Wireless Mobile Communication and Healthcare

In this paper, we present the potential of a device, originally designed for energy harvesting, to form a self-powered medical implant that monitors critical parameters of the cardiovascular system. The original design consists of a coil that deforms with an artery inside magnetic field applied by two permanent magnets. We fabricated the device, and developed appropriate experimental setup that simulates blood flow and arterial wall pulsation with adjustable frequency and pressure. The voltage and power of the moving coil, as well as the pressure inside the tube simulating the pulsating artery were measured at different frequencies. In-vitro experiments and theoretical analysis showed that the voltage induced across the coil’s terminals can provide information on blood pressure, heart rate, arterial wall deformation and velocity.

In studies of human biomechanics utilizing inertial sensors, motion sensor units of type Xsens are recognized as the state-of-the-art. However, the requirement to use them with a personal computer for collecting and processing data could be a limiting factor. In the present work, we demonstrate a simple solution to using up to four Xsens MTx units with a custom portable base station. The base station is capable of obtaining data from Xsens MTx units, processing the data and saving them to an SD card. Thus, it allows the use of the units outside laboratory settings without the need of a personal computer, the capability to directly use onboard custom algorithms to process the data of several units in real time, and interconnectivity with external systems for synchronized collection of multimodal data. We demonstrate these benefits by two examples: synchronized collection of data from an Xsens MTx unit and a Footscan® plantar pressure plate, and knee angle measurement using two Xsens MTx units that we validated by synchronized recording of goniometric data.

Falls might cause serious traumas especially among elderly people. To deliver timely medical aid, fall detection systems should be able to notify appropriately personnel immediately, when fall occurs. However, as in any system, notification mechanism affects overall energy consumption. Considering that energy efficiency affects reliability, as it influences runtime of the system, notification mechanism should be energy aware. We propose an IoT-enabled fall detection system with a messenger-based notification method, which allows to obtain energy efficient solution, decrease development time and allow to reuse facilities of a popular messaging platform.

Understanding ingredients or additives in food is essential for a healthy life. The general public should be encouraged to learn more about the effect of food they consume, especially for people with allergy or other health problems. However, reading the ingredient label of every packaged food is tedious and no one will spend time on this. This paper proposed a mobile app to leverage the troublesome and at the same time provide health advices of packaged food. To facilitate acquisition of the ingredient list, apart from barcode scanning, we recognize text on the ingredient labels directly. Thus, our application will provide proper alert on allergen found in food. Also it suggests users to avoid food that is harmful to health in long term, like high fat or calories food. A preliminary user study reveals that the adviser app is useful and welcomed by many users who care about their dietary.

User Engagement is a keyword employed by software companies, researchers, and developers designing user-centred applications. Indeed, designing digital experiences to engage users is a goal that is becoming increasingly important for several disciplines such as education, marketing, information systems, and much more. Since opinions concerning the definition of user engagement greatly vary, the question comes up whether it is possible to provide a universal set of metrics to equally measure the engagement in any kind of application and in mobile applications in particular. Starting from results in the literature, this paper provides a simple definition of user engagement and a related set of metrics. Such metrics will be evaluated in a pilot study with more than 300 teenagers in four European countries.

Adolescence is a vulnerable stage in which the development of certain unhealthy behaviours can occur. The prevalence of overweight and obesity among European teenagers is rapidly increasing and may lead to both short- and long-term health complications. The fast development of the ICT, and in particular mobile technologies, together with their increasing diffusion among the EU populations offers an important opportunity for facing these issues in an innovative manner introducing the possibility of a new technological framework to re-design the healthcare system model. The PEGASO project relies on a mobile-and cloud-based ICT platform to set up a system of new healthcare services targeted to teens for obesity prevention. The present paper describes the protocol of a six-month Pilot Study that will be carried out on 525 adolescents in four different European sites (Italy, Catalonia, England, Scotland), aiming to evaluate the PEGASO system usability and effectiveness in promoting healthy lifestyles.

Promoting healthy lifestyles can be a successful weapon in counter-fighting the epidemics of overweight and obesity. The PEGASO project aims at encouraging adolescents to become co-creators of their own health. In particular, it aims at creating an ecosystem where adolescents are motivated and supported in adopting healthy lifestyles. In this ecosystem, the PEGASO Companion, a smartphone app, plays the role of universal access to healthy services and providing personalised mechanisms to support behaviour change.

According to the National institute on Aging, 8% of the world’s population is over 65 or older. There is a need for a long term care and a remote home-care environment for the aging population using smart technologies as this number expected to double by 2050. With the advancement of embedded sensing technologies, wireless sensing technologies have been used to monitor user’s activities and maintain a healthy lifestyle. In this paper, we develop a Smart Medication Alert and Treatment Electronic Systems (SmartMATES) using a non-intrusive wearable sensor system to detect and prevent a home-based patient from missing his or her medication. The sensor collects and processes both the accelerometer and radio signal strength measurement on the left and right wrist. Based on the data collected, SmartMATES correlates the left and right wrist accelerometer reading to model the action of taking medication. If SmartMATES detects the patient is not taking the medication within a time-frame, it will be send an alert to the mobile phone to remind the users to take their medication. We have evaluated the SmartMATES on 9 participants. The results show that the SmartMATES can identify and prevent missing dosage in a less intrusive way than existing mobile application and traditional approaches.

Wearable devices, e.g. smart-watches, are gaining popularity in many fields and in wellness monitoring too. In this paper we propose an IoT application to alert the medical doctor assigned to a critical unit by using a smart-watch. The wearable device improves the efficacy of monitoring patients at risk in hospital units allowing the medical doctor to access information at any time and from any place. A network was built to wirelessly connect bio-sensing platforms, which measure metabolites concentration in patients’ fluids (e.g. blood), with a dedicated application running on the smart-watch. In case of anomalous measured values, incoming alert notifications are received to ask urgent medical intervention. The main advantage of this new approach is that the doctors, or in general the caregivers, can freely move in the hospital other structures and perform other tasks meanwhile simultaneously and constantly monitoring all the patients thanks to the technology on their wrist.

Project Sherpam (Sensors for HEalth Recording and Physical Activity Monitoring) aims to provide an open-source, flexible, customizable system to monitor the health condition of patients affected by chronic diseases during their day to day activities at home or out of home, while detecting and reacting to anomalies automatically. This paper presents the architecture of the flexible system that is being developed in the context of this project, and illustrates how this system could be used through a realistic use case.

Affecting up to 40% of the world’s population, arterial hypertension results in high economic and social burden. Long-term treatment period along with the necessity of personal lifestyle changes lead to the low adherence to the treatment among the patients. As a consequence, the hypertension-related complications can be gradually developed between visits to the doctor, among them are heart attack, heart failures, strokes and even sudden cardiac death. In the proposed integrated approach, the mobile personal monitoring system, constructed on the principles of smart spaces, is used to address the problem of low adherence. Both continuous monitoring of the vital signs and the questionnaire-based regular health status audit are used for the assessment of the complication risk. Health parameters and evaluated risk markers are published in the semantic-driven information storage, and the personalized recommendation service, aimed at the increasing the adherence to the treatment among hypertensive patients, is constructed based on cooperation of distributed software agents.

Early Warning Score (EWS) systems are utilized in hospitals by health-care professionals to interpret vital signals of patients. These scores are used to measure and predict amelioration or deterioration of patients’ health status to intervene in an appropriate manner when needed. Based on an earlier work presenting an automated Internet-of-Things based EWS system, we propose an architecture to analyze and enhance data reliability and consistency. In particular, we present a hierarchical agent-based data confidence evaluation system to detect erroneous or irrelevant vital signal measurements. In our extensive experiments, we demonstrate how our system offers a more robust EWS monitoring system.

This study presents the application of a wearable monitoring system for the assessment of tic events in subjects affected by Tourette Syndrome (TS). A multifactorial analysis and validation of the proposed system is carried out collecting simultaneous and synchronized recordings of data from the wearable actigraph and from two video cameras that allowed two medical doctors with different expertise to classify the motor events as tics and their related severity scale. A dedicated software implements the algorithm for automatic tic detection and to compare this assessment with the standard video recording protocol used to discriminate and classify tic events of high intensity and tic event of low intensity (facial grimacing or vocal tics). Double blind analysis on a nine subjects allowed us to compare the variability between operators and wearable device, and conclude the system has good potential but algorithms refinement is still needed before its possible application in clinical practice. Currently it still requires the integration with a video analysis protocol if the tics are mild or are vowels giving a complete clinical frame.

With the advancement of technology, non-intrusive monitoring of some physiological signals through smart watches and other wearable devices are made possible. This provides us with new opportunities of exploring newer fields of information technology applied in our everyday lives. One application which can help individuals with difficulty in expressing their emotions, e.g. autistic individuals, is emotion recognition through bio-signal processing. To develop such systems, however, a significant amount of measurement data is necessary to establish proper paradigms, which enable such analyses. Given the sparsity of the available data in the literature, specifically the ones using portable devices, we conducted a set of experiments to help in enriching the literature. In our experiments, we measured physiological signals of various subjects during four different emotional experiences; happiness, sadness, pain, and anger. Measured bio-signals are Electrodermal activity (EDA), Skin Temperature, and Heart rate. In this paper, we share our measurement results and our findings regarding their relation with happiness, sadness, anger, and pain.

The objective of the study is to develop a methodology for gathering data on phalanges to be utilised in wearable technology research with the potential to assist Raynaud’s Phenomena (RP) sufferers. This paper gives an overview of a pilot study using a method developed from an existing medical practise called ‘cold challenge’, which is used in the clinical analysis of RP, and amended for data collection. Due to the alterations that differentiate the pilot study from the clinical exam, it is expected that adjustments will be required to the methodology before a full study is undertaken. The paper centres on the pilot study and the developments made through the analysis of the pilot study results for implementation in further research. The pilot study illustrates a method trialled in the early stages of R&D within PhD design research.

The Internet of Medical Things (IoMT) can be described as connecting everyday devices and wearables to the Internet in order to intelligently link them together, thus enabling new forms of communication between things (medical devices) and people (patients) and between things themselves. This paper describes a context-aware access control model that hinges on the role-based and attribute-based access control (RABAC) and the capability-based access control (CapBAC) models. A prototype access control mechanism based on the model is intended to be incorporated into a personal health record (PHR) platform.

This work describes a standard conform Java based modular IoT framework for context-aware applications for AAL and home care. An extensive support of Bluetooth Low Energy personal health devices as well as various home sensor networks is provided.

In this paper we will present the prototype of a system meant to quantitatively and continuously monitor the information measured during the daily use of powered wheelchairs, early adopted by severely impaired children. The system is based on a non-conventional use of a common smartphone, and it may represent an interesting application for long-term remote monitoring of health-related information.

Billions of interconnected neurons are the building block of the human brain. For each brain activity these neurons produce electrical signals or brain waves that can be obtained by the Electroencephalogram (EEG) recording. Due to the characteristics of EEG signals, recorded signals often contaminate with undesired physiological signals other than the cerebral signal that is referred to as the EEG artifacts such as the ocular or the muscle artifacts. Therefore, identification and handling of artifacts in the EEG signals in a proper way is becoming an important research area. This paper presents an automated EEG artifacts handling approach, combining Wavelet transform, Independent Component Analysis (ICA), and Hierarchical clustering. The effectiveness of the proposed approach has been examined and observed on real EEG recording. According to the result, the proposed approach identified artifacts in the EEG signals effectively and after handling artifacts EEG signals showed acceptable considering visual inspection.

Health status measurements are vital in understanding a patient’s health. However, current means of measuring health status, such as questionnaires, are limited. Research has shown that there is a need for more objective and accurate methods of measuring health status. We postulate that novel sensor solutions could be used to make observations about a patients’ behaviour and make predictions relating to their health status. In order to achieve this overall goal, the problem of building a dataset comprising behaviour observations, from sensors, and health status measure must be addressed. In this work, we propose a crowd-sourced solution to this dataset problem where a Smartphone App is developed in order to facilitate in the collection of behaviour data, via sensors, and health status information. Results show that, after just 4 months, 1311 people have downloaded the App and 541 participants have completed a health status questionnaire (SF-36). Preliminary analysis of the data also shows a statistically significant correlation between the amount of time a participant is active and the health status of the participant.

Background: The use of mobile applications in dermatology to support remote diagnosis is becoming more important each day, particularly in rural areas where dermatology services are commonly managed by healthcare personnel with no speciality training.Objective: The aim of this study is to assess the reliability of mobile applications to support remote dermatological diagnosis, when used together with a dermatological ontology in underprivileged areas.Methods: A mobile application that allows characterization of skin lesions was developed. The experiment was conducted in a remote area without access to a dermatologist. A total of 64 dermatological queries were recorded in the mobile application.Results: The results showed that the probability of obtaining a correct diagnosis was between 64.4% and 85.6% and a confidence interval of 95%.Conclusions: This study demonstrates the implementation of a Teledermatology strategy based on mobile applications and domain ontology-driven knowledge base to provide timely assistance to healthcare professionals. This approach was found to be pertinent in the Colombian rural context, particularly in forest regions where dermatology specialists are not available.

Context information, in particular location changes as indicator for motoric activity, are indicators for state changes of patients suffering from affective disorders. Traditionally, such information is assessed via self-report questionnaires. However, this approach is obtrusive and requires direct involvement of the patient. Related work already started to rely on unobtrusively gathered smartphone data. Despite its ubiquitousness, WiFi data was barely considered yet. Due to the increasing availability of public hot spots we want to focus on this data source. We investigate the usefulness of WiFi data in two use cases: detect location changes and estimate the number of nearby persons. In a two-week study we captured MAC addresses, WiFi SSIDs and timestamps to identify current location and location changes of ten subjects in a five minute interval. We achieved a recall of 98% for location changes which proves the usability of WiFi data for this purpose. We confirm a basic feasibility of using WiFi data for unobtrusive, opportune and energy-efficient detection of location changes.

We have developed a rapid remote health monitoring architecture called RASPRO using wearable sensors and smartphones. RASPRO’s novelty comes from its techniques to efficiently compute compact alerts from sensor data. The alerts are computationally fast to run on patients’ smartphones, are effective to accurately communicate patients’ severity to physicians, take into consideration inter-sensor dependencies, and are adaptive based on recently observed parametric trends. Preliminary implementation with practicing physicians and testing on patient data from our collaborating multi-specialty hospital has yielded encouraging results.

Arrhythmia related disorders are one of the leading causes of cardiac deaths in the world. Previous studies have shown that Arrhythmia can further lead to major cardiac diseases like the Sudden Cardiac Death (SCD) syndrome. The difficulty in detecting Arrhythmia in the early stages often results in poor prognosis and presents the need for a costefficient diagnostic device. To this end, we propose a realtime portable ECG device with special emphasis on Arrhythmia detection and classification. The device is centered on a Raspberry Pi 3 (RasPi) module. RasPi with its signal processing and wireless transfer capabilities acts like an adapter between the sensors and a personalized mobile device application that is used for tracking the ECG. A highly sensitive peak detection algorithm was used by RasPi to detect and extract features from the ECG signals at real time. The peak detection algorithm was tested on the standard MITBIH arrhythmia database and reported an accuracy of greater than 95%. Hence, we propose a novel low cost approach towards arrhythmia monitoring and detection with wide applications in mobile health systems.

The aim of this paper is to present a didactic experience in designing mobile health systems during a Bachelor Degree class in Industrial Design. The scope is to prove the role of Design in the innovation process and how its approach and methodologies connect research, innovation and technology. As case studies, two projects are presented. In the first one, the students have developed a training suite for figure skating; the second one is related to the development of a system that detects and counts instruments and sterile dressings in the operating suites.

Obesity is now one of the most critical and demanding public health condition due to the correlation with many medical and psychological comorbidities, such as cardiovascular, orthopedic, pneumological, endocrinological, psychopathological complications, above all the type 2 diabetes. Obesity traditionally needs long and expensive treatments in a chronic care management approach. So clinical research has to develop, test and validate cheaper rehabilitation programs. For this reason, we developed the DIABESITY study, the design of a mHealth integrated platform to promote the empowerment of patients in self-monitoring and successfully managing their pathological conditions (focusing on obesity and type 2 diabetes) through the use of mobile devices. In this paper we report this study by discussing the following two important aspects of DIABESITY. (i) Dietary mHealth tools for home-patients; (ii) Measures to capture the psychological factors and processes which mediate change of behavior and affect initiation and maintenance phases.

mHealth is an emerging and rapidly developing field with huge exploitation expectancies both in improving life quality of patients and in market opportunities. Patents and innovations in mHealth represents a priority for companies to enter and exploit their know-how and market requests. This paper focuses on the analysis of the Intellectual Property Rights in the field of mHealth systems to draw a reference knowledge framework of the mHealth scenario. An up-to-date detailed categorization, the geographical distribution and the identification of top players in mHealth is presented.

We present the setup of an observational study that aims to examine the application of wearables in ambulatory palliative care to monitor the patients’ health status – especially during the transition phase from hospital to home since this phase is critical and often patients are re-hospitalised. Following an user-centred design approach, we performed interviews with patients recruited at the Clinic of Radiation Oncology of the University Hospital Zurich, Switzerland. The patient group was perceived as very vulnerable and varied largely in physiological burden and mental aspects. Special needs concern primarily obtrusiveness of the system and sensitivity in the work with this vulnerable patient group.

Falls are a significant health and social problem for older adults and their relatives. In this paper we study the use of a barometer placed at the user’s head (e.g., embedded in a pair of glasses) as a means to improve current wearable sensor-based fall detection methods. This approach proves useful to reliably detect falls even if the acceleration produced during the impact is relatively small. Prompt detection of a fall and/or an abnormal lying condition is key to minimize the negative effect on health.

Fall detection is typically based on temporal and spectral analysis of multi-dimensional signals acquired from wearable sensors such as tri-axial accelerometers and gyroscopes which are attached at several parts of the human body. Our aim is to investigate the location where such wearable sensors should be placed in order to optimize the discrimination of falls from other Activities of Daily Living (ADLs). To this end, we perform feature extraction and classification based on data acquired from a single sensor unit placed on a specific body part each time. The investigated sensor locations include the head, chest, waist, wrist, thigh and ankle. Evaluation of several classification algorithms reveals the waist and the thigh as the optimal locations.

Falls are a major threat for senior citizens living independently. Sensor technologies and fall detection algorithms have emerged as a reliable, low-cost solution for this issue. We proposed a sensor orientation calibration algorithm to better address the uncertainty issue faced by fall detection algorithms in real world applications. We conducted controlled experiments of simulated fall events and non-fall activities on student subjects. We evaluated our proposed algorithm using sequence matching based machine learning approaches on five different body positions. The algorithm achieved an F-measure of 90 to 95% in detecting falls. Sensors worn as necklace pendants or in chest pockets performed best.

Fall avoidance systems reduce injuries due to unintentional falls, but most of them are fall detections that activate an alarm after the fall occurrence. Since predicting a fall is the most promising approach to avoid a fall injury, this study proposes a method based on new features and multilayer perception that outperforms state-of-the-art approaches. Since accelerometer and gyroscope embedded in a smartphone are recognized to be precise enough to be used in fall avoidance systems, they have been exploited in an experimental analysis in order to compare the proposal with state-of-the-art approaches. The results have shown that the proposed approach improves the accuracy from 83% to 90%.

It is a common practice in supervised learning techniques to use human judgment to label training data. For this process, data reliability is fundamental. Research on sleep quality found that human sleep stage misperception may occur. In this paper we propose that human judgment be supported by software-driven evaluation based on physiological parameters, selecting as training data only data sets for which human judgment and software evaluation are aligned. A prototype system to provide a broad-spectrum perception of sleep quality data comparable with human judgment is presented. The system requires users to wear a smartwatch recording heartbeat rate and wrist acceleration. It estimates an overall percentage of the sleep stages, to achieve an effective approximation of conventional sleep measures, and to provide a three-class sleep quality evaluation. The training data are composed of the heartbeat rate, the wrist acceleration and the three-class sleep quality. As a proof of concept, we experimented the approach on three subjects, each one over 20 nights.

Radial Basis Function (RBF) Kernel Machines have become commonly used in Machine Learning tasks, but they contain certain flaws (e.g., some suffer from fast growth in the number of learning parameters while predicting data with large number of variations). Besides, Kernel Machines with single hidden layers lack mechanisms for feature selection in multidimensional data space, and machine learning tasks become intractable. This paper investigates “deep learning” architecture composed of multilayered adaptive non-linear components – Multilayer RBF Kernel Machine – to address RBF limitations. Three different approaches of features selection and dimensionality reduction to train RBF based on Multilayer Kernel Learning are explored, and comparisons made between them in terms of accuracy, performance and computational complexity. Results show that the multilayered system produces better results than single-layer architecture. In particular, developing decision support system in term of data mining.

Kalman filters have been popular in applications to predict time-series data analysis and prediction. This paper uses a form of Extended Kalman Filter to predict the occurrence of CAD (Coronary Artery Disease) using patients data based on different relevant parameters. The work takes a novel approach by using different neural networks training algorithms Quasi-Newton and SCG with combination of activation functions to predict the existence/non-existence of CAD in a patient based on patient’s data set. The prediction probability of this combination is resulted in accuracy of about 92% or above, using cross validation and thresholding to remove the limitation of time-series prediction introduced because of the Extended Kalman filter behavior.

In the last years, rule-based systems have been used in mobile health and wellness applications for embedding and reasoning over domain-specific knowledge and suggesting actions to perform. However, often, no sufficient information is available to infer definite indications about the action to perform and one or more hypothesis should be formulated and evaluated with respect to their possible impacts. In order to face this issue, this paper proposes a mobile hypothetical reasoning system able to evaluate set of hypotheses, infer their outcomes and support the user in choosing the best one. In particular, it offers facilities to: (i) build specific scenarios starting from different initial hypothesis formulated by the user; (ii) optimize them by eliminating common domain-specific elements and avoiding their processing more than once; (iii) efficiently evaluate a set of logic rules over the optimized scenarios directly on the mobile devices and infer the logical consequences by providing timely responses and limiting the consumption of their resources. A case study has been arranged in order to evaluate the system’s effectiveness within a mobile application for managing personal diets according to daily caloric needs.

Markerless motion capture systems have been developed in an effort to evaluate human movements in a natural setting. However, the accuracy and reliability of these systems remain nowadays understudied. This paper describes a study performed to evaluate the accuracy and repeatability of the identification of posture using the Microsoft Kinect V2 markerless motion capture system. The measurement repeatability has been studied by observing a mannequin from different positions, with different light conditions, with obstacles partially hiding the lower limbs and with different clothes. The metrics for the evaluation of repeatability were the length of forearms, arms, thighs, legs and spine and the angle of the elbows and knees. Results showed the preferential positions of measuring in terms of distance and angular position between the sensor and the target. The presence of occluded or hidden limbs and close subject represent the most critical problems of body detection returning misleading results.

The cervical joint position error test is a method to assess proprioception. This test is particularly relevant for people with neck pain and whiplash associated disorder, and it is of potential interest for people with neurological disorders. In clinical practice, patients are asked to move their head and match the original position while wearing a laser pointer on their head. The error is measured manually as the distance between the projection of the laser on a target before and after neck movement. We developed a web page which delivers this test while measuring the position of the head with a head tracking software. We tested the reliability of our application, using our software simultaneously to the laser method on 14 healthy volunteers. Our results show good correlation (r = 0.83, 0.69 and 0.68 after extension, right and left rotation, respectively, all with, p < 0.001) and limits of agreement (±2.64 cm) between the two methods, suggesting that our application can be used for measuring the joint position sense error.

In this study, we evaluate the performances of the body tracking algorithm of the Kinect V2 low-cost time-of-flight camera for medical rehabilitation purposes. Kinect V2 is an affordable motion capture system, capable to monitor patients ability to perform the exercise programs at home after a training period inside the hospital, which is more convenient and comfortable for them. In order to verify the reliability of the body tracking algorithm of the Kinect V2, it has been compared with an actual stereophotogrammetric optoelectronic 3D motion capture system, routinely used in a Motion Analysis Laboratory in a Rehabilitation Centre, focusing on the upper limb rehabilitation process. The results obtained from the analysis reveal that the device is suitable for the rehabilitation application and, more generally, for all the applications in which the required accuracy related to the joint position does not exceed a couple of centimetres.

The “Timed Up and Go” (TUG) test is widely used in various disorders to evaluate subject’s mobility, usually evaluating only time execution. TUG test specificity could be improved by using instrumented assessment based on inertial sensors. Position of the sensor is critical. This study aimed to assess the reliability and validity of an inertial sensor placed in three different positions to correctly segment the different phases in the TUG test. Finding demonstrated good reliability of the proposed methodology compared to the gold standard motion analysis approach based on surface markers and an optoelectronic system. Placing the sensor just beneath the lumbar-sacral joint reported the lower values of deviation with respect to the gold standard. Optimized position can extend the proposed methodology from the clinical context towards ubiquitous solutions in an ecological approach.

Most of the interfaces of the current upper limb prosthetic device are rigid. However, human limbs and body are a combination of rigid and soft parts. Such a combination inherently suggests to implement soft ergonomic interfaces between the human body and such prosthetic devices. To this aim we have developed a novel set of wearable solutions, including a textile sleeve embedding EMG electrodes for the control of hand prosthesis. This interface has been integrated and preliminary tested in order to control a 5 d.o.f. low cost robotic hand.

In this work we propose, for the first time, to improve the performance of a Hand Pose Reconstruction (HPR) technique from RGBD camera data, which is affected by self-occlusions, leveraging upon postural synergy information, i.e., a priori information on how human most commonly use and shape their hands in everyday life tasks. More specifically, in our approach, we ignore joint angle values estimated with low confidence through a vision-based HPR technique and fuse synergistic information with such incomplete measures. Preliminary experiments are reported showing the effectiveness of the proposed integration.

Electrical Impedance Tomography (EIT) is a method used to display, through an image, the conductivity distribution inside a domain by using measurements taken from electrodes placed at its periphery. This paper presents our prototype of a stretchable touch sensor, which is based on the EIT method. We then test its performance by comparing voltage data acquired from testing with two different materials, using the performance parameters Signal-to-Noise Ratio (SNR), Boundary Voltage Changes (BVC) and Singular Value Decomposition (SVD). The paper contributes to the literature by demonstrating that, depending on the present stimuli position over the conductive domain, the selection of electrodes on which current injection and voltage reading are performed, can be chosen dynamically resulting in an improved quality of the reconstructed image and system performance.

In the context of Augmented Reality (AR), industrial pioneers and early adopters have considered the wearable optical see-through (OST) displays as proper and effective tools in applications spanning from manufacturing and maintenance up to the entertainment field and the medical area, because they provide the user with an egocentric viewpoint maintaining the quality of the visual perception of the real world.The common OST displays paradigm entails intrinsic perceptual conflicts owing to mismatched accommodation between real 3D world and virtual 2D images projected over semitransparent surfaces. Such paradigm is suitable for augmenting the reality with simple virtual elements (models, icons or text), but various shortcomings remain in case of complex virtual contents. The major shortcoming is due to the tedious and error prone calibration methods required to obtain geometrical consistency, pivotal in many of the aforementioned fields of application. These shortcomings are due to the intrinsic incompatibility between the nature of the 4D light field, related to the real world, and the nature of the virtual content, rendered as a 2D image.In this paper we describe a radical rethinking of the wearable OST displays paradigm by generating, through integral imaging technique, the virtual content as a light field, in order to overcome the typical limitations of the traditional approach. This paper describes the hardware components and an innovative rendering strategy in more details in respect to a previous work. Furthermore we report early results with the implementation of the integral imaging display using a lens array instead of a pinhole array.

To improve the quality of life of elderly subjects affected by dementia, the rehabilitation environment has to translate from the hospital to the patient’s home. A holistic tele-rehabilitation system can be successfully used to support and enhance a home-based rehabilitation process. The ABILITY platform foresees mobile and wireless technologies, integrated into a unique environment in which patients can become primary actors in their own care. In this work, we present a Pilot Study (N = 10) about the motor recovery, and in particular the relationship between the motor recovery and the cognitive recovery, in dementia patients. A group of control patients followed the usual care treatment and another group used the ABILITY platform at home. The results of the study suggested that the use of the tele-rehabilitation platform could improve both the motor skills, the cognitive skill and the interaction between them.

The project proposes a comprehensive preventive program of dementia in elderlies with minor cognitive disorders due to neurodegenerative diseases. The program combines physical and cognitive training, by means of an integrated technological system composed of a Virtual Environment, simulating daily activities, a smart garment measuring physiological parameters, a bicycle ergometer and tailoring the system to the specific patient’s status. Preliminary results confirm the feasibility of this intervention and appear promising in order to contrast age-related cognitive neurodegeneration.

The growing number of elderly people with health issues is the consequence of the increase in life expectancy. Tele-homecare applications have already reported promising results on reducing health care costs and improving quality of life. In this study, we present the SMARTA platform (www.smarta-project.it): a fully integrated system capable to monitor its user’s health condition. The latest telemedicine and wearable technologies have been used to make cooperating users and caregivers. The system integrates wearable (ECG and accelerometry), non-wearable (temperature, weight, blood pressure etc.) and environmental (light, refrigerator etc.) sensors.

This works investigates the possibility of identifying the elders’ fall using accelerometers located on the ground. The work is divided in three parts: in the first we have designed a force platform to measure the forces generated during the fall and we have estimated the force generated by the impact of a subject with the floor using a crash test dummy. The effect of the dummy initial posture, of the presence of obstacles on the fall trajectory and of other parameters has been analysed as well. In the second part of the study we have analysed the vibration transmissibility in different dwellings. The final part of the research was focused on the estimation of the force starting from the vibration and from the impedance of the floor. Results have shown the possibility of identifying the elders’ falls in the majority of dwellings.

According to the International Diabetes Federation, in Europe 59.8 million people have diabetes and the number will rise to 71.1 million adults by 2040. Research on new models of care organisation demonstrates that advanced technologies and ICT systems and services may have the potentiality to respond to the increasing burden of diabetes and the complexity of managing it, and, in doing so, to contribute to the sustainability of health and care systems. In this paper we propose the development of a new Personalized Integrated Predictive Diabetes Management System, based on a design-driven approach in contrast with the technology–driven one generally used in medical field. The Novel System here presented is called Dia_Friend, an integrated care models, oriented to the needs of the user and focused on the way technology is used and shaped for him, instead of on the mere instrumental use of it.

Smart devices are increasingly used for health monitoring. We present a novel connectionist architecture to detect elderly behavior shift from data gathered by wearable or ambient sensing technology. Behavior shift is a pattern used in many applications: it may indicate initial signs of disease or deviations in performance. In the proposed architecture, the input samples are aggregated by functional structures called trails. The trailing process is inspired by stigmergy, an insects’ coordination mechanism, and is managed by computational units called Stigmergic Receptive Fields (SRFs), which provide a (dis-)similarity measure between sample streams. This paper presents the architectural view, and summarizes the achievements related to three application case studies, i.e., indoor mobility behavior, sleep behavior, and physical activity behavior.

It is typical for the older adults with or without cognitive impairment to manifest sensory declines. This indirectly affects their sense of direction and wayfinding ability as oriented search is linked with sensory, mainly the visual. The deterioration of spatial navigation skill due to aging and cognitive decline is well recognized. We present the conceptual design of a wearable navigation device with tactile display and its prototype development, aimed to assist the navigation of individuals with cognitive impairment. The results of a pilot test conducted on individuals with dementia using the working prototype are also presented and discussed. The experiment intended to verify the positive outcomes of using the haptic modality for navigation and its wearability. Results suggest that the haptic stimulus is a helpful signal for wayfinding. From the user assessment however, some limitations are traceable due to the wearable design of the device. This is needed to be improved and emphasized in our future works.