Abstract

Abstract
Non-traditional data like the applicant's bank statement is a significant source for decision-making when granting loans. We find that we can use methods from network science on the applicant's bank statements to convert inherent cash flow characteristics to predictors for default prediction in a credit scoring or credit risk assessment model. First, the credit cash flow is extracted from a bank statement and later converted into a visibility graph or network. Afterwards, we use this visibility network to find features that predict the borrowers' repayment behaviour. We see that feature selection methods select all the five extracted features. Finally, SMOTE is used to balance the training data. The model using the features from the network and the standard features together is shown having superior performance compared to the model that uses only the standard features, indicating the network features' predictive power.

Abstract
The advance of industrialization regarding the optimization of production to obtain greater productivity and consequently generate more profits has led to the emergence of Industry 4.0, which aims to create an environment called smart manufacturing. On the other hand, the Internet of Things is a global network of interrelated physical devices, such as sensors, actuators, intelligent applications, computers, mechanical machines, objects, and people, becoming an essential part of the Internet. These devices are data sources that provide abundant information on manufacturing processes in an industrial environment. A concern of this type of system is processing large sets of data and generating knowledge. These challenges often raise concerns about security, more specifically cybersecurity. Good cybersecurity practices make it possible to avoid damage to production lines and information. With the growing increase in threats in terms of security, this paper aims to carry out a review of existing technologies about cybersecurity in intelligent manufacturing and an introduction to the architecture of the IoT and smart manufacturing.

Abstract
Laser-induced breakdown spectroscopy allows fast chemical analysis of light elements without significant sample preparation, turning it into a promising technique for on-site mining operations. Still, the performance for quantification purposes remains its major caveat, obstructing a broader application of the technique. In this work, we present an extensive comparison of the performances of distinct algorithms for quantification of Lithium in a mining prospection stage, using spectra acquired with both a commercial handheld device and a laboratory prototype. Covering both linear and non-linear methodologies, the results show that, when covering a wide range of concentrations typical on a mining operation, non-linear methodologies manage to achieve errors compatible with a semi-quantitative performance, offering performances better than those obtained with linear methods, which are more affected by saturation and matrix effects. The findings enclosed offer support for future applications in the field and may possibly be generalized for other elements of interest in similar mining environments.

Abstract
The evacuation of buildings in case of fire is a sensitive issue for civil society that also motivates the academic community to develop and study solutions to improve the efficiency of evacuating these spaces. The study of human behavior in fire emergencies has been one of the areas that have deserved the attention of researchers. However, this modeling of human behavior is difficult and complex because it depends on factors that are difficult to know and that vary from country to country. In this paper, a paradigm shift is proposed which, instead of focusing on modeling the behavior of occupants, focuses on conditioning this behavior by providing real-time information on the most efficient evacuation routes. Making this information available to occupants is possible with a solution that takes advantage of the growing use of the IoT (Internet of Things) in buildings to help occupants adapt to the environment. Supported by the IoT, multi-agent recommender systems can help users to adapt to the environment and provide the occupants with the most efficient evacuation routes. This paradigm shift is achieved through a context-based multi-agent recommender system based on contextual data obtained from IoT devices, which recommends the most efficient evacuation routes at any given time. The obtained results suggest that the proposed solution can improve the efficiency of evacuating buildings in the event of a fire; for a scenario with two hundred people following the system recommendations, the time they take to reach a safe place decreases by 17.7%.

Abstract
Teaching project management to engineering students demands realworld experiences in which they can apply and develop work-ready skills, such as critical thinking, empathy, and teamwork. While a shortage of these skills in new graduates is frequently claimed by engineering companies and educational bodies, there is still a lack of higher education research studies on how to foster them through teaching practice. This paper intends to contribute to filling this gap by presenting an exploratory case study research of a Project-Based Learning (PjBL) experience aimed at designing and implementing a professional (re)integration plan for social and economic deprived people (e.g., long/short-term unemployed), who depend on external food supply provided by a non-profit organization called REFOOD. The experience was carried out in Portugal, from February to June 2021, with 7 MSc mechanical engineering students from the University of Trasos-Montes and Alto Douro (UTAD). We firstly describe the PjBL experience in terms of the key driving question, the learning goals, the educational activities, the collaboration among students and stakeholders, the scaffolding activities, and the tangible learning artefacts produced. We further discuss the preliminary results of the study from data collected through documental analysis, participant observation, and self-completion questionnaires on students' perceptions of the PjBL experience. Data analysis shows that this experience positively impacted the development of students' project management, empathy, critical thinking, and team-working skills, by mainly having challenged their personal belief systems and biases related to the real-world scenarios they dealt with. Finally, we outline implications for the teaching practice concerning the development of similar PjBL experiences, as well as future research directions.