Search

Our research team previously developed an accelerometry-based device, which can be worn on the waist during daily life activities and detects the occurrence of dyskinesia in patients with Parkinson’s disease. The goal of this study was to analyze the magnitude of correlation between the numeric output of the device algorithm and the results of the Unified Dyskinesia Rating Scale (UDysRS), administered by a physician. In this study, 13 Parkinson’s patients, who were symptomatic with dyskinesias, were monitored with the device at home, for an average period of 30¿minutes, while performing normal daily life activities. Each patient’s activity was simultaneously video-recorded. A physician was in charge of reviewing the recorded videos and determining the severity of dyskinesia through the UDysRS for every patient. The sensor device yielded only one value for dyskinesia severity, which was calculated by averaging the recorded device readings. Correlation between the results of physician’s assessment and the sensor output was analyzed with the Spearman’s correlation coefficient. The correlation coefficient between the sensor output and UDysRS result was 0.70 (CI 95%: 0.33–0.88; p¿=¿0.01). Since the sensor was located on the waist, the correlation between the sensor output and the results of the trunk and legs scale sub-items was calculated: 0.91 (CI 95% 0.76–0.97: p¿<¿0.001). The conclusion is that the magnitude of dyskinesia, as measured by the tested device, presented good correlation with that observed by a physician., Postprint (published version)

Postprint (published version)

Engagement in activities is crucial to improve quality of life in dementia. Yet, its measurement relies exclusively on behavior observation and the influence that behavioral and psychological symptoms of dementia (BPSD) have on it is overlooked. This study investigated whether quantity of movement, gauged with a wrist-worn accelerometer, could be a sound measure of engagement and whether apathy and depression negatively affected engagement. Fourteen participants with dementia took part in 6 sessions of activities: 3 of cognitive games (eg, jigsaw puzzles) and 3 of robot play (Pleo). Results highlighted significant correlations between quantity of movement and observational scales of engagement and a strong negative influence of apathy and depression on engagement. Overall, these findings suggest that quantity of movement could be used as an ancillary measure of engagement and underline the need to profile people with dementia according to their concurrent BPSD to better understand their engagement in activities., Peer Reviewed, Postprint (published version)

A presentation of the eHealth related concepts and challenges is done, together with an analysis on how the use of the Artificial Intelligence (AI) techniques can improve the management of the data generated by the eHealth activity, permitting to take more advanced decisions on the treatment and supervision of the patients. A concrete example and developed solution to be applied to the management of Parkinson Disease is presented and discussed., Peer Reviewed, Postprint (published version)

e-offprint for personal use only and shall not be selfarchived in electronic repositories., Posture transitions are one of the most mechanically demanding tasks and are useful to evaluate the motor status of patients with motor impairments, frail individuals or the elderly, among others. So far, wearable inertial systems have been one of the most employed tools in the study of these movements due to their suitable size and weight, being non-invasive systems. These devices are mainly composed of accelerometers and, to a lesser extent, gyroscopes, magnetometers or barometers. Although accelerometers provide the most reliable measurement, detecting activities where a change of altitude is observed, such as some posture transitions, may require additional sensors to reliably detect these activities. In this work, we present an algorithm that combines the information of a barometer and an accelerometer to detect posture transitions and falls. In contrast to other works, we test different activities (where altitude is involved) in order to achieve a reliable classifier against false positives. Furthermore, by means of feature selection methods, we obtain optimal subsets of features for the accelerometer and barometer sensors to contextualise these activities. The selected features are tested through several machine learning classifiers, which are assessed with an evaluation data set. Results show that the inclusion of barometer features in addition to those obtained for an accelerometer clearly enhances the detection accuracy up to a 11%, in terms of geometric mean between sensitivity and specificity, compared to algorithms where only the accelerometer is used. Finally, we have also analysed the computer burden; in this sense, the usage of barometers, in addition to increase the accuracy, also reduces the computational resources required to classify a new pattern, as shown by a reduction in the number of support vectors., Peer Reviewed, Postprint (published version)

The treatment of Parkinson's disease (PD) with levodopa is very effective. However, over time, motor complications (MCs) appear, restricting the patient from leading a normal life. One of the most disabling MCs is ON-OFF fluctuations. Gathering accurate information about the clinical status of the patient is essential for planning treatment and assessing its effect. Systems such as the REMPARK system, capable of accurately and reliably monitoring ON-OFF fluctuations, are of great interest. Objective To analyze the ability of the REMPARK System to detect ON-OFF fluctuations. Methods Forty-one patients with moderate to severe idiopathic PD were recruited according to the UK Parkinson's Disease Society Brain Bank criteria. Patients with motor fluctuations, freezing of gait and/or dyskinesia and who were able to walk unassisted in the OFF phase, were included in the study. Patients wore the REMPARK System for 3 days and completed a diary of their motor state once every hour. Results The record obtained by the REMPARK System, compared with patient-completed diaries, demonstrated 97% sensitivity in detecting OFF states and 88% specificity (i.e., accuracy in detecting ON states). Conclusion The REMPARK System detects an accurate evaluation of ON-OFF fluctuations in PD; this technology paves the way for an optimisation of the symptomatic control of PD motor symptoms as well as an accurate assessment of medication efficacy., Peer Reviewed, Postprint (published version)

The following work presents the study of fall detection using inertial and barometric pressure sensors. Technological advances have made it possible to develop inertial sensors of very small size that allow, among other things, to monitor human movement, and in this case, more specifically, detect falls. These sensors are used in so-called inertial measuring units, which are small devices that are placed on a specific part of the body and are able to measure motion. The thesis focuses on reducing the number of false positives generated with this type of systems by adding an extra measurement component, height, to the inertial system to detect falls, using a barometric pressure sensor. A number of steps have been taken to achieve this goal. First of all, a barometric pressure sensor has been chosen from the current sensors on the market. This sensor has been chosen by performing a series of tests to determine the best sensor among 3 possible candidates. Once selected, the sensor configuration parameters have been optimized for our task. Secondly, a heterogeneous database of 14 volunteers of different heights, ages and sexes has been compiled using the inertial measurement unit and the barometric pressure sensor. Thirdly, signal processing techniques and methods of extracting features have been applied to the database to obtain 4 different sets of data that include signals obtained by combining inertial measurements with barometric and signals obtained only from inertial measurements, to then make a comparison between the two and see if better results are obtained by combining the different sensors. Finally, 5 supervised learning algorithms have been trained with the data obtained. The results obtained demonstrate the feasibility of adding a barometric pressure sensor to an inertial system.

Among Parkinson’s disease (PD) motor symptoms, freezing of gait (FOG) may be the most incapacitating. FOG episodes may result in falls and reduce patients’ quality of life. Accurate assessment of FOG would provide objective information to neurologists about the patient’s condition and the symptom’s characteristics, while it could enable non-pharmacologic support based on rhythmic cues. This paper is, to the best of our knowledge, the first study to propose a deep learning method for detecting FOG episodes in PD patients. This model is trained using a novel spectral data representation strategy which considers information from both the previous and current signal windows. Our approach was evaluated using data collected by a waist-placed inertial measurement unit from 21 PD patients who manifested FOG episodes. These data were also employed to reproduce the state-of-the-art methodologies, which served to perform a comparative study to our FOG monitoring system. The results of this study demonstrate that our approach successfully outperforms the state-of-the-art methods for automatic FOG detection. Precisely, the deep learning model achieved 90% for the geometric mean between sensitivity and specificity, whereas the state-of-the-art methods were unable to surpass the 83% for the same metric., Peer Reviewed, Postprint (published version)

Background: Our group earlier developed a small monitoring device, which uses accelerometer measurements to accurately detect motor fluctuations in patients with Parkinson’s (On and Off state) based on an algorithm that characterizes gait through the frequency content of strides. To further validate the algorithm, we studied the correlation of its outputs with the motor section of the Unified Parkinson’s Disease Rating Scale part-III (UPDRS-III). Method: Seventy-five patients suffering from Parkinson’s disease were asked to walk both in the Off and the On state while wearing the inertial sensor on the waist. Additionally, all patients were administered the motor section of the UPDRS in both motor phases. Tests were conducted at the patient’s home. Convergence between the algorithm and the scale was evaluated by using the Spearman’s correlation coefficient. results: Correlation with the UPDRS-III was moderate (rho -0.56; p < 0.001). Correlation between the algorithm outputs and the gait item in the UPDRS-III was good (rho -0.73; p < 0.001). The factorial analysis of the UPDRS-III has repeatedly shown that several of its items can be clustered under the so-called Factor 1: “axial function, balance, and gait.” The correlation between the algorithm outputs and this factor of the UPDRS-III was -0.67 (p < 0.01). conclusion: The correlation achieved by the algorithm with the UPDRS-III scale suggests that this algorithm might be a useful tool for monitoring patients with Parkinson’s disease and motor fluctuations., Postprint (published version)

Among Parkinson’s disease (PD) symptoms, freezing of gait (FoG) is one of the most debilitating. To assess FoG, current clinical practice mostly employs repeated evaluations over weeks and months based on questionnaires, which may not accurately map the severity of this symptom. The use of a non-invasive system to monitor the activities of daily living (ADL) and the PD symptoms experienced by patients throughout the day could provide a more accurate and objective evaluation of FoG in order to better understand the evolution of the disease and allow for a more informed decision-making process in making adjustments to the patient’s treatment plan. This paper presents a new algorithm to detect FoG with a machine learning approach based on Support Vector Machines (SVM) and a single tri-axial accelerometer worn at the waist. The method is evaluated through the acceleration signals in an outpatient setting gathered from 21 PD patients at their home and evaluated under two different conditions: first, a generic model is tested by using a leave-one-out approach and, second, a personalised model that also uses part of the dataset from each patient. Results show a significant improvement in the accuracy of the personalised model compared to the generic model, showing enhancement in the specificity and sensitivity geometric mean (GM) of 7.2%. Furthermore, the SVM approach adopted has been compared to the most comprehensive FoG detection method currently in use (referred to as MBFA in this paper). Results of our novel generic method provide an enhancement of 11.2% in the GM compared to the MBFA generic model and, in the case of the personalised model, a 10% of improvement with respect to the MBFA personalised model. Thus, our results show that a machine learning approach can be used to monitor FoG during the daily life of PD patients and, furthermore, personalised models for FoG detection can be used to improve monitoring accuracy., Peer Reviewed, Postprint (published version)

Inertial measurement units (IMUs) are devices used, among other fields, in health applications, since they are light, small and effective. More concretely, IMUs have demonstrated to accurately monitor motor symptoms of Parkinson’s disease (PD). In this sense, most of previous works have attempted to assess PD symptoms through IMUs in controlled environments or short tests. This paper presents the design of an IMU called 9x3 that aims to assess PD symptoms, enabling the possibility to perform a map of patients’ symptoms at their homes during long periods of time. The designed device is able to acquire and store raw inertial data for artificial intelligence algorithmic training purposes. Furthermore, the presented IMU also enables the real-time execution of the developed and embedded learning models. Results show the great flexibility of the 9x3, capable of storing inertial information and algorithm outputs, sending messages to external devices. This paper also presents the results of detecting freezing of gait and brad kinetic gait in 12 patients, with sensitivity and specificity above 80%. Additionally, the system enables working 23.09 days (at waking hours) with a 1200mAh battery sampling at 50 Hz, opening up the possibility to be employed at other applications like wellbeing and sports., Peer Reviewed, Postprint (published version)

Freezing of gait (FoG) is one of the most disturbing and incapacitating symptoms in Parkinson's disease. It is defined as a sudden block in effective stepping, provoking anxiety, stress and falls. FoG is usually evaluated by means of different questionnaires; however, this method has shown to be not reliable, since it is subjective due to its dependence on patients’ and caregivers’ judgment. Several authors have analyzed the usage of MEMS inertial systems to detect FoG with the aim of objectively evaluating it. So far, specific methods based on accelerometer's frequency response has been employed in many works; nonetheless, since they have been developed and tested in laboratory conditions, their performance is commonly poor when being used at patients’ home. Therefore, this work proposes a new set of features that aims to detect FoG in real environments by using accelerometers. This set of features is compared with three previously reported approaches to detect FoG. The different feature sets are trained by means of several machine learning classifiers; furthermore, different window sizes are also evaluated. In addition, a greedy subset selection process is performed to reduce the computational load of the method and to enable a real-time implementation. Results show that the proposed method detects FoG at patients’ home with 91.7% and 87.4% of sensitivity and specificity, respectively, enhancing the results of former methods between a 5% and 11% and providing a more balanced rate of true positives and true negatives., Peer Reviewed, Postprint (published version)

Bradykinesia is a cardinal symptom of Parkinson's disease (PD) and describes the slowness of movement revealed in patients. Current PD therapies are based on dopamine replacement, and given that bradykinesia is the symptom that best correlates with the dopaminergic deficiency, the knowledge of its fluctuations may be useful in the diagnosis, treatment and better understanding of the disease progression. This paper evaluates a machine learning method that analyses the signals provided by a triaxial accelerometer placed on the waist of PD patients in order to automatically assess bradykinetic gait unobtrusively. This method employs Support Vector Machines to determine those parts of the signals corresponding to gait. The frequency content of strides is then used to determine bradykinetic walking bouts and to estimate bradykinesia severity based on an epsilon-Support Vector Regression model. The method is validated in 12 PD patients, which leads to two main conclusions. Firstly, the frequency content of the strides allows for the dichotomic detection of bradykinesia with an accuracy higher than 90%. This process requires the use of a patient-dependant threshold that is estimated based on a leave-one-patient-out regression model. Secondly, bradykinesia severity measured through UPDRS scores is approximated by means of a regression model with errors below 10%. Although the method has to be further validated in more patients, results obtained suggest that the presented approach can be successfully used to rate bradykinesia in the daily life of PD patients unobtrusively., Postprint (author's final draft)

The final publication is available at Springer via https://doi.org/10.1007/978-3-319-59147-6_30, Freezing of gait (FOG) is one of the most incapacitating symptoms among the motor alterations of Parkinson’s disease (PD). Manifesting FOG episodes reduce patients’ quality of life and their autonomy to perform daily living activities, while it may provoke falls. Accurate ambulatory FOG assessment would enable non-pharmacologic support based on cues and would provide relevant information to neurologists on the disease evolution. This paper presents a method for FOG detection based on deep learning and signal processing techniques. This is, to the best of our knowledge, the first time that FOG detection is addressed with deep learning. The evaluation of the model has been done based on the data from 15 PD patients who manifested FOG. An inertial measurement unit placed at the left side of the waist recorded tri-axial accelerometer, gyroscope and magnetometer signals. Our approach achieved comparable results to the state-of-the-art, reaching validation performances of 88.6% and 78% for sensitivity and specificity respectively., Peer Reviewed, Postprint (author's final draft)

© 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., The study of engagement is central to improve the quality of care and provide people with dementia with meaningful activities. Current assessment techniques of engagement for people with dementia rely exclusively on behavior observation. However, novel unobtrusive sensing technologies, capable of tracking psychological states during activities, can provide us with a deeper layer of knowledge about engagement. We compared the engagement of persons with dementia involved in two playful activities, a game-based cognitive stimulation and a robot-based free play, using observational rating scales and electrodermal activity (EDA). Results highlight significant differences in observational rating scales and EDA between the two activities and several significant correlations between the items of observational rating scales of engagement and affect, and EDA features. Electrodermal Activity: Explorations in the Psychophysiology of Engagement with Social Robots in Dementia, Peer Reviewed, Postprint (author's final draft)

Este documento presenta los algoritmos de monitorización de síntomas de Parkinson desarrollados por el Centro de Estudios Tecnológicos para la Dependencia y la Vida Autónoma (CETpD) de Vilanova y la Geltrú, perteneciente a la Universidad Politécnica de Catalunya, y cuyos derechos de explotación han sido transferidos a la empresa Sense4Care. Más concretamente, se describe su funcionamiento entrando en el detalle de los algoritmos, presentando de forma exhaustiva los algoritmos tal y como se encuentran a fecha de redacción del documento., Preprint

Altered movement control is typically the first noticeable symptom manifested by Parkinson’s disease (PD) patients. Once under treatment, the effect of the medication is very patent and patients often recover correct movement control over several hours. Nonetheless, as the disease advances, patients present motor complications. Obtaining precise information on the long-term evolution of these motor complications and their short-term fluctuations is crucial to provide optimal therapy to PD patients and to properly measure the outcome of clinical trials. This paper presents an algorithm based on the accelerometer signals provided by a waist sensor that has been validated in the automatic assessment of patient’s motor fluctuations (ON and OFF motor states) during their activities of daily living. A total of 15 patients have participated in the experiments in ambulatory conditions during 1 to 3 days. The state recognised by the algorithm and the motor state annotated by patients in standard diaries are contrasted. Results show that the average specificity and sensitivity are higher than 90%, while their values are higher than 80% of all patients, thereby showing that PD motor status is able to be monitored through a single sensor during daily life of patients in a precise and objective way., Peer Reviewed, Postprint (author's final draft)

Background After several years of treatment, patients with Parkinson's disease (PD) tend to have, as a side effect of the medication, dyskinesias. Close monitoring may benefit patients by enabling doctors to tailor a personalised medication regimen. Moreover, dyskinesia monitoring can help neurologists make more informed decisions in patient's care. Objective To design and validate an algorithm able to be embedded into a system that PD patients could wear during their activities of daily living with the purpose of registering the occurrence of dyskinesia in real conditions. Materials and methods Data from an accelerometer positioned in the waist are collected at the patient's home and are annotated by experienced clinicians. Data collection is divided into two parts: a main database gathered from 92 patients used to partially train and to evaluate the algorithms based on a leave-one-out approach and, on the other hand, a second database from 10 patients which have been used to also train a part of the detection algorithm. Results Results show that, depending on the severity and location of dyskinesia, specificities and sensitivities higher than 90% are achieved using a leave-one-out methodology. Although mild dyskinesias presented on the limbs are detected with 95% specificity and 39% sensitivity, the most important types of dyskinesia (any strong dyskinesia and trunk mild dyskinesia) are assessed with 95% specificity and 93% sensitivity. Conclusion The presented algorithmic method and wearable device have been successfully validated in monitoring the occurrence of strong dyskinesias and mild trunk dyskinesias during activities of daily living., Postprint (published version)

Freezing of Gait (FoG) is one of the most disturbing symptoms in Parkinson’s disease (PD). Current algorithms that detect this symptom depend on frequency features extracted from wearable systems. These algorithms have only been evaluated under laboratory conditions and, in real life, they might present false positives, reducing the reliability of the algorithm. This paper presents the evaluation of 20 PD patients in their homes and the inclusion of a posture algorithm to contextualize FoG detection. This algorithm, in average, improves specificity a 5% while preserves the sensitivity. In some patients, specificity increases by 11.9% maintaining the sensitivity., Peer Reviewed, Postprint (published version)

The analysis and evaluation of human movement is a growing research area within the field of sports monitoring. This analysis can help support the enhancement of an athlete's performance, the prediction of injuries or the optimization of training programs. Although camera-based techniques are often used to evaluate human movements, not all movements of interest can be analyzed or distinguished effectively with computer vision only. Wearable inertial systems are a promising technology to address this limitation. This paper presents a new wearable sensing system to record human movements for sports monitoring. A new paradigm is presented with the purpose of monitoring basketball players with multiple inertial measurement units. A data collection plan has been designed and implemented, and experimental results show the potential of the system in basketball activity recognition., Peer Reviewed, Postprint (author's final draft)

Este documento presenta los algoritmos de monitorización de síntomas de Parkinson desarrollados por el Centro de Estudios Tecnológicos para la Dependencia y la Vida Autónoma (CETpD) de Vilanova y la Geltrú, perteneciente a la Universidad Politécnica de Catalunya, y cuyos derechos de explotación han sido transferidos a la empresa Sense4Care. Más concretamente, se describe su funcionamiento entrando en el detalle de los algoritmos, presentando de forma exhaustiva los algoritmos tal y como se encuentran a fecha de redacción del documento., Preprint

Background: Patients with severe idiopathic Parkinson’s disease experience motor fluctuations, which are often difficult to control. Accurate mapping of such motor fluctuations could help improve patients’ treatment. Objective: The objective of the study was to focus on developing and validating an automatic detector of motor fluctuations. The device is small, wearable, and detects the motor phase while the patients walk in their daily activities. Methods: Algorithms for detection of motor fluctuations were developed on the basis of experimental data from 20 patients who were asked to wear the detector while performing different daily life activities, both in controlled (laboratory) and noncontrolled environments. Patients with motor fluctuations completed the experimental protocol twice: (1) once in the ON, and (2) once in the OFF phase. The validity of the algorithms was tested on 15 different patients who were asked to wear the detector for several hours while performing daily activities in their habitual environments. In order to assess the validity of detector measurements, the results of the algorithms were compared with data collected by trained observers who were accompanying the patients all the time. Results: The motor fluctuation detector showed a mean sensitivity of 0.96 (median 1; interquartile range, IQR, 0.93-1) and specificity of 0.94 (median 0.96; IQR, 0.90-1). Conclusions: ON/OFF motor fluctuations in Parkinson's patients can be detected with a single sensor, which can be worn in everyday life, Peer Reviewed, Postprint (author’s final draft)

Identification of activities of daily living is essential in order to evaluate the quality of life both in the elderly and patients with mobility problems. Posture transitions (PT) are one of the most mechanically demanding activities in daily life and,thus, they can lead to falls in patients with mobility problems. This paper deals with PT recognition in Parkinson’s Disease (PD) patients by means of a triaxial accelerometer situated between the anterior and the left lateral part of the waist. Since sensor’s orientation is susceptible to change during long monitoring periods, a hierarchical structure of classifiers is proposed in order to identify PT while allowing such orientation changes. Results are presented based on signals obtained from 20 PD patients and 67 healthy people who wore an inertial sensor on different positions among the anterior and the left lateral part of the waist. The algorithm has been compared to a previous approach in which only the anterior-lateral location was analyzed improving the sensitivity while preserving specificity. Moreover, different supervised machine l earning techniques have been evaluated in distinguishing PT. Results show that the location of the sensor slightly affects method’s performance and, furthermore, PD motor state does not alter its accuracy., Peer Reviewed, Postprint (author’s final draft)

Freezing of gait (FOG) is a common motor symptom of Parkinson’s disease (PD), which presents itself as an inability to initiate or continue gait. This paper presents a method to monitor FOG episodes based only on acceleration measurements obtained from a waist-worn device. Three approximations of this method are tested. Initially, FOG is directly detected by a support vector machine (SVM). Then, classifier’s outputs are aggregated over time to determine a confidence value, which is used for the final classification of freezing (i.e., second and third approach). All variations are trained with signals of 15 patients and evaluated with signals from another 5 patients. Using a linear SVM kernel, the third approach provides 98.7 % accuracy and a geometric mean of 96.1 %. Moreover, it is investigated whether frequency features are enough to reliably detect FOG. Results show that these features allow the method to detect FOG with accuracies above 90 % and that frequency features enable a reliable monitoring of FOG by using simply a waist sensor., Postprint (published version)

The following dissertation presents the contributions of the author in the field of human movement analysis and, specifically, in Parkinson's disease. Recent technologies have allowed developing reduced inertial sensors capable of monitoring human movement. This, along with the reduced prices of these inertial sensors, the so-called inertial measurement units, which consists in small devices capable to measure movement by means of inertial sensors, have widely spread. Inertial measurement units have been employed among others, in fields such as medicine, sports, automotive and gaming. In the first part of the present thesis, a wearable long-term monitoring inertial measurement unit is presented as the first main contribution in human movement analysis. The unit is capable of acquiring data and provides the possibility of implementing artificial intelligence-based classifiers in real time. A specific hardware and firmware has been developed in order to implement both operations. This tool has been validated in different European projects and studies carried out in the Technical Research Centre for Dependency Care and Autonomous Living of the Universitat Politècnica de Catalunya (CETpD-UPC). The second part of the thesis addresses the analysis of human posture based on accelerometry measurements. To this end, data acquired from the inertial system described at the first part of the thesis have been used. Two methodologies are presented that have been validated on healthy people and patients with Parkinson's disease. The algorithms developed are focused on the detection of positions with a single inertial system located at the waist thereby achieving an enhanced comfort and acceptance by the users. A key contribution is the methodology provided to detect postural transitions, which consist in the movement performed to achieve a position from another one. The algorithm is based on support vector machines applied to the inertial data coming from a single measurement unit, La siguiente disertación presenta las aportaciones del autor en el campo de la monitorización del movimiento humano y, especialmente, en la enfermedad del Parkinson. Las recientes tecnologías han permitido desarrollar sensores inerciales de tamaño muy reducido para monitorizar el movimiento humano. Estos sensores se emplean en las llamadas unidades de medida inercial, que son unos dispositivos de pequeño tamaño capaces de medir el movimiento, se ha extendido ampliamente empleándose, entre otros, en campos como la medicina, el deporte, la automoción o los videojuegos. En la primera parte de la presente tesis, se describe el desarrollo de una unidad de medida inercial optimizada para realizar la adquisición y el tratamiento de los datos con un mínimo consumo y, de esa forma, conseguir una larga autonomía. La principal novedad aportada consiste en la posibilidad de implementar en tiempo real clasificadores basados en inteligencia artificial a través de un hardware y un firmware diseñados específicamente para que el sistema inercial sea flexible y capaz de implementar las dos operaciones, captura de datos y ejecución de algoritmos. Esta herramienta se ha validado en diferentes proyectos europeos y diferentes trabajos llevados a cabo en el Centro de Estudios Tecnológicos para la Atención de la Dependencia y la Vida Autónoma de la Universidad Politécnica de Catalunya (CETpDUPC). En la segunda parte de la tesis se describen dos algoritmos para identificar diferentes tipos de posturas. Los datos empleados para poder desarrollar los algoritmos se han adquirido con el sistema inercial presentado en la primera parte de la tesis. Los algoritmos desarrollados se han validado en personas sanas y en pacientes con la enfermedad del Parkinson. Estos algoritmos se focalizan en la detección de posturas con un único sistema inercial localizado en la cintura. Esta localización permite una mayor comodidad para los usuarios, entre otras ventajas. Una aportación importante es la metodologí, Postprint (published version)

This paper presents REMPARK system, a novel approach to deal with Parkinson's Disease (PD). REMPARK system comprises two closed loops of actuation onto PD. The first loop consists in a wearable system that, based on a belt-worn movement sensor, detects movement alterations that activate an auditory cueing system controlled by a smartphone in order to improve patient's gait. The belt-worn sensor analyzes patient's movement through real-time learning algorithms that were developed on the basis of a database previously collected from 93 PD patients. The second loop consists in disease management based on the data collected during long periods and that enables neurologists to tailor medication of their PD patients and follow the disease evolution. REMPARK system is going to be tested in 40 PD patients in Spain, Ireland, Italy and Israel. This paper describes the approach followed to obtain this system, its components, functionalities and trials in which the system will be validated., Postprint (published version)

Postprint (published version)