Joan Vila-Francés

Prof. Dr. Joan Vila-Francés

IDAL. Electronic Engineering Department, University of Valencia, Av. Universitat, SN, Burjassot, 46100 Valencia, Spain
orcid

Research Focus & Metrics

Academic Career Length

23Years (2004-Present)

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

Representative Publications

View All Publications
28 July 2017 in Remote Sensing
Verified
Journal Article
Open access
PDF file
LALuis Alonso
Luis Alonso
SWShari Van Wittenberghe
Shari Van Wittenberghe
JAJulia Amoros-Lopez
Julia Amoros-Lopez
Joan Vila-FrancésJoan Vila-Francés
Joan Vila-Francés
Luis Gómez-ChovaLuis Gómez-Chova
Luis Gómez-Chova
Jose MorenoJose Moreno
Jose Moreno
In order to estimate vegetation photosynthesis from remote sensing observations; some critical parameters need to be quantified. From all absorbed light; the plant needs to release any excess that is not used for photosynthesis; by non-photochemical quenching; by fluorescence emission and unregulated thermal dissipation. Non-photochemical quenching (NPQ) processes are controlled photoprotective mechanisms which; once activated; strongly control the dynamics of photochemical efficiency. With illumination conditions increasing and decreasing during a diurnal cycle; photoprotection mechanisms needs to change accordingly. The goal of this work is to quantify dynamic NPQ; measured from active fluorescence measurements; based on passive proximal sensing leaf measurements. During a 22-day controlled light and water stress experiment on a tobacco (Nicotiana tabacum L.) leaf we measured the diurnal dynamics of passive fluorescence (Chl F); the Photochemical Reflectance Index (PRI); the Absorbed Photosynthetically Active Radiation (APAR) and leaf temperature in combination with the actively retrieved non-photochemical quenching (NPQ) parameter. Based on a bi-linear combination of diurnal APAR and PRI (plane fit model) we succeeded to estimate NPQ with a RMSE of 0.08. The simple plane fit model estimation represents well the diurnal NPQ dynamics; except for the high light stress phase; when additional reversible photoinhibition processes took place. The present works presents a way of determining NPQ from passive remote sensing measurements; as a necessary step towards estimating photosynthetic rate.

14 May 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
ABAndrea Bonetti
Andrea Bonetti
Marcelino Martínez SoberMarcelino Martínez Sober
Marcelino Martínez Sober
JTJulio Torres
Julio Torres
JVJose Maria Vega
Jose Maria Vega
SPSebastien Pellerin
Sebastien Pellerin
Joan Vila-FrancésJoan Vila-Francés
Joan Vila-Francés
The way we communicate has been revolutionised by the widespread use of social networks. Any kind of online message can reach anyone in the world almost instantly. The speed with which information spreads is undoubtedly the strength of social networks, but at the same time, any user of these platforms can see how toxic messages spread in parallel with likes, comments and ratings about any person or entity. In such cases, the victim feels even more helpless and defenceless as a result of the rapid spread. For this reason, we have implemented an automatic detector of toxic messages on social media. This allows us to stop toxicity in its tracks and protect victims. In particular, the aim of the survey is to demonstrate how traditional Machine Learning methods of Natural Language Processing (NLP) work on equal terms with Deep Learning methods represented by a Transformer architecture and characterised by a higher computational cost. In particular, the paper describes the results obtained by testing different supervised Machine Learning classifiers (Logistic Regression, Random Forest and Support Vector Machine) combined with two topic-modelling techniques of NLP, (Latent Semantic Analysis and Latent Dirichlet Allocation). A pre-trained Transformer named BERTweet was also tested. All models performed well in this task, so much so that values close to or above 90% were achieved in terms of the F1 score evaluation metric. The best result achieved by Transformer BERTweet, 91.40%, was therefore not impressive in this context, as the performance gains are too small compared to the computational overhead.

13 April 2022 in Acta Psychiatrica Scandinavica
Verified
Journal Article
Open access
JSJoan Vicent Sánchez‐Ortí
Joan Vicent Sánchez‐Ortí
Vicent Balanzá-MartínezVicent Balanzá-Martínez
Vicent Balanzá-Martínez
PGPatricia Correa Ghisays
Patricia Correa Ghisays
GVGabriel Vera
Gabriel Vera
Joan Vila-FrancésJoan Vila-Francés
Joan Vila-Francés
RTRafael Tabarés-Seisdedos
Rafael Tabarés-Seisdedos
Objective: Obesity and metabolic diseases such as metabolic syndrome (MetS) are more prevalent in people with type 2 diabetes mellitus (T2DM), major depressive disorder (MDD), bipolar disorder (BD), and schizophrenia (SZ). MetS components might be associated with neurocognitive and functional impairments in these individuals. The predictive and discriminatory validity of MetS and its components regarding those outcomes were assessed from prospective and transdiagnostic perspectives.Methods: Metabolic syndrome components and neurocognitive and social functioning were assessed in 165 subjects, including 30 with SZ, 42 with BD, 35 with MDD, 30 with T2DM, and 28 healthy controls (HCs). A posteriori, individuals were classified into two groups. The MetS group consisted of those who met at least three of the following criteria: abdominal obesity (AO), elevated triglycerides (TG), reduced high‐density lipoprotein cholesterol (HDL), elevated blood pressure (BP), and elevated fasting glucose (FPG); the remaining participants comprised the No‐MetS group. Mixed one‐way analysis of covariance and linear and binary logistic regression analyses were performed.Results: Cognitive impairment was significantly greater in the MetS group (n = 82) than in the No‐MetS group (n = 83), with small effect sizes (p < 0.05; η²p = 0.02 – 0.03). In both groups, the most robust associations between MetS components and neurocognitive and social functioning were observed with TG and FPG (p < 0.05). There was also evidence for a significant relationship between cognition and BP in the MetS group (p < 0.05). The combination of TG, FPG, elevated systolic BP and HDL best classified individuals with greater cognitive impairment (p < 0.001), and TG was the most accurate (p < 0.0001).Conclusions: Specific MetS components are significantly associated with cognitive impairment across somatic and psychiatric disorders. Our findings provide further evidence on the summative effect of MetS components to predict cognition and social functioning and allow the identification of individuals with worse outcomes. Transdiagnostic, lifestyle‐based therapeutic interventions targeted at that group hold the potential to improve health outcomes.

26 February 2025 in Information
Verified
Journal Article
Open access
PDF file
AHAntonio Herreros-Martínez
Antonio Herreros-Martínez
RMRafael Magdalena
Rafael Magdalena
Joan Vila-FrancésJoan Vila-Francés
Joan Vila-Francés
Antonio-José Serrano-LópezAntonio-José Serrano-López
Antonio-José Serrano-López
Sonia Pérez-DíazSonia Pérez-Díaz
Sonia Pérez-Díaz
José Javier Martínez HerraizJosé Javier Martínez Herraiz
José Javier Martínez Herraiz
In the era of increasing digitalisation, organisations face the critical challenge of detecting anomalies in large volumes of data, which may indicate suspicious activities. To address this challenge, audit engagements are conducted regularly, and internal auditors and purchasing specialists seek innovative methods to streamline these processes. This study introduces a methodology to prioritise the investigation of anomalies identified in two large real-world purchase datasets. The primary objective is to enhance the effectiveness of companies’ control efforts and improve the efficiency of anomaly detection tasks. The approach begins with a comprehensive exploratory data analysis, followed by the application of unsupervised machine learning techniques to identify anomalies. A univariate analysis is performed using the z-Score index and the DBSCAN algorithm, while multivariate analysis employs k-Means clustering and Isolation Forest algorithms. Additionally, the Silhouette index is used to evaluate the quality of the clustering, ensuring each method produces a prioritised list of candidate transactions for further review. To refine this process, an ensemble prioritisation framework is developed, integrating multiple methods. Furthermore, explainability tools such as SHAP are utilised to provide actionable insights and support specialists in interpreting the results. This methodology aims to empower organisations to detect anomalies more effectively and streamline the audit process.

1 July 2006 in Review of Scientific Instruments
Verified
Journal Article
Closed access
PDF file
Joan Vila-FrancésJoan Vila-Francés
Joan Vila-Francés
JCJavier Calpe-Maravilla
Javier Calpe-Maravilla
JMJordi Muñoz-Marí
Jordi Muñoz-Marí
Luis Gómez-ChovaLuis Gómez-Chova
Luis Gómez-Chova
JAJulia Amoros-Lopez
Julia Amoros-Lopez
VDVicente Durán-Bosch
Vicente Durán-Bosch
This article presents a new imaging spectrometer called autonomous tunable filtering system. The instrument acquires sequential images at different spectral wavelengths in the visible and near infrared range of the electromagnetic spectrum. The spectral selection is performed by an acousto-optic tunable filter (AOTF), which is driven by a custom radio-frequency (rf) generator based on a direct digital synthesizer (DDS). The DDS allows a high flexibility in terms of acquisition speed and bandwidth selection. The rf power is dynamically controlled to drive the AOTF with the optimum value for each wavelength. The images are formed through a carefully designed optical layout and acquired with a high performance digital camera. The application software controls the instrument and acquires the raw spectral images from the camera. This software optionally corrects the image for the AOTF nonidealities, such as diffraction efficiency variations, spatial nonuniformity, and chromatic aberration, and generates a single multiband image file. Moreover, the software can calculate the reflectance or transmittance of the acquired images. The instrument has been calibrated to give precise and repetitive measurements and has been validated against a high performance point spectrometer. As a case example, the instrument has been successfully used for the mapping of chlorophyll content of plant leaves from their multispectral reflectance images.

28 November 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
ARAlejandro Dionis Ros
Alejandro Dionis Ros
Joan Vila-FrancésJoan Vila-Francés
Joan Vila-Francés
RMRafael Magdalena
Rafael Magdalena
Fernando Mateo JiménezFernando Mateo Jiménez
Fernando Mateo Jiménez
Antonio-José Serrano-LópezAntonio-José Serrano-López
Antonio-José Serrano-López
In this article, we propose the detection of crowd anomalies through the extraction of information in the form of time series in video format using a multimodal approach. Through pattern recognition algorithms and segmentation, informative measures of the number of people and image occupancy are extracted at regular intervals, which are then analyzed to obtain trends and anomalous behaviors. Specifically, through temporal decomposition and residual analysis, intervals or specific situations of unusual behaviors are identified, which can be used in decision-making and the improvement of actions in sectors related to human movement such as tourism or security. This methodology introduces a novel, privacy-focused approach by analyzing anonymized metrics rather than tracking or recognizing individuals, setting a new standard for ethical crowd monitoring. Applied to the webcam of Turisme Comunitat Valenciana in the town of Morella (Comunitat Valenciana, Spain), this approach has shown excellent results, correctly detecting specific anomalous situations and unusual overall increases during the previous weekend and during the October 2023 festivities. These results have been obtained while preserving the confidentiality of individuals at all times by using measures that maximize anonymity, without trajectory recording or person recognition.