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

Virtual external stimulation promotes the transformation of the brain state from early mild cognitive impairment to health

Brain-X

引用

Brain-X 2023年第4期1卷

作者： Wang, Weiping Wang, Weiwei Zhao, Haiyan Wang, Zhen Luo, Xiong Ouyang, Jipeng School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China Shunde Innovation School University of Science and Technology Beijing Guangdong Shunde China Beijing Key Laboratory of Knowledge Engineering for Materials Science Beijing China Department of Neurology Peking University Third Hospital Beijing China The Center for Optical Imagery Analysis and Learning and School of Mechanical Engineering Northwestern Polytechnical University Shaanxi Xi'an China Department of Neurology Shunde Hospital Southern Medical University Guangdong Shunde China

Neurostimulation has emerged as a potential remedy for early mild cognitive impairment (EMCI). However, further exploration is needed on how external stimulation of brain regions promotes the transition of the brain state from EMCI to health and the selection of target locations. In this study, a functional magnetic resonance imaging dataset was used to evaluate the brain states of healthy individuals and patients with EMCI to explore the probabilistic metastable substate space, identifying abnormal manifestations of EMCI. Stimulation targets were then identified and stimulated to achieve complete controllability of the effective connection network for EMCI. A whole-brain model successfully fitted the brain state of the patients with EMCI based on diffusion tensor imaging data. Based on this whole-brain model, stimulation of the hippocampus, medial frontal gyrus, suboccipital gyrus, and fusiform gyrus can promote the transformation of the brain state from EMCI to health. The findings reveal the underlying brain mechanisms of cognitive decline in patients with EMCI and the stimulation targets of the neural mechanisms of EMCI restoration, which could help in designing more effective therapeutic interventions for EMCI. © 2023 The Authors. Brain-X published by John Wiley & Sons Australia, Ltd on behalf of Ainuohui Medical Technology.

关键词： brain state transition computational modeling early mild cognitive impairment exact controllability functional dynamics

来源：评论

学校读者我要写书评

暂无评论

Completability vs (In)completeness

引用

Acta Linguistica 2020年第2期52卷 260-284页

作者： Eleni Gregoromichelaki Gregory James Mills Christine Howes Arash Eshghi Stergios Chatzikyriakidis Matthew Purver Ruth Kempson Ronnie Cann Patrick G. T. Healey Heinrich Heine University of Düsseldorf Düsseldorf Germany Department of Philosophy King’s College London Department of Philosophy Linguistics and Theory of Science University of Gothenburg Gothenburg Sweden Centre for Language and Cognition Department of Communication and Information Science University of Groningen Groningen Netherlands Department of Computer Science School of Mathematical and Computer Sciences Heriot-Watt University Edinburgh UK Cognitive Science Research Group School of Electronic Engineering and Computer Science Queen Mary University of London London UK Department of Knowledge Technologies Institut Jožef Stefan Ljubljana Slovenia School of Philosophy Psychology and Language Sciences University of Edinburgh Edinburgh UK

ABSTRACTABSTRACTIn everyday conversation, no notion of “complete sentence” is required for syntactic licensing. However, so-called “fragmentary”, “incomplete”, and abandoned utterances are problematic for standard formalisms. When contextualised, such data show that (a) non-sentential utterances are adequate to underpin agent coordination, while (b) all linguistic dependencies can be systematically distributed across participants and turns. Standard models have problems accounting for such data because their notions of ‘constituency’ and ‘syntactic domain’ are independent of performance considerations. Concomitantly, we argue that no notion of “full proposition” or encoded speech act is necessary for successful interaction: strings, contents, and joint actions emerge in conversation without any single participant having envisaged in advance the outcome of their own or their interlocutors’ actions. Nonetheless, morphosyntactic and semantic licensing mechanisms need to apply incrementally and subsententially. We argue that, while a representational level of abstract syntax, divorced from conceptual structure and physical action, impedes natural accounts of subsentential coordination phenomena, a view of grammar as a “skill” employing domain-general mechanisms, rather than fixed form-meaning mappings, is needed instead. We provide a sketch of a predictive and incremental architecture (Dynamic Syntax) within which underspecification and time-relative update of meanings and utterances constitute the sole concept of “syntax”.

关键词： Dynamic syntax ellipsis fragments incrementality joint action repair split utterances English Modern Greek

来源：评论

学校读者我要写书评

暂无评论

Autonomous Design of Biomimetic 3D DNA Origami Capsules 17

Autonomous Design of Biomimetic 3D DNA Origami Capsules

引用

17th Annual Conference on Foundations of Nanoscience: Self-Assembled Architectures and Devices, FNANO 2020

作者： Narayanan, Raghu Pradeep Fu, Daniel Zhang, Fei Williams, Dewight Schreck, John Reif, John Yan, Hao School of Molecular Sciences and Biodesign Institute Arizona State University TempeAZ85287 United States Department of Computer Science DurhamNC27708 United States Department of Chemistry Rutgers University NewarkNJ07102 United States Erying Materials Center Arizona State University Office of Knowledge Enterprise Development TempeAZ85287 United States Department of Chemical Engineering Colombia University New YorkNY10027 United States

来源：评论

学校读者我要写书评

暂无评论

Solar still performance investigation by incorporating the shape of basin liner: A short review

引用

Materials Today: Proceedings 2021年 43卷 597-604页

作者： Raj Vardhan Patel Kiran Bharti Gaurav Singh Rajeev Kumar Sandeep Chhabra Desh Bandhu Singh Department of Mechanical Engineering Sherwood College of Engineering Research and Technology Barabanki Uttar Pradesh 225003 India Department of Computer Science and Engineering Saraswati Institute of Engineering and Technology NH-24 Pilkhuwa Hapur Uttar Pradesh 245304 India Galgotias University Plot No. 2 Sector 17-A Yamuna Expressway Greater Noida G. B. Nagar UP India Galgotias College of Engineering and Technology Plot No. 1 Knowledge Park II Greater Noida UP India Uttar Pradesh Institute of Design C-22 C Block Phase 2 Industrial Area Sector – 62 Noida 201301 Uttar Pradesh India Department of Mechanical Engineering KIET Group of Institutions Delhi-NCR Ghaziabad 201206 UP India Department of Mechanical Engineering Graphic Era Deemed to be University Bell Road Clement Town Dehardun 248002 Uttarakhand India

The source of solar energy is unlimited and it has the potential of reducing the contemporary shortage of fresh water prevalent throughout the globe if the solar energy is used wisely. This source of energy has emerged as one of the best alternatives to mitigate the crisis of energy as well as fresh water which are the two important factors for the survival of human beings on the earth. The research is going on throughout the world and new type of solar energy technology based water purifiers are being reported. The various studies have been reported in the literature with various designs of the basin liner with an objective of increasing the fresh water output. In this work, a review on the performance investigation of solar still by incorporating the different shapes of basin liner has been carried out. Authors have critically reviewed the solar stills with fins, corrugates wick, hemispherical basin and stepped still. It has been concluded that the evaporation area can be increased by changing the design of basin liner which provides higher fresh water output.

关键词： Solar still Finned basin liner Corrugated shape Fresh water yield Evaporation area

来源：评论

学校读者我要写书评

暂无评论

knowledge discovery in multidimensional knowledge representation framework: An integrative approach for the visualization of text analytics results

引用

Iran Journal of computer science 2018年第4期1卷 199-216页

作者： Zenkert, Johannes Klahold, André Fathi, Madjid Department of Electrical Engineering and Computer Science Institute of Knowledge Management and Knowledge Based Systems University of Siegen Siegen Germany

Visualization of results is one of the central challenges in big data analytics and integrative text mining. With a growing amount of unstructured data and different perspectives on big data, knowledge graphs have difficulties to simultaneously represent and visualize all analyzed dimensions of knowledge. This paper proposes integrative text mining as a solution to combine results from different dimensional analysis in a multidimensional knowledge representation (MKR) for knowledge discovery and visualization purpose. Analysis results from named entity recognition, topic detection, sentiment analysis and the extraction of semantic relationships are, therefore, integrated into a common representation structure. In the implementation part of this research, an application is introduced which utilizes MKR based on the results of stated text mining methods applied on a German and English news data set. State-of-the-art visualizations are used in the application and MKR adaptively transforms the visualization type of the knowledge graph according to the selected context for knowledge discovery. © Springer International Publishing AG, part of Springer Nature 2018.

关键词： Information visualization knowledge graphs knowledge representation Natural language processing Text mining

来源：评论

学校读者我要写书评

暂无评论

Adaptive Dynamic Surface Control of Constrained Nonlinear Systems

Adaptive Dynamic Surface Control of Constrained Nonlinear Sy...

引用

第32届中国控制与决策会议

作者： Ailiang Xing Biao Song Yixin Yin School of Automation and Electrical Engineering University of Science and Technology Beijing Key Laboratory of Knowledge Automation for Industrial Processes Ministry of Education Demonstration and Research Department of Network Information System Beijing Institute of Computer Application

This paper presents an adaptive dynamic surface control for uncertain nonlinear strict feedback systems with constraints on both input and *** technology is employed in the controller *** performance method with asymmetric barrier Lyapunov function(BLF) is used to deal with the output *** input saturation is solved by using the Nussbaum *** dynamic surface control(DSC) technique is employed to reduce the complexity of the virtual *** is illustrated that all closed-loop signals are semi-global uniformly ultimately bounded(SGUUB).Finally,a simulation example proves the proposed results.

关键词： Input saturation Output constraints Nussbaum function Dynamic surface control

来源：评论

学校读者我要写书评

暂无评论

Utilizing bidirectional encoder representations from transformers for answer selection

arXiv

引用

arXiv 2020年

作者： Laskar, Md Tahmid Rahman Hoque, Enamul Huang, Jimmy Xiangji Department of Electrical Engineering and Computer Science York University Toronto Canada Information Retrieval & Knowledge Management Research Lab York University Toronto Canada School of Information Technology York University Toronto Canada

Pre-training a transformer-based model for the language modeling task in a large dataset and then fine-tuning it for downstream tasks has been found very useful in recent years. One major advantage of such pre-trained language models is that they can effectively absorb the context of each word in a sentence. However, for tasks such as the answer selection task, the pre-trained language models have not been extensively used yet. To investigate their effectiveness in such tasks, in this paper, we adopt the pre-trained Bidirectional Encoder Representations from Transformer (BERT) language model and fine-tune it on two Question Answering (QA) datasets and three Community Question Answering (CQA) datasets for the answer selection task. We find that fine-tuning the BERT model for the answer selection task is very effective and observe a maximum improvement of 13.1% in the QA datasets and 18.7% in the CQA datasets compared to the previous state-of-the-art. Copyright © 2020, The Authors. All rights reserved.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Prior-guided dual-stage diabetic retinopathy grading model based on feature collaboration of lesion and vascular structure

引用

Expert Systems with Applications 2025年 285卷

作者： Guo, Xiaoxin Yang, Guangqi Xu, Chenfangqian Dong, Hongliang Hu, Xiaoying Che, Songtian Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University 2699 Qianjin Street Changchun130012 China College of Computer Science and Technology Jilin University 2699 Qianjin Street Changchun130012 China Ophthalmology Department Bethune First Hospital of Jilin University Changchun Jilin130021 China Ophthalmology Department Bethune Second Hospital of Jilin University Changchun Jilin130041 China

In order to fully utilize lesion features and vascular structure and solve the problem of class imbalance, diabetes retinopathy (DR) grading is modeled as a dual-stage task, and the prior-guided dual-stage diabetes retinopathy grading model is proposed by designing an end-to-end hierarchical framework, consisting of XE-Net and MFC-Net. The former uses vascular structure from color fundus images as prior knowledge to guide the classification of proliferative diabetic retinopathy (PDR) and non-PDR;the latter further classifies non-PDR images using color fundus images with four types of segmented lesions. The core of MFC-Net is the feature collaboration block (FCB) for multi-classification tasks, which is proposed to facilitate effective collaboration between global and local features. In addition, a class-balanced (CB) loss weight is also introduced to address the common class imbalance problem in DR datasets. The experimental results on two publicly available datasets, DDR and IDRiD show that the proposed model has significant advantages. © 2025 Elsevier Ltd

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Distributed Representations of Entities in Open-World knowledge Graphs

arXiv

引用

arXiv 2020年

作者： Guo, Lingbing Chen, Zhuo Chen, Jiaoyan Zhang, Yichi Sun, Zequn Bo, Zhongpu Fang, Yin Liu, Xiaoze Chen, Huajun Zhang, Wen College of Computer Science and Technology Zhejiang University China Zhejiang University Ant Group Joint Laboratory of Knowledge Graph China Donghai Laboratory China Department of Computer Science The University of Manchester United Kingdom Department of Computer Science and Technology Nanjing University China Ant Group China Elmore Family School of Electrical and Computer Engineering Purdue University United States School of Software Technology Zhejiang University China

Graph neural network (GNN)-based methods have demonstrated remarkable performance in various knowledge graph (KG) tasks. However, most existing approaches rely on observing all entities during training, posing a challenge in real-world knowledge graphs where new entities emerge frequently. To address this limitation, we introduce Decentralized Attention Network (DAN). DAN leverages neighbor context as the query vector to score the neighbors of an entity, thereby distributing the entity semantics only among its neighbor embeddings. To effectively train a DAN, we introduce self-distillation, a technique that guides the network in generating desired representations. Theoretical analysis validates the effectiveness of our approach. We implement an end-to-end framework and conduct extensive experiments to evaluate our method, showcasing competitive performance on conventional entity alignment and entity prediction tasks. Furthermore, our method significantly outperforms existing methods in open-world settings. © 2020, CC0.

关键词： knowledge graph

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：