检索结果-内蒙古大学图书馆

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Qicong Xie Xiaohai Tian Guanghou Liu Kun Song Lei Xie Zhiyong Wu Hai Li Song Shi Haizhou Li Fen Hong Hui Bu Xin Xu ASLP@NPU School of Computer Science Northwestern Polytechnical University China National University of Singapore Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China iQIYI Inc China Machine Listening Lab University of Bremen Germany Originbeat Inc China Beijing Shell Shell Technology Co. Ltd China

The Multi-speaker Multi-style Voice Cloning Challenge (M2VoC) aims to provide a common sizable dataset as well as a fair testbed for the benchmarking of the popular voice cloning task. Specifically, we formulate the challenge to adapt an average TTS model to the stylistic target voice with limited data from target speaker, evaluated by speaker identity and style similarity. The challenge consists of two tracks, namely few-shot track and one-shot track, where the participants are required to clone multiple target voices with 100 and 5 samples respectively. There are also two sub-tracks in each track. For sub-track a, to fairly compare different strategies, the participants are allowed to use only the training data provided by the organizer strictly. For sub-track b, the participants are allowed to use any data publicly available. In this paper, we present a detailed explanation on the tasks and data used in the challenge, followed by a summary of submitted systems and evaluation results.

关键词： Deep learning Target tracking Conferences Cloning Training data Signal processing Data models

来源：评论

学校读者我要写书评

暂无评论

From common low temperature to ultra-low temperature: overview of frosting characteristics and defrosting techniques in equipment

引用

Applied Thermal Engineering 2025年 278卷

作者： Chen Ma Xiaojing Ge Haikun Zheng Mengjie Song Wei Sheng Xiaozhuan Chen Dongyu Fu Chaobin Dang School of Mechanical and Power Engineering Henan Polytechnic University Jiaozuo 454003 China School of Computer Science and Technology Henan Polytechnic University Jiaozuo 454003 China Hami Yu-Xin Energy Industry Institute Co Hami 839000 China Department of Energy and Power Engineering School of Mechanical Engineering Beijing Institute of Technology Beijing 100081 China Graduate School of Engineering University of Fukui 3-9-1 Bunkyo Fukui-shi Fukui 910-8507 Japan

With the rapid advancement of low-temperature refrigeration technology, its applications have expanded beyond conventional low-temperature civilian equipment to include large-scale industrial equipment in the field of ultra-low temperatures. The operation of cryogenic equipment inherently involves heat exchange with the surrounding environment. In low-temperature, high-humidity conditions, the surfaces of heat exchangers in such equipment are highly susceptible to frosting. Frost accumulation increases thermal resistance, significantly reducing energy efficiency and causing substantial power wastage. The frosting rates of cryogenic equipment vary due to differences in operating conditions across devices. This review systematically examines recent advancements in frosting characteristics, influencing factors, and anti-frosting and defrosting technologies across various equipment and operating environments. Identifying and implementing suitable anti-frosting and defrosting strategies for specific conditions can significantly improve equipment performance and efficiency. This article categorizes temperature into three zones: common low temperature, transitional low temperature, and ultra-low temperature. It provides a detailed analysis of the frosting characteristics of representative equipment in each zone. Based on the research findings, targeted anti-frosting and defrosting strategies are proposed to optimize the maintenance and management of low-temperature refrigeration equipment. The insights presented serve as a valuable reference for researchers, manufacturers, and designers aiming to enhance equipment performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Combinatorial Engineered Immuno-Fragments Targeting SARS-CoV-2 Nucleocapsid Protein for Epitope Complementarity

SSRN

引用

SSRN 2024年

作者： Dlamini, Nhlanhla Benedict Lee, Chi-Hsin Wang, Wei-Chu Huang, Peng-Nien Leu, Sy-Jye Tseng, Sung-Nien Shih, Shin-Ru Chiang, Liao-Chun Mao, Yan-Chiao Tsai, Bor-Yu Yang, Yi-Yuan Ph.D. Program in Medical Biotechnology College of Medical Science and Technology Taipei Medical University Taipei110301 Taiwan School of Medical Laboratory Science and Biotechnology College of Medical Science and Technology Taipei Medical University Taipei110301 Taiwan Research Center for Emerging Viral Infections Chang Gung University Taoyuan333423 Taiwan Division of Infectious Diseases Department of Pediatrics Linkou Chang Gung Memorial Hospital Taoyuan333423 Taiwan Graduate Institute of Medical Sciences College of Medicine Taipei Medical University Taipei110301 Taiwan Department of Microbiology and Immunology School of Medicine College of Medicine Taipei Medical University Taipei110301 Taiwan Department of Laboratory Medicine Linkou Chang Gung Memorial Hospital Taoyuan333423 Taiwan College of Life Sciences National Tsing Hua University Hsinchu300040 Taiwan Division of Clinical Toxicology Department of Emergency Medicine Taichung Veterans General Hospital Taichung407219 Taiwan Navi Bio-Therapeutics Inc. Taipei10351 Taiwan Core Laboratory of Antibody Generation and Research Taipei Medical University Taipei110301 Taiwan

Recombinant avian phage display immunoglobulin Y derivative single chain variable fragment (IgY-scFv) antibodies have evolved as robust single-chain antigen recognizing IgY analogues due to the advent of immuno-nanotechnology and other immunomolecular biotechnology applications. This academic study reports on the engineering and characterization of severe acute respiratory syndrome coronavirus 2 nucleocapsid (SARS-CoV-2 N) monoaffinity recombinant chicken IgY derivative single chain variable fragment (IgY-scFv) antibody fragments as versatile tools for surrogate immunological identification of the SARS-CoV-2 virus nuclear biomarker. To improve the immunopanning selection for specific binders, layer hens were immunised with the SARS-CoV-2 nucleocapsid protein to pre-enrich higher affinity B cell gene repertoires prior to library construction. Pre-enrichment humoral egg yolk polyclonal IgY antibodies were isolated following the PEG-8000 precipitation protocol. An experimental based modelling approach was applied in order to create IgY derivative N protein single chain variable fragments (IgY-scFv N) M13KO7 phage antibody libraries, an immune phage display library constructed system that supported the generation of functional anti-SARS-CoV-2 N protein IgY-scFv affinity monospecific fragment immunomolecules. After the immunopanning enrichment selection process three distinct positive sequence family IgY-scFv fragments obtained demonstrated epitope specific affinity (micromolar range kinetics) towards the targeted recombinant SARS-CoV-2 N protein and also positively identified native SARS-CoV-2 (COVID-19) N protein in formalin-fixed paraffin-embedded (FFPE) 293T cell pellets. © 2024, The Authors. All rights reserved.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Development of Artificial Intelligence-Based Model for Prediction of the Compressive Strength of Self-Compacting Concrete

SSRN

引用

SSRN 2021年

作者： Ly, Hai-Bang Pham, Binh Thai Nguyen, Thuy-Anh Nguyen, May Huu Civil Engineering Department University of Transport Technology 54 Trieu Khuc Thanh Xuan Hanoi100000 Viet Nam Civil and Environmental Engineering Program Graduate School of Advanced Science and Engineering Hiroshima University 1-4-1 Kagamiyama Higashi-Hiroshima Hiroshima739-8527 Japan

This study investigated the usability of an artificial neural network model (ANN) and the Grey Wolf Optimizer (GWO) method for predicting the compressive strength of self-compacting concrete (SCC). The ANN-GWO model was developed using an experimental database of 115 samples obtained from various sources considering nine key factors of SCC. The validation of the proposed model was evaluated via six indices including correlation coefficient, mean squared error, mean absolute error, IA, Slope, and mean absolute percentage error. In addition, the importance of each parameter affecting the compressive strength of SCC was investigated utilizing partial dependence plots. The findings demonstrated that the proposed ANN-GWO model is a reliable predictor of SCC compressive strength. Following that, an examination of the parameters impacting the compressive strength of SCC was provided. © 2021, The Authors. All rights reserved.

关键词： Compressive strength

来源：评论

学校读者我要写书评

暂无评论

Low energy performance boost through a hardware stereoscopic trigger between CTA LST-1 and MAGIC 38

Low energy performance boost through a hardware stereoscopic...

引用

38th International Cosmic Ray Conference, ICRC 2023

作者： Baxter, J. Barrio, J.A. Bitossi, M. Donini, A. Mazin, D. Paoletti, R. Pérez Aguilera, A. Tejedor Álvarez, L.Á. Abe, H. Abe, K. Abe, S. Abhir, J. Acciari, V.A. Aguasca-Cabot, A. Agudo, I. Alvarez Crespo, N. Aniello, T. Ansoldi, S. Antonelli, L.A. Aramo, C. Arbet-Engels, A. Cornelia, A. Artero, M. Asano, K. Aubert, P. Baack, D. Babić, A. Baktash, A. Bamba, A. Baquero Larriva, A. Baroncelli, L. Barres de Almeida, U. Barrio, J.A. Batkovic, I. Becerra González, J. Bednarek, W. Bernardini, E. Bernardos, M.I. Bernete Medrano, J. Berti, A. Besenrieder, J. Bhattacharjee, P. Biederbeck, N. Bigongiari, C. Biland, A. Bissaldi, E. Blanch, O. Bonnoli, G. Bordas, P. Bošnjak, Ž. Bulgarelli, A. Burelli, I. Burmistrov, L. Buscemi, M. Busetto, G. Campoy-Ordaz, A. Cardillo, M. Caroff, S. Carosi, A. Carosi, R. Carrasco, M.S. Carretero-Castrillo, M. Cassol, F. Castro-Tirado, A.J. Cauz, D. Cerasole, D. Ceribella, G. Chai, Y. Cheng, K. Chiavassa, A. Chikawa, M. Chilingarian, A. Chytka, L. Cifuentes, A. Cikota, S. Colombo, E. Contreras, J.L. Cortina, J. Costantini, H. Covino, S. D’Amico, G. Dalchenko, M. D’Elia, V. Da Vela, P. Dazzi, F. De Angelis, A. de Bony de Lavergne, M. De Lotto, B. De Lucia, M. de Menezes, R. Del Peral, L. Deleglise, G. Delfino, M. Delgado, C. Delgado Mengual, J. della Volpe, D. Dellaiera, M. Del Popolo, A. Depaoli, D. Di Piano, A. Di Pierro, F. Di Pilato, A. Di Tria, R. Di Venere, L. Díaz, C. Dominik, R.M. Dominis Prester, D. Donini, A. Dorner, D. Doro, M. Eisenberger, L. Elsässer, D. Emery, G. Escudero, J. Fallah Ramazani, V. Fariña, L. Fattorini, A. Ferrara, G. Ferrarotto, F. Fiasson, A. Foffano, L. Font, L. Freixas Coromina, L. Fröse, S. Fukami, S. Fukazawa, Y. Garcia, E. Garcia López, R. Garczarczyk, M. Gasbarra, C. Gasparrini, D. Gasparyan, S. Gaug, M. Geyer, D. Giesbrecht Paiva, J. Giglietto, N. Giordano, F. Gliwny, P. Godinovic, N. Grau, R. Green, J. Green, D. Gunji, S. Günther, P. Hackfeld, J. Hadasch, D. Hahn, A. Hashiyama, K. Hassan, T. Hayashi, K. Institute for Cosmic Ray Research University of Tokyo Chiba Kashiwa277-8582 Japan IPARCOS Institute EMFTEL Department Universidad Complutense de Madrid Spain Sezione di Pisa Pisa56127 Italy Osservatorio Astronomico di Roma Italy Max-Planck-Institut für Physik Föhringer Ring 6 München80805 Germany Università degli Studi di Siena via Roma 56 Siena53100 Italy Department of Physics Tokai University Japan ETH Zürich Switzerland Instituto de Astrofísica de Canarias Departamento de Astrofísica Universidad de La Laguna Spain Departament de Física Quàntica i Astrofísica Institut de Ciències del Cosmos Universitat de Barcelona IEEC-UB Spain Instituto de Astrofísica de Andalucía-CSIC Spain EMFTEL department IPARCOS Universidad Complutense de Madrid Spain Italy INFN Sezione di Trieste Università degli Studi di Udine Italy Italy INAF Osservatorio Astronomico di Roma Italy INFN Sezione di Napoli Italy INFN Sezione di Padova Università degli Studi di Padova Italy The Barcelona Institute of Science and Technology Spain LAPP Univ. Grenoble Alpes Univ. Savoie Mont Blanc CNRS-IN2P3 Annecy France Department of Physics TU Dortmund University Germany Croatia Universität Hamburg Institut für Experimentalphysik Germany Graduate School of Science University of Tokyo Japan Universidad del Azuay Ecuador INAF Osservatorio di Astrofisica e Scienza dello spazio di Bologna Italy Centro Brasileiro de Pesquisas Físicas Brazil Faculty of Physics and Applied Informatics University of Lodz Poland CIEMAT Spain INFN Sezione di Bari Politecnico di Bari Italy INAF Osservatorio Astronomico di Brera Italy University of Geneva Département de physique nucléaire et corpusculaire Switzerland INFN Sezione di Catania Italy Departament de Física CERES-IEEC Universitat Autónoma de Barcelona Spain Italy Università di Pisa INFN Pisa Italy Aix Marseille Univ CNRS IN2P3 CPPM France INFN Sezione di Bari Università di Bari Italy INFN Sezione di Torino Italy ICRANet-Armenia at

The next generation facility for gamma-ray ground-based observations is the Cherenkov Telescope Array (CTA) observatory, which comprises three types of imaging atmospheric Cherenkov telescopes (IACTs). The Large-Sized Telescopes (LSTs) of CTA are the largest telescope type with a mirror dish of 23 m diameter. They cover the low energy end of the accessible gamma-ray energies for IACTs, starting from about 20 GeV up to a few TeV. The first LST prototype, known as LST-1, was officially inaugurated at the Observatorio del Roque de Los Muchachos in La Palma (Canary Islands, Spain) in 2018 and has since performed calibration observations of various known gamma-ray sources. Additionally, the site houses the MAGIC telescopes, two 17 m IACTs situated approximately 100 m away from LST-1, which have been performing stereo observations since 2009. Currently, joint observations between LST-1 and MAGIC are being carried on, and the data taken independently by the two IACT systems is analyzed by combining events via software. However, this method increases the energy threshold, as it discards all but the relatively high-energy events triggered by all three telescopes. To address this issue, we have developed a novel hardware stereo trigger system between LST-1 and MAGIC, which is capable of handling events triggered by any-two out of the three telescopes. In this contribution, we will report on the performance estimation of joint LST-1 and MAGIC observations using the hardware trigger. © Copyright owned by the author(s) under the terms of the Creative Commons.

关键词： Cosmology

来源：评论

学校读者我要写书评

暂无评论

The evolution of supermassive blackhole mass-bulge mass relation by a semi-analytic model, ν2GC

arXiv

引用

arXiv 2024年

作者： Shimizu, Tatsuki Oogi, Taira Okamoto, Takashi Nagashima, Masahiro Enoki, Motohiro Department of Cosmosciences Graduate School of science Hokkaido University N10 W8 Kitaku Sapporo060-0810 Japan Department of Electrical and Computer Engineering National Institute of Technology Asahikawa College Shunkodai 2-2-1-6 Asahikawa071-8142 Japan Research Center for Space and Cosmic Evolution Ehime University Bunkyo-cho Matsuyama Ehime790-8577 Japan Faculty of Science Hokkaido University N10 W8 Kitaku Sapporo060-0810 Japan Faculty of Education Bunkyo University 3337 Minami-ogishima Koshigaya Saitama343-8511 Japan Center for General Education Tokyo Keizai University 1-7-34 Minami-cho Kokubunji Tokyo185-8502 Japan

We have investigated the redshift evolution of the relationship between supermassive black hole (SMBH) mass and host bulge mass using a semi-analytical galaxy formation model ν2GC. Our model reproduces the relation in the local universe well. We find that, at high redshift (z 3), two sequences appear in the SMBH mass-bulge mass plane. The emergence of these two sequences can be attributed to the primary triggers of the growth of the SMBHs and bulges: galaxy mergers and disc instabilities. The growth of SMBHs and bulges as a result of galaxy mergers is responsible for giving rise to the high-mass sequence, in which SMBHs are more massive for a given host bulge mass than in the low-mas sequence. Conversely, disc instabilities are accountable for the emergence of the low-mass sequence. At lower redshifts, galaxy mergers tend to become increasingly deficient in gas, resulting in a preferential increase of bulge mass without a corresponding growth in SMBH mass. This has the effect of causing galaxies in the upper sequence to shift towards the lower one on the SMBH mass-bulge mass plane. The galaxies that undergo dry mergers serve to bridge the gap between the two sequences, eventually leading to convergence into a single relation known in the local universe. Our results suggest that the observations of the SMBH mass-bulge mass relation in high redshifts can provide insight into their growth mechanisms. © 2024, CC BY.

关键词： Galaxies

来源：评论

学校读者我要写书评

暂无评论

Inception Network-Based Weather Image Classification with Pre-filtering Process 23rd

Inception Network-Based Weather Image Classification with Pr...

引用

23rd International computer Symposium, ICS 2018

作者： Kang, Li-Wei Feng, Tian-Zheng Fu, Ru-Hong Graduate School of Engineering Science and Technology National Yunlin University of Science and Technology Yunlin Taiwan Department of Computer Science and Information Engineering National Yunlin University of Science and Technology Yunlin Taiwan Artificial Intelligence Recognition Industry Service Research Center National Yunlin University of Science and Technology Yunlin Taiwan

ISBN: (纸本)9789811391897

Visual data (e.g., images/videos) captured from outdoor visual devices are usually degraded by turbid media, such as haze, rain, or snow. Hence, weather conditions would usually disrupt or degrade proper functioning of vision-based applications, such as transportation systems or advanced driver assistance systems, as well as several other outdoor surveillance-based systems. To cope with these problems, removal of weather effects (or the so-called deweathering) from visual data has been critical and received much attention. Therefore, it is important to provide a preprocessing step to automatically decide the current weather condition for input visual data, and then the corresponding proper deweathering operations (e.g., removals of rain or snow) will be properly triggered accordingly. This paper presents an inception network-based weather image classification framework relying on the GoogLeNet by considering the two common weather conditions (with similar characteristics), including rain and snow, in outdoor scenes. For an input image, our method automatically classifies it into one of the two categories or none of them (e.g., sunny or others). We also evaluate the possible impact on image classification performance derived from the image preprocessing via filtering. Extensive experiments conducted on open weather image datasets with/without preprocessing are conducted to evaluate the proposed method and the feasibility has been verified. © Springer Nature Singapore Pte Ltd. 2019.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Observation of Active Galactic Nuclei with the Large-Sized Telescope prototype of the Cherenkov Telescope Array 38

Observation of Active Galactic Nuclei with the Large-Sized T...

引用

38th International Cosmic Ray Conference, ICRC 2023

作者： Takeishi, R. Álvarez Crespo, N. Arbet-Engels, A. Baquero Larriva, A. Baxter, J. Biederbeck, N. Caroff, S. Di Marco, G. Fallah Ramazani, V. Green, D. Heckmann, L. Láinez, M. Nickel, L. Nievas Rosillo, M. Pons, E. Priyadarshi, C. Sanchez, D.A. Vázquez Acosta, M. Abe, K. Abe, S. Aguasca-Cabot, A. Agudo, I. Antonelli, L.A. Aramo, C. Arcaro, C. Artero, M. Asano, K. Aubert, P. Baktash, A. Bamba, A. Baquero Larriva, A. Baroncelli, L. Barres de Almeida, U. Barrio, J.A. Batkovic, I. Becerra González, J. Bernardini, E. Bernardos, M.I. Bernete Medrano, J. Berti, A. Bhattacharjee, P. Bigongiari, C. Bissaldi, E. Blanch, O. Bonnoli, G. Bordas, P. Bulgarelli, A. Burelli, I. Burmistrov, L. Buscemi, M. Cardillo, M. Carosi, A. Carrasco, M.S. Cassol, F. Cauz, D. Cerasole, D. Ceribella, G. Chai, Y. Cheng, K. Chiavassa, A. Chikawa, M. Chytka, L. Cifuentes, A. Contreras, J.L. Cortina, J. Costantini, H. Dalchenko, M. Dazzi, F. De Angelis, A. de Bony de Lavergne, M. De Lotto, B. De Lucia, M. de Menezes, R. Del Peral, L. Deleglise, G. Delgado, C. Delgado Mengual, J. della Volpe, D. Dellaiera, M. Di Piano, A. Di Pierro, F. Di Pilato, A. Di Tria, R. Di Venere, L. Díaz, C. Dominik, R.M. Dominis Prester, D. Donini, A. Dorner, D. Doro, M. Eisenberger, L. Elsässer, D. Emery, G. Escudero, J. Ferrara, G. Ferrarotto, F. Fiasson, A. Foffano, L. Freixas Coromina, L. Fröse, S. Fukami, S. Fukazawa, Y. Garcia, E. Garcia López, R. Gasbarra, C. Gasparrini, D. Geyer, D. Giesbrecht Paiva, J. Giglietto, N. Giordano, F. Gliwny, P. Godinovic, N. Grau, R. Gunji, S. Günther, P. Hackfeld, J. Hadasch, D. Hahn, A. Hashiyama, K. Hassan, T. Hayashi, K. Heller, M. HerreraLlorente, J. Hirotani, K. Hoffmann, D. Horns, D. Houles, J. Hrabovsky, M. Hrupec, D. Hui, D. Hütten, M. Iarlori, M. Imazawa, R. Inada, T. Inome, Y. Ioka, K. Iori, M. Ishio, K. Jimenez Martinez, I. Jurysek, J. Kagaya, M. Karas, V. Katagiri, H. Kataoka, J. Kerszberg, D. Kobayashi, Y. Kohri, K. Kong, A. Kubo, H. Kushida, J. Lamanna, G. Lamastra, A. Institute for Cosmic Ray Research University of Tokyo Chiba Kashiwa277-8582 Japan Grupo de Electronica Universidad Complutense de Madrid Av. Complutense s/n Madrid28040 Spain Max-Planck-Institut für Physik Föhringer Ring 6 München80805 Germany IPARCOS-UCM Instituto de Física de Partículas y del Cosmos EMFTEL Department Universidad Complutense de Madrid MadridE-28040 Spain Faculty of Science and Technology Universidad del Azuay Cuenca Ecuador Department of Physics TU Dortmund University Otto-Hahn-Str. 4 Dortmund44227 Germany Univ. Savoie Mont Blanc CNRS Laboratoire d’Annecy de Physique des Particules - IN2P3 Annecy74000 France Instituto de Astrofísica de Canarias Departamento de Astrofísica Universidad de La Laguna Tenerife La Laguna Spain Institut für Theoretische Physik Lehrstuhl IV: Plasma-Astroteilchenphysik Ruhr-Universität Bochum Universitätsstraße 150 Bochum44801 Germany The Barcelona Institute of Science and Technology Campus UAB Bellaterra Barcelona08193 Spain Department of Physics Tokai University Japan Departament de Física Quàntica i Astrofísica Institut de Ciències delCosmos Universitat de Barcelona IEEC-UB Spain Instituto de Astrofísica de Andalucía-CSIC Spain EMFTEL department IPARCOS Universidad Complutense de Madrid Spain INAF - Osservatorio Astronomico di Roma Italy INFN Sezione di Napoli Italy INFN Sezione di Padova Università degli Studi di Padova Italy Universität Hamburg Institut für Experimentalphysik Germany Graduate School of Science University of Tokyo Japan Universidad del Azuay Ecuador INAF - Osservatorio di Astrofisica e Scienza dello spazio di Bologna Italy Centro Brasileiro de Pesquisas Físicas Brazil CIEMAT Spain INFN Sezione di Bari Politecnico di Bari Italy INAF - Osservatorio Astronomico di Brera Italy INFN Sezione di Trieste Università degli Studi di Udine Italy University of Geneva Département de physique nucléaire et corpusculaire Switzerland INFN Sezione di Catania Italy Italy Aix Marseille Uni

Cherenkov Telescope Array (CTA) will be the next generation gamma-ray observatory. It will consist of three different sizes of telescopes, with a collective improvement of about an order of magnitude in sensitivity, compared with the current generation gamma-ray telescopes. LargeSized Telescopes (LSTs) will be the most sensitive at energies from tens of GeV up to a few TeVs, and will be the best suited to observe gamma-ray sources such as Active Galactic Nuclei (AGN). The first Large-Sized Telescope prototype (LST-1), inaugurated in 2018 and currently in commissioning phase, has accumulated more than one thousand hours of data to date. From 2020 to 2022, we have detected various gamma-ray sources, and prominent among them are several well-known AGN, like Mrk 421, Mrk 501, 1ES 1959+650, 1ES 0647+250, PG 1553+113, etc. We report on light curves and energy spectra reconstructed out of these observations down to energies of tens of GeV, which is very close to the energy threshold of LST-1. © Copyright owned by the author(s) under the terms of the Creative Commons.

关键词： Active Galactic Nuclei

来源：评论

学校读者我要写书评

暂无评论

ExchNet: A unified Hashing network for large-scale fine-grained image retrieval

arXiv

引用

arXiv 2020年

作者： Cui, Quan Jiang, Qing-Yuan Wei, Xiu-Shen Li, Wu-Jun Yoshie, Osamu Graduate School of IPS Waseda University Japan National Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University China Megvii Research Nanjing Megvii Technology China

Retrieving content relevant images from a large-scale fine-grained dataset could suffer from intolerably slow query speed and highly redundant storage cost, due to high-dimensional real-valued embeddings which aim to distinguish subtle visual differences of fine-grained objects. In this paper, we study the novel fine-grained hashing topic to generate compact binary codes for fine-grained images, leveraging the search and storage efficiency of hash learning to alleviate the aforementioned problems. Specifically, we propose a unified end-to-end trainable network, termed as ExchNet. Based on attention mechanisms and proposed attention constraints, it can firstly obtain both local and global features to represent object parts and whole fine-grained objects, respectively. Furthermore, to ensure the discriminative ability and semantic meaning’s consistency of these part-level features across images, we design a local feature alignment approach by performing a feature exchanging operation. Later, an alternative learning algorithm is employed to optimize the whole ExchNet and then generate the final binary hash codes. Validated by extensive experiments, our proposal consistently outperforms state-of-the-art generic hashing methods on five fine-grained datasets, which shows our effectiveness. Moreover, compared with other approximate nearest neighbor methods, ExchNet achieves the best speed-up and storage reduction, revealing its efficiency and practicality. Copyright © 2020, The Authors. All rights reserved.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Deep Clustering with LSTM for Vital Signs Separation in Contact-free Heart Rate Estimation

Deep Clustering with LSTM for Vital Signs Separation in Cont...

引用

IEEE International Conference on Communications (ICC)

作者： Chen Ye Guan Gui Tomoaki Ohtsuki Graduate School of Science and Technology Keio University Yokohama Japan College of Telecommunications and Information Engineering NJUPT Nanjing China Department of Informand Computer Science Keio University Yokohama Japan

ISBN: (数字)9781728150895

ISBN: (纸本)9781728150901

So far, most separation approaches of vital signs such as heartbeat and respiration, are implemented based on linear mixtures. However, some literatures have reported that non-linear mixtures actually occur in the associated applications, e.g., heart rate (HR) estimation with Doppler radar, where the simple linear demixing architecture may limit the effect of source separation. In addition, the human motions during HR measurement further complicate the mixing processes. The issue motivates us to exploit a more suitable separation approach to deal with contact-free HR estimation, considering non-linear mixtures including motions. A semi-supervised deep clustering (DC) is proposed to separate the three mixed sources of heartbeat, respiration, and motions, by segmenting the spectrogram of Doppler signal. First, through training a deep recurrent neural network (RNN) with long short-term memory (LSTM) via heartbeat/respiration-only data, the embeddings to each frame-sample from spectrogram can be acquired, which enables feature optimization in a lower dimensional space. Then, in the test phase, K-means clusters the embeddings associated with each source, to infer the masks used for spectrogram segmentation. The proposed deep clustering has three main strengths: It (i) gets rid of the restriction of mixture class, relying on data mining; (ii) can handle three-source mixtures by training two sorts of source-independent samples; (iii) only requires the mixtures from single-channel. The HR measurement experiments on subjects' sitting still and typing, validate the improvements of accuracy and robustness by our proposal, over some prevailing approaches in signal decomposition or separation.

关键词： Heart beat Estimation Spectrogram Doppler radar Doppler effect Training

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：