Abstract
This paper studies a real world dedicated parallel machine scheduling problem with sequence dependent setups, different machine release dates and additional resources (PMSR). To solve this problem, two previously proposed models have been adapted and a novel objective function, the minimisation of the sum of the machine completion times, is proposed to reflect the real conditions of the manufacturing environment that motivates this work. One model follows the strip-packing approach and the other is time-indexed. The solutions obtained show that the new objective function provides a compact production schedule that allows the simultaneous minimisation of machine idle times and setup times. In conclusion, this study provides valuable insights into the effectiveness of different models for solving PMSR problems in real-world contexts and gives directions for future research in this area using complementary approaches such as matheuristics. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
Process Mining offers a powerful framework for uncovering, analyzing, and optimizing real-world business processes. Petri nets provide a versatile means of modeling process behavior. However, traditional methods often struggle to effectively compare complex Petri nets, hindering their potential for process enhancement. To address this challenge, we introduce PetriNet2Vec, an unsupervised methodology inspired by Doc2Vec. This approach converts Petri nets into embedding vectors, facilitating the comparison, clustering, and classification of process models. We validated our approach using the PDC Dataset, comprising 96 diverse Petri net models. The results demonstrate that PetriNet2Vec effectively captures the structural properties of process models, enabling accurate process classification and efficient process retrieval. Specifically, our findings highlight the utility of the learned embeddings in two key downstream tasks: process classification and process retrieval. In process classification, the embeddings allowed for accurate categorization of process models based on their structural properties. In process retrieval, the embeddings enabled efficient retrieval of similar process models using cosine distance. These results demonstrate the potential of PetriNet2Vec to significantly enhance process mining capabilities.

Abstract
Various relevant aspects of our lives relate to the places we visit and our daily activities. The movement of individuals between regular places, such as work, school, or other important personal locations is getting increasing attention due to the pervasiveness of geolocation devices and the amount of data they generate. This work presents an approach for location prediction using a probabilistic model and data mining techniques over mobility data streams. We evaluate the method over 5 real-world datasets. The results show the usefulness of the proposal in comparison with other-well-known approaches.

Abstract
The dowry payment system is used in the cultural context and tradition of certain financial transactions related to marriages and engagement. However, disputes, fraud, and financial gaps in exploitation occur in these systems, which affect user confidence. This study uses an exploratory approach to identify the main weaknesses of current traditional dowry payment systems and analyses the benefits that blockchain technology and smart contracts can provide. The proposed data security framework combines blockchain security features such as decentralisation, cryptography, and automatic verification through smart contracts to ensure the integrity and reliability of dowry payment transactions. In this study, we adopt the Design Science Research (DSR) methodology to propose producing and developing artefacts that support solving problems in the existing dowry payment system more efficiently. We will disseminate new ideas or concepts developed to indigenous communities in Timor-Leste using the Diffusion of Innovation (DOI) and Technology Acceptance Model (TAM) frameworks to ensure that the technological framework developed can be used safely and efficiently.

Abstract
In everyday life, the production lines of companies are required to be flexible, rapidly adopting new processes and methods in order to ensure their competitiveness in the market. The main objective of this study was to analyze the impact of automation on a workstation at an industrial company which paints accessories. By means of simulation, one was able to identify several aspects that negatively affect the company’s overall capacity, namely reduced productivity and long cycle times. The digital tools developed through Visual Basic for Applications constituted the starting point for the automation of several repetitive and bureaucratic tasks which support decision-making, initiating the process of Digital Transformation at the organization. In economic terms, this improvement in the workplace can potentially reduce costs in the order of thousands of euros annually, in addition to increasing productivity thus improving the company’s general performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

Abstract
Gliomas are a common and aggressive kind of brain tumour that is difficult to diagnose due to their infiltrative development, variable clinical presentation, and complex behaviour, making them an important focus in neuro-oncology. Segmentation of brain tumour images is critical for improving diagnosis, prognosis, and treatment options. Manually segmenting brain tumours is time-consuming and challenging. Automatic segmentation algorithms can significantly improve the accuracy and efficiency of tumour identification, thus improving treatment planning and outcomes. Deep learning-based segmentation tumours have shown significant advances in the last few years. This study evaluates the impact of four denoising filters, namely median, Gaussian, anisotropic diffusion, and bilateral, on tumour detection and segmentation. The U-Net architecture is applied for the segmentation of 3064 contrast-enhanced magnetic resonance images from 233 patients diagnosed with meningiomas, gliomas, and pituitary tumours. The results of this work demonstrate that bilateral filtering yields superior outcomes, proving to be a robust and computationally efficient approach in brain tumour segmentation. This method reduces the processing time by 12 epochs, which in turn contributes to lowering greenhouse gas emissions by optimizing computational resources and minimizing energy consumption.