基于阶段注意力机制的电力线提取算法

电力系统维护是电力系统稳定运行的重要保障，应用智能算法的无人机电力巡检则为电力系统维护提供便捷。电力线提取是自主电力巡检以及保障飞行器低空飞行安全的关键技术，结合深度学习理论进行电力线提取是电力巡检的重要突破点。本文将深度学习方法用于电力线提取任务，结合电力线图像特点嵌入改进的图像输入策略和注意力模块，提出一种基于阶段注意力机制的电力线提取模型（SA-Unet）。本文提出的SA-Unet模型编码阶段采用阶段输入融合策略（Stage input fusion strategy， SIFS），充分利用图像的多尺度信息减少空间位置信息丢失。解码阶段通过嵌入阶段注意力模块（Stage attention module，SAM）聚焦电力线特征，从大量信息中快速筛选出高价值信息。实验结果表明，该方法在复杂背景的多场景中具有良好的性能。     

A hybrid knowledge and ensemble classification approach for prediction of venous thromboembolism

Clinical narratives such as progress summaries, lab reports, surgical reports, and other narrative texts contain key biomarkers about a patient's health. Evidence-based preventive medicine needs accurate semantic and sentiment analysis to extract and classify medical features as the input to appropriate machine learning classifiers. However, the traditional approach of using single classifiers is limited by the need for dimensionality reduction techniques, statistical feature correlation, a faster learning rate, and the lack of consideration of the semantic relations among features. Hence, extracting semantic and sentiment-based features from clinical text and combining multiple classifiers to create an ensemble intelligent system overcomes many limitations and provides a more robust prediction outcome. The selection of an appropriate approach and its interparameter dependency becomes key for the success of the ensemble method. This paper proposes a hybrid knowledge and ensemble learning framework for prediction of venous thromboembolism (VTE) diagnosis consisting of the following components: a VTE ontology, semantic extraction and sentiment assessment of risk factor framework, and an ensemble classifier. Therefore, a component-based analysis approach was adopted for evaluation using a data set of 250 clinical narratives where knowledge and ensemble achieved the following results with and without semantic extraction and sentiment assessment of risk factor, respectively: a precision of 81.8% and 62.9%, a recall of 81.8% and 57.6%, an F measure of 81.8% and 53.8%, and a receiving operating characteristic of 80.1% and 58.5% in identifying cases of VTE.     

Semantically enriched Massive Open Online Courses (MOOCs) platform

Massive Open Online Courses (MOOCs) are becoming an essential source of information for both students and teachers. Noticeably, MOOCs have to adapt to the fast development of new technologies; they also have to satisfy the current generation of online students. The current MOOCs’ Management Systems, such as Coursera, Udacity, edX, etc., use content management platforms where content are organized in a hierarchical structure. We envision a new generation of MOOCs that support interpretability with formal semantics by using the SemanticWeb and the online social networks. Semantic technologies support more flexible information management than that offered by the current MOOCs’ platforms. Annotated information about courses, video lectures, assignments, students, teachers, etc., can be composed from heterogeneous sources, including contributions from the communities in the forum space. These annotations, combined with legacy data, build foundations for more efficient information discovery in MOOCs’ platforms. In this article we review various Collaborative Semantic Filtering technologies for building Semantic MOOCs’ management system, then, we present a prototype of a semantic middle-sized platform implemented at Western Kentucky University that answers these aforementioned requirements.     

基于桥连接的词典学习方法的语义解析

现阶段的语义解析方法大部分都基于组合语义,这类方法的核心就是词典。词典是词汇的集合,词汇定义了自然语言句子中词语到知识库本体中谓词的映射。语义解析一直面临着词典中词汇覆盖度不够的问题。针对此问题,该文在现有工作的基础上,提出了基于桥连接的词典学习方法,该方法能够在训练中自动引入新的词汇并加以学习,为了进一步提高新学习到的词汇的准确度,该文设计了新的词语—二元谓词的特征模板,并使用基于投票机制的核心词典获取方法。该文在两个公开数据集(WebQuestions和Free917)上进行了对比实验,实验结果表明,该文方法能够学习到新的词汇,提高词汇的覆盖度,进而提升语义解析系统的性能,特别是召回率。     

Mímir: An open-source semantic search framework for interactive information seeking and discovery

Semantic search is gradually establishing itself as the next generation search paradigm, which meets better a wider range of information needs, as compared to traditional full-text search. At the same time, however, expanding search towards document structure and external, formal knowledge sources (e.g. LOD resources) remains challenging, especially with respect to efficiency, usability, and scalability.This paper introduces Mímir—an open-source framework for integrated semantic search over text, document structure, linguistic annotations, and formal semantic knowledge. Mímir supports complex structural queries, as well as basic keyword search.Exploratory search and sense-making are supported through information visualisation interfaces, such as co-occurrence matrices and term clouds. There is also an interactive retrieval interface, where users can save, refine, and analyse the results of a semantic search over time. The more well-studied precision-oriented information seeking searches are also well supported.The generic and extensible nature of the Mímir platform is demonstrated through three different, real-world applications, one of which required indexing and search over tens of millions of documents and fifty to hundred times as many semantic annotations. Scaling up to over 150 million documents was also accomplished, via index federation and cloud-based deployment.     

Stress-strain relations in elastoplastic solids with Dugdale-type cracks

Mechanical behavior of a two-dimensional elastoplastic solid with rectilinear cracks is investigated. Plastic strip model is used to reduce plasticity problem to the equivalent linear elasticity formulation. Two realizations of the mixed mode plastic strip model are considered: in-line plastic strips as proposed by Becker and Gross [Int. J. Fract. 37 (1988) 163], and inclined plastic strips of Panasyuk and Savruk [Appl. Mech. Rev. 47 (1994) 151]. The effective mechanical response predictions are based on the procedure presented in Kachanov et al., [Appl. Mech. Rev. 47 (1994) 151]. Stress-strain relations are obtained for parallel and randomly oriented non-interacting cracks. Results are compared with known elastic solutions.     

可拓知识空间和可拓知识网格模型(Ⅱ):可拓知识网格

第1部分中已介绍了可拓知识空间定义和相关操作，以及可拓知识空间关联函数计算方法。这一部分进一步建立可拓知识空间语义网、可拓知识网格和可拓知识网格服务，并给出实例和相关的分析讨论。     

Qualitative representation of spatial knowledge in two-dimensional space

Various relation-based systems, concerned with the qualitative representation and processing of spatial knowledge, have been developed in numerous application domains. In this article, we identify the common concepts underlying qualitative spatial knowledge representation, we compare the representational properties of the different systems, and we outline the computational tasks involved in relation-based spatial information processing. We also describesymbolic spatial indexes, relation-based structures that combine several ideas in spatial knowledge representation. A symbolic spatial index is an array that preserves only a set of spatial relations among distinct objects in an image, called the modeling space; the index array discards information, such as shape and size of objects, and irrelevant spatial relations. The construction of a symbolic spatial index from an input image can be thought of as a transformation that keeps only a set of representative points needed to define the relations of the modeling space. By keeping the relative arrangements of the representative points in symbolic spatial indexes and discarding all other points, we maintain enough information to answer queries regarding the spatial relations of the modeling space without the need to access the initial image or an object database. Symbolic spatial indexes can be used to solve problems involving route planning, composition of spatial relations, and update operations.     

Network topology and the theory of rubber elasticity

The earliest investigations on rubber elasticity, commencing in the 19th century, were necessarily limited to phenomenological interpretations. The realisation that polymers consist of very long molecular chains. commencing c. 1930, gave impetus to the molecular theory of rubber elasticity (1932-). according to which the high deformability of an elastomer, and the elastic force generated by deformation, stem from the configurations accessible to long molecular chains. Theories of rubber elasticity put forward from 1934-1946 relied on the assumption that the junctions of the rubber network undergo displacements that are affine in macroscopic strain. The theory of James and Guth (1947) dispensed with this premise, and demonstrated instead that the mean positions of the junctions of a ‘phantom’ network consisting of Gaussian chains devoid of material properties are affine in the strain. The vital significance of the distinction between the actual distribution of chain vectors in a network and their distribution if the junctions would be fixed at their mean positions went unnoticed for nearly 30 years. Experimental investigations, commencing with the incisive work of Gee in 1946. revealed large departures from the relationship of stress to strain predicted by the theories cited. This discrepancy prompted extensive studies, theoretical and experimental, during succeeding years. Inquiry into the fundamentals of polymer networks, formed for example by interlinking very long polymer molecules, exposed the need to take account of network imperfections, typically consisting of chains attached at only one end to a network junction. Various means were advocated to make corrections for these imperfections. The cycle rank ζ of the network has been shown (1976) to be the fundamental measure of its connectivity, regardless of the junction functionality and pattern of imperfections. Often overlooked is the copious interpenetration of the chains comprising typical elastomeric networks. Theories that attempt to represent such networks on a lattice are incompatible with this universal feature. Moreover, the dense interpenetration of chains may limit the ability of junctions in real networks to accommodate the fluctuations envisaged in the theory of phantom networks. It was suggested in 1975 that departures from the form predicted for the elastic equation of state are due to constraints on the fluctuations of junctions whose effect diminishes with deformation and with dilation. Formulation of a self-consistent theory based on this suggestion required recognition of the non-affine connection between the chain vector distribution function and the macroscopic strain in a real network, which may partake of characteristics of a phantom network in some degree. Implementation of the idea was achieved through postulation of domains of constraint affecting the equilibrium distribution of fluctuations of network junctions from their mean positions. This led in due course to a theory that accounts for the relationship of stress to strain virtually throughout the ranges of strain accessible to measurement. The theory establishes connections between structure and elastic properties. This is achieved with utmost frugality in arbitrary parameters.     

What does the object decision task measure? Reflections on the basis of evidence from semantic dementia.

The authors investigated the impact of semantic knowledge on visual object analysis by assessing the performance of patients with semantic dementia on a different-views object matching test and on 2 object decision tests differing, for example, in whether the nonreal items were nonsense objects or chimeras of 2 real objects. On average, the patients scored normally on both the object matching and the object decision test including nonsense objects but were impaired on the object decision test including chimeras; this latter was also the only visual object test that correlated significantly with degree of semantic impairment. These findings demonstrate that object decision is not a single task or ability and that it is not necessarily independent of conceptual knowledge. (PsycINFO Database Record (c) 2010 APA, all rights reserved)