Pedro Marcelino

Bebras tasks are considered to develop Computational Thinking (CT) and are currently used for this purpose in many studies. However, the relationship between Bebras tasks and CT is recent and, given the scarcity of validated instruments for assessing CT that are not associated with a specific learning environment, the expected development of CT through Bebras tasks has not been sufficiently evaluated, especially in Primary School. For this reason, we designed the ABC-Thinking program for the development of CT in which a set of Bebras tasks were selected and categorised according to the CT skills they were related to, specific lesson plans were designed to integrate these tasks in a 12-week curriculum, and teachers were trained to apply the program. Using the competent Computational Thinking test (cCTt) in a pre-post-test experimental design, we looked to determine whether Primary School students developed specific CT skills after the program, and, therefore, whether Bebras could be considered suitable for the development of this competence. The results show a significant development in specific CT skills, interesting findings in the gender differences in this development, and between high and low performers. Finally, qualitative data indicate the suitability of the ABC-Thinking program with respect to teachers’ practice.

In recent years, there has been an increasing interest in the application of machine learning for the prediction of pavement performance. Prediction models are used to predict the future pavement condition, helping to optimally allocate maintenance and rehabilitation funds. However, few studies have proposed a systematic approach to the development of machine learning models for pavement performance prediction. Most of the studies focus on artificial neural networks models that are trained for high accuracy, disregarding other suitable machine learning algorithms and neglecting the importance of models’ generalisation capability for Pavement Engineering applications. This paper proposes a general machine learning approach for the development of pavement performance prediction models in pavement management systems (PMS). The proposed approach supports different machine learning algorithms and emphasizes generalisation performance. A case study for prediction of International Roughness Index (IRI) for 5 and 10-years, using the Long-Term Pavement Performance, is presented. The proposed models were based on a random forest algorithm, using datasets comprising previous IRI measurements, structural, climatic, and traffic data.

This paper proposes the application of the MACBETH approach for the development of a multi criteria value model to enable the prioritization of maintenance and rehabilitation interventions in the pavements of road networks according to technical, economic, and social aspects. A case-study design considering the Portuguese network was undertaken to illustrate the proposed approach. Using an interactive structuring process developed with the decision-maker, a set of five evaluation criteria related to maintenance costs, traffic, pavement condition, safety, and social equity were defined. The MACBETH approach was then used to build value functions and establish relative weights for the criteria. An application of the resulting model was made to a portfolio of possible intervention projects, prioritizing them according to the principle of benefit/cost maximization. The case-study demonstrated the application of the MACBETH approach and its suitability to solve the decision-making problem, thus proving the usefulness of this approach for road agencies with pavement management responsibilities.

The selection and use of technical parameters and performance indicators plays an essential role in the pavement management process. It is known that if more parameters are used, a more accurate evaluation of pavement condition is achieved, improving the choice of maintenance and rehabilitation interventions. However, one of the most expensive activities of the pavement management process is data collection. Accordingly, it is necessary to find a balance between the data collected and the real needs of the process. This paper presents a new approach for the development of pavement condition indicators using a machine learning algorithm named regularised regression with lasso. The present discussion is supported by a case study, which compares the proposed method with current practice for the description of the condition of a Portuguese motorway. The results suggest that the application of machine learning methods can improve the accuracy of pavement condition indicators when less data are available, contributing to achieve a balance between the needed data and information obtained.