João Pascoal Faria

João Pascoal Faria

Auto-generated profile, based on publicly available information

João Pascoal Faria

University of Porto

Research Focus & Metrics

Academic Career Length

24Years (2003-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 August 2023 in IEEE Access
Verified
Journal Article
Open access
ASAndré O. Sousa
André O. Sousa
DVDaniel T. Veloso
Daniel T. Veloso
HGHenrique M. Gonçalves
Henrique M. Gonçalves
JFJoão Pascoal Faria
João Pascoal Faria
JMJoão Mendes-Moreira
João Mendes-Moreira
PHPedro Castro Henriques
Pedro Castro Henriques
CONTEXT: Software estimation is a vital yet challenging project management activity. Various methods, from empirical to algorithmic, have been developed to fit different development contexts, from plan-driven to agile. Recently, machine learning techniques have shown potential in this realm but are still underexplored, especially for individual task estimation. OBJECTIVES: We investigate the use of machine learning techniques in predicting task effort and duration in software projects to assess their applicability and effectiveness in production environments, identify the best-performing algorithms, and pinpoint key input variables (features) for predictions. METHOD: We conducted experiments with datasets of various sizes and structures exported from three project management tools used by partner companies. For each dataset, we trained regression models for predicting the effort and duration of individual tasks using eight machine learning algorithms. The models were validated using k-fold cross-validation and evaluated with several metrics. RESULTS: Ensemble algorithms like Random Forest, Extra Trees Regressor, and XGBoost consistently outperformed non-ensemble ones across the three datasets. However, the estimation accuracy and feature importance varied significantly across datasets, with a Mean Magnitude of Relative Error (MMRE) ranging from 0.11 to 9.45 across the datasets and target variables. Nevertheless, even in the worst-performing dataset, effort estimates aggregated to the project level showed good accuracy, with MMRE = 0.23. CONCLUSIONS: Machine learning algorithms, especially ensemble ones, seem to be a viable option for estimating the effort and duration of individual tasks in software projects. However, the quality of the estimates and the relevant features may depend largely on the characteristics of the available datasets and underlying projects. Nevertheless, even when the accuracy of individual estimates is poor, the aggregated estimates at the project level may present a good accuracy due to error compensation.

1 January 2005
Verified
Book Chapter
Closed access
PDF file
APAna C. R. Paiva
Ana C. R. Paiva
JFJoão C. P. Faria
João C. P. Faria
NTNikolai Tillmann
Nikolai Tillmann
RVRaul A. M. Vidal
Raul A. M. Vidal

1 September 2014
Verified
Conference Paper
Closed access
IMInes Coimbra Morgado
Ines Coimbra Morgado
APAna C.R. Paiva
Ana C.R. Paiva
JFJoao Pascoal Faria
Joao Pascoal Faria
This paper presents an approach for testing mobile applications using reverse engineering and behavioural patterns. The goal of this research work is to ease the testing of mobile applications by automatically identifying and testing behaviour that is common in this type of applications, i.e., behaviour patterns. The approach includes a tool to automatically explore an Android application. This tool also identifies patterns in the behaviour of the application and apply tests previously associated with those patterns. The final results of this research work will be a catalogue of behavioural patterns and the tool which will output a report on the matched patterns and another one on the testing of those patterns.

5 November 2018
Verified
Conference Paper
Open access
PPPedro Martins Pontes
Pedro Martins Pontes
BLBruno Lima
Bruno Lima
JFJoão Pascoal Faria
João Pascoal Faria

1 January 2010
Verified
Book Chapter
Closed access
PDF file
António Miguel Rosado da CruzAntónio Miguel Rosado da Cruz
António Miguel Rosado da Cruz
JFJoão Pascoal Faria
João Pascoal Faria

1 September 2018
Verified
Conference Paper
Closed access
JDJoão Pedro Dias
João Pedro Dias
JFJoao Pascoal Faria
Joao Pascoal Faria
HFHugo Sereno Ferreira
Hugo Sereno Ferreira
Software has a longstanding association with a state of crisis considering its success rate. The explosion of Internet-connected devices - Internet-of-Things - adds to the complexity of software systems. The particular characteristics of these systems, such as its large-scale and heterogeneity, pose increasingly new challenges. Model-based approaches have been widely used as a mechanism to abstract low-level programming details and processes. By using such approaches, and leveraging concepts as reactive design, visual notations, and live programming, we believe to be able to reduce the complexity of creating, operate/monitor and evolve such systems. The main objective of this Ph.D. is to delve into the software engineering practices for developing IoT systems and systems of systems, exploiting models as a suitable abstraction, expecting to reduce the complexity of managing most of the software development lifecycle that targets IoT systems and to develop the prototype that will aid on the validation of such approach.