Naive Bayesian Classifier Based Semi-supervised Learning for Matching Ontologies

Pervasive environments include sensors, actuators, handheld devices, set of protocols and services. The specialty of this environment is its power to manage with any device at any time anywhere and work autonomously for providing customized services to user. The different entities of pervasive environment collaborate with each other to accomplish an objective by sharing data among them. It raises an interesting problem called semantic heterogeneity. To address this problem, a hybrid ontology matching technique which combines direct and indirect matching techniques is proposed in this paper. To share and integrate data semantically, ontology matching technique establishes a semantic correspondence among various entities of pervasive application ontologies. To find the efficiency of proposed approach, we carried out set of experiments with real world pervasive applications. Experimental results prove that the proposed approach shows excellent performance in hybrid ontology matching. Results also proved that the use of background knowledge has influence over the performance of ontology matching technique.

In positive and unlabeled (PU) learning problems, only positive examples are labeled. Unlabeled data contain both positive and negative examples. Studies show that positive examples of (secondary) diagnoses, and clinical conditions, such as sepsis, are present in unlabeled hospital administrative data, potentially distorting hospital reimbursement systems, and negatively affecting hospitals' revenue and profitability. We investigate whether PU learning is suitable for improving the quality of hospital administrative data. We train three models on 313,434 hospital cases using hospital cost features: two based on the two-step "spy" approach and one using a robust PU learning method. For model evaluation, we rely exclusively on positive examples due to the PU setting. To further assess model performance, we perform an external validity check: We relabel unlabeled sepsis cases, derive new sepsis rates, and compare them to those reported in medical record review studies. All models identify true positives well in unseen data. External validity checks show, however, that only the robust PU learner effectively discriminates between positives and negatives in the unlabeled data, yielding new sepsis rates within the range of sepsis rates reported in medical record review studies. PU learning can improve the quality of hospital administrative data, but its effectiveness depends strongly on the choice of learning approach and classifier. The output of a PU learner can potentially improve hospital reimbursement systems, hospital revenue and profitability management, and sensitivity analyses in healthcare management science, health economics, health services research, and disease surveillance.

As a key representation model of knowledge, ontology has been widely used in a lot of NLP related tasks, such as semantic parsing, information extraction and text mining etc. In this paper, we study the task of ontology matching, which concentrates on finding semantically related entities between different ontologies that describe the same domain, to solve the semantic heterogeneity problem. Previous works exploit different kinds of descriptions of an entity in ontology directly and separately to find the correspondences without considering the higher level correlations between the descriptions. Besides, the structural information of ontology haven’t been utilized adequately for ontology matching. We propose in this paper an ontology matching approach, named ERSOM, which mainly includes an unsupervised representation learning method based on the deep neural networks to learn the general representation of the entities and an iterative similarity propagation method that takes advantage of more abundant structure information of the ontology to discover more mappings. The experimental results on the datasets from Ontology Alignment Evaluation Initiative (OAEI1) show that ERSOM achieves a competitive performance compared to the state-of-the-art ontology matching systems. The OAEI is an international initiative organizing annual campaigns for evaluating ontology matching systems. All of the ontologies provided by OAEI are described in OWL-DL language, and like most of the other participates our ERSOM also manages the OWL ontology in its current version. OAEI: http://oaei.ontologymatching.org/

文本分类是信息检索的关键问题之一.提取更多的可信反例和构造准确高效的分类器是PU(positive andunlabeled)文本分类的两个重要问题.然而,在现有的可信反例提取方法中,很多方法提取的可信反例数量较少,构建的分类器质量有待提高.分别针对这两个重要步骤提供了一种基于聚类的半监督主动分类方法.与传统的反例提取方法不同,利用聚类技术和正例文档应与反例文档共享尽可能少的特征项这一特点,从未标识数据集中尽可能多地移除正例,从而可以获得更多的可信反例.结合SVM 主动学习和改进的Rocchio 构建分类器,并采用改进的TFIDF(term frequency inverse document frequency)进行特征提取,可以显著提高分类的准确度.分别在3 个不同的数据集中测试了分类结果(RCV1,Reuters-21578,20 Newsgoups).实验结果表明,基于聚类寻找可信反例可以在保持较低错误率的情况下获取更多的可信反例,而且主动学习方法的引入也显著提升了分类精度.

Recently semantic web technologies, such as ontologies, have been proposed as key enablers for integrating heterogeneous data schemas in business and governmental systems. Algorithms designed to align different but related ontologies have become necessary as differing ontologies proliferate. The process of ontology alignment seeks to find corresponding entities in a second ontology with the same or the closest meaning for each entity in a single ontology. This research is motivated by the need to provide tools and techniques to support the task of validating ontology alignment statements, since it cannot be guaranteed that the results from automated tools are accurate. The authors present a framework for understanding ontology alignment quality and describe how AlViz, a tool for visual ontology alignment, may be used to improve the quality of alignment results. An experiment was undertaken to test the claim that AlViz supports the task of validating ontology alignments. A promising result found that the tool has potential for identifying missing alignments and for rejecting false alignments.

Ontology matching is an effective technique to solve the ontology heterogeneous problem in Semantic Web. Since different ontology matchers do not necessarily find the same correct correspondences, usually several competing matchers are applied to the same pair of entities in order to increase evidence towards a potential match or mismatch. How to select, combine and tune various ontology matchers to obtain the high quality ontology alignment is one of the main challenges in ontology matching domain. Recently, Evolutionary Algorithms (EA) has become the most suitable methodology to face this challenge, however, the huge memory consumption, slow convergence and premature convergence limit its application and reduce the solution’s quality. To this end, in this paper, we propose a Hybrid Population-based Incremental Learning algorithm (HPBIL) to automatically select, combine and tune different ontology matchers, which can overcome three drawbacks of EA based ontology matching techniques and improve the ontology alignment’s quality. In one hand, HPBIL makes use of a probabilistic representation of the population to perform the optimization process, which can significantly reduce EA’s the memory consumption and the possibility of the premature convergence. In the other, we introduce the local search strategy into PBIL’s evolving process to trade off its exploration and exploitation, and this marriage between global search and local search is helpful to reduce the runtime. In the experiment, we utilize different scale testing cases provided by the Ontology Alignment Evaluation Initiative (OAEI 2016) to test HPBIL’s performance, and the experimental results show that HPBIL’s results significantly outperform other EA based ontology matching techniques and top-performers of the OAEI competitions.

With the explosive growth in generating data in the hydrographical domain, many hydrography ontologies have been developed and maintained to describe hydrographical features and the relationships between them. However, the existing hydrography ontologies are developed with varying project perspectives and objectives, which inevitably results in the differences in terms of knowledge representation. Determining various relationships between two entities in different ontologies offers the opportunity to link hydrographical data for multiple purposes, though the research on this topic is in its infancy. Different from the traditional ontology alignment whose cardinality is 1:1, i.e. one source ontology entity is mapping with one target ontology entity and vice versa, and the relationship is the equivalence, matching hydrography ontologies is a more complex task, whose cardinality could be 1:1, 1:n or m:n and the relationships could be equivalence or subsumption. To efficiently optimize the ontology alignment, in this paper, a discrete optimal model is first constructed for the ontology matching problem, and then a Compact Particle Swarm Optimization algorithm (CPSO) based matching technique is proposed to efficiently solve it. CPSO utilizes the compact real-value encoding and decoding mechanism and the objective-decomposing strategy to approximate the PSO’s evolving process, which can dramatically reduce PSO’s memory consumption and runtime while at the same time ensure the solution’s quality. The experiment exploits the Hydrography dataset in Complex track provided by the Ontology Alignment Evaluation Initiative (OAEI) to test our proposal’s performance. The experimental results show that CPSO-based approach can effectively reduce PSO’s runtime and memory consumption, and determine high-quality hydrography ontology alignments.

Since different ontologies are mostly developed independently, establishing meaningful links between their entities, so-called ontology matching, is critical to ensure their communication. Due to the complexity of the ontology matching problem, Evolutionary Algorithm (EA) can present a good methodology for determining ontology alignments. However, since none of the similarity measure can distinguish all the identical ontology entities in any context, ontology alignments generated by the automatic matching tools should be validated by the users to ensure their qualities. To improve the quality of the ontology alignment, in this work, a similarity measure is first proposed to calculate the similarity value of two ontology entities; then, an optimal model for ontology matching problem is constructed; after that, an EA-based automatic matcher is presented to solve the ontology matching problem, which can also adaptively determine the timing of getting user involved; and finally, the ontology concept hierarchy graph based reasoning approaches are proposed to tradeoff the user's workload and his work's effect. The experiment is conducted on the Interactive track provided by the Ontology Alignment Evaluation Initiative (OAEI), and the comparisons with OAEI's participants show the effectiveness of our proposal.

Interoperability between heterogeneous ontological descriptions can be performed through ontology mediation techniques. At the heart of ontology mediation lies the alignment: a specification of correspondences between ontology entities. Ontology matching can bring some automation but are limited to finding simple correspondences. Design patterns have proven themselves useful to capture experience in design problems. In this article, we introduce ontology alignment patterns as reusable templates of recurring correspondences. Based on a detailed analysis of frequent ontology mismatches, we develop a library of common patterns. Ontology alignment patterns can be used to refine correspondences, either by the alignment designer or via pattern detection algorithms. We distinguish three levels of abstraction for ontology alignment representation, going from executable transformation rules, to concrete correspondences between two ontologies, to ontology alignment patterns at the third level. We express patterns using an ontology alignment representation language, making them ready to use in practical mediation tasks. We extract mismatches from vocabularies associated with data sets published as linked open data, and we evaluate the ability of correspondence patterns to provide proper alignments for these mismatches. Finally, we describe an application of ontology alignment patterns for an ontology transformation service.

Ontology mapping, alignment, and translation has been an active research component of the general research on semantic integration and interoperability. In our talk, we gave our own classification of different topics in this research. We talked about types of heterogeneity between ontologies, various mapping representations, classified methods for discovering methods both between ontology concepts and data, and talked about various tasks where mappings are used. In this extended abstract of our talk, we provide an annotated bibliography for this area of research, giving readers brief pointers on representative papers in each of the topics mentioned above. We did not attempt to compile a comprehensive bibliography and hence the list in this abstract is necessarily incomplete. Rather, we tried to sketch a map of the field, with some specific reference to help interested readers in their exploration of the work to-date.

Ontology matching is an important process for integration of heterogeneous data sources. A large number of different matchers for comparing ontologies exist. They can be classified into element-level and structure-level matchers. The element-level matchers compare entities ignoring their relations with other entities, while the structure-level matchers consider these relations. The TF/IDF (term frequency / inverse document frequency) measure is useful for specifying key terms weights in documents. In our matching system we use the TF/IDF measure for comparing documents that store data about ontology entities. However, the TF/IDF does not take synonyms into account, and it may occur that the terms that describe two entities the best are synonyms. In this paper we propose a matcher that combines the TF/IDF measure with synonym recognition when determining key term weights, in order to improve the results of ontology matching. Evaluation of the matcher is performed on case study examples.

The heterogeneity problem among different sensor ontologies hinders the interaction of information. Ontology matching is an effective method to address this problem by determining the heterogeneous concept pairs. In the matching process, the similarity measure serves as the kernel technique, which calculates the similarity value of two concepts. Since none of the similarity measures can ensure its effectiveness in any context, usually, several measures are combined together to enhance the result’s confidence. How to find suitable aggregating weights for various similarity measures, i.e., ontology metamatching problem, is an open challenge. This paper proposes a novel ontology metamatching approach to improve the sensor ontology alignment’s quality, which utilizes the heterogeneity features on two ontologies to tune the aggregating weight set. In particular, three ontology heterogeneity measures are firstly proposed to, respectively, evaluate the heterogeneity values in terms of syntax, linguistics, and structure, and then, a semiautomatically learning approach is presented to construct the conversion functions that map any two ontologies’ heterogeneity values to the weights for aggregating the similarity measures. To the best of our knowledge, this is the first time that heterogeneity features are proposed and used to solve the sensor ontology metamatching problem. The effectiveness of the proposal is verified by comparing with using state-of-the-art ontology matching techniques on Ontology Alignment Evaluation Initiative (OAEI)’s testing cases and two pairs of real sensor ontologies.

Interlinking different data sources has become a crucial task due to the explosion of diverse, heterogeneous information repositories in the so-called Web of Data. In this paper an approach to extract relationships between entities existing in huge Linked Data sources is presented. Our approach hinges on the Map-Reduce processing framework and context-based ontology matching techniques so as to discover the maximum number of possible relationships between entities within different data sources in an computationally efficient fashion. To this end the processing flow is composed by three Map-Reduce jobs in charge for 1) the collection of linksets between datasets; 2) context generation; and 3) construction of entity pairs and similarity computation. In order to assess the performance of the proposed scheme an exemplifying prototype is implemented between DBpedia and LinkedMDB datasets. The obtained results are promising and pave the way towards benchmarking the proposed interlinking procedure with other ontology matching systems.KeywordsSemantic WebLinked Data SourcesWeb of Dataontology matchingdata interlinking

Ontologies are widely used in various domain such as medical, e-commerce and semantic web. However, heterogeneous ontologies are one of the main challenges in realizing the semantic interoperation in the domain of ontology. Ontology matching is proposed as the solution to realize the semantic interoperation. In general, three main categories of ontology matching strategies proposed by researchers: string based matching; structural based matching and also instance-based matching. Instances in ontology contain lot of semantic information which can be used for the matching purposes. However, some of the ontology contains superfluous concepts/classes which should be removed in order to increase the performance of matching. In this paper, an idea for instance-based matching with rough set feature selection capability approach is proposed to perform the ontology matching task and further increase the matching's efficiency is presented.

Objective: Using methylation characteristics of human genes to construct machine learning predictive models for screening cervical cancer and precancerous lesions. Methods: Human DNA methylation detection was performed on 224 cervical exfoliated cell specimens from the Cancer Hospital of the Chinese Academy of Medical Sciences, Tianjin Central Hospital of Gynecology Obstetrics, Xinmi Maternal and Child Health Hospital of Henan Province, West China Second Affiliated Hospital of Sichuan University, and Heping Hospital Affiliated to Changzhi Medical College collected during April 2014 and March 2015. The hypermethylated gene fragments related to cervical cancer were selected by high-density, high-association, and hypermethylated gene fragment screening and the LASSO regression algorithm. Taking cervical intraepithelial neoplasia grade 2 (CIN2) or more severe lesions as the research outcome, machine learning predictive models based on the random forest (RF), naive Bayes (NB), and support vector machine (SVM) algorithm, respectively, were constructed. A total of 144 outpatient specimens were used as the training set and 80 cervical exfoliated cell specimens from women participating in the cervical cancer screening program were used as the test set to verify the predictive models. Using histological diagnosis results as the gold standard, the detection efficacy for CIN2 or more severe lesions of the three machine learning predictive models were compared with that of the human papilloma virus (HPV) detection and cytological diagnosis. Results: In the training set of 144 cases, there were 34 cases of HPV positivity, with a positive rate of 23.61%. Cytologically, there were 37 cases diagnosed as no intraepithelial lesion or malignancy (NILM), and 107 cases diagnosed as atypical squamous cells of undetermined significance (ASC-US) or above. Histologically, there were 28 cases without cervical intraepithelial neoplasia or benign cervical lesions, 31 cases of CIN1, 18 cases of CIN2, 31 cases of CIN3, and 36 cases of squamous cell carcinoma. Seven hypermethylated gene fragments were selected from 45 genes, and three machine learning prediction models based on the RF, NB, and SVM algorithm, respectively, were constructed. In the validation set of 80 cases, there were 28 cases of HPV positivity, with a positive rate of 35.00%. Cytologically, there were 65 cases diagnosed as NILM and 15 cases as ASC-US or above. Histologically, there were 39 cases without cervical intraepithelial neoplasia or benign cervical lesions, 10 cases of CIN1, 10 cases of CIN2, 11 cases of CIN3, and 10 cases of squamous cell carcinoma. In the validation set, the area under the curve (AUC) values of the RF model, NB model, SVM model, HPV detection, and cytological diagnosis of CIN2 or above were 0.90, 0.88, 0.82, 0.68, and 0.45, respectively. The DeLong test showed that there was no statistically significant difference in the AUC values between the RF, NB, and SVM models (all P＞0.05), and the AUC values of the RF and NB models were higher than that of HPV detection (both P＜0.01), and the AUC values of the RF, NB, and SVM models were higher than that of cytological diagnosis (all P＜0.01). Compared with the NB model, the sensitivity of the RF model was similar (80.65% vs. 77.42%), but the specificity of the NB model was much higher than that of the RF model (93.88% vs. 73.47%). Conclusion: Among the machine learning prediction models for cervical cancer and precancerous lesions constructed based on human DNA methylation, the NB model has good predictive performance for CIN2 and above lesions, and may be used for screening of cervical cancer and precancerous lesions.