoretische Physik Universität Heidelberg Heidelberg Germany University College London LondonWC1E 6BT United Kingdom Department of Physics and Astronomy Tufts University BostonMA02155 United States Department of Physics Carleton University OttawaONK1S 5B6 Canada Department of Physics and Astronomy University of California IrvineCA92697 United States Physics Division Lawrence Berkeley National Laboratory BerkeleyCA94720 United States University of Sheffield SheffieldS10 2TN United Kingdom LPNHE Sorbonne Université Université de Paris CNRS/IN2P3 Paris France National Energy Research Scientific Computing Center BerkeleyCA94720 United States Berkeley Institute for Data Science University of California BerkeleyCA94720 United States Nikhef Theory Group Science Park 105 Amsterdam1098 XG Netherlands Department of Physics and Astronomy Vrije Universiteit Amsterdam AmsterdamNL-1081 HV Netherlands Center for Theoretical Physics Massachusetts Institute of Technology CambridgeMA02139 United States The NSF AI Institute for Artificial Intelligence and Fundamental Interactions Université Catholique de Louvain Louvain-la-Neuve1348 Belgium

Machine learning tools have empowered a qualitatively new way to perform differential cross section measurements whereby the data are unbinned, possibly in many dimensions. Unbinned measurements can enable, improve, or at least simplify comparisons between experiments and with theoretical predictions. Furthermore, many-dimensional measurements can be used to define observables after the measurement instead of before. There is currently no community standard for publishing unbinned data. While there are also essentially no measurements of this type public, unbinned measurements are expected in the near future given recent methodological advances. The purpose of this paper is to propose a scheme for presenting and using unbinned results, which can hopefully form the basis for a community standard to allow for integration into analysis workflows. This is foreseen to be the start of an evolving community dialogue, in order to accommodate future developments in this field that is rapidly evolving. © 2021, CC BY.

关键词：

A new machine learning framework for understanding the link etween cannabis use and first-episode psychosis 12

学校读者我要写书评

暂无评论

A new machine learning framework for understanding the link ...

12th Annual Conference on Health Informatics Meets eHealth, eHealth 2018

作者： Alghamdi, Wajdi Stamate, Daniel Stahl, Daniel Zamyatin, Alexander Murray, Robin Di Forti, Marta Data Science and Soft Computing Lab Department of Computing Goldsmiths University of London United Kingdom Department of Biostatistics and Health Informatics Institute of Psychiatry Psychology and Neuroscience King's College London United Kingdom Faculty of Informatics Department of Applied Informatics National Research Tomsk State University Russia Department of Psychosis Studies Institute of Psychiatry Psychology and Neuroscience King's College London United Kingdom MRC Social Genetic and Developmental Psychiatry Centre Institute of Psychiatry Psychology and Neuroscience King's College London United Kingdom

ISBN: (纸本)9781614998570

Lately, several studies started to investigate the existence of links between cannabis use and psychotic disorders. This work proposes a refined Machine Learning framework for understanding the links between cannabis use and 1st episode psychosis. The novel framework concerns extracting predictive patterns from clinical data using optimised and post-processed models based on Gaussian Processes, Support Vector Machines, and Neural Networks algorithms. The cannabis use attributes' predictive power is investigated, and we demonstrate statistically and with ROC analysis that their presence in the dataset enhances the prediction performance of the models with respect to models built on data without these specific attributes. © 2018 The authors and IOS Press.

关键词： eHealth First-episode psychosis Gaussian processes Machine learning Neural networks Support vector machine

ASVspoof 2017 Version 2.0: meta-data analysis and baseline enhancements

学校读者我要写书评

暂无评论

ASVspoof 2017 Version 2.0: meta-data analysis and baseline e...

2018 Speaker and Language Recognition Workshop, ODYSSEY 2018

作者： Delgado, Héctor Todisco, Massimiliano Sahidullah, Md Evans, Nicholas Kinnunen, Tomi Lee, Kong Aik Yamagishi, Junichi Department of Digital Security EURECOM France MULTISPEECH Inria France School of Computing University of Eastern Finland Finland Data Science Research Laboratories NEC Corporation Japan Digital Content and Media Sciences Research Division National Institute of Informatics Japan Centre of Speech Technology Research University of Edinburgh United Kingdom

The now-acknowledged vulnerabilities of automatic speaker verification (ASV) technology to spoofing attacks have spawned interests to develop so-called spoofing countermeasures. By providing common databases, protocols and metrics for their assessment, the ASVspoof initiative was born to spearhead research in this area. The first competitive ASVspoof challenge held in 2015 focused on the assessment of countermeasures to protect ASV technology from voice conversion and speech synthesis spoofing attacks. The second challenge switched focus to the consideration of replay spoofing attacks and countermeasures. This paper describes Version 2.0 of the ASVspoof 2017 database which was released to correct data anomalies detected post-evaluation. The paper contains as-yet unpublished meta-data which describes recording and playback devices and acoustic environments. These support the analysis of replay detection performance and limits. Also described are new results for the official ASVspoof baseline system which is based upon a constant Q cesptral coefficient frontend and a Gaussian mixture model backend. Reported are enhancements to the baseline system in the form of log-energy coefficients and cepstral mean and variance normalisation in addition to an alternative i-vector backend. The best results correspond to a 48% relative reduction in equal error rate when compared to the original baseline system. © ODYSSEY 2018. All rights reserved.

关键词： Metadata

Integrated presentation attack detection and automatic speaker verification: Common features and Gaussian back-end fusion 19

学校读者我要写书评

暂无评论

Integrated presentation attack detection and automatic speak...

19th Annual Conference of the International Speech Communication, INTERSPEECH 2018

作者： Todisco, Massimiliano Delgado, Héctor Lee, Kong Aik Sahidullah, Md Evans, Nicholas Kinnunen, Tomi Yamagishi, Junichi Department of Digital Security EURECOM France Data Science Research Laboratories NEC Corporation Japan MULTISPEECH Inria France School of Computing University of Eastern Finland Finland Digital Content and Media Sciences Research Division National Institute of Informatics Japan Centre of Speech Technology Research University of Edinburgh United Kingdom

The vulnerability of automatic speaker verification (ASV) systems to spoofing is widely acknowledged. Recent years have seen an intensification in research efforts to develop spoofing countermeasures, also known as presentation attack detection (PAD) systems. Much of this work has involved the exploration of features that discriminate reliably between bona fide and spoofed speech. While there are grounds to use different front-ends for ASV and PAD systems (they are different tasks) the use of a single front-end has obvious benefits, not least convenience and computational efficiency, especially when ASV and PAD are combined. This paper investigates the performance of a variety of different features used previously for both ASV and PAD and assesses their performance when combined for both tasks. The paper also presents a Gaussian back-end fusion approach to system combination. In contrast to cascaded architectures, it relies upon the modelling of the two-dimensional score distribution stemming from the combination of ASV and PAD in parallel. This approach to combination is shown to generalise particularly well across independent ASVspoof 2017 v2.0 development and evaluation datasets. © 2018 International Speech Communication Association. All rights reserved.

关键词： Computational efficiency

Automated Detection and Forecasting of COVID-19 using Deep Learning Techniques: A Review

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Shoeibi, Afshin Khodatars, Marjane Jafari, Mahboobeh Ghassemi, Navid Sadeghi, Delaram Moridian, Parisa Khadem, Ali Alizadehsani, Roohallah Hussain, Sadiq Zare, Assef Sani, Zahra Alizadeh Khozeimeh, Fahime Nahavandi, Saeid Rajendra Acharya, U. Gorriz, Juan M. The Data Science and Computational Intelligence Institute University of Granada Spain The Computer Engineering Department Ferdowsi University of Mashhad Mashhad Iran Deakin University VIC3217 Australia The Faculty of Electrical Engineering K. N. Toosi University of Technology Tehran Iran System Administrator at Dibrugarh University Assam786004 India Faculty of Electrical Engineering Gonabad Branch Islamic Azad University Gonabad Iran Rajaie Cardiovascular Medical and Research Center Iran University of Medical Sciences Tehran Iran The School of Mathematics Physics and Computing University of Southern Queensland Springfield Australia Dept. of Psychiatry University of Cambridge United Kingdom

Coronavirus, or COVID-19, is a hazardous disease that has endangered the health of many people around the world by directly affecting the lungs. COVID-19 is a medium-sized, coated virus with a single-stranded RNA, and also has one of the largest RNA genomes and is approximately 120 nm. The X-Ray and computed tomography (CT) imaging modalities are widely used to obtain a fast and accurate medical diagnosis. Identifying COVID-19 from these medical images is extremely challenging as it is time-consuming and prone to human errors. Hence, artificial intelligence (AI) methodologies can be used to obtain consistent high performance. Among the AI methods, deep learning (DL) networks have gained popularity recently compared to conventional machine learning (ML). Unlike ML, all stages of feature extraction, feature selection, and classification are accomplished automatically in DL models. In this paper, a complete survey of studies on the application of DL techniques for COVID-19 diagnostic and segmentation of lungs is discussed, concentrating on works that used X-Ray and CT images. Additionally, a review of papers on the forecasting of coronavirus prevalence in different parts of the world with DL is presented. Lastly, the challenges faced in the detection of COVID-19 using DL techniques and directions for future research are discussed. © 2020, CC BY-NC-ND.

关键词： COVID-19

A review on image processing for fish disease detection

学校读者我要写书评

暂无评论

Journal of Physics: Conference Series 2021年第1期1997卷

作者： S N Pauzi M G Hassan N Yusoff N H Harun A H Abu Bakar B C Kua School of Technology Management and Logistics Universiti Utara Malaysia 06010 Sintok Kedah Malaysia Department of Data Science Universiti Malaysia Kelantan 16100 Kota Bharu Kelantan Malaysia School of Computing Universiti Utara Malaysia 06010 Sintok Kedah Malaysia Faculty of Electronic Engineering Technology Universiti Malaysia Perlis 01000 Kangar Perlis Malaysia National Fish Health Research Centre Fisheries Research Institute Department of Fisheries Malaysia 11960 Batu Maung Penang Malaysia

Fish disease is considered the main cause for production and economic losses by fish farmers. Fish disease detection and health monitoring is a demanding task by manual method of human visualization. Therefore, any potential approach that is fast, reliable and possesses high automation supports an interest in this issue. Nowadays, with the current emergence in the technology revolution, image processing has been extensively used in disease detection field, especially in human and plant, aiding the human experts in providing the right treatment. Image processing technique offers opportunities to improve the traditional approach in achieving accurate results. Besides, several steps in image processing are adopted including image acquisition, image pre-processing, image segmentation, object detection, feature extraction and classification. The objective of this paper is to briefly review the work established in the fish disease detection field with the use of numerous classification techniques of image processing, including rule-based expert system, machine learning, deep learning, statistical method and hybrid method. The present review recognizes the need for improvement in these image processing approaches that would be valuable for further advancement in terms of performance.

关键词：

The GAPS program at TNG XLVII: The unusual formation history of V1298 Tau

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Turrini, D. Marzari, F. Polychroni, D. Claudi, R. Desidera, S. Mesa, D. Pinamonti, M. Sozzetti, A. Mascareño, A. Suárez Damasso, M. Benatti, S. Malavolta, L. Micela, G. Zinzi, A. Béjar, V.J.S. Biazzo, K. Bignamini, A. Bonavita, M. Borsa, F. Del Burgo, C. Chauvin, G. Delorme, P. Hernández, J.I. González Gratton, R. Hagelberg, J. Janson, M. Langlois, M. Lanza, A.F. Lazzoni, C. Lodieu, N. Maggio, A. Mancini, L. Molinari, E. Molinaro, M. Murgas, F. Nardiello, D. Inaf - Osservatorio Astrofisico di Torino via Osservatorio 20 Pino TorineseI-10025 Italy Icsc National Research Centre for High Performance Computing Big Data and Quantum Computing Via Magnanelli 2 Casalecchio di RenoI-40033 Italy Inaf - Istituto di Astrofisica e Planetologia Spaziali via Fosso del Cavaliere 100 RomaI-00133 Italy Dipartimento di Fisica e Astronomia Università di Padova Via Marzolo 8 PadovaI-35121 Italy Inaf - Osservatorio Astronomico di Padova Vicolo dell'Osservatorio 5 PadovaI-35122 Italy Inaf - Osservatorio Astronomico di Trieste Via G. B. Tiepolo 11 TriesteI-34143 Italy Inaf - Osservatorio Astronomico di Palermo Piazza del Parlamento 1 Palermo90134 Italy Space Science Data Center - Asi Via del Politecnico snc Roma00133 Italy Instituto de Astrofísica de Canarias Tenerife La LagunaE-38200 Spain Universidad de la Laguna Dept. Astrofísica Tenerife La LagunaE-38206 Spain Inaf - Osservatorio Astronomico di Roma Via Frascati 33 Monte Porzio CatoneI-00040 Italy School of Physical Sciences The Open University Walton Hall Milton KeynesMK7 6AA United Kingdom Supa Institute for Astronomy University of Edinburgh Blackford Hill EdinburghEH9 3HJ United Kingdom Inaf - Osservatorio Astronomico di Brera Via E. Bianchi 46 MerateI-23087 Italy Instituto Nacional de Astrofísica Óptica y Electrónica Luis Enrique Erro 1 Sta. Ma. Tonantzintla Puebla Mexico Universitè Côte d'Azur Observatoire de la Côte d'Azur Cnrs Laboratoire Lagrange Nice France Universitè Grenoble Alpes Cnrs Ipag Grenoble38000 France Geneva Observatory University of Geneva Chemin Pegasi 51 Versoix1290 Switzerland Department of Astronomy Stockholm University AlbaNova University Center Stockholm10691 Sweden Cral Umr 5574 Cnrs Université de Lyon Ecole Normale Supérieure de Lyon 46 allée d'Italie Lyon69364 Cedex 07 France Inaf - Osservatorio Astrofisico di Catania Via Santa Sofia 78 Catania95123 Italy Department of Physics and Astronomy University of Ex

Context. Observational data from space and ground-based campaigns reveal that the 10-30 Ma old V1298 Tau star hosts a compact and massive system of four planets. Mass estimates are available for the two outer giant planets and point to unexpectedly high densities for their young ages. Aims. We investigate the formation of these two outermost giant planets, V1298 Tau b and e, and the present dynamical state of V1298 Tau's global architecture to shed light on the history of this young and peculiar extrasolar system. Methods. We perform detailed N-body simulations to explore the link between the densities of V1298 Tau b and e and their migration and accretion of planetesimals within the native circumstellar disk. We combine N-body simulations and the normalized angular momentum deficit (NAMD) analysis of the architecture to characterize V1298 Tau's dynamical state and connect it to the formation history of the system. We search for outer planetary companions to constrain V1298 Tau's planetary architecture and the extension of its primordial circumstellar disk. Results. The high densities of V1298 Tau b and e suggest they formed quite distant from their host star, likely beyond the CO2snowline. The higher nominal density of V1298 Tau e suggests it formed farther out than V1298 Tau b. The current architecture of V1298 Tau is not characterized by resonant chains. Planet-planet scattering with an outer giant planet is the most likely cause for the instability, but our search for outer companions using SPHERE and GAIA observations can currently exclude only the presence of planets more massive than 2 MJ. Conclusions. The most plausible scenario for V1298 Tau's formation is that the system is formed by convergent migration and resonant trapping of planets born in a compact and plausibly massive disk. The migration of V1298 Tau b and e leaves in its wake a dynamically excited protoplanetary disk and naturally creates the conditions for the later breaking of the resonant chain

关键词： Stars