Artur Jorge Ferreira

Prof. Dr. Artur Jorge Ferreira

ISEL - Dep. Computer Science and Engineering, Instituto Politécnico de Lisboa, Lisbon, Lisboa, Portugal
+2
orcid
Artur Ferreira EE (1999), MSc (2003), PhD (2014) Associate P...
avatar
Co-authors
avatar
Following
avatar
Followers

Research Focus & Metrics

Explore full metrics on Scilit

Academic Career Length

28Years (1999-Present)

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

Representative Publications

View All Publications
19 January 2012
Verified
Book Chapter
Closed access
PDF file
Artur Jorge FerreiraArtur Jorge Ferreira
Artur Jorge Ferreira
MFMário Figueiredo
Mário Figueiredo
1 October 2012 in Pattern Recognition Letters
Verified
Journal Article
Closed access
Artur Jorge FerreiraArtur Jorge Ferreira
Artur Jorge Ferreira
MFMário Figueiredo
Mário Figueiredo
1 September 2012 in Pattern Recognition
Verified
Journal Article
Closed access
Artur Jorge FerreiraArtur Jorge Ferreira
Artur Jorge Ferreira
MFMário Figueiredo
Mário Figueiredo
1 January 2014 in Procedia Technology
Verified
Journal Article
Open access
AUArtem Umanets
Artem Umanets
Artur Jorge FerreiraArtur Jorge Ferreira
Artur Jorge Ferreira
NLNuno Leite
Nuno Leite
In the past few years, with the proliferation of mobile devices people are experiencing frequent communication and information exchange. For instance, in the context of tourist visits, it is often the case that each person carries out a smartphone, to get information about touristic places. When one visits some location, a tourist guide application will recommend useful information, according to its current location, preferences, and past visits. Afterwards, the tourist guide allows for the user to provide feedback about each visit. In this paper, we address the development and the key features of a tourist guide, named GuideMe. Its mobile and Web applications provide consultation, publication, and recommendation of touristic locations. Each user may consult places of touristic interest, receive suggestions of previously unseen touristic places according to other users recommendations, and to perform its own recommendations. The recommendations are carried out using the well-known Mahout library. As compared to previous recommender based tourist guides, the key novelties of GuideMe are its integration with social networks and the unique set of options offered in the application. The usability and load tests performed to evaluate the service, including its recommendation engine, have shown both the adequacy of the designed interfaces as well as good response times
1 January 2024 in Information
Verified
Journal Article
Open access
PDF file
CPCatarina Palma
Catarina Palma
Artur Jorge FerreiraArtur Jorge Ferreira
Artur Jorge Ferreira
MFMário Figueiredo
Mário Figueiredo
The presence of malicious software (malware), for example, in Android applications (apps), has harmful or irreparable consequences to the user and/or the device. Despite the protections app stores provide to avoid malware, it keeps growing in sophistication and diffusion. In this paper, we explore the use of machine learning (ML) techniques to detect malware in Android apps. The focus is on the study of different data pre-processing, dimensionality reduction, and classification techniques, assessing the generalization ability of the learned models using public domain datasets and specifically developed apps. We find that the classifiers that achieve better performance for this task are support vector machines (SVM) and random forests (RF). We emphasize the use of feature selection (FS) techniques to reduce the data dimensionality and to identify the most relevant features in Android malware classification, leading to explainability on this task. Our approach can identify the most relevant features to classify an app as malware. Namely, we conclude that permissions play a prominent role in Android malware detection. The proposed approach reduces the data dimensionality while achieving high accuracy in identifying malware in Android apps.
1 January 2014 in Procedia Technology
Verified
Journal Article
Open access
TTTeodoro Trindade
Teodoro Trindade
Artur Jorge FerreiraArtur Jorge Ferreira
Artur Jorge Ferreira
Edgar FernandesEdgar Fernandes
Edgar Fernandes
The applicability of image data processing to estimate the spatial distribution of Air/Fuel ratio at the flame front on gas combustion systems are presented and discussed. The objective is to devise a procedure capable of converting a single RGB image data, obtained by conventional CCD cameras, into a reliable sensing on local combustion state for practical application on atmospheric flames of premixed methane and propane gases. In this context, this paper proposes a fast and innovative image processing methodology. An image processing algorithm based on the camera sensor transfer function, a lookup calibration table, and sparse matrices operations is proposed. The optimized version of our image processing algorithm is able to process high resolution images at rates as high as 0.6 Mpixel/s on a standard personal computer (3.5GHz clock frequency). As a result, color RGB images are converted into quasi real-time detectors of local combustion state for practical flames of CH4 and C3H8 gases. It has been experimentally observed that camera blue and green channels mimic the flame CH* and C* chemiluminescence emissions, revealing a wide applicability on φ detection (Air/Fuel ratio), roughly ranging between 0.8 and 1.4