Case Study Dataset Research Articles

Filling the gaps in soil data: A multi-model framework for addressing data gaps using pedotransfer functions and machine-learning with uncertainty estimates to estimate bulk density

Legacy soil datasets are a valuable resource and should be used to the greatest extent possible. However, such datasets may be incomplete, and lack observations for every attribute, as the dataset may be compiled from multiple studies. To use these datasets in soil mapping and modeling work, it is useful to fill the gaps in the dataset with estimated values. Machine learning is an approach that can provide estimates with high accuracy. In this study, the machine learner Random Forest (RF) was used to estimate bulk density values in an existing dataset from the province of British Columbia (BC), Canada, which was used as a case study dataset. As the dataset had missing observations across all attributes, multiple models needed to be generated and tested to determine the accuracy of the estimated values produced. A total of 512 models were tested using RF, which were then ranked based on the concordance correlation coefficient (CCC) of their estimates; the CCC of all models ranged from 0.51 to 0.92. The estimates of 27 of these models were then used to fill the missing observations in the dataset; the accuracy of these models ranged from a CCC of 0.63 to 0.92. Further, uncertainty estimates for the predictions were generated using quantile regression, which was coupled with the RF approach. Each model tested therefore had an accuracy measurement and an uncertainty estimate. This approach, of using multiple models developed in RF, can be applied to other legacy soil datasets with inconsistently missing values to produce estimates which can fill the missing observations, and produce uncertainty estimates for those estimates.

Self-X heterogeneous attributed graph embedding-based product configuration framework for cognitive mass personalization

Cognitive mass personalization (CMP) is a promising manufacturing paradigm; equipped with cognitive capabilities like reasoning, CMP satisfies changeable needs via configuring personalized products at scale. In CMP, knowledge graphs (KGs) are exploited by smart product-service systems (SPSS) to support cognitive configuration/reconfiguration processes. However, the extant KG-enabled SPSSs are built upon fixed configurations and hybrid frameworks due to lacking a graph embedding (GE) model to render cognitive configuration decisions. In fact, GE is scarcely used in SPSS configuration, because it is not only compromised by the heterogeneity of KGs entailed by content-related specifications and complex structures but also influenced by the feature randomness and feature drift problems, which are triggered by accumulative errors and inconsistent objectives due to noisy assignments and different configuration tasks, separately. To address these limitations, a Self-X Heterogeneous Attributed Graph Embedding (SXHAGE) model is proposed in a Self-X architecture, which includes 1) self-attention graph attention networks, 2) a self-adaptive autoencoder, and 3) self-optimizing training objectives, to present heterogeneous data through jointly optimizing heterogeneous attributed entities and relations. A systematic SXHAGE-based configuration framework, in which product family design and configuration recommending are enabled by graph clustering and link prediction, is developed as a continuous updating loop to proactively configure personalized products. A real-world case study, i.e., configure personalized electric clippers via a web-based sustainable configuration platform, is performed to validate the applicability of the proposed framework in the CMP context. Moreover, extensive experiments on the case study dataset demonstrate the superiority of SXHAGE over the state-of-the-art algorithms, e.g., surpassing Deep Neighbor-Aware Embedding (DNENC) by 18 % in F1-score for graph clustering and by 5 % in ROC-AUC for link prediction.

Opportunities offered by latent-based multiblock strategies to integrate biomarkers of chemical exposure and biomarkers of effect in environmental health studies

Modern environmental epidemiology benefits from a new generation of technologies that enable comprehensive profiling of biomarkers, including environmental chemical exposure and omic datasets. The integration and analysis of large and structured datasets to identify functional associations is constrained by computational challenges that cannot be overcome using conventional regression methods. Some extensions of Partial Least Squares (PLS) regression have been developed to efficently integrate multiple datasets, including Multiblock PLS (MB-PLS) and Sequential and Orthogonalized PLS; however, these approaches remain seldom applied in environmental epidemiology. To address that research gap, this study aimed to assess and compare the applicability of PLS-based multiblock models in an observational case study, where biomarkers of exposure to environmental chemicals and endogenous biomarkers of effect were simultaneously integrated to highlight biological links related to a health outcome. The methods were compared with and without sparsity coupling two metrics to support the variable selection: Variable Importance in Projection (VIP) and Selectivity Ratio (SR). The framework was applied to a case-study dataset mimicking the structure of 36 environmental exposure biomarkers (E-block), 61 inflammation biomarkers (M-block), and their relationships with the gestational age at delivery of 161 mother-infant pairs. The results showed an overall consistency in the selected variables across models, although some specific selection patterns were identified. The block-scaled concatenation-based approaches (e.g. MB-PLS) tended to select more variables from the E-block, while these methods were unable to identify certain variables in the M-block. Overall, the number of variables selected using the SR criterion was higher than using the VIP criterion, with lower predictive performances. The multiblock models coupled to VIP, appeared to be the methods of choice for identifying relevant variables with similar statistical performances. Overall, the use of multiblock PLS-based methods appears to be a good strategy to efficiently support the variable selection process in modern environmental epidemiology.

Assessing and Improving Automated Viewpoint Planning for Static Laser Scanning Using Optimization Methods

Abstract. The preparation of laser scanning missions is important for efficiency and data quality. Furthermore, it is a prerequisite for automated data acquisition, which has numerous applications in the built environment, including autonomous inspections and monitoring of construction progress and quality criteria. The scene and potential scanning locations can be discretized to facilitate the analysis of visibility and quality aspects. The remaining mathematical problem to generate an economic scan strategy is the Viewpoint Planning Problem (VPP), which asks for a minimum number of scanning locations within the given scene to cover the scene under pre-defined requirements. Solutions for this problem are most commonly found using heuristics. While these efficient methods scale well, they cannot generally return globally optimal solutions. This paper investigates the VPP based on a problem description that considers quality-constrained visibility in 3D scenes and suitable overlaps between individual viewpoints for targetless registration of acquired point clouds. The methodology includes the introduction of a preprocessing method designed to simplify the input data without losing information about the problem. The paper details various solution methods for the VPP, encompassing conventional heuristics and a mixed-integer linear programming formulation, which is solved using Benders decomposition. Experiments are carried out on two case study datasets, varying in specifications and sizes, to evaluate these methods. The results show the actual quality of the obtained solutions and their deviation from optimality (in terms of the estimated optimality gap) for instances where exact solutions can not be achieved.

Factoring Building Refurbishment and Climatic Effect into Heat Demand Assessments and Forecasts: Case Study and Open Datasets for Germany

Reducing the heat demand of existing buildings is an essential prerequisite for achieving a greenhouse gas-neutral energy supply. Numerous studies and open-source tools deal with heat demand mapping. It is not uncommon that estimated heat demands deviate from real heat consumption, so existing approaches should be improved by including in-depth building information. Some tools have recognised this problem and offer built-in functions for factoring various parameters into their assessments. Nevertheless, the necessary information is usually missing and should be obtained first. In this paper, we analyse the impact of thermal refurbishment and climate on building heat demand; hence, generate public datasets with corresponding key figures for each building type in different efficiency states and years. Accounting for already performed refurbishments in methodologies for assessing the actual state heat demand for cities will result in a reduction of at least 8% up to more than 21%, depending on whether conventional or passive house components were installed. As a result of climatic differences within Germany, a building’s heat demand can be up to 39% higher or up to 21% lower than the heat demand of an identical building in the reference climate of Germany. By further developing the approaches of the tools Hotmaps and Heat Cadastre Hamburg, we could improve the estimated heat demand of Hamburg to a value approximating the real consumption.

3D Deep Learning for Segmentation of Masonry Tunnel Joints

Historic masonry lined tunnels form a large proportion of the world’s railway tunnel stock. However, as many of these date from the second industrial revolution over 150 years ago, they typically contain large areas of structural deterioration. Masonry spalling is a pervasive form of surface damage and its severity, defined by the depth of spalling, is indicative of a tunnel’s structural condition. Current tunnel spalling condition assessment procedures are largely manual, so the extent of spalling observed on many historic tunnels presents a challenge for timely and cost-effective assessment. Automated machine learning based workflows have shown substantial potential for automating and reducing the subjectivity of the assessment process. A key step in these workflows involves segmenting the location of masonry joints from 3D point clouds of the tunnel lining in order to isolate masonry block locations. The most prevalent method is to unroll 3D tunnel lining data into 2D before applying U-Net based convolutional neural networks to segment joint locations. However, recent developments in 3D point based neural networks enable semantic segmentation to be conducted directly on the input point cloud. Point based methods such as KPCONV provide 3D feature characterization and enable semantic segmentation of a wider variety of tunnel geometries by default, since a handcrafted unrolling strategy is not required. This study conducted a performance comparison between 3D KPCONV, 2D U-Net, and XGBOOST feature classifier based joint identification techniques. In order to effectively compare a real-world use-case where time consuming manual data labelling should be minimized, the methods were only trained on a 9.94m section of tunnel. It was found that a 2D U-Net combined with tunnel unrolling workflow could be more successfully trained on the case study dataset and due to effective transfer learning, achieved superior performance to KPCONV and XGBOOST methods.

Optimizing the Capacitated Vehicle Routing Problem at PQR Company: A Genetic Algorithm and Grey Wolf Optimizer Approach

Product distribution for companies in the industrial sector is an important issue as it is necessary to increase customer satisfaction and reduce costs. In this study, Nondominated-Sorting Genetic Algorithm II is used to solve Capacitated Vehicle Routing Problem in a case study dataset from the biggest fertilizer company in Indonesia. NSGA-II algorithm reduced the need for vehicles in product distribution with an advantage of 44.7%, while GWO algorithm yielded better results with an increase of time of 16.9%.

Prediction of the severity of exceeding design traffic loads on highway bridges

Being a driver of failure consequences, forecasting the severity of events where design traffic load limits on bridges have been exceeded (DLEEs) is fundamental for road safety. Previous research has focused on estimating failure consequences by direct and indirect cost metrics. Only recently has research assessed severity unconventionally, in which the type of DLEEs was predicted by applying econometric models through Binomial Logistic Regression (BLR). Since machine learning models using Artificial Neural Networks (ANN) have not yet been explored, this study will enhance the literature as follows. First, two different ‘severity’ models were set up as a function of bridge-side, temporal-context, and traffic load hazard variables. Whilst the former relied on a BLR, the latter used an ANN. Second, the performance of these models was assessed using confusion matrixes, some performance indicators, and a cross-entropy parameter. Raw Weigh-In-Motion data on 7.4 M+ individual vehicle transits on a bridge along a primary roadway in Brescia (Italy) were processed. Although a similarly strong performance was achieved for BLR and ANN, the results indicated that ANN was able to predict severity records with a higher level of confidence than BLR on the case study dataset, with the cross-entropy of the ANN less than one third of that of the BLR. These analyses can support road authority traffic management to safeguard bridges from traffic load hazards. Finally, this study recommends future developments, such as considering the structural effects of traffic loads in the modelling, prioritizing traffic management actions among bridges at network level, and exploring the impact of ANN models in risk assessment.

Hybrid self-supervised learning-based architecture for construction progress monitoring

Automating construction progress monitoring is essential for the timely completion of projects. Computer vision-based construction progress monitoring (CV-CPM) stands out as a promising technology, leveraging 3D point clouds as inputs. Both heuristics-based and learning-based approaches have been explored for identifying building elements. Nevertheless, prevailing supervised methods require project-specific manual labeling, rendering them non-generalizable. This paper introduces a hybrid self-supervised learning architecture named ConPro-NET, which integrates heuristics with learning-based techniques for element identification from construction point clouds. The proposed approach conducts unsupervised segmentation through a region-growing-based method, followed by feature extraction using contrastive learning. Contrastive learning matches object pairs to learn their features, which are refined and augmented with handcrafted features based on local geometric and visual properties to form the hybrid feature vector. The model demonstrates an overall classification accuracy of 80.86% on the S3DIS dataset and 80.95% on a case study dataset, encompassing the classification of six object classes.

Multimodal Asynchronous Kalman Filter for monitoring unstable rock slopes

Unstable rock slopes pose a hazard to inhabitants and infrastructure in their vicinity, necessitating advanced monitoring methodologies for timely risk assessment and mitigation. Recent geotechnical monitoring techniques often rely on sensor data fusion to enhance forecasting for imminent failures. Our investigation extends beyond a single sensor type to data fusion for heterogeneous sensor networks using a Multimodal Asynchronous Kalman Filter. We illustrate the application of the proposed method on a case study data set consisting of data from an on-site sensor network enriched by remote sensing data. Employing a Multimodal Asynchronous Kalman Filter, we capitalise on the distinct resolutions inherent in each sensor input. The outcome was a combined dataset with a high spatiotemporal resolution. Our approach facilitates the estimation of essential physical attributes for monitored objects, encompassing translation, rotation, velocities and accelerations. The case study site was an unstable rock section of ca. 50.000 m 3 in Aurland, Norway, which collapsed as a multi-stage failure in July 2023. Our method can be transposed to various sites with distinct sensor networks, enhancing state estimations for objects on unstable rock slopes. These estimations can significantly improve applications such as risk assessment and robust early-warning systems, enhancing predictions of critical failure points.

COCKPIT CREW SAFETY PERFORMANCE PREDICTION BASED ON THE INTEGRATED MACHINE LEARNING MULTI-CLASS CLASSIFICATION MODELS AND MARKOV CHAIN

The main tool of cockpit crew performance evaluation is the recorded flight data used for flight operations safety improvement since all certified airlines require implementation of a safety and quality management system. The safety performance of a flight has been a challenging issue in the aviation industry and plays an important role to acquire competitive benefits. In this study, an integrated multi-class classification machine learning models and Markov chain were developed for cockpit crew performance evaluation during their flights. At the outset, the main features related to a flight are identified based on the literature review, flight operations expert’s statements, and the case study dataset (as numerical example). Afterwards, the flights’ performance is evaluated as a target column based on four multi-class classification models (Decision Tree, Support Vector Machine, Neural Network, and Random Forest). The results showed that the random forest classifier has the greatest value in all evaluation metrics (i.e., accuracy = 0.90, precision = 0.91, recall = 0.97, and F1-score = 0.93). Therefore, this model can be used by the airline companies to predict flight crew performance before the flight in order to prevent or decrease flight safety risks.

A framework for recalibrating pedotransfer functions using nonlinear least squares and estimating uncertainty using quantile regression

Pedotransfer functions (PTFs) have been developed for many regions to estimate values missing from soil profile databases. However, globally there are many areas without existing PTFs, and it is not advisable to use PTFs outside their domain of development due to poor performance. Further, developed PTFs often lack accompanying uncertainty estimations. To address these issues, a framework is proposed where existing equation-based PTFs are recalibrated using a nonlinear least squares (NLS) approach and validated on two regions of Canada; this process is coupled with the use of quantile regression (QR) to generate uncertainty estimates. Many PTFs have been developed to predict soil bulk density, so this variable is used as a case study to evaluate the outcome of recalibration. New coefficients are generated for existing soil bulk density PTFs, and the performance of these PTFs is validated using three case study datasets, one from the Ottawa region of Ontario and two from the province of British Columbia, Canada. The improvement of the performance of the recalibrated PTFs is evaluated using root mean square error (RMSE) and the concordance correlation coefficient (CCC). Uncertainty estimates produced using QR are communicated through the mean prediction interval (MPI) and prediction interval coverage probability (PICP) graphs. This framework produces dataset-specific PTFs with improved accuracy and minimized uncertainty, and the method can be applied to other regional datasets to improve the estimations of existing PTF model forms. The methods are most successful with large datasets and PTFs with fewer variables and minimal transformations; further, PTFs with organic carbon (OC) as one of or the sole input variable resulted in the highest accuracy.

At the Intersections of Gender Inequality and State Fragility in Africa

ABSTRACT Intersectionality has become a widely used theoretical lens through which scholars examine women’s political and economic participation. Intersectional frameworks analyze the ways in which formal state structures produce gender inequalities. It is precisely this conceptual and empirical strength that make a theory originally rooted in the experiences of Black women in the United States, applicable to other groups of women in a range of national contexts. Extensive debates surround the generalizability of intersectional theory. Using my work on gender inequality as a predictor of state fragility in the African region, this piece addresses these questions both conceptually and methodologically. My larger project is a cross-national study; however, I will use original country case study datasets from women’s local civil society organizations in Nigeria and Ghana to illustrate the relationships between institutionalized inequalities and the mobilization efforts of different groups of women. First, I begin by defining intersectionality. Next, I combine African feminists and African Muslim feminists’ theoretical contributions which extend and expand intersectionality. This piece contributes to conversations about the ways in which intersectionality can be applied to other groups of Black women outside of the United States. Third, I demonstrate how intersectionality is used to capture the range of priorities and strategies activists used to define and promote gender equality within formal state structures.

Cyanobacterial toxins and components induce expression of pro-inflammatory cytokines/chemokines and secretion of soluble cell receptors in a 3D skin cell model

Abstract Exposure to cyanobacterial toxins has been linked to several diseases and disorders including skin rashes and damage to the liver and kidneys. Previous research has shown that Microcystin-LR, the most common and toxic microcystin in fresh water, induces the NLRP3 inflammasome in response to administration to mice by oral gavage. In this study, we used a Reconstructed Human Epidermis to investigate immune system responses to cyanobacterial exposure. This 3D tissue model consisting of normal, human-derived epidermal keratinocytes was exposed to Spirulina, anatoxin-contaminated lake water, and phycocyanin. The cell supernatant was probed with a multiplex of 38 cytokines/chemokines and 14 soluble receptors to elucidate the immunological response. Our results revealed that: while most proteins were down-regulated, a number were up-regulated; the expression of many proteins were highly correlated and clustered together; and across the case study datasets, multiple cytokines/chemokines (G-CSF, GRO, IL-6, IL-8, and MCP-1) and soluble cell receptors (sCD30, sEGFR, sTNFRII and sVEGFR1, sVEGFR2 and sVEGFR3) were highly expressed when exposed to the toxins. Our findings correspond with preliminarily histological results showing tissue damage when the skin cells were exposed to the cyanobacterial components. This work shows great promise in the ability to examine the immune response to toxic exposures and aids in the development of techniques useful for studying the impact of harmful algal blooms on public health. Future studies will focus on mapping the immune pathway in response to harmful algal bloom exposure and studying the roles of each of the expressed cytokines and soluble cell receptors in the inflammatory response. This work is supported by the United States Environmental Protection Agency.

The role of calcite mineral elastic moduli in carbonate rock physics

Rock-physics models for carbonate reservoirs assume that the mineral elastic moduli are known variables. A review of publications reveals a range of values for calcite that are out of date and misleading. We present a robust compilation for future investigations. We subsequently discuss the application of calcite elastic moduli for rock-physics modeling and interpretation of wireline data through a case study data set from an offshore Canada carbonate reservoir. The data set exhibits an offset between the zero-porosity intercept and the calcite elastic moduli values. Our experience indicates that this phenomenon is present in many wireline data sets from carbonate reservoirs around the world. We demonstrate that the data can be reconciled to the mineral elastic moduli through the interpretation of microcracks in the formation (defined by a crack density of 0.06). Understanding the microcrack effect in relatively low-porosity formations is important for the correct calibration of pore microstructure parameters and for fluid-substitution calculations. Results in the case study data set show a relatively high sensitivity to changes in fluid saturation. The sensitivity can be reduced through the use of effective mineral elastic moduli that are derived from the data. We justify the effective mineral elastic moduli as a representation of the mineral moduli plus microcracks. The effective mineral elastic moduli are proposed as a relatively simple method to constrain the fluid substitution calculations in low-porosity formations where microcracks are present.

General Words Representation Method for Modern Language Model

This paper proposes a new word representation method emphasizes general words over specific words. The main motivation for developing this method is to address the weighting bias in modern Language Models (LMs). Based on the Transformer architecture, contemporary LMs tend to naturally emphasize specific words through the Attention mechanism to capture the key semantic concepts in a given text. As a result, general words, including question words are often neglected by LMs, leading to a biased word significance representation (where specific words have heightened weight, while general words have reduced weights). This paper presents a case study, where general words' semantics are as important as specific words' semantics, specifically in the abstractive answer area within the Natural Language Processing (NLP) Question Answering (QA) domain. Based on the selected case study datasets, two experiments are designed to test the hypothesis that "the significance of general words is highly correlated with its Term Frequency (TF) percentage across various document scales”. The results from these experiments support this hypothesis, justifying the proposed intention of the method to emphasize general words over specific words in any corpus size. The output of the proposed method is a list of token (word)-weight pairs. These generated weights can be used to leverage the significance of general words over specific words in suitable NLP tasks. An example of such task is the question classification process (classifying question text whether it expects factual or abstractive answer). In this context, general words, particularly the question words are more semantically significant than the specific words. This is because the same specific words in different questions might require different answers based on their question words (e.g. "How many items are on sale?" and "What items are on sale?" questions). By employing the general weight values produced by this method, the weightage of question and specific words can be heightened, making it easier for the classification system to differentiate between these questions. Additionally, the token (word)-weight pair list is made available online at https://www.kaggle.com/datasets/saliimiabbas/genwords-weight.

Microservice Security Metrics for Secure Communication, Identity Management, and Observability

Microservice architectures are increasingly being used to develop application systems. Despite many guidelines and best practices being published, architecting microservice systems for security is challenging. Reasons are the size and complexity of microservice systems, their polyglot nature, and the demand for the continuous evolution of these systems. In this context, to manually validate that security architecture tactics are employed as intended throughout the system is a time-consuming and error-prone task. In this article, we present an approach to avoid such manual validation before each continuous evolution step in a microservice system, which we demonstrate using three widely used categories of security tactics: secure communication, identity management, and observability. Our approach is based on a review of existing security guidelines, the gray literature, and the scientific literature, from which we derived Architectural Design Decisions (ADDs) with the found security tactics as decision options. In our approach, we propose novel detectors to detect these decision options automatically and formally defined metrics to measure the conformance of a system to the different options of the ADDs. We apply the approach to a case study data set of 10 open source microservice systems, plus another 20 variants of these systems, for which we manually inspected the source code for security tactics. We demonstrate and assess the validity and appropriateness of our metrics by performing an assessment of their conformance to the ADDs in our systems’ dataset through statistical methods.

Tri-clustering–based exploration of spatio-temporal heterogeneity of six criteria air pollutants and their relationships in China

Severe air pollution in China has become a challenging issue because of its adverse health effects. The distribution of air pollutants and their relationships exhibits spatio-temporal heterogeneity due to influences by meteorological and socioeconomic factors. Investigation of spatio-temporal variations of criteria air pollutants and their relationships, thus, helps understand the current status and further assist pollution prevention and control. Even though many studies have been conducted, relationships among pollutants are non-linear due to complicated chemical reactions and were difficult to model by linear analyses in previous studies. Here, we presented a tri-clustering–based method, the Bregman cuboid average tri-clustering algorithm with I-divergence (BCAT_I), to explore spatio-temporal heterogeneity of air pollutants and their relationships in China. Concentrations of PM2.5, PM10, CO, SO2, NO2, and O3 in 31 provincial cities in 2021 were used as the case study dataset. Results showed that air pollutants except O3 exhibited spatial and seasonal variations, i.e., low in summer in southern cities and high in winter in northern cities. Variations of PMs were more similar to those of CO than other pollutants in southern cities in 2021. Results also found that relationships among these air pollutants were heterogeneous in different regions and time periods in China. Moreover, with the increasing level of NO2 from summer to winter in northern cities, concentrations of O3 first decreased and then increased. This is because the response of O3 to NO2 was negative at the low pollution level due to the titration reaction, which, however, changed to positive when concentrations of NO2 became high.

Application of Humboldt Extension to Real-world Cases

Access to high-quality ecological data is pivotal to assessing and modeling biodiversity and its change through space and time. Inventory data (i.e., recording multiple species at specific places and times) are particularly relevant to monitoring species distributions and abundance, but their reliability for use in downstream models depends on reporting the methodology implemented and associated sampling effort and completeness. This information about the inventory processes is often either not reported or described in an unstructured manner, greatly limiting potential re-use for larger-scale analyses. In order to support the reuse of inventories and to assure better standardization of newly collected data, we developed a framework to standardize inventory data reporting that is general enough for broad use. Guralnick et al. (2018) introduced the Humboldt Core as a proof of concept. In 2021, the TDWG Humboldt Core Task Group was established to review how to best integrate the terms proposed in the original publication with existing standards and implementation schemas. In the context of sharing data using the Darwin Core standard (DwC), different types of inventories can be represented as Events with different nesting levels. Therefore, it was deemed appropriate to develop an extension to DwC that allows capturing the details of the inventory process. The Task Group members revised all original terms, reformulated definitions, and discarded or added new terms where needed. We are developing a user guide and reaching out to the larger biodiversity community to test the Humboldt Extension with real-world case study datasets using a test instance of the GBIF Integrated Publishing Toolkit (IPT). In this presentation, we will review the development process, give an overview of how the Humboldt Extension can be used to report key information on the inventory process, and provide example cases. After testing with real world cases, our next step will be to seek ratification of Humboldt as a Darwin Core Event extension following the Vocabulary Maintenance Standard. We expect that this will help to overcome a key bottleneck in the sharing of critically important ecological data, enhancing data discoverability, interoperability and re-use while lowering reporting burden.

Parameterisation of domain knowledge for rapid and iterative prototyping of knowledge-based systems

In critical infrastructure applications, timely and consistent fault detection and diagnosis is an increasingly important operational process, especially in the energy sector where safety is of the utmost importance. To realise this, engineers have to manually analyse data acquired from several assets using predefined diagnostic processes, but this is a time-consuming process requiring significant amounts of specialist expert knowledge. Data-driven approaches to support fault detection and diagnosis, and other similar problems, can produce accurate results comparable to what the engineers can achieve in a fraction of the time. However, the majority of these data-driven techniques are black box techniques and lack explainability which is often necessary for explaining decisions about critical assets in the power generation industry. Knowledge-based systems, such as rule-based expert systems have been shown to provide not only accurate decisions but also the explanation and reasoning behind these decisions in some related applications. However, there is a significant time cost associated with the development of knowledge-based systems, and in particular with the knowledge elicitation process, where the domain expert’s knowledge is formalised and is encoded into the system. This challenge is commonly referred to as the knowledge elicitation bottleneck.In this paper, we present a novel approach to performing the knowledge elicitation using a set of symbolic primitives (rise, fall, fluctuate, and stable) to parameterise typical time-series condition monitoring data. The knowledge is represented by using a common language that can easily be communicated with (and from) the domain experts. This allows for the quick and accurate elicitation of the domain experts knowledge, but also the formalisation and implementation of the knowledge into a rapidly produced diagnostic system. Further to this, due to the parametrisation of the knowledge, it is possible to iteratively improve the knowledge base by updating these parameters based on new unseen data. This approach was applied to the Tennessee Eastman dataset, which is simulated data of a real-world industrial process. It was found that by using this approach it was possible to accurately and quickly capture the knowledge required to detect several faults within the case study dataset, but also provided fully explained reasons why each fault was detected by relating the explanations to the symbolic primitives previously defined.