Iván González

An Ambulatory System for Gait Monitoring Based on Wireless Sensorized Insoles

A new gait phase detection system for continuous monitoring based on wireless sensorized insoles is presented. The system can be used in gait analysis mobile applications, and it is designed for real-time demarcation of gait phases. The system employs pressure sensors to assess the force exerted by each foot during walking. A fuzzy rule-based inference algorithm is implemented on a smartphone and used to detect each of the gait phases based on the sensor signals. Additionally, to provide a solution that is insensitive to perturbations caused by non-walking activities, a probabilistic classifier is employed to discriminate walking forward from other low-level activities, such as turning, walking backwards, lateral walking, etc. The combination of these two algorithms constitutes the first approach towards a continuous gait assessment system, by means of the avoidance of non-walking influences.

Comparison between passive vision-based system and a wearable inertial-based system for estimating temporal gait parameters related to the GAITRite electronic walkway

Quantitative gait analysis allows clinicians to assess the inherent gait variability over time which is a functional marker to aid in the diagnosis of disabilities or diseases such as frailty, the onset of cognitive decline and neurodegenerative diseases, among others. However, despite the accuracy achieved by the current specialized systems there are constraints that limit quantitative gait analysis, for instance, the cost of the equipment, the limited access for many people and the lack of solutions to consistently monitor gait on a continuous basis. In this paper, two low-cost systems for quantitative gait analysis are presented, a wearable inertial system that relies on two wireless acceleration sensors mounted on the ankles; and a passive vision-based system that externally estimates the measurements through a structured light sensor and 3D point-cloud processing. Both systems are compared with a reference clinical instrument using an experimental protocol focused on the feasibility of estimating temporal gait parameters over two groups of healthy adults (five elders and five young subjects) under controlled conditions. The error of each system regarding the ground truth is computed. Inter-group and intra-group analyses are also conducted to transversely compare the performance between both technologies, and of these technologies with respect to the reference system. The comparison under controlled conditions is required as a previous stage towards the adaptation of both solutions to be incorporated into Ambient Assisted Living environments and to provide continuous in-home gait monitoring as part of the future work.

Estimation of Temporal Gait Events from a Single Accelerometer Through the Scale-Space Filtering Idea

The purpose of this paper is to develop an accelerometry system capable of performing gait event demarcation and calculation of temporal parameters using a single waist-mounted device. Particularly, a mobile phone positioned over the L2 vertebra is used to acquire trunk accelerations during walking. Signals from the acceleration magnitude and the vertical acceleration are smoothed through different filters. Cut-off points between filtered signals as a result of convolving with varying levels of Gaussian filters and other robust features against temporal variation and noise are used to identify peaks that correspond to gait events. Five pre-frail older adults and five young healthy adults were recruited in an experiment. Cadence, step/stride time, step/stride CV, step asymmetry and percentages of the stance/swing and single/double support phases, among the two groups of different mobility were quantified by the system.

Towards Context-Aware and User-Centered Analysis in Assistive Environments

One of the main challenges on Ambient Assisted Living (AAL) is to reach an appropriate acceptance level of the assistive systems, as well as to analyze and monitor end user tasks in a feasible and efficient way. The development and evaluation of AAL solutions based on user-centered perspective help to achive these goals. In this work, we have designed a methodology to integrate and develop analytics user-centered tools into assistive systems. An analysis software tool gathers information of end users from adapted psychological questionnaires and naturalistic observation of their own context. The aim is to enable an in-deep analysis focused on improving the life quality of elderly people and their caregivers.

Smart Device-Based Notifications to Promote Healthy Behavior Related to Childhood Obesity and Overweight

Obesity is one of the most serious public health challenges of the 21st century and it is a threat to the life of people according to World Health Organization. In this scenario, family environment is important to establish healthy habits which help to reduce levels of obesity and control overweight in children. However, little efforts have been focused on helping parents to promote and have healthy lifestyles. In this paper, we present two smart device-based notification prototypes to promote healthy behavior with the aim of avoiding childhood overweight and obesity. The first prototype helps parents to follow a healthy snack routine, based on a nutritionist suggestion. Using a fridge magnet, parents receive graphical reminders of which snacks they and their children should consume. The second prototype provides a graphical reminder that prevents parents from forgetting the required equipment to practice sports. Prototypes were evaluated by nine nutritionists from three countries (Costa Rica, Mexico and Spain). Evaluations were based on anticipation of use and the ergonomics of human–system interaction according to the ISO 9241-210. Results show that the system is considered useful. Even though they might not be willing to use the system, they would recommend it to their patients. Based on the ISO 9241-210 the best ranked features were the system’s comprehensibility, the perceived effectiveness and clarity. The worst ranked features were the system’s suitability for learning and its discriminability.

A Proposal for Long-Term Gait Monitoring in Assisted Living Environments Based on an Inertial Sensor Infrastructure

Clinical gait analysis provides an evaluation tool that allows clinicians to characterize person’s locomotion at a particular time. There are currently specialized systems to detect gait events and compute spatio-temporal parameters of human gait, which are accurate and redundant. These systems are expensive and are limited to controlled settings with gait evaluations widely spaced in terms of time. As alternative, a proposal for long-term gait monitoring in Assisted Living Environments based on an infrastructure of wireless inertial sensors is presented. Specifically, heel-strike events will be identified in multiple elders in a rest home and throughout the day. A small wearable device composed of a single inertial measurement unit will be placed at the back of each elder, on the thoracic zone, capturing trunk accelerations and orientations which will enable the demarcation of heel-strike events and the computation of temporal gait parameters. This proposal attempts to contribute to the development of a less intrusive and reachable alternative for long-term gait monitoring of multiple residents, which has been poorly investigated.

A Dual Approach for Quantitative Gait Analysis Based on Vision and Wearable Pressure Systems

This paper proposes two approaches to characterize gait taking into account only quantitative measurements of dynamic nature. A pair of wireless sensorized insoles are used to obtain gait phases based on the involved forces, and a computer vision system externally estimates measurements through movement analysis. The wearable approach is composed of a pair of insoles, consisting of an assembly of FSRs and an inertial measurement unit. A micro-controller provides the captured data to a Bluetooth module that transmits it to be processed. The vision system obtains gait features using a single RGB camera. We have developed an algorithm to extract the silhouette using background subtraction, and locating heel and toe of each foot using the shape of the silhouettes. Detection of Heel-strike and Toe-off is based on gradient. Gait phases and other spatio-temporal parameters are derived from them.

Comparison of a Vision-Based System and a Wearable Inertial-Based System for a Quantitative Analysis and Calculation of Spatio-Temporal Parameters

Clinical gait analysis provides an evaluation tool that allows clinicians to assess the abnormality of gait in patients. There are currently specialized systems to detect gait events and calculate spatio-temporal parameters of human gait, which are accurate and redundant. These systems are expensive and are limited to very controlled settings. As alternative, a wearable inertial system and a single depth-camera system are proposed in order to detect gait events, and then, estimate spatial and temporal gait parameters. An experimental protocol is detailed in this paper using both systems in order to compare their performance with respect to a specialized human gait system for two age groups, elder and youth. This research attempts to contribute to the development of clinical decision support technologies by combining vision systems and wearable sensors.

Towards a Non-intrusive Self-management System for Asthma Control Using Smartphones

A noise-robust algorithm for segmentation of breath events during continuous speech is presented. The built-in microphone of a smartphone is used to capture the speech signal (voiced and breath frames) under conditions of a relatively noisy background. A template matching approach, using mel-cepstrograms, is adopted for constructing several similarity measurements to distinguish between breath and non-breath frames. Breath events will be used for lung function regression.

m-Health: Lessons Learned by m-Experiences

m-Health is an emerging area that is transforming how people take part in the control of their wellness condition. This vision is changing traditional health processes by discharging hospitals from the care of people. Important advantages of continuous monitoring can be reached but, in order to transform this vision into a reality, some factors need to be addressed. m-Health applications should be shared by patients and hospital staff to perform proper supervised health monitoring. Furthermore, the uses of smartphones for health purposes should be transformed to achieve the objectives of this vision. In this work, we analyze the m-Health features and lessons learned by the experiences of systems developed by MAmI Research Lab. We have focused on three main aspects: m-interaction, use of frameworks, and physical activity recognition. For the analysis of the previous aspects, we have developed some approaches to: (1) efficiently manage patient medical records for nursing and healthcare environments by introducing the NFC technology; (2) a framework to monitor vital signs, obesity and overweight levels, rehabilitation and frailty aspects by means of accelerometer-enabled smartphones and, finally; (3) a solution to analyze daily gait activity in the elderly, carrying a single inertial wearable close to the first thoracic vertebra.