Simone Porcu

Dr. Simone Porcu

University of Cagliari
orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
20 May 2021 in Energies
Verified
Journal Article
Open access
PDF file
Alessandro FlorisAlessandro Floris
Alessandro Floris
SPSimone Porcu
Simone Porcu
RGRoberto Girau
Roberto Girau
Luigi AtzoriLuigi Atzori
Luigi Atzori
Smart buildings use Internet of Things (IoT) sensors for monitoring indoor environmental parameters, such as temperature, humidity, luminosity, and air quality. Due to the huge amount of data generated by these sensors, data analytics and machine learning techniques are needed to extract useful and interesting insights, which provide the input for the building optimization in terms of energy-saving, occupants’ health and comfort. In this paper, we propose an IoT-based smart building (SB) solution for indoor environment management, which aims to provide the following main functionalities: monitoring of the room environmental parameters; detection of the number of occupants in the room; a cloud platform where virtual entities collect the data acquired by the sensors and virtual super entities perform data analysis tasks using machine learning algorithms; a control dashboard for the management and control of the building. With our prototype, we collected data for 10 days, and we built two prediction models: a classification model that predicts the number of occupants based on the monitored environmental parameters (average accuracy of 99.5%), and a regression model that predicts the total volatile organic compound (TVOC) values based on the environmental parameters and the number of occupants (Pearson correlation coefficient of 0.939).

11 November 2020 in Electronics
Verified
Journal Article
Open access
PDF file
SPSimone Porcu
Simone Porcu
Alessandro FlorisAlessandro Floris
Alessandro Floris
Luigi AtzoriLuigi Atzori
Luigi Atzori
Most Facial Expression Recognition (FER) systems rely on machine learning approaches that require large databases for an effective training. As these are not easily available, a good solution is to augment the databases with appropriate data augmentation (DA) techniques, which are typically based on either geometric transformation or oversampling augmentations (e.g., generative adversarial networks (GANs)). However, it is not always easy to understand which DA technique may be more convenient for FER systems because most state-of-the-art experiments use different settings which makes the impact of DA techniques not comparable. To advance in this respect, in this paper, we evaluate and compare the impact of using well-established DA techniques on the emotion recognition accuracy of a FER system based on the well-known VGG16 convolutional neural network (CNN). In particular, we consider both geometric transformations and GAN to increase the amount of training images. We performed cross-database evaluations: training with the "augmented" KDEF database and testing with two different databases (CK+ and ExpW). The best results were obtained combining horizontal reflection, translation and GAN, bringing an accuracy increase of approximately 30%. This outperforms alternative approaches, except for the one technique that could however rely on a quite bigger database.

20 August 2020 in IEEE Transactions on Network and Service Management
Verified
Journal Article
Closed access
SPSimone Porcu
Simone Porcu
Alessandro FlorisAlessandro Floris
Alessandro Floris
JVJan-Niklas Voigt-Antons
Jan-Niklas Voigt-Antons
Luigi AtzoriLuigi Atzori
Luigi Atzori
SMSebastian Moller
Sebastian Moller
This paper investigates the possibility to estimate the perceived Quality of Experience (QoE) automatically and unobtrusively by analyzing the face of the consumer of video streaming services, from which facial expression and gaze direction are extracted. If effective, this would be a valuable tool for the monitoring of personal QoE during video streaming services without asking the user to provide feedback, with great advantages for service management. Additionally, this would eliminate the bias of subjective tests and would avoid bothering the viewers with questions to collect opinions and feedback. The performed analysis relies on two different experiments: i) a crowdsourcing test, where the videos are subject to impairments caused by long initial delays and re-buffering events; ii) a laboratory test, where the videos are affected by blurring effects. The facial Action Units (AU) that represent the contractions of specific facial muscles together with the position of the eyes’ pupils are extracted to identify the correlation between perceived quality and facial expressions. An SVM with a quadratic kernel and a k-NN classifier have been tested to predict the QoE from these features. These have also been combined with measured application-level parameters to improve the quality prediction. From the performed experiments, it results that the best performance is obtained with the k-NN classifier by combining all the described features and after training it with both the datasets, with a prediction accuracy as high as 93.9% outperforming the state of the art achievements.

1 June 2019
Verified
Conference Paper
Closed access
SPSimone Porcu
Simone Porcu
SUStefan Uhrig
Stefan Uhrig
JVJan-Niklas Voigt-Antons
Jan-Niklas Voigt-Antons
SMSebastian Moller
Sebastian Moller
LALuigi Atzori
Luigi Atzori
As known from everyday contexts of multimedia usage, suddenly occurring quality impairments are capable of causing strong negative emotions in human users. This is particularly the case if the displayed content is highly relevant to current motives and behavioral goals. The present study investigated the effects of visual degradations on quality perception and emotional state of participants who were exposed to a series of short video clips. After each video playback, participants had to decide whether a certain event happened in the video. For data collection, subjective measures of quality and emotion were complemented by behavioral measures derived from capturing participants' spontaneous facial expressions. For data analysis, two general approaches were combined: First, a multivariate analysis of variance approach allowed to examine the effects of visual degradation factors on perceived quality and subjective emotional dimensions. It mainly revealed that perceived quality and emotional valence were both sensitive to degradation intensity, whereas the impact of degradation length was limited when task-relevant video content had already been obscured. Second, using a machine learning approach, an automatic Video Quality of Experience (VQoE) prediction system based on the recorded facial expressions was derived, demonstrating a strong correlation between facial expressions and perceived quality. Hereby, estimates of VQoE might be delivered in an objective, continuous and concealed manner, thus diminishing any further need for subjective self-reports.

1 February 2019
Verified
Conference Paper
Closed access
SPSimone Porcu
Simone Porcu
Alessandro FlorisAlessandro Floris
Alessandro Floris
LALuigi Atzori
Luigi Atzori
In this paper we investigate on the potentials to implicitly estimate the Quality of Experience (QoE) of a user of video streaming services by acquiring a video of her face and monitoring her facial expression and gaze direction. To this, we conducted a crowdsourcing test in which participants were asked to watch and rate the quality when watching 20 videos subject to different impairments, while their face was recorded with their PC's webcam. The following features were then considered: the Action Units (AU) that represent the facial expression, and the position of the eyes' pupil. These features were then used, together with the respective QoE values provided by the participants, to train three machine learning classifiers, namely, Support Vector Machine with quadratic kernel, RUSBoost trees and bagged trees. We considered two prediction models: only the AU features are considered or together with the position of the eyes' pupils. The RUSBoost trees achieved the best results in terms of accuracy, sensitivity and area under the curve scores. In particular, when all the features were considered, the achieved accuracy is of 44.7%, 59.4% and 75.3% when using the 5-level, 3level and 2-level quality scales, respectively. Whereas these results are not satisfactory yet, these represent a promising basis.

22 January 2024 in ACM Transactions on Multimedia Computing, Communications, and Applications
Verified
Journal Article
Open access
GBGülnaziye Bingöl
Gülnaziye Bingöl
SPSimone Porcu
Simone Porcu
Alessandro FlorisAlessandro Floris
Alessandro Floris
Luigi AtzoriLuigi Atzori
Luigi Atzori
The utilization of user’s facial- and speech-related features for the estimation of the Quality of Experience (QoE) of multimedia services is still underinvestigated despite its potential. Currently, only the use of either facial or speech features individually has been proposed, and relevant limited experiments have been performed. To advance in this respect, in this study, we focused on WebRTC-based videoconferencing, where it is often possible to capture both the facial expressions and vocal speech characteristics of the users. First, we performed thorough statistical analysis to identify the most significant facial- and speech-related features for QoE estimation, which we extracted from the participants’ audio-video data collected during a subjective assessment. Second, we trained individual QoE estimation machine learning-based models on the separated facial and speech datasets. Finally, we employed data fusion techniques to combine the facial and speech datasets into a single dataset to enhance the QoE estimation performance due to the integrated knowledge provided by the fusion of facial and speech features. The obtained results demonstrate that the data fusion technique based on the Improved Centered Kernel Alignment (ICKA) allows for reaching a mean QoE estimation accuracy of 0.93, whereas the values of 0.78 and 0.86 are reached when using only facial or speech features, respectively.