In the machine learning domain, clustering is a fundamental unsupervised learning operation which aims to partition the instances of a dataset into clusters (i.e, groups, subsets) such that instances within the same cluster are much similar to each other and much different from the other clusters. In the broad spectrum of clustering methods, prototype-based methods characterize each cluster through a prototype (i.e. centroid) and a relocation scheme is employed to iteratively redistribute the instances into the clusters, guided by an objective function. In this paper, several prototype-based methods are brought into focus, including K-means, K-medoids, K-medians, Fuzzy C-means and Kernel K-means. These algorithms are experimentally analyzed on several original benchmark datasets, distorted benchmark datasets and synthetic datasets. The comparative analysis is oriented in two main aspects: accuracy and sensitivity to noise and outliers.

Berat is one of the most beautiful places in Albania, attracting thou­sands of tourists. The Ethnographic Museum, a former traditional house, today reassessed as a city museum represents one of the main attractions. The sur­rounding urban context in the proximity of the building presents some anal­ogies with the organic structure of the historic quarters. Virtual travel is an in­novative form of tourism where users can experience a place by being actively and meaningfully engaged with the history, people, culture, artefacts and en­vironment of a specific historical period. Our goal was to create a user-friend­ly platform that empowers users with easy access to a vast range of cultural re­sources, thereby enhancing their overall experience. The proposed virtual tour is going to be a step forward in the museum sector because it will offer users a different experience based on interactivity thanks to 3D Virtual Reality.

The changing needs of customers for a more interactive, personalized, and smooth shopping experience have changed the field of e-commerce. This has led to the use of immersive technologies like Augmented Reality (AR), Virtual Reality (VR), and Artificial Intelligence (AI), which have a great potential to enrich the consumer experience, increase efficiency, and ultimately contribute to higher sales through the integration of AI. This study aims to examine the influence of AI and immersive technologies on online shopping, integrating contemporary trends, consumer behaviors, and case studies. To achieve this, the study aims to combine theoretical and practical knowledge through the synthesis of 210 sources, later narrowed down to 89 relevant ones. The study provides a unified understanding of a previously fragmented field, creating a valuable source of knowledge for any individual seeking to advance the field of online shopping.

Commercial operations across trading, import/export, logistics, and technology distribution are being reshaped by the convergence of artificial intelligence (AI), machine learning, multi-agent robotics, and Extended Reality (XR). Small and Medium-sized Enterprises (SMEs) feel this shift acutely: they face the same pressures as their larger competitors; labor shortages, high-SKU inventories that resist tidy categorization, narrow margins, and customer expectations set by Amazon-grade fulfilment, but rarely command the capital or the structured warehouse environments that make industrial automation straightforward. Existing frameworks for AI-driven automation and digital twins have been developed primarily for large-scale industrial settings and do not account for the capital, infrastructure, and organizational constraints specific to SMEs, leaving a gap in SME-scoped integration models. This research addresses that gap by asking how AI-driven robotics and immersive technologies can be integrated to optimize commercial workflows in SMEs operating in dynamic logistics and trading environments. The proposed framework is grounded in Sociotechnical Systems Theory, which treats technology and organizational workflows as jointly designed and mutually adapting, and follows a Design Science orientation in which the architecture itself is constructed as an evaluable artifact rather than a purely descriptive model. Methodologically, the study conducts a narrative synthesis of literature on embodied AI, computer vision, digital twins, VR training, and AR-assisted operations, combined with workflow analysis to identify where SMEs lose the most time and money. These are translated into a four-layer system architecture (perception, cognition, execution, integration) deployed through a four-phase implementation model: needs assessment, digital-twin and VR pre-training, controlled hardware pilot, and AR-supported scaling. The contribution of the study is twofold: conceptually, it brings together several technologies that are often discussed separately in the literature, while focusing specifically on the needs and constraints of SMEs while practically, it proposes a phased roadmap that can help SMEs adopt these technologies gradually, reducing both financial and operational risks. The approach also emphasizes human–robot collaboration rather than replacing human workers. The study does not include experimental validation, it presents a conceptual architecture and implementation roadmap consistent with a Design Science artifact-construction stage that can serve as a basis for empirical testing in real commercial environments.

In this paper, we will represent some applications to various problems of mass theory and integration, by using the concept of local convergences and exhaustive sequences. We will continue the idea of point-wise I -convergence, Ideal exhaustiveness that was introduced by Komisarski [3], and Kostyrko, Sal´at and Wilczy´nski [4]. The equi-integrable introduced in Bohner-type ideal integrals and a new study on the application of symmetric differences have been presented in the theory of mass and continuous functions, continuing the results of Boccuto, Das, Dimitriou, Papanastassiou [2].