Domain Experts Research Articles

Methodology for the selection of learning measures for the competence development of assembly workers

ABSTRACT Mass personalization and shorter product life cycles complicate the assembly of manufacturing companies. To handle the complexity, a high number of employees execute varying assembly tasks. Their work is characterized by learning new tasks frequently to produce different variants. To achieve good learning results in a short amount of time, a suitable individual assembly workers’ competence development process is crucial. Therefore, this publication shows the development of a user methodology to plan the competence development process focusing on selecting learning measures that fit both the work situation and learning employees. The presented user methodology is based on a standardized description and selection procedure for learning measures by using results of a Domain Mapping Matrix, Delphi study, and expert interviews. The publication contributes to improved competence development to support the strategic empowerment of the workforce and to increase the flexibility in manual assembly.

Development and expert inspections of the user interface for a primary care decision support system

BackgroundGeneral practitioners play a unique key role in diagnosing patients with unclear diseases. Decision support systems in primary care can assist with diagnosis provided that they are efficient and user-friendly. ObjectivesThe objective of this study is to develop a high-fidelity prototype of the user interface of a clinical decision support system for primary care, particularly for diagnosis support in unclear diseases, using expert inspections at an early stage of development to ensure a high level of usability. MethodsThe user interface prototype was iteratively developed based on previous research, design principles, and usability guidelines. During the development phase, three usability inspections were carried out by all experts at four-week intervals as heuristic walkthrough. Each inspection consisted of two parts: 1) Task-based inspection 2) Free exploration and evaluation based on usability heuristics. Five domain experts assessed the current status of development.The tasks in the inspections were based on the task model derived in the requirements analysis: perform data entry, review and discuss results, schedule further diagnostics, refer to specialists and close case. ResultsAs a result of this iterative development, a high-fidelity, clickable user interface prototype was created that is able to fulfil all six tasks of our task model. The usability inspections identified a total of 196 usability issues (for all 3 inspections; Part 1: 90 issues, Part 2: 106 issues), ranging in severity from minor to severe. These served the continuous adjustment and improvement of the prototype. All main tasks were completed successfully despite these problems. ConclusionUsability inspections through heuristic walkthroughs can support and optimise the development of a user-centred decision support system in order to ensure its suitability for performing relevant tasks.

Efficient detection of data entry errors in large-scale public health surveys: an unsupervised machine learning approach

Data entry errors in large-scale public health surveys can undermine the effectiveness of data-driven interventions. Therefore, identifying these data entry errors is crucial for public health experts. In large-scale public health surveys, manually verifying the accuracy of every data point by domain experts is nearly impossible. This study evaluates unsupervised machine learning algorithms for detecting these errors, focusing on the 'weight' parameter in the Annual Health Survey (AHS) dataset. The AHS, conducted by the Ministry of Health and Family Welfare, Government of India, in collaboration with the Registrar General of India, is a large-scale, stratified, household-level survey targeting maternal and child health across nine states in India. The dataset is freely available on the Open Government Data (OGD) Platform of India for public health research. In this study, five algorithms—DBSCAN, K-Means, Gaussian Mixture Model (GMM), Isolation Forest (IF), and One-Class SVM (1C-SVM) were applied to detect erroneous data entries. The evaluation process involved comprehensive preprocessing and feature engineering to optimize detection capabilities. Performance metrics such as precision, recall, accuracy, false anomaly, and missed anomaly rates were used to assess each algorithm. Among these, DBSCAN demonstrated superior performance, achieving a recall of 94.7% and a precision of 81.9%, making it highly effective for this task. The findings underscore the potential of unsupervised machine learning in automating the detection of data entry errors, thereby improving the integrity of public health data. This research contributes to the advancement of precision public health, supporting more accurate and reliable evidence-based decision-making and policy formulation.

Towards multimodal visualization of esophageal motility: fusion of manometry, impedance, and videofluoroscopic image sequences.

Dysphagia is the inability or difficulty to swallow normally. Standard procedures for diagnosing the exact disease are, among others, X-ray videofluoroscopy, manometry and impedance examinations, usually performed consecutively. In order to gain more insights, ongoing research is aiming to collect these different modalities at the same time, with the goal to present them in a joint visualization. One idea to create a combined view is the projection of the manometry and impedance values onto the right location in the X-ray images. This requires to identify the exact sensor locations in the images. This work gives an overview of the challenges associated with the sensor detection task and proposes a robust approach to detect the sensors in X-ray image sequences, ultimately allowing to project the manometry and impedance values onto the right location in the images. The developed sensor detection approach is evaluated on a total of 14 sequences from different patients, achieving a F1-score of 86.36%. To demonstrate the robustness of the approach, another study is performed by adding different levels of noise to the images, with the performance of our sensor detection method only slightly decreasing in these scenarios. This robust sensor detection provides the basis to accurately project manometry and impedance values onto the images, allowing to create a multimodal visualization of the swallow process. The resulting visualizations are evaluated qualitatively by domain experts, indicating a great benefit of this proposed fused visualization approach. Using our preprocessing and sensor detection method, we show that the sensor detection task can be successfully approached with high accuracy. This allows to create a novel, multimodal visualization of esophageal motility, helping to provide more insights into swallow disorders of patients.

A Conceptual Framework for the Development of Effective Serious Games for Learning

Currently, the interest in using serious games as a tool for learning and teaching in traditional educational processes has increased significantly. Therefore, serious games for learning are gaining increasing attention from researchers and domain experts (educators), as they are both looking for methods and tools to improve the quality of learning. Even though there are many existing design frameworks, models, and methodologies that offer valuable insights into the possibilities and limitations of serious games for learning, they focus mostly on high-level aspects and requirements of these games. Therefore, they do not fully help in understanding how such aspects can be concretely fulfilled. In this research, we investigate, characterize, and categorize the functional requirements and aspects needed for developing effective serious games for learning. This investigation aims to construct a conceptual framework to fill the gap in the current design frameworks. The proposed conceptual framework is used to understand the game´s structure and behavior with a focus on both aspects of serious games (educational and entertainment aspects), in other words, providing a way to think about the relationships between serious game components and the learning objectives of the game. The main contributions of the proposed conceptual framework are to facilitate and support the design and development process of these games as well as to enhance the collaborative work within a multidisciplinary development team. Finally, to show the feasibility and applicability of the conceptual framework, a practical example is presented to demonstrate the use of this framework. Furthermore, we conducted an evaluation process for implementing the conceptual model. The evaluation shows promising results in helping participants, particularly those with gaming experience, to understand and identify the roles of each component in the game and recognize the game's learning objectives. This will eventually lead to design and develop effective learning games in a flexible and easy-to-use way.

Knowledge, attitudes, and practices of paediatric medical officers and registrars on the developmental origins of health and disease in a tertiary women’s and children’s hospital

BackgroundTo mitigate the growing burden of non-communicable diseases, doctors training to become paediatricians should be equipped with concepts and knowledge regarding Developmental Origins of Health and Disease (DOHaD).MethodsWe assessed the knowledge, attitudes, and practices (KAP) of medical officers, resident physicians, as well as junior and senior residents practising in the paediatric department of a tertiary women’s and children’s hospital. This was done through a cross-sectional online survey, with questions developed after focused group discussions with domain experts, and responses based on a 5-point Likert scale.ResultsA total of 95 physicians met the inclusion criteria, grouped into Medical Officers (MOs) and Registrars (REGs), and we received a 100% response rate. Results showed that few physicians (n = 22, 23.2%) knew the term DOHaD, and majority rated their colleagues to be inadequately informed (n = 84, 88.4%). Among the physicians, one third (n = 32, 33.7%) were not confident in their ability to counsel patients about initiating healthy feeding practices to prevent future metabolic diseases in their children. However, there was a readiness to be better equipped with DOHaD principles and knowledge, and 95.8% (n = 91) strongly acknowledged the physician’s responsibility to optimise early life determinants of cardiometabolic health.ConclusionIn conclusion, the findings suggest a poor translation of DOHaD concepts, indicating that bridging the gap between DOHaD research knowledge and clinical application represents an unmet need. These principles should be inculcated early in the professional training of all healthcare providers.

Problem-driven visualization design of health and pollution big data

We present the design of a big data visualization application aimed at investigating the potential relationships between air pollution and perinatal health. We integrated data from singleton pregnancies in Brazil over a seven-year period and records of fine particulate matter (PM2.5) levels. Our methodology combines Design by Immersion and co-design, engaging specialists from various domains in problem-driven visualization design. The interactive visualization allows exploratory queries and comparative analyses based on medical birth certificate data restructured according to estimated conception dates. The collaboration of various domain experts was essential for leveraging complex data for an informed decision-making visualization.

Similar Data Points Identification with LLM: A Human-in-the-Loop Strategy Using Summarization and Hidden State Insights

This study introduces a simple yet effective method for identifying similar data points across non-free text domains, such as tabular and image data, using Large Language Models (LLMs). Our two-step approach involves data point summarization and hidden state extraction. Initially, data is condensed via summarization using an LLM, reducing complexity and highlighting essential information in sentences. Subsequently, the summarization sentences are fed through another LLM to extract hidden states, serving as compact, feature-rich representations. This approach leverages the advanced comprehension and generative capabilities of LLMs, offering a scalable and efficient strategy for similarity identification across diverse datasets. We demonstrate the effectiveness of our method in identifying similar data points on multiple datasets. Additionally, our approach enables non-technical domain experts, such as fraud investigators or marketing operators, to quickly identify similar data points tailored to specific scenarios, demonstrating its utility in practical applications. In general, our results open new avenues for leveraging LLMs in data analysis across various domains.

MS-CGAN: Fusion of conditional generative adversarial networks and multi-scale spatio-temporal features for lithology identification

Lithology identification constitutes a crucial undertaking in formation evaluation and reservoir characterization. However, the need for improved precision arises in conventional lithology identification models due to the difficulties presented by unequal distributions of small-sample logging data. An effective combination of domain expertise and data-driven models to predict lithology is essential due to the intricate and nonlinear connection between logging parameters and lithology, combined with the distinct characteristics of the oilfield environments. In this paper, we proposed a multi-scale conditional generative adversarial network(MS-CGAN) method, which combines conditional generative adversarial networks with multi-scale spatio-temporal features to address data imbalance issues and enhance the accuracy of lithology classification. Our approach, tested on two small datasets from the Hugoton and Panoma fields, USA, and the Daqing production wells, China, stands out as the optimal choice compared to other models. Comprehensive evaluation results indicate promising practical applications and potential benefits of the new model in enhancing lithology identification using limited data.

A competency framework for simulation facilitation in low-resource settings: a modified Delphi study.

Skilled facilitators are essential to drive effective simulation training in healthcare. Competency-based frameworks support the development of facilitation skills but, to our knowledge, there are no frameworks that specifically address context-sensitive priorities developed with practitioners working in low-resource settings. We aimed to develop a core competency framework for healthcare simulation facilitation in low-resource settings using a modified Delphi process. We drew on the domain expertise of members of the Vital Anaesthesia Simulation Training Community of Practice, with the study guided by a four-member steering group experienced in the conduct of simulation in low-resource settings. In survey round 1, participants (n = 54) were presented with an initial competency set derived from a previous qualitative study and co-created a set of 57 competencies for effective simulation facilitation in low-resource settings. In survey round 2, participants (n = 52) ranked competencies by relevance into three performance categories: techniques; artistry; and values. In survey round 3, participants (n = 50) ranked competencies on their importance. The steering group collated results and presented a draft core competency framework. In survey round 4, participants (n = 50) voted with 98% agreement that this framework represented the most relevant and important competencies for effective facilitation of simulation sessions in low-resource settings. The final 32-item framework encompasses core competencies found in existing standards and includes important new concepts such as demonstration of cultural sensitivity; humility; ability to recognise and respond to potential language barriers; facilitation team collaboration; awareness of logistics; and contingency planning. This competency-based framework highlights specific practices required for effective simulation facilitation in low-resource settings. Further work is required to refine and validate this tool to train simulation facilitators to deliver effective training to improve patient safety.

Enhanced MRI brain tumor detection and classification via topological data analysis and low-rank tensor decomposition

The advent of artificial intelligence in medical imaging has paved the way for significant advancements in the diagnosis of brain tumors. This study presents a novel ensemble approach that uses magnetic resonance imaging (MRI) to identify and categorize common brain cancers, such as pituitary, meningioma, and glioma. The proposed workflow is composed of a two-fold approach: firstly, it employs non-trivial image enhancement techniques in data preprocessing, low-rank Tucker decomposition for dimensionality reduction, and machine learning (ML) classifiers to detect and predict the type of brain tumor. Secondly, persistent homology (PH), a topological data analysis (TDA) technique, is exploited to extract potential critical areas in MRI scans. When paired with the ML classifier output, this additional information can help domain experts to identify areas of interest that might contain tumor signatures, improving the interpretability of ML predictions. When compared to automated diagnoses, this transparency adds another level of confidence and is essential for clinical acceptance. The performance of the system was quantitatively evaluated on a well-known MRI dataset, with an overall classification accuracy of 97.28% using an extremely randomized trees model. The promising results show that the integration of TDA, ML, and low-rank approximation methods is a successful approach for brain tumor identification and categorization, providing a solid foundation for further study and clinical application.

Experts – Part I: What They Are and How to Identify Them

AbstractThis paper investigates the topic of expertise in cognitive domains from a socio‐epistemological perspective. In particular, two central questions in the epistemology of expertise are discussed: what an expert is according to extant theories on the market; and how ordinary people can identify an expert in domains in which they have no competence of their own.

Assessing Preregistration Deviations: A Comparative Analysis of Psychologists and Open Science Experts

ABSTRACTUndisclosed deviations between preregistration plans and published articles challenge research transparency. This study examines whether open science experts can aid in assessing such deviations by comparing their evaluations with those of psychology experts. Using content analysis, we compared assessments of 25 preregistration plans and articles, following a psychologist studying preregistration discrepancies framework. The 72.6% agreement rate suggests differences stemmed from distinct perspectives. Psychologists leveraged domain knowledge to scrutinize subtle inconsistencies, while open science experts, deeply committed to transparency principles, focused more on procedural adherence. Open science experts, unfamiliar with psychology's implicit norms, faced challenges in discerning field‐specific knowledge and interpreting ambiguities as non‐deviations due to unclear preregistration formats and ambiguous content. Targeted support and collaborative approaches engaging both expert groups could enhance preregistration adherence evaluations, balancing the open science experts' emphasis on transparent processes with the psychologists' domain expertise, ultimately strengthening research transparency and reproducibility.

Dynamic collaborative learning with heterogeneous knowledge transfer for long-tailed visual recognition

Solving the long-tailed visual recognition with deep convolutional neural networks is still a challenging task. As a mainstream method, multi-experts models achieve SOTA accurary for tackling this problem, but the uncertainty in network learning and the complexity in fusion inference constrain the performance and practicality of the multi-experts models. To remedy this, we propose a novel dynamic collaborative learning with heterogeneous knowledge transfer model (DCHKT) in this paper, in which experts with different expertise collaborate to make predictions. DCHKT consists of two core components: dynamic adaptive weight adjustment and heterogeneous knowledge transfer learning. First, the dynamic adaptive weight adjustment is designed to shift the focus of model training between the global expert and domain experts via dynamic adaptive weight. By modulating the trade-off between the learning of features and classifier, the dynamic adaptive weight adjustment can enhance the discriminative ability of each expert and alleviate the uncertainty of model learning. Then, heterogeneous knowledge transfer learning, which measures the distribution differences between the fusion logits of multiple experts and the predicted logits of each expert with different specialties, can achieve message passing between experts and enhance the consistency of ensemble prediction in model training and inference to promote their collaborations. Finally, extensive experimental results on public long-tailed datasets: CIFAR-LT, ImageNet-LT, Place-LT and iNaturalist2018, demonstrate the effectiveness and superiority of our DCHKT.

Quantitative Process of Retrieving Documents on Specific Technology Using an Academic Database and the Sentence Transformer

ABSTRACTAs competition in technologies such as semiconductors and AI intensifies, the importance of technology analysis in establishing R&D strategies is increasing. Although frequently used, technological document searches by domain experts often suffer from limitations in qualitative judgment and inconsistency. This study proposes a process for quantitatively assembling a collection of documents on specific technologies using an academic database and a language model. Using approximately 92 million records from the Web of Science, we identified related keywords from author keywords and used scientometric approaches to determine a core set of technology‐related literature. Then, a deep learning‐based Sentence Transformer model was employed to extract technology literature with high similarity to the documents, ultimately forming a set of documents for technology analysis. This study aims to overcome cognitive limitations and introduce quantitative criteria for technology analysis, which is particularly significant for data‐driven science and technology policy.

An exploratory Q-matrix estimation method based on sparse non-negative matrix factorization.

Cognitive diagnostic assessment (CDA) is widely used because it can provide refined diagnostic information. The Q-matrix is the basis of CDA, and can be specified by domain experts or by data-driven estimation methods based on observed response data. The data-driven Q-matrix estimation methods have become a research hotspot because of their objectivity, accuracy, and low calibration cost. However, most of the existing data-driven methods require known prior knowledge, such as initial Q-matrix, partial q-vector, or the number of attributes. Under the G-DINA model, we propose to estimate the number of attributes and Q-matrix elements simultaneously without any prior knowledge by the sparse non-negative matrix factorization (SNMF) method, which has the advantage of high scalability and universality. Simulation studies are carried out to investigate the performance of the SNMF. The results under a wide variety of simulation conditions indicate that the SNMF has good performance in the accuracy of attribute number and Q-matrix elements estimation. In addition, a set of real data is taken as an example to illustrate its application. Finally, we discuss the limitations of the current study and directions for future research.

Use of Focus Groups and Reflexive Thematic Analysis to Uncover the Essential Conditions for UK Built Environment Degree Apprenticeships

ABSTRACT Degree Apprenticeships within UK Architecture, Engineering and Construction (AEC) organizations present a raft of unprecedented opportunities. However, little is understood on precisely how AEC Employer Organizations (EO’s) truly engage with Higher Education Institutions (HEI’s) in order to create “meaningful” Built Environment Degree Apprenticeships. Understanding this challenge and minutia of this engagement forms the starting trajectory of this work. To do this, and informed by Boundary Object Theory, an interpretivist approach was used to capture qualitative data from transdisciplinary focus groups – representing domain experts from AEC/HEI sector bodies. Primary data was evaluated using reflexive thematic analysis. An integrated inductive/deductive approach was used to examine nuance, subjectivity, understanding and meaning. Research findings culminate in the form of a thematic map, highlighting four essential conditions to support the delivery of UK AEC DA’s; specifically, the need for: (i) Onboarding, (ii) Structure (iii) Cooperation, and, (iv) Infrastructure. These findings identified that the knowledge needed to support engagement goes beyond existing acknowledged boundaries – ergo, that the corollary impact of these essential conditions require much deeper understanding than first thought. These findings form part of a wider study, the results of which will be reported in later works.

The Evolving Role of Information Professionals in Navigating Places, Spaces, and Nurturing New Discourses in the In‐Between

ABSTRACTInformation professionals are at the forefront of navigating the intricacies of shifting landscapes of the Fourth Industrial Revolution and Society 5.0, such as physical places, digital domains, and transitional zones in between, where boundaries blur and new discourses emerge. They are expected to extend their expertise into new domains and enrich their professional practice to better meet the evolving needs of their users. Third Space theory reported in Kuhlthau's work on guided inquiry and information literacy offers a framework, that creates an “in‐between” space, which allows personal experience to merge with professional information and encounters to help information professionals expand beyond their traditional domain expertise. These spaces promote the bridging of theory and practice, the navigation of ethical boundaries, access to multi‐perspective discourse, engagement in active listening, adjustment to evolving technologies, and facilitation of innovative methods. Creating in‐between spaces that promote conversations, interaction, information flow, and access is critical to navigating the intricacies. This interactive panel will explore how information professionals may use Third Space as a framework to offer a new way of thinking and addressing complex societal challenges while prioritizing human values, needs, and well‐being.

BI‐LAVA: Biocuration With Hierarchical Image Labelling Through Active Learning and Visual Analytics

AbstractIn the biomedical domain, taxonomies organize the acquisition modalities of scientific images in hierarchical structures. Such taxonomies leverage large sets of correct image labels and provide essential information about the importance of a scientific publication, which could then be used in biocuration tasks. However, the hierarchical nature of the labels, the overhead of processing images, the absence or incompleteness of labelled data and the expertise required to label this type of data impede the creation of useful datasets for biocuration. From a multi‐year collaboration with biocurators and text‐mining researchers, we derive an iterative visual analytics and active learning (AL) strategy to address these challenges. We implement this strategy in a system called BI‐LAVA—Biocuration with Hierarchical Image Labelling through Active Learning and Visual Analytics. BI‐LAVA leverages a small set of image labels, a hierarchical set of image classifiers and AL to help model builders deal with incomplete ground‐truth labels, target a hierarchical taxonomy of image modalities and classify a large pool of unlabelled images. BI‐LAVA's front end uses custom encodings to represent data distributions, taxonomies, image projections and neighbourhoods of image thumbnails, which help model builders explore an unfamiliar image dataset and taxonomy and correct and generate labels. An evaluation with machine learning practitioners shows that our mixed human–machine approach successfully supports domain experts in understanding the characteristics of classes within the taxonomy, as well as validating and improving data quality in labelled and unlabelled collections.

A transfer learning framework for the assessment of unconventional resources opportunities in the Middle East

An inadequate understanding of fluid transport processes in ultra-low permeability rocks has propelled data-driven modeling as an alternative and complementary tool to create recovery forecasts that honor the available data in the field. However, newly discovered fields lack data, which makes it challenging to apply traditional data-driven approaches to decision-making. Transfer learning provides an opportunity to start the early-stage analysis of the asset before adequate data becomes available. Here, we present a transfer learning framework that allows the basin-wide assessment of new shale gas and tight oil prospects. The proposed method is developed on real-world data from several thousand horizontal hydraulically fractured wells in the Eagle Ford super-basin in South Texas. A novel aspect of our method is integrating reservoir engineering domain expertise and the relationship among geologic and petrophysical variables, drilling and completion parameters, and well productivity in the data pre-processing and feature generation steps. We consider the temporal and spatial balancing of the training data to ensure that the resulting predictive models honor the real-world practices followed during unconventional field development. Our full-cycle transfer learning workflow consists of dimensionality reduction and unsupervised clustering, supervised learning, and hyperparameter fine-tuning. We test the workflow by examining the performance of a data-driven model of the Eagle Ford Basin on potential plays in the Middle East: Tuwaiq Mountain and Hanifa. The existence of multiple types of hydrocarbons–liquid oil, condensate, and dry gas–in the Eagle Ford results in a model flexible enough to be tested on various types of assets in a new location. We address the challenge of model overfitting by using data types with a relatively low resolution, which allows generalization to different geologies with basin-wide accuracy.