检索结果-内蒙古大学图书馆

11th IEEE International Conference on Intelligent systems, IS 2022

作者： Charytanowicz, Malgorzata Olwert, Anna Radziszewska, Weronika Jarnicka, Jolanta Gajowniczek, Krzysztof Zabkowski, Tomasz Brozyna, Jacek Mentel, Grzegorz Matejko, Grzegorz Research Institute Pas Center for Methods of Data Analysis Systems Warsaw Poland Research Institute Pas Department of Computer Science Systems Warsaw Poland Research Institute Pas Center for Computer Modelling Systems Warsaw Poland Warsaw University of Life Sciences Institute of Information Technology Warsaw Poland Rzeszow University of Technology Department of Quantitative Methods Rzeszów Poland Polskie Towarzystwo Cyfrowe Lublin Poland

ISBN: (纸本)9781665456562

This paper refers to real-life data on energy consumption from three companies, connected to a medium voltage grid. The companies use single-, two-, or three-zone tariffs and the general characteristic of their activity is comparable. The input dataset contains hourly electricity consumption recorded from January 2020 to December 2020. The independent variables used for the study include weather, time-dependent factors, and aggregated energy factors. We perform the prediction of consumption using three methods: naive, multiple regression, and extreme gradient boosting regression. The performance of the methods is compared based on the MSE, RMSE, MAE, and MAPE metrics. The study shows that the scores achieved for the extreme gradient boosting method are higher than for the multiple regression. To gain the interpretability of the energy load forecasting and feature analysis the Shapley additive explanations method is used for the best model. As a result, a ranking of the most important factors is created. It shows the importance of aggregated energy factors and weather conditions while placing daylight and season at the bottom of the ranking. © 2022 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

ROSE: Robust Selective Fine-tuning for Pre-trained Language Models

ROSE: Robust Selective Fine-tuning for Pre-trained Language ...

引用

2022 Conference on Empirical methods in Natural Language Processing, EMNLP 2022

作者： Jiang, Lan Zhou, Hao Lin, Yankai Li, Peng Zhou, Jie Jiang, Rui MOE Key Laboratory of Bioinformatics Center for Synthetic and Systems Biology Department of Automation BNRist Tsinghua University China Pattern Recognition Center WeChat AI Tencent Inc. China Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Tsinghua University China

Even though the large-scale language models have achieved excellent performances, they suffer from various adversarial attacks. A large body of defense methods has been proposed. However, they are still limited due to redundant attack search spaces and the inability to defend against various types of attacks. In this work, we present a novel fine-tuning approach called RObust SEletive fine-tuning (ROSE) to address this issue. ROSE conducts selective updates when adapting pre-trained models to downstream tasks, filtering out invaluable and unrobust updates of parameters. Specifically, we propose two strategies: the first-order and second-order ROSE for selecting target robust parameters. The experimental results show that ROSE achieves significant improvements in adversarial robustness on various downstream NLP tasks, and the ensemble method even surpasses both variants above. Furthermore, ROSE can be easily incorporated into existing fine-tuning methods to improve their adversarial robustness further. The empirical analysis confirms that ROSE eliminates unrobust spurious updates during fine-tuning, leading to solutions corresponding to flatter and wider optima than the conventional method. Code is available at https://***/jiangllan/ROSE. © 2022 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Energy Load Prediction and its Interpretation

Machine Learning for Energy Load Prediction and its Interpre...

引用

International IEEE Conference on Intelligent systems, IS

作者： Małgorzata Charytanowicz Anna Olwert Weronika Radziszewska Jolanta Jarnicka Krzysztof Gajowniczek Tomasz Ząbkowski Jacek Brożyna Grzegorz Mentel Grzegorz Matejko Center for Methods of Data Analysis Systems Research Institute PAS Warsaw Poland Department of Computer Science Systems Research Institute PAS Warsaw Poland Center for Computer Modelling Systems Research Institute PAS Warsaw Poland Institute of Information Technology Warsaw University of Life Sciences Warsaw Poland Department of Quantitative Methods Rzeszow University of Technology Rzeszów Poland Polskie Towarzystwo Cyfrowe Lublin Poland

ISBN: (纸本)9781665492768

关键词： Measurement Additives Load forecasting Tariffs Companies Medium voltage Predictive models

来源：评论

学校读者我要写书评

暂无评论

ROSE: Robust Selective Fine-tuning for Pre-trained Language Models

arXiv

引用

arXiv 2022年

作者： Jiang, Lan Zhou, Hao Lin, Yankai Li, Peng Zhou, Jie Jiang, Rui Ministry of Education Key Laboratory of Bioinformatics Center for Synthetic and Systems Biology Department of Automation BNRist Tsinghua University China Pattern Recognition Center WeChat AI Tencent Inc. China Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Tsinghua University China

Even though the large-scale language models have achieved excellent performances, they suffer from various adversarial attacks. A large body of defense methods has been proposed. However, they are still limited due to redundant attack search spaces and the inability to defend against various types of attacks. In this work, we present a novel fine-tuning approach called RObust SEletive fine-tuning (ROSE) to address this issue. ROSE conducts selective updates when adapting pretrained models to downstream tasks, filtering out invaluable and unrobust updates of parameters. Specifically, we propose two strategies: the first-order and second-order ROSE for selecting target robust parameters. The experimental results show that ROSE achieves significant improvements in adversarial robustness on various downstream NLP tasks, and the ensemble method even surpasses both variants above. Furthermore, ROSE can be easily incorporated into existing fine-tuning methods to improve their adversarial robustness further. The empirical analysis confirms that ROSE eliminates unrobust spurious updates during fine-tuning, leading to solutions corresponding to flatter and wider optima than the conventional method. Code is available at https://***/jiangllan/ROSE. © 2022, CC BY.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Stroke genetics informs drug discovery and risk prediction across ancestries (vol 611, pg 115, 2022)

引用

NATURE 2022年第7938期612卷 E7-E7页

作者： Mishra, Aniket Malik, Rainer Hachiya, Tsuyoshi Jurgenson, Tuuli Namba, Shinichi Posner, Daniel C. Kamanu, Frederick K. Koido, Masaru Le Grand, Quentin Shi, Mingyang He, Yunye Georgakis, Marios K. Caro, Ilana Krebs, Kristi Liaw, Yi-Ching Vaura, Felix C. Lin, Kuang Winsvold, Bendik Slagsvold Srinivasasainagendra, Vinodh Parodi, Livia Bae, Hee-Joon Chauhan, Ganesh Chong, Michael R. Tomppo, Liisa Akinyemi, Rufus Roshchupkin, Gennady V. Habib, Naomi Jee, Yon Ho Thomassen, Jesper Qvist Abedi, Vida Carcel-Marquez, Jara Nygaard, Marianne Leonard, Hampton L. Yang, Chaojie Yonova-Doing, Ekaterina Knol, Maria J. Lewis, Adam J. Judy, Renae L. Ago, Tetsuro Amouyel, Philippe Armstrong, Nicole D. Bakker, Mark K. Bartz, Traci M. Bennett, David A. Bis, Joshua C. Bordes, Constance Borte, Sigrid Cain, Anael Ridker, Paul M. Cho, Kelly Chen, Zhengming Cruchaga, Carlos Cole, John W. de Jager, Phil L. de Cid, Rafael Endres, Matthias Ferreira, Leslie E. Geerlings, Mirjam I. Gasca, Natalie C. Gudnason, Vilmundur Hata, Jun He, Jing Heath, Alicia K. Ho, Yuk-Lam Havulinna, Aki S. Hopewell, Jemma C. Hyacinth, I. Hyacinth Inouye, Michael Jacob, Mina A. Jeon, Christina E. Jern, Christina Kamouchi, Masahiro Keene, Keith L. Kitazono, Takanari Kittner, Steven J. Konuma, Takahiro Kumar, Amit Lacaze, Paul Launer, Lenore J. Lee, Keon-Joo Lepik, Kaido Li, Jiang Li, Liming Manichaikul, Ani Markus, Hugh S. Marston, Nicholas A. Meitinger, Thomas Mitchell, Braxton D. Montellano, Felipe A. Morisaki, Takayuki Mosley, Thomas H. Nalls, Mike A. Nordestgaard, Borge G. O'Donnell, Martin J. Okada, Yukinori Onland-Moret, N. Charlotte Ovbiagele, Bruce Peters, Annette Psaty, Bruce M. Rich, Stephen S. Rosand, Jonathan Sabatine, Marc S. Sacco, Ralph L. Saleheen, Danish Sandset, Else Charlotte Salomaa, Veikko Sargurupremraj, Muralidharan Sasaki, Makoto Satizabal, Claudia L. Schmidt, Carsten O. Shimizu, Atsushi Smith, Nicholas L. Sloane, Kelly L. Sutoh, Yoichi Sun, Yan V. Tanno, Kozo Tiedt, Steffen Tatlisumak, Turgut Torres-Aguila, Nuria P. Tiwari, Hemant K. Tregouet, Bordeaux Population Health Research Center University of Bordeaux Inserm UMR 1219 Bordeaux France Department of Public Health Bordeaux University Hospital Bordeaux France Department of Neurology Memory Clinic Bordeaux University Hospital Bordeaux France Department of Neurology Institute for Neurodegenerative Diseases CHU de Bordeaux Bordeaux France Institute for Stroke and Dementia Research (ISD) University Hospital LMU Munich Munich Germany Center for Genomic Medicine Massachusetts General Hospital Boston MA USA Program in Medical and Population Genetics Broad Institute of Harvard and the Massachusetts Institute of Technology Cambridge MA USA Munich Cluster for Systems Neurology Munich Germany German Center for Neurodegenerative Diseases (DZNE) Munich Germany Iwate Tohoku Medical Megabank Organization Iwate Medical University Iwate Japan Estonian Genome Centre Institute of Genomics University of Tartu Tartu Estonia Institute of Mathematics and Statistics University of Tartu Tartu Estonia Department of Computational Biology University of Lausanne Lausanne Switzerland Swiss Institute of Bioinformatics Lausanne Switzerland University Center for Primary Care and Public Health Lausanne Switzerland Department of Statistical Genetics Osaka University Graduate School of Medicine Suita Japan Department of Genome Informatics Graduate School of Medicine The University of Tokyo Tokyo Japan Laboratory for Systems Genetics RIKEN Center for Integrative Medical Sciences Yokohama Japan Laboratory of Statistical Immunology Immunology Frontier Research Center (WPI-IFReC) Osaka University Suita Japan Integrated Frontier Research for Medical Science Division Institute for Open and Transdisciplinary Research Initiatives Osaka University Suita Japan Center for Infectious Disease Education and Research (CiDER) Osaka University Suita Japan Massachusetts Veterans Epidemiology Research and Information Center (MAVERIC) VA Boston Healthcare System Boston MA USA TIMI S

来源：评论

学校读者我要写书评

暂无评论

A complete gradient clustering algorithm

A complete gradient clustering algorithm

引用

3rd International Conference on Artificial Intelligence and Computational Intelligence, AICI 2011

作者： Kulczycki, Piotr Charytanowicz, Malgorzata Systems Research Institute Polish Academy of Sciences Center for Stochastic Data Analysis Methods Newelska 6 PL-01-447 Warsaw Poland Cracow University of Technology Department of Automatic Control and Information Technology Cracow Poland Catholic University of Lublin Institute of Mathematics and Computer Science Lublin Poland

ISBN: (纸本)9783642238956

A gradient clustering algorithm, based on the nonparametric methodology of statistical kernel estimators, expanded to its complete form, enabling implementation without particular knowledge of the theoretical aspects or laborious research, is presented here. The possibilities of calculating tentative optimal parameter values, and then - based on illustrative interpretation - their potential changes, result in the proposed Complete Gradient Clustering Algorithm possessing many original and valuable, from an applicational point of view, properties. Above all the number of clusters is not arbitrarily imposed but fitted to a real data structure. It is also possible to increase the scale of the number (still avoiding arbitrary assumptions), as well as the proportion of clusters in areas of dense and sparse situation of data elements. The method is universal in character and can be applied to a wide range of practical problems, in particular from the bioinformatics, management and engineering fields. © 2011 Springer-Verlag.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

data analysis and exploration for a fault detection, diagnosis, and prognosis system

Data analysis and exploration for a fault detection, diagnos...

引用

IEEE International Energy Conference and Exhibition (EnergyCon)

作者： Piotr Kulczycki Systems Research Institute Center of Statistical Data Analysis Methods Polish Academy of Sciences Warsaw Poland

The subject of this paper is a statistical fault detection system with the scope of detection, diagnosis and prognosis. It was designed using the fundamental procedures of data analysis and exploration: recognizing atypical elements (outliers), clustering, and classification, based on the nonparametric methodology of kernel estimators. Employing a homogenous mathematical apparatus for all three of the above tasks significantly facilitates practical implementation. The formula for the proposed concept is universal in character, and the investigated system can be applied in a wide range of tasks, particularly in engineering and management. Experimental tests showed its effectiveness in identifying abrupt as well as slowly progressing anomalies. For the latter case in particular, the still rarely-used function for prediction of faults prevailed.

关键词： Kernel Random variables Smoothing methods Fault detection data analysis Finite element methods Approximation methods

来源：评论

学校读者我要写书评

暂无评论

Influence of human engineering on manning levels and human performance on ships

引用

NAVAL ENGINEERS JOURNAL 1997年第5期109卷 67-76页

作者： Anderson, DE Oberman, FR Malone, TB Baker, CC David E. Anderson:has a bachelor of science degree in environmental engineering from Florida Technological University and a master's degree in environmental engineering from the University of Central Florida. He is a graduate of the Naval Sea Systems Command's Engineer-In-Training (EIT) Program. Mr. Anderson was instrumental in introducing the collective protection system (CPS) in the U.S. Navy developing the initial forward-fit package for the USS Gunston Hall and the engineering change proposal (ECP) for the USS Wasp. In 1990 he joined the Human Systems Integration (HSI) Division (SEA 55W5) where he was task leader for auxiliary ships. He is currently the HSI manager for the future technology variant of the SeaLift ship and the future carrier. Association of Scientists and Engineers 33rdAnnual Technical Symposium 26 April 1996. Fred R. Oberman:has B.A. and M.A. degrees from the University of Chicago and Loyola University (experimental psychology) and an M.S. degree in industrial engineering and operations research from Virginia Polytechnic Institute (VPI). He has more than 30 years experience in HSI management planning research analysis design and testing in government and private sector positions. He is currently responsible for NavSea HSI generic research and tool development efforts. He is responsible for Human Engineering Specifications and Standards (Commercial Hypertext) and is the NavSea 03D7 representative on HSI in Performance Specifications and for integration of HSI within Integrated Logistic Support (ILS). He has served as DoD HSI SubTAG chair and member of the Simulation and Modeling Test and Evaluation Display and Control Systems Human Computer Interaction Specifications and Standards and Systems Design Sub Tags as a member of the Society of Naval Architects and Marine Engineers (SNAME) Systems Safety Panel and a member of NATO RSG 14 on man-machine analysis. Thomas B. Malone: CHFEP received a Ph.D. in experimental psychology from Fordham University in 1964. He is president of Carlow

The objectives of Human Engineering (HE) are generally viewed as increasing human performance, reducing human error, enhancing personnel and equipment safety, and reducing training and related personnel costs. There are other benefits that are thoroughly consistent with the direction of the Navy of the future, chief among these is reduction of required numbers of personnel to operate and maintain Navy ships. The Naval Research Advisory Committee (NRAC) report on Man-Machine Technology in the Navy estimated that one of the benefits from increased application of man-machine technology to Navy ship design is personnel reduction as well as improving system availability, effectiveness, and safety The objective of this paper is to discuss aspects of the human engineering design of ships and systems that affect manning requirements, and impact human-performance and safety The paper will also discuss how the application of human engineering leads to improved performance, and crew safety, and reduced workload, all of which influence manning levels. Finally, the paper presents a discussion of tools and case studies of good human engineering design practices which reduce manning.

关键词： Human engineering

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：