Knowledge Discovery Approach Research Articles

A Novel Approach for Knowledge Discovery from AIS Data: An Application for Transit Marine Traffic in the Sea of Marmara

A Novel Approach for Knowledge Discovery from AIS Data: An Application for Transit Marine Traffic in the Sea of Marmara

A Novel Operation Sequence Similarity-Based Approach for Typical Process Route Knowledge Discovery

A typical process route essentially represents the commonly used process planning-related knowledge and can be modified to generate new process routes easily. Hence, its quality directly affects the performance of newly generated process routes and thereby the goodness of products. To effectively discover typical process route knowledge, a reasonable similarity measure and a clustering method specifically for process routes are required. However, existing operation sequence similarity coefficients often assign coarse-grained similarities, which leads to inaccurate clustering results. For the clustering problem, most researchers have not considered the practical constraints during typical process route discovery. In this paper, an operation sequence similarity-based discovery method is presented. First, the characteristics and information requirements of the operation sequence similarity problem are analysed, and a novel comprehensive similarity coefficient combined with a modified pseudo-longest-common-subsequence (pseudo-LCS) and Jaccard similarity coefficient is proposed based on this analysis. This coefficient considers the precedence relationship, the number of common operations, and the operation similarity simultaneously to handle all the potential similarity situations. Second, two soft constraints, namely, quantity constraint and size constraint, are introduced in the traditional process route clustering problem to ensure the quality and validity of the discovered typical process routes. To solve this more practical problem and achieve a balance between these two conflicting constraints, the K-medoids method is improved with an adjustment mechanism to generate valid results under these two soft constraints. Finally, numerical illustrations are presented to verify the effectiveness of the proposed methods. The results show that compared with existing similarity coefficients, the proposed comprehensive similarity coefficient is more sensitive and much better at distinguishing the tiny difference between the process routes. In addition, the modified K-medoids method can perform much better than existing methods on process route discovery data sets under two conflicting soft constraints.

Heterogeneous ensembles of classifiers in predicting Bundesliga football results

Predicting sports results is a well-known problem, and it applies to the more predictable individual sports as well as to the less predictable team sports – e.g., football. In the vast amount of information and parameters that are associated with team sports, there are few solutions related to the comprehensive approach of knowledge discovery in databases (KDD). In this paper, we propose a new approach to the whole process of discovering knowledge from data to predict the result of Bundesliga football matches. The main goal of the paper is to improve the prediction of football match results using heterogeneous ensembles of classifiers. To achieve the goal, it is necessary to prepare a training set and to develop a learning model – in this case, we analyze whether the use of limited information allows for the correct prediction of the results of football matches. The use of the developed model based on heterogeneous ensembles in the prediction of Bundesliga match results allows for improved prediction compared to classical ensembles models and single classifiers. Additionally, the possibilities arising from the use of heterogeneous ensembles of classifiers allow to distinguish some of the analyzed cases. The proposed approach was tested on real-world data, the results of Bundesliga football matches analyzed from the 2010/2011 season to the 2019/2020 season. Experiments were performed on methods selected based on an in-depth literature review. Conducted experiments, supported by the proper statistical analysis, confirm the usefulness of the proposed approach in predicting Bundesliga football results.

Knowledge Discovery in Heterogeneous and Unstructured Data of Industry 4.0 Systems: Challenges and Approaches

With the rise of the Internet of Things and Industry 4.0, the number of digital devices and their produced data increases tremendously. Due to the heterogeneity of devices, the generated data is mostly heterogeneous and unstructured. This challenges established approaches for knowledge discovery, which typically consume structured data from one source. The paper first describes aspects of data heterogeneity and their relevance for Industry 4.0 systems. Following, the upcoming challenges for different steps inside the knowledge discovery process for Industry 4.0 systems, such as for data integration and data mining, are discussed. Additionally, it mentions approaches to tackle them.

Transition from building information modeling (BIM) to integrated digital delivery (IDD) in sustainable building management: A knowledge discovery approach based review

Over the past decade, building information modeling (BIM) and sustainability have attracted increased interest, with a concomitant rise in the number of related publications. However, research efforts made in BIM for sustainable building management, especially using in all four Integrated Digital Delivery (IDD) phases are minimal. Therefore, this study features a combined scientometric analysis and IDD thematic discussion examining 471 scholarly bibliographies accessed from the Web of Science (WoS) database. The purpose of this study is to statistically classify BIM-sustainability publications from 2007 to 2019 in order to understand the research status, key themes, trends, and future challenges to be addressed in the field of sustainable BIM. The most influential scholars, institutes, regions/countries, articles, and journals have been identified. Moreover, clustering analyses identified topics that sustainable BIM research tended to gravitate toward, such as cloud approaches, data sharing, life cycle energy efficiency, and informetric analysis. The top 100 most cited documents from WoS were also manually classified into four quadrants of IDD, namely design, fabrication, construction, and asset delivery and management. Ten BIM-sustainability phenomena were observed throughout the life cycle of IDD. Finally, key research gaps and important areas for future research in this field were identified. The clearly delineated clusters and themes provide a practical overview and a deeper understanding of the current research progress of IDD for building sustainability, highlighting the challenges and research gaps for future research.

Alcoholic liver disease: A registry view on comorbidities and disease prediction.

Alcoholic-related liver disease (ALD) is the cause of more than half of all liver-related deaths. Sustained excess drinking causes fatty liver and alcohol-related steatohepatitis, which may progress to alcoholic liver fibrosis (ALF) and eventually to alcohol-related liver cirrhosis (ALC). Unfortunately, it is difficult to identify patients with early-stage ALD, as these are largely asymptomatic. Consequently, the majority of ALD patients are only diagnosed by the time ALD has reached decompensated cirrhosis, a symptomatic phase marked by the development of complications as bleeding and ascites. The main goal of this study is to discover relevant upstream diagnoses helping to understand the development of ALD, and to highlight meaningful downstream diagnoses that represent its progression to liver failure. Here, we use data from the Danish health registries covering the entire population of Denmark during nineteen years (1996–2014), to examine if it is possible to identify patients likely to develop ALF or ALC based on their past medical history. To this end, we explore a knowledge discovery approach by using high-dimensional statistical and machine learning techniques to extract and analyze data from the Danish National Patient Registry. Consistent with the late diagnoses of ALD, we find that ALC is the most common form of ALD in the registry data and that ALC patients have a strong over-representation of diagnoses associated with liver dysfunction. By contrast, we identify a small number of patients diagnosed with ALF who appear to be much less sick than those with ALC. We perform a matched case–control study using the group of patients with ALC as cases and their matched patients with non-ALD as controls. Machine learning models (SVM, RF, LightGBM and NaiveBayes) trained and tested on the set of ALC patients achieve a high performance for data classification (AUC = 0.89). When testing the same trained models on the small set of ALF patients, their performance unsurprisingly drops a lot (AUC = 0.67 for NaiveBayes). The statistical and machine learning results underscore small groups of upstream and downstream comorbidities that accurately detect ALC patients and show promise in prediction of ALF. Some of these groups are conditions either caused by alcohol or caused by malnutrition associated with alcohol-overuse. Others are comorbidities either related to trauma and life-style or to complications to cirrhosis, such as oesophageal varices. Our findings highlight the potential of this approach to uncover knowledge in registry data related to ALD.

Extracting Problem Linkages to Improve Knowledge Exchange between Science and Technology Domains using an Attention-based Language Model

Science and technology activities can be considered problem-solving activities, and scientific papers and patent publications can be viewed as providing explicit knowledge gained from the problem-solving of academia and industry respectively. However, even in the same field, the approach to the same problem is not consistent between a paper and the patented technology. The creation of information silos in science and technology generates inefficiency in human intellectual production. Therefore, this study examines whether insights from technical problems can be shared with academics to solve scientific problems. We propose a concept to link the problems between these two domains using a linguistic approach for knowledge discovery that connects science and technology. We extracted scientific papers from the Association for Computational Linguistics dataset, and patent literature from the Derwent Innovation platform. From these, pairs of problem defining sentences were identified and extracted using an attention-based language model. For example, we were able to extract examples of issues that do not necessarily arise from scientific papers, such as annotation difficulties in the analysis of social network data, but can be hinted at by patented techniques prior to the paper. These results suggest that scientific problems and industrial solutions can provide mutual insight. This knowledge discovery approach is recommended not only for benefiting corporate activities but also for grasping research trends.

A data mining approach for lubricant-based fault diagnosis

PurposeThe purpose of this paper is to develop a maintenance decision support system (DSS) framework using in-service lubricant data for fault diagnosis. The DSS reveals embedded patterns in the data (knowledge discovery) and automatically quantifies the influence of lubricant parameters on the unhealthy state of the machine using alternative classifiers. The classifiers are compared for robustness from which decision-makers select an appropriate classifier given a specific lubricant data set.Design/methodology/approachThe DSS embeds a framework integrating cluster and principal component analysis, for feature extraction, and eight classifiers among them extreme gradient boosting (XGB), random forest (RF), decision trees (DT) and logistic regression (LR). A qualitative and quantitative criterion is developed in conjunction with practitioners for comparing the classifier models.FindingsThe results show the importance of embedded knowledge, explored via a knowledge discovery approach. Moreover, the efficacy of the embedded knowledge on maintenance DSS is emphasized. Importantly, the proposed framework is demonstrated as plausible for decision support due to its high accuracy and consideration of practitioners needs.Practical implicationsThe proposed framework will potentially assist maintenance managers in accurately exploiting lubricant data for maintenance DSS, while offering insights with reduced time and errors.Originality/valueAdvances in lubricant-based intelligent approach for fault diagnosis is seldom utilized in practice, however, may be incorporated in the information management systems offering high predictive accuracy. The classification models' comparison approach, will inevitably assist the industry in selecting amongst divergent models' for DSS.

Penerapan Data Mining Menggunakan Algoritma Apriori Terhadap Data Transaksi Sebagai Pendukung Informasi Strategi Penjualan

Retail business in West Java province ranks fourth most. This indicates that there is an increase in retail business competition followed by an increase in information technology implementation. The problem of stacking stocks that could harm retail store entrepreneurs is quite common; to overcome such a precise sales strategy is indispensable. In determining the right sales strategy requires the availability of useful data and information. In order to be more efficient data of sales transaction can be processed by applying data mining technique. The method applied by researchers to design the program is the approach of knowledge discovery in the database, including data analysis to the determination of the a-priori algorithm. The purpose of this research is to obtain information about the relation between products that support the sales strategy of the sales transaction data. The linkage information between the products can later be used to support the decision of the retail business sales strategy by adjusting the product to be packaged, product offerings to the buyer and the placement of the product. The results showed that the priori algorithm can be used to process the data of sales transactions into new information in relation between products based on testing with Orange tools. The associative rules established are tested using the lift ratio, so it is important to know the association rules among the most powerful products.

Biclustering high-frequency MeSH terms based on the co-occurrence of distinct semantic types in a MeSH tree

The co-occurrence analysis of medical subject heading (MeSH) terms in the bibliographic database is used in both bibliometrics and text mining fields. Because MeSH itself contains a hierarchical structure and MeSH descriptors represent different semantic types (i.e., disease, chemicals), the biclustering analysis of distinct semantic MeSH terms may be a novel approach for knowledge discovery. This study aimed to bicluster high-frequency MeSH terms based on their co-occurrence of distinct semantic types in a MeSH tree, so as to represent the structure (or status) of a scientific topic more specifically. The study was mainly comprised of four parts: construction of a MeSH term co-occurrence matrix of distinct semantic types, the biclustering algorithm, case study, and comparison. The first three parts were completed using R and the gCLUTO software. In the case study section, more specific knowledge models about the techniques and corresponding applications were discovered, proving that the method proposed in this study was valid and could be used in the universe of knowledge discovery.

Knowledge discovery from remote sensing images: A review

AbstractThe development of Earth observation (EO) technology has made the volume of remote sensing data archiving continually larger, but the knowledge hidden in massive remote sensing images has not been fully exploited. Through in‐depth research on the artificial intelligence (AI)‐based knowledge discovery approaches from remote sensing images, we divided them into four typical types according to their development stage, including rule‐based approaches, data‐driven approaches, reinforcement learning approaches, and ensemble methods. The basic principles, typical applications, advantages, and disadvantages have been detailed for commonly used algorithms within each category. Conclusions include the following: (a) Rule‐based, data‐driven and reinforcement learning algorithms form a trilogy from knowledge to data, and to capabilities. (b) Rule‐based data mining algorithms can provide prior knowledge for data‐driven approaches, the knowledge discovered by data‐driven models can be as an important complement to expert knowledge and rule sets, and reinforcement learning approaches can effectively make up for the lack of training samples or small training sample in data‐driven models. (c) The traditional data‐driven machine learning approaches and their ensemble methods are the current and may be the future mainstream methods for large regional and even global scale long time series remote sensing data mining and analysis, and improving their computing efficiency is the key research direction. (d) Deep learning, deep reinforcement learning, transfer learning, and an ensemble approach of the three may be the main means for small‐area scope, short time series, and key geoscience information extraction from remote sensing images within a long time of the future.This article is categorized under:Algorithmic Development > Spatial and Temporal Data MiningFundamental Concepts of Data and Knowledge > Big Data MiningTechnologies > Artificial Intelligence

An Integrated Approach for Knowledge discovery and Information retrieval on Web

This Paper focuses on the integration of web information and subsequent knowledge relationship discovery within the integrated web data. The problem of information overload on the Internet has brought new attention to the ideas of filtering information on internet. Knowledge Discovery is often used for analysis of large amounts of web data and enables addressing a number of tasks that arise in Semantic Web and require scalable solutions. The World Wide Web and related web Information resources no arguably stand as the best-preferred medium for distributing information. It introduces various approaches to knowledge relation discovery like model creation, exact comparison and dynamic comparison. The nature of the web and the mass of valuable web information it holds, poses an ideal stage for applying data mining techniques for efficient discovery of knowledge from the World Wide Web. The eagerness shown by various research communities has made web based data mining (Web Mining) a rich mixture of different technologies. Therefore the heterogeneity in the area of web mining is as high as web itself. Our objective is to design an approach for information filtering, a general approach to personalized information filtering. Social Information filtering essentially automates the process of “word-of-mouth” recommendations: items are recommended to a user based upon values assigned by other people with similar taste. The system determines which users have similar taste via standard formulas for computing statistical correlations. The World Wide Web (WWW) provides a vast source of information. Technique for making personalized recommendations from any type of database to a user based on similarities between the interest profile of that user and those of other users. Recent years have seen the explosive growth of the sheer volume of information.

Knowledge Discovery With Machine Learning for Hospital-Acquired Catheter-Associated Urinary Tract Infections.

Massive generation of health-related data has been key in enabling the big data science initiative to gain new insights in healthcare. Nursing can benefit from this era of big data science, as there is a growing need for new discoveries from large quantities of nursing data to provide evidence-based care. However, there are few nursing studies using big data analytics. The purpose of this article is to explain a knowledge discovery and data mining approach that was employed to discover knowledge about hospital-acquired catheter-associated urinary tract infections from multiple data sources, including electronic health records and nurse staffing data. Three different machine learning techniques are described: decision trees, logistic regression, and support vector machines. The decision tree model created rules to interpret relationships among associated factors of hospital-acquired catheter-associated urinary tract infections. The logistic regression model showed what factors were related to a higher risk of hospital-acquired catheter-associated urinary tract infections. The support vector machines model was included to compare performance with the other two interpretable models. This article introduces the examples of cutting-edge machine learning approaches that will advance secondary use of electronic health records and integration of multiple data sources as well as provide evidence necessary to guide nursing professionals in practice.

Knowledge Discovery in Nanophotonics Using Geometric Deep Learning

Herein, a new approach for using the intelligence aspects of artificial intelligence for knowledge discovery rather than device optimization in electromagnetic (EM) nanostructures is presented. This approach uses training data obtained through full‐wave EM simulations of a series of nanostructures to train geometric deep learning algorithms to assess the range of feasible responses as well as the feasibility of a desired response from a class of EM nanostructures. To facilitate the knowledge discovery, this approach combines the dimensionality reduction technique with convex‐hull and one‐class support‐vector‐machine (SVM) algorithms to find the range of the feasible responses in the latent response space of the EM nanostructure. More importantly, the one‐class SVM algorithm can be trained to provide the degree of feasibility of a response from a given nanostructure. This important information can be used to modify the initial structure to an alternative one that can enable an initially unfeasible response. To show the applicability of this approach, it is applied to two important classes of binary metasurfaces (MSs), formed by an array of plasmonic nanostructures, and periodic MSs formed by an array of dielectric nanopillars. These theoretical and experimental results confirm the unique features of this approach for knowledge discovery in EM nanostructures.

Chemometrics approach for the prediction of chemical compounds’ toxicity degree based on quantum inspired optimization with applications in drug discovery

Chemometrics, the application of mathematical and statistical methods to the analysis of chemical data, is finding ever widening applications in the chemical process environment. The reliable prediction of toxic effects of chemicals in living systems is highly desirable in domains such as cosmetics, drug discovery, food safety, and the manufacturing of chemical compounds. Toxicity prediction requires several new approaches for knowledge discovery from data to paradigm composite associations between the modules of the chemical compound; the computational demands of such techniques increase greatly with the number of chemical compounds involved. State-of-the-art prediction methods such as neural networks and multi-layer regression require either tuning parameters or complex transformations of predictor or outcome variables and do not achieve highly accurate results. This paper proposes a Quantum Inspired Genetic Programming “QIGP” model to improve prediction accuracy. Genetic Programming is utilized to give a linear equation for calculating the degree of toxicity more accurately. Quantum computing is employed to improve the selection of the best-of-run individuals and handles parsimony pressure to reduce the complexity of solutions. The results of the internal validation analysis indicated that the QIGP model has better goodness of fit statistics then, and significantly outperforms, the Neural Network model.

Authorship Verification using a Graph Knowledge Discovery Approach

This paper presents an approach to solve authorship verification, a forensic text problem which consists in determining whether or not an unknown document was written by a particular author, from some samples of the author’s writing style. The core of the approach is the use of a graph representati on to extract relevant linguistic features based on network analysis techniques. The use of graphs provides rich data structures for representing lexical and syntactic aspects of texts, allowing the reinterpretation of centrality measures to extract linguistic features that do not depend entirely of stylistic elements of text documents. The proposed method is applied on the English language partitions of the clef PAN 2014 and 2015 author verification datasets, producing competitive results that outperform the state of the art baselines and are near (or surpass in one of the cases) to the best results reported so far, given the same training and test corpora. These experimental results showed that our interpretation of the four centrality measures: closeness, betweenness, degree and eigenvector allow to detect relevant patterns of an author’s writing style. In particular, words with high closeness which are part of some chunk phrases and words with high betweenness that are included in bigrams and trigrams, contribute in a more effective way to verify document authorship.

Quantum‐inspired genetic programming model with application to predict toxicity degree for chemical compounds

AbstractCheminformatics plays a vital role in maintaining large amounts of chemical data. The reliable prediction of toxic effects of chemicals in living systems is highly desirable in domains such as cosmetics, drug design, food safety, and the manufacturing of chemical compounds. Toxicity prediction requires several new approaches for knowledge discovery from data to paradigm composite associations between the modules of the chemical compound; the computational demands of such techniques increase greatly with the number of chemical compounds involved. State‐of‐the‐art prediction methods such as neural networks and multilayer regression require either tuning parameters or complex transformations of predictor or outcome variables and do not achieve highly accurate results. This paper proposes a quantum‐inspired genetic programming model to improve prediction accuracy. Genetic programming is utilized to give a linear equation for calculating the degree of toxicity more accurately. Quantum computing is employed to improve the selection of the best‐of‐run individuals and handles parsimony pressure to reduce the complexity of solutions. The results of the internal validation analysis indicated that the quantum‐inspired genetic programming model has better goodness‐of‐fit statistics then and significantly outperforms the neural network model.

A deep learning approach for power system knowledge discovery based on multitask learning

Power system security assessment is an important and challenging problem. Large variations in loads and power generation present increased risks to the secure operation of power systems. This study proposes a distributed deep network structure for power system security knowledge discovery based on multitask learning to monitor and control power grids more properly and effectively. First, a deep neural network structure based on the deep belief network (DBN) is designed to non-linearly extract deep and abstract features layer-by-layer for total transfer capability (TTC) regression tasks. Then, a distributed training algorithm for the deep structure is developed to accelerate the training process. Furthermore, multitask learning is adopted by grouping and training-related tasks together to improve the task performance. Finally, the accuracy and efficiency of the deep structure are evaluated using the Guangdong Power Grid in China. The simulation results demonstrate that the proposed model can outperform the existing shallow models in terms of accuracy and stability and can meet the requirements of online computing efficiency.

Biodiversity Observations Miner: A web application to unlock primary biodiversity data from published literature

BackgroundA considerable portion of primary biodiversity data is digitally locked inside published literature which is often stored as pdf files. Large-scale approaches to biodiversity science could benefit from retrieving this information and making it digitally accessible and machine-readable. Nonetheless, the amount and diversity of digitally published literature pose many challenges for knowledge discovery and retrieval. Text mining has been extensively used for data discovery tasks in large quantities of documents. However, text mining approaches for knowledge discovery and retrieval have been limited in biodiversity science compared to other disciplines.New informationHere, we present a novel, open source text mining tool, the Biodiversity Observations Miner (BOM). This web application, written in R, allows the semi-automated discovery of punctual biodiversity observations (e.g. biotic interactions, functional or behavioural traits and natural history descriptions) associated with the scientific names present inside a corpus of scientific literature. Furthermore, BOM enable users the rapid screening of large quantities of literature based on word co-occurrences that match custom biodiversity dictionaries. This tool aims to increase the digital mobilisation of primary biodiversity data and is freely accessible via GitHub or through a web server.

A hybrid and exploratory approach to knowledge discovery in metabolomic data

In this paper, we propose a hybrid and exploratory knowledge discovery approach for analyzing metabolomic complex data based on a combination of supervised classifiers, pattern mining and Formal Concept Analysis (FCA). The approach is based on three main operations, preprocessing, classification, and postprocessing. Classifiers are applied to datasets of the form individuals × features and produce sets of ranked features which are further analyzed. Pattern mining and FCA are used to provide a complementary analysis and support for visualization. A practical application of this framework is presented in the context of metabolomic data, where two interrelated problems are considered, discrimination and prediction of class membership. The dataset is characterized by a small set of individuals and a large set of features, in which predictive biomarkers of clinical outcomes should be identified. The problems of combining numerical and symbolic data mining methods, as well as discrimination and prediction, are detailed and discussed. Moreover, it appears that visualization based on FCA can be used both for guiding knowledge discovery and for interpretation by domain analysts.