Hugo Gamboa

One Lead ECG Based Personal Identification with Feature Subspace Ensembles

In this paper we present results on real data, focusing on personal identification based on one lead ECG, using a reduced number of heartbeat waveforms. A wide range of features can be used to characterize the ECG signal trace with application to personal identification. We apply feature selection (FS) to the problem with the dual purpose of improving the recognition rate and reducing data dimensionality. A feature subspace ensemble method (FSE) is described which uses an association between FS and parallel classifier combination techniques to overcome some FS difficulties. With this approach, the discriminative information provided by multiple feature subspaces, determined by means of FS, contributes to the global classification system decision leading to improved classification performance. Furthermore, by considering more than one heartbeat waveform in the decision process through sequential classifier combination, higher recognition rates were obtained.

Novel fiducial and non-fiducial approaches to electrocardiogram-based biometric systems

The electrocardiogram (ECG) is a non-invasive and widely used technique for cardiac electrophysiological assessment. Although the ECG has traditionally only been used for functional diagnostic and evaluation, several advances in electrophysiological sensing have made available robust signal acquisition devices, particularly suited for ambulatory conditions, widening its range of applications. In particular, recent work has shown the potential of the ECG as a biometric trait, both for human identification and authentication. This study sets the ground for an ECG-based real-time biometric system. The authors describe an experimental setup and the evaluation of new fiducial and non-fiducial approaches, including data acquisition, signal processing, feature extraction and analysis and classification methodologies, showing the applicability of the ECG as a real-time biometric. Performance evaluation was done in clinical-grade ECG recording from 51 healthy control individuals (of a publicly available benchmark dataset) as well as on data collected from 26 healthy volunteers performing computer activities without any posture or motion limitations, thus simulating a regular computer usage scenario.

Webbiometrics: User Verification Via Web Interaction

We introduce a biometric trait based on the user behavior extracted from his interaction with a Web page. We propose the integration of this soft biometric trait in a conventional login Internet page to enhance the security of the system. We call this security layer WebBiometrics. This layer monitors the user mouse movements while he clicks his PIN code numbers. The proposed biometric method provides a non-intrusive soft behavioral biometric add-on to enhance on-line security. We describe the functionality of the system, the set of algorithms developed for the verification framework and preliminary experimental results. We also present quantitative measures of security enhancement offered by the introduction of this soft biometric compared to a PIN only based Web access.

Human activity data discovery from triaxial accelerometer sensor: Non-supervised learning sensitivity to feature extraction parametrization

Abstract Background : Our methodology describes a human activity recognition framework based on feature extraction and feature selection techniques where a set of time, statistical and frequency domain features taken from 3-dimensional accelerometer sensors are extracted. This framework specifically focuses on activity recognition using on-body accelerometer sensors. We present a novel interactive knowledge discovery tool for accelerometry in human activity recognition and study the sensitivity to the feature extraction parametrization. Results : The implemented framework achieved encouraging results in human activity recognition. We have implemented a new set of features extracted from wearable sensors that are ambitious from a computational point of view and able to ensure high classification results comparable with the state of the art wearable systems (Mannini et al. 2013). A feature selection framework is developed in order to improve the clustering accuracy and reduce computational complexity. 1 Several clustering methods such as K-Means, Affinity Propagation, Mean Shift and Spectral Clustering were applied. The K-means methodology presented promising accuracy results for person-dependent and independent cases, with 99.29% and 88.57%, respectively. Conclusions : The presented study performs two different tests in intra and inter subject context and a set of 180 features is implemented which are easily selected to classify different activities. The implemented algorithm does not stipulate, a priori , any value for time window or its overlap percentage of the signal but performs a search to find the best parameters that define the specific data. A clustering metric based on the construction of the data confusion matrix is also proposed. The main contribution of this work is the design of a novel gesture recognition system based solely on data from a single 3-dimensional accelerometer.

Multimodal biosignal sensor data handling for emotion recognition

We present an experimental setup, sensor data handling, and evaluation framework for emotion recognition, based on multimodal biosignal sensor data. For labeled data acquisition we developed an emotion elicitation block, with a bank of labeled videos containing different triggering stimuli. A biosignal acquisition apparatus was used to collect multimodal data, namely: Electromyography (EMG); Electrocardiography (ECG); Electrodermal Activity (EDA); Blood Volume Pulse (BVP); Peripheral Temperature (SKT); and Respiration (RESP). An automated biosignal processing and feature extraction toolbox was developed to convert raw data into meaningful parameters. Experimental results revealed trends associated with triggering events, providing a baseline for emotion recognition. Through LOOCV with a k-NN classifier, we obtained recognition rates of 81% to distinguish between positive and negative emotions, and of 70% to distinguish between positive, neutral, and negative emotions.

On applying approximate entropy to ECG signals for knowledge discovery on the example of big sensor data

Information entropy as a universal and fascinating statistical concept is helpful for numerous problems in the computational sciences. Approximate entropy (ApEn), introduced by Pincus (1991), can classify complex data in diverse settings. The capability to measure complexity from a relatively small amount of data holds promise for applications of ApEn in a variety of contexts. In this work we apply ApEn to ECG data. The data was acquired through an experiment to evaluate human concentration from 26 individuals. The challenge is to gain knowledge with only small ApEn windows while avoiding modeling artifacts. Our central hypothesis is that for intra subject information (e.g. tendencies, fluctuations) the ApEn window size can be significantly smaller than for inter subject classification. For that purpose we propose the term truthfulness to complement the statistical validity of a distribution, and show how truthfulness is able to establish trust in their local properties.

AAL+: Continuous Institutional and Home Care Through Wireless Biosignal Monitoring Systems

This chapter describes the research and development of AAL+, a new tool for continuous short-to-medium and long range patient monitoring. The system has two versions, each targeted at a different environment and at subjects with different needs: (a) AAL+ Institutional, for patients that live in healthcare institutions such as assisted living facilities, with delicate needs in terms of medical assistance and monitoring; and (b) AAL+ Home, for individuals that live in their homes, maintaining some independence and physical capabilities. In the next sections we describe the particular characteristics of each version as well as the development, test and deployment scenarios, in close collaboration with partners from the clinical field and end-users. Currently, the system is in a late prototype stage and was tested in a real environment at two healthcare institutions: an assisted living residence and a public hospital Users’ reactions show that this system brings advantages which extend to institutions, caregivers and end-users, and translate into faster assistance, higher efficiency of the services and new intervention models.

GENDER DIFFERENCES IN KNEE STABILITY IN RESPONSE TO WHOLE-BODY VIBRATION

Abstract Sañudo, B, Feria, A, Carrasco, L, de Hoyo, M, Santos, R, and Gamboa, H. Gender differences in knee stability in response to whole-body vibration. J Strength Cond Res 26(8): 2156–2165, 2012—The purpose of this study was to determine whether there are kinematic and electromyographic (EMG) differences between men and women in how the knee is controlled during a single-legged drop landing in response to whole-body vibration (WBV). Forty-five healthy volunteers, 30 men (age 22 ± 3 years; weight 76.8 ± 8.8 kg; height 179.0 ± 6.8 cm) and 15 women (age 22 ± 3 years; weight 61.0 ± 7.7 kg; height 161.9 ± 7.2 cm) were recruited for this study. Knee angles, vertical ground reaction forces, and the time to stabilize the knee were assessed after single-legged drop landings from a 30-cm platform. Surface EMG data in rectus femoris (RF) and hamstrings (H) and knee and ankle accelerometry signals were also acquired. The participants performed 3 pretest landings, followed by a 3-minute recovery and then completed 1 minute of WBV (30 Hz to 4 mm). Before vibration, the female subjects had a significantly higher peak vertical force value, knee flexion angles, and greater H preactivity (EMGRMS 50 milliseconds before activation) than did the male subjects. In addition, although not significant, the medial-lateral (ML) acceleration in both knee and ankle was also higher in women. After WBV, no significant differences were found for any of the other variables. However, there was a decrease in the RF to H activation ratio during the precontact phase and an increase in the ratio during the postcontact phase just in women, which leads to a decrement in ML acceleration. The gender differences reported in knee stability in response to WBV underline the necessity to perform specific neuromuscular training programs based on WBV together with instruction of the proper technique, which can assist the clinician in the knee injury prevention.

HiMotion: a new research resource for the study of behavior, cognition, and emotion

The HiMotion research project was designed to create a multimodal database and several support tools for the study of human behavior, cognition and emotion, in the context of computer-based tasks designed to elicit cognitive load and specialized affective responses. The database includes both human-computer interaction (HCI) and psychophysiological data, collected through an experimental setup that we devised for synchronized recording of keyboard, mouse, and central/ peripheral nervous system measurements. Currently we provide a battery of five different cognitive tasks, and a video bank for affective elicitation, together with a set of introductory and self-reporting screens. We have conducted two experiments, one involving a population of 27 subjects, which followed the cognitive tasks protocol, and another involving a population of 20 subjects, which followed the video bank visualization protocol. We provide an overview of several studies that have used the HiMotion database to test multiple hypothesis in the behavioral and affective domains, highlighting the usefulness of our contribution.

A User Authentication Technic Using a~Web Interaction Monitoring System

User authentication based on biometrics has explored both physiological and behavioral characteristics. We present a system, called Web Interaction Display and Monitoring (WIDAM), that captures an user interaction on the web via a pointing device. This forms the basis of a new authentication system that uses behavioral information extracted from these interaction signals. The user interaction logs produced by WIDAM are presented to a sequential classifier, that applies statistical pattern recognition techniques to ascertain the identity of an individual – authentication system. The overall performance of the combined acquisition / authentication systems is measured by the global equal error rate, estimated from a test set. Preliminary results show that the new technique is a promising tool for user authentication, exhibiting comparable performances to other behavioural biometric techniques. Exploring standard human-computer interaction devices, and enabling remote access to behavioural information, this system constitutes an inexpensive and practical approach to user authentication through the world wide web.