A. Min Tjoa

Artificial intelligence (AI) systems are increasingly proposed for agricultural decision support, precision farming and precision livestock farming (PLF), yet large-scale and durable adoption by practitioners remains the exception rather than the rule. Established maturity scales such as the Technology Readiness Level (TRL) capture the engineering progression of a technology from basic principles to operational deployment, but they are agnostic to whether end users actually rely on the resulting system in their daily work. This paper introduces the Technology Acceptance Level (TAL) as a complementary, human-centered metric for evaluating the usability, trustworthiness and operational uptake of AI in agriculture. TAL is defined as a nine-level ordinal scale, anchored in the Technology Acceptance Model and the European Union ethics guidelines for Trustworthy AI, that captures the trajectory from initial exposure of a system to a practitioner up to its stable, autonomous integration into routine decision-making. Each level is operationalised by a small set of measurable criteria spanning perceived usefulness, perceived ease of use, transparency, reliability under changing conditions, and alignment with agricultural workflows. We provide a mathematically grounded aggregation rule based on a non-compensatory, minimum-of-dimensions principle that prevents a single weak dimension from being masked by strong scores elsewhere, and we derive a confidence interval for TAL estimates from practitioner survey data. The framework is illustrated through three representative use cases—variable-rate nitrogen management in arable cropping, vision-based fruit detection for selective harvesting, and computer-vision-based lameness detection in dairy cattle—demonstrating how the same AI artefact can occupy very different acceptance levels across deployment contexts. By explicitly addressing the human-in-the-loop, TAL provides a practical instrument to diagnose adoption barriers, prioritise iterative system improvement, and steer the transition from technically functional prototypes to practically accepted, trustworthy AI in the agri-food sector.

Financial statement fraud detection is critical to maintaining trust among investors, regulators, and analysts. However, traditional audit procedures often fail to detect anomalies effectively because they occur infrequently but can result in significant economic losses. This study proposes an oversampling approach using a modified threshold in the Wasserstein Generative Adversarial Network with Gradient Penalty (WGANGP) to enhance synthetic data variance in financial fraud detection. The financial data were collected from the financial reports of companies listed on the Indonesia Stock Exchange and were labelled according to the Balanced Scorecard framework into four categories: normal, alarm, risky, and fraud. Given the severe class imbalance, this study introduces a WGANGP model with threshold optimisation in the generator and a gradient penalty to generate high-quality synthetic samples. This study conducted general and per-entity oversampling scenarios and evaluated them using Euclidean distance, Wasserstein distance, and classification metrics. In Scenario 1, the Generative Adversarial Network (GAN) outperformed the Synthetic Minority Oversampling Technique (SMOTE) and vice versa in Scenario 2. However, in financial fraud detection, the WGANGP with enhanced thresholding improved the F1-score by 13% to 17% compared to SMOTE and five GAN-based models across thirteen classification models, including traditional, machine learning, and deep learning models. This finding suggests that optimising the threshold in WGANGP reduces variance and improves model performance. Furthermore, generating synthetic data that is very similar to actual data may not necessarily improve classification; therefore, it is necessary to test how oversampling affects subsequent stages.

This study examined the system quality requirements of halal e-commerce platforms from a Sharia compliance perspective. Utilizing a qualitative approach, in-depth interviews were conducted with key stakeholders from two Malaysian halal e-commerce platforms. Thematic analysis revealed three key system quality criteria: user-friendliness, website quality, and system adaptability. The study highlights the necessity of quality management practices that align with Islamic principles to foster consumer trust and enhance the online shopping experience. Findings emphasize the importance of incorporating technological advancements, such as mobile apps and blockchain, to enhance transparency and streamline operations in halal e-commerce. The findings highlighted the need for halal e-commerce platforms to integrate quality management practices that align with Sharia requirements to meet the growing demand for halal products in the global market. Additionally, the findings of this research provide valuable recommendations for e-commerce stakeholders, policymakers, and halal business owners to strengthen system quality and enhance market competitiveness in the halal digital economy.

Privacy requirements engineering acts as a role to systematically elicit privacy requirements from system requirements and legal requirements such as the GDPR. Many methodologies have been proposed, but the majority of them are focused on the waterfall approach, making adopting privacy engineering in agile software development difficult. The other major issue is that the process currently is to a high degree manual. This paper focuses on closing these gaps through the development of a machine learning-based approach for identifying privacy requirements in an agile software development environment, employing natural language processing (NLP) techniques. Our method aims to allow agile teams to focus on functional requirements while NLP tools assist them in generating privacy requirements. The main input for our method is a collection of user stories, which are typically used to identify functional requirements in agile software development. The NLP approach is then used to automate some human-intensive tasks such as identifying personal data and creating data flow diagrams from user stories. The data flow diagram forms the basis for the automatic creation of privacy requirements. Our evaluation shows that our NLP method achieves a fairly good performance in terms of F-Measure. We are also demonstrate the feasibility of our NLP approach in CamperPlus project. Lastly, we are developing a tool to integrate our NLP approach into the privacy requirements engineering pipeline, allowing for manual editing of results so that agile teams can maintain control over the automated approach.

A short term production planning system based on the behaviour integrated entity relationship approach (BIER) is described. The BIER model is characterized by its ability to support both the static and dynamic aspects of a workflow model. The implementation described in this paper has been used in an application for short term production planning in the automotive sector. Keywords: active data bases, workflow system, production planning systems, dynamic models.

The integration of heterogeneous and weakly linked log data poses a major challenge in many log-analytic applications. Knowledge graphs (KGs) can facilitate such integration by providing a versatile representation that can interlink objects of interest and enrich log events with background knowledge. Furthermore, graph-pattern based query languages, such as SPARQL, can support rich log analyses by leveraging semantic relationships between objects in heterogeneous log streams. Constructing, materializing, and maintaining centralized log knowledge graphs, however, poses significant challenges. To tackle this issue, we propose VloGraph—a distributed and virtualized alternative to centralized log knowledge graph construction. The proposed approach does not involve any a priori parsing, aggregation, and processing of log data, but dynamically constructs a virtual log KG from heterogeneous raw log sources across multiple hosts. To explore the feasibility of this approach, we developed a prototype and demonstrate its applicability to three scenarios. Furthermore, we evaluate the approach in various experimental settings with multiple heterogeneous log sources and machines; the encouraging results from this evaluation suggest that the approach can enable efficient graph-based ad-hoc log analyses in federated settings.