Ana Alves

Prof. Dr. Ana Alves

Center of Informatics and Systems of the University of Coimbra, CISUC
+1
orcid

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

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

Representative Publications

View All Publications
1 September 2015 in Computers, Environment and Urban Systems
Verified
Journal Article
Open access
SJShan Jiang
Shan Jiang
Ana AlvesAna Alves
Ana Alves
FRFilipe Rodrigues
Filipe Rodrigues
JFJoseph Ferreira
Joseph Ferreira
FPFrancisco C. Pereira
Francisco C. Pereira
Over the last few years, much online volunteered geographic information (VGI) has emerged and has been increasingly analyzed to understand places and cities, as well as human mobility and activity. However, there are concerns about the quality and usability of such VGI. In this study, we demonstrate a complete process that comprises the collection, unification, classification and validation of a type of VGI—online point-of-interest (POI) data—and develop methods to utilize such POI data to estimate disaggregated land use (i.e., employment size by category) at a very high spatial resolution (census block level) using part of the Boston metropolitan area as an example. With recent advances in activity-based land use, transportation, and environment (LUTE) models, such disaggregated land use data become important to allow LUTE models to analyze and simulate a person’s choices of work location and activity destinations and to understand policy impacts on future cities. These data can also be used as alternatives to explore economic activities at the local level, especially as government-published census-based disaggregated employment data have become less available in the recent decade. Our new approach provides opportunities for cities to estimate land use at high resolution with low cost by utilizing VGI while ensuring its quality with a certain accuracy threshold. The automatic classification of POI can also be utilized for other types of analyses on cities

Verified
Journal Article
Open access
PDF file
RARenato Andrade
Renato Andrade
Ana AlvesAna Alves
Ana Alves
CBCarlos Bento
Carlos Bento
The modern planning and management of urban spaces is an essential topic for smart cities and depends on up-to-date and reliable information on land use and the functional roles of the places that integrate urban areas. In the last few years, driven by the increased availability of geo-referenced data from social media, embedded sensors, and remote sensing images, various techniques have become popular for land use analysis. In this paper, we first highlight and discuss the different data types and methods usually adopted in this context, as well as their purposes. Then, based on a systematic state-of-the-art study, we focused on exploring the potential of points of interest (POIs) for land use classification, as one of the most common categories of crowdsourced data. We developed an application to automatically collect POIs for the study area, creating a dataset that was used to generate a large number of features. We used a ranking technique to select, among them, the most suitable features for classifying land use. As ground truth data, we used CORINE Land Cover (CLC), which is a solid and reliable dataset available for the whole European territory. It was used an artificial neural network (ANN) in different scenarios and our results reveal values of more than 90% for the accuracy and F-score in one experiment performed. Our analysis suggests that POI data have promising potential to characterize geographic spaces. The work described here aims to provide an alternative to the current methodologies for land use and land cover (LULC) classification, which are usually time-consuming and depend on expensive data types.

7 April 2025 in Future Internet
Verified
Journal Article
Open access
PDF file
ÁPÁgata Palma
Ágata Palma
Mário AntunesMário Antunes
Mário Antunes
Jorge BernardinoJorge Bernardino
Jorge Bernardino
Ana AlvesAna Alves
Ana Alves
The Internet of Vehicles (IoV) presents complex cybersecurity challenges, particularly against Denial-of-Service (DoS) and spoofing attacks targeting the Controller Area Network (CAN) bus. This study leverages the CICIoV2024 dataset, comprising six distinct classes of benign traffic and various types of attacks, to evaluate advanced machine learning techniques for instrusion detection systems (IDS). The models XGBoost, Random Forest, AdaBoost, Extra Trees, Logistic Regression, and Deep Neural Network were tested under realistic, imbalanced data conditions, ensuring that the evaluation reflects real-world scenarios where benign traffic dominates. Using hyperparameter optimization with Optuna, we achieved significant improvements in detection accuracy and robustness. Ensemble methods such as XGBoost and Random Forest consistently demonstrated superior performance, achieving perfect accuracy and macro-average F1-scores, even when detecting minority attack classes, in contrast to previous results for the CICIoV2024 dataset. The integration of optimized hyperparameter tuning and a broader methodological scope culminated in an IDS framework capable of addressing diverse attack scenarios with exceptional precision.

4 September 2017
Verified
Conference Paper
Open access
AAAlexandre Almeida
Alexandre Almeida
Ana AlvesAna Alves
Ana Alves
Although smartphones include a set of sensors that enable innovative interactions, current mobile game interaction is mostly touch-based. Some games also include tilt movement based on the accelerometer sensor. However, sensors like accelerometers and gyroscopes can be used to recognize, in real time, full body motions. Exploring this can lead to innovative and immersive experiences while promoting physical activity. We present a proof of concept 3D endless running game called ActivRunner which implements an activity recognition system that predicts, in real time, 4 activities: standing, move left, move right, squat and jump. The goal is to replace the traditional touch interaction with a more natural movement-based one, showing the potential of this kind of interaction to create innovative and immersive mobile experiences while promoting physical activity.

1 January 2009 in Lecture Notes in Computer Science
Verified
Book Chapter
Closed access
PDF file
Ana AlvesAna Alves
Ana Alves
FPFrancisco C. Pereira
Francisco C. Pereira
ABAssaf Biderman
Assaf Biderman
CRCarlo Ratti
Carlo Ratti

Verified
Journal Article
Open access
PDF file
GFGonçalo Ferreira
Gonçalo Ferreira
Ana AlvesAna Alves
Ana Alves
Marco VelosoMarco Veloso
Marco Veloso
CBCarlos Bento
Carlos Bento
Digital location traces are a relevant source of insights into how citizens experience their cities. Previous works using call detail records (CDRs) tend to focus on modeling the spatial and temporal patterns of human mobility, not paying much attention to the semantics of places, thus failing to model and enhance the understanding of the motivations behind people’s mobility. In this paper, we applied a methodology for identifying individual users’ routine locations and propose an approach for attaching semantic meaning to these locations. Specifically, we used circular sectors that correspond to cellular antennas’ signal areas. In those areas, we found that all contained points of interest (POIs), extracted their most important attributes (opening hours, check-ins, category) and incorporated them into the classification. We conducted experiments with real-world data from Coimbra, Portugal, and the initial experimental results demonstrate the effectiveness of the proposed methodology to infer activities in the user’s routine areas.