2023
Authors
Jorio, M; Amaral, A; Neto, T; Ferreira, P;
Publication
PROCEEDINGS OF THE 5TH INTERNATIONAL CONFERENCE ON PRODUCTION ECONOMICS AND PROJECT EVALUATION, ICOPEV 2022
Abstract
The uncontrolled growth of some cities and significant social inequalities were reflected in the population's housing conditions. Since housing projects must meet the needs of their inhabitants today and in the future, impacted by climate change, it is essential to search for more sustainable alternatives for social housing. To help decision-making on housing programs and incentives for sustainable building, this study aims to identify the main barriers and critical success factors of sustainable building projects. With this objective, a combination of qualitative data collection methods was applied, including the literature review and semi-structured interviews. The study's main results are the most significant barriers to sustainable social housing, such as lack of information, high cost, and lack of government incentives. Besides the critical success factors to guide sustainable social housing projects, the study highlights results such as the implementation of policies by government and professional bodies, monitoring compliance by the government, and commitment to sustainable delivery with the opinion of all stakeholders. Therefore, sustainable social housing projects can work as a tool to encourage social housing, strengthening the environmental pillar of sustainability. Furthermore, directly benefits the population with lower purchasing power, strengthening the economic and social pillars.
2023
Authors
Liang, T; Duarte, N; Yue, GX;
Publication
International Journal of Emerging Technologies in Learning (iJET)
Abstract
2023
Authors
Kulli, A; Grzywinska Rapca, M; Duarte, N; Goci, E; Pereira, C;
Publication
Central European Economic Journal
Abstract
2023
Authors
Majewska, M; Mazur-Wierzbicka, E; Duarte, N; Niezurawska, J;
Publication
Przeglad Organizacji
Abstract
2023
Authors
Palumbo, G; Guimaraes, M; Carneiro, D; Novais, P; Alves, V;
Publication
AMBIENT INTELLIGENCE-SOFTWARE AND APPLICATIONS-13TH INTERNATIONAL SYMPOSIUM ON AMBIENT INTELLIGENCE
Abstract
As the field of Machine Learning evolves, the number of available learning algorithms and their parameters continues to grow. On the one hand, this is positive as it allows for the finding of potentially more accurate models. On the other hand, however, it also makes the process of finding the right model more complex, given the number of possible configurations. Traditionally, data scientists rely on trial-and-error or brute force procedures, which are costly, or on their own intuition or expertise, which is hard to acquire. In this paper we propose an approach for algorithm recommendation based on meta-learning. The approach can be used in real-time to predict the best n algorithms (based on a selected performance metric) and their configuration, for a given ML problem. We evaluate it through cross-validation, and by comparing it against an Auto ML approach, in terms of accuracy and time. Results show that the proposed approach recommends algorithms that are similar to those of traditional approaches, in terms of performance, in just a fraction of the time.
2023
Authors
Palumbo, G; Carneiro, D; Guimares, M; Alves, V; Novais, P;
Publication
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
Abstract
In the last years, the number of machine learning algorithms and their parameters has increased significantly. On the one hand, this increases the chances of finding better models. On the other hand, it increases the complexity of the task of training a model, as the search space expands significantly. As the size of datasets also grows, traditional approaches based on extensive search start to become prohibitively expensive in terms of computational resources and time, especially in data streaming scenarios. This paper describes an approach based on meta-learning that tackles two main challenges. The first is to predict key performance indicators of machine learning models. The second is to recommend the best algorithm/configuration for training a model for a given machine learning problem. When compared to a state-of-the-art method (AutoML), the proposed approach is up to 130x faster and only 4% worse in terms of average model quality. Hence, it is especially suited for scenarios in which models need to be updated regularly, such as in streaming scenarios with big data, in which some accuracy can be traded for a much shorter model training time.
The access to the final selection minute is only available to applicants.
Please check the confirmation e-mail of your application to obtain the access code.