检索结果-内蒙古大学图书馆

Simultaneous outlier detection and elimination in hyperspectral unmixing via weighted non-negative matrix tri-factorization

引用

Machine Learning 2025年第7期114卷

作者： Hashemi-Nazari, Yasin Saberi-Movahed, Farid Tajaddini, Azita Moreira, Catarina Ning, Xin Tiwari, Prayag Department of Applied Mathematics Faculty of Mathematics and Computer Shahid Bahonar University of Kerman Kerman Iran Department of Applied Mathematics Faculty of Sciences and Modern Technologies Graduate University of Advanced Technology Kerman Iran Data Science Institute University of Technology Sydney Sydney Australia AnnLab Institute of Semiconductors Chinese Academy of Sciences Beijing China School of Information Technology Halmstad University Halmstad Sweden

Hyperspectral unmixing (HU) involves separating mixed pixel spectra into pure endmember spectra and their corresponding abundance fractions. However, it faces significant challenges due to outliers in the hyperspectral data, which often appear as pixel and band anomalies. Outliers in pixels could result in incorrect classification and inaccurate quantification of materials, while outliers in bands could alter spectral characteristics, leading to misidentifying endmembers and incorrect estimates of abundance. To tackle these issues, this paper introduces a new approach, named simultaneous outlier detection and elimination via weighted non-negative matrix tri-factorization (SODE-WNMTF), which offers an efficient means of addressing the impact of outliers in the unmixing process. Leveraging the co-clustering property of NMTF, SODE-WNMTF introduces a novel weighting matrix, which involves simultaneous clustering of both pixels and spectral bands to effectively detect and mitigate the negative impact of both pixel and band outliers during the unmixing process. At the same time, the inherent structure of the hyperspectral image (HSI) is utilized through the examination of local and global connections among pixels and spectral bands, consequently improving the co-clustering procedure. In addition, SODE-WNMTF proposes a spatial weighting factor, which utilizes the similarity of adjacent pixels, to promote piecewise smoothness in abundance maps while mitigating the impact of outliers. Moreover, since pixels in regions dominated by a single endmember exhibit spectra closely resembling that endmember, SODE-WNMTF incorporates a sparse estimation technique for endmember signatures. Finally, to verify the performance of SODE-WNMTF, a series of experiments is conducted on both synthetic and real HSIs, with outcomes proving its superiority against other cutting-edge approaches. The source code is also available at https://***/yasinhashemi/SODE-WNMTF. © The Author(s) 2025.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Features Importance in Classification Models for Colorectal Cancer Cases Phenotype in Indonesia

引用

Procedia computer science 2019年 157卷 313-320页

作者： Tjeng Wawan Cenggoro Bharuno Mahesworo Arif Budiarto James Baurley Teddy Suparyanto Bens Pardamean Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 BioRealm LLC Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta Indonesia 11480

Recently there has been an interest in predicting complex disease risk using models that combine the effects of many genetic factors together. These are known as polygenic models and are useful in evaluating risk of disease in patients. These models, however, often do not include important non-genetic factors that are important to the prediction of the disease. In this paper, we explore the prediction of colorectal cancer in Indonesia from non-genetic factors using common machine learning algorithms: XGBoost and Elastic Net. The result of this study identified 8 features with strong importance from both XGBoost and Elastic Net. We recommend including these features as covariates in future genetic association studies of colorectal cancer in Indonesia. Ultimately these models may be implemented as tools to screen patients for colorectal cancer risk.

关键词： Feature Importance Feature Selection XGBoost Generalized Linear Model Elastic Net Colorectal Cancer

来源：评论

学校读者我要写书评

暂无评论

New evidence supporting past dust ejections from active asteroid (4015) Wilson–Harrington

arXiv

引用

arXiv 2024年

作者： Jin, Sunho Ishiguro, Masateru Geem, Jooyeon Naito, Hiroyuki Takahashi, Jun Akitaya, Hiroshi Kuroda, Daisuke Urakawa, Seitaro Takagi, Seiko Oono, Tatsuharu Sekiguchi, Tomohiko Perna, Davide Ieva, Simone Bach, Yoonsoo P. Imazawa, Ryo Kawabata, Koji S. Watanabe, Makoto Jo, Hangbin Department of Physics and Astronomy Seoul National University 1 Gwanak-ro Gwanak-gu Seoul08826 Korea Republic of SNU Astronomy Research Center Department of Physics and Astronomy Seoul National University 1 Gwanak-ro Gwanak-gu Seoul08826 Korea Republic of Nayoro Observatory 157-1 Nisshin Nayoro Hokkaido096-0066 Japan Center for Astronomy University of Hyogo 407-2 Nishigaichi Sayo Hyogo679-5313 Japan Astronomical Research Center Chiba Institute of Technology 2-17-1 Tsudanuma Narashino Chiba275-0016 Japan Planetary Exploration Research Center Chiba Institute of Technology 2-17-1 Tsudanuma Narashino Chiba275-0016 Japan Hiroshima Astrophysical Science Center Hiroshima University 1-3-1 Kagamiyama Higashi-Hiroshima Hiroshima739-8526 Japan Bisei Spaceguard Center Japan Spaceguard Association 1716-3 Okura Bisei-cho Ibara Okayama714-1411 Japan Department of Earth and Planetary Sciences Faculty of Science Hokkaido University Kita-ku Sapporo Hokkaido060-0810 Japan Department of Cosmosciences Graduate School of Science Hokkaido University Kita-ku Sapporo Hokkaido060-0810 Japan Asahikawa Campus Hokkaido University of Education Hokumon Hokkaido Asahikawa070-8621 Japan INAF - Osservatorio Astronomico di Roma Via Frascati 33 Monte Porzio CatoneI-00078 Italy 776 Daedeok-daero Yuseong-gu Daejeon34055 Korea Republic of Physics Program Graduate School of Advanced Science and Engineering Hiroshima University 1-3-1 Kagamiyama Higashi-Hiroshima Hiroshima739-8526 Japan Department of Physics Okayama University of Science 1-1 Ridai-cho Kita-ku Okayama Okayama700-0005 Japan

Context. (4015) Wilson–Harrington (hereafter, WH) was discovered as a comet in 1949 but has a dynamical property consistent with that of a near-Earth asteroid. Although there is a report that the 1949 activity is associated with an ion tail, the cause of the activity has not yet been identified. Aims. This work aims to reveal the mysterious comet-like activity of the near-Earth asteroid. Methods. We conducted new polarimetric observations of WH from May 2022 to January 2023, reanalyses of the photographic plate images taken at the time of its discovery in 1949, and dust tail simulation modelings, where the dust terminal velocity and ejection epoch are taken into account. Results. We found that this object shows polarization characteristics similar to those of low-albedo asteroids. We derived the geometric albedo ranging from pV = 0.076 ± 0.010 to pV = 0.094 ± 0.018 from our polarimetry (the values vary depending on the data used for fitting and the slope-albedo relationship coefficients). In addition, the 1949 image showed an increase in brightness around the nucleus. Furthermore, we found that the color of the tail is consistent with sunlight, suggesting that the 1949 activity is associated with dust ejection. From the dust tail analysis, ∼ 9 × 105 kg of material was ejected episodically at a low velocity equivalent to or even slower than the escape velocity. Conclusions. We conclude that WH is most likely an active asteroid of main belt origin and that the activity in 1949 was likely triggered by mass shedding due to fast rotation. © 2024, CC BY.

关键词： Asteroids

来源：评论

学校读者我要写书评

暂无评论

Collecting the public perception of AI and robot rights

arXiv

引用

arXiv 2020年

作者： Lima, Gabriel Kim, Changyeon Ryu, Seungho Jeon, Chihyung Cha, Meeyoung School of Computing KAIST Daejeon Korea Republic of Dept. of Computer Science Dept. of Mathematics HKUST Hong Kong Hong Kong Graduate School of Science and Technology Policy KAIST Daejeon Korea Republic of IBS & School of Computing KAIST Daejeon Korea Republic of

Whether to give rights to artificial intelligence (AI) and robots has been a sensitive topic since the European Parliament proposed advanced robots could be granted "electronic personalities." Numerous scholars who favor or disfavor its feasibility have participated in the debate. This paper presents an experiment (N=1270) that 1) collects online users’ first impressions of 11 possible rights that could be granted to autonomous electronic agents of the future and 2) examines whether debunking common misconceptions on the proposal modifies one’s stance toward the issue. The results indicate that even though online users mainly disfavor AI and robot rights, they are supportive of protecting electronic agents from cruelty (i.e., favor the right against cruel treatment). Furthermore, people’s perceptions became more positive when given information about rights-bearing non-human entities or myth-refuting statements. The style used to introduce AI and robot rights significantly affected how the participants perceived the proposal, similar to the way metaphors function in creating laws. For robustness, we repeated the experiment over a more representative sample of U.S. residents (N=164) and found that perceptions gathered from online users and those by the general population are similar. Copyright © 2020, The Authors. All rights reserved.

关键词： Autonomous agents

来源：评论

学校读者我要写书评

暂无评论

Author Correction: Single-cell transcriptomics uncovers EGFR signaling-mediated gastric progenitor cell differentiation in stomach homeostasis

引用

Nature communications 2023年第1期14卷 6540页

作者： Hitomi Takada Yohei Sasagawa Mika Yoshimura Kaori Tanaka Yoshimi Iwayama Tetsutaro Hayashi Ayako Isomura-Matoba Itoshi Nikaido Akira Kurisaki Laboratory of Stem Cell Technologies Graduate School of Science and Technology Nara Institute of Science and Technology Takayama-cho Ikoma Nara Japan. Laboratory for Bioinformatics Research RIKEN Center for Biosystems Dynamics Research Wako Saitama Japan. Department of Functional Genome Informatics Biological Data Science Medical Research Institute Tokyo Medical and Dental University Bunkyo Tokyo Japan. Laboratory for Bioinformatics Research RIKEN Center for Biosystems Dynamics Research Wako Saitama Japan. itoshi.nikaido@riken.jp. Department of Functional Genome Informatics Biological Data Science Medical Research Institute Tokyo Medical and Dental University Bunkyo Tokyo Japan. itoshi.nikaido@riken.jp. Master's/Doctoral Program in Life Science Innovation (Bioinformatics) Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba Ibaraki Japan. itoshi.nikaido@riken.jp. Laboratory of Stem Cell Technologies Graduate School of Science and Technology Nara Institute of Science and Technology Takayama-cho Ikoma Nara Japan. akikuri@bs.naist.jp.

来源：评论

学校读者我要写书评

暂无评论

A Scenario-Based Branch-and-Bound Approach for Mes Scheduling In Urban Buildings

arXiv

引用

arXiv 2020年

作者： Dan, Mainak Srinivasan, Seshadhri Sundaram, Suresh Easwaran, Arvind Glielmo, Luigi Interdisciplinary Graduate Program Nanyang Technological University Singapore Singapore Department of Aerospace Engineering Indian Institute of Science Bangalore India School of Computer Science and Engineering Nanyang Technological University Singapore Singapore Department of Engineering University of Sannio Benevento Italy

This paper presents a novel solution technique for scheduling multi-energy system (MES) in a commercial urban building to perform price-based demand response and reduce energy costs. The MES scheduling problem is formulated as a mixed integer nonlinear program (MINLP), a non-convex NP-hard problem with uncertainties due to renewable generation and demand. A model predictive control approach is used to handle the uncertainties and price variations. This in-turn requires solving a time-coupled multi-time step MINLP during each time-epoch which is computationally intensive. This investigation proposes an approach called the Scenario-Based Branch-and-Bound (SB3), a light-weight solver to reduce the computational complexity. It combines the simplicity of convex programs with the ability of meta-heuristic techniques to handle complex nonlinear problems. The performance of the SB3 solver is validated in the Cleantech building, Singapore and the results demonstrate that the proposed algorithm reduces energy cost by about 17.26% and 22.46% as against solving a multi-time step heuristic optimization model. Copyright © 2020, The Authors. All rights reserved.

关键词： Nonlinear programming

来源：评论

学校读者我要写书评

暂无评论

Maximum mean discrepancy test is aware of adversarial attacks

arXiv

引用

arXiv 2020年

作者： Gao, Ruize Liu, Feng Zhang, Jingfeng Han, Bo Liu, Tongliang Niu, Gang Sugiyama, Masashi Department of Computer Science Hong Kong Baptist University Department of Computer Science and Engineering The Chinese University of Hong Kong DeSI Lab AAII University of Technology Sydney RIKEN-AIP TML Lab University of Sydney Graduate School of Frontier Sciences University of Tokyo

The maximum mean discrepancy (MMD) test could in principle detect any distributional discrepancy between two datasets. However, it has been shown that the MMD test is unaware of adversarial attacks-the MMD test failed to detect the discrepancy between natural and adversarial data. Given this phenomenon, we raise a question: are natural and adversarial data really from different distributions? The answer is affirmative-the previous use of the MMD test on the purpose missed three key factors, and accordingly, we propose three components. Firstly, Gaussian kernel has limited representation power, and we replace it with an effective deep kernel. Secondly, test power of the MMD test was neglected, and we maximize it following asymptotic statistics. Finally, adversarial data may be non-independent, and we overcome this issue with the wild bootstrap. By taking care of the three factors, we verify that the MMD test is aware of adversarial attacks, which lights up a novel road for adversarial data detection based on two-sample tests. Copyright © 2020, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Development of an Interactive Semantic Medical Image Segmentation System

Development of an Interactive Semantic Medical Image Segment...

引用

IEEE Global Conference on Consumer Electronics (GCCE)

作者： Hikari Jinbo Titinunt Kitrungrotsaku Yutaro Iwamoto Lanfen Lin Hongjie Hu Yen-Wei Chen Graduate School of Information Science and Engineering Ritsumeikan University Shiga Japan Research Center for Healthcare Data Science Zhejiang Lab Hangzhou China College of Computer Science and Technology Zhejiang University Hangzhou China Sir Run Run Shaw Hospital Hangzhou China

ISBN: (数字)9781728198026

ISBN: (纸本)9781728198033

Medical image segmentation (i.e., liver segmentation) is an important pre-processing for computer-aided diagnosis and computer-aided surgery. Deep learning, which can perform fully automated segmentation, has been popular in the medical field because of its ability to reduce the burden on doctors. However, segmentation is inherently a difficult problem and the accuracy of current deep learning-based segmentation methods remains insufficient. In this work, an interactive network-based segmentation is proposed, which can improve the operation through collaborations with a doctor.

关键词： Image segmentation Semantics Surgery Medical services Tools Medical diagnostic imaging Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

P-1.5: Dynamic Current Stress-Induced Instabilities of a-InGaZnO TFTs

引用

SID Symposium Digest of Technical Papers 2022年第S1期53卷

作者： Fayang Liu Yuheng Zhou Xiaoliang Zhou Huan Yang Zhihe Xia Fion Sze Yan Yeung Man Wong Hoi Sing Kwok Shengdong Zhang Lei LU School of Electronic and Computer Engineering Shenzhen Graduate School Peking University Shenzhen China State Key Laboratory on Advanced Displays and Optoelectronics Technologies Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong China

The degradation and breakdown behaviors of top-gate self-aligned a-InGaZnO thin-film transistors (TFTs) under dynamic current stresses (DCSs) were systematically investigated. Both linear- and saturation-regime DCSs were found to be capable of causing the self-heating degradations, including the negative shift of threshold voltage, the increase of subthreshold slope and drain current. While the linear DCS eventually forms a conductor-like channel, the saturation DCS causes an additional hot carrier (HC) effect to form a defective drain regions of high energy barrier, disconnecting the �conductor channel� from the drain side.

关键词： Amorphous oxide semiconductor (AOS) indium-gallium-zinc oxide (IGZO) thin-film transistor (TFT) dynamic current stress (DCS) self-heating (SH) hot carrier (HC)

来源：评论

学校读者我要写书评

暂无评论

Variational Tensor Network Operator

arXiv

引用

arXiv 2022年

作者： Chen, Yu-Hsueh Hsu, Ke Tu, Wei-Lin Lee, Hyun-Yong Kao, Ying-Jer Center for Theoretical Physics Department of Physics National Taiwan University Taipei10607 Taiwan Division of Display and Semiconductor Physics Korea University Sejong30019 Korea Republic of Department of Applied Physics Graduate School Korea University Sejong30019 Korea Republic of Interdisciplinary Program in E·ICT-Culture-Sports Convergence Korea University Sejong30019 Korea Republic of Center for Quantum Science and Technology National Taiwan University Taipei10607 Taiwan

We propose a simple and generic construction of the variational tensor network operators to study the quantum spin systems by the synergy of ideas from the imaginary-time evolution and variational optimization of trial wave functions. By applying these operators to simple initial states, accurate variational ground state wave functions with extremely few parameters can be obtained. Furthermore, the framework can be applied to study spontaneously symmetry breaking, symmetry protected topological, and intrinsic topologically ordered phases, and we show that symmetries of the local tensors associated with these phases can emerge directly after the optimization without any gauge fixing. This provides a universal way to identify quantum phase transitions without prior knowledge of the system. Copyright © 2022, The Authors. All rights reserved.

关键词： Tensors

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：