Biometric Signals-Based Artificial Intelligence Technologies for Health Assessment

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Applied Biosciences and Bioengineering".

Deadline for manuscript submissions: closed (25 May 2022) | Viewed by 2710

Special Issue Editors

Telecom SudParis, Institut Polytechnique de Paris, 91120 Palaiseau, France
Interests: pattern recognition; signal processing; data-driven machine learning methods; speech, speaker and language recognition; biometrics (2D and 3D face and voice); crypto-biometrics (including privacy preserving biometrics); human–machine interaction; detection and assessment of neurodegenerative diseases from biometric signals
Telecom SudParis, Institut Polytechnique de Paris, 91120 Palaiseau, France
Interests: machine learning; deep learning; pattern recognition; modeling behavioral and physiological human data; human activity and gesture recognition; handwriting and voice analysis; human mobility analysis; biometrics; human–computer interaction; detection and assessment of neurodegenerative diseases from biometric signals
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Biometrics, in the scientific and the industrial circles, refers to technology consisting in identifying or authenticating people based on their biometric signals, i.e., their physiological and behavioral traits, such as their voice, face, iris, handwriting, gait, etc. This field has been the subject of research for decades, and technological solutions have been deployed at a large scale for access control in airports, government facilities, schools, etc. The main factors behind these success stories are twofold: the availability of large biometric datasets, and the systematic application of effective machine learning and, more recently, deep learning models for classification.

Driven by their success in the security context, more recently, researchers have started to investigate the harnessing of biometric signals in the e-health context, with the objective of developing digital biomarkers that can serve as an aid to diagnose medical conditions or for detecting a health status, such as stress or depression. These endeavors, however, are facing several challenges associated with the lack of sufficient training data related to e-health, the need for decision understandability by the stakeholders, and the optimal specificity and sensitivity required for these tools to be usable in practice. As a result, the artificial intelligence techniques considered in the e-health field should, among others, be based on sound transfer learning from the security context to the health one, be as interpretable as possible, and be assessed according to sound evaluation metrics.

This Special Issue aims at gathering recent interdisciplinary research advancements in artificial intelligence algorithms, particularly advanced machine/deep learning methods that harness biometric signals to develop tools for aiding diagnosis and, in general, to assess an individual’s health status. The Special Issue seeks to bring together academics, physicians, and industry professionals to contribute to and discuss the latest research and innovations in this field.

Dr. Dijana Petrovska-Delacrétaz
Prof. Dr. Mounim A. El Yacoubi
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • biometrics for identification and authentication
  • e-health assessment based on biometric signals and digital biomarkers
  • neurodegenerative diseases, medical imaging, stress, depression, and emotions
  • face, voice, gait, handwriting, ECG, and EEG
  • machine leaning/deep learning
  • convolutional neural networks, recurrent neural networks, and transformers
  • transfer learning
  • interpretability and explainability
  • evaluation metrics
  • artificial intelligence and ethics and privacy

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

17 pages, 3428 KiB  
Article
Application of a Deep Learning Neural Network for Voiding Dysfunction Diagnosis Using a Vibration Sensor
by Yuan-Hung Pong, Vincent F.S. Tsai, Yu-Hsuan Hsu, Chien-Hui Lee, Kun-Ching Wang and Yu-Ting Tsai
Appl. Sci. 2022, 12(14), 7216; https://doi.org/10.3390/app12147216 - 18 Jul 2022
Cited by 2 | Viewed by 1996
Abstract
In a clinical context, there are increasing numbers of people with voiding dysfunction. To date, the methods of monitoring the voiding status of patients have included voiding diary records at home or urodynamic examinations at hospitals. The former is less objective and often [...] Read more.
In a clinical context, there are increasing numbers of people with voiding dysfunction. To date, the methods of monitoring the voiding status of patients have included voiding diary records at home or urodynamic examinations at hospitals. The former is less objective and often contains missing data, while the latter lacks frequent measurements and is an invasive procedure. In light of these shortcomings, this study developed an innovative and contact-free technique that assists in clinical voiding dysfunction monitoring and diagnosis. Vibration signals during urination were first detected using an accelerometer and then converted into the mel-frequency cepstrum coefficient (MFCC). Lastly, an artificial intelligence model combined with uniform manifold approximation and projection (UMAP) dimensionality reduction was used to analyze and predict six common patterns of uroflowmetry to assist in diagnosing voiding dysfunction. The model was applied to the voiding database, which included data from 76 males aged 30 to 80 who required uroflowmetry for voiding symptoms. The resulting system accuracy (precision, recall, and f1-score) was around 98% for both the weighted average and macro average. This low-cost system is suitable for at-home urinary monitoring and facilitates the long-term uroflow monitoring of patients outside hospital checkups. From a disease treatment and monitoring perspective, this article also reviews other studies and applications of artificial intelligence-based methods for voiding dysfunction monitoring, thus providing helpful diagnostic information for physicians. Full article
Show Figures

Figure 1

Back to TopTop