Showing papers on "Knowledge extraction published in 2018"

Image Captioning and Visual Question Answering Based on Attributes and External Knowledge

Abstract: Much of the recent progress in Vision-to-Language problems has been achieved through a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). This approach does not explicitly represent high-level semantic concepts, but rather seeks to progress directly from image features to text. In this paper we first propose a method of incorporating high-level concepts into the successful CNN-RNN approach, and show that it achieves a significant improvement on the state-of-the-art in both image captioning and visual question answering. We further show that the same mechanism can be used to incorporate external knowledge, which is critically important for answering high level visual questions. Specifically, we design a visual question answering model that combines an internal representation of the content of an image with information extracted from a general knowledge base to answer a broad range of image-based questions. It particularly allows questions to be asked where the image alone does not contain the information required to select the appropriate answer. Our final model achieves the best reported results for both image captioning and visual question answering on several of the major benchmark datasets.

Reactome graph database: Efficient access to complex pathway data.

Abstract: Reactome is a free, open-source, open-data, curated and peer-reviewed knowledgebase of biomolecular pathways One of its main priorities is to provide easy and efficient access to its high quality curated data At present, biological pathway databases typically store their contents in relational databases This limits access efficiency because there are performance issues associated with queries traversing highly interconnected data The same data in a graph database can be queried more efficiently Here we present the rationale behind the adoption of a graph database (Neo4j) as well as the new ContentService (REST API) that provides access to these data The Neo4j graph database and its query language, Cypher, provide efficient access to the complex Reactome data model, facilitating easy traversal and knowledge discovery The adoption of this technology greatly improved query efficiency, reducing the average query time by 93% The web service built on top of the graph database provides programmatic access to Reactome data by object oriented queries, but also supports more complex queries that take advantage of the new underlying graph-based data storage By adopting graph database technology we are providing a high performance pathway data resource to the community The Reactome graph database use case shows the power of NoSQL database engines for complex biological data types

Knowledge Distillation by On-the-Fly Native Ensemble

Abstract: Knowledge distillation is effective to train the small and generalisable network models for meeting the low-memory and fast running requirements. Existing offline distillation methods rely on a strong pre-trained teacher, which enables favourable knowledge discovery and transfer but requires a complex two-phase training procedure. Online counterparts address this limitation at the price of lacking a high-capacity teacher. In this work, we present an On-the-fly Native Ensemble (ONE) learning strategy for one-stage online distillation. Specifically, ONE only trains a single multi-branch network while simultaneously establishing a strong teacher on-the-fly to enhance the learning of target network. Extensive evaluations show that ONE improves the generalisation performance of a variety of deep neural networks more significantly than alternative methods on four image classification dataset: CIFAR10, CIFAR100, SVHN, and ImageNet, whilst having the computational efficiency advantages.

Discussion and review on evolving data streams and concept drift adapting

Abstract: Recent advances in computational intelligent systems have focused on addressing complex problems related to the dynamicity of the environments. In increasing number of real world applications, data are presented as streams that may evolve over time and this is known by concept drift. Handling concept drift is becoming an attractive topic of research that concerns multidisciplinary domains such that machine learning, data mining, ubiquitous knowledge discovery, statistic decision theory, etc... Therefore, a rich body of the literature has been devoted to the study of methods and techniques for handling drifting data. However, this literature is fairly dispersed and it does not define guidelines for choosing an appropriate approach for a given application. Hence, the main objective of this survey is to present an ease understanding of the concept drift issues and related works, in order to help researchers from different disciplines to consider concept drift handling in their applications. This survey covers different facets of existing approaches, evokes discussion and helps readers to underline the sharp criteria that allow them to properly design their own approach. For this purpose, a new categorization of the existing state-of-the-art is presented with criticisms, future tendencies and not-yet-addressed challenges.

Patient2Vec: A Personalized Interpretable Deep Representation of the Longitudinal Electronic Health Record

Abstract: The wide implementation of electronic health record (EHR) systems facilitates the collection of large-scale health data from real clinical settings. Despite the significant increase in adoption of EHR systems, these data remain largely unexplored, but present a rich data source for knowledge discovery from patient health histories in tasks, such as understanding disease correlations and predicting health outcomes. However, the heterogeneity, sparsity, noise, and bias in these data present many complex challenges. This complexity makes it difficult to translate potentially relevant information into machine learning algorithms. In this paper, we propose a computational framework, Patient2Vec , to learn an interpretable deep representation of longitudinal EHR data, which is personalized for each patient. To evaluate this approach, we apply it to the prediction of future hospitalizations using real EHR data and compare its predictive performance with baseline methods. Patient2Vec produces a vector space with meaningful structure, and it achieves an area under curve around 0.799, outperforming baseline methods. In the end, the learned feature importance can be visualized and interpreted at both the individual and population levels to bring clinical insights.

Data Mining Applications. A Comparative Study for Predicting Student's Performance

Abstract: Knowledge Discovery and Data Mining (KDD) is a multidisciplinary area focusing upon methodologies for extracting useful knowledge from data and there are several useful KDD tools to extracting the knowledge. This knowledge can be used to increase the quality of education. But educational institution does not use any knowledge discovery process approach on these data. Data mining can be used for decision making in educational system. A decision tree classifier is one of the most widely used supervised learning methods used for data exploration based on divide & conquer technique. This paper discusses use of decision trees in educational data mining. Decision tree algorithms are applied on students' past performance data to generate the model and this model can be used to predict the students' performance. It helps earlier in identifying the dropouts and students who need special attention and allow the teacher to provide appropriate advising/counseling.

Transforming data into knowledge for improved wastewater treatment operation : A critical review of techniques

Abstract: The aim of this paper is to describe the state-of-the art computer-based techniques for data analysis to improve operation of wastewater treatment plants. A comprehensive review of peer-reviewed papers shows that European researchers have led academic computer-based method development during the last two decades. The most cited techniques are artificial neural networks, principal component analysis, fuzzy logic, clustering, independent component analysis and partial least squares regression. Even though there has been progress on techniques related to the development of environmental decision support systems, knowledge discovery and management, the research sector is still far from delivering systems that smoothly integrate several types of knowledge and different methods of reasoning. Several limitations that currently prevent the application of computer-based techniques in practice are highlighted.

Deep Logic Networks: Inserting and Extracting Knowledge From Deep Belief Networks

Abstract: Developments in deep learning have seen the use of layerwise unsupervised learning combined with supervised learning for fine-tuning. With this layerwise approach, a deep network can be seen as a more modular system that lends itself well to learning representations. In this paper, we investigate whether such modularity can be useful to the insertion of background knowledge into deep networks, whether it can improve learning performance when it is available, and to the extraction of knowledge from trained deep networks, and whether it can offer a better understanding of the representations learned by such networks. To this end, we use a simple symbolic language—a set of logical rules that we call confidence rules —and show that it is suitable for the representation of quantitative reasoning in deep networks. We show by knowledge extraction that confidence rules can offer a low-cost representation for layerwise networks (or restricted Boltzmann machines). We also show that layerwise extraction can produce an improvement in the accuracy of deep belief networks. Furthermore, the proposed symbolic characterization of deep networks provides a novel method for the insertion of prior knowledge and training of deep networks. With the use of this method, a deep neural–symbolic system is proposed and evaluated, with the experimental results indicating that modularity through the use of confidence rules and knowledge insertion can be beneficial to network performance.

Onto2Vec: joint vector-based representation of biological entities and their ontology-based annotations.

Abstract: Motivation Biological knowledge is widely represented in the form of ontology-based annotations: ontologies describe the phenomena assumed to exist within a domain, and the annotations associate a (kind of) biological entity with a set of phenomena within the domain The structure and information contained in ontologies and their annotations make them valuable for developing machine learning, data analysis and knowledge extraction algorithms; notably, semantic similarity is widely used to identify relations between biological entities, and ontology-based annotations are frequently used as features in machine learning applications Results We propose the Onto2Vec method, an approach to learn feature vectors for biological entities based on their annotations to biomedical ontologies Our method can be applied to a wide range of bioinformatics research problems such as similarity-based prediction of interactions between proteins, classification of interaction types using supervised learning, or clustering To evaluate Onto2Vec, we use the gene ontology (GO) and jointly produce dense vector representations of proteins, the GO classes to which they are annotated, and the axioms in GO that constrain these classes First, we demonstrate that Onto2Vec-generated feature vectors can significantly improve prediction of protein-protein interactions in human and yeast We then illustrate how Onto2Vec representations provide the means for constructing data-driven, trainable semantic similarity measures that can be used to identify particular relations between proteins Finally, we use an unsupervised clustering approach to identify protein families based on their Enzyme Commission numbers Our results demonstrate that Onto2Vec can generate high quality feature vectors from biological entities and ontologies Onto2Vec has the potential to significantly outperform the state-of-the-art in several predictive applications in which ontologies are involved Availability and implementation https://githubcom/bio-ontology-research-group/onto2vec Supplementary information Supplementary data are available at Bioinformatics online

A retrospective of knowledge graphs

Abstract: Information on the Internet is fragmented and presented in different data sources, which makes automatic knowledge harvesting and understanding formidable for machines, and even for humans. Knowledge graphs have become prevalent in both of industry and academic circles these years, to be one of the most efficient and effective knowledge integration approaches. Techniques for knowledge graph construction can mine information from either structured, semi-structured, or even unstructured data sources, and finally integrate the information into knowledge, represented in a graph. Furthermore, knowledge graph is able to organize information in an easy-to-maintain, easy-to-understand and easy-to-use manner. In this paper, we give a summarization of techniques for constructing knowledge graphs. We review the existing knowledge graph systems developed by both academia and industry. We discuss in detail about the process of building knowledge graphs, and survey state-of-the-art techniques for automatic knowledge graph checking and expansion via logical inferring and reasoning. We also review the issues of graph data management by introducing the knowledge data models and graph databases, especially from a NoSQL point of view. Finally, we overview current knowledge graph systems and discuss the future research directions.

Data mining and predictive analytics applications for the delivery of healthcare services: a systematic literature review

Abstract: With the widespread use of healthcare information systems commonly known as electronic health records, there is significant scope for improving the way healthcare is delivered by resorting to the power of big data. This has made data mining and predictive analytics an important tool for healthcare decision making. The literature has reported attempts for knowledge discovery from the big data to improve the delivery of healthcare services, however, there appears no attempt for assessing and synthesizing the available information on how the big data phenomenon has contributed to better outcomes for the delivery of healthcare services. This paper aims to achieve this by systematically reviewing the existing body of knowledge to categorize and evaluate the reported studies on healthcare operations and data mining frameworks. The outcome of this study is useful as a reference for the practitioners and as a research platform for the academia.

Knowledge discovery out of text data: a systematic review via text mining

Abstract: Purpose The aim of this work is to increase awareness of the potential of the technique of text mining to discover knowledge and further promote research collaboration between knowledge management and the information technology communities. Since its emergence, text mining has involved multidisciplinary studies, focused primarily on database technology, Web-based collaborative writing, text analysis, machine learning and knowledge discovery. However, owing to the large amount of research in this field, it is becoming increasingly difficult to identify existing studies and therefore suggest new topics. Design/methodology/approach This article offers a systematic review of 85 academic outputs (articles and books) focused on knowledge discovery derived from the text mining technique. The systematic review is conducted by applying “text mining at the term level, in which knowledge discovery takes place on a more focused collection of words and phrases that are extracted from and label each document” (Feldman et al., 1998, p. 1). Findings The results revealed that the keywords extracted to be associated with the main labels, id est, knowledge discovery and text mining, can be categorized in two periods: from 1998 to 2009, the term knowledge and text were always used. From 2010 to 2017 in addition to these terms, sentiment analysis, review manipulation, microblogging data and knowledgeable users were the other terms frequently used. Besides this, it is possible to notice the technical, engineering nature of each term present in the first decade. Whereas, a diverse range of fields such as business, marketing and finance emerged from 2010 to 2017 owing to a greater interest in the online environment. Originality/value This is a first comprehensive systematic review on knowledge discovery and text mining through the use of a text mining technique at term level, which offers to reduce redundant research and to avoid the possibility of missing relevant publications.

Which method to use? An assessment of data mining methods in Environmental Data Science

Abstract: Data Mining (DM) is a fundamental component of the Data Science process. Over recent years a huge library of DM algorithms has been developed to tackle a variety of problems in fields such as medical imaging and traffic analysis. Many DM techniques are far more flexible than more classical numerial simulation or statistical modelling approaches. These could be usefully applied to data-rich environmental problems. Certain techniques such as artificial neural networks, clustering, case-based reasoning or Bayesian networks have been applied in environmental modelling, while other methods, like support vector machines among others, have yet to be taken up on a wide scale. There is greater scope for many lesser known techniques to be applied in environmental research, with the potential to contribute to addressing some of the current open environmental challenges. However, selecting the best DM technique for a given environmental problem is not a simple decision, and there is a lack of guidelines and criteria that helps the data scientist and environmental scientists to ensure effective knowledge extraction from data. This paper provides a broad introduction to the use of DM in Data Science processes for environmental researchers. Data Science contains three main steps (pre-processing, data mining and post-processing). This paper provides a conceptualization of Environmental Systems and a conceptualization of DM methods, which are in the core step of the Data Science process. These two elements define a conceptual framework that is on the basis of a new methodology proposed for relating the characteristics of a given environmental problem with a family of Data Mining methods. The paper provides a general overview and guidelines of DM techniques to a non-expert user, who can decide with this support which is the more suitable technique to solve their problem at hand. The decision is related to the bidimensional relationship between the type of environmental system and the type of DM method. An illustrative two way table containing references for each pair Environmental System-Data Mining method is presented and discussed. Some examples of how the proposed methodology is used to support DM method selection are also presented, and challenges and future trends are identified.

Challenges and Innovations in Building a Product Knowledge Graph

Abstract: Knowledge graphs have been used to support a wide range of applications and enhance search results for multiple major search engines, such as Google and Bing. At Amazon we are building a Product Graph, an authoritative knowledge graph for all products in the world. The thousands of product verticals we need to model, the vast number of data sources we need to extract knowledge from, the huge volume of new products we need to handle every day, and the various applications in Search, Discovery, Personalization, Voice, that we wish to support, all present big challenges in constructing such a graph. In this talk we describe four scientific directions we are investigating in building and using such a knowledge graph. First, we have been developing advanced extraction technologies to harvest product knowledge from semi-structured sources on the web and from text product profiles. Our annotation-based extraction tool selects a few webpages (typically below 10 pages) from a website for annotations, and can derive XPaths to extract from the whole website with average precision and recall of 97% [1]. Our distantly supervised extraction tool, CERES, uses an existing knowledge graph to automatically generate (noisy) training labels, and can obtain a precision over 90% when extracting from long-tail websites in various languages [1]. Our OpenTag technique extends state-of-the-art techniques such as Recursive Neural Network (RNN) and Conditional Random Field with attention and active learning, to achieve over 90% precision and recall in extracting attribute values (including values unseen in training data) from product titles, descriptions, and bullets [3].

Mining High Utility Itemsets Using Bio-Inspired Algorithms: A Diverse Optimal Value Framework

Abstract: Mining high utility itemsets (HUI) is an interesting research problem in the field of data mining and knowledge discovery. Recently, bio-inspired computing has attracted considerable attention, leading to the development of new algorithms for mining HUIs. These algorithms have shown good performance in terms of efficiency, but are not guaranteed to find all HUIs in a database. That is, the quality is comparatively poor in terms of the number of discovered HUIs. To solve this problem, a new framework based on bio-inspired algorithms is proposed. This approach adjusts the standard roadmap of bio-inspired algorithms by proportionally selecting discovered HUIs as the target values of the next population, rather than maintaining the current optimal values in the next population. Thus, the diversity within populations can be improved. Three new algorithms based on the Bio-HUI framework are developed using the genetic algorithm, particle swarm optimization, and the bat algorithm, respectively. Extensive tests conducted on publicly available datasets show that the proposed algorithms outperform existing state-of-the-art algorithms in terms of efficiency, quality of results, and convergence speed.

Tolerance-based intuitionistic fuzzy-rough set approach for attribute reduction

Abstract: Due to technological advancement and the explosive growth of electrically stored information, automated methods are required to aid users in maintaining and processing this huge amount of information. Experts, as well as machine learning processes on large volumes of data, are the main sources of knowledge. Knowledge extraction is an important step in framing expert and intelligent systems. However, the knowledge extraction phase is very slow or even impossible due to noise and large size of data. To enhance the productivity of machine learning algorithms, feature selection or attribute reduction plays a key role in the selection of relevant and non-redundant features to improve the performance of classifiers and interpretability of data. Many areas like machine learning, image processing, data mining, natural language processing and Bioinformatics, etc., which have high relevancy to expert and intelligent systems, are applications of feature selection. Rough set theory has been successfully applied for attribute reduction, but this theory is inadequate in the case of attribute reduction of real-valued data set as it may lose some information during the discretization process. Fuzzy and rough set theories have been combined and various attribute selection techniques were proposed, which can easily handle the real-valued data. An intuitionistic fuzzy set possesses a strong ability to represent information and better describing the uncertainty when compared to the classical fuzzy set theory as it considers positive, negative and hesitancy degree simultaneously for an object to belong to a set. This paper proposes a novel mechanism of attribute selection using tolerance-based intuitionistic fuzzy rough set theory. For this, we present tolerance-based intuitionistic fuzzy lower and upper approximations and formulate a degree of dependency of decision features over the set of conditional features. Moreover, the basic results on lower and upper approximations based on rough sets are extended for intuitionistic fuzzy rough sets and analogous results are established. In the end, the proposed algorithm is applied to an example data set and the comparison between tolerance-based fuzzy rough and intuitionistic fuzzy rough sets approaches for feature selection is presented. The proposed concept is found to be better performing in the form of selected attributes.

Global Model Interpretation Via Recursive Partitioning

Abstract: In this work, we propose a simple but effective method to interpret black-box machine learning models globally. That is, we use a compact binary tree, the interpretation tree, to explicitly represent the most important decision rules that are implicitly contained in the black-box machine learning models. This tree is learned from the contribution matrix which consists of the contributions of input variables to predicted scores for each single prediction. To generate the interpretation tree, a unified process recursively partitions the input variable space by maximizing the difference in the average contribution of the split variable between the divided spaces. We demonstrate the effectiveness of our method in diagnosing machine learning models on multiple tasks. Also, it is useful for new knowledge discovery as such insights are not easily identifiable when only looking at single predictions. In general, our work makes it easier and more efficient for human beings to understand machine learning models.

Data mining and machine learning in textile industry

Abstract: Data mining has been proven useful for knowledge discovery in many areas, ranging from marketing to medical and from banking to education. This study focuses on data mining and machine learning in textile industry as applying them to textile data is considered an emerging interdisciplinary research field. Thus, data mining studies, including classification and clustering techniques and machine learning algorithms, implemented in textile industry were presented and explained in detail in this study to provide an overview of how clustering and classification techniques can be applied in the textile industry to deal with different problems where traditional methods are not useful. This article clearly shows that a classification technique has higher interest than a clustering technique in the textile industry. It also shows that the most commonly applied classification methods are artificial neural networks and support vector machines, and they generally provide high accuracy rates in the textile applications. For the clustering task of data mining, a K-means algorithm was generally implemented in textile studies among the others that were investigated in this article. We conclude with some remarks on the strength of the data mining techniques for textile industry, ways to overcome certain challenges, and offer some possible further research directions. WIREs Data Mining Knowl Discov 2018, 8:e1228. doi: 10.1002/widm.1228 This article is categorized under: Application Areas > Business and Industry Application Areas > Industry Specific Applications Application Areas > Science and Technology

Learning Visual Knowledge Memory Networks for Visual Question Answering

Abstract: Visual question answering (VQA) requires joint comprehension of images and natural language questions, where many questions can't be directly or clearly answered from visual content but require reasoning from structured human knowledge with confirmation from visual content. This paper proposes visual knowledge memory network (VKMN) to address this issue, which seamlessly incorporates structured human knowledge and deep visual features into memory networks in an end-to-end learning framework. Comparing to existing methods for leveraging external knowledge for supporting VQA, this paper stresses more on two missing mechanisms. First is the mechanism for integrating visual contents with knowledge facts. VKMN handles this issue by embedding knowledge triples (subject, relation, target) and deep visual features jointly into the visual knowledge features. Second is the mechanism for handling multiple knowledge facts expanding from question and answer pairs. VKMN stores joint embedding using key-value pair structure in the memory networks so that it is easy to handle multiple facts. Experiments show that the proposed method achieves promising results on both VQA v1.0 and v2.0 benchmarks, while outperforms state-of-the-art methods on the knowledge-reasoning related questions.

An intelligent system on knowledge generation and communication about flooding

Abstract: Communities are at risk from extreme events and natural disasters that can lead to dangerous situations for residents. Improving resilience by helping people learn how to better prepare for, recover from, and adapt to disasters is critical to reduce the impacts of these extreme events. This project presents an intelligent system, Flood AI, designed to improve societal preparedness for flooding by providing a knowledge engine that uses voice recognition, artificial intelligence, and natural language processing based on a generalized ontology for disasters with a primary focus on flooding. The knowledge engine uses flood ontology to connect user input to relevant knowledge discovery channels on flooding by developing a data acquisition and processing framework using environmental observations, forecast models, and knowledge bases. The framework’s communication channels include web-based systems, agent-based chatbots, smartphone applications, automated web workflows, and smart home devices, opening the knowledge discovery for flooding to many unique use cases.

Time series segmentation through automatic feature learning

Abstract: Internet of things (IoT) applications have become increasingly popular in recent years, with applications ranging from building energy monitoring to personal health tracking and activity recognition. In order to leverage these data, automatic knowledge extraction - whereby we map from observations to interpretable states and transitions - must be done at scale. As such, we have seen many recent IoT data sets include annotations with a human expert specifying states, recorded as a set of boundaries and associated labels in a data sequence. These data can be used to build automatic labeling algorithms that produce labels as an expert would. Here, we refer to human-specified boundaries as breakpoints. Traditional changepoint detection methods only look for statistically-detectable boundaries that are defined as abrupt variations in the generative parameters of a data sequence. However, we observe that breakpoints occur on more subtle boundaries that are non-trivial to detect with these statistical methods. In this work, we propose a new unsupervised approach, based on deep learning, that outperforms existing techniques and learns the more subtle, breakpoint boundaries with a high accuracy. Through extensive experiments on various real-world data sets - including human-activity sensing data, speech signals, and electroencephalogram (EEG) activity traces - we demonstrate the effectiveness of our algorithm for practical applications. Furthermore, we show that our approach achieves significantly better performance than previous methods.

Automatic Non-Taxonomic Relation Extraction from Big Data in Smart City

Abstract: The explosive data growth in smart city is making domain big data a hot topic for knowledge extraction. Non-taxonomic relations refer to any relations between concept pairs except the is-a relation, which is an important part of Knowledge Graph. In this paper, toward big data in smart city, we present a multi-phase correlation search framework to automatically extract non-taxonomic relations from domain documents. Different kinds of semantic information are used to improve the performance of the system. First, inspired by the works of network representation; we propose a Semantic Graph-Based method to combine structure information of semantic graph and context information of terms together for non-taxonomic relationships identification. Second, different semantic types of verb sets are extracted based on the dependency syntactic information, which are ranked to act as non-taxonomic relationship labels. Extensive experiments demonstrate the efficiency of the proposed framework. The F1 value reaches 81.4% for identification of non-taxonomic relationships. The total precision of the non-taxonomic relationship labels extraction is 73.4%, and 87.8% non-taxonomic relations can be provided with “good” labels. We hope this article can provide a useful way for domain big data knowledge extraction in smart city.