Entity and relation extraction with rule-guided dictionary as domain knowledge

Entity and relation extraction is an indispensable part of domain knowledge graph construction, which can serve relevant knowledge needs in a specific domain, such as providing support for product research, sales, risk control, and domain hotspot analysis. The existing entity and relation extraction methods that depend on pretrained models have shown promising performance on open datasets. However, the performance of these methods degrades when they face domain-specific datasets. Entity extraction models treat characters as basic semantic units while ignoring known character dependency in specific domains. Relation extraction is based on the hypothesis that the relations hidden in sentences are unified, thereby neglecting that relations may be diverse in different entity tuples. To address the problems above, this paper first introduced prior knowledge composed of domain dictionaries to enhance characters’ dependence. Second, domain rules were built to eliminate noise in entity relations and promote potential entity relation extraction. Finally, experiments were designed to verify the effectiveness of our proposed methods. Experimental results on two domains, including laser industry and unmanned ship, showed the superiority of our methods. The F1 value on laser industry entity, unmanned ship entity, laser industry relation, and unmanned ship relation datasets is improved by +1%, +6%, +2%, and +1%, respectively. In addition, the extraction accuracy of entity relation triplet reaches 83% and 76% on laser industry entity pair and unmanned ship entity pair datasets, respectively.     

LitStoryTeller+: an interactive system for multi-level scientific paper visual storytelling with a supportive text mining toolbox

The continuing growth of scientific publications has posed a double-challenge to researchers, to not only grasp the overall research trends in a scientific domain, but also get down to research details embedded in a collection of core papers. Existing work on science mapping provides multiple tools to visualize research trends in domain on macro-level, and work from the digital humanities have proposed text visualization of documents, topics, sentences, and words on micro-level. However, existing micro-level text visualizations are not tailored for scientific paper corpus, and cannot support meso-level scientific reading, which aligns a set of core papers based on their research progress, before drilling down to individual papers. To bridge this gap, the present paper proposes LitStoryTeller+, an interactive system under a unified framework that can support both meso-level and micro-level scientific paper visual storytelling. More specifically, we use entities (concepts and terminologies) as basic visual elements, and visualize entity storylines across papers and within a paper borrowing metaphors from screen play. To identify entities and entity communities, named entity recognition and community detection are performed. We also employ a variety of text mining methods such as extractive text summarization and comparative sentence classification to provide rich textual information supplementary to our visualizations. We also propose a top-down story-reading strategy that best takes advantage of our system. Two comprehensive hypothetical walkthroughs to explore documents from the computer science domain and history domain with our system demonstrate the effectiveness of our story-reading strategy and the usefulness of LitStoryTeller+.

     

Critical Relation Path Aggregation-Based Industrial Control Component Exploitable Vulnerability Reasoning

With the growing discovery of exposed vulnerabilities in the Industrial Control Components (ICCs), identification of the exploitable ones is urgent for Industrial Control System (ICS) administrators to proactively forecast potential threats. However, it is not a trivial task due to the complexity of the multi-source heterogeneous data and the lack of automatic analysis methods. To address these challenges, we propose an exploitability reasoning method based on the ICC-Vulnerability Knowledge Graph (KG) in which relation paths contain abundant potential evidence to support the reasoning. The reasoning task in this work refers to determining whether a specific relation is valid between an attacker entity and a possible exploitable vulnerability entity with the help of a collective of the critical paths. The proposed method consists of three primary building blocks: KG construction, relation path representation, and query relation reasoning. A security-oriented ontology combines exploit modeling, which provides a guideline for the integration of the scattered knowledge while constructing the KG. We emphasize the role of the aggregation of the attention mechanism in representation learning and ultimate reasoning. In order to acquire a high-quality representation, the entity and relation embeddings take advantage of their local structure and related semantics. Some critical paths are assigned corresponding attentive weights and then they are aggregated for the determination of the query relation validity. In particular, similarity calculation is introduced into a critical path selection algorithm, which improves search and reasoning performance. Meanwhile, the proposed algorithm avoids redundant paths between the given pairs of entities. Experimental results show that the proposed method outperforms the state-of-the-art ones in the aspects of embedding quality and query relation reasoning accuracy.     

基于注意力机制的包装命名实体识别

目的 为了解决包装行业相关文本命名实体识别困难问题,提出在BiLSTM（Bidirectional Long Short-Term Memory）神经网络中加入注意力机制（Attention）和字词联合特征,构建一种基于注意力机制的BiLSTM深度学习模型（简称Attention-BiLSTM）,以识别包装命名实体。方法 首先构建包装领域词典匹配包装语料中词语的类别特征,同时将包装语料转换为字特征和词特征联合的向量特征,并且在过程中加入POS（词性）信息。然后将以上特征联合馈送到BiLSTM网络,以获取文本的全局特征,并利用注意力机制获取局部特征。最后根据文本的全局特征和局部特征使用CRF（Conditional Random Field）解码整个句子的最优标注序列。结果 通过对《中国包装网》新闻数据集的实验,获得了85.6%的F值。结论 所提方法在包装命名实体识别中优于传统方法。     

A conceptual framework for the generation of simulation models from process plans and resource configuration

Although simulation is a popular tool for modelling and analysing modern manufacturing systems, to model shop floor control systems (SFCSs) in simulation requires quite costly efforts, since they are responsible for resolving various decision problems, such as deadlock, part dispatching, and resource conflict. The objective of the paper is to address a conceptual framework necessary to generate a WITNESS simulation model automatically from graph-based process plans and resource configurations. A graph-based process plan is used to capture part operations, their related resource requirements, and their temporal precedence relationships. A WITNESS simulation model is a graphical representation of shop floor resources with the part flow logic embedded within each resource element. To generate a WITNESS model, a process plan is automatically converted into a machine-centred part routeing graph (MCPRG) and then a transport-tending part routeing graph (TTPRG). The MCPRG implies part flows among machines, in which a node represents a machine and an edge represents a part route. The TTPRG implies part flows among machines and material handling devices, in which a node represents either machine or material handler, and an edge represents a part route. From the TTPRG, the part's input and output rules for each resource can be automatically extracted and plugged into the WITNESS model. The approach proposed in the paper enables manufacturers to generate a simulation model rapidly and effectively for performance measurement, such as bottleneck identification, work in progress, throughput times, dynamic resource utilization, and deadlock, of the SFCSs.     

基于t-SNE和LSTM的旋转机械剩余寿命预测

针对旋转机械的剩余使用寿命预测问题,提出了一种基于t分布随机近邻嵌入(t-SNE)和长短期记忆网络(LSTM)的预测方法。将t-SNE降维方法引入旋转机械振动信号特征提取,实例验证表明无论针对时频域特征或小波包分解得到的能量特征,经t-SNE降维后特征区分度更加明显,利用降维后的特征进行故障模式识别,正确率接近100%;提出利用样本间散度作为旋转机械退化指标,实验表明样本间散度对旋转机械性能退化趋势的表现相比其他指标更加明显;以不同的训练样本量,利用LSTM方法进行剩余使用寿命预测,为了验证LSTM方法的有效性,将其与BP神经网络、灰色预测模型、支持向量机等方法进行比较,结果表明LSTM方法能够预测旋转机械退化趋势,显著提高剩余使用寿命的预测精度,对旋转机械的健康监测和寿命预测具有一定的理论指导意义。     

采用ObjectARX 2006的多段线自动生成及编辑

将AutoCAD中的图形粘贴到Office系列软件中会导致图线宽度丢失和线宽不易调整等问题,将图线转化为多段线是解决这一问题的常用方法.论文分析了使用AutoCAD内部命令实现图线转化成多段线过程中存在的问题,给出了一种将工程图形自动转化为多段线的方法.该方法将工程图形中的图线分成开环和闭环两种,并自动识别图线类型,智能调整图线宽度,避免了手工调整过程中存在的问题,提高了效率.     

Robust medical image registration based on phase congruency and regional mutual information

Abstract

In this paper, a new approach of multi-modality image registration is represented with not only image intensity, but also features describing image structure. There are two novelties in the proposed method. First, instead of standard mutual information based on joint intensity histogram, a graph-based implementation of multi-dimensional regional mutual information is employed, which allows neighbourhood information to be taken into account. Second, a new feature image is obtained by means of phase congruency, which is invariant to brightness or contrast changes. By incorporating these features and intensity into regional mutual information, we can combine aspects of both structural and neighbourhood information together, which offers a more robust and a high level of registration accuracy that is essential in application to the medical domain.     

深度双重注意力的生成与判别联合学习的行人重识别

在行人重识别任务中存在数据集标注难度大,样本量少,特征提取后细节特征缺失等问题。针对以上问题提出深度双重注意力的生成与判别联合学习的行人重识别。首先,构建联合学习框架,将判别模块嵌入生成模块,实现图像生成和判别端到端的训练,及时将生成图像反馈给判别模块,同时优化生成模块与判别模块。其次,通过相邻的通道注意力模块间连接和相邻空间注意力模块间连接,融合所有通道特征和空间特征,构建深度双重注意力模块,将其嵌入教师模型,使模型能更好地提取行人细节身份特征,提高模型识别能力。实验结果表明,该算法在Market-1501和DukeMTMC-ReID数据集上具有较好的鲁棒性、判别性。     

A framework for identification of high-value customers by including social network based variables for churn prediction using neuro-fuzzy techniques

Customer churn has become a significant problem and is one of the prime challenges that many in the services industry are facing. While all kinds of churn lead to incur loss, the loss of low-value customers will be naturally less damaging than the loss of loyal and high-value ones. So companies need to build a churn prediction model for their high-value customers. In this paper, a two-phase framework for prediction of high-value customer churn has been proposed. Phase 1 is the identification phase which takes into account social-network based variables of customers in identifying the high-value ones. The data of an identified high-value customer is used as the input for Phase 2 to prepare the churn prediction model. Data of a major telecommunication company has been used to implement the framework. The customers were clustered by using K-means algorithm. After ranking clusters, the top-cluster was selected according to clusters ratings. The data belonging to the top cluster is used in churn prediction model building phase. In this phase, two neuro-fuzzy techniques, namely the adaptive neuro-fuzzy inference system (ANFIS) and the locally linear neuro-fuzzy (LLNF) have been applied together with locally linear model tree (LoLiMoT) learning algorithm on churn data. A new algorithm has been devised for comparing these methods with the most widely used neural networks such as multi layer perceptron (MLP) and radial basis function (RBF) networks. Results of comparison indicate that the neuro-fuzzy techniques perform better than neural network models and they are a good candidate for churn prediction purposes.     

Road network safety evaluation using Bayesian hierarchical joint model

Safety and efficiency are commonly regarded as two significant performance indicators of transportation systems. In practice, road network planning has focused on road capacity and transport efficiency whereas the safety level of a road network has received little attention in the planning stage. This study develops a Bayesian hierarchical joint model for road network safety evaluation to help planners take traffic safety into account when planning a road network. The proposed model establishes relationships between road network risk and micro-level variables related to road entities and traffic volume, as well as socioeconomic, trip generation and network density variables at macro level which are generally used for long term transportation plans. In addition, network spatial correlation between intersections and their connected road segments is also considered in the model.A road network is elaborately selected in order to compare the proposed hierarchical joint model with a previous joint model and a negative binomial model. According to the results of the model comparison, the hierarchical joint model outperforms the joint model and negative binomial model in terms of the goodness-of-fit and predictive performance, which indicates the reasonableness of considering the hierarchical data structure in crash prediction and analysis. Moreover, both random effects at the TAZ level and the spatial correlation between intersections and their adjacent segments are found to be significant, supporting the employment of the hierarchical joint model as an alternative in road-network-level safety modeling as well.     

Fatigue of metals – What the designer needs?

Engineering designers have to tackle various fatigue problems in their routine work. Some problems are simple and other are complex. Most of the designers have been taught only a small part of the suitable fatigue knowledge needed to successfully deal with many of these problems except for the most trivial ones. The main reason is the vast amount and complexity of the fatigue discipline, and lack of a clear integrated approach to the main fatigue problems that may be conveniently utilized by designers. An integrated approach to fatigue, that has been introduced by one of the authors in the past, is here extended, simplified and proposed as a comprehensive fatigue design tool for engineers. The whole fatigue domain is divided into six zones that include different fatigue regimes. The propagating crack length is considered as the sole parameter to evaluate safe fatigue life, including the use of an “equivalent crack propagation rate”, which averages the intense variations of CPR in the vicinity of grain boundaries. Contrary to the many unified relations to evaluate fatigue crack propagation that were proposed in the past, the current study is based on separation. For each fatigue zone a unique prediction relation is presented. Flow chart of comprehensive software for calculation of crack propagation in the whole fatigue domain is explained, and simulation results show good fit to published test results. The method is claimed to fit for use mainly by design engineers, but possibly by fatigue experts as well.     

基于混沌理论的海底混响中目标回波提取

提出了基于混沌理论的混响中目标回波提取新方法。该方法主要得益于一种新的预测模型,该模型基于径向基函数神经网络,综合利用了时间序列的前向和后向预测,解释了该模型用于混沌信号分离的基本原理,用几种混沌时间序列分析了该模型用于混沌信号建模和谐波信号提取的性能。该方法用于湖试混响中目标回波提取的结果表明:该模型可以用于提取信混比不小于1dB的目标回波。     

Algebraic geometry and group theory in geometric constraint satisfaction for computer-aided design and assembly planning

Mechanical design and assembly planning inherently involve geometric constraint satisfaction or scene feasibility (GCS/SF) problems. Such problems imply the satisfaction of proposed relations placed between undefined geometric entities in a given scenario. If the degrees of freedom remaining in the scene are compatible with the proposed relations or constraints, a set of entities is produced that populate the scenario satisfying the relations. Otherwise, a diagnostic of inconsistency of the problem is emitted. This problem appears in various forms in assembly planning (assembly model generation), process planning, constraint driven design, computer vision, etc. Previous attempts at solution using separate numerical, symbolic or procedural approaches suffer serious shortcomings in characterizing the solution space, in dealing simultaneously with geometric (dimensional) and topological (relational) inconsistencies, and in completely covering the possible physical variations of the problem. This investigation starts by formulating the problem as one of characterizing the solution space of a set of polynomials. By using theories developed in the area of algebraic geometry, properties of Grobner Bases are used to assess the consistency and ambiguity of the given problem and the dimension of its solution space. This method allows for die integration of geometric and topological reasoning. The high computational cost of Grobner Basis construction and the need for a compact and physically meaningful set of variables lead to the integration of known results on group theory. These results allow the characterization of geometric constraints in terms of the subgroups of the Special Group of Euclidean displacements in E³, SE(3). Several examples arc developed which were solved with computer algebra systems (MAPLE and Mathematica). They are presented to illustrate the use of the Euclidean group-based variables, and to demonstrate the theoretical completeness of the algebraic geometry analysis over the domain of constraints expressible as polynomials.     

Robust recurrent neural network modeling for software fault detection and correction prediction

Software fault detection and correction processes are related although different, and they should be studied together. A practical approach is to apply software reliability growth models to model fault detection, and fault correction process is assumed to be a delayed process. On the other hand, the artificial neural networks model, as a data-driven approach, tries to model these two processes together with no assumptions. Specifically, feedforward backpropagation networks have shown their advantages over analytical models in fault number predictions. In this paper, the following approach is explored. First, recurrent neural networks are applied to model these two processes together. Within this framework, a systematic networks configuration approach is developed with genetic algorithm according to the prediction performance. In order to provide robust predictions, an extra factor characterizing the dispersion of prediction repetitions is incorporated into the performance function. Comparisons with feedforward neural networks and analytical models are developed with respect to a real data set.     

装配尺寸链自动生成的研究

基于装配的计算机辅助公差设计主要包括公差表达、公差链的生成、公差分析和公差综合四个部分。公差链的生成是其余三部分的基础。本文在实体关系模型的基础上研究了装配尺寸链的自动生成算法, 在一维尺寸链生成算法中提出基于搜索方向的配合关系图生成的新算法。该算法中加入了配合关系方向性的取舍, 降低了配合图生成的复杂度, 同时该算法可以判断关系设计的冗余性。     

深度卷积神经网络在滑动轴承转子轴心轨迹识别中的应用

针对传统旋转机械智能识别方法需要人为提取特征及诊断精度低的问题,基于深度学习的强大学习能力,提出一种深度卷积神经网络故障诊断模型(Deep Convolutional Neural Network Fault Diagnosis Model,DCNN-FDM)用于轴心轨迹识别.该模型包括输入模块、特征提取模块及分类模块...     

Deep learning based pipeline with multichannel inputs for patent classification

This work introduces a deep learning pipeline for automatic patent classification with multichannel inputs based on LSTM and word vector embeddings. Sophisticated text mining methods are used to extract the most important segments from patent texts, and a domain-specific pre-trained word embeddings model for the patent domain is developed; it was trained on a very large dataset of more than five million patents. The deep learning pipeline is using multiple parallel LSTM networks that read the source patent document using different input dimensions namely embeddings of different segments of patent texts, and sparse linear input of different metadata. Classifying patents into corresponding technical fields is selected as a use case. In this use case, a series of patent classification experiments are conducted on different patent datasets, and the experimental results indicate that using the segments of patent texts as well as the metadata as multichannel inputs for a deep neural network model, achieves better performance than one input channel.