基于混合神经网络的实体和事件联合抽取方法

实体和事件抽取旨在从文本中识别出实体和事件信息并以结构化形式予以呈现。现有工作通常将实体抽取和事件抽取作为两个单独任务,忽略了这两个任务之间的紧密关系。实际上,事件和实体密切相关,实体往往在事件中充当参与者。该文提出了一种混合神经网络模型,同时对实体和事件进行抽取,挖掘两者之间的依赖关系。模型采用双向LSTM识别实体,并将在双向LSTM中获得的实体上下文信息进一步传递到结合了自注意力和门控卷积的神经网络来抽取事件。在英文ACE 2005语料库上的实验结果证明了该文方法优于目前最好的基准系统。     

面向多语料库的通用事件指代消解

事件同指消解对篇章理解、信息抽取意义重大。该文在事件抽取完成的基础上聚焦事件同指,给出了一个基于卷积神经网络的事件同指消解完整框架,针对实例分布不均衡问题给出了基于事件语义类别和时态信息的事件兼容性过滤策略。为了最大化适用不同的事件标注策略,提出了最小事件本身描述和事件间关系描述相结合的特征表示方法。针对基于事件对模型进行同指消解产生的局部最优问题,给出了一种全局优化的后处理方案。在KBP2015和ACE2005语料上的各类实验表明,上述三个解决方案均能有效解决问题,提升整个事件同指消解平台的性能。     

A hybrid approach to constrained global optimization

In this paper, we propose a novel hybrid global optimization method to solve constrained optimization problems. An exact penalty function is first applied to approximate the original constrained optimization problem by a sequence of optimization problems with bound constraints. To solve each of these box constrained optimization problems, two hybrid methods are introduced, where two different strategies are used to combine limited memory BFGS (L-BFGS) with Greedy Diffusion Search (GDS). The convergence issue of the two hybrid methods is addressed. To evaluate the effectiveness of the proposed algorithm, 18 box constrained and 4 general constrained problems from the literature are tested. Numerical results obtained show that our proposed hybrid algorithm is more effective in obtaining more accurate solutions than those compared to.     

A two-stage framework for road extraction from high-resolution satellite images by using prominent features of impervious surfaces

The segmentation and classification of high-resolution satellite images (HRSI) are useful approaches to extract information. In recent times, roads and buildings have been classified for analysis of urban areas in a better manner. Apart from these, healthy trees are also an important factor in HRSI, i.e. adjacent to roads, and vegetation. They reflect the area in an image as land cover. Other important information, shadow, is extracted from satellite images, which indicates the presence of trees and built-up areas such as buildings, flyovers, etc. In this article, a weighted membership-function-based fuzzy c-means with spatial constraints (WMFCSC) approach for automated satellite image classification is proposed. Initially, spatially fuzzy clustering is used to classify the satellite images in healthy trees with vegetation, roads, and shadows, which includes the information of spatial constraints. The road results of the classified image are still having non-road segments. Therefore, the proposed four intermediate stages (IS) are used to extract the road information, followed by the results of road areas of the WMFCSC approach. The framework of IS helps to remove the false road segments which are adjacent to roads and renovates the segmented roads due to the shadow effect. A final step of a hybrid WMFCSC-IS approach is used to extract the road network. The results of classified images confirm the effectiveness of the WMFCSC-IS approach for satellite image classification.     

基于多尺度变形卷积的特征金字塔光流计算方法

针对现有深度学习光流计算方法的运动边缘模糊问题,提出了一种基于多尺度变形卷积的特征金字塔光流计算方法.首先,构造基于多尺度变形卷积的特征提取模型,显著提高图像边缘区域特征提取的准确性;然后,将多尺度变形卷积特征提取模型与特征金字塔光流计算网络耦合,提出一种基于多尺度变形卷积的特征金字塔光流计算模型;最后,设计一种结合图像与运动边缘约束的混合损失函数,通过指导模型学习更加精准的边缘信息,克服了光流计算运动边缘模糊问题.分别采用MPI-Sintel和KITTI2015测试图像集对该方法与代表性的深度学习光流计算方法进行综合对比分析.实验结果表明,该方法具有更高的光流计算精度,有效解决了光流计算的边缘模糊问题.     

Exploration on efficient similar sentences extraction

Measuring the semantic similarity between sentences is an essential issue for many applications, such as text summarization, Web page retrieval, question-answer model, image extraction, and so forth. A few studies have explored on this issue by several techniques, e.g., knowledge-based strategies, corpus-based strategies, hybrid strategies, etc. Most of these studies focus on how to improve the effectiveness of the problem. In this paper, we address the efficiency issue, i.e., for a given sentence collection, how to efficiently discover the top-k semantic similar sentences to a query. The previous methods cannot handle the big data efficiently, i.e., applying such strategies directly is time consuming because every candidate sentence needs to be tested. In this paper, we propose efficient strategies to tackle such problem based on a general framework. The basic idea is that for each similarity, we build a corresponding index in the preprocessing. Traversing these indices in the querying process can avoid to test many candidates, so as to improve the efficiency. Moreover, an optimal aggregation algorithm is introduced to assemble these similarities. Our framework is general enough that many similarity metrics can be incorporated, as will be discussed in the paper. We conduct extensive experimental evaluation on three real datasets to evaluate the efficiency of our proposal. In addition, we illustrate the trade-off between the effectiveness and efficiency. The experimental results demonstrate that the performance of our proposal outperforms the state-of-the-art techniques on efficiency while keeping the same high precision as them.     

An approach to multimodal biomedical image registration utilizing particle swarm optimization

Biomedical image registration, or geometric alignment of two-dimensional and/or three-dimensional (3D) image data, is becoming increasingly important in diagnosis, treatment planning, functional studies, computer-guided therapies, and in biomedical research. Registration based on intensity values usually requires optimization of some similarity metric between the images. Local optimization techniques frequently fail because functions of these metrics with respect to transformation parameters are generally nonconvex and irregular and, therefore, global methods are often required. In this paper, a new evolutionary approach, particle swarm optimization, is adapted for single-slice 3D-to-3D biomedical image registration. A new hybrid particle swarm technique is proposed that incorporates initial user guidance. Multimodal registrations with initial orientations far from the ground truth were performed on three volumes from different modalities. Results of optimizing the normalized mutual information similarity metric were compared with various evolutionary strategies. The hybrid particle swarm technique produced more accurate registrations than the evolutionary strategies in many cases, with comparable convergence. These results demonstrate that particle swarm approaches, along with evolutionary techniques and local methods, are useful in image registration, and emphasize the need for hybrid approaches for difficult registration problems.     

流体的旋涡特征提取方法综述

近年来,流体可视化已成为计算机图形学领域的一个研究热点,其最重要的目的 之一是旋涡特征的提取与可视化。由于目前仍未有一个通用的定义描述旋涡,导致文献对旋涡 是否存在的判断依据各不相同。为了对流体的旋涡特征提取方法进行较为系统的综述,首先对 旋涡提取研究方向的相关概念进行解释,回顾流体旋涡特征提取方法的发展情况再进行总结, 将常用的旋涡提取方法分为基于点、线、几何和基于机器学习的方法。对于新近提出的参考系 不变性,将旋涡提取方法分为伽利略不变性、旋转不变性和拉格朗日不变性。为了比较不同方 法的优势和缺陷,在综述每一类方法时分别给出若干经典方法,为研究者提供了一个清晰的研 究思路。最后总结每类方法存在的难点和问题,并指出今后的研究重点。     

基于混合模型的事件触发词抽取

事件结构性语法特征与事件语义特征各有优势,二者融合利于准确表征事件触发词,进而有利于完成事件触发词抽取任务。现有的基于特征、基于结构及基于神经网络模型等的抽取方法仅能捕捉事件的部分特征,不能够准确表征事件触发词。为解决上述问题,提出一种融合了事件结构性语法特征和事件语义特征的混合模型,完成事件触发词抽取任务。首先,在初始化向量模型中融入句子的依存句法信息,使初始向量中包含事件结构性语法特征;然后,将初始向量依次传入神经网络模型中的CNN和BiGRU-E-attention模型中,在捕获多维度事件语义特征的同时,完成事件结构性语法特征与事件语义特征的融合;最后,进行事件触发词的抽取。在CEC中文突发语料库上进行事件触发词位置识别和分类实验,该模型的F值较基准模型的分别提高了0.86%和4.07%;在ACE2005英文语料库上,该模型的F值较基准模型的分别提高了1.4%和1.5%。实验结果表明,混合模型在事件触发词抽取任务中取得了优异的效果。     

RTL验证中的混合可满足性求解

RTL混合可满足性求解方法分为基于可满足性模理论(SMT)和基于电路结构搜索两大类.前者主要使用逻辑推理的方法,目前已在处理器验证中得到了广泛的应用,主要得益于SMT支持用于描述验证条件的基础理论;后者能够充分地利用电路中的约束信息,因而求解效率较高.介绍了每一大类中的典型研究及其所采用的重要策略,以及RTL可满足性求解方面的研究进展.     

基于混合N-Gram模型和XGBoost算法的内部威胁检测方法

随着政府企事业单位网络安全机制的建立健全,单纯从外部进入目标系统的攻击门槛越来越高,导致内部威胁逐渐增多。内部威胁区别于外部威胁,攻击者主要来自于内部用户,使得攻击更具隐蔽性,更难被检测。本文提出一种基于混合N-Gram模型和XGBoost算法的内部威胁检测方法。采用词袋、N-Gram、词汇表3种特征提取方法进行实验比对及参数N值筛选,基于混合N-Gram模型和XGBoost算法的内部威胁检测方法检测效果比通过1维数据、2维数据、4维数据的不同特征进行组合的特征子集效果更优,特定度达到0.23,灵敏度达到27.65,准确度达到0.94,F1值达到0.97。对比特定度、灵敏度、准确度、F1值4项评价指标,基于混合N-gram特征提取方法比传统的词袋、词汇表特征提取方法在检测中更有效。此检测方法不仅提高了内部威胁检测特征码的区分度,同时提高了特征提取的准确性和计算性能。     

迁移学习在医学图像分类中的研究进展

医学影像作为医疗数据的主要载体,在疾病预防、诊断和治疗中发挥着重要作用。医学图像分类是医学影像分析的重要组成部分。如何提高医学图像分类效率是一个持续的研究问题。随着计算机技术进步,医学图像分类方法已经从传统方法转到深度学习,再到目前热门的迁移学习。虽然迁移学习在医学图像分类中得到较广泛应用,但存在不少问题,本文对该领域的迁移学习应用情况进行综述,从中总结经验和发现问题,为未来研究提供线索。1)对基于迁移学习的医学图像分类研究的重要文献进行梳理、分析和总结,概括出3种迁移学习策略,即迁移模型的结构调整策略、参数调整策略和从迁移模型中提取特征的策略;2)从各文献研究设计的迁移学习过程中提炼共性,总结为5种迁移学习模式,即深度卷积神经网络(deep convolution neural network, DCNN)模式、混合模式、特征组合分类模式、多分类器融合模式和二次迁移模式。阐述了迁移学习策略和迁移学习模式之间的关系。这些迁移学习策略和模式有助于从更高的抽象层次展现迁移学习应用于医学图像分类领域的情况;3)阐述这些迁移学习策略和模式在医学图像分类中的具体应用,分析这些策略及模式的优点、局...     

彩色图像灰度化算法综述*

彩色图像灰度化是图像处理和计算机视觉领域的基本课题和重要前提。针对2005年之后的多种主流灰度化方法进行研究,根据是否对所有像素使用相同映射函数将其分为全局映射法,局部映射法及混合法,介绍每类方法所包含的典型算法的基本思想、实现步骤及优缺点。最后用定性和定量两种评价方法对各种主要算法的实验结果和性能进行对比分析,进一步提出存在的问题及下一步研究方向,为今后的彩色图像灰度化研究提供参考和借鉴。     

供应链中控制多级存储的射频辨识Push/Pull混合策略设计与仿真

由于射频辨识(radio frequency identification,RFID)激励的电子看板系统能够从远端看见供应链节点企业库存的状况,使得广域分布的供应链多级存储能够实现RFID激励的Pull控制.本文根据供应链分销网络多级存储的结构特点,以及系统运作期间各阶段节点企业的功能,在不同阶段采用不同的控制策略.因此,设计了多种不同的RFID激励的Push/Pull混合控制策略.为了比较和验证各混合策略对多级存储的控制性能,建立了以总库存成本、总缺货损失、总运行成本和库存周转率作为评价策略性能的指标体系.由于供应链系统的动态性与随机性,难以进行数学建模和精确求解,因此基于离散事件系统仿真原理,设计并实现了仿真模型.通过对各策略下多种结构的供应链分销网络多级存储的仿真,验证并分析了制造商阶段采用Push控制,分销商和零售商阶段采用Pull控制的策略的有效性和最优性.     

Hybrid rolling-horizon optimization for berth allocation and quay crane assignment with unscheduled vessels

Port operations usually suffer from uncertainties, such as vessels’ arrival time and handling time and unscheduled vessels. To address this, this study presents a dynamic berth allocation and crane assignment specific problem (BACASP) when unscheduled vessels arrive at the port, which is branded the berth allocation and quay crane assignment specific problem with unscheduled vessels (UBACASP). A rolling-horizon based method is proposed to decompose the UBACASP into a multi-stage static decision BACASP, wherein a rescheduling margin-based hybrid rolling-horizon optimization method is developed by incorporating the event-driven and periodical rolling-horizon strategies as the urgency of dynamic events is evaluated. In each rolling horizon, a mixed integer linear programming model (MILP) is presented for the BACASP to minimize the total port stay time of vessels and the penalties of delays associated with the spatial and temporal constraints, such as the length of continuous berth, number of quay cranes (QCs) and non-crossing of QCs. A discretization strategy is designed to divide the continuous berth into discrete segments, and convert the BACASP to a discrete combinatorial optimization problem, which is efficiently solved by the proposed adaptive large neighborhood search algorithm (ALNS). Case studies with different problem characteristics are conducted to prove the effectiveness of the solution methods proposed in this study. Moreover, the performances of the ALNS and the existing methods for solving the BACASP are compared, and the advantages and disadvantages of different rolling strategies under different degrees of uncertainties are deeply analyzed.     

A gene-level hybrid search framework for multiobjective evolutionary optimization

This paper proposes a general framework of gene-level hybrid search (GLHS) for multiobjective evolutionary optimization. Regarding the existing hybrid search methods, most of them usually combine different search strategies and only select one search strategy to generate child solution. This kind of hybrid search is called as a chromosome-level approach in this paper. However, in GLHS, every gene bit of the child solution can be produced using different search strategies and such operation provides the enhanced exploration capability. As an example, two different DE mutation strategies are used in this paper as the variance candidate pool to implement the proposed GLHS framework, named GLHS-DE. To validate the effectiveness of GLHS-DE, it is embedded into one state-of-the-art algorithmic framework of MOEA/D, and is compared to a basic DE operator and two competitive hybrid search operators, i.e., FRRMAB and CDE, on 80 test problems with two to fifteen objectives. The experimental results show GLHS-DE obtains a superior performance over DE, FRRMAB and CDE on about 70 out of 80 test problems, indicating the promising application of our approach for multiobjective evolutionary optimization.

     

Age estimation using a hierarchical classifier based on global and local facial features

The research related to age estimation using face images has become increasingly important, due to the fact it has a variety of potentially useful applications. An age estimation system is generally composed of aging feature extraction and feature classification; both of which are important in order to improve the performance. For the aging feature extraction, the hybrid features, which are a combination of global and local features, have received a great deal of attention, because this method can compensate for defects found in individual global and local features. As for feature classification, the hierarchical classifier, which is composed of an age group classification (e.g. the class of less than 20 years old, the class of 20-39 years old, etc.) and a detailed age estimation (e.g. 17, 23 years old, etc.), provide a much better performance than other methods. However, both the hybrid features and hierarchical classifier methods have only been studied independently and no research combining them has yet been conducted in the previous works. Consequently, we propose a new age estimation method using a hierarchical classifier method based on both global and local facial features. Our research is novel in the following three ways, compared to the previous works. Firstly, age estimation accuracy is greatly improved through a combination of the proposed hybrid features and the hierarchical classifier. Secondly, new local feature extraction methods are proposed in order to improve the performance of the hybrid features. The wrinkle feature is extracted using a set of region specific Gabor filters, each of which is designed based on the regional direction of the wrinkles, and the skin feature is extracted using a local binary pattern (LBP), capable of extracting the detailed textures of skin. Thirdly, the improved hierarchical classifier is based on a support vector machine (SVM) and a support vector regression (SVR). To reduce the error propagation of the hierarchical classifier, each age group classifier is designed so that the age range to be estimated is overlapped by consideration of false acceptance error (FAE) and false rejection error (FRE) of each classifier. The experimental results showed that the performance of the proposed method was superior to that of the previous methods when using the BERC, PAL and FG-Net aging databases.     

基于字词混合的中文实体关系联合抽取方法

针对中文关系抽取中分词时引起的边界切分出错而造成的歧义问题,以及出现实体对重叠不能提取出所涉及的多个关系问题,提出一种基于字词混合的联合抽取方法.首先,对于分词边界问题,嵌入层在词向量的基础上结合字向量,并且增加位置信息来保证字与字之间的正确顺序.其次,模型引入混合扩张卷积网络进行不同粒度、更远距离的特征提取.最后,采用分层标注方法,通过得到的主实体信息标记对应的关系和客实体,每个主实体可对应多个关系和客实体.与其他关系抽取方法在相同中文数据集上进行实验对比,实验结果表明,该方法的抽取效果最佳,并且也表现出更好的稳定性.     

A new hybrid feature extraction method in a dyadic scheme for classification of hyperspectral data

The feature extraction is an important preprocessing step of the classification procedure particularly in high-dimensional data with limited number of training samples. Conventional supervised feature extraction methods, for example, linear discriminant analysis (LDA), generalized discriminant analysis, and non-parametric weighted feature extraction ones, need to calculate scatter matrices. In these methods, within-class and between-class scatter matrices are used to formulate the criterion of class separability. Because of the limited number of training samples, the accurate estimation of these matrices is not possible. So the classification accuracy of these methods falls in a small sample size situation. To cope with this problem, a new supervised feature extraction method namely, feature extraction using attraction points (FEUAP) has been recently proposed in which no statistical moments are used. Thus, it works well using limited training samples. To take advantage of this method and LDA one, this article combines them by a dyadic scheme. In the proposed scheme, the similar classes are grouped hierarchically by the k-means algorithm so that a tree with some nodes is constructed. Then the class of each pixel is determined from this scheme. To determine the class of each pixel, depending on the node of the tree, we use FEUAP or LDA for a limited or large number of training samples, respectively. The experimental results demonstrate the better performance of the proposed hybrid method in comparison with other supervised feature extraction methods in a small sample size situation.