Abstract
This article presents an investigation into the classification of endoscopic capsule pathologies using Multiple Instance Learning (MIL) methods in conjunction with deep neural network architectures. The primary problem addressed in this study is the accurate and efficient detection of gastrointestinal pathologies, a significant challenge in medical diagnostics that can have a profound impact on patient outcomes. The use of endoscopic capsules is particularly important as they provide a minimally invasive method to capture comprehensive images of the gastrointestinal tract, facilitating early detection of conditions such as ulcers, polyps, bleeding, and Crohn's disease. Specifically, we explore three variants of MIL-Max, Mean, and Attention-for analysing sets of images captured by the endoscopic capsule. MIL was employed because it effectively handles scenarios where individual image instances are not explicitly labelled but are grouped in bags with known labels, making it suitable for the complex nature of endoscopic data. Furthermore, MIL has not yet been extensively applied in this modality, highlighting the innovative aspect of our approach. In addition, we evaluated the performance of three convolutional neural network architectures-VGG16, ResNet50, and DenseNet121-in the classification task. The results indicate that the combination of MIL methods and deep neural network architectures offers a promising approach to the detection and classification of gastrointestinal pathologies, with significant improvements in diagnostic accuracy and efficiency. © 2025 The Author(s).

Abstract
This study investigates the role of artificial intelligence (AI) in recruitment, with a specific emphasis on small and medium enterprises (SMEs) and cultural diversity, two dimensions frequently underrepresented in existing research. The objective is to evaluate the benefits, challenges, and strategies for the responsible adoption of AI in recruitment. To achieve this, a Multivocal Literature Review (MLR) was conducted, systematically synthesising peer-reviewed studies and grey literature published from 2018 onwards. Following Kitchenham’s systematic review guidelines and Garousi’s multivocal extensions, academic and practitioner perspectives were analysed to capture both theoretical insights and real-world practices. The findings indicate that AI can streamline recruitment processes, improve decision-making accuracy, and enhance candidate experience through tools such as résumé screening, predictive analytics, and generative AI applications. However, issues of algorithmic bias, limited transparency, data quality, regulatory compliance, and workforce scepticism persist, particularly in SMEs that face resource constraints. Although much of the available evidence reflects Western contexts, this review broadens the scope by integrating global perspectives and highlighting how cultural and regional factors influence AI acceptance. The novelty of this study lies in combining academic and industry evidence to propose actionable strategies— such as bias audits, explainable AI frameworks, and human-in-the-loop approaches—for more inclusive, sustainable, and globally relevant adoption of AI in recruitment. © 2025 by the authors. Licensee ESJ, Italy.

Abstract
We show that recent approaches to quantitative analysis based on non-idempotent typing systems can be extended to programming languages with effects. In particular, we consider two cases: the weak open call-by-name (CBN) and call-by-value (CBV) variants of the $\lambda$ -calculus, equipped with operations to write and read from a global state. In order to capture quantitative information with respect to time and space for both CBN and CBV, we design for each of them a quantitative type system based on a (tight) multi-type system. One key observation of this work is how CBN and CBV influence the composition of state types. That is, each type system is developed by taking into account how each language manages the global state: in CBN, the composition of state types is almost straightforward, since function application does not require evaluation of its argument; in CBV, however, the interaction between functions and arguments makes the composition of state types more subtle since only values can be passed as actual arguments. The main contribution of this paper is the design of type systems capturing quantitative information about effectful CBN and CBV programming languages. Indeed, we develop type systems that are qualitatively and quantitatively sound and complete.

Abstract
This paper explores advancements in Video Anomaly Detection (VAD), combining theoretical insights with practical solutions to address model limitations. Through comprehensive experimental analysis, the study examines the role of feature representations, sampling strategies, and curriculum learning in enhancing VAD performance. Key findings include the impact of class imbalance on the Cross-Modal Awareness-Local Arousal (CMALA) architecture and the effectiveness of techniques like pseudo-curriculum learning in mitigating noisy classes, such as Car Accident. Novel strategies like the Sample-Batch Selection (SBS) dynamic segment selection and pre-trained image-text models, including Contrastive Language-Image Pre-training (CLIP) and ViTamin encoder, significantly improve anomaly detection. The research underscores the potential of multimodal VAD, highlighting the integration of audio and visual modalities and the development of multimodal fusion techniques. To support this evolution, the study proposes a Unified WorkStation 4 VAD (UWS4VAD) to streamline research workflows and introduces a new VAD benchmark incorporating multimodal data and textual information. The work envisions enhanced anomaly interpretation and performance by leveraging joint representation learning and Large Language Models (LLMs). The findings set the stage for future advancements, advocating for large-scale pre-training on audio-visual datasets and shifting toward a more integrated, multimodal approach to VADs. Source code of the project available at https://github.com/zuble/uws4vad

Abstract
Current descriptions of immersive learning cases are often difficult or impossible to compare. This is due to a myriad of different options on what details to include, which aspects are relevant, and on the descriptive approaches employed. Also, these aspects often combine very specific details with more general guidelines or indicate intents and rationales without clarifying their implementation. In this paper we provide a method to describe immersive learning cases that is structured to enable comparisons, yet flexible enough to allow researchers and practitioners to decide which aspects to include. This method leverages a taxonomy that classifies educational aspects at three levels (uses, practices, and strategies) and then utilizes two frameworks, the Immersive Learning Brain and the Immersion Cube, to enable a structured description and interpretation of immersive learning cases. The method is then demonstrated on a published immersive learning case on training for wind turbine maintenance using virtual reality. Applying the method results in a structured artifact, the Immersive Learning Case Sheet, that tags the case with its proximal uses, practices, and strategies, and refines the free text case description to ensure that matching details are included. This contribution is thus a case description method in support of future comparative research of immersive learning cases. We then discuss how the resulting description and interpretation can be leveraged to change immersion learning cases, by enriching them (considering low-effort changes or additions) or innovating (exploring more challenging avenues of transformation). The method holds significant promise to support better-grounded research in immersive learning.

Abstract