Toni Giorgino

Sensor Evaluation for Wearable Strain Gauges in Neurological Rehabilitation

Conductive elastomers are a novel strain sensing technology which can be unobtrusively embedded into a garments fabric, allowing a new type of sensorized cloths for motion analysis. A possible application for this technology is remote monitoring and control of motor rehabilitation exercises. The present work describes a sensorized shirt for upper limb posture recognition. Supervised learning techniques have been employed to compare classification models for the analysis of strains, simultaneously measured at multiple points of the shirt. The instantaneous position of the limb was classified into a finite set of predefined postures, and the movement was decomposed in an ordered sequence of discrete states. The amount of information given by the observation of each sensor during the execution of a specific exercise was quantitatively estimated by computing the information gain for each sensor, which in turn allows the data-driven optimization of the garment. Real-time feedback on exercise progress can also be provided by reconstructing the sequence of consecutive positions assumed by the limb.

Wireless Support to Poststroke Rehabilitation: MyHeart's Neurological Rehabilitation Concept

Recent studies suggest that the quality of recovery after a stroke can be increased by early and more intensive rehabilitation. Portable unobtrusive devices are promising candidates for the realization of stroke-rehabilitation systems that complement care in the post-acute rehabilitation phase, both in the clinic and at home. The proposed system allows patients to increase the amount of motor exercise they can perform in autonomy, providing them with a real-time feedback based on wearable sensors embedded in the garments tissue across the upper limb and trunk. A dynamic time warping algorithm allows for the recognition of correct and incorrect motor exercises. After the feedback phase, data are stored in a central location for review and statistics. Workstations can be installed either at home or at the hospital to support patients, independent of their location. The performance of the system on healthy subjects was quantified for seven types of motor exercises for upper limbs rehabilitation. Finally, we present the preliminary results of a pilot clinical study to test the systems acceptability and usability by post-stroke patients, and physicians in a clinical setting.

Posture Classification via Wearable Strain Sensors for Neurological Rehabilitation

Stroke and other neurological accidents account for a wide fraction of the healthcare costs in industrialised societies. The last step in the chain of recovery from a neurological event often includes motor rehabilitation. While current motion-sensing technologies are inadequate for automated monitoring of rehabilitation exercises at home, conductive elastomers are a novel strain-sensing technology which can be embedded unobtrusively into a garments fabric. A sensorized garment was realized to simultaneously measure the strains at multiple points of a shirt covering the thorax and upper limb. Supervised learning techniques were employed to analyse the strain measures in order to reconstruct upper-limb posture and provide real-time feedback on exercise progress

Adaptable dialog architecture and runtime engine (AdaRTE): A framework for rapid prototyping of health dialog systems

Spoken dialog systems have been increasingly employed to provide ubiquitous access via telephone to information and services for the non-Internet-connected public. They have been successfully applied in the health care context; however, speech technology requires a considerable development investment. The advent of VoiceXML reduced the proliferation of incompatible dialog formalisms, at the expense of adding even more complexity. This paper introduces a novel architecture for dialogue representation and interpretation, AdaRTE, which allows developers to lay out dialog interactions through a high-level formalism, offering both declarative and procedural features. AdaRTEs aim is to provide a ground for deploying complex and adaptable dialogs whilst allowing experimentation and incremental adoption of innovative speech technologies. It enhances augmented transition networks with dynamic behavior, and drives multiple back-end realizers, including VoiceXML. It has been especially targeted to the health care context, because of the great scale and the need for reducing the barrier to a widespread adoption of dialog systems.

A Multivariate Time-Warping Based Classifier for Gesture Recognition with Wearable Strain Sensors

Conductive elastomer elements can be industrially embedded into garments to form unobtrusive strain sensing stripes. The present article outlines the structure of a strain- sensor based gesture detection algorithm. Current sensing prototypes include several dozens of sensors; their redundancy with respect to the limbs degrees of freedom, and other artifacts implied by this measurement technique, call for the development of novel robust multivariate pattern-matching techniques. The algorithms construction is explained, and its performances are evaluated in the context of motor rehabilitation exercises for both two-class and multi-class tasks.

Experiments in the detection of upper limb posture through kinestetic strain sensors

Conductive elastomers are strain-sensing technology which can be embedded unobtrusively into a garments fabric. A prototype was realized to simultaneously measure the strains at multiple points of a shirt covering the thorax and upper limb. This paper describes preliminary experiments with machine learning techniques, employed to analyse the strain measures in order to reliably reconstruct upper-limb posture. The scope of the application is to detect execution, correctness and progress of physical exercises performed as part of neurological rehabilitation therapy

Application of Spoken Dialogue Technology in a Medical Domain

The paper describes the ITC-irst approach for handling spoken dialogue interactions over the telephone. In particular, we have used the technology to develop a telemedicine prototype system that provides health-care to chronic patients. First, the system architecture will be summarized, then we will describe an automatic service for home monitoring of patients affected by hypertension pathology. Patients must periodically introduce data into a database containing their personal medical records. The collected data are managed, according to well established medical guidelines, by a software agent connected to a relational database, which contains the detailed history of each patient.

An automated voice response system for anticoagulant therapy management

The system described in this paper is aimed at improving the clinical workflow of post-stroke patients under oral anticoagulant therapy (OAT). The system helps both physicians and patients during the periodic control visits necessary to assess the anticoagulation status and the next therapeutic plan. Controls represent a burden for both patients, which after blood drawing must wait for the result, and for physicians, that, after assessing the therapy plan, must communicate it to patients, face-to-face or by telephone. A system is proposed, which embeds an algorithm for the patient-tailored calculation of the drug dosage and scheduling, and an automatic telephone dialogue for the communication of the therapy plan, once it has been validated or adjusted by the physician.

AdaRTE: An Extensible and Adaptable Architecture for Dialog Systems

Dialog Systems have been proven useful to provide the general public with access to services via speech devices. In this paper, we present AdaRTE, an Adaptable Dialog Architecture and Runtime Engine. AdaRTE uses dynamic Augmented Transition Networks and enables the generation of different backend formats; for instance, it supports VoiceXML generation to guarantee portability and standards compliance. The scope of AdaRTE is to provide a ground for deploying complex adaptable dialogs such as those found in the patient-care domain, and for experimenting with innovative speech solutions including Natural Language Processing. AdaRTE is an extensive architecture for dialog representation and interpretation, which helps developers to layout dialog interactions through a high level formalism whilst allowing the inclusion of voice applications best-practices.

Instrumental Kinesiology Approach in Neurorehabilitation Follow-up

Stroke is a serious neurological accident which accounts for a wide fraction of the healthcare costs. Recovery from stroke includes motor rehabilitation. The MyHeart consortium is addressing several aspects of Neurological Rehabilitation (NR) management by combining clothes with embedded biomedical sensors. This Poster describes how MyHeart¿s Concept NR is structured to support motor rehabilitation.