This thesis describes the work performed during the internship at Healthy Reply, an Italian ICT company specialized in e-health. I was part of the team of TWB - Therapeutic Wearable Virtual Reality and Biosensors, an EC funded project in therapeutic services sector that employs Virtual Reality to support the treatment of phobias and mental disorders, and biosensors to gather user’s physiological parameters in real time and derive measures of the user inner state (e.g., distress). The TWB project is coordinated by Healthy Reply and involves two additional partners: IMEC NL and Politecnico di Milano. The goal of my thesis was to integrate TWB devices and service in Ticuro, the existing telemedicine platform commercialized by Reply, and to empower the flexibility and services office of this system. One of the main challenges of my work are related to solving different kinds of integration issues, embedding algorithms concerning signal processing and exploring methods to fully exploit biometric data in the perspective of post session analysis. The TWB components are an aggregation of various elements, each one requiring the use of different technologies. In particular, integrating the Chillband biosensor provided by IMEC, which tracks multiple physiological signals, was problematic, because of the mismatch between the Ticuro environment and IMEC software managing the biosensor. An additional challenge was the integration of biomedical algorithms concerning the elaboration of specific signals extracted from commercial biosensors. Those algorithms were developed by biomedical researchers in Matlab, which was appropriate for stand-alone data analysis but difficult to integrate into Ticuro. Furthermore, the thesis involved the exploration of Machine Learning techniques to enable the development of data analysis advanced tools for therapists, offering them new insights on the patients’ behavior during virtual reality therapeutic sessions.
Questa tesi illustra il lavoro portato avanti nel corso dello stage presso Healthy Reply, azienda ICT italiana specializzata nel settore e-health. Ho fatto parte del team di lavoro su TWB - Therapeutic Wearable Virtual Reality and Biosensors, progetto finanziato dalla Comunità Europea nel settore dei servizi terapeutici. TWB impiega la realtà virtuale a supporto del trattamento di fobie e disturbi mentali, e biosensori per raccogliere in tempo reale i parametri fisiologici dell’utente e ricavare informazioni sullo stato interiore del paziente stesso (ad esempio, angoscia). Il progetto è coordinato da Healthy Reply e coinvolge altri due partner: IMEC NL ed il Politecnico di Milano. L’obiettivo della mia tesi era l’integrazione dei servizi e dispositivi di TWB in Ticuro, la piattaforma di telemedicina distribuita da Reply, e potenziare la flessibilità ed i servizi di questo sistema. Uno dei passaggi chiave del mio lavoro riguardava la risoluzione di diverse tipologie di problemi di integrazione, inserendo gli algoritmi di elaborazione dei segnali e valutando metodologie per sfruttare pienamente i dati biometrici in un contesto di analisi a sessione terminata. I componenti di TWB aggregano vari elementi, ognuno dei quali richiede l’utilizzo di diverse tecnologie. In particolare, l’integrazione del biosensore Chillband, fornito da IMEC ed in grado di tracciare segnali fisiologici differenti, era problematica, a causa della mancanza di uno standard di comunicazione condiviso tra l’ambiente di Ticuro ed il software di Imec che gestisce il biosensore stesso. Ulteriore sfida era l’integrazione degli algoritmi biomedici finalizzati all’elaborazione di specifici segnali estratti dai biosensori distribuiti. Tali algoritmi erano stati sviluppati dai ricercatori di Ingegneria Biomedica in Matlab, strumento appropriato per un approccio di analisi dei dati stand-alone ma difficile da integrare in Ticuro. Inoltre, la tesi ha incluso l’esplorazione di tecniche di Machine Learning per permettere lo sviluppo di avanzati strumenti di analisi dei dati a supporto dei terapisti, offrendo loro nuove informazioni sul comportamento dei pazienti nel corso delle sessioni terapeutiche con realtà virtuale.
Improving flexibility and services of a therapeutical web platform : the TWB use case
LUCCA, MATTIA
2018/2019
Abstract
This thesis describes the work performed during the internship at Healthy Reply, an Italian ICT company specialized in e-health. I was part of the team of TWB - Therapeutic Wearable Virtual Reality and Biosensors, an EC funded project in therapeutic services sector that employs Virtual Reality to support the treatment of phobias and mental disorders, and biosensors to gather user’s physiological parameters in real time and derive measures of the user inner state (e.g., distress). The TWB project is coordinated by Healthy Reply and involves two additional partners: IMEC NL and Politecnico di Milano. The goal of my thesis was to integrate TWB devices and service in Ticuro, the existing telemedicine platform commercialized by Reply, and to empower the flexibility and services office of this system. One of the main challenges of my work are related to solving different kinds of integration issues, embedding algorithms concerning signal processing and exploring methods to fully exploit biometric data in the perspective of post session analysis. The TWB components are an aggregation of various elements, each one requiring the use of different technologies. In particular, integrating the Chillband biosensor provided by IMEC, which tracks multiple physiological signals, was problematic, because of the mismatch between the Ticuro environment and IMEC software managing the biosensor. An additional challenge was the integration of biomedical algorithms concerning the elaboration of specific signals extracted from commercial biosensors. Those algorithms were developed by biomedical researchers in Matlab, which was appropriate for stand-alone data analysis but difficult to integrate into Ticuro. Furthermore, the thesis involved the exploration of Machine Learning techniques to enable the development of data analysis advanced tools for therapists, offering them new insights on the patients’ behavior during virtual reality therapeutic sessions.File | Dimensione | Formato | |
---|---|---|---|
tesi_mattia_lucca.pdf
accessibile in internet solo dagli utenti autorizzati
Descrizione: Testo della tesi
Dimensione
1.66 MB
Formato
Adobe PDF
|
1.66 MB | Adobe PDF | Visualizza/Apri |
I documenti in POLITesi sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/10589/152289