Knowledge Extraction Framework Research Articles

KEFST: a knowledge extraction framework using finite-state transducers

PurposeThe purpose of this research study is to extract and identify named entities from Hadith literature. Named entity recognition (NER) refers to the identification of the named entities in a computer readable text having an annotation of categorization tags for information extraction. NER is an active research area in information management and information retrieval systems. NER serves as a baseline for machines to understand the context of a given content and helps in knowledge extraction. Although NER is considered as a solved task in major languages such as English, in languages such as Urdu, NER is still a challenging task. Moreover, NER depends on the language and domain of study; thus, it is gaining the attention of researchers in different domains.Design/methodology/approachThis paper proposes a knowledge extraction framework using finite-state transducers (FSTs) – KEFST – to extract the named entities. KEFST consists of five steps: content extraction, tokenization, part of speech tagging, multi-word detection and NER. An extensive empirical analysis using the data corpus of Urdu translation of Sahih Al-Bukhari, a widely known hadith book, reveals that the proposed method effectively recognizes the entities to obtain better results.FindingsThe significant performance in terms of f-measure, precision and recall validates that the proposed model outperforms the existing methods for NER in the relevant literature.Originality/valueThis research is novel in this regard that no previous work is proposed in the Urdu language to extract named entities using FSTs and no previous work is proposed for Urdu hadith data NER.

A Two-Step Knowledge Extraction Framework for Improving Disease Diagnosis

AbstractIn the last decades, various methodologies have been proposed by the researchers for developing effective disease diagnosis support systems (DDSSs). The present research proposes a two-step framework in which an entropy-based feature-selection approach is introduced in the first step and a rule-base hybrid model using Perfect Rule Induction by Sequential Method (PRISM) is explored in the subsequent step for effective diagnosis of diseases. The suggested feature-selection technique is validated using five state-of-the-art classifiers namely C4.5 (a decision tree-based classifier), naïve Bayes (NB), Repeated Incremental Pruning to Produce Error Reduction (RIPPER), neural network (NN) and support vector machine (SVM) over fourteen benchmark diseases that are very common and the leading causes of deaths. Next, on the basis of top three performance metrics, viz., prediction accuracy, sensitivity and false positive rate, the performance of the hybrid model over the datasets is compared with its base learner: PRISM, two other competent learners namely C4.5 and NN, and some specialized models. The empirical outcomes positively demonstrate that the hybrid model with application of feature-selection method is a generic model and effective in diagnosing diseases. More importantly, the model not only is able to produce good results but also to elucidate its knowledge in understandable: IF-THEN form (convenient for medical practitioners).

Explainable deep learning based medical diagnostic system

Abstract Recently, many researchers have conducted data mining over medical data to uncover hidden patterns and use them to learn prediction models for clinical decision making and personalized medicine. While such healthcare learning models can achieve encouraging results, they seldom incorporate existing expert knowledge into their frameworks and hence prediction accuracy for individual patients can still be improved. However, expert knowledge spans across various websites and multiple databases with heterogeneous representations and hence is difficult to harness for improving learning models. In addition, patients' queries at medical consult websites are often ambiguous in their specified terms and hence the returned responses may not contain the information they seek. To tackle these problems, we first design a knowledge extraction framework that can generate an aggregated dataset to characterize diseases by integrating heterogeneous medical data sources. Then, based on the integrated dataset, we propose an end-to-end deep learning based medical diagnosis system ( D L - M D S ) to provide disease diagnosis for authorized users. We also provide explanations for the diagnose results. Evaluations on real-world data demonstrate that our proposed system achieves good performance on diseases diagnosis with a diverse set of patients’ queries.

A semantic-based knowledge fusion model for solution-oriented information network development: a case study in intrusion detection field

Building information networks using semantic based techniques to avoid tedious work and to achieve high efficiency has been a long-term goal in the information management world. A great volume of research has focused on developing large scale information networks for general domains to pursue the comprehensiveness and integrity of the information. However, constructing customised information networks containing subject-specific knowledge has been neglected. Such research can potentially return high value in terms of both theoretical and practical contribution. In this paper, a new type of network, solution-oriented information network, is coined that includes research problems and proposed techniques as nodes, and the relationship between them. A lightweight Semantic-based Knowledge Fusion Model (SKFM) is proposed leveraging the power of Natural Language Processing (NLP) and Crowdsourcing to construct the proposed information networks using academic papers (knowledge) from Scopus. SKFM relies on NLP in terms of automatic components while Crowdsourcing is initiated when uncertain cases arise. Applying the NLP technique assists to develop a semi-automatic knowledge fusion method for saving effort and time in extracting information from academic papers. Leveraging human power in uncertain cases is to make sure the essential concepts for developing the information networks are extracted reliably and connected correctly. SKFM shows a theoretical contribution in terms of lightweight knowledge extraction and reconstruction framework, as well as practical value by providing solutions proposed in academic papers to address corresponding research issues in subject-specific areas. Experiments have been implemented which have shown promising results. In the research field of intrusion detection, the information of attack types and proposed solutions has been extracted and integrated in a graphic manner with high accuracy and efficiency.

Knowledge extraction and visualization of digital design process

After digitally designing components of vehicles, a design team creates a virtual manufacturing environment that resembles actual manufacturing facilities. During this digital pre-assembly process, a review team examines each component, and records its problems and requirements in part verification reports. Once these reports are delivered to specific design team responsible for each part, the design team can make appropriate adjustments to their designs. This digital pre-assembly process can evaluate and prevent flaws in design prior to actual manufacturing, improving production quality and reducing manufacturing cost. As these reports are written in free text form, they, however, are not fully utilized for understanding problems arising from the design process. This paper proposes a method of applying text mining techniques on verification reports to extract insights for quality improvement. In this paper, following three text mining approaches are proposed: (1) Extracting n-grams for text preprocessing and constructing domain ontology; (2) Extracting meaningful insights from text preprocessing; (3) Creating intuitive visual tools to understand the extracted insights. The proposed method is applied on approximately 140,000 reports, and is validated through the quality of the answers obtained for the questions posed by the domain experts. The proposed method successfully extracts useful information from the text database, and provides intuitive graphical interface, thereby satisfying the need of the domain experts. This paper proposes a systematic framework of transforming huge amount of raw text data into intuitive visualization. Through this framework, meaningful knowledge can be extracted, analyzed and shared to improve the quality of the products. Main contribution of our paper is that it proposes a framework for knowledge extraction from pre-assembly process. Not only does it systematically arrange the data, but it also combines various data sources and creates a knowledge system to improve efficiency of the design process.

A new TRIZ-based patent knowledge management system for construction technology innovation

PurposeThe quantity of construction technology innovations in patent database grows at a high speed. More challenging technical problems require knowledge workers to make full use of the huge existing technology innovation knowledge base to propose new innovative solutions. Hence, it is critical to deliver the right knowledge to the right people at the right time. To improve innovation efficiency and effectiveness, this research explores the development of a new patent knowledge management system to satisfy the increasing demand of construction innovations.Design/methodology/approachTRIZ-based patent knowledge management system (TPKMS) development involves the integration of construction patent knowledge management, theory of inventive problem-solving (TRIZ) theory, database techniques and computer programing technology. The contradiction matrix in TRIZ theory serves as the patent knowledge extraction framework, while SQL Server 2000 database management system is employed to manage the extracted patent knowledge, TRIZ and user account information. Visual C++ 6.0 is adopted as the development tool.FindingsThe developed system to manage construction patent knowledge integrates TRIZ with the database design, enabling the system users to be more problem-focused, systematic and efficient. The system provides a heuristic environment to help improve the innovation effectiveness by motivating knowledge workers’ innovative thinking. Further development of the system is proposed in the context of the age of big data.Originality/valueA new TRIZ-based patent knowledge management system for construction technology innovation was developed.

Knowledge Extraction Framework for Building a Largescale Knowledge Base

Knowledge Extraction Framework for Building a Largescale Knowledge Base

Mining scheduling knowledge for job shop scheduling problem

The optimal or near-optimal schedules generated by traditional optimization or approximation methods for job shop scheduling problems (JSSP) contain valuable scheduling patterns about this kind of scheduling problems. These patterns could be used to improve the dispatching performance and provide insights into the corresponding scheduling problems. This paper uses timed Petri nets to describe the dispatching processes of the job shop scheduling scenarios. On this basis, a data mining based scheduling knowledge extraction framework is developed to mine the expected scheduling knowledge from the solutions generated by traditional optimization or approximation method for JSSP. Based on this, we show how to use the extracted knowledge as a new dispatching rule to generate complete schedules. A novel method is further developed to combine the extracted knowledge with traditional heuristics to construct new composite dispatching rules which could gain better performance. Besides, we propose a novel approach to utilize the extracted knowledge to improve a Petri net based branch and bound algorithm used in this paper. A series of experiments is carried out to evaluate the performance of the proposed methods.

An architectural framework for knowledge extraction from meteorological data

The methods of knowledge extraction from spatio-temporal data such as meteorological domain suffer from various problems like missing values, noise, improper format, and large in volume. Therefore, data pre-processing and reorganisation are the important concerns of this domain. In this paper, we have discussed a layered framework for data fetching, pre-processing and persisting. Further, we develop knowledge extraction modules for supporting the future extensibility and reusing well established tools. We have presented experimental results achieved using this architecture, in addition to its other potential benefits.

A concept-driven biomedical knowledge extraction and visualization framework for conceptualization of text corpora

A number of techniques such as information extraction, document classification, document clustering and information visualization have been developed to ease extraction and understanding of information embedded within text documents. However, knowledge that is embedded in natural language texts is difficult to extract using simple pattern matching techniques and most of these methods do not help users directly understand key concepts and their semantic relationships in document corpora, which are critical for capturing their conceptual structures. The problem arises due to the fact that most of the information is embedded within unstructured or semi-structured texts that computers can not interpret very easily. In this paper, we have presented a novel Biomedical Knowledge Extraction and Visualization framework, BioKEVis to identify key information components from biomedical text documents. The information components are centered on key concepts. BioKEVis applies linguistic analysis and Latent Semantic Analysis (LSA) to identify key concepts. The information component extraction principle is based on natural language processing techniques and semantic-based analysis. The system is also integrated with a biomedical named entity recognizer, ABNER, to tag genes, proteins and other entity names in the text. We have also presented a method for collating information extracted from multiple sources to generate semantic network. The network provides distinct user perspectives and allows navigation over documents with similar information components and is also used to provide a comprehensive view of the collection. The system stores the extracted information components in a structured repository which is integrated with a query-processing module to handle biomedical queries over text documents. We have also proposed a document ranking mechanism to present retrieved documents in order of their relevance to the user query.

The development of a two-phase knowledge extraction framework on liquid crystal display image quality with knowledge-creation process

This study develops a two-phase knowledge extraction framework of liquid crystal display (LCD) to provide some useful knowledge for ordinary users and manufacturers. At the first phase, the knowledge about important factors from ordinary users' viewpoints is extracted through an experiment. At the second phase, a systematic method is developed to convert these important factors into related manufacturing techniques and materials from manufacturers' viewpoints. Finally, the two-phase knowledge extraction framework is demonstrated to illustrate the knowledge extraction process of LCD image quality.