Emergence of A Novel Domain Expert: A Generative AI-based Framework for Software Function Point Analysis

Cyanobacterial blooms in freshwater sources are a global concern, and gaining insight into their causes is crucial for effective resource management and control. In this study, we present a novel computational framework for the causal analysis of cyanobacterial harmful algal blooms (cyanoHABs) in Lake Kinneret. Our framework integrates Convergent Cross Mapping (CCM) and Extended CCM (ECCM) causal networks with Bayesian Network (BN) models. The constructed CCM-ECCM causal networks and BN models unveil significant interactions among factors influencing cyanoHAB formation. These interactions have been validated by domain experts and supported by evidence from peer-reviewed publications. Our findings suggest that Microcystis flos-aquae levels are influenced not only by community structure but also by ammonium, phosphate, oxygen, and temperature levels in the weeks preceding bloom occurrences. We demonstrated a non-parametric computational framework for causal analysis of a multivariate ecosystem. Our framework offers a more comprehensive understanding of the underlying mechanisms driving M. flos-aquae blooms in Lake Kinneret. It captures complex interactions and provides an explainable prediction model. By considering causal relationships, temporal dynamics, and joint probabilities of environmental factors, the proposed framework enhances our understanding of cyanoHABs in Lake Kinneret.

Representations of strategic knowledge in design

PurposeMobile peer‐to‐peer communications is an essential phase in the evolution of mobile communications technologies, motivating this research which aims to focus on how established industry stakeholders and new entrants can adapt themselves to the new situation.Design/methodology/approachBased on existing literature, the authors identified three distinctive evolution paths for mobile peer‐to‐peer communications and developed an analysis framework for their comparison. The authors validated the analysis by conducting a questionnaire study among domain experts, and analyzed its results using statistical analysis.FindingsInternet‐driven evolution has high value proposition, is profitable and has subscription fees as an important revenue model. Telecom‐driven evolution creates value, leverages markets, leverages competence, is likely to encounter regulatory intervention and benefits all customer segments. Proprietary evolution has a successful revenue model, results in alliances of competitors and is competence‐enhancing to mobile device vendors.Research limitations/implicationsFuture work consists mainly of analyzing quantitatively the implications of the new technologies when they become readily available and evaluating the value analysis framework in other applicable cases.Practical implicationsInternet‐driven evolution enables new business opportunities to independent service operators and equipment vendors by enabling opportunities in profiting from sales of advanced devices and networks. Telecom‐driven evolution benefits mostly incumbent mobile network operators. Proprietary evolution enables limited competition against incumbent actors by independent service operators.Originality/valueThis study is one of the first journal publications on mobile peer‐to‐peer communications from a holistic techno‐economic point of view, beneficial to both academics and practitioners.

Nowadays, many works are interested in adapting to the context without taking into account neither the responsiveness to adapt their solution, nor the ability of designers to model all the relevant concerns. Our paper provides a new architecture for context management that tries to solve both problems. This approach is also based on the analysis and synthesis of context-aware frameworks proposed in literature. Our solution is focus on a separation of contextual concerns at the design phase and preserves it as much as possible at runtime. For this, we introduce the notion of independent views that allow designers to focus on their domain of expertise. At runtime, the architecture is splitted in 2 independent levels of adaptation. The highest is in charge of current context identification and manages each view independently. The lowest handles the adaptation of the application according to the rules granted by the previous level.

Accurate dynamic hydrological models are often too complex and costly for the rapid, broad-scale screening necessitated for proactive land-use planning against increasing cloudburst risks. This paper demonstrates the use of GPT-4 to develop a GUI-based Python 3.13.2 application for geospatial flood risk assessments. The study used instructive prompt techniques to script a traditional stream and catchment delineation methodology, further embedding it with a custom GUI. The resulting application demonstrates high performance, processing a 29.63 km2 catchment at a 1 m resolution in 30.31 s, and successfully identifying the main upstream contributing areas and flow paths for a specified area of interest. While its accuracy is limited by terrain data artifacts causing stream breaks, this study demonstrates how human–AI collaboration, with the LLM acting as a coding assistant guided by domain expertise, can empower domain experts and facilitate the development of advanced GIS-based decision-support systems.

RCA-Seq: An original approach for enhancing the analysis of sequential data based on hierarchies of multilevel closed partially-ordered patterns

Modern HPC centers comprise clusters, storage, networks, power and cooling infrastructure, and more. Analyzing the efficiency of these complex facilities is a daunting task. Increasingly, facilities deploy sensors and monitoring tools, but with millions of instrumented components, analyzing collected data manually is intractable. Data from an HPC center comprises different formats, granularities, and semantics, and handwritten scripts no longer suffice to transform the data into a digestible form.We present ScrubJay, an intuitive, scalable framework for automatic analysis of disparate HPC data. ScrubJay decouples the task of specifying data relationships from the task of analyzing data. Domain experts can store reusable transformations that describe relations between domains. ScrubJay also automates performance analysis. Analysts provide a query over logical domains of interest, and ScrubJay automatically derives needed steps to transform raw measurements. ScrubJay makes large-scale analysis tractable, reproducible, and provides insights into HPC facilities.

TV-MV Analytics: A visual analytics framework to explore time-varying multivariate data

Manual annotation of data in invasion games is a costly task which poses a natural limit on sample sizes and the level of granularity used in match and performance analyses. To overcome this challenge, this work introduces FAUPA-ML, a Framework for Automatic Upscaled Performance Analysis with Machine Learning, which leverages graph neural networks to scale domain-specific expert knowledge to large data sets. Networks were trained using position data of match phases (counter/position attacks), annotated manually by domain experts in 10 matches. The best network was applied to contextualize N = 539 matches of elite handball (2019/20–2021/22 German Men’s Handball Bundesliga) with 86% balanced accuracy. Distance covered, speed, metabolic power, and metabolic work were calculated for attackers and defenders and differences between counters and position attacks across seasons analyzed with an ANOVA. Results showed that counter attacks are shorter, less frequent and more intense than position attacks and that attacking is more intense than defending. Findings show that FAUPA-ML generates accurate replications of expert knowledge that can be used to gain insights in performance analysis previously deemed infeasible. Future studies can use FAUPA-ML for large-scale, contextualized analyses that investigate influences of team strength, score-line, or team tactics on performance.

The capacity to detect facts or observations that differ from what is normally thought of by domain experts is crucial for many contemporary applications. These outliers may be located with the use of anomaly detection, and the system can subsequently implement the required adjustments. This study presents a scalable anomaly detection framework for network traffic analysis in cybersecurity using advanced machine learning. Approaches. Leveraging the NSL-KDD dataset. Before model building, Recursive Feature Elimination (RFE) identifies the most relevant features for classification. Machine learning models—DNN, KNN, RF, and NB—are employed and evaluated using F1-score, recall, accuracy, and precision, with a confusion matrix to assess performance. Results show RF achieves the highest accuracy (99.81%), precision (99.89%), and recall (99.90%), followed closely by KNN. Generally speaking, both NB and DNN perform worse since their metrics are lower. The results reveal the enhanced performance of RF and KNN in terms of identifying and categorising anomalous behaviours in the network traffic and, therefore, providing a viable solution to augment existing real-time cybersecurity systems.

This study examines the integration of climate change risks and sustainability goals within Saudi Arabia’s financial regulatory framework to enhance green finance initiatives aligned with Vision 2030. A qualitative research design synthesises insights from a comprehensive literature review, semi-structured interviews with domain experts, and a detailed analysis of critical Saudi green finance frameworks and legislation. This research identifies mechanisms for embedding sustainability in the financial sector and addresses the challenges, opportunities, and strategic directions essential for Saudi Arabia within the global context of sustainable finance. The findings reveal a robust foundation laid by Vision 2030 initiatives yet underscore the need for enhanced regulatory frameworks, increased market readiness, and greater societal engagement. This study highlights a significant literature gap in understanding Saudi Arabia’s unique approach to green finance amid its economic diversification and sustainability goals. Contributing to original insights, this research underscores the critical role of Saudi Arabia in the global energy market and its substantial economic and environmental transformations. It offers detailed analyses and recommendations that enrich the discourse on sustainable finance, impacting policymakers, financial practitioners, and scholars.

Archetypal analysis is a popular exploratory tool that explains a set of observations as compositions of few 'pure' patterns. The standard formulation of archetypal analysis addresses this problem for real valued observations by finding the approximate convex hull. Recently, a probabilistic formulation has been suggested which extends this framework to other observation types such as binary and count. In this article we further extend this framework to address the general case of nominal observations which includes, for example, multiple-option questionnaires. We view archetypal analysis in a generative framework: this allows explicit control over choosing a suitable number of archetypes by assigning appropriate prior information, and finding efficient update rules using variational Bayes'. We demonstrate the efficacy of this approach extensively on simulated data, and three real world examples: Austrian guest survey dataset, German credit dataset, and SUN attribute image dataset.

We provide a generalizable framework for the systematic analysis of complicated, longitudinal clinical features in pediatric cancer. We use a threefold pipeline of exploratory data analysis, ontological categorization through a multi-modal data transformation process towards predictive analytics. We derive a data-driven phenotype from a subset of a sample of over 1900 brain tumor cases focused specifically on High-Grade Gliomas. We implement an analyst-friendly process to make machine learning-ready data sets based on domain ontologies ready for enumeration and vectorization. The results are clinical domain expert readable data points from 4.3 million observational events across 16,000 patient days. In this research, we address the gap in phenotypic data features by utilizing extensive harmonized observational clinical data and identify resources and specific processes for their use in rare tumor research.

DNAsmart: Multiple attribute ranking tool for DNA data storage systems

New performance requirements to adapt to the changing environment and to maintain a competitive advantage have contributed since the 1980s to the emergence of new types of organizations focused on projects or processes. To facilitate the implementation of this process view of organizations, many theorists and practitioners have proposed analysis and modelling frameworks, ontologies being considered as a relevant tool to conduct a ‘semantic analysis’ of business processes. This analysis provides a referential of concepts defined through consensus between domain experts. These concepts should improve the commensurability of the interpretation schemas of the decision makers. Thus, in general, any decision-making process consists of four phases, which are: (1) intelligence, (2) design, (3) choice and (4) evaluation and revision. The ‘design’ phase is aimed at building a repository of concepts collected from the first phase. These concepts model the activity of the organization in terms of knowledge. This knowledge should be shared and adopted by the group decision makers in order to perform any collective decision. Approaches in this area are, however, based on ad hoc, often implicit modelling principles, and the proposed ontologies remain poor in terms of expressiveness. The objective of this paper is to analyse the ontological foundations of the processes of organizations following a formal approach. We propose a core ontology of organization processes which specializes the Descriptive Ontology for Linguistic and Cognitive Engineering (DOLCE) foundational ontology and supplementing Bottazzi and Ferrario’s DOLCE-based formal ontology of organizations. This ontology comprises several modules to reflect both the ‘static’ aspects of organizations and their behaviours, including intentional ones. In this article, we present the contents of the ontology, the formal ontological tools reused for its design, and the various theories the ontology is committed to.