检索结果-内蒙古大学图书馆

SSRN 2022年

作者： Wang, Hanlin Yuan, Fan Xie, Zhihua Sun, Chao Wu, Fangda Mikhaylov, Roman Shen, Minghong Yang, Jian Zhou, You Liang, Dongfang Sun, Xianfang Wu, Zhenlin Yang, Zhiyong Yang, Xin Department of Electrical and Electronic Engineering School of Engineering Cardiff University CF24 3AA United Kingdom Department of Biomedical Engineering School of Engineering Duke University NC27708-0281 United States Department of Civil Engineering School of Engineering Cardiff University CF24 3AA United Kingdom School of Life Sciences Northwestern Polytechnical University 710072 China Division of Cancer and Genetics School of Medicine Cardiff University CF14 4XN United Kingdom Systems Immunity Research Institute School of Medicine Cardiff University CF14 4XN United Kingdom Department of Engineering University of Cambridge CB2 1PZ United Kingdom School of Computer Science Cardiff University CF24 3AA United Kingdom School of Optoelectronic Engineering and Instrumentation Science Dalian University of Technology 116023 China School of Mechanical Engineering Tianjin University 300072 China

Acoustofluidic techniques are increasingly used to manipulate nano- and micro-particles in microfluidics. A wide range of acoustofluidic devices integrating microchannel and acoustic sources have been developed for applications in biochemistry and biomedicine. In this work, we developed two novel acoustofluidic configurations: a microchannel was sandwiched between two identical surface acoustic wave (SAW) transducers (SAW-SAW), or between a piezoelectric transducer (PZT) and a SAW transducer (PZT-SAW). We numerically simulated the distributions of the acoustic pressure, time-averaged streaming velocity, and particle trajectories in these devices, and compared the simulation results among the different acoustofluidic configurations. The results revealed that both the SAW-SAW and PZT-SAW configurations produced significantly higher acoustic pressure and particle velocity in the microchannel © 2022, The Authors. All rights reserved.

关键词： Microfluidics

来源：评论

学校读者我要写书评

暂无评论

Control design considering magnetic flux characteristic uncertainty for magnetic levitation system with magnetic flux and current feedback

IEEJ Transactions on Electronics, Information and Systems

引用

IEEJ Transactions on Electronics, Information and systems 2019年第10期139卷 1159-1166页

作者： Urasaki, Shinpachiro Kobayashi, Yoshimitsu Kami, Yasushi Mitani, Yuichiroh Nobuyama, Eitaku Department of Electronic Control Engineering National Institute of Technology Gifu College 2236-2. Kamimakuwa. Motosu. Gifu 501-0495 Japan Department of Electrical and Computer Engineering National Institute of Technology Akashi College 679-3. Nishioka. Uozumi Akashi. Hyogo674-8501 Japan Department of Mechanical Engineering National Institute of Technology Numazu College 3600. Ooka. Numazu Shizuoka410-8501 Japan Department of Systems Innovation and Informatics Faculty of Computer Science and System Engineering Kyushu Institute of Technology 680-4.Kawazu. Iizuka Fukuoka820-8502 Japan

This paper describes control design considering magnetic flux characteristic uncertainty for magnetic levitation system with magnetic flux and current feedback. The position of the levitated object is calculated from the hall voltage and current of the electromagnet. We show the uncertainty for magnetic flux characteristic and design the stabilizing controller by proportional feedback with the hall voltage and current. Moreover, we tried to design servo controller by two-degree-of-freedom control by using a finite number of frequency response (FNFR) model including the uncertainty and confirmed the validity of the proposed method by experiment results. © 2019 The Institute of Eleclrical Engineers of Japan.

关键词： Frequency response

来源：评论

学校读者我要写书评

暂无评论

The Quantum Internet (Technical Version)

arXiv

引用

arXiv 2025年

作者： Rohde, Peter P. Huang, Zixin Ouyang, Yingkai Huang, He-Liang Su, Zu-En Devitt, Simon Ramakrishnan, Rohit Mantri, Atul Tan, Si-Hui Liu, Nana Harrison, Scott Radhakrishnan, Chandrashekar Brennen, Gavin K. Baragiola, Ben Q. Dowling, Jonathan P. Byrnes, Tim Munro, William J. Centre for Quantum Software and Information Faculty of Engineering and Information Technology University of Technology Sydney SydneyNSW Australia Hearne Institute for Theoretical Physics Louisiana State University Baton Rouge United States School of Mathematical and Physical Sciences Macquarie University NSW2109 Australia School of Mathematical and Physical Sciences University of Sheffield SheffieldS3 7RH United Kingdom Henan Key Laboratory of Quantum Information and Cryptography Henan Zhengzhou450000 China Hefei National Laboratory for Physical Sciences at Microscale Department of Modern Physics University of Science & Technology of China Hefei China CAS Centre for Excellence and Synergetic Innovation Centre in Quantum Information & Quantum Physics University of Science & Technology of China Hefei China CAS-Alibaba Quantum Computing Laboratory Shanghai China InstituteQ Aalto University Espoo02150 Finland Indian Institute of Science Bangalore India Singapore University of Technology & Design Singapore Centre for Quantum Technologies National University of Singapore Singapore Horizon Quantum Ireland 24 Fitzwilliam Place Dublin 2 D02 T296 Ireland Institute of Natural Sciences Shanghai Jiao Tong University Shanghai200240 China School of Mathematical Sciences Shanghai Jiao Tong University Shanghai200240 China Ministry of Education Key Laboratory in Scientific and Engineering Computing Shanghai Jiao Tong University Shanghai200240 China Shanghai Artificial Intelligence Laboratory Shanghai China University of Michigan Shanghai Jiao Tong University Joint Institute Shanghai200240 China Leibniz Institute for Research & Information in Education Frankfurt am Main Germany Department of Computer Science and Engineering NYU Shanghai 567 West Yangsi Road Shanghai200124 China Centre of Excellence in Engineered Quantum Systems Macquarie University NSW Australia Centre for Quantum Computation and Communication Technology School of Science RMIT University VIC

The desire to share and unite remote digital assets motivated the development of the classical internet, the enabler of the entire 21st century economy and our modern way of life. As we enter the quantum era, it is to be expected there will be a similar demand for networking quantum assets, motivating a global quantum internet for bringing together the world's quantum resources, leveraging off their exponential trajectory in capability. We present models for quantum networking, how they might be applied in the future, and the implications they will have. Socially, economically, politically and geostrategically, the upcoming era of quantum supremacy will be as significant for the 21st century as the transistor was for the 20th. The inherently different scaling in the computational power of quantum computers fundamentally changes the dynamics of how they will operate in the future. Given their high expected initial cost, a client/server model for outsourcing computation will be essential for enabling the accessibility and proliferation of this technology, and ensuring its economic viability. We therefore anticipate the emergence of cloud quantum computing, a model for outsourcing quantum computations to the network. We argue that economic efficiency will mandate that all future quantum computers be united into a single global virtual quantum computer, offering exponentially more power to all network participants than if they were to keep their resources to themselves. This model for the allocation of computational resources is uniquely quantum, with no classical analogue, completely altering the economic landscape for the future of computation. Given the sensitivity of much of the data to which future quantum computers are going to foreseeably be applied, protocols for encrypted quantum computation will be essential - the outsourcing of computations that neither an eavesdropper nor even the server performing the computation can spy upon. This will enable new models fo

关键词： Outsourcing

来源：评论

学校读者我要写书评

暂无评论

Input optics systems of the KAGRA detector during O3GK (vol 2023, 023F01, 2023)

引用

PROGRESS OF THEORETICAL AND EXPERIMENTAL PHYSICS 2023年第5期2023卷

作者： Akutsu, T. Ando, M. Arai, K. Arai, Y. Araki, S. Araya, A. Aritomi, N. Asada, H. Aso, Y. Bae, S. Bae, Y. Baiotti, L. Bajpai, R. Barton, M. A. Cannon, K. Cao, Z. Capocasa, E. Chan, M. Chen, C. Chen, K. Chen, Y. Chiang, C-I Chu, H. Chu, Y-K Eguchi, S. Enomoto, Y. Flaminio, R. Fujii, Y. Fujikawa, Y. Fukunaga, M. Fukushima, M. Furuhata, T. Gao, D. Ge, G-G Ha, S. Hagiwara, A. Haino, S. Han, W-B Hasegawa, K. Hattori, K. Hayakawa, H. Hayama, K. Himemoto, Y. Hiranuma, Y. Hirata, N. Hirose, E. Hong, Z. Hsieh, B-H Huang, G-Z Huang, H-Y Huang, P. Huang, Y-C Huang, Y-J Hui, D. C. Y. Ide, S. Ikenoue, B. Imam, S. Inayoshi, K. Inoue, Y. Ioka, K. Ito, K. Itoh, Y. Izumi, K. Jeon, C. Jin, H-B Jung, K. Jung, P. Kaihotsu, K. Kajita, T. Kakizaki, M. Kamiizumi, M. Kanbara, S. Kanda, N. Kang, G. Kataoka, Y. Kawaguchi, K. Kawai, N. Kawasaki, T. Kim, C. Kim, J. Kim, J. C. Kim, Ws Kim, Y-M Kimura, N. Kita, N. Kitazawa, H. Kojima, Y. Kokeyama, K. Komori, K. Kong, A. K. H. Kotake, K. Kozakai, C. Kozu, R. Kumar, R. Kume, J. Kuo, C. Kuo, H-S Kuromiya, Y. Kuroyanagi, S. Kusayanagi, K. Kwak, K. Lee, H. K. Lee, H. W. Lee, R. Leonardi, M. Li, K. L. Lin, L. C-C Lin, C-Y Lin, F-K Lin, F-L Lin, H. L. Liu, G. C. Luo, L-W Majorana, E. Marchio, M. Michimura, Y. Mio, N. Miyakawa, O. Miyamoto, A. Miyazaki, Y. Miyo, K. Miyoki, S. Mori, Y. Morisaki, S. Moriwaki, Y. Nagano, K. Nagano, S. Nakamura, K. Nakano, H. Nakano, M. Nakashima, R. Nakayama, Y. Narikawa, T. Naticchioni, L. Negishi, R. Quynh, L. Nguyen Ni, W-T Nishizawa, A. Nozaki, S. Obuchi, Y. Ogaki, W. Oh, J. J. Oh, S. H. Ohashi, M. Ohishi, N. Ohkawa, M. Ohta, H. Okutani, Y. Okutomi, K. Oohara, K. Ooi, C. Oshino, S. Otabe, S. Pan, K-C Pang, H. Parisi, A. Park, J. Arellano, F. E. Pena Pinto, I. Sago, N. Saito, S. Saito, Y. Sakai, K. Sakai, Y. Sakuno, Y. Sato, S. Sato, T. Sawada, T. Sekiguchi, T. Sekiguchi, Y. Shao, L. Shibagaki, S. Shimizu, R. Shimoda, T. Shimode, K. Shinkai, H. Shishido, T. Shoda, A. Somiya, K. Son, E. J. Sotani, H. Sugimoto, R. Suresh, J. Suzuki, T. Suzuki, T. Tagoshi, H. Takahashi, H Gravitational Wave Science Project National Astronomical Observatory of Japan 2-21-1 Osawa Mitaka City Tokyo 181-8588 Japan Advanced Technology Center National Astronomical Observatory of Japan 2-21-1 Osawa Mitaka City Tokyo 181-8588 Japan Department of Physics The University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo 113-0033 Japan Research Center for the Early Universe The University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo 113-0033 Japan Institute for Cosmic Ray Research KAGRA Observatory The University of Tokyo 5-1-5 Kashiwa-no-Ha Kashiwa City Chiba 277-8582 Japan Accelerator Laboratory High Energy Accelerator Research Organization (KEK) 1-1 Oho Tsukuba City Ibaraki 305-0801 Japan Earthquake Research Institute The University of Tokyo 1-1-1 Yayoi Bunkyo-ku Tokyo 113-0032 Japan Department of Mathematics and Physics Graduate School of Science and Technology Hirosaki University 3 Bunkyo-cho Hirosaki Aomori 036-8561 Japan Kamioka Branch National Astronomical Observatory of Japan 238 Higashi-Mozumi Kamioka-cho Hida City Gifu 506-1205 Japan The Graduate University for Advanced Studies (SOKENDAI) 2-21-1 Osawa Mitaka City Tokyo 181-8588 Japan Korea Institute of Science and Technology Information 245 Daehak-ro Yuseong-gu Daejeon 34141 Republic of Korea National Institute for Mathematical Sciences 70 Yuseong-daero 1689 Beon-gil Yuseong-gu Daejeon 34047 Republic of Korea International College Osaka University 1-1 Machikaneyama-cho Toyonaka City Osaka 560-0043 Japan School of High Energy Accelerator Science The Graduate University for Advanced Studies (SOKENDAI) 1-1 Oho Tsukuba City Ibaraki 305-0801 Japan Department of Astronomy Beijing Normal University Xinjiekouwai Street 19 Haidian District Beijing 100875 China Department of Applied Physics Fukuoka University 8-19-1 Nanakuma Jonan Fukuoka City Fukuoka 814-0180 Japan Department of Physics Tamkang University No. 151 Yingzhuan Road Danshui Dist. New Taipei City 25137 Taiwan Department of Physics

KAGRA, the underground and cryogenic gravitational-wave detector, was operated for its solo observation from February 25 to March 10, 2020, and its first joint observation with the GEO 600 detector from April 7 to April 21, 2020 (O3GK). This study presents an overview of the input optics systems of the KAGRA detector, which consist of various optical systems, such as a laser source, its intensity and frequency stabilization systems, modulators, a Faraday isolator, mode-matching telescopes, and a high-power beam dump. These optics were successfully delivered to the KAGRA interferometer and operated stably during the observations. The laser frequency noise was observed to limit the detector sensitivity above a few kilohertz, whereas the laser intensity did not significantly limit the detector sensitivity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamical multiple polynomial-based neural networks classifier realized with the aid of dropfilter and dual statistical selection

引用

Engineering Applications of Artificial Intelligence 2025年 157卷

作者： Zhen Wang Sung-Kwun Oh Zunwei Fu Seok-Beom Roh Witold Pedrycz Research Center for Big Data and Artificial Intelligence Linyi University Linyi 276005 China School of Automation and Electrical Engineering Linyi University Linyi 276005 Shandong China School of Electrical & Electronic Engineering The University of Suwon 17 Wauan-gil Bongdam-eup Hwaseong-si Gyeonggi-do 18323 South Korea Department of Electronic Engineering Seokyeong University Seoul 02713 South Korea Department of Computer Science The University of Suwon 17 Wauan-gil Bongdam-eup Hwaseong-si Gyeonggi-do 18323 South Korea Department of Electrical and Computer Engineering University of Alberta Edmonton AB T6G 2R3 Canada Systems Research Institute Polish Academy of Sciences 00-901 Warsaw Poland Department of Computer Engineering Faculty of Engineering and Natural Sciences Istinye University Sariyer Istanbul Turkiye

Polynomial neural networks (PNN) have emerged as an effective regression modeling methodology in computational intelligence, relying on its interpretable polynomial nodes to fit complex nonlinear data relationships and the adaptive nature of self-organizing networks. To break the bottleneck of PNN structure in the field of multi-classification, this study designs a dynamical multiple polynomial-based neural networks (DMPNN) classifier, focusing on developing a flexible polynomial network classification methodology that enhances predictive capabilities without sacrificing the advantages of PNN structures. Our approach effectively addresses the challenges of multi-class classification with uncertain class boundaries and reduces computational complexity, which is achieved through the synergy of several proposed techniques. Three key issues underpin the proposed DMPNN: (a) The integration of PNN regression models using the one-against-all strategy can provide effective and scalable solutions to multi-class classification problems, especially for uncertain class boundary issues. (b) The dual statistical selection (DSS) approach aims to eliminate redundant inputs during data processing, reduce the computational burden, and increase the variety of neural network nodes in the model neuron selection stage. (c) The synergy of regularization methods including the ℓ2 norm-based method (ℓ2-LSM) and the DropFilter, is exploited to mitigate potential overfitting in coefficient estimation and enhance the generalization capabilities of the proposed classifier. A series of ablation experiments and parameter analysis were conducted to demonstrate the stability and reliability of the proposed model. Then, we applied DMPNN to 17 publicly available datasets and two engineering applications: Recycling of black plastic wastes and phased resolved partial discharge. The performance results show that the DMPNN model outperforms five classical classifiers and four state-of-the-art (SOTA) class

关键词：

来源：评论

学校读者我要写书评

暂无评论

A novel ensemble XGBoost and deep Q-network for pregnancy risk prediction on multi-class imbalanced datasets

引用

ICT Express 2025年

作者： Kurnianingsih Nobukawa, Sou Widyawati, Melyana Nurul Pramana, Cipta Aji, Nurseno Bayu Thohari, Afandi Nur Aziz Hendrawati, Dwiana Sato-Shimokawara, Eri Kubota, Naoyuki Department of Electrical Engineering Politeknik Negeri Semarang H. Soedarto Tembalang Central Java Semarang 50275 Indonesia Department of Computer Science Chiba Institute of Technology 2-17-1 Tsudanuma Chiba Narashino 275-0016 Japan Poltekkes Kemenkes Semarang Tirto Agung Pedalangan Banyumanik Central Java Semarang 50268 Indonesia Department of Obstetrics and Gynecology KRMT Wongsonegoro Hospital Fatmawati Tembalang Central Java Semarang 50272 Indonesia Department of Mechanical Engineering Politeknik Negeri Semarang H. Soedarto Tembalang Central Java Semarang 50275 Indonesia Faculty of Systems Design Tokyo Metropolitan University Tokyo 1910065 Japan

Addressing imbalanced data is essential for accurate prediction. We propose a novel ensemble method of XGBoost and deep Q-learning networks (DQN) for pregnancy risk prediction. First, we train the majority class utilizing XGBoost. We subsequently utilize DQN to train the minority class into binary classifications. Finally, we use the trained models from DQN and XGBoost in ensemble learning to generate the final classification results. The XGBoost-DQN model achieves high performance with 0.9819 in precision, recall, F1-score, and accuracy, outperforming several baseline classifiers on private data from 5313 pregnant women in Indonesia and showing superior results on public datasets. © 2025 The Author(s)

关键词： Deep Q-network Ensemble learning Imbalanced dataset Pregnancy risk XGBoost tree

来源：评论

学校读者我要写书评

暂无评论

Deep learning enabled smart charging technology for electric vehicles

引用

AIP Conference Proceedings 2022年第1期2527卷

作者： T. Blesslin Sheeba C. Sharanya C. Nayanatara S. K. Indumathi K. Kalins G. Ignisha Rajathi 1Department of ECE R.M.K. Engineering College Chennai India 2Department of ECE Vels Institute of Science Technology and Advanced Studies Chennai India 3Department of EEE Sri Sairam Engineering College Chennai India 4Centre for Automation and Robotics Hindustan Institute of Technology and Science Chennai India 5Department of Science and Humanities Sri Krishna College of Engineering and Technology Coimbatore India 6Department of Computer Science and Business Systems Sri Krishna College of Engineering and Technology Coimbatore India

Reliability, efficiency, and cost-effectiveness of smart grids are enhanced with power demand softening by means of efficient load management in electric vehicles. In such initiatives, the involvement of EV users may reduce due to the lack of adaptable user-centric approaches. During the connection sessions, the EV charging time is determined using a deep learning algorithm-based smart charging strategy proposed in this paper. Here, the total energy cost of the vehicle is minimized by making charging decisions considering demand time series, pricing, environment, driving, and other auxiliary data. The memorization technique is used for the estimation of the optimal solution of the existing connection sessions in the initial stage. The deep learning models are trained with this existing data and optimal decisions to make suitable decisions in real-time scenarios where car usage or future energy price values are undetermined. A significant reduction in the charging cost is observed by training the neural network with the proposed model. The results obtained are compared to the optimal charging costs computed and are found to be closely similar.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TOI-2458 b: A mini-Neptune consistent with in situ hot Jupiter formation

arXiv

引用

arXiv 2024年

作者： Šubjak, Jan Gandolfi, Davide Goffo, Elisa Rapetti, David Jankowski, Dawid Mizuki, Toshiyuki Dai, Fei Serrano, Luisa M. Wilson, Thomas G. Goździewski, Krzysztof Nowak, Grzegorz Jenkins, Jon M. Twicken, Joseph D. Winn, Joshua N. Bieryla, Allyson Ciardi, David R. Cochran, William D. Collins, Karen A. Deeg, Hans J. Garcia, Rafael A. Guenther, Eike W. Hatzes, Artie P. Kabath, Petr Korth, Judith Latham, David W. Livingston, John H. Lund, Michael B. Mathur, Savita Narita, Norio Orell-Miquel, Jaume Palle, Enric Persson, Carina M. Redfield, Seth Schwarz, Richard P. Watanabe, David Ziegler, Carl Astronomical Institute Czech Academy of Sciences Fričova 298 Ondřejov251 65 Czech Republic Center for Astrophysics | Harvard & Smithsonian 60 Garden Street CambridgeMA02138 United States Dipartimento di Fisica Universita degli Studi di Torino via Pietro Giuria 1 TorinoI-10125 Italy Thuringer Landessternwarte Tautenburg Sternwarte 5 Tautenburg07778 Germany NASA Ames Research Center Moffett FieldCA94035 United States Research Institute for Advanced Computer Science Universities Space Research Association WashingtonDC20024 United States Institute of Astronomy Faculty of Physics Astronomy and Informatics Nicolaus Copernicus University Grudziadzka 5 Toruń87-100 Poland Astrobiology Center of NINS 2-21-1 Osawa Mitaka Tokyo181-8588 Japan National Astronomical Observatory of Japan 2-21-2 Osawa Mitaka Tokyo181-8588 Japan Institute for Astronomy University of Hawai'i 2680 Woodlawn Drive HonoluluHI96822 United States Department of Physics University of Warwick Gibbet Hill Road CoventryCV4 7AL United Kingdom SETI Institute Mountain ViewCA94043 United States Department of Astrophysical Sciences Princeton University PrincetonNJ08544 United States NASA Exoplanet Science Institute-Caltech/IPAC PasadenaCA91125 United States McDonald Observatory The University of Texas AustinTX United States Center for Planetary Systems Habitability The University of Texas AustinTX United States C. Via Lactea S/N Tenerife La LagunaE-38205 Spain Dept. de Astrofisica Tenerife La LagunaE-38206 Spain Universite Paris-Saclay Universite Paris Cite CEA CNRS AIM Gif-sur-Yvette91191 France Lund Observatory Division of Astrophysics Department of Physics Lund University Box 118 Lund22100 Sweden Astronomical Science Program Graduate University for Advanced Studies SOKENDAI 2-21-1 Osawa Mitaka Tokyo181-8588 Japan Komaba Institute for Science The University of Tokyo 3-8-1 Komaba Meguro Tokyo153-8902 Japan Chalmers University of Technology Departmen

We report on the discovery and spectroscopic confirmation of TOI-2458 b, a transiting mini-Neptune around an F-type star leaving the mainsequence with a mass of M*= 1.05 ± 0.03Mo, a radius of R*= 1.31 ± 0.03 Ro, an effective temperature of Teff = 6005 ± 50 K, and a metallicity of -0.10 ± 0.05 dex. By combining TESS photometry with high-resolution spectra acquired with the HARPS spectrograph, we found that the transiting planet has an orbital period of ∼3.74 days, a mass of Mp = 13.31±0.99M⊕ and a radius of Rp = 2.83±0.20 R⊕. The host star TOI-2458 shows a short activity cycle of ∼54 days revealed in the HARPS S-index and Hα times series. We took the opportunity to investigate other F stars showing activity cycle periods comparable to that of TOI-2458 and found that they have shorter rotation periods than would be expected based on the gyrochronology predictions. In addition, we determined TOI-2458's stellar inclination angle to be i*= 10.6+13.3 -10.6 degrees. We discuss that both phenomena (fast stellar rotation and planet orbit inclination) could be explained by in situ formation of a hot Jupiter interior to TOI-2458 b. It is plausible that this hot Jupiter was recently engulfed by the star. Analysis of HARPS spectra has identified the presence of another planet with a period of P = 16.55 ± 0.06 days and a minimum mass of Mp sin i = 10.22 ± 1.90M⊕. Using dynamical stability analysis, we constrained the mass of this planet to the range Mc (10, 25)M⊕. © 2024, CC BY.

关键词： Stars

来源：评论

学校读者我要写书评

暂无评论

Deformations of unitary Howe dual pairs

arXiv

引用

arXiv 2020年

作者： Ciubotaru, Dan de Bie, Hendrik de Martino, Marcelo Oste, Roy Mathematical Institute University of Oxford OxfordOX2 6GG United Kingdom Department of Electronics and Information Systems Ghent University Krijgslaan 281 Gent9000 Belgium Department of Applied Mathematics Computer Science and Statistics Ghent University Krijgslaan 281-S9 Gent9000 Belgium

We study deformations of the Howe dual pairs (U(n), u(1, 1)) and (U(n), u(2|1)) to the context of a rational Cherednik algebra H1,c(G, E) associated with a real reflection group G acting on a real vector space E of even dimension. For each pair, we show that the Lie (super)algebra structure of one partner is preserved under the deformation, which leads to a multiplicity-free decomposition of the standard module or its tensor product with a spinor space. For the case where E is two-dimensional and G is a dihedral group, we provide complete descriptions for the deformed pair and the relevant *** Codes 16S80, 16W10, 16W22, 17B10 Copyright © 2020, The Authors. All rights reserved.

关键词： Deformation

来源：评论

学校读者我要写书评

暂无评论

An investigation of interpretability techniques for deep learning in predictive process analytics

arXiv

引用

arXiv 2020年

作者： Moreira, Catarina Sindhgatta, Renuka Ouyang, Chun Bruza, Peter Wichert, Andreas School of Information Systems Science and Engineering Faculty of Queensland University of Technology 2 George St Brisbane City BrisbaneQLD4000 Australia Department of Computer Science and Engineering Instituto Superior Técnico / INESC-ID University of Lisbon Av. Prof. Dr. Cavaco Silva Porto Salvo2744-016 Portugal

This paper explores interpretability techniques for two of the most successful learning algorithms in medical decision-making literature: deep neural networks and random forests. We applied these algorithms in a real-world medical dataset containing information about patients with cancer, where we learn models that try to predict the type of cancer of the patient, given their set of medical activity records. We explored different algorithms based on neural network architectures using long short term deep neural networks, and random forests. Since there is a growing need to provide decision-makers understandings about the logic of predictions of black boxes, we also explored different techniques that provide interpretations for these classifiers. In one of the techniques, we intercepted some hidden layers of these neural networks and used autoencoders in order to learn what is the representation of the input in the hidden layers. In another, we investigated an interpretable model locally around the random forest’s prediction. Results show learning an interpretable model locally around the model’s prediction leads to a higher understanding of why the algorithm is making some decision. Use of local and linear model helps identify the features used in prediction of a specific instance or data point. We see certain distinct features used for predictions that provide useful insights about the type of cancer, along with features that do not generalize well. In addition, the structured deep learning approach using autoencoders provided meaningful prediction insights, which resulted in the identification of nonlinear clusters correspondent to the patients’ different types of cancer. Copyright © 2020, 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

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：