Mobile users can open program in new tab for better viewing.

Open program in new tab

Day 1 10/12/2020
Room #1

Welcome Message 09:00 - 09:20

CET time zone

PPG and Algorithms 09:20 - 10:20

Three papers on PPG signal processing and data extraction
09:20 - 09:40
Blood Pressure Estimation using a Single PPG Signal

Early Warning Score (EWS) is a measure commonly used in hospitals since 90's to quantitatively assess the health of patients and predict its deterioration. Currently, nurses perform this assessment periodically by measuring respiration rate, oxygen saturation, systolic blood pressure, heart rate, core body temperature, and level of consciousness. Automation of this process using wearable devices allows for continuous monitoring inside and outside hospitals while reducing nurses' workload and monitoring costs. Current systems designed for this purpose use a separate device for measuring each of those bio-metric signals. This presents a challenge for the comfort and practicality of use in a real-life setup and increases its associated costs. In this work, we present a new method for estimation of systolic blood pressure, which allows reduction of the number of sensors. In our proposed method we use a smartwatch Photoplethysmogram (PPG) signal, which is mainly used for hear rate estimation, to estimate the (systolic) blood pressure too. An important feature of this system, in contrast to State-of-the-Art (SoA), is continuous, easy, and comfortable monitoring of blood pressure.
Authors: Nima TaheriNejad (Institute of Computer Technology, TU Wien, Austria), Yasaman Rahmati (TU Wien),
Hide Authors & Abstract

Show Authors & Abstract
09:40 - 10:00
Multi-level Motion Artifacts Reduction in Photoplethysmography Signal using Singular Value Decomposition

Photoplethysmography (PPG) is used for measuring vital cardiopulmonary indi-ces such as heart rate and blood oxygen saturation (SpO2). But PPG signals get inevitably corrupted by movements of the patient and results in inaccurate calcula-tion of heart rate and SpO2. In this paper, we report a method that uses a multi-level singular value decomposition (SVD) technique for effective reduction of motion artifacts while preserving the PPG morphology along with baseline. Re-sults show impressive improvement on the signal quality and suppression of mo-tion artifacts of the PPG signal. The PPG signals without motion artifacts ob-tained using out proposed method shows an average error of 0.69 % in heart rate measurement with respect to the reference signal and an average max difference of 1.73 % in the SpO2 estimation (in comparison to the average max difference of 1.69 % for the reference signal). The proposed method has potential for accurate estimation of heart rate and SpO2 from PPG signal.
Authors: Shibam Debbarma, Seyedfakhreddin Nabavi (McGill University), Sharmistha Bhadra (McGill University),
Hide Authors & Abstract

Show Authors & Abstract
10:00 - 10:20
Intraoral Monitoring of Photoplethysmogram Signal to Estimate Cardiorespiratory Parameters

Photoplethysmograpghy (PPG) is a simple, non-invasive, optical method already known in clinical and home monitoring setups for its wide ap-plications in cardiorespiratory measurements such as heart rate, breathing, and blood oxygen saturation (SpO2). Here, we present an intraoral measurement of such cardiorespiratory parameters using a photoplethysmogram (PPG) sensor. A reflective PPG sensor is placed inside the oral cavity, facing the buccal mu-cosa opposite to upper jaw, and PPG signal is obtained. The average heart rate, breathing signal and average SpO2 variation are calculated from the intraoral PPG signal. Accuracy of the measured parameters are validated against stand-ard monitoring methods: a commercial PPG sensor mounted on the left index fingertip to monitor heart rate and SpO2 levels and a respiration monitoring belt worn around the diaphragm for breathing. Results obtained from subject’s tests show an average absolute error of 0.75 % in heart rate measurement and 5.83 % in breathing detection compared to standard references. Whereas, the average variation in SpO2 levels are 2.41 % and 1.35 % from the intra-oral measurement and the reference measurement, respectively. Intraoral measurement of such cardiorespiratory parameters can have useful applications such as smart man-dibular advancement devices to monitor sleep while treating patients with sleep apnea.
Authors: Shibam Debbarma, Sharmistha Bhadra (McGill University),
Hide Authors & Abstract

Show Authors & Abstract

IoT and Smart Sensors 10:20 - 12:20

Five papers on Internet of Medical things and different application of smart sensors
10:20 - 10:40
Empowering the Citizen in the Main Pillars of Health by Using IoT

To live longer, healthier, and more active, people at any age have to follow simple and clear suggestions that cover the 3 main pillars of health: physical activity, nutrition, and sleeping. Unfortunately, due to the intrinsic (e.g., daily-life habits) and extrinsic (e.g., environmental change) factors, people are far to have a healthy life and, thus, there is an increase of chronic diseases, mental disorders, and premature death. Approaches to increase citizen empowerment vary from self-management programs to those for promoting citizen (especially patients) involvement in treatment shared decision-making, to those to facilitating also the clinician-patient cooperation, when required. This paper presents the approach followed in CarpeDiem, an IoT-based system focused on self-management as a way to engage and empower citizens in order to improve their quality of life, to allow a better follow-up by clinicians in case of patients or elderly people, and to improve training in case of sportsmen.
Authors: Eloisa Vargiu (Eurecat, Centre Tecnòlogic de Catalunya, eHealth Unit), Meritxell Gómez-Martínez (Eurecat, Centre Tecnòlogic de Catalunya, eHealth Unit), Silvia Orte (Eurecat, Centre Tecnòlogic de Catalunya, eHealth Unit), Laura Ros-Freixedes (Eurecat, Centre Tecnòlogic de Catalunya, eHealth Unit), Kian Seif (Eurecat, Centre Tecnòlogic de Catalunya, eHealth Unit),
Hide Authors & Abstract

Show Authors & Abstract
10:40 - 11:00
Sharing Wearable Health Data using User-defined Blockchain Policies

Sharing Wearable Health Data using User-defined Blockchain Policies With recent advances in wearable technology and the rapid adoption of wearable devices, there are increased opportunities for setting up innovative data markets through which large amounts of user-generated physiological data can be made available to health researchers in at relatively low costs. However, given the sensitive nature of such data, a major challenge associated with realizing a trusted wearable data marketplace is ensuring fine-grained access control and assuring conformance to it. In this paper, we propose a policy-based approach for facilitating the secure exchange of data between the wearable owner and the health researcher. User-defined data-sharing policies are translated into executable smart contracts that provide deterministic and transparent execution of transactions as per the agreed usage terms and conditions. We also present a proof-of-concept implementation of the proposed policy-based access control mechanism using the open source Multichain platform.
Authors: Mohammad Jabed Morshed Chowdhury (La Trobe University, Melbourne, Australia), Alan Colman (Swinburne University of Technology), Mohan Baruwal Chhetri (CSIRO Data61, Melbourne, Australia),
Hide Authors & Abstract

Show Authors & Abstract
11:20 - 11:40
Wearable textile-based device for human lower-limbs kinematics and muscle activity sensing

Lower-limbs kinematics and muscle electrical activity are typically adopted as feedback during rehabilitation or athletes training to provide patients’ progress evaluation or athletic performance information. However, the complexity of motion tracking and surface electromyography (sEMG) systems limits the use of such technologies to laboratory settings and requires special training and expertise. This paper presents a new wearable textile-based muscle activity and motion sensing device for human lower-limbs, which is capable of recording and wirelessly transmitting sEMG data for several specific muscles as well as kinematic parameters, allowing outdoor and at-home use without direct supervision by non-expert users. In particular, this work is focused on the development and analysis of textile electrodes and garment design, as well as the definition of a proof-of-concept study for sEMG data recording. Obtained values were compared against average rectified values recorded using a gold-standard conventional wireless sEMG system. Apart from one muscle (vastus medialis), the developed device showed overall promising results in the muscle activity sensing, highlighting its possible use in the rehabilitation and sport performance fields. In addition, a washing test was conducted on the electrodes, where it was shown that the proposed textile electrodes maintained structural integrity and showed an acceptable level of electrical parameters deterioration.
Authors: Liudmila Khokhlova (Tyndall National Institute, UCC), Marco Belcastro (Tyndall National Institute, UCC), Pasqualino Torchia (Tyndall National Institute, UCC), Brendan O'Flynn (Tyndall National Institute), Salvatore Tedesco (UCC),
Hide Authors & Abstract

Show Authors & Abstract
11:40 - 12:00
Integration of Wearable Inertial Sensors and Mobile Technology for Outpatient Functional Assessment: a Paradigmatic Application to Evaluate Shoulder Stability

Wearable devices based on inertial measurement units (IMUs) are now-a-days a de facto standard in the field of human motion analysis. Lower costs, improved quality and enhanced accuracy have been supporting a very fast and diffused adoption of such devices in the healthcare and wellness areas. Specifically, in clinical settings, these technological solutions demonstrated to allow for a quanti-tative evaluation of functional and clinical tests. Several solutions are present on the consumer market, with peculiar advantages and general limitations. This arti-cle aimed to present a practical and feasible approach based on low-cost IMU-based wearable devices and mobile applications to rapidly collect 3D motion in-formation coming from different body segments. The proposed system was spe-cifically designed for a rapid and precise monitoring of the patient’s status both outdoor and indoor, including home and clinical contexts. The modularity concept in designing the application allows to easily plug specific and customized mod-ules addressing data analysis and patient status assessment. The acquired data are always available to the user thus, to be archived or re-processed. Without loss of generality, the developed system was tested in a real clinical context, addressing the need for assessing the shoulder mobility in order to automatically identify the presence of symptomatic or asymptomatic humerus-scapular dyskinesis.
Authors: Paolo Mosna, Manuela Morghen (Genetica Amica Association), Nicola Francesco Lopomo (Dipartimento di Ingegneria dell’Informazione, Università degli Studi di Brescia), Roberto Luongo (Genetica Amica Association),
Hide Authors & Abstract

Show Authors & Abstract
12:00 - 12:20
Multimodal Wearable System for Motor Rehabilitation - Design perspective and Development

Wearables can ease the transition towards a personalized medicine, bringing healthcare to anyone, anytime and anywhere. For wearable devices, human factors are essential; from conception to subsequent design phase. Current solutions are cumbersome and, despite they are designed according to standardized guidelines, they are developed for skilled users (physicians or engineers), without taking into consideration the real actors who will use and wear them: the patients. This paper aims to describe the application of a new methodology for integrating design and technology requirements in the development of wearable systems
Authors: Paolo Perego (Politecnico di Milano - Design dept), Roberto Sironi (Politecnico di Milano - Design dept), Martina Scagnoli (Politecnico di Milano), Angelo Davalli (CENTRO PROTESI INAIL), Emanuele Gruppioni (CENTRO PROTESI INAIL), Marcello Fusca (Politecnico di Milano),
Hide Authors & Abstract

Show Authors & Abstract

Lunch Break 12:20 - 13:30

Keynote 13:30 - 14:30

Keynote speaker Prof. David Atienza Title: "Mimicking the Brain for Energy-Minimal Smart Wearables

Innovation by Design 14:40 - 16:20

New design and concept definitions for innovation
14:40 - 15:00
Quality-by-Design Development of a Patient Mobility e-Monitoring System

Wearable sensors are a growing trend within the Internet-of-Things. Their use within many fields, such as e-Health, is more and more common and with such versatility and constraints due to their portable nature, it is important to achieve the best fine-tuning possible for the desired application. To this end, the application of the Quality-by-Design good practices of development could drastically ease the process. This study aims to apply the Quality-by-Design approach to the development of an e-monitoring solution of patient mobility. After defining the profiles of the targeted system, three critical quality attributes: autonomy, data upload duration and data integrity are defined. A criticality assessment study, based on the implementation of specific designs of experiments, is carried out to identify the most impacting process parameters. Finally, suitable operating modalities of the sampling rate, number of sensors, as well as uploading mode and period are determined to comply with the specifications on the three critical quality attributes.
Authors: Yaël KOLASA (CRAN, Université de Lorraine), Eliott GANDIOLE (Université de Lorraine), Thierry BASTOGNE (CRAN, Université de Lorraine),
Hide Authors & Abstract

Show Authors & Abstract
15:00 - 15:20
Wear-to-Care. Co-designing the Next Wave of Open Wearables in the Healthcare sector.

The paper explores the topic of design, materialization and release of open source wearables that can increase the social awareness about the mental, behavioral and physical conditions of people with health impairments. The first part, which is based on literature review, investigates the design of healthcare wearables connected to the emerging phenomena of open and us-er innovation. The second part describes the whole process of design and materialization of DermAware, an open source “experiential” wearable de-veloped within the project Distributed Design Market Platform (Creative Europe Programme) and specifically conceived to increase the social aware-ness on a pathology such as Atopic Dermatitis. The final part defines an op-erational framework to design open source wearables, evidencing the pro-cess - from design to materialization – and the main critical aspects and op-portunities related to the development of “experiential” devices. The con-clusions of the paper identify a possible field for designing healthcare wearables called “Wear-to-Care”.
Authors: Massimo Bianchini (Politecnico di Milano), Patrizia Bolzan (Politecnico di Milano), Barbara Parini (Politecnico di Milano), Stefano Maffei (Politecnico di Milano), Filippo Cipriani (Sanofi Genzyme),
Hide Authors & Abstract

Show Authors & Abstract
15:20 - 15:40
Parametric Design and Data Visualization for Orthopedic Devices

The paper aims to illustrate the ongoing research based on the development of orthopedic devices, characterized by the integration between parametric design and data visualization, for the product customization on specific morphologies and needs of users, and the return of information of the course and therapeutic advancement made readable for both, patients and doctors. As highlighted by the scientific literature and by the state of arts, nowadays always more the convergence between design, medicine, and data analysis/mining, is the experimental field for the research and develop of innovative biomedical devices, which integrate users as proactive part of the design and treatment processes, thanks to the integration of different methods and techniques of design: as Sabine and Dietrich affirm, design of orthopedics devices based on systems of parametric and generative prototyping, let's get a high level of personalization of medical devices (2017), which can be enriched by the integration of different kind of sensors which returns complex and scientific information. The extraction, analysis, and translation of these data, make it possible to represent this complexity in visual form making it readable not only for the scientific community of reference but for a wider range of users (Stoll, 2014).
Authors: Gabriele Pontillo (Università degli Studi della Campania "Luigi Vanvitelli"), Roberta Angari (Università degli Studi della Campania "Luigi Vanvitelli"), Carla Langella (Università degli Studi della Campania "Luigi Vanvitelli"),
Hide Authors & Abstract

Show Authors & Abstract
15:40 - 16:00
Design of an innovative integrated system for upper limb prosthesis

Nowadays the prosthetic system can be configured as a multifactorial set that includes reciprocal relationships between the stump, the socket, the prosthesis and the tridigital/ robotic hand. This system presents some critical issues that can be addressed by improv-ing the integration between the parts and redesigning some components through innova-tive design-driven solutions. The paper describes the design of a sensorized liner for upper limb prostheses according to the User Centered Design methodology, focusing on the socket - which is conceived as an integrated system composed by Hypermat (the external rigid meta-structure) and the sensorized liner. The system was designed on the basis of the results that emerged in the focus group which involved amputee users, technologists and a heterogeneous set of design figures. The project requirements on which the liner development and its integration with the Hypermat metastructure were based were defined. The paper describes the design of the sensorized liner taking into consideration the choice of materials, the application of myoe-lectric textile sensors and pressure sensors, the connector design for the connection be-tween sensors and circuitry, the assembly and production methods.
Authors: Roberto Sironi (Politecnico di Milano - Design dept), Paolo Perego (Politecnico di Milano), Giuseppe Andreoni (Politecnico di Milano), Emanuele Gruppioni (CENTRO PROTESI INAIL), Angelo Davalli (CENTRO PROTESI INAIL), Simone Pittaccio (CNR ICMATE), jacopo Romanò (CNR ICMATE), Lorenzo Garavaglia (CNR ICMATE),
Hide Authors & Abstract

Show Authors & Abstract
16:00 - 16:20
Participant modeling: The use of a guided master in the modern world of Virtual Reality Exposure Therapy

With the percentage of mental health disorders on the rise and the cost for their treatment reaching astounding proportions, research in their treatment has also become quite extensive. Individuals suffering from the effects of their disorder constituting them incapable at various levels to lead a normal life, the need for a more effective treatment has been well established. We have focused on anxiety disorders specifically, which have mainly fear as their common denominator, and using this we decided to look into the role of the clinician in live ET sessions so as to examine whether this role can be replicated in a VRET simulation with similar or better outcomes for the patient, i.e. a more effective treatment. Our hypothesis was tested in an out-patient setting with patients being separated into two groups. We examined whether the presence of a virtual guided master using participant modeling in a virtual environment was as effective or more effective than the Standard ET method. Data on the outcomes were gathered via the Session Rating Scale by Miller which led to the conclusion that participant modeling with-in a VRET approach can lead to a better treatment quality.
Authors: Pamela Caravas (McLean Hospital, Harvard Medical School Affiliate, Boston MA, United States), Dimitris Koutsouris (Biomedical Engineering Laboratory, National Technical University of Athens), Giorgos Alevizopoulos (National Kapodistrian University of Athens), Jacob Kritikos (National Technical University of Athens),
Hide Authors & Abstract

Show Authors & Abstract

Wearable Applications 16:20 - 17:30

Three different application of wearbale devices.
16:30 - 16:50
Automatic assessment of Clinical Frailty of Parkinson’s Disease subjects by wearable actigraphy

A wearable actigraph was applied in the functional assessment of subject affected by Parkinson Disease in Day Hospital setting. 24 PD patients participated in this study. A set of standard functional tests (6MWT, TUG, 10-meter and 50-meter) were administered to collect data of functioning and physiatrist assigned the score according to the Clinical Frailty Scale. An automatic evaluation of this frailty score is proposed using data from 6MWT and TUG. The coherence of this automated classification method based on a basic summative linear equation of the 2 functional scores, is 66,7% with respect to the score assigned by skilled physiatrists. The inclusion of the other tests is expected to improve reliability and the possibility to have an automatic identification of the frailty level through quantitative data could open the possibility to have a more detailed assessment and even continuous and domiciliary follow ups.
Authors: Marcello Fusca (Politecnico di Milano), Emanuela Riva (A.S.P. “Golgi-Redaelli”), Paolo Perego (Politecnico di Milano - Design Dept.), Francesca Omini (Università degli Studi di Milano-Bicocca), Emanuele Conte (A.S.P. “Golgi-Redaelli”), M Impallomeni (A.S.P. “Golgi-Redaelli”), Stefania Rosaspina (A.S.P. “Golgi-Redaelli”), Antonio Grillo (A.S.P. “Golgi-Redaelli”), Teresa Suardi (A.S.P. “Golgi-Redaelli”), Stefano Fabbrini (A.S.P. “Golgi-Redaelli”), Giuseppe Andreoni (Politecnico di Milano),
Hide Authors & Abstract

Show Authors & Abstract
16:50 - 17:10
Development of a wearable sensors system to monitor foot-transmitted vibration

Exposure to mechanical vibration may lead to harmful effect on the human body if it does not occur in a controlled environment. ISO 2631-1 regulates how to measure the vibration exposure and provides safety limits. According to this standard, the acceleration signals should be measured at the interface between the vibrating surface and the human body, for a time interval long enough to represent a whole working shift. This is impossible to achieve in the case of foot-transmitted vibration, as standard equipment cannot fit between the foot and the floor. For this reason, a new system of sensors has been devel-oped to be small enough to fit inside a regular foot insole. This system is pow-ered through batteries and transmit the data to a regular cellphone through the Bluetooth connection, thus enabling a precise and continuous measurement. After production, the system has been validated by comparing the vibration exposure with the one measured by standard piezo-electric accelerometers. The validation process took place both in laboratory controlled conditions and in real outdoor conditions. The experimental results show a root-mean-squared error in the evaluation of vibration exposure lower than 0.1 m/s2, thus proving the potential of the proposed system.
Authors: Alex P. Moorhead (Politecnico di Milano, Mechanical Dept.), Pietro Marzaroli (Politecnico di Milano, Mechanical Dept.), Marco Tarabini (Politecnico di Milano, Mechanical Dept.), Manuela Galli (Politecnico di Milano, E4 Sport Lab), Filippo Goi (Vibram Spa), Roberto Caimi (Sires s.r.l.),
Hide Authors & Abstract

Show Authors & Abstract
17:10 - 17:30
ADLs Detection with a Wrist-Worn Accelerometer in Uncontrolled Conditions

In 2017, the European Commission estimated that 29% of European population will be aged 65 and over, by 2070. The capability of tracking and recognizing people's daily activities may promote and support an active and independent lifestyle. In this regard, Human Activity Recognition allows to obtain meaningful information by monitoring daily activities using wearable devices, that are small, easy to use, and minimally invasive. In this paper, we discuss the recognition performance of six machine learning classifiers applied to accelerometer data only. Data was collected by 36 individuals, wearing a single wrist-worn sensor to monitor six daily activities pertaining to Hygiene and House Cleaning scenarios. Following a pre-processing phase, both temporal and frequency features were computed to classify and recognize the collected real-world data. The study presents some statistical results obtained from each classifier in order to compare their performance. The findings of experiments are promising for the adoption of the Random Forest classifier in Human Activity Recognition with acceleration data from a single wrist-worn device.
Authors: Angelica Poli (Università  Politecnica delle Marche), Susanna Spinsante (Università Politecnica delle Marche), Sandro Fioretti (Università Politecnica delle Marche), Annachiara Strazza (Università Politecnica delle Marche), Marica Olivastrelli (Università Politecnica delle Marche),
Hide Authors & Abstract

Show Authors & Abstract

Closing Message and Best paper 17:30 - 17:40

Day 2 11/12/2020