Knowledge Discovery Research Articles

ICEED: Integrated customized extraction of enzyme data.

Enzymes catalyze diverse biochemical reactions and are building blocks of cellular and metabolic pathways. Data and metadata of enzymes are distributed across databases and are archived in various formats. The enzyme databases provide utilities for efficient searches and downloading enzyme records in batch mode but do not support organism-specific extraction of subsets of data. Users are required to write scripts for parsing entries for customized data extraction prior to downstream analysis. Integrated Customized Extraction of Enzyme Data (iCEED) has been developed to provide organism-specific customized data extraction utilities for seven commonly used enzyme databases and brings these resources under an integrated portal. iCEED provides dropdown menus and search boxes using typehead utility for submission of queries as well as enzyme class-based browsing utility. A utility to facilitate mapping and visualization of functionally important features on the three-dimensional (3D) structures of enzymes is integrated. The customized data extraction utilities provided in iCEED are expected to be useful for biochemists, biotechnologists, computational biologists, and life science researchers to build curated datasets of their choice through an easy to navigate web-based interface. The integrated feature visualization system is useful for a fine-grained understanding of the enzyme structure-function relationship. Desired subsets of data, extracted and curated using iCEED can be subsequently used for downstream processing, analyses, and knowledge discovery. iCEED can also be used for training and teaching purposes.

Toward Automated Knowledge Discovery in Case-Based Reasoning

Automated Case Elicitation (ACE) enables case-based reasoning (CBR) systems to automatically acquire knowledge through real-time exploration and interaction with environments. CBR is an explainable AI methodology, where decisions are based on previous encounters. ACE combined with CBR continues learning as it is being deployed, and produces specific cases that can be reviewed by humans, unlike pretrained large language models (LLMs) that learn by training offline on prior data. ACE and CBR may be useful methods to gather training data for use with generative AI, or to help them to adapt on the fly. This research explores ACE's potential by applying it to chess and conducting extensive experiments against Stockfish, the world's highest rated chess engine. An ACE agent was developed that combines random exploration with shallow alpha-beta search for novel game states. Results over 1000+ games showed the ACE player defeated Stockfish in nearly 10% of games—a notable achievement given Stockfish's extreme strength. Notably, the ACE agent required only 0.1 seconds per game compared an average of 8 minutes for Stockfish, while still gradually improving its win rate through accrued experience. Detailed analyses revealed how the relaxation of ACE's case matching criteria along with selective retention of useful cases enabled accumulation of strategic chess knowledge. The research provides valuable insights into ACE's proficiency for knowledge discovery in complex, adversarial domains. It lays groundwork for integrating ACE, an unsupervised CBR learner, with modern deep learning techniques like neural networks and large language models to combine the strengths of symbolic and subsymbolic AI. By demonstrating ACE's ability to extract strategic knowledge against world-class opponents, this work highlights its potential for impact across gaming, autonomous systems, and other complex problem-solving domains.

An interoperable software system to store, associate, visualize, and publish global open science data of earth surface system

Multi-source heterogeneous, multi-modal, and multi-type open scientific data (e.g., thematic sharing sites, metadata, journal articles, etc.) on earth surface systems (EES) provide important data sources for knowledge mining, discovery, and accurate recommendations, and also pose increasing challenges, resulting in the need to develop appropriate tools to address these challenges and support decision-making. This paper constructs an interoperable software system to store, visualize, and publish open science data of ESS. Utilizing an open scientific data catalogue repository encompassing EES information as foundational input and employing an integrated modeling methodology, this system endeavors to synthesize heterogeneous surface data of diverse linguistic, sourced, and typological origins. The objective is to facilitate multidimensional data retrieval and precise data auto-recommendation, thereby fostering the dissemination of scientific data and facilitating value-added services within EES domain. The tool may be used by stakeholders including researchers, data analysts, policymakers and national authorities to support decision-making on questions ranging from locating the location of open data related to the topic, to discovering high-quality data, selecting the data with the better overall evaluation. Along with a description of the system/platform design process, its structure, and the constituent models, key results are presented relating to the user interface, and several application examples. Software systems can help modelers to use the best features of a single software tool to answer open scientific data-related questions that seek to discovery, use, comparison or synthesis within or across topics of ESS.

Incorporation of adaptive compression into a GPU parallel computing framework for analyzing large-scale vessel trajectories

Automatic Identification System (AIS) offers a wealth of vessel navigation data, which underpins research in maritime data mining, situational awareness, and knowledge discovery within the realm of intelligent transportation systems. The flourishing marine industry has prompted AIS satellites and base stations to generate massive amounts of vessel trajectory data, escalating both data storage and calculation costs. The conventional Douglas-Peucker (DP) algorithm used for trajectory compression sets a uniform threshold, which hampers effective compression. Additionally, compressing and accelerating the computation of large datasets poses a significant challenge in real-world applications. To address these limitations, this paper aims to develop a new Graphics Processing Unit (GPU) parallel computing and compression framework that enables the acceleration of the optimal threshold calculation for each trajectory automatically in maritime big data mining. It achieves this by incorporating a new Adaptive DP with Speed and Course (ADPSC) algorithm, which utilizes the dynamic navigation characteristics of different vessels. It can effectively solve the associated computational time cost concern when using the ADPSC algorithm to compress vast trajectory datasets in the real world. Additionally, this paper proposes a novel evaluation metric for assessing compression efficacy based on the Dynamic Time Warping (DTW) method. Comprehensive experiments encompass vessel trajectory datasets from three representative research areas: Tianjin Port, Chengshan Jiao Promontory, and Caofeidian Port. The experimental results demonstrate that 1) the newly developed ADPSC method outperforms in terms of compression, and 2) the designed GPU parallel computing framework can significantly shorten the compression time for extensive datasets. The GPU-accelerated compression methodology not only minimizes storage and transmission costs for data from both manned and unmanned vessels but also enhances data processing speed, supporting real-time decision-making. From a theoretical perspective, it provides the key to the puzzle of realizing the real-time anti-collision of manned and unmanned ships, particularly in complex waters. It hence makes significant contributions to maritime safety in the autonomous shipping era.

Current and future applications of artificial intelligence in surgery: implications for clinical practice and research.

Surgeons are skilled at making complex decisions over invasive procedures that can save lives and alleviate pain and avoid complications in patients. The knowledge to make these decisions is accumulated over years of schooling and practice. Their experience is in turn shared with others, also via peer-reviewed articles, which get published in larger and larger amounts every year. In this work, we review the literature related to the use of Artificial Intelligence (AI) in surgery. We focus on what is currently available and what is likely to come in the near future in both clinical care and research. We show that AI has the potential to be a key tool to elevate the effectiveness of training and decision-making in surgery and the discovery of relevant and valid scientific knowledge in the surgical domain. We also address concerns about AI technology, including the inability for users to interpret algorithms as well as incorrect predictions. A better understanding of AI will allow surgeons to use new tools wisely for the benefit of their patients.

Application of Knowledge Discovery in Databases (KDD) to environmental, economic, and social indicators used in BIM workflow to support sustainable design

Life Cycle Sustainability Assessment (LCSA) can help to predict the impact of products and services, such as buildings, during their entire life cycle. However, it is an extensive data method. The Building Information Modelling (BIM) method can contribute towards reducing the effort involved and simplifying the data collection relating to the building elements. To this end, databases adjusted to the BIM workflow are needed to systematise and harmonise the structure of the environmental, economic and social data of said elements. This paper provides a solution to this problem by presenting an innovative Triple Bottom Line (TBL) database with environmental, economic, and social indicators of building elements to support the triple assessment adapted to the BIM workflow. An analysis employing Knowledge Discovery in Databases (KDD) was performed for the first time on this type of database to better understand the correlations between the dimensions. The key contributions include correlation detection, 83 % of which were direct, which showed that, overall, the environmental (CO2 emissions), economic (cost), and social (labour) dimensions experience similar growth trends. Strong correlations between economic and social variables were found in 68 % of the cases, followed by those of the economic and environmental (32 %), and social and environmental (18 %) variables. Findings from the correlation analysis between the three dimensions reveal their influence on the type of building system, element and material. Four scenarios were thereby identified in accordance with these correlations, to aid in sustainable decision-making. Various growth trends were detected, which can facilitate the implementation of the LCSA.

Knowledge graph-guided data-driven design of ultra-high-performance concrete (UHPC) with interpretability and physicochemical reaction discovery capability

Traditional methods for designing concrete materials typically rely on labor-intensive laboratory experiments, resulting in time and cost inefficiencies. Recently, designing concrete using artificial intelligence (AI) methods has shown high efficiency, but existing AI methods often rely solely on data, which can lead to violation with scientific principles and result in models lacking reasoning abilities. To overcome these challenges, this paper presents an interpretable knowledge graph-guided data-driven design approach. By integrating advanced computing techniques with domain knowledge via knowledge graphs, this approach enables the interpretation of data-driven models and uncovers the underlying mechanisms behind predictions. This approach is applied to ultra-high-performance concrete (UHPC) involving complex physicochemical reactions. The domain knowledge about UHPC is imparted using a knowledge graph, and UHPC properties are predicted using a machine learning model considering mixing proportions, processing methods, and physiochemical properties of materials via natural language processing. The results show that the knowledge graph displays crucial design variables and their effects on UHPC properties, aiding in selecting variables for machine learning models and interpreting their results. The prediction accuracy of the machine learning model reached 0.95. The research paves the way for more transparent and scientific AI models for material design and AI-enabled discovery of scientific knowledge.

Dynamic knowledge graph applications for augmented built environments through “The World Avatar”

The proliferation of digital building models in recent years has led to a corresponding rise in specialised, non-interoperable models. These models impede sustainable developments by forming data silos that hinder cross-application data exchange and knowledge discovery processes. Although Semantic Web solutions hold promise in addressing these silos, current approaches primarily focus on developing novel ontologies, yielding similar outcomes. But it is unclear how these methodologies could support broader knowledge discovery processes and application requirements. This paper addresses these research challenges by introducing a dynamic knowledge graph as implemented within The World Avatar for interoperable building models. We demonstrate its value through two distinct applications in urban energy management and laboratory automation. The dynamic knowledge graph revolves around a comprehensive structured knowledge model constructed from ontologies and agents. Ontologies semantically annotate data and represent domain knowledge and their relationships with standardised definitions. When augmented with an agent architecture, the resulting knowledge model can align stakeholder perspectives and accommodate the dynamic and scalable nature of urban data. Moreover, the dynamic knowledge graph fosters innovative human-machine interactions through visualisation interfaces to augment knowledge discovery processes in the built environment for greater efficiencies and innovation. As the knowledge model expands, users gain access to a broader spectrum of private and public data sources and technologies, while reducing integration barriers. This is especially pertinent for smaller and less influential entities like municipal and local governments with limited resources, who can realise substantial benefits at reduced costs.

Knowledge graph learning algorithm based on deep convolutional networks

Knowledge graphs (KGs) serve as invaluable tools for organizing and representing structural information, enabling powerful data analysis and retrieval. In this paper, we propose a novel knowledge graph learning algorithm based on deep convolutional neural networks (KGLA-DCNN) to enhance the classification accuracy of KG nodes. Leveraging the hierarchical and relational nature of KGs, our algorithm utilizes deep convolutional neural networks to capture intricate patterns and dependencies within the graph. We evaluate the effectiveness of KGLA-DCNN on two benchmark datasets, Cora and Citeseer, renowned for their challenging node classification tasks. Through extensive experiments, we demonstrate that our proposed algorithm significantly improves classification accuracy compared to state-of-the-art methods, showcasing its capability to leverage the rich structural information inherent in KGs. The results highlight the potential of deep convolutional neural networks in enhancing the learning and representation capabilities of knowledge graphs, paving the way for more accurate and efficient knowledge discovery in diverse domains.

Explaining deep learning for ECG analysis: Building blocks for auditing and knowledge discovery

Deep neural networks have become increasingly popular for analyzing ECG data because of their ability to accurately identify cardiac conditions and hidden clinical factors. However, the lack of transparency due to the black box nature of these models is a common concern. To address this issue, explainable AI (XAI) methods can be employed. In this study, we present a comprehensive analysis of post-hoc XAI methods, investigating the glocal (aggregated local attributions over multiple samples) and global (concept based XAI) perspectives. We have established a set of sanity checks to identify saliency as the most sensible attribution method. We provide a dataset-wide analysis across entire patient subgroups, which goes beyond anecdotal evidence, to establish the first quantitative evidence for the alignment of model behavior with cardiologists’ decision rules. Furthermore, we demonstrate how these XAI techniques can be utilized for knowledge discovery, such as identifying subtypes of myocardial infarction. We believe that these proposed methods can serve as building blocks for a complementary assessment of the internal validity during a certification process, as well as for knowledge discovery in the field of ECG analysis.

Importance of Characteristic Features and Their Form for Data Exploration.

The nature of the input features is one of the key factors indicating what kind of tools, methods, or approaches can be used in a knowledge discovery process. Depending on the characteristics of the available attributes, some techniques could lead to unsatisfactory performance or even may not proceed at all without additional preprocessing steps. The types of variables and their domains affect performance. Any changes to their form can influence it as well, or even enable some learners. On the other hand, the relevance of features for a task constitutes another element with a noticeable impact on data exploration. The importance of attributes can be estimated through the application of mechanisms belonging to the feature selection and reduction area, such as rankings. In the described research framework, the data form was conditioned on relevance by the proposed procedure of gradual discretisation controlled by a ranking of attributes. Supervised and unsupervised discretisation methods were employed to the datasets from the stylometric domain and the task of binary authorship attribution. For the selected classifiers, extensive tests were performed and they indicated many cases of enhanced prediction for partially discretised datasets.

Sensitivity analysis for knowledge discovery in scramjet intake design optimization using deep-learning flowfield prediction

Scramjet engines are a promising propulsion technology for future space transportation systems, and its design exploration represents a significant task toward development of high-performance scramjets. While sensitivity analysis is expected to facilitate acquisition of physical insights for effective scramjet design, the substantial computational cost incurred due to numerical simulations required for statistical analysis poses a challenge to the application, limiting the capability of this analysis. The present study has conducted sensitivity analysis using deep-learning-based flowfield prediction that can significantly reduce the computational cost for numerical simulations providing flowfield data. Global sensitivity analyses have been employed to investigate influential design variables on the flowfield and performance. These have allowed for identifying the design variables that dominantly influence or determine the performance parameters. Local sensitivity analyses have been performed to elucidate the design rationales and the characteristic flow structures for high-performance intake designs. The sensitivity analysis methods in conjunction with flowfield prediction have enabled generation of rich insights that would otherwise be difficult to acquire without this approach, demonstrating the capabilities of the proposed methodology.

A feature selection method for multimodal multispectral LiDAR sensing

Optical remote sensing techniques can indicate the properties of objects by observing different modalities (physical quantities) of the backscattered light at different optical wavelengths. Established examples are reflectance, fluorescence, Raman, or depolarization spectroscopy. LiDAR sensing, on the other hand, allows acquiring the geometry of objects by measuring the propagation delay of optical probing signals. Multimodal multispectral (MM) LiDAR combines these capabilities and extends conventional monochromatic LiDAR in both spectral and modal dimensions within a single instrument, thus enriching point cloud data with non-geometric information. The potentially high dimension of MM LiDAR data, however, poses significant challenges for instrumental design, data acquisition, and data processing. MM LiDAR data are structured as several or all modalities are available in each of the spectral channels. The above challenges can thus be mitigated by feature selection (FS), if the structure of the features is taken into account, i.e., if entire spectral channels or entire modalities are selected or omitted. Herein, we focus on the feature selection method for MM LiDAR and propose a multiclass group feature selection algorithm (MGSVM FS) consisting of a structural sparsity-based embedded feature selection method with an all-in-one support vector machine (SVM). It tackles jointly the challenges arising from the high dimension of the MM data and the need for a multiclass classification task while exploiting the structure of the MM data. In addition, we introduce a complete workflow for evaluating the feature selection and for decision-making. We apply the framework to selecting an optimum spectral and modal configuration for remote material classification using an experimental MM LiDAR system that provides reflectance, distance, and degree of linear polarization in 28 spectral channels of 10 nm width. For the experimental investigation, we use MM LiDAR data obtained in a controlled lab environment from thirty specimens of four material classes relevant for construction. Using all three modalities, we find a configuration with only 3 spectral channels that achieves a classification mean-F1 score of 100% within this small dataset. Similar classification performance can also be achieved with only two modalities when using more spectral channels. MGSVM FS improves the classification mean-F1 score by up to 25% as compared to random selection and outperforms two other commonly used filter and embedded feature selection methods, in this application example. The proposed group feature selection algorithm and decision-making are useful for MM LiDAR, providing a link between instrumental design, data acquisition, and data processing. However, they are also transferable to other application fields related to multiclass classification, regression, and knowledge discovery, with features structured in groups. The collected MM feature dataset, the MGSVM FS algorithm, and the evaluation pipeline are accessible online.11https://github.com/yuhan-yhyh/Dataset_Code_MGSVM-FS-MM-LiDAR.git.

Dimension Reduction With Prior Information for Knowledge Discovery.

This paper addresses the problem of mapping high-dimensional data to a low-dimensional space, in the presence of other known features. This problem is ubiquitous in science and engineering as there are often controllable/measurable features in most applications. To solve this problem, this paper proposes a broad class of methods, which is referred to as conditional multidimensional scaling (MDS). An algorithm for optimizing the objective function of conditional MDS is also developed. The convergence of this algorithm is proven under mild assumptions. Conditional MDS is illustrated with kinship terms, facial expressions, textile fabrics, car-brand perception, and cylinder machining examples. These examples demonstrate the advantages of conditional MDS over conventional dimension reduction in improving the estimation quality of the reduced-dimension space and simplifying visualization and knowledge discovery tasks. Computer codes for this work are available in the open-source cml R package.

Degree Descriptors and Graph Entropy Quantities of Zeolite ACO.

Cheminformatics is a fascinating emerging subfield of chemical graph theory that studies quantitative structure-activity and property relationships of molecules and, in turn, uses these to predict the physical and chemical properties, which are extremely useful in drug discovery and optimization. Knowledge discovery can be put to use in pharmaceutical data matching to help in finding promising lead compounds. Topological descriptors are numerical quantities corresponding to the chemical structures that are used in the study of these phenomena. This paper is concerned with developing the generalized analytical expression of topological descriptors for zeolite ACO structures with underlying degree and degree-sum parameters. To demonstrate improved discrimination power between the topological descriptors, we have further modified Shannon's entropy approach and used it to calculate the entropy measures of zeolite ACO structures.

Evaluation of Single/Multiple Joint Effects of Lipid Profiles on Hypertension, Diabetes Mellitus and Obesity Accompanying Coronary Artery Disease

Objective: Although cardiovascular diseases are among the most prominent causes of mortality/morbidity in the world, they are even more important together with comorbidities. This study aims to reveal the single/multiple effects of total cholesterol (TC), high-density lipoprotein-cholesterol (HDL-C), low-density lipoprotein-cholesterol (LDL-C), and triglyceride (TG) on hypertension (HT), type 2 diabetes mellitus (T2DM) and obesity accompanying coronary artery disease (CAD). Method: The data were retrospectively achieved from the records of CAD patients undergoing coronary bypass surgery at the Department of Cardiovascular Surgery, Medical Center, University. The medical knowledge discovery process (MKDP) was applied to the data concerning HT, DM, obesity, TC, HDL-C, LDL-C, and TG variables. Different methods were used to determine the optimal cut-off points of lipid profiles. Logistic regression analysis (LRA) was examined the single/multiple effects of lipid profiles on HT, T2DM, and obesity. Results: TC, LDL-C, TG, and HDL-C lipid profiles categorized according to the cut-off points determined in the current study were analyzed with LRA models. LDL-C (>117 mg/dL)*TC (>191 mg/dL)*HDL-C (>37.2 mg/dL) in HT and TC (>190 mg/dL)*TG (>197) mg/dL)*HDL-C (>36.3 mg/dL) in T2DM interaction terms had a moderate effect size. LDL-C (>115 mg/dL)*TG (>197 mg/dL)*HDL-C (>36.3 mg/dL) interaction terms in T2DM and TC (>192 mg/dL)*LDL-C (>117 mg/dL)*HDL-C (>36.8 mg/dL), TK (>192 mg/dL)*TG (>193 mg/dL)*HDL-C (>36.8 mg/dL) and LDL-C (>117 mg/dL)*TG (>193 mg/dL)*HDL-C (>36.8 mg/dL) interaction terms in obesity were reported as having a high effect size. Conclusion: In conclusion, it is recommended to use the approach that analyzes the cut-off points proposed in this study for lipid profiles in predicting HT, T2DM, and obesity.

Multi-agent modelling and analysis of the knowledge learning of a human-machine hybrid intelligent organization with human-machine trust

Machine learning (ML) technologies have changed the paradigm of knowledge discovery in organizations and transformed traditional organizational learning to human-machine hybrid intelligent organizational learning. However, the general distrust among humans towards knowledge derived from machine learning has hindered effective knowledge exchange between humans and machines, thereby compromising the efficiency of human-machine hybrid intelligent organizational learning. To explore this issue, we used multi-agent simulation to construct a knowledge learning model of a human-machine hybrid intelligent organization with human-machine trust. The simulation showed that whether human-machine trust has a positive effect on knowledge level depends on the initial input and the magnitude of the effect depends on the human learning propensity (exploration and exploitation). When humans reconfigure machine learning excessively, whether human-machine trust has a positive effect on the knowledge level depends on human learning propensity (exploration and exploitation). Maintaining appropriate human-machine trust in turbulent environments assists humans in integrating diverse knowledge to meet changing knowledge needs. Our study extends the human-machine hybrid intelligence organizational learning model by modeling human-machine trust. It will assist managers in effectively designing the most economical level of human-machine trust, thereby enhancing the efficiency of human-machine collaboration in human-machine hybrid intelligent organization.

Online Education Big Data Management and Mining Based on Intelligent Technology

The advent of online education platforms has revolutionized traditional learning paradigms, providing unprecedented access to educational resources worldwide. However, the vast amounts of data generated by these platforms present significant challenges in terms of effective management and utilization. This paper proposes a comprehensive approach to address these challenges through the integration of big data management and mining techniques, supported by intelligent technologies. By harnessing the power of advanced data management strategies and cutting-edge machine learning algorithms, our approach aims to unlock valuable insights from online education data, thereby enhancing the learning experience and improving educational results. This paper presents a systematic framework for online education big data management and mining, encompassing data collection, storage, preprocessing, analysis, and visualization. Furthermore, we discuss the role of intelligent technologies such as artificial intelligence, natural language processing, and predictive analytics in optimizing the process of data mining and knowledge discovery. Through case studies and experimental evaluations, we demonstrate the effectiveness and applicability of our approach in real-world online education scenarios. Our research contributes to the growing body of knowledge in the field of educational data mining and underscores the potential of intelligent technology in shaping the future of online learning.

Discovering Links between Geospatial Data Sources in the Web of Data: The Open Geospatial Engine Approach

The Web of Data has been fueled significantly by geospatial data over the last few years. In the current link discovery frameworks, there is still a lack of robust support for finding geospatial-aware links between geospatial data sources in the Web of Data. They are also limited in efficient association capabilities for large-scale datasets. This paper extends the data integration capability based on the spatial metrics in the open geospatial engine OGE. These metrics include topological relationships and spatial matching between geospatial entities within multiple geospatial data sources. Thus, the tool can be employed by data publishers to set geospatial-aware links to facilitate geospatial data and knowledge discovery in the Web of Data. Several geospatial data sources are used to demonstrate the usability and effectiveness of the approach and tool implementation.

Survey on A Smart Medical System on Drug Analysis using ML Algorithms

Online health communities continue to offer huge variety of medical information useful for medical practitioners, system administrators and patients alike. In this system we collect real time health posts from reputed websites, where patients express their views, including their experiences and side-effects on drugs used by them. We propose to perform Summarization of user posts per drug, and come out with useful conclusions for medical fraternity as well as patient community at a glance. Further, we propose to classify the users based on their ‘emotional state of mind’. Also, we shall perform knowledge discovery from user posts, whereby useful ‘patterns’ about the triad ‘drugs-symptoms-medicine’ is done by Association Rule Mining. Association rule mining is a popular and widely-known machine learning task. It is used to find out interesting relations between variables in large database. Rules generated by association have two disjoint set of items having form LHS (Left Hand Side) => RHS (Right Hand Side). The rule says that RHS is likely to occur whenever the LHS set occurs.