Oresti Baños

Daily living activity recognition based on statistical feature quality group selection

The benefits arising from proactive conduct and subject-specialized healthcare have driven e-health and e-monitoring into the forefront of research, in which the recognition of motion, postures and physical exercise is one of the main subjects. We propose here a multidisciplinary method for the recognition of physical activity with the emphasis on feature extraction and selection processes, which are considered to be the most critical stages in identifying the main unknown activity discriminant elements. Efficient feature selection processes are particularly necessary when dealing with huge training datasets in a multidimensional space, where conventional feature selection procedures based on wrapper methods or branch and bound are highly expensive in computational terms. We propose an alternative filter method using a feature quality group ranking via a couple of two statistical criteria. Satisfactory results are achieved in both laboratory and semi-naturalistic activity living datasets for real problems using several classification models, thus proving that any body sensor location can be suitable to define a simple one-feature-based recognition system, with particularly remarkable accuracy and applicability in the case of the wrist.

Dealing with the Effects of Sensor Displacement in Wearable Activity Recognition

Most wearable activity recognition systems assume a predefined sensor deployment that remains unchanged during runtime. However, this assumption does not reflect real-life conditions. During the normal use of such systems, users may place the sensors in a position different from the predefined sensor placement. Also, sensors may move from their original location to a different one, due to a loose attachment. Activity recognition systems trained on activity patterns characteristic of a given sensor deployment may likely fail due to sensor displacements. In this work, we innovatively explore the effects of sensor displacement induced by both the intentional misplacement of sensors and self-placement by the user. The effects of sensor displacement are analyzed for standard activity recognition techniques, as well as for an alternate robust sensor fusion method proposed in a previous work. While classical recognition models show little tolerance to sensor displacement, the proposed method is proven to have notable capabilities to assimilate the changes introduced in the sensor position due to self-placement and provides considerable improvements for large misplacements.

mHealthDroid: A Novel Framework for Agile Development of Mobile Health Applications

Mobile health is an emerging field which is attracting much attention. Nevertheless, tools for the development of mobile health applications are lacking. This work presents mHealthDroid, an open source Android implementation of a mHealth Framework designed to facilitate the rapid and easy development of biomedical apps. The framework is devised to leverage the potential of mobile devices like smartphones or tablets, wearable sensors and portable biomedical devices. The framework provides functionalities for resource and communication abstraction, biomedical data acquisition, health knowledge extraction, persistent data storage, adaptive visualization, system management and value-added services such as intelligent alerts, recommendations and guidelines.

Human activity recognition based on a sensor weighting hierarchical classifier

The analysis of daily living human behavior has proven to be of key importance to prevent unhealthy habits. The diversity of activities and the individuals’ particular execution style determine that several sources of information are normally required. One of the main issues is to optimally combine them to guarantee performance, scalability and robustness. In this paper we present a fusion classification methodology which takes into account the potential of the individual decisions yielded at both activity and sensor classification levels. Particularly tested on a wearable sensors based system, the method reinforces the idea that some parts of the body (i.e., sensors) may be specially informative for the recognition of each particular activity, thus supporting the ranking of the decisions provided by each associated sensor decision entity. Our method systematically outperforms the results obtained by traditional multiclass models which otherwise may require a high-dimensional feature space to acquire a similar performance. The comparison with other activity-recognition fusion approaches also demonstrates our model scales significantly better for small sensor networks.

A benchmark dataset to evaluate sensor displacement in activity recognition

This work introduces an open benchmark dataset to investigate inertial sensor displacement effects in activity recognition. While sensor position displacements such as rotations and translations have been recognised as a key limitation for the deployment of wearable systems, a realistic dataset is lacking. We introduce a concept of gradual sensor displacement conditions, including ideal, self-placement of a user, and mutual displacement deployments. These conditions were analysed in the dataset considering 33 fitness activities, recorded using 9 inertial sensor units from 17 participants. Our statistical analysis of acceleration features quantified relative effects of the displacement conditions. We expect that the dataset can be used to benchmark and compare recognition algorithms in the future.

Design, implementation and validation of a novel open framework for agile development of mobile health applications

The delivery of healthcare services has experienced tremendous changes during the last years. Mobile health or mHealth is a key engine of advance in the forefront of this revolution. Although there exists a growing development of mobile health applications, there is a lack of tools specifically devised for their implementation. This work presents mHealthDroid, an open source Android implementation of a mHealth Framework designed to facilitate the rapid and easy development of mHealth and biomedical apps. The framework is particularly planned to leverage the potential of mobile devices such as smartphones or tablets, wearable sensors and portable biomedical systems. These devices are increasingly used for the monitoring and delivery of personal health care and wellbeing. The framework implements several functionalities to support resource and communication abstraction, biomedical data acquisition, health knowledge extraction, persistent data storage, adaptive visualization, system management and value-added services such as intelligent alerts, recommendations and guidelines. An exemplary application is also presented along this work to demonstrate the potential of mHealthDroid. This app is used to investigate on the analysis of human behavior, which is considered to be one of the most prominent areas in mHealth. An accurate activity recognition model is developed and successfully validated in both offline and online conditions.

On the Use of Sensor Fusion to Reduce the Impact of Rotational and Additive Noise in Human Activity Recognition

The main objective of fusion mechanisms is to increase the individual reliability of the systems through the use of the collectivity knowledge. Moreover, fusion models are also intended to guarantee a certain level of robustness. This is particularly required for problems such as human activity recognition where runtime changes in the sensor setup seriously disturb the reliability of the initial deployed systems. For commonly used recognition systems based on inertial sensors, these changes are primarily characterized as sensor rotations, displacements or faults related to the batteries or calibration. In this work we show the robustness capabilities of a sensor-weighted fusion model when dealing with such disturbances under different circumstances. Using the proposed method, up to 60% outperformance is obtained when a minority of the sensors are artificially rotated or degraded, independent of the level of disturbance (noise) imposed. These robustness capabilities also apply for any number of sensors affected by a low to moderate noise level. The presented fusion mechanism compensates the poor performance that otherwise would be obtained when just a single sensor is considered.

Multi-sensor Fusion Based on Asymmetric Decision Weighting for Robust Activity Recognition

The recognition of human activity has been deeply explored during the recent years. However, most proposed solutions are mainly devised to operate in ideal conditions, thus not addressing crucial real-world issues. One of the most prominent challenges refers to common sensor technological anomalies. Sensor faults and failures introduce variations in the measured sensor data with respect to the equivalent observations in ideal conditions. As a consequence, predefined recognition systems may potentially fail to identify actions in the anomalous sensor data. This paper presents a novel model devised to cope with the effects introduced by sensor technological anomalies. The model builds on the knowledge gained from multi-sensor configurations, through asymmetrically weighting the decisions provided at both activity and sensor levels. Insertion and rejection weighting metrics are particularly used to eventually yield a unique recognized activity. For the sake of comparison, the tolerance to sensor faults and failures of standard activity recognition systems and the new proposed model are evaluated. The results prove classic activity-aware systems to be incapable of recognition under the effects of sensor technological anomalies, while the proposed model demonstrates to be robust against both sensor faults and failures.

Activity recognition based on a multi-sensor meta-classifier

Ensuring ubiquity, robustness and continuity of monitoring is of key importance in activity recognition. To that end, multiple sensor configurations and fusion techniques are ever more used. In this paper we present a multi-sensor meta-classifier that aggregates the knowledge of several sensor-based decision entities to provide a unique and reliable activity classification. This model introduces a new weighting scheme which improves the rating of the impact that each entity has on the decision fusion process. Sensitivity and specificity are particularly considered as insertion and rejection weighting metrics instead of the overall accuracy classification performance proposed in a previous work. For the sake of comparison, both new and previous weighting models together with feature fusion models are tested on an extensive activity recognition benchmark dataset. The results demonstrate that the new weighting scheme enhances the decision aggregation thus leading to an improved recognition system.

Classification of MRI Images for Alzheimer's Disease Detection

Alzheimers Disease (AD) is normally identified by several behavioral symptoms often mistakenly associated to age-related concerns or stress. However correct diagnosis and monitoring of the disease requires of additional resources. This paper presents a new methodology for classification of Alzheimers disease from MR images for medical support. A large database with more than one thousand patients was used. Two different problems are tackled in this work: a first one where a classification method is developed to classify MR images as either normal or with the Alzheimers disease and a second one for the identification and classification between normal subjects, MCI patients and AD patients. It is noteworthy that with this last study we could offer a tool to assist the early diagnosis of dementia. The outline of the methodology includes wavelet feature extraction from the MRIs, dimensionality reduction, training-test subdivision and classification using Support Vector Machines. Some concerns related to performance evaluation and dimensionality reduction are discussed.