Marta Fernández-Diego

Dr. Marta Fernández-Diego

orcid

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

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

Representative Publications

View All Publications
3 September 2020 in IEEE Access
Verified
Journal Article
Open access
MFMarta Fernández-Diego
Marta Fernández-Diego
EMErwin R. Mendez
Erwin R. Mendez
FGFernando González-Ladrón-de-Guevara
Fernando González-Ladrón-de-Guevara
SASilvia Abrahao
Silvia Abrahao
EIEmilio Insfran
Emilio Insfran
Software developers require effective effort estimation models to facilitate project planning. Although Usman et al. systematically reviewed and synthesized the effort estimation models and practices for Agile Software Development (ASD) in 2014, new evidence may provide new perspectives for researchers and practitioners. This paper presents a systematic literature review that updates the Usman et al. study from 2014 to 2020 by analyzing the data extracted from 73 new papers. This analysis allowed us to identify six agile methods: Scrum, Xtreme Programming and four others, in all of which expert-based estimation methods continue to play an important role. This is particularly the case of Planning Poker, which is very closely related to the most frequently used size metric (story points) and the way in which software requirements are specified in ASD. There is also a remarkable trend toward studying techniques based on the intensive use of data. In this respect, although most of the data originate from single-company datasets, there is a significant increase in the use of cross-company data. With regard to cost factors, we applied the thematic analysis method. The use of team and project factors appears to be more frequent than the consideration of more technical factors, in accordance with agile principles. Finally, although accuracy is still a challenge, we identified that improvements have been made. On the one hand, an increasing number of papers showed acceptable accuracy values, although many continued to report inadequate results. On the other, almost 29% of the papers that reported the accuracy metric used reflected aspects concerning the validation of the models and 18% reported the effect size when comparing models.

4 July 2014 in JOURNAL OF CIVIL ENGINEERING AND MANAGEMENT
Verified
Journal Article
Open access
PBPablo Ballesteros-Perez
Pablo Ballesteros-Perez
MGMaria-Carmen González-Cruz
Maria-Carmen González-Cruz
MFMarta Fernández-Diego
Marta Fernández-Diego
EPEugenio Pellicer
Eugenio Pellicer
Research in Bid Tender Forecasting Models (BTFM) has been in progress since the 1950s. None of the developed models were easy-to-use tools for effective use by bidding practitioners because the advanced mathematical apparatus and massive data inputs required. This scenario began to change in 2012 with the development of the Smartbid BTFM, a quite simple model that presents a series of graphs that enables any project manager to study competitors using a relatively short historical tender dataset. However, despite the advantages of this new model, so far, it is still necessary to study all the auction participants as an indivisible group; that is, the original BTFM was not devised for analyzing the behavior of a single bidding competitor or a subgroup of them. The present paper tries to solve that flaw and presents a stand-alone methodology useful for estimating future competitors’ bidding behaviors separately.

24 June 2024
Verified
Conference Paper
Open access
DGDaniel Gaspar-Figueiredo
Daniel Gaspar-Figueiredo
MFMarta Fernández-Diego
Marta Fernández-Diego
RNRuben Nuredini
Ruben Nuredini
SASilvia Abrahao
Silvia Abrahao
EIEmilio Insfran
Emilio Insfran
Adapting the user interface (UI) of software systems to meet the needs and preferences of users is a complex task. The main challenge is to provide the appropriate adaptations at the appropriate time to offer value to end-users. Recent advances in Machine Learning (ML) techniques may provide effective means to support the adaptation process. In this paper, we instantiate a reference framework for Intelligent User Interface Adaptation by using Reinforcement Learning (RL) as the ML component to adapt user interfaces and ultimately improving the overall User Experience (UX). By using RL, the system is able to learn from past adaptations to improve the decision-making capabilities. Moreover, assessing the success of such adaptations remains a challenge. To overcome this issue, we propose to use predictive Human-Computer Interaction (HCI) models to evaluate the outcome of each action (i.e., adaptations) performed by the RL agent. In addition, we present an implementation of the instantiated framework, which is an extension of OpenAI Gym, that serves as a toolkit for developing and comparing RL algorithms. This Gym environment is highly configurable and extensible to other UI adaptation contexts. The evaluation results show that our RL-based framework can successfully train RL agents able to learn how to adapt UIs in a specific context to maximize the user engagement by using an HCI model as rewards predictor.

7 May 2025 in Empirical Software Engineering
Verified
Journal Article
Open access
PDF file
DGDaniel Gaspar-Figueiredo
Daniel Gaspar-Figueiredo
MFMarta Fernández-Diego
Marta Fernández-Diego
SASilvia Abrahão
Silvia Abrahão
EIEmilio Insfran
Emilio Insfran
Context: Adapting the User Interface (UI) of software systems to users’ requirements and their context of use is a challenging task. It involves determining the right adaptation, at the right time and place, to make it valuable for end-users. We believe that recent progress in Machine Learning (ML) techniques could provide useful ways in which to support adaptation more effectively. In particular, Reinforcement Learning (RL) has proven to be effective in planning a sequence of UI adaptations over a long time horizon. However, RL requires either manually specifying a reward function or learning a reward model. Currently there is no empirical evidence supporting the usefulness of reward models for UI adaptation. Objective: This paper presents a confirmatory empirical study aimed at investigating the effectiveness of two different approaches to generating reward models in the context of UI adaptation using reinforcement learning: (1) a reward model derived exclusively from predictive Human-Computer Interaction (HCI) models (AUI-HCI), and (2) a reward model derived from predictive HCI models augmented by human feedback (AUI-HCI-HF), compared to non-adaptive (NA) interfaces. Method: A controlled experiment with an AB/BA crossover design was conducted to evaluate the impact of these reward models on user experience, measured through objective and subjective engagement, as well as user satisfaction. Our study contributes to the understanding of how reward modeling can facilitate UI adaptation through RL. Results: The results showed a significant improvement in objective engagement for AUI-HCI-HF compared to non-adaptive interfaces. However, no significant differences were found between AUI-HCI and non-adaptive interfaces for any of the other measurements, across any conditions. Conclusion: Integrating human feedback into RL reward models enhances objective engagement, but its impact on subjective engagement and user satisfaction remains limited. While AUI-HCI-HF shows promise for improving interaction metrics, further research is needed to better align reward models with broader user perceptions and preferences, particularly compared to non-adaptive interfaces.

12 August 2024 in Knowledge and Information Systems
Verified
Journal Article
Open access
PDF file
MNMahsa Nooribakhsh
Mahsa Nooribakhsh
MFMarta Fernández-Diego
Marta Fernández-Diego
FGFernando González-Ladrón-de-Guevara
Fernando González-Ladrón-de-Guevara
MMMahdi Mollamotalebi
Mahdi Mollamotalebi
One of the important issues in social networks is the social communities which are formed by interactions between its members. Three types of community including overlapping, non-overlapping, and hidden are detected by different approaches. Regarding the importance of community detection in social networks, this paper provides a systematic mapping of machine learning-based community detection approaches. The study aimed to show the type of communities in social networks along with the algorithms of machine learning that have been used for community detection. After carrying out the steps of mapping and removing useless references, 246 papers were selected to answer the questions of this research. The results of the research indicated that unsupervised machine learning-based algorithms with 41.46% (such as k means) are the most used categories to detect communities in social networks due to their low processing overheads. On the other hand, there has been a significant increase in the use of deep learning since 2020 which has sufficient performance for community detection in large-volume data. With regard to the ability of NMI to measure the correlation or similarity between communities, with 53.25%, it is the most frequently used metric to evaluate the performance of community identifications. Furthermore, considering availability, low in size, and lack of multiple edge and loops, dataset Zachary’s Karate Club with 26.42% is the most used dataset for community detection research in social networks.

14 July 2020 in IEEE Access
Verified
Journal Article
Open access
XGXimena Guerron
Ximena Guerron
SASilvia Abrahao
Silvia Abrahao
EIEmilio Insfran
Emilio Insfran
MFMarta Fernández-Diego
Marta Fernández-Diego
FGFernando González-Ladrón-de-Guevara
Fernando González-Ladrón-de-Guevara
A large number of metrics with which to assess the quality of cloud services have been proposed over the last years. However, this knowledge is still dispersed, and stakeholders have little or no guidance when choosing metrics that will be suitable to evaluate their cloud services. The objective of this paper is, therefore, to systematically identify, taxonomically classify, and compare existing quality of service (QoS) metrics in the cloud computing domain. We conducted a systematic literature review of 84 studies selected from a set of 4333 studies that were published from 2006 to November 2018. We specifically identified 470 metric operationalizations that were then classified using a taxonomy, which is also introduced in this paper. The data extracted from the metrics were subsequently analyzed using thematic analysis. The findings indicated that most metrics evaluate quality attributes related to performance efficiency (64%) and that there is a need for metrics that evaluate other characteristics, such as security and compatibility. The majority of the metrics are used during the Operation phase of the cloud services and are applied to the running service. Our results also revealed that metrics for cloud services are still in the early stages of maturity – only 10% of the metrics had been empirically validated. The proposed taxonomy can be used by practitioners as a guideline when specifying service level objectives or deciding which metric is best suited to the evaluation of their cloud services, and by researchers as a comprehensive quality framework in which to evaluate their approaches.