August 26, 2016

Wearable Haptic Devices for Post-Stroke Gait Rehabilitation

Theodoros Georgiou
The Open University

Simon Holland
The Open University

Janet van der Linden
The Open University

Wearable technologies, in the form of small, light and inconspicuous devices, can be designed to help individuals suffering from neurological conditions carry out regular rehabilitation exercises. Current research has shown that walking to a rhythm can lead to significant improvements in various aspects of gait. Our primary aim is to provide a suitable, technology based intervention to enhance gait rehabilitation of people with chronic and degenerative neurological health conditions (such as stroke). This intervention will be in the form of small, lightweight, wireless, wearable devices the user can take out of the clinic, extending their rehabilitation to their own home setting. The devices can deliver a series of vibrations at a steady rhythm giving the patient a more stable and symmetric pace of walking. The simplest version of this approach typically comprise of a very small network of just two nodes and a central controller. The existing prototypes (called the Haptic Bracelets) capture and analyse motion data in real time to provide adaptive haptic (through vibrations) cueing. In the future and after more refinement, the system could allow a single therapist to monitor and advise groups of stroke survivors undergoing therapy sessions.

A Vision for Heart Rate Health Through Wearables

Reem Albaghli
University of Colorado Boulder

Kenneth M. Anderson
University of Colorado Boulder

Wearable technology has great potential for helping members of the public monitor their health. We are interested in medical conditions that can be monitored using the sensors on wearable devices like the Apple Watch. We are interested in the insights that can be provided by the monitoring of a person’s heart rate. We have conducted interviews with doctors to understand what can be learned about the health of an individual via their heart rate and how we can use that information to design applications that aid in monitoring these conditions. In this paper, we explore this design space and identify the applications we will develop to help users track these conditions in considerably less invasive ways than current methods.

Identifying Coronary Artery Disease from Photoplethysmogram

Rohan Banerjee
Innovation Labs
Tata Consultancy Services

Anirban Dutta Choudhury
Innovation Labs
Tata Consultancy Services

Ramu Vempada
Innovation Labs
Tata Consultancy Services

Arpan Pal
Innovation Labs
Tata Consultancy Services

Dr. K. M. Mandana
Fortis Hospital

This paper presents the idea of a non invasive screening system for identifying Coronary Artery Disease (CAD) patients from fingertip Photoplethysmogram (PPG) signal. A combined feature set, related to heart rate variability (HRV) as well as shapes of PPG waveform has been defined for distinguishing CAD and non CAD subjects. Support Vector Machine (SVM) is used for classification. Our methodology yields sensitivity and specificity scores of 0.82 and 0.88 respectively in identifying CAD patients on a corpus of 112 subjects, selected from MIMIC II dataset. Further, we achieved sensitivity and specificity scores of 0.73 and 0.87 on another dataset of 30 subjects, collected from an urban hospital using commercial oximeter device.

Using Design Fiction to Reflect on Autonomy in Smart Technology for People Living With Dementia

Britta F. Schulte
University College London

The field of HCI is changing, which brings with it new responsibilities. Ubiquitous computing touches on many aspects of modern life and its consequences are not yet fully understood. In the context of dementia ubiquitous technologies are currently developed to augment care and thereby enhancing quality of life for people living with dementia as well as reducing the financial pressures on the health care system. Within this paper a design fiction is presented as a method to explore the issues that may arise from the new technologies in this context. It introduces the idea of replacing Smart Home technology with wearable solutions to observe the technologies more critically through de-familiarization and use these observations to feed back into technology design.

B-ePain: A Wearable Interface to Self-Report Pain and Emotions

Iyubanit Rodriguez
Pontificia Universidad Católica de Chile

Carolina Fuentes
Pontificia Universidad Católica de Chile

Valeria Herskovic
Pontificia Universidad Católica de Chile

Mauricio Campos
Pontificia Universidad Católica de Chile

Chronic pain reduces quality of life and affects patients’ emotional well-being. When technologies for monitoring and reporting emotions are applied to people suffering from chronic pain, mental health problems may be detected, allowing health professionals to improve patients’ treatments and understand their patients in real contexts. However, older patients with chronic pain are limited by their knowledge about technology. Our work aims to understand how to design wearable devices that allow older adults to input complex information such as pain levels and emotional states.

Multiple Sensor Fusion approach to Map Environmental Noise Impact on Health

Faiza Guerrache
Computer &Technology
Nottingham Trent University

Ahmed Aldabbagh
Computer &Technology
Nottingham Trent University

Eiman Kanjo
Computer &Technology
Nottingham Trent University

Urban spaces have a great influence on how people feel and behave. There is a number of factors that affect our health in outdoor space. In this paper, we objectively propose a new way to measure environmental noise impact on health and reactions in places by monitoring their physiological signals in relation to their health and wellbeing. By integrating wearable biosensors with smartphones, we will be able to get multi-devices, geo-annotated and synchronous measurements from users in crowd sourcing fashion. The data then aggregated and analyzed to visualize the body responses data by creating layers over a geographical map. Consequently, we can establish a better understanding of the interdependency between health and environmental surroundings.

Towards Decisive Garments for Heat Stress Risk Detection

Mitra Baratchi
University of Twente

Lennart Teunissen,
Peter Ebben,
Wouter Teeuw,
Saxion University of Applied Sciences
{l.p.j.teunissen, p.w.g.ebben,

One of the numerous applications of wearable computers is providing safety in occupations where heat-related injuries are prevalent. Core temperature, as a parameter that cannot be measured by on-body sensors is a variable that is specifically interesting for realizing such applications. In the context of the design of a sensor-shirt that can be used by firefighters, in this paper we study the importance of different types of sensor measurements and their placement for estimating core temperature. We propose a model for inferring the dangerous states of core temperature. Our evaluation results show that our model can to a great extent estimate hazardous situations caused by heat accumulation.

A Digital Technology Framework to Optimise the Self-Management of Obesity

Patrick McAllister
School of Computing and Engineering
Ulster University

Huiru Zheng
School of Computing and Engineering
Ulster University

Raymond Bond
School of Computing and Engineering
Ulster University

Anne Moorhead
School of Communication
Ulster University

Obesity is increasing globally and can cause major chronic conditions. Much research has been completed in utilizing digital technologies to optimize the self-management of obesity. This research proposes an obesity management framework which highlights digital technologies to promote self-management of obesity. This work discusses preliminary research using image classification to promote food logging and crowdsourcing to determine calorie content of food images through aggregating the predictions of experts and non-experts. Preliminary results from image classification show SMO classifier achieved 73.87% accuracy in classifying 15 food items, which is promising as computer vision methods could be incorporated into food logging methods. Crowdsourcing results show that aggregated expert group mode percentage error was +2.60% (SD 3.87) in predicting calories in meals and non-expert group mode percentage error was +29.07% (SD 20.48). Further analysis on the crowdsourcing dataset will be completed to ascertain how many experts or non-experts is needed to get the most accurate calorie prediction.

Personal MobileCoach: Tailoring Behavioral Interventions to the Needs of Individual Participants

Filipe Barata
ETH Zürich

Tobias Kowatsch
University St.Gallen & ETH Zürich

Peter Tinschert
University St.Gallen

Andreas Filler
University of Bamberg & ETH Zürich

MobileCoach, an open source behavioral intervention platform, has been developed to provide health professionals with an authoring tool to design evidence-based, scalable and low-cost digital health interventions (DHI). Its potential meets the lack in resources and capacity of health care systems to provide DHI for the treatment of noncommunicable diseases. In the current work, we introduce the first personalization approach for MobileCoach with the purpose of identifying the needs of participants, tailoring the treatment and, as a consequence, enhancing the capability of MobileCoach-based DHIs. The personalization approach is then exemplified by a very first prototype of a DHI for people with asthma that is able to detect coughing by just using a smartphone’s microphone. First empirical results with five healthy subjects and 80 coughs indicate its technical feasibility as the detection accuracy yielded 83.3%. Future work will focus on the integration of personalized sensing and supporting applications for MobileCoach.

The Ultimate Wearable: Connecting Prosthetic Limbs to the IoPH

Rhys James Williams
University College London
UCL Interaction Centre

Catherine Holloway
University College London
UCL Interaction Centre

Mark Miodownik
University College London
Institute of Making

A new wearable device called the ‘Ubi-Sleeve’ is currently being developed that enables prosthesis wearers and other stakeholders to review temperature, humidity and prosthesis slippage behavior during everyday prosthesis wear. A combination of custom 3D printed strain sensors and off the shelf temperature and humidity sensors will be integrated into an unobtrusive sleeve to create a device that enables a deeper level of understanding of heat and sweat issues. To create the device, a series of experiments are in progress that will quantify changes in heat, humidity and slippage that negatively affect the prosthesis experience. Interviews and focus groups are also being conducted to gain a deeper understanding of the human side of prosthesis wear and to also ensure that data are presented in a way that is effective, useful and easy to understand.