BIOSIGNALS 2015 Abstracts


Full Papers
Paper Nr: 5
Title:

Single Trial Classification for Mobile BCI - A Multiway Kernel Approach

Authors:

Lieven Billiet, Borbála Hunyadi, Vladimir Matic, Sabine Van Huffel, Michel Verleysen and Maarten De Vos

Abstract: Subspace methods have been applied in various application fields to obtain robust results. Using multilinear algebra, they can also be applied on structured tensorial data. This work combines this principle with the power of non-linear kernels to investigate its merits in single trial classification for a mobile BCI ERP classification task. The accuracy difference with regard to more conventional vector kernels is evaluated for sitting and walking condition, increasing training data set and averaging over multiple trials. The study concludes that in general, the tensorial approach does not yield any advantage, though it might for specific subjects.
Download

Paper Nr: 11
Title:

Exploratory Analysis of Ventilation Signals from Resuscitation Data of Newborns

Authors:

Huyen Vu, Trygve Eftestøl, Kjersti Engan, Joar Eilevstjønn, Jørgen E. Linde and Hege Ersdal

Abstract: Prevention of neonatal mortality and morbidity because of birth asphyxia is still a major challenge. In a non-breathing baby, resuscitation including manual ventilation should start within one minute after birth. Information extracted from ventilation signals might give a good indication of the effectiveness of therapy. A framework for exploratory data analysis was developed facilitating the development of signal parameters to identify the relationships between certain signal characteristics and various outcome groups. Low p-values found for some ventilation parameters indicates that the method presented could be useful in discovering factors and parameters that might be important for the outcome of ventilation therapy and for guiding further treatment.
Download

Paper Nr: 17
Title:

Sparse-input Detection Algorithm with Applications in Electrocardiography and Ballistocardiography

Authors:

F. Wadehn, L. Bruderer, D. Waltisberg, T. Keresztfalvi and Hans -A. Loeliger

Abstract: Sparse-input learning, especially of inputs with some form of periodicity, is of major importance in bio-signal processing, including electrocardiography and ballistocardiography. Ballistocardiography (BCG), the measurement of forces on the body, exerted by heart contraction and subsequent blood ejection, allows non-invasive and non-obstructive monitoring of several key biomarkers such as the respiration rate, the heart rate and the cardiac output. In the following we present an efficient online multi-channel algorithm for estimating single heart beat positions and their approximate strength using a statistical hypothesis test. The algorithm was validated with 10 minutes long ballistocardiographic recordings of 12 healthy subjects, comparing it to synchronized surface ECG measurements. The achieved mean error rate for the heart beat detection excluding movement artifacts was 4.7%.
Download

Paper Nr: 19
Title:

Facial Expression Recognition based on EOG toward Emotion Detection for Human-Robot Interaction

Authors:

Aniana Cruz, Diogo Garcia, Gabriel Pires and Urbano Nunes

Abstract: The ability of an intelligent system to recognize the user’s emotional and mental states is of considerable interest for human-robot interaction and human-machine interfaces. This paper describes an automatic recognizer of the facial expression around the eyes and forehead based on electrooculographic (EOG) signals. Six movements of the eyes, namely, up, down, right, left, blink and frown, are detected and reproduced in an avatar, aiming to analyze how they can contribute for the characterization of facial expression. The recognition algorithm extracts time and frequency domain features from EOG, which are then classified in real-time by a multiclass LDA classifier. The offline and online classification results showed a sensitivity around 92% and 85%, respectively.
Download

Paper Nr: 27
Title:

Periocular Recognition under Unconstrained Settings with Universal Background Models

Authors:

João C. Monteiro and Jaime S. Cardoso

Abstract: The rising challenges in the fields of iris and face recognition are leading to a renewed interest in the area. In recent years the focus of research has turned towards alternative traits to aid in the recognition process under less constrained image acquisition conditions. The present work assesses the potential of the periocular region as an alternative to both iris and face in such scenarios. An automatic modeling of SIFT descriptors, regardless of the number of detected keypoints and using a GMM-based Universal Background Model method, is proposed. This framework is based on the Universal Background Model strategy, first proposed for speaker verification, extrapolated into an image-based application. Such approach allows a tight coupling between individual models and a robust likelihood-ratio decision step. The algorithm was tested on the UBIRIS.v2 and the MobBIO databases and presented state-of-the-art performance for a variety of experimental setups.
Download

Paper Nr: 32
Title:

Analysis of the Electromechanical Activity of the Heart from Synchronized ECG and PCG Signals of Subjects Under Stress

Authors:

Ana Castro, Ali Moukadem, Samuel Schmidt, Alain Dieterlen and Miguel T. Coimbra

Abstract: In this exploratory study we propose to analyze, in healthy adult volunteers, the heart electrical (electrocardiogram, ECG) and mechanical (phonocardiogram, PCG) activity during exercise. Heart sounds amplitude, frequency content, and RS2, may be important features in the non-invasive assessment of heart activity, such as for the estimation of cardiac output and blood pressure. Nine healthy volunteers were monitored with ECG and PCG simultaneously, under a stress test. After each workload level a 10 s window of signal was collected. PCG first (S1) and second (S2) heart sounds were manually annotated, based on time of QRS complex occurrence. A QRS detector was implemented to detect the QRS complex, and time intervals between electrical and mechanical events. Extracted features were analyzed in relation to heart rate (HR), including RS2, S1 and S2 amplitudes, and high frequency content of S1 and S2. Spearman correlation was used. Changes between baseline and maximum workload stage/HR for each volunteer were analyzed. Significant correlation was observed between HR, and all characteristics extracted (P<0.01). There was a clear difference between all variables from baseline to maximum workload level: with increasing workload/HR heart sounds amplitude increased (more pronounced in S1), RS2 decreased, and high frequency content of S2 decreased in relation to the high frequency content of S1, demonstrating that dynamic cardiovascular relations are individualized during cardiac stress and that assumptions for resting conditions may not be assumed.
Download

Paper Nr: 39
Title:

Comparison of Black Box Implementations of Two Algorithms of Processing of NMR Spectra, Gaussian Mixture Model and Singular Value Decomposition

Authors:

M. Staniszewski, F. Binczyk, A. Skorupa, L. Boguszewicz, M. Sokol, J. Polanska and A. Polanski

Abstract: Analysis of NMR spectra is a multi-stage computational process performed with the use of appropriately chosen sequence of algorithms. Initial stages of this process, called pre-processing, including filtering, baseline correction, phase correction and removal of unwanted components, are aimed at improving the quality of NMR spectral signal by rejection of noise, removing unnecessary spectral components and irregularities. After pre-processing the basic operations on NMR spectra are aimed at estimation of levels of certain metabolites by analysis of appropriate structural properties of NMR spectral signals. In this paper authors present design and implementation of two signals modelling methods. The first one is based on singular value decomposition of the induction decay signal. The second is done with use of mixture model constructed for frequency spectrum. Authors present all assumption that need to be satisfied and processing steps that must be performed before final analysis. The methods studied in the paper are implemented under the black - box assumption; i.e., prior knowledge of parameters of metabolites in the spectra is not used. As a second part of the project authors present a comparison of obtained result with popular modelling techniques and software LCmodel and Tarquin, based on experimental phantom dataset. Comparisons between different methods are based on the commonly used quality indexes, mean squared errors corresponding to levels of detected metabolites and specificities and sensitivities of the process of detection of metabolites. Using the presented comparisons we authors are able to characterize advantages and drawbacks of the studied approaches.
Download

Paper Nr: 41
Title:

Computational Investigation of Adaptive Deep Brain Stimulation

Authors:

Christopher Y. Thang and Paul A. Meehan

Abstract: Deep Brain Stimulation of the sub-thalamic nucleus (STN) has been proven to be effective at reducing symptoms of patients with Parkinson’s disease (PD). Currently an implanted pulse generator provides chronic electrical stimulation to the STN via an electrode and the stimulation parameters are chosen heuristically. Closed-loop Deep Brain Stimulation (DBS) has been proposed as an improvement to this, utilising neural signal feedback to select stimulation parameters, adjust the duration of stimulation and achieve better patient outcomes more efficiently. In this research, potential neural feedback signals were investigated using a computational simulation of the basal ganglia. It was found that the interspike-interval in the globus pallidus externus provided a possible metric for ‘on’ and ‘off’ states in Parkinson’s disease. This parameter was subsequently implemented as neural feedback in an adaptive closed-loop DBS simulation and was shown to be effective. In particular, the thalamic relaying capability was evaluated using an Error Index (EI) and the adaptive DBS was found to reduce the EI to 2%, which compared with 20% for the PD case without DBS. This was achieved using 58% of the stimulation time used during continuous DBS, indicating a large reduction in DBS energy requirements. This selection and implementation of a potential neural feedback parameter will assist in developing improved implanted DBS pulse generators.
Download

Paper Nr: 45
Title:

Human Activity Recognition Based on Novel Accelerometry Features and Hidden Markov Models Application

Authors:

Ana Luísa Gomes, Vítor Paixão and Hugo Gamboa

Abstract: The Human Activity Recognition (HAR) systems require objective and reliable methods that can be used in the daily routine and must offer consistent results according to the performed activities. In this work, a framework for human activity recognition in accelerometry (ACC) based on our previous work and with new features and techniques was developed. The new features set covered wavelets, the CUIDADO features implementation and the Log Scale Power Bandwidth creation. The Hidden Markov Models were also applied to the clustering output. The Forward Feature Selection chose the most suitable set from a 423th dimensional feature vector in order to improve the clustering performances and limit the computational demands. K-means, Affinity Propagation, DBSCAN and Ward were applied to ACC databases and showed promising results in activity recognition: from 73.20% 7.98% to 89.05% +/- 7.43% and from 70.75% +/- 10.09% to 83.89% +/- 13.65% with the Hungarian accuracy (HA) for the FCHA and PAMAP databases, respectively. The Adjust Rand Index (ARI) was also applied as clustering evaluation method. The developed algorithm constitutes a contribution for the development of reliable evaluation methods of movement disorders for diagnosis and treatment applications.
Download

Paper Nr: 47
Title:

Combining Spectral and Prosodic Features in HMM-based Single Utterance Speaker Verification

Authors:

Osman Büyük and Levent M. Arslan

Abstract: In this paper, we combine spectral and prosodic features together in order to improve the verification performance on a text-dependent single utterance speaker verification task. The baseline spectral system makes use of a whole-phrase sentence HMM topology for the fixed utterance. We extract prosodic features using time alignment information obtained from the HMM states. In our experiments we observe that, although the prosodic features individually do not yield high performance, they provide complementary information to the spectral features. We achieve approximately 10% relative reduction in EER when the information sources are combined with a multi-layer neural network.
Download

Paper Nr: 60
Title:

Quadriceps Muscle Fatigue and Comfort Generated by Neuromuscular Electrical Stimulation with Current Modulated Waveforms

Authors:

Tiago Araújo, Ana Anjos, Neuza Nunes, Pedro Rebelo and Hugo Gamboa

Abstract: Introduction: Neuromuscular electrical stimulation (NMES) is used by physical therapists in the clinic. The efficacy of NMES is limited by the rapid onset muscle fatigue. The role of NMES parameters is muscle fatigue is not clear. Objective: To determine the effects of shape waveform on muscle fatigue, during NMES. Methods: Twelve healthy subjects participated in the study. Subjects were assigned to 1 of 3 groups, randomly. Group assignment determined the order in which they were tested using 3 different shape waveforms. Maximal voluntary isometric contraction (MVIC) was measured during the first session. Fatigue test was applied with amplitude required to elicit 50% of the MVIC. In each 3 testing sessions torque of contraction and level comfort were measured, and percent fatigue was calculated. Analysis of variance tests for dependent samples was used to determine the effect of shape waveform on muscle fatigue and comfort scores Results: The results showed no one shape waveform was most fatigable and that SQ wave induced more uncomfortable stimulus.
Download

Paper Nr: 65
Title:

Recognizing Hand and Finger Gestures with IMU based Motion and EMG based Muscle Activity Sensing

Authors:

Marcus Georgi, Christoph Amma and Tanja Schultz

Abstract: Session- and person-independent recognition of hand and finger gestures is of utmost importance for the practicality of gesture based interfaces. In this paper we evaluate the performance of a wearable gesture recognition system that captures arm, hand, and finger motions by measuring movements of, and muscle activity at the forearm. We fuse the signals of an Inertial Measurement Unit (IMU) worn at the wrist, and the Electromyogram (EMG) of muscles in the forearm to infer hand and finger movements. A set of 12 gestures was defined, motivated by their similarity to actual physical manipulations and to gestures known from the interaction with mobile devices. We recorded performances of our gesture set by five subjects in multiple sessions. The resulting datacorpus will be made publicly available to build a common ground for future evaluations and benchmarks. Hidden Markov Models (HMMs) are used as classifiers to discriminate between the defined gesture classes. We achieve a recognition rate of 97.8% in session-independent, and of 74.3% in person-independent recognition. Additionally, we give a detailed analysis of error characteristics and of the influence of each modality to the results to underline the benefits of using both modalities together
Download

Paper Nr: 78
Title:

A User-centric Design of Permanent Magnetic Articulography based Assistive Speech Technology

Authors:

Lam A. Cheah, Jie Bai, Jose A. Gonzalez, Stephen R. Ell, James M. Gilbert, Roger K. Moore and Phil D. Green

Abstract: This paper addresses the design considerations and challenges faced in developing a wearable silent speech interface (SSI) based on Permanent Magnetic Articulography (PMA). To improve its usability, a new prototype was developed with the involvement of end users in the design process. Hence, desirable features such as appearance, portability, ease of use and light weight were incorporated into the prototype. The device showed a comparable performance with its predecessor, but has a much improved appearance, portability and hardware in terms of miniaturisation and cost.
Download

Short Papers
Paper Nr: 12
Title:

Speech/Non-Speech Detection for Electro-Larynx Speech Using EMG

Authors:

Anna Katharina Fuchs, Clemens Amon and Martin Hagmüller

Abstract: Electro-larynx speech (EL) is a possibility to re-obtain speech when the larynx is surgically removed or damaged. As currently available devices normally are hand-held, a new generation of EL devices would benefit from a hands-free version. In this work we use electromyographic (EMG) signals to investigate speech/nonspeech detection for EL speech. The muscle activity, which is represented by the EMG signal, correlates with the intention to produce speech sounds and therefore, the short-term energy can serve as a feature to make a speech/non-speech decision. We developed a data acquisition hardware to record EMG signals using surface electrodes. We then recorded a small database with parallel recordings of EMG and EL speech and used different approaches to classify the EMG signal into speech/non-speech sections. We compared the following envelope calculation methods: root mean square, Hilbert envelope, and low-pass filtered envelope, and different classification methods: single threshold, double threshold and a Gaussian mixture model based classification. This study suggests that the results are speaker dependent, i.e. they strongly depend on the signal-to-noise ratio of the EMG signal. We show that using low-pass filtered envelope together with double threshold detection outperforms the rest.
Download

Paper Nr: 25
Title:

Epileptic Seizure Detection using Bipolar Singular Value Decomposition

Authors:

Mojtaba Bandarabadi, Jalil Rasekhi, Cesar A. Teixeira and António Dourado

Abstract: We propose a robust method for automated detection of epileptic seizures using intracranial electroencephalogram (iEEG) recordings with two electrodes. The state-of-the-art seizure detection methods suffer from high number of false detections, even when designed to be patient-specific. The solution reported here aims to achieve very low false detection rate, while providing a high sensitivity. Two adjacent iEEG recordings are subtracted from each other to make the bipolar iEEG signal. The values achieved from singular value decomposition (SVD) of the bipolar iEEG signal are used as measure. A threshold is subsequently applied on the measure. Results indicate robustness of the proposed measure for seizure detection. The method is applied on 5 invasive recordings containing 54 seizures in 780 hours of multichannel iEEG recordings. On average, the results revealed 85.2% sensitivity and a very low false detection rate of 0.02 per hour in long-term continuous iEEG recordings.
Download

Paper Nr: 35
Title:

New Visualization Model for Large Scale Biosignals Analysis

Authors:

Catarina Cavaco, Ricardo Gomes, Hugo Gamboa and Ricardo Matias

Abstract: The development of new resources in the medical field, such as wearable sensors, allowed the improvement of biosignals monitoring. Acquired data is then an important source of information to clinicians and researchers. Thus, extracting useful information from data is a task of the greatest importance that involves a variety of concepts and methods, from which stands out data visualization. However, these methods present several limitations mainly when dealing with big data. In this paper we present an innovative web-based application for biosignals visualization and exploration in a fast and user friendly way overcoming the detected limitations. Three case studies are presented and a usability study supports the reliability of the implemented work.
Download

Paper Nr: 42
Title:

Application of a MEMS Blood Flowmeter for Power Spectrum Analysis of Heart Rate Variability

Authors:

Terukazu Akiyama, Tatsuya Miyazaki, Hiroki Ito, Hirofumi Nogami and Renshi Sawada

Abstract: We investigated the possibility of applying a MEMS blood flowmeter to heart rate variability (HRV) analysis. We conducted simultaneous measurements of HRV by electrocardiogram and MEMS blood flowmeter. TPP for the MEMS blood flowmeter was defined as the interval between peaks, which were designated as where the first-order differential of the signal changes from negative to positive. TRR (i.e., the R-R interval of the electrocardiogram) and TPP were compared by regression analysis. Autonomic indices transformed by power spectrum analysis were also compared by regression analysis. Fast Fourier transform (FFT) and maximum entropy method (MEM) were employed in the frequency analysis. By FFT analysis, the coefficient of determination for the regression between LF%, HF%, and LF/HF derived by TRR versus TPP was 0.8781, 0.8781, and 0.8946, respectively. By MEM analysis, the coefficient of determination for the regression between LF%, HF%, and LF/HF derived by TRR versus TPP was 0.9649, 0.8026, and 0.9181, respectively. These high correlations suggest that the TPP of the MEMS blood flowmeter is a reliable metric that can be utilized in applications of HRV analysis.
Download

Paper Nr: 43
Title:

Spatio-temporal Comparison between ERD/ERS and MRCP-based Movement Prediction

Authors:

Anett Seeland, Laura Manca, Frank Kirchner and Elsa Andrea Kirchner

Abstract: In brain-computer interfaces (BCIs) based on electroencephalography (EEG), two distinct types of EEG patterns related to movement have been used for detecting the brain’s preparation for voluntary movements: a) event-related patterns in the time domain named movement related cortical potentials (MRCPs) and b) patterns in the frequency domain named event-related desynchronization/synchronization (ERD/ERS). The applicability of those patterns in BCIs is often evaluated by the classification performance. To this end, the known spatio-temporal differences in EEG activity can be of interest, since they might influence the classification performance of the two different patterns. In this paper, we compared the classification performance based on ERD/ERS and MRCP while varying the time point of prediction as well as the used electrode sites. Empirical results were obtained from eight subjects performing voluntary right arm movements. Results show: a) classification based on MRCP is superior compared to ERD/ERS close to the movement onset whereas the opposite results farther away from the movement onset, b) the performance maximum of MRCP is located at central electrodes whereas it is at fronto-central electrodes for ERD/ERS. In summary, the results contribute to a better insight into the spatial and temporal differences between ERD/ERS and MRCP in terms of prediction performance.
Download

Paper Nr: 44
Title:

Electromyographic Signal Dynamic Behavior in Neuropathies - Spectral Parameters Evaluation and Classification

Authors:

Maria Marta Santos, Ana Luisa Gomes, Hugo Gamboa, Mamede Carvalho, Susana Pinto and Carla Quintão

Abstract: Amyotrophic Lateral Sclerosis (ALS) is a neurodegenerative disease characterized by motor neurons degeneration, which reduces muscular force, being very difficult to diagnose. Mathematical methods, such as Coherence, Phase Locking Factor (PLF), Fractal Dimension (FD), Lempel-Ziv (LZ) techniques, Detrended Fluctuation Analysis (DFA) and Multiscale Entropy (MSE) are used to analyze the surface electromiographic signal’s chaotic behavior and evaluate different muscle groups’ synchronization. Surface electromiographic signal acquisitions were performed in upper limb muscles, being the analysis executed for instants of contraction recorded from patients and control groups. Results from LZ, DFA and MSE analysis present capability to distinguish between the patient and the control groups, whereas coherence, PLF and FD algorithms present results very similar for both groups. LZ, DFA and MSE algorithms appear then to be a good measure of corticospinal pathways integrity. A classification algorithm was applied to the results in combination with extracted features from the surface electromiographic signal, with an accuracy percentage higher than 70% for 118 combinations for at least one classifier. The classification results demonstrate capability to distinguish both groups. These results can demonstrate a major importance in the disease diagnose, once surface electromyography (sEMG) may be used as an auxiliary diagnose method.
Download

Paper Nr: 52
Title:

Conceptual Design and Evaluation of a Multichannel ECG Data Acquisition Device

Authors:

Mohammadreza Robaei, Yesim Serinagaoglu Dogrusoz and Fikret Küçükdeveci

Abstract: In this study, we developed a conceptual design for a high resolution multichannel ECG data acquisition system for recording of electrical activity of the heart. The system has modular architecture, both in hardware and software layers. It consists of several recording units controlled by sub-microcontrollers, and one main unit that contains the main-microcontroller. Special distributed message based operating system has been developed and embedded to sub-microcontrollers and main-microcontroller to provide communication between them. The operating system is accomplished by the General Purpose Parallel Bus (GPPB) developed for this design. GPPB is responsible to convey commands, data, addresses, and handshaking messages. In each recording unit, 8 channels have been sampled by octal simultaneous 24-bit high resolution S-? analog-to-digital converter. Sampled data is read out via Serial Peripheral Interface (SPI) by the corresponding sub-microcontroller. Then, data in the sub-microcontrollers are transferred to the main-microcontroller using GPPB. At the last step, recorded data is sent from the main-microcontroller to the computer using USB interface.
Download

Paper Nr: 57
Title:

Analyzing the Transfemoral Amputee Gait using Inertial Sensors - Identifying Gait Parameters for Investigating the Symmetry of Gait - A Pilot Study

Authors:

Katja Orlowski, Harald Loose, Falko Eckardt, Jürgen Edelmann-Nusser and Kerstin Witte

Abstract: The amputation of a lower limb is a drastic event and it completely changes the life of the person. Current development of prosthesis is already advanced, but most of the affected persons suffer from changes in the gait which are visible to the general public. The gait of transfemoral amputees was investigated in the laboratory environment and is called asymmetric due to different facts: shorter step length, smaller velocity and smaller cadence. The use of mobile inertial sensors can be supportive in the rehabilitation process of these patients. That is why a pilot study is conducted to evaluate the gait of transfemoral amputees and compare their gait parameters with those of the healthy subjects. The purpose of the investigation is to identify gait parameters showing the asymmetric properties of the amputees gait. Eight parameters seem to be distinctive and descriptive.
Download

Paper Nr: 59
Title:

Estimation of Fingertip Force from Surface EMG - A Multivariate Bayesian Mixture of Experts Approach

Authors:

Tara Baldacchino, William Jacobs, Sean R. Anderson, Keith Worden and Jennifer Rowson

Abstract: Improving the dexterity of active prostheses is a major research area amalgamating machine learning algorithms and biosignals. A recent research niche has emerged from this- providing proportional control to a prosthetic hand by modelling the force applied at the fingertips using surface electromyography (sEMG). The publicly released NinaPro database contains sEMG recording for 6 degree-of-freedom force activations for 40 intact subjects. In this preliminary study the authors successfully perform multivariate force regression using Bayesian mixture of experts (MoE). The accuracy of the model is compared to the benchmark set by the authors of NinaPro; comparable performance is achieved, however in this work a lower dimensional feature extraction representation obtains the best modelling accuracies, hence reducing training time. Inherent to the Bayesian framework is the inclusion of uncertainty in the model structure, providing a natural step in obtaining confidence bounds on the predictions. The MoE model used in this paper provides a powerful method for modelling force regression with application to actively controlling prosthetic and robotic arms for rehabilitation purposes, resulting in highly refined movements.
Download

Paper Nr: 61
Title:

The Theta/Beta Ratio as an Indicator of Evolution in Pediatric Patients Treated for Attention-Deficit/Hyperactivity Disorder (ADHD) - A Retrospective Study

Authors:

María Evangelina Herrán-Paz, Raúl Ortiz-Monasterio, Antonio Rodríguez-Díaz, Olivia Mendoza, Juan R. Castro and Hector J. Willys

Abstract: This study was performed to assess whether the theta/beta ratio can be regarded as an indicator of pediatric patients’ evolution while receiving treatment for ADHD. This required a spectral analysis of the electrophysiological power output from several channels with reference at the vertex (Cz). The files and EEG signals of sixteen clinical cases, which included children and adolescents from 4 to 16 years of age, were analyzed. The analysis of the EEG signals was performed using the Fast Fourier Transform (FFT) to obtain the frequency bands. Patients were under pharmacological treatment for at least one year and had at least 2 EEG studies. The results indicate that a good correlation exists between the theta/beta ratio and the patient’s clinical evolution. 42% of the patients who had 3 or more EEG’s, showed good correlation (r > 0.9), which was coherent with their good clinical evolution. 33% showed linear tendency (0.63 < r < 0.73), with variable response and recovery tendency. 25% had bad correlation (r < 0.3), also with variable treatment response. These results relate to poor adherence to the pharmacological treatment.
Download

Paper Nr: 64
Title:

Neuronal Patterns in the Cavity Wall of Lesions during Gait Cycle in a Rat Model of Brain Lesion Cavities

Authors:

Ioana Nica, Marjolijn Deprez, Frederik Ceyssens, Kris van Kuyck, Robert Puers, Bart Nuttin and Jean-Marie Aerts

Abstract: Oscillatory neural activity was reported to have various physiological roles in information processing of brain functions. It is now established that extracellular activity in the motor cortex encodes aspects of movement, involving planning and motor control. Oscillatory patterns have also been hypothesized to play a role in brain recovery and functional remapping. In this study, we measured neural activity from within the cavity wall of a motor cortex lesion, in a rat model, while the animals performed a skilled walking task. We aim at providing a possible framework of analysis, focused on revealing oscillatory patterns in the cavity wall and their correlation with motor deficits, by using a combination of spectral features, involving power spectra and coherence estimates in the beta and gamma frequency bands.
Download

Paper Nr: 67
Title:

Inertial Measurement Units in Gait Analysis Applications - Questions, Suggestions and Answers

Authors:

Harald Loose, Katja Orlowski and Robert Amann

Abstract: The paper deals with inertial measurement units (IMU) and their application in gait analysis in the wide range from movement monitoring through rehabilitation feedback to sports improvement. An IMU sensor incorporates three microelectromechanical sensors - triple-axis gyroscope, accelerometer, magnetometer – and, optionally, a barometer. The outputs of all sensors are processed by an on-board microprocessor and sent over a serial interface using wired or wireless communication channels. The on-board processing may include sensor conditioning, compensations, strap-down integration as well as determination of orientation. The sensor output is sent to applications working on standard PC, tablets or smart phones using different sampling rates. The output data of one IMU sensor allow motion analysis of the sensor unit itself as well as the motion of the limb where the sensor is mounted to. Using a combination of two or more sensors the movement of limbs/legs can be compared; their relative motion can be investigated; angles can be calculated. In general, in motion and gait analysis, we like to get primary information about the position of all interesting points, the orientation of the limbs and the joint angles at each moment of time as well as derived averaged and summarized characteristics about the motion and the gait. Based on our own investigations the paper discusses how much information is really necessary to determine gait events and gait features for different purposes.
Download

Paper Nr: 70
Title:

Information Fusion for Semi-supervised Cluster Labelings

Authors:

Huaying Li and Aleksandar Jeremic

Abstract: Clustering analysis is a widely used technique to find hidden patterns of a data set. Combining multiple clustering results into a consensus clustering (cluster ensemble) is a popular and efficient method to improve the quality of clustering analysis. Many algorithms were proposed in the literature and most of which are unsupervised learning techniques. In this paper, we proposed a semi-supervised cluster ensemble algorithm. It is so-called semi-supervised because labels of some data points in the given data set are known or provided by experts. To evaluate the performance of the proposed algorithm, we compare it with other well-known algorithms, such as MCLA and BCE.
Download

Paper Nr: 72
Title:

Spectral and Time Domain Parameters for The Classification of Atrial Fibrillation

Authors:

Diana Batista and Ana Fred

Abstract: Atrial fibrillation (AF) is the most common type of arrhythmia. This work presents a pattern analysis approach to automatically classify electrocardiographic (ECG) records as normal sinus rhythm or AF. Both spectral and time domain features were extracted and their discrimination capability was assessed individually and in combination. Spectral features were based on the wavelet decomposition of the signal and time parameters translated heart rate characteristics. The performance of three classifiers was evaluated: k-nearest neighbour (kNN), artificial neural network (ANN) and support vector machine (SVM). The MITBIH arrhythmia database was used for validation. The best results were obtained when a combination of spectral and time domain features was used. An overall accuracy of 99.08 % was achieved with the SVM classifier.
Download

Paper Nr: 73
Title:

Interfaces in a Game-theoretic Setting for Controlling the Plasmodium Motions

Authors:

Andrew Schumann and Krzysztof Pancerz

Abstract: The plasmodium is the large one-cell organism containing a mass of multinucleate protoplasm. It is an active feeding stage of Physarum polycephalum or Badhamia utricularis and it moves by protoplasmic streaming which reverses every 30-60 s. In moving, the plasmodium switches its direction or even multiplies in accordance with different biosignals attracting or repelling its motions, e.g. in accordance with pheromones of bacterial food, which attract the plasmodium, and high salt concentrations, which repel it. So, the plasmodium motions can be controlled by different topologies of attractants and repellents so that the plasmodium can be considered a programmable biological device in the form of a timed transition system, where attractants and repellents determine the set of all plasmodium transitions. Furthermore, we can define $p$-adic probabilities on these transitions and, using them, we can define a knowledge state of plasmodium and its game strategy in occupying attractants as payoffs for the plasmodium. As a result, we can regard the task of controlling the plasmodium motions as a game and we can design different interfaces in a game-theoretic setting for the controllers of plasmodium transitions.
Download

Paper Nr: 76
Title:

ECG Biometrics Using a Dissimilarity Space Representation

Authors:

Francisco Marques, Carlos Carreiras, André Lourenço, Ana Fred and Rui Ferreira

Abstract: Electrocardiogram (ECG) biometrics are a relatively recent trend in biometric recognition, with at least 13 years of development in peer-reviewed literature. Most of the proposed biometric techniques perform classification on features extracted from either heartbeats or from ECG based transformed signals. The best representation is yet to be decided. This paper studies an alternative representation, a dissimilarity space, based on the pairwise dissimilarity between templates and subjects´ signals. Additionally, this representation can make use of ECG signals sourced from multiple leads. Configurations of three leads will be tested and contrasted with single-lead experiments. Using the same k-NN classifier the results proved superior to those obtained through a similar algorithm which does not employ a dissimilarity representation. The best Authentication EER went as low as 1.53% for a database employing 503 subjects. However, the employment of extra leads did not prove itself advantageous.
Download

Paper Nr: 1
Title:

ECG Denoising based on PCA and using R Peaks Detection

Authors:

Talbi Mourad

Abstract: In this paper, we propose a new Electrocardiogram (ECG) Denoising technique based on Principal Component Analysis (PCA) and using R peaks detection. This technique consists at first step in cutting the entire ECG signal into frames then the denoising is performed frame by frame by using PCA. Each frame is located between two successive R peaks. The R peaks detection is performed by using a new detection method based on multi-scale product of the undecimated wavelet coefficients. The Reconstructed ECG signal is obtained by concatenating all the denoised frames. The evaluation of the proposed technique is performed by comparing it to the denoising technique based on PCA and applied to the entire noisy ECG signal. The two techniques are tested on four ECG signals taken from MIT-BIH database. The used criteria in this evaluation of these two techniques are the SNR improvement and the mean square error (MSE). The obtained results from this evaluation show clearly that the denoising technique based on PCA and applied to the entire noisy ECG signal, is slightly better than the proposed technique. However this latter has the advantage of working in real-time because the processing is performed frame by frame and not on the entire noisy ECG signal. Concerning the new proposed technique of R peaks detection, it is very accurate because it permits a perfect reconstruction of the ECG signal when concatenating all the frames.
Download

Paper Nr: 6
Title:

Determination of Bifurcation Angles of the Retinal Vascular Tree through Multiple Orientation Estimation based on Regularized Morphological Openings

Authors:

Sandra Morales, Álvar-Ginés Legaz-Aparicio, Valery Naranjo and Rafael Verdú-Monedero

Abstract: This paper describes a new approach to compute bifurcation angles in retinal images. This approach is based on the estimation of multiple orientations at each pixel of a gray retinal image. The main orientations are provided by directional openings whose outputs are regularized in order to extend the orientation information to the whole image. The detection of vessel bifurcations is based on the coexistence of two or more than two different main orientations at the same pixel. Once the bifurcations and crossovers has been identified, bifurcation angles are calculated. The proposed procedure of computing bifurcation angles by means of orientation estimation at all pixels of the gray level image is much more stable than those methods which are based on the skeleton of the vascular tree, since a slight variation of a pixel of the skeleton can produce a significant change in the angle value.
Download

Paper Nr: 9
Title:

Discrimination of Healthy and Post-partum Subjects using Wavelet Filterbank and Auto-regressive Modelling

Authors:

Rolf Vetter, Jonas Schild, Annette Kuhn and Lorenz Radlinger

Abstract: Rehabilitation therapies to treat female stress urinary incontinence focus on the reactivation of pelvic floor muscle (PFM) activity. An objective measure is essential to assess a subject’s improvement in PFM capabilities and increase the success rate of the therapy. In order to provide such a measure, we propose a method for the discrimination of healthy subjects with strong PFM and post-partum subjects with weak PFM. Our method is based on a dyadic discrete wavelet decomposition of electromyograms (EMG) that projects slow-twitched and fast-twitched muscle activities onto different scales. We used a parametric auto-regressive (AR) model for the estimation of the frequency of each wavelet scale to overcome the poor frequency resolution of the dyadic decomposition. The feature used for discrimination was the frequency of the wavelet scale with the highest variance after interpolation with the nearest neighboring scales. Twenty-three healthy and 26 post-partum women with weak PFM who executed 4 maximum voluntary contractions (MVC) were retrospectively analysed. EMGs were recorded using a vaginal probe. The proposed method has a lower rate of false discrimination (4%) compared to the two classical methods based on mean (9%) and median (7%) frequency estimation from the power spectral density.
Download

Paper Nr: 14
Title:

Brain Activity Quantification for Sport Audiovisual Content Visualization using EEG

Authors:

Adrián Colomer, Valery Naranjo, Jaime Guixeres, Juan Carlos Rojas, Javier Coret and Mariano Alcañiz

Abstract: This study aims to analyse the brain activity occurring during the observation of football videos randomly intermingled in a documentary. The electroencephalography recording is employed to measure the signal scalp of 20 healthy subjects. The signal preprocessing is performed using Independent Component Analysis (ICA) and ADJUST. The cerebral activity is quantified through Global Field Power (GFP) in order to classify the clips following an emotive scale, to establish differences between positive and negative video stimuli. Results are summarized as follows: (1) Comparing the cerebral activity of a positive video with its predecessor neutral stimulus, significant differences were obtained (p = .0019). However, the same analysis for negative videos shows no significant differences (p = .096). (2) The number of peaks in brain activity allow us to classify the videos used in the study. (3) The brain activity in theta and beta bands presents different distribution of peaks, occurring at different frames.
Download

Paper Nr: 15
Title:

Intuitionistic Fuzzy Sets with Shannon Relative Entropy

Authors:

Lingling Zhao, Yingjun Zhang, Peijun Ma, Xiaohong Su and Chunmei Shi

Abstract: Bio-signal or bio-medical pattern recognition includes uncertainty. Intuitionistic fuzzy sets (IFSs) are effective representation of the uncertainty factor. We present a pattern recognition method based on the weighted distance of intuitionistic fuzzy sets (IFSs) in dealing with the fuzzy recognition problem. The proposed method has a particular focus on handling the problem of choosing feature weights and feature selection in the framework of IFSs. Depending on the idea of information-theoretic entropy and relative entropy, a method is presented in dealing with the said two key problems, i.e., choosing feature weights and feature selection. The proposed pattern recognition method in the framework of IFSs can not only represent the dissimilarity between pair of features based on choosing feature weights but also reduce the computational complexity depending on feature selection. Finally, a numerical example is utilized to validate the proposed pattern recognition method.
Download

Paper Nr: 16
Title:

Identification of Observations of Correct or Incorrect Actions using Second Order Statistical Features of Event Related Potentials

Authors:

P. Asvestas, A. Korda, S. Kostopoulos, I. Karanasiou, G. K. Matsopoulos and E. M. Ventouras

Abstract: The identification of correct or incorrect actions is a very significant task in the field of the brain-computer interface systems. In this paper, observations of correct or incorrect actions are identified by means of event related potentials (ERPs) that represent the brain activity as a response to an external stimulus or event. ERP signals from 47 electrodes, located on various positions on the scalp, were acquired from sixteen volunteers. The volunteers observed correct or incorrect actions of other subjects, who performed a special designed task. The recorded signals were analysed and five second order statistical features were calculated from each one. The most prominent features were selected using a statistical ranking procedure forming a set of 32 feature vectors, which were fed to a Support Vector Machines (SVM) classifier. The performance of the classifier was assessed by means of the leave-one-out cross validation procedure resulting in classification accuracy 84.4%. The obtained results indicate that the analysis of ERP-signals that are collected during the observation of the actions of other persons could be used to understand the specific cognitive processes that are responsible for processing the observed actions.
Download

Paper Nr: 18
Title:

Features of Event-related Potentials Used to Recognize Clusters of Facial Expressions

Authors:

Masahiro Yasuda, Zhang Dou and Minoru Nakayama

Abstract: To assess human emotion using electroencephalograms (EEGs), the relationship between emotional impressions of images of facial expressions and features of Event Related Potentials (ERPs) recorded using three electrodes was analyzed. First, two clusters of emotional impressions were extracted using two-dimensional responses of the Affect Grid scale. Second, features of ERPs in response to the two clusters were examined. Time slots where amplitude differences in ERP appeared were measured, and differences in the frequency power of ERP were also extracted for each electrode. To evaluate these features, prediction performance for the two clusters was examined using discriminant analysis of the features. Also, the dependency of some band pass filters was measured.
Download

Paper Nr: 20
Title:

New Spectral Representation and Dissimilarity Measures Assessment for FTIR-spectra using Unsupervised Classification

Authors:

Francisco Peñaranda, Fernando López-Mir, Valery Naranjo, Jesús Angulo, Lena Kastl and Juergen Schnekenburger

Abstract: In this work, different combinations of dissimilarity coefficients and clustering algorithms are compared in order to separate FTIR data in different classes. For this purpose, a dataset of eighty five spectra of four types of sample cells acquired with two different protocols are used (fixed and unfixed). Five dissimilarity coefficients were assessed by using three types of unsupervised classifiers (K-means, K-medoids and Agglomerative Hierarchical Clustering). We introduce in particular a new spectral representation by detecting the signals´ peaks and their corresponding dynamics and widths. The motivation of this representation is to introduce invariant properties with respect to small spectra shifts or intensity variations. As main results, the dissimilarity measure called Spectral Information Divergence obtained the best classification performance for both treatment protocols when is used over the proposed spectral representation.
Download

Paper Nr: 34
Title:

Can We Find Deterministic Signatures in ECG and PCG Signals?

Authors:

J. H. Oliveira, V. Ferreira and M. Coimbra

Abstract: The first step in any non linear time series analysis, is to characterize signals in terms of periodicity, stationarity ,linearity and predictability. In this work we aim to find if PCG (phonocardiogram) and ECG (electrocardiogram) time series are generated by a deterministic system and not from a random stochastic process. If PCG and ECG are non-linear deterministic systems and they are not very contaminated with noise, data should be confined to a finite dimensional manifold, which means there are structures hidden under the signal that could be used to increase our knowledge in forecasting future values of the time series. A non-linear process can give rise to very complex dynamic behaviours, even though the underlying process is purely deterministic and probably low-dimensional. To test this hypothesis, we have generated 99 surrogates and then we compared the fitting capability of AR (auto-regressive) models on the original and surrogate data. The results show with a 99% of confidence level that PCG and ECG were generated by a deterministic process. We compared the fitting capability of an ECG and PCG to AR linear models, using a multi-channel approach. We make an assumption that if a signal is more linearly predictable than another one, it may adjust better to these AR linear models. The results showed that ECG is more linearly predictable (for both channels) than PCG, although a filtering step is needed for the first channel. Finally we show that the false nearest neighbour method is insufficient to identify the correct dimension of the attractor in the reconstructed state space for both PCG and ECG signals.
Download

Paper Nr: 36
Title:

Effect of Fuzzy and Crisp Clustering Algorithms to Design Code Book for Vector Quantization in Applications

Authors:

Yukinori Suzuki, Hiromu Sakakita and Junji Maeda

Abstract: Image coding technologies are widely studies not only to economize storage device but also to use communication channel effectively. In various image coding technologies, we have been studied vector quantization. Vector quantization technology does not cause deterioration image quality in a high compression region and also has a negligible computational cost for image decoding. It is therefore useful technology for communication terminals with small payloads and small computational costs. Furthermore, it is also useful for biomedical signal processing: medical imaging and medical ultrasound image compression. Encoded and/or decoded image quality depends on a code book that is constructed in advance. In vector quantization, a code book determines the performance. Various clustering algorithms were proposed to design a code book. In this paper, we examined effect of typical clustering (crisp clustering and fuzzy clustering) algorithms in terms of applications of vector quantization. Two sets of experiments were carried out for examination. In the first set of experiments, the learning image to construct a code book was the same as the test image. In practical vector quantization, learning images are different from test images. Therefore, learning images that were different from test images were used in the second set of experiments. The first set of experiments showed that selection of a clustering algorithm is important for vector quantization. However, the second set of experiments showed that there is no notable difference in performance of the clustering algorithms. For practical applications of vector quantization, the choice of clustering algorithms to design a code book is not important.
Download

Paper Nr: 37
Title:

Binary Reweighted l1-Norm Minimization for One-Bit Compressed Sensing

Authors:

Hui Wang, Xiaolin Huang, Yipeng Liu, Sabine Van Huffel and Qun Wan

Abstract: The compressed sensing (CS) can acquire and reconstruct a sparse signal from relatively fewer measurements than the classical Nyquist sampling. Practical ADCs not only sample but also quantize each measurement to a finite number of bits; moreover, there is an inverse relationship between the achievable sampling rate and the bit depth. The quantized CS has been studied recently and it has been demonstrated that accurate and stable signal acquisition is still possible even when each measurement is quantized to just a single bit. Many algorithms have been proposed for 1-bit CS however, most of them require that the prior knowledge of the sparsity level (number of the nonzero elements) should be known. In this paper, we explored the reweighted l1-norm minimization method in recovering signals from 1-bit measurements. It is a nonconvex penalty and gives different weights according to the order of the absolute value of each element. Simulation results show that our method has much better performance than the state-of-art method (BIHT) when the sparsity level is unknown. Even when the sparsity level is known, our method can get a comparable performance with the BIHT method. Besides,we validate our methods in an ECG signal recovery problem.
Download

Paper Nr: 48
Title:

Multi-biosignals Analysis - The Effect of Peripheral Nerve Stimulation on Skin Conductance and Heart Rate Variability

Authors:

Tiago Araújo, Pedro Dias, Neuza Nunes and Hugo Gamboa

Abstract: Objectives: This study aims to evaluate the influence of standard electrical stimulation on human electrophysiology. Methods: A total of 10 healthy subjects were submitted to the same protocol. The electrical stimuli were applied on the median nerve of the left wrist. Blood Volume Pulse (BVP) and Electrodermal Activity (EDA) signals were acquired from the index finger through an oximeter and from both the abductor pollicis muscle and the 3rd palmar interosseous muscle of the right hand, respectively. Nerve stimulation was performed using increasing intensities current: range from 5 to 30 mA, with 1mA step and applying 20 stimuli per step. Heart Rate (HR) and Heart Rate Variability (HRV) were computed, from the analysis of the latency between BVP pulses, in basal state and during stimulation. EDA parameters response latency, response rise time and readaptation slope were computed for each burst. Discussion: Electrical stimulation reveals to influence several parameters of the Autonomic Nervous System (ANS). It was easily detected an EDA rise response for each of the applied bursts and also an increase of the HRV during stimulation.
Download

Paper Nr: 53
Title:

Packet-size-Controlled ECG Compression Algorithm based on Discrete Wavelet Transform and Running Length Encoding

Authors:

Asiya Al-Busaidi and Lazhar Khriji

Abstract: This paper presents a development of new size-controlled compression algorithm for Electrocardiogram signal (ECG). Discrete Wavelet Transform (DWT) method, Bit-Field Preserving (BFP) and Running Length Encoding (RLE) are selected as compression tools in this work. Even though DWT-BFP-RLE is a lossy compression method, it has shown a potential in preserving the critical (diagnostic) part of the signal. Knowing that the size of transmitted packets of the battery-powered mobile telecardiology systems is limited within few bytes, the current algorithm is aiming to ensure that the compressed packets fit into the limited payload size. A parametric study of different mother wavelets and decomposition levels of DWT is presented with an emphasize on compression ratio (CR), percentage mean-square difference (PRD) and quality score (QS). The mother wavelet giving the best CR and QS results is then adopted to perform the dynamic compression algorithm on ECG records from MIT-BIH arrhythmia database.
Download

Paper Nr: 55
Title:

SMUAP Decomposition Method Considering Estimated Distance from Surface Electrodes to Motor Unit during Voluntary Isovelocity Elbow Flexion

Authors:

Jun Akazawa and Ryuhei Okuno

Abstract: The purpose of this study was to decompose Surface Motor Unit Acton Potential (SMUAP) clearly even in case that the estimated distance from surface electrodes to motor units changing during voluntary isovelocity elbow flexion. We developed decomposition algorithm focusing on SMUAP Profile, and investigated motor unit (MU) recruitment and firing rate in biceps short head muscle during isovelocity elbow flexion using our developed method. As a result, we concerned that calculated MUs firing rates were almost same as the results in the previous studies, and the estimated MU’s territory was changed with elbow flexion. It was shown that the developed algorithm was useful for decomposing SMUAP when the estimated distance from surface electrodes to MU changing during voluntary isovelocity elbow flexion.
Download

Paper Nr: 58
Title:

Dynamic Response of Electrocardiographic Indices During Abrupt Heart Rate Changes - Comparison between Young and Middle-aged Subjects

Authors:

Marcos Javier Teperino, María Paula Bonomini, Pablo Daniel Cruces and Pedro David Arini

Abstract: Abnormal modifications in ventricular repolarization dispersion (VRD) have been shown to constitute a substrate for malignant arrhythmias. In this work, we have induced abrupt heart rate (HR) changes to young and middle-aged healthy subjects through a Tilt-test and have analyzed the evolution of several VRD indices. Duration ones, based on electrocardiogram intervals; energy ones, developed through a Principal Components Analysis (PCA) in T-wave; and the morphology ones, extracted feature from an absolute T-wave. In both groups, results have shown significant decreases in early repolarization duration. These changes are responsible for the alterations in the total repolarization duration, because T-wave peak-to-end has not shown statistical significance. Moreover, we have found significant decreases in total, early and late repolarization energy, and in the T-wave amplitude. In another sense, we have observed that the repolarization energy obtained by PCA jointly with early T-wave slope and amplitude have been able to reflect VRD differences between young and middle-aged subjects. Finally, this work provides the range of values for VRD in normal conditions during abrupt HR changes. Outside this range, we could assume that it exists a cardiac risk.
Download

Paper Nr: 63
Title:

Mathematical Modelling and Numerical Simulations in Nerve Conduction

Authors:

N. J. Ford, P. M. Lima and P. M. Lumb

Abstract: In this paper we are concerned with the numerical solution of the discrete FitzHugh-Nagumo equation. This equation describes the propagation of impulses across a myelinated axon. We analyse the asymptotic behaviour of the solutions of the considered equation and numerical approximations are computed by a new algorithm, based on a finite difference scheme and on the Newton method. The efficiency of the method is discussed and its performance is illustrated by a set of numerical examples.
Download

Paper Nr: 66
Title:

Estimating Positive Definite Matrices using Frechet Mean

Authors:

Mehdi Jahromi, Kon Wong and Aleksandar Jeremic

Abstract: Estimation of covariance matrices is a common problem in signal processing applications. Commonly applied techniques based on the cost optimization (e.g. maximum likelihood estimation) result in an unconstrained estimation in which the positive definite nature of covariance matrices is ignored. Consequently this may result in accurate estimation of the covariance matrix which may affect overall performance of the system. In this paper we propose to estimate the covariance matrix using Fréchet mean which ensures that the estimate also has positive definite structure. We demonstrate the applicability of the proposed technique on both estimation and classification accuracy using numerical simulations. In addition we discuss some of the preliminary results we obtained by applying our techniques to high content cell imaging data set.
Download

Paper Nr: 68
Title:

Detecting Nonlinear Acoustic Properties of Snoring Sounds using Hilbert-Huang Transform

Authors:

Tsuyoshi Mikami, Satoshi Ueki, Hirotaka Takahashi and Kazuya Yonezawa

Abstract: Since snoring is known to be related to sleep apnea syndrome, many medical/physiological researchers have focused on the biomechanism of snoring and the acoustic properties. Snoring sounds are the mixture of the nonlinear oscillation sounds of the oropharyngeal soft tissues and the airflow noises during inhalation. In conventional studies, however, such properties have not been paid attention to, because there were no suitable methods for the analysis of nonlinear and nonstationary time series data. In this paper, we adopt Hilbert-Huang Transform (HHT) to clarify the nonlinear and nonstationary properties in a nasal snoring sound. As a result, two types of frequency fluctuation are found in the Hilbert-Huang spectrum.
Download

Paper Nr: 69
Title:

Classification of Involuntary Hand Movements

Authors:

Aki Härmä

Abstract: Involuntary movements of arms and legs reflect neural and metabolic processes in the human body. In this paper the focus is on the properties of physiological tremor, shivering, and tremors caused by physical fatigue measured in fingers of a subject. Three different signal modeling paradigms are compared in the paper using accelerometer data. It is first demonstrated that the data can be modeled as a nearly stationary low-order AR process. Next, it is shown that the different data types can be classified using long-term feature distributions in a naive Bayes classifier. Finally, a comparable performance is obtained when the signal is modeled as a Markov process emitting small prototypical movements or jerks.
Download

Paper Nr: 71
Title:

Balance Perturbation Leads a Stretching Reflexion on Tibialis Anterior Muscle

Authors:

Renata Gonçalves Pinheiro Corrêa, Matheus Lucas Aguiar, Caluê Papcke, Eduardo Borba Neves, Agnelo Denis Vieira and Eduardo Mendonça Scheeren

Abstract: Human posture control is a sophisticated process involving the relationship among multiple joints, muscle groups and environment. The aim of this study is to show how the balance perturbation (in posterior-anterior direction) leads to a stretching reflexion on the tibialis anterior (TA) muscle. A case study that involved a male participant with 23 years old. To disturb the participant's balance, it has been employed a specially plataform designed with dimensions 1.5 m by 1.5 m with movement of 5 mm of amplitude on a total time of 3 ms along the axis coinciding with participant's anterior-posterior axis. Soleus (SO) and TA electromyography signal (EMG) has been recorded. Perturbation in the equilibrium was delivered in the posterior-anterior direction. The first event observed was the pre-activation of the TA muscle that leads a reduction in the SO muscle activation, due the stretch reflex at TA.
Download

Paper Nr: 74
Title:

Improving Performance of Bio-radars for Remote Heartbeat and Breathing Detection by using Cyclostationary Features

Authors:

Daniel Malafaia, José Vieira and Ana Tomé

Abstract: In this paper we present a continuous wave radar created using a software defined radio platform that uses doppler effect to measure the heart-rate and breathing. The measurements are evaluated using a classic energy detection method and a cyclic spectrum estimation technique, then the two methods are compared. The results show that by taking advantaging of the cyclic autocorrelation of the bio-signals we can get better detection than the usual energy detection.
Download