检索结果-内蒙古大学图书馆

Proceedings of the 2020 4th International Symposium on computer science and Intelligent Control

作者： Bekkouch Imad Ibrahim Dragoş Constantin Nicolae Adil Khan Syed Imran Ali Asad Khattak Machine Learning and Knowledge Representation Lab Institute of Data Science & AI Innopolis Tatarstan Russia Institutul de cercetări pentru Inteligenta Artificiala 'Mihai Draganescu' România Department of Computer Engineering Kyung Hee University Yongin-si South Korea College of Technological Innovations Zayed University Abu Dhabi United Arab Emirates

ISBN: (纸本)9781450388894

Outlier detection is one of the main fields in machine learning and it has been growing rapidly due to its wide range of applications. In the last few years, deep learning-based methods have outperformed machine learning and handcrafted outlier detection techniques, and our method is no different. We present a new twist to generative models which leverages variational autoencoders as a source for uniform distributions which can be used to separate the inliers from the outliers. Both the generative and adversarial parts of the model are used to obtain three main losses (Reconstruction loss, KL-divergence, Discriminative loss) which in return are wrapped with a one-class SVM which is used to make the predictions. We evaluated our method against several datasets both for images and tabular data and it has shown great results for the zero-shot outlier detection problem and was able to easily generalize it for supervised outlier detection tasks on which the performance has increased. For comparison, we evaluated our method against several of the common outlier detection techniques such as DBSCAN-based outlier detection, GMM, K-means and one class SVM directly, and we have outperformed all of them on all datasets.

关键词： Deep Learning Generative Models Machine Learning Outlier Detection

来源：评论

学校读者我要写书评

暂无评论

Document-Level Relation Extraction with Entity Type Constraints

SSRN

引用

SSRN 2024年

作者： Han, Ridong Peng, Tao Zhu, BeiBei Bi, Haijia Han, Jiayu Liu, Lu College of Computer Science and Technology Jilin University Jilin Changchun130012 China College of Software Jilin University Jilin Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin Changchun130012 China College of Computer and Artificial Intelligence Liaoning Normal University Liaoning Dalian116081 China Department of Linguistics University of Washington SeattleWA98195 United States

Long-tail problem and multi-label problem are two commonly encountered challenges in document-level relation extraction task. Current efforts are concerned with enhancing the representations of entity pairs through Transformer or document graphs, which cannot tackle the above challenges well. Relation correlations are a potential solution, which allows head relations to assist in the training of tail ones by transferring correlation knowledge between them, and can measure the semantic distance between relations to assist the classifier in assigning multiple semantically similar relations to multi-label instances. This paper proposes to learn relation correlations from both global and local views using entity type constraints, which means that the subject-object entity types limit the scope of possible relations. Globally, we statistically construct the Type-constrained Graph between entity types and relations, which formulates all possible subject/object types for each relation. Different relations are connected by common entity types, reflecting the desired correlations. Locally, given an entity pair, the classification probability of relations matching its entity types should be greater than those unmatched. Therefore, the Type-constrained Loss is proposed to make the matched relations have greater probabilities. Detailed experiments are conducted on DocRED and DWIE datasets, and our model significantly outperforms baselines under long-tail and multi-label setups. © 2024, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Elucidating Spatial Complex Structures from Mass Spectrometry Imaging with Deep Multimodal Model

Elucidating Spatial Complex Structures from Mass Spectrometr...

引用

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Jiangnan Cui Junjie Xia Xuan Li Yan Wang Fufang Qiu Yaochen Xu Keren Xu Chunman Zuo School of Computer Science and Technology Institute of Artificial Intelligence Donghua University Shanghai China Institute of Artificial Intelligence Donghua University Shanghai China College of Computer Science and Technology Jilin University Changchun China Department of Neurosurgery Huashan Hospital Shanghai China CAS Key Laboratory of Systems Biology Shanghai Institute of Biochemistry and Cell Biology Center for Excellence in Molecular Cell Science Chinese Academy of Sciences Shanghai China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

Spatial mass spectrometry imaging (SMSI) technology has enabled the characterization of biomolecule patterns within the tissue microenvironment, yet its analyses suffer from substantial noise. The lack of effective methods for exploiting multi-view features (e.g., spatial location) has hindered their elucidation ability for tissue heterogeneity. Here, we propose MSG, a multimodal modal that integrates histology, spatial location, and MSI data, in deciphering tissue structure by graph neural network. Specifically, MSG learns low-dimensional representations by aggregating histomorphological features from neighboring tiles via graph attention autoencoder. MSG outperforms other methods in identifying spatial domains and denoising data. The subsequent domain-guided differential expression analysis of the denoised data enables the identification of ions with significantly enriched patterns within the recognized domains. MSG exhibits its versatility in handling SMSI data from various platforms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SPFLOW: An easy and extensible library for deep probabilistic learning using sum-product networks

arXiv

引用

arXiv 2019年

作者： Molina, Alejandro Vergari, Antonio Stelzner, Karl Peharz, Robert Subramani, Pranav Di Mauro, Nicola Poupart, Pascal Kersting, Kristian Machine Learning Group Computer Science Department TU Darmstadt Germany Probabilistic Learning Group Empirical Inference Department Max-Planck-Institute Germany Machine Learning Group Engineering Dept. University of Cambridge United Kingdom Knowledge Acquisition & Machine Learning Group University of Bari "Aldo Moro" Italy Waterloo AI Institute Vector Institute University of Waterloo CA Canada Centre for Cognitive Science TU Darmstadt Germany

We introduce SPFlow, an open-source Python library providing a simple interface to inference, learning and manipulation routines for deep and tractable probabilistic models called Sum-Product Networks (SPNs). The library allows one to quickly create SPNs both from data and through a domain specific language (DSL). It efficiently implements several probabilistic inference routines like computing marginals, conditionals and (approximate) most probable explanations (MPEs) along with sampling as well as utilities for serializing, plotting and structure statistics on an SPN. Moreover, many of the algorithms proposed in the literature to learn the structure and parameters of SPNs are readily available in SPFlow. Furthermore, SPFlow is extremely extensible and customizable, allowing users to promptly distill new inference and learning routines by injecting custom code into a lightweight functional-oriented API framework. This is achieved in SPFlow by keeping an internal Python representation of the graph structure that also enables practical compilation of an SPN into a TensorFlow graph, C, CUDA or FPGA custom code, significantly speeding-up computations. Copyright © 2019, The Authors. All rights reserved.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Preface

引用

计算机科学技术学报（英文版） 2007年第2期22卷插1-插2页

作者： Shan Wang Jian-Zhong Li Scholl of Information Key Lab Data Engineering and Knowledge EngineeringRenmin University of China Department of Computer Science and Technology Harbin Institute of Technology

Recent advances in database related applications propose many new challenges and have inspired database researchers and practitioners to further make their efforts on new database technologies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Preface

EAI/Springer Innovations in Communication and Computing

引用

EAI/Springer Innovations in Communication and Computing 2022年 V-VI页

作者： Haldorai, Anandakumar Ramu, Arulmurugan Mohanram, Sudha Lu, Joan Department of Computer Science and Engineering Sri Eshwar College of Engineering TN Coimbatore India Department of Computer Science and Engineering Presidency University KA Bengaluru India Sri Eshwar College of Engineering TN Coimbatore India Department of Computer Science School of Computing and Engineering Centre for Planning Autonomy and Representation of Knowledge University of Huddersfield Huddersfield United Kingdom

来源：评论

学校读者我要写书评

暂无评论

Deep learning - A first meta-survey of selected reviews across scientific disciplines, their commonalities, challenges and research impact

arXiv

引用

arXiv 2020年

作者： Egger, Jan Pepe, Antonio Gsaxner, Christina Jin, Yuan Li, Jianning Kern, Roman Institute of Computer Graphics and Vision Faculty of Computer Science and Biomedical Engineering Graz University of Technology Graz Austria Computer Algorithms for Medicine Laboratory Graz Austria Department of Oral and Maxillofacial Surgery Medical University of Graz Graz Austria University Medicine Essen Essen Germany Research Center for Connected Healthcare Big Data Zhejiang Lab Zhejiang Hangzhou China Research Unit Experimental Neurotraumatology Department of Neurosurgery Medical University of Graz Graz Austria Knowledge Discovery Know-Center Graz Austria Institute of Interactive Systems and Data Science Graz University of Technology Graz Austria

Deep learning belongs to the field of artificial intelligence, where machines perform tasks that typically require some kind of human intelligence. Deep learning tries to achieve this by drawing inspiration from the learning of a human brain. Similar to the basic structure of a brain, which consists of (billions of) neurons and connections between them, a deep learning algorithm consists of an artificial neural network, which resembles the biological brain structure. Mimicking the learning process of humans with their senses, deep learning networks are fed with (sensory) data, like texts, images, videos or sounds. These networks outperform the state-of-the-art methods in different tasks and, because of this, the whole field saw an exponential growth during the last years. This growth resulted in way over 10,000 publications per year in the last years. For example, the search engine PubMed alone, which covers only a sub-set of all publications in the medical field, provides already over 11,000 results in Q3 2020 for the search term 'deep learning', and around 90% of these results are from the last three years. Consequently, a complete overview over the field of deep learning is already impossible to obtain and, in the near future, it will potentially become difficult to obtain an overview over a subfield. However, there are several review articles about deep learning, which are focused on specific scientific fields or applications, for example deep learning advances in computer vision or in specific tasks like object detection. With these surveys as a foundation, the aim of this contribution is to provide a first high-level, categorized meta-survey of selected reviews on deep learning across different scientific disciplines and outline the research impact that they already have during a short period of time. The categories (computer vision, language processing, medical informatics and additional works) have been chosen according to the underlying data sources (image,

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Approach to Classify Biomedical Acoustic Features for Baby Cries

引用

Journal of Voice 2023年

作者： Aggarwal, Gaurav Jhajharia, Kavita Izhar, Jaweria Kumar, Manoj Abualigah, Laith Department of Information Technology and Engineering Amity University in Tashkent Uzbekistan Department of Information Technology Manipal University Jaipur India Department of Engineering and Information Sciences School of Computer Science FEIS University of Wollongong in Dubai Dubai Knowledge Park Dubai United Arab Emirates Department of Information Technology Al al-Bayt University Jordan and MEU Research Unit Faculty of Information Technology Middle East University Amman 11831 Jordan

Communication is imperative for living beings for exchanging information. But for newborns, the only way of communicating with the world is through crying, and it is the only medium through which caregivers can know about the needs of their children. Timely addressing baby cries is very important so that the child is relieved at the earliest. It has been a challenge, especially for new parents. The literature says newborn babies use The Dustan Baby Language to communicate. According to this language, there are five words to understand a baby's needs, which are “Neh” (hungry), “Eh” (burp is needed), “Owh/Oah” (fatigue), “Eair/Eargghh” (cramps), “Heh” (feel hot or wet, physical discomfort). This research aims to develop a model for recognizing baby cries and distinguishing between different kinds of baby cries. Here we more broadly focus on whether the infant is in pain due to hunger or discomfort. The study proposes a comparative approach using four classification models: random forest, support vector machine, logistic regression, and decision tree. These algorithms learn from the spectral features: chroma_stft, spectral_centroid, bandwidth, spectral_rolloff, mel-frequency cepstral coefficients, linear predictive coding, res, zero_crossing_rate extracted from the infant cry. The support vector machine model outperforms other classifiers for correctly classifying infant cries. © 2023 The Voice Foundation

关键词： Acoustic features Classification Cry Discomfort Hunger Spectral features SVM

来源：评论

学校读者我要写书评

暂无评论

Exploring advanced materials: Harnessing the synergy of inverse gas chromatography and artificial vision intelligence

引用

TrAC - Trends in Analytical Chemistry 2024年 173卷

作者： Basivi, Praveen Kumar Hamieh, Tayssir Kakani, Vijay Pasupuleti, Visweswara Rao Sasikala, G. Heo, Sung Min Pasupuleti, Kedhareswara Sairam Kim, Moon-Deock Munagapati, Venkata Subbaiah Siva Kumar, Nadavala Wen, Jet-Chau Kim, Chang Woo Pukyong National University Industry-University Cooperation Foundation Pukyong National University Busan48513 Korea Republic of Faculty of Science and Engineering Maastricht University P.O. Box 616 MD Maastricht6200 Netherlands Faculty of Sciences Lebanese University Hadath Lebanon Department of Integrated System Engineering INHA University 100 Inha-ro Namgu Incheon22212 Korea Republic of Center for International Relations and Research Collaborations and School of Applied Sciences REVA University Rukmini Knowledge Park Kattigenahalli Yelahanka Karnataka Bangalore560064 India School of Computer Sciences and Applications REVA University Kattigenahalli Rukmini Knowledge Park Bangalore560064 India Department of Smart Green Technology Engineering Pukyong National University Busan48513 Korea Republic of Chungnam National University 99 Daehak-ro Yuseong-gu Daejeon34134 Korea Republic of National Yunlin University of Science and Technology Douliou Yunlin64002 Taiwan Department of Safety Health and Environmental Engineering National Yunlin University of Science and Technology Douliou Yunlin64002 Taiwan Department of Chemical Engineering College of Engineering King Saud University P.O. Box - 800 Riyadh11421 Saudi Arabia Department of Nanotechnology Engineering College of Engineering Pukyong National University Busan48513 Korea Republic of

Inverse gas chromatography (IGC) has emerged as a highly sensitive, adaptable, and effective technology for material analysis. Through employing thermochemical approaches, IGC provides crucial insight into physicochemical information of materials such as dispersive surface free energy, Gibbs surface energy components and Guttamann Lewis acid-base parameters. In this comprehensive review, we delve into the historical background, instrumentation, and diverse applications of IGC. Researchers and practitioners will find valuable information on the selection and description of numerous models used in IGC experiments. The applications of IGC span various domains, including polymers, medicines, minerals, surfactants, and nanomaterials. Furthermore, IGC facilitates the measurement of important parameters such as sorption enthalpy and entropy, surface energy components (dispersive and specific), co/adhesion work, glass transition temperature, surface heterogeneity, miscibility, solubility parameters, and specific surface area. These insights contribute to a deeper understanding of material behavior and aid in the design and optimization of advanced materials. Moreover, the integration of computer vision and image processing techniques with IGC has enhanced our understanding of materials intricate surface texture, roughness, and related properties. This convergence of IGC with computer vision and artificial intelligence (AI) presents exciting opportunities for future exploration of chemical materials, opening new avenues for research and discovery. This paper not only provides a comprehensive overview of IGC, its techniques, and applications but also highlights the synergistic potential of combining IGC with AI and computer vision. The informative content and insights presented here will benefit researchers, scientists, and professionals in the field of advanced materials, enabling them to leverage IGC and AI for innovative materials discovery and development. © 2024 Elsevier

关键词： Interfacial energy

来源：评论

学校读者我要写书评

暂无评论

PhylOnt: A domain-specific ontology for phylogeny analysis

PhylOnt: A domain-specific ontology for phylogeny analysis

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Maryam Panahiazar Ajith Ranabahu Vahid Taslimi Hima Yalamanchili Arlin Stoltzfus Jim Leebens-Mack Amit P. Sheth Ohio Center for Excellence in Knowledge-enabled Computing (kno.e.sis) College of Computer Science and Engineering Wright State University Dayton OH USA Bioinformatics Institute University of Georgia Athens GA USA Institute for Bioscience and Biotechnology Research University of Maryland Rockville MD USA Biochemical Science Division NIST Gaithersburg MD USA Department of Plant Biology University of Georgia Athens GA USA

Phylogenetic analyses can resolve historical relationships among genes, organisms or higher taxa. Understanding such relationships can elucidate a wide range of biological phenomena including the role of adaptation as a driver of diversification, the importance of gene and genome duplications in the evolution gene function, or the evolutionary consequences of biogeographic shifts. The variety of methods of analysis and data types typically employed in phylogenetic analyses can pose challenges for semantic reasoning due to significant representational and computational complexity. These challenges could be ameliorated with the development of an ontology designed to capture and organize the variety of concepts used to describe phylogenetic data, methods of analysis and the results of phylogenetic analyses. In this paper, we discuss the development of PhylOnt - an ontology for phylogenetic analyses, which establishes a foundation for semantics-based workflows including meta-analyses of phylogentic data and trees. PhylOnt is an extensible ontology, which describes the methods employed to estimate trees given a data matrix, models and programs used for phylogenetic analysis and descriptions of phylogenetic trees including branch-length information and support values. The relational vocabulary included in PhylOnt will facilitate the integration of heterogeneous data types derived from both structured and unstructured sources. To illustrate the utility of PhylOnt, we annotated scientific literature to support semantic search. The semantic annotations can subsequently support workflows that requiring the exchange and integration of heterogeneous phylogenetic information.

关键词： Phylogeny Ontologies Semantics Analytical models Vegetation Measurement

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：