BIOSIGNALS 2014 Abstracts

Full Papers Short Papers
Full Papers
Paper Nr: 22
Title:

Data based Modelling of Expired Airflow Clarifies Chronic Obstructive Pulmonary Disease
Authors:

Topalovic Marko, Vasileios Exadaktylos, Jean-Marie Aerts, Thierry Troosters, Marc Decramer, Daniel Berckmans and Wim Janssens
Abstract: One of the major health challenges of the future is Chronic Obstructive Pulmonary Disease (COPD). It is characterized by airflow limitations, although current diagnosis does not give attention to the flow measurements. We aimed to develop a data-based model of the decline of the forced expiratory flow. Moreover, we analysed the relationship of model parameters with COPD presence and its severity. The data-based model was developed in 474 smoking individuals, who are at risk of having COPD, and have performed complete pulmonary function tests in order to identify whether the disease is present and at which stage. The time series of the decline of the flow was parameterised using the poles and steady state gain (SSG) of a second order transfer function model. These parameters were then linked with the presence of COPD. Observing SSG, median (IQR) in subjects with COPD was lower 3.9(2.7-5.6) compared to 8.2(7.1-9.3) in subjects without, (p<0.0001). Significant difference was also found when observing median (IQR) of two poles in subjects without disease were 0.9868(0.9810-0.9892) and 0.9333(0.9010-0.9529), respectively, compared to 0.9929(0.9901-0.9952) and 0.9082(0.8669-0.9398) in subjects with COPD (p<0.001 for both poles). Forced exhaled air can be used to expand understanding of the COPD. Moreover, the suggested parameterisation of the flow decline could be used to access COPD using spirometry.
Download
Paper Nr: 24
Title:

Velum Movement Detection based on Surface Electromyography for Speech Interface
Authors:

João Freitas, António Teixeira, Samuel Silva, Catarina Oliveira and Miguel Sales Dias
Abstract: Conventional speech communication systems do not perform well in the absence of an intelligible acoustic signal. Silent Speech Interfaces enable speech communication to take place with speech-handicapped users and in noisy environments. However, since no acoustic signal is available, information on nasality may be absent, which is an important and relevant characteristic of several languages, particularly European Portuguese. In this paper we propose a non-invasive method – surface Electromyography (EMG) electrodes - positioned in the face and neck regions to explore the existence of useful information about the velum movement. The applied procedure takes advantage of Real-Time Magnetic Resonance Imaging (RT-MRI) data, collected from the same speakers, to interpret and validate EMG data. By ensuring compatible scenario conditions and proper alignment between the EMG and RT-MRI data, we are able to estimate when the velum moves and the probable type of movement under a nasality occurrence. Overall results of this experiment revealed interesting and distinct characteristics in the EMG signal when a nasal vowel is uttered and that it is possible to detect velum movement, particularly by sensors positioned below the ear between the mastoid process and the mandible in the upper neck region.
Download
Paper Nr: 29
Title:

Observer Design for a Nonlinear Minimal Model of Glucose Disappearance and Insulin Kinetics
Authors:

Driss Boutat, Mohamed Darouach and Holger Voos
Abstract: This work deals with an observer design for a nonlinear minimal dynamic model of glucose disappearance and insulin kinetics (GD-IK). At first, the model is transformed into a nonlinear observer normal form. Then, using the knowledge of the plasma blood glucose level, we estimate the state variables that are not directly available from the system, i.e. the remote compartment insulin utilization, the plasma insulin deviation and the infusion rate. In addition, we estimate the amount of absorbed glucose by means of the inverse dynamics.
Download
Paper Nr: 38
Title:

Understanding the Genesis of Cardiac Signals in Electrical Impedance Tomography
Authors:

M. Proença, F. Braun, M. Lemay, B. Grychtol, M. Bührer, M. Rapin, P. Krammer, S. Böhm, J. Solà and J.-Ph. Thiran
Abstract: Electrical impedance tomography (EIT) is a safe and low-cost imaging technology allowing the monitoring of ventilation. While most EIT studies have investigated respiration-related events, EIT-based cardiovascular applications have received increasing attention over the last years only. Variations in intra-thoracic blood volume induce impedance changes that can be monitored with EIT and used for the estimation of hemodynamic parameters. There is, however, increasing evidence that variations in blood volume are not the only factors contributing to cardiac impedance changes within the heart. The mechanical action of the myocardium and movement of the heart-lung interface are suspected to generate impedance changes of non-negligible amplitude. To test this hypothesis we designed a dynamic 2D bio-impedance model from segmented human magnetic resonance data. EIT simulations were performed and showed that EIT signals in the heart area might be dominated up to 70% by motion-induced impedance changes.
Download
Paper Nr: 39
Title:

Angle Measurements during 2D and 3D Movements of a Rigid Body Model of Lower Limb - Comparison between Integral-based and Quaternion-based Methods
Authors:

Takashi Watanabe and Kento Ohashi
Abstract: Angle measurement system using inertial sensors was developed by our research group, in which lower limb angles were calculated based on the integral of angular velocity using Kalman filter. The angle calculation method was shown to be practical in measurement of angles in the sagittal plane during gait of healthy subjects. In this paper, in order to realize practical measurements of 3 dimensional (3D) movements with inertial sensors, the integral-based and the quaternion-based methods were tested in measurement of 2D movements in the sagittal plane and 3D movements of rigid body models of lower limb. The tested three calculation methods, extended integral-based method, quaternion-based method proposed in this study and simplified previous quaternion-based method, were suggested to measure the 2D movements with high measurement accuracy. It was also suggested that there were no large difference in measurement of 2D and 3D movements between 3 methods. Visualization by stick figure animation of circumduction gait simulated by a healthy subject also suggested that the angle calculation methods can be useful. It is expected to improve measurement accuracies of 3D movements to those of 2D movements.
Download
Paper Nr: 45
Title:

Analysis of Robust Implementation of an EMG Pattern Recognition based Control
Authors:

Simone Benatti, Elisabetta Farella, Emanuele Gruppioni and Luca Benini
Abstract: Control of active hand prostheses is an open challenge. In fact, the advances in mechatronics made available prosthetic hands with multiple active degrees of freedom; however the predominant control strategies are still not natural for the user, enabling only few gestures, thus not exploiting the prosthesis potential. Pattern recognition and machine learning techniques can be of great help when applied to surface electromyography signals to offer a natural control based on the contraction of muscles corresponding to the real movements. The implementation of such approach for an active prosthetic system offers many challenges related to the reliability of data collected to train the classification algorithm. This paper focuses on these problems and propose an implementation suitable for an embedded system.
Download
Paper Nr: 46
Title:

Synchronization of Electroencephalography and Eye Tracking using Global Illumination Changes
Authors:

Daniel Siboska, Henrik Karstoft and Henrik Pedersen
Abstract: This paper describes a flexible method for synchronizing electroencephalography (EEG) and eye tracking (ET) recordings to the presentation of visual stimuli. The method consists of embedding a synchronization signal in the visual stimuli, and recording this signal with both the EEG and ET equipment. The signal is recorded by the EEG device as an additional data channel, and with the camera used in the ET equipment by modulating the global illumination of the scene in time with the synchronizing signal. The prototype system where this method was implemented resulted in a single sample of jitter in both the EEG and ET system, while the ET system achieved a spatial resolution of 1.26 degrees. The system will be used in future work with augmented memory applications.
Download
Paper Nr: 55
Title:

Semi-Markov Modeling-Clustering of Human Sleep with Efficient Initialization and Stopping
Authors:

Chiying Wang, Sergio A. Alvarez, Carolina Ruiz and Majaz Moonis
Abstract: Collective Dynamical Modeling-Clustering (CDMC) is an algorithmic framework for time series dynamical modeling and clustering using probabilistic state-transition models. In this paper, an efficient initialization technique based on Itakura slope-constrained Dynamic Time Warping is applied to CDMC. Semi-Markov chains are used as the dynamical models. Experimental evaluation demonstrates the effectiveness of the proposed approach in providing more realistic dynamical modeling of sleep stage dynamics than Markov models, with improved clustering quality and convergence speed as compared with pseudorandom initialization.
Download
Paper Nr: 69
Title:

Setting the Criteria for the MATHOV + QAVS Tool - Qualitative and Quantitative Aspects for Wearable Fall Prediction
Authors:

Mario Sáenz Espinoza and Miguel Velhote Correia
Abstract: For the first time in history, the world shows a clear trend towards aging. This poses an intrinsic hazard for the ever growing population, which becomes more vulnerable to common age-related illnesses and conditions. One of the most serious risks elders face is falling, as it is responsible for countless admissions to geriatric care institutions and thousands of deaths each year. In an effort to improve elders’ safety and quality of life many groups have address the fall prevention issue, coming to several different results as of what variables are the most important to consider in a fall prediction tool. These variables range from qualitative aspects (history of falls, dementia, use of medication, etc.) to quantitative ones (total walked distance per day, walking cadence, center of mass, etc.), but none of them per se seems to deliver a definite and complete answer to the problem at hand. The paper herein aims to present a new hybrid approach, which combines both the highest co-related qualitative and quantitative biovariables in a single tool: the MATHOV + QAVS, which is proposed as a new fall assessment screening tool and eventually as baseline criteria for a complete elder fall prediction system.
Download
Paper Nr: 72
Title:

Diagnostics of Coronary Stenoses - Analysis of Arterial Blood Pressure Signals and Mathematical Modeling
Authors:

Natalya Kizilova
Abstract: Severity of the coronary stenoses and necessity of the percutaneous coronary intervention is usually estimated basing on analysis of the pressure and flow signals measured in vivo by a pressure gauge at certain distances before and after the stenosis. In the paper the differences in the pressure gradients at different stenosis severity are shown and discussed. A method of decomposition of the measured biosignals into the mean and oscillatory components is proposed. A mathematical model of the steady and pulsatile flow through the viscoelastic blood vessel in the presence of the rigid guiding wire is developed for biomechanical interpretation of the measured coronary blood pressure and flow signals. A novel approach for estimation the stenotic severity basing on the measured and computed data is proposed.
Download
Short Papers
Paper Nr: 10
Title:

The Development of a Stress Measurement System with the Minimal Card Pulse Wave Sensor and the Experiment on Demonstration of the Validity of the System
Authors:

Osamu Nitta, Yasunari Fujimoto and Masanobu Kinoshita
Abstract: [Purpose] This study was designed to analyze relationships between results of chaos analysis and the blood concentration of salivary amylase (s-AMY) and to assess the validity of the results of chaos analysis. [Methods] The subjects were 10 healthy adults. This study was performed under approval from the Ethics Committee, Tokyo Metropolitan University. The subjects were instructed to perform the task including the 3-minute inverse operation (counting 7 from 1000) 3 times. After the task a pulse wave sensor was applied to the index finger. Simultaneously with the measurement, one physician collected a 5ml blood sample. The pulse wave data were converted to the acceleration rate, followed by the chaos analysis and calculation of a degree of parallelism in neighborhood space and size of neighborhood space. The blood s-AMY levels were determined in the blood samples. [Results and Discussion] After the task the mean blood s-AMY level was 58.3 U/L (SD 14.16) and the mean degree of parallelism was 0.178 (0.05) in the chaos analysis of the pulse wave data converted to the acceleration rate. It was confirmed that there is a significant correlation between the blood levels and the degree of parallelism (p<0.05) and Pearson’s product moment correlation coefficient 0.72.
Paper Nr: 15
Title:

Permutation Entropy of the Electroencephalogram Background Activity in Alzheimer’s Disease - Investigation into the Incidence of Repeated Values
Authors:

Samantha Simons and Daniel Abásolo
Abstract: This pilot study applied Permutation Entropy (PE), a non-linear symbolic measure, and a novel modification (modPE), to investigate the regularity of electroencephalogram (EEG) signals from 11 Alzheimer’s disease (AD) patients and 11 age-matched controls given input parameters n (embedding vector), τ (coarse graining) and slide (difference between the start of two concurrent embedding vectors). PE discriminated better than modPE with controls showing reduced regularity over AD patients. Increasing τ identified the greatest differences between EEG signals. Longer embedding vectors were also more able to identify differences. The greatest difference between groups was at Fp1 with n,τ,slide = 3,10,1 (p=0.0112 Kruskal Wallis with Bonferroni). Subject and epoch based leave-one-out cross validation was carried out with thresholding from Receiver Operating Characteristic Curves. The greatest ability to correctly identify AD patients and controls were 81.82% (Fp2 n,τ,slide = 7,4,4, PE and modPE, F7 n,τ,slide = 3,10,1, PE and modPE) and 90.91% (Fp1 n,τ,slide = 3,10,1, PE and modPE), respectively. The maximum accuracy (both groups correctly identified) was 81.82% seen at many electrode and input combinations. All are with subject based analysis. This suggests that PE can identify changes in EEG signals in AD, given appropriate variables. However, modPE makes little improvement over PE.
Download
Paper Nr: 18
Title:

Structural and Functional Changes Occuring During Growth of the Respiratory System Can Be Quantified and Classified
Authors:

Clara M. Ionescu, Dana Copot, Hannes Maes, Gerd Vandersteen, Amélie Chevalier and Robin De Keyser
Abstract: This paper describes the nonlinear effects in the respiratory signals captured by means of the forced oscillation technique (FOT) non-invasive lung function tests. The measurements are performed using a prototype device developed such that it overcomes the limitations present in commercial FOT devices and allows the generation of multisine signals below 4 Hz. The principle of sending detection lines in the frequency domain for characterizing odd and even nonlinear contributions from a nonlinear system are introduced briefly to the reader. Two detection methods are presented: a robust method based on multiple measurements and a fast method based on a single measurement. The ingenious combination of the device and the method allow to detect the nonlinear contributions in the respiratory signals: pressure and flow. The intrinsicly pesent nonlinear effects are quantified by means of a novel index and analyzed in two groups of healthy volunteers, aged 14 years and aged 17 years, respectively. The results we obtain suggest that the proposed device, method and index are a successful combination of lung function testing, signal processing and classification items.
Download
Paper Nr: 20
Title:

Orientation and Mobility with Prosthetic Vision - Combination of Luminosity and Depth Information for Scene Representation
Authors:

Guillaume Tatur, Isabelle Marc, Gerard Dupeyron and Michel Dumas
Abstract: Recent advances in visual prostheses raise good hope for enhancement of late blind people performances in daily life tasks. Autonomy in mobility is a major factor of quality of life and ongoing researches aim to develop new image processing for environment representation and try to evaluate mobility performances. We present a novel approach for the generation of a scene representation devoted to mobility tasks, which may complement current prosthetic vision research. In this work, done in collaboration with low vision rehabilitation specialists, depth cues as well as contrast perception are made accessible through a composite representation. After presenting advantages and drawbacks of a scene representation based solely on captured depth or luminosity information, we introduce our method that combines both types of information in a unique representation based on a temporal scanning of depth layers.
Download
Paper Nr: 21
Title:

Nonparametric Discriminant Projections for Improved Myoelectric Classification
Authors:

Ernest N. Kamavuako, Erik J. Scheme and Kevin B. Englehart
Abstract: Linear discriminant analysis (LDA) is widely used for classification of myoelectric signals and it has been shown to outperform simple classifiers such as k-Nearest Neighbour (kNN). However the normality assumption of the LDA may cause its performance to decrease when the distribution of the feature space is far from Gaussian. In this study we investigate whether nonparametric discriminant (NDA) projections in combination with kNN classifiers can significantly decrease the classification error. Data sets based on both surface and intramuscular electromyography (EMG) were used in order to solve classification problems of up to 9 classes, including simultaneous movements. Results showed that in all data sets, the classification error was significantly lower when using NDA projections compared with LDA.
Download
Paper Nr: 26
Title:

Improving Color Constancy in the Presence of Multiple Illuminants using Depth Information
Authors:

Marc Ebner and Johannes Hansen
Abstract: A human observer is able to judge the color of objects independent of the illuminant. In contrast, a digital sensor (or the retinal receptors for that matter) only measure reflected light which varies with the illuminant. The brain is somehow able to compute a color constant descriptor from the light falling onto the retina. We have improved a well known color constancy algorithm based on local space average color. This color constancy algorithm can be mapped to the different visual processing stages of the human brain. We have extended this algorithm by incorporating depth information. The idea is that wherever there are depth discontinuities there may also be a change of the illuminant in the image. Hence, depth discontinuities are used to separate different illuminants. This allows us to better estimate the local illumination and allows us to compute an improved color constant descriptor. We also compute local space average depth to decide locally whether to average data from retinal sensors uniformly or non-uniformly. We show how our algorithm works on real world scenes. Depth information is obtained from a standard Kinect sensor.
Download
Paper Nr: 31
Title:

Coherence and Phase Locking Disruption in Electromyograms of Patients with Amyotrophic Lateral Sclerosis
Authors:

Mafalda Camara, Mamede de Carvalho, Tiago Araújo, Hugo Gamboa and Carla Quintão
Abstract: In motor neuron disease, the aim of therapy is to prevent or slow neuronal degeneration and early diagnosis is thus essential. Hypothesising that beta-band (15􀀀30 Hz) is a measure of pathways integrity as shown in literature, coherence and phase locking factor (PLF) could be used as an electrophysiological indicator of upper and lower neuron integrity in patients with amyotrophic lateral sclerosis (ALS). In this work are applied such tools in different variable situations. Coherence and PLF analysis was computed for EMG signals registered from 2 groups: control subjects and ALS patients. The data was recorded during instants of steady contraction for both contra and ipsilateral acquisitions. Ipsilateral coherence and PLF was computed for one member of each group and results present significant differences between both groups. Contrarily, contralateral acquisitions were performed on 6 members of each group and both coherence and PLF results present no significant differences. So, while control subjects present no neuronal or muscular disorders and therefore higher synchrony and coherence for beta-band EMG signals, patients with ALS do not present synchronism or coherence in any frequency, specially for beta-band. All results allowed to conclude that contralateral coherence is not a good measure of corticospinal pathways integrity. However, ipsilateral acquisitions show promising results and it is possible to affirm that ipsilateral measurements may reflect neuronal degeneration. For future work is suggested a deeper analysis of PLF, that appear to have potential as a quantitative test of upper and lower neuron integrity related to ALS.
Download
Paper Nr: 36
Title:

A Controlled Study for Measuring Stress Induced Changes of Physiologic Tremor with a Wearable Activity Sensor
Authors:

Rüdiger Zillmer, Brian Newby and Robert Treloar
Abstract: This work presents the results of a controlled study with the aim to quantify the effect of emotional stress on physiologic tremor. A paced auditory addition test is utilized to induce emotional stress. The tremor is measured by means of a wearable activity sensor (GENEA), were empirical mode decomposition is used to extract the tremor signal. An autoregressive model and the fractal dimension of the signal are used to construct tremor features. The result of an ANOVA test provides evidence that the stress condition increases the tremor strength compared to the control. The observed changes of the spectral properties indicate that emotional stress affects intentional tremor. These findings support the usage of wearable activity sensors for the investigation of stress-related tremor changes and the evaluation of emotional context.
Download
Paper Nr: 37
Title:

Robot and Insect Navigation by Polarized Skylight
Authors:

F. J. Smith and D. W. Stewart
Abstract: A study of a large number of published experiments on the behaviour of insects navigating by skylight has led to the design of a system for navigation in lightly clouded skies, suitable for a robot or drone. The design is based on the measurement of the directions in the sky at which the polarization angle, i.e. the angle χ between the polarized E-vector and the meridian, equals ±π/4 or ±(π/4 + π/3) or ±(π/4 - π/3). For any one of these three options, at any given elevation, there are usually 4 such directions and these directions can give the azimuth of the sun accurately in a few short steps, as an insect can do. A simulation shows that this compass is accurate as well as simple and well suited for an insect or robot. A major advantage of this design is that it is close to being invariant to variable cloud cover. Also if at least two of these 12 directions are observed the solar azimuth can still be found by a robot, and possibly by an insect.
Download
Paper Nr: 40
Title:

Spatial Artifact Detection for Multi-channel EMG-based Speech Recognition
Authors:

Till Heistermann, Matthias Janke, Michael Wand and Tanja Schultz
Abstract: We introduce a spatial artifact detection method for a surface electromyography (EMG) based speech recognition system. The EMG signals are recorded using grid-shaped electrode arrays affixed to the speakers face. Continuous speech recognition is performed on the basis of these signals. As the EMG data are highdimensional, Independent Component Analysis (ICA) can be applied to separate artifact components from the content-bearing signal. The proposed artifact detection method classifies the ICA components by their spatial shape, which is analyzed using the spectra of the spatial patterns of the independent components. Components identified as artifacts can then be removed. Our artifact detection method reduces the word error rates (WER) of the recognizer significantly. We observe a slight advantage in terms of WER over the temporal signal based artifact detection method by (Wand et al., 2013a).
Download
Paper Nr: 47
Title:

Removal of Gradient Artefacts during Transient Head Movements for Continuous EEG-fMRI
Authors:

José L. Ferreira, Ronald M. Aarts and Pierre J. M. Cluitmans
Abstract: This paper presents a novel approach for removing gradient artefacts from the EEG signal recorded during continuous EEG-fMRI, which are influenced by transient head movements of the subject within the magnetic scanner. Transient head movements provoke abrupt changes in the gradient artefact waveform, in such a way that they compromise the estimation of an artefact waveform to be subtracted and achieve the EEG correction. According to our proposed methodology, a cubic spline waveform is used to model and represent the signal transitions components. This model is then used to change and approximate the shape of the EEG signal as homogeneous data, in order to improve the performance of the gradient artefact correction technique. The proposed approach also makes use of the signal slope adaption (SSD) method, combined with sum-of-sinusoids modelling for correction of the gradient artefact. Our methodology reveals to perform a robust and satisfactory removal of gradient artefacts under the occurrence of abrupt transient head movements.
Download
Paper Nr: 58
Title:

Simple Algorithms for the Determination of the Walking Distance based on the Acceleration Sensor
Authors:

Katja Orlowski and Harald Loose
Abstract: The paper presents simple algorithms for the estimation of displacement based on inertial sensors and integration of the horizontal acceleration. Experiments were conducted including nine healthy subjects. They were asked to walk three distances (20, 40 and 60m) at different speeds (normal, slow and fast). The acceleration and the angular velocity vectors ere captured by inertial sensors from SHIMMER research and Xsens technology fixed to the lower shank. Two algorithms - whole signal integration and stepwise integration - were compared with regard to their accuracy. A priori knowledge about the motion was included in the calculation. Statistically all methods work well (mean of the relative distance is 0.97 while the variance is not negligible (s = 9%). The quality of the results depends especially on the tempo of motion.
Download
Paper Nr: 64
Title:

First Heart Sound Detection Methods - A Comparison of Wavelet Transform and Fourier Analysis in Different Frequency Bands
Authors:

P. Langer, P. Jurák, J. Halámek and V. Vondra
Abstract: Methods of heart sound pre-processing are compared in this study. These methods are wavelet transform and Fourier analysis in different frequency bands. After pre-processing, the first heart sound was detected. Correlation of the first heart sound with respiration was chosen, as a sign of optimal detection. The results are demonstrated in a study of 30 volunteers. Optimal band selection for heart sound filtering is shown to be strongly individual, and is far more important than selecting Fourier analysis or wavelet transform as filtering method. Correlation with respiration proved to be a good sign for first heart sound detection evaluation.
Download
Paper Nr: 65
Title:

Runtime Calibration of Online EEG based Movement Prediction using EMG Signals
Authors:

Marc Tabie, Hendrik Woehrle and Elsa Andrea Kirchner
Abstract: Prediction of voluntary movements from electroencephalographic (EEG) signals is widely used and investigated for applications like brain-computer interfaces (BCIs) or in the field of rehabilitation. Different combinations of signal processing and machine learning methods can be found in literature for solving this task. Machine learning algorithms suffer from small signal-to-noise ratios and non-stationarity of EEG signals. Due to the non-stationarity, prediction performance of a fixed classifier may degrade over time. This is because the shape of motor-related cortical potentials associated with movement prediction change over time and thus may no longer be well represented by the classifier. A solution is online calibration of the classifier. Therefore, we propose a novel approach in which movement onsets, detected by the analysis of electromyographic (EMG) signals are used to recalibrate the classifier during runtime. We conducted experiments with 8 subjects performing self-initiated, self-paced movements of the right arm. We investigated the differences of online calibration versus applying a fixed classifier. Further the effect of varying initial training instances ( 1 3 or 2 3 of available data) was examined. In both cases we found a significant improvement in prediction performance (p < 0:05) when the online calibration was used.
Download
Paper Nr: 67
Title:

Harmonicity of the Movement as a Measure of Apraxic Behaviour in Stroke Survivors
Authors:

Marta Bieńkiewicz, Philipp Gulde, Georg Goldenberg and Joachim Hermsdörfer
Abstract: Due to the brain damage caused by stroke, apraxic patients suffer from tool use impairment, and sequencing actions during daily tasks (ADL). Patients fail to use tools in a purposeful manner, often adopting an inappropriate speed of the movement and a disrupted movement path (Laimgruber et al., 2005). The core of this symptom lies in the compromised ability to access the appropriate motor program relevant to the task goal (Hermsdörfer et al., 2006). Although many studies have explored kinematic and spatial features of apraxia both in object and non-object related motor tasks, there is a niche in the research to provide a spatiotemporal biomarker for this behaviour. We propose a novel approach based on dynamical systems framework (Bootsma et al., 2004), looking into the temporal and spatial components of movements. Preliminary data shows that this measure has a potential to encapsulate the disrupted motor behaviour in those patients. We put forward a circular-fit based model to quantify deviations from the regular movement pattern. The application of this study is to create a measure of motor behaviour to be implemented in the autonomous assistance system (CogWatch) that could facilitate performance of ADL both in the clinical and home-based setting.
Download
Paper Nr: 12
Title:

Model Adaptation via MAP for Speech Recognition in Noisy Environments
Authors:

Tatiane Melo Vital and Carlos Alberto Ynoguti
Abstract: The accuracy of speech recognition systems degrades severely when operating in noisy environments, mainly due to the mismatch between training and testing environmental conditions. The use of noise corrupted training utterances is being used with success in many works. However, as the type and intensity of the noise at operation time is unpredictable, the present work proposes a step beyond: the use of the MAP method to use samples of the actual audio signal that is being processed to adapt such systems to the real noise condition. Experimental results show an increase of almost 2% on average in the recognition rates, when compared to systems trained with noisy utterances.
Download
Paper Nr: 16
Title:

Correlation between Psychological and Physiological Responses during Fear - Relationship to Perceived Intensity of Fear
Authors:

Eun-Hye Jang, Byoung-Jun Park, Sang-Hyeob Kim, Myung-Ae Chung and Jin-Hun Sohn
Abstract: The purpose of this study is to examine the physiological responses to predict the psychological level of perceived fear. Thirty male and female college students (15 male and 15 female, mean age: 22.6±1.24) participated in the experiment. EDA (electrodermal activity), ECG (electrocardiogram), and facial EMG (electromyogram) as physiological signals were measured on the subjects’ hands and face for 60sec before presentation of emotional stimulus and for 120sec during presentation of stimulus. Experimental conditions consisted of emotional condition where fear was induced by a threatening film clip and neutral condition where no emotion was provoked by a neutral film clip. After presentation of the stimulus, subjects rated their experienced emotion on the emotion assessment scale. Analysis of psychological responses was performed to examine appropriateness (label of the subjects’ experienced emotion) and effectiveness (intensity of their experienced emotion). In the analysis of physiological responses, the selected features were skin conductance level (SCL), skin conductance response (SCR), number of skin conductance response (NSCR), R-R interval (R-R), heart rate (HR), respiration (RESP), activation in the bilateral corrugators (COR), and bilateral orbicularis oris’ (ORB). The results showed that the psychological responses to stimulus were appropriate and effective. Physiological responses showed significant increases in all features except R-R and ORB during fear condition compared to baseline condition. Also, the perceived level of fear was positively correlated with SCL, SCR, and ORB. Our result offer that the users’ perceived emotion i.e., individual differences of psychological responses must be considered to recognize human emotions by physiological signals in HCI.
Download
Paper Nr: 19
Title:

A Study on Autonomic Nervous System Responses and Feauture Selection for Emotion Recognition - Emotion Recognition using Machine Learning Algorithms
Authors:

Byoung-Jun Park, Eun-Hye Jang, Sang-Hyeob Kim, Myung-Ae Chung and Jin-Hun Sohn
Abstract: This study is related with emotion recognition based on autonomic nervous system responses. Three different emotional states, fear, surprise and stress, are evoked by stimuli and the autonomic nervous system responses for the induced emotions are measured as physiological signals such as skin temperature, electrodermal activity, electrocardiogram, and photoplethysmography. Twenty-eight features are analysed and extracted from these signals. The results of one-way ANOVA toward each parameter, there are significant differences among three emotions in some features. Therefore we select eight features from 28 features for emotion recognition. The comparative results of emotion recognition are discussed in view point of feature space with the selected features. For emotion recognition, we use four machine learning algorithms, namely, linear discriminant analysis, classification and regression tree, self-organizing map and naïve bayes, and those are evaluated by only training, 10-fold cross-validation and repeated random sub-sampling validation. This can be helpful to provide the basis for the emotion recognition technique in human computer interaction as well as contribute to the standardization in emotion-specific ANS responses.
Download
Paper Nr: 27
Title:

Automated Quantification of the Relation between Resistor-capacitor Subcircuits from an Impedance Spectrum
Authors:

Thomas Schmid, Dorothee Günzel and Martin Bogdan
Abstract: In epithelial physiology, it is common to use an equivalent electric circuit with two resistor-capacitor (RC) subcircuits in series as a model for the electrical behavior of body cells. The relation between these two subcircuits can be quantified by a quotient of their time constants t. While this quotient is a direct indicator of the shape of impedance spectra, its value cannot be determined directly. Here, we suggest a machine learning-based approach to predict the t quotient from impedance spectra. We perform systematic extraction of statistical features, algorithmic feature ranking and dimension reduction on model impedance spectra derived from tissue-equivalent electric circuits. Our results demonstrate that this quotient can be predicted reliably enough from implicit features to discriminate semicircular against non-semicircular impedance spectra.
Download
Paper Nr: 28
Title:

Changes in the Spectral Characteristics of Plethysmographic Waveforms Due to PAOD
Authors:

Irina Mizeva, Andrey Dumler and Nikita Muraviev
Abstract: Peripheral arterial occlusive disease (PAOD) of increasing severity can lead progressively to disabling claudication, ischemic rest pain and gangrene. The blood supply of a limb with peripheral arterial disease is restored by surgical operations, which treats the critical limb ischemia (CLI) only in 30% of the cases. CLI occurs when the arterial lumen decreases significantly and the nutritive requirements of the tissues, supplied by microcirculation, cannot be met. In the present paper, a simple, non-invasive and low-cost technique is proposed for early screening diagnosis of PAOD. The approach is based on the investigation of the spectral characteristics of pulse waves measured by photoplethysmography. Painless, versatility and simplicity are significant merits of the proposed methodology.
Download
Paper Nr: 30
Title:

Human Activity Recognition from Triaxial Accelerometer Data - Feature Extraction and Selection Methods for Clustering of Physical Activities
Authors:

Inês Machado, Ricardo Gomes, Hugo Gamboa and Vítor Paixão
Abstract: The demand for objectivity in clinical diagnosis has been one of the greatest challenges in Biomedical Engineering. The study, development and implementation of solutions that may serve as ground truth in physical activity recognition and in medical diagnosis of chronic motor diseases is ever more imperative. This paper 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. In this paper, unsupervised learning is applied to the feature representation of accelerometer data to discover the activities performed by different subjects. A feature selection framework is developed in order to improve the clustering accuracy and reduce computational costs. The features which best distinguish a particular set of activities are selected from a 180th- dimensional feature vector through machine learning algorithms. The implemented framework achieved very encouraging results in human activity recognition: an average person-dependent Adjusted Rand Index (ARI) of 99:29%0:5% and a person-independent ARI of 88:57%4:0% were reached.
Download
Paper Nr: 35
Title:

New Nonlinearities Interpolation Approach Applied to Surface EMG Signal
Authors:

Abdul Khaleq A. Al-naqeeb, Ayad A. Ibrahim and Qussay S. Tawfeeq
Abstract: One of the main problems that arise in many scientific engineering applications is the estimation of the missing data in a sequence of a series. A new technique is proposed in this work to handle such a problem. An implementation of a feedback for missing process in the surface of electromyography signal has been carried out by developing a robust forecasting formula on the basis of nonlinearities interpolation technique (NIT). Extracted electromyography signal from a Biceps Brachii muscle of one subject aged 35 years has been studied when muscle on tension under normal and fatigue conditions. A pair of gold-coated stainless steel bipolar electrodes have been used for the detection of the electromyography. The damaged signals are derived from the actual signals, with the amount of damage of about 80%. With a processing time of 50 msec, results show a conformity of the interpolated signals to those of the real electromyography signals, with a high degree of accuracy among the values of interpolated and of the real signals.
Download
Paper Nr: 43
Title:

Identification of Gait Events using Expert Knowledge and Continuous Wavelet Transform Analysis
Authors:

Siddhartha Khandelwal and Nicholas Wickström
Abstract: Many gait analysis applications involve long-term or continuous monitoring which require gait measurements to be taken outdoors. Wearable inertial sensors like accelerometers have become popular for such applications as they are miniature, low-powered and inexpensive but with the drawback that they are prone to noise and require robust algorithms for precise identification of gait events. However, most gait event detection algorithms have been developed by simulating physical world environments inside controlled laboratories. In this paper, we propose a novel algorithm that robustly and efficiently identifies gait events from accelerometer signals collected during both, indoor and outdoor walking of healthy subjects. The proposed method makes adept use of prior knowledge of walking gait characteristics, referred to as expert knowledge, in conjunction with continuous wavelet transform analysis to detect gait events of heel strike and toe off. It was observed that in comparison to indoor, the outdoor walking acceleration signals were of poorer quality and highly corrupted with noise. The proposed algorithm presents an automated way to effectively analyze such noisy signals in order to identify gait events.
Download
Paper Nr: 44
Title:

Advanced EEG Processing for the Detection of Drowsiness in Drivers
Authors:

Griet Goovaerts, Ad Denissen, Milica Milosevic, Geert van Boxtel and Sabine Van Huffel
Abstract: Drowsiness is a serious problem for drivers which causes many accidents every day. It is estimated that drowsiness is the cause of four deaths and 100 injuries per day in the United States. In this paper two methods have been developed to detect drowsiness based on features of ocular artifacts in EEG signals. The ocular artifacts are derived from the EEG signals by using Canonical Correlation Analysis (BSS-CCA). Wavelet transforms are used to automatically select components containing eye blinks. Sixteen features are then calculated from the eye blink and used for drowsiness detection. The first method is based on linear regression, the second on fuzzy detection. For the first method, the drowsiness level is correctly detected in 72% of the epochs. The second method uses fuzzy detection and detects the drowsiness correctly in 65% of the epochs. The best results are obtained when using one single eye blink feature.
Download
Paper Nr: 48
Title:

Reproducibility of Pulse Wave Analysis and Pulse Wave Velocity in Healthy Subjects
Authors:

T. Pereira, I. Santos, T. Pereira, H. Santos, V. Almeida, H. Pereira, C. Correia and J. Cardoso
Abstract: The hemodynamic parameters extracted from pulse pressure waveform, by pulse wave analysis (PWA) and pulse wave velocity (PWV) are strong independent predictors of cardiovascular morbidity. The aim of this study is to investigate the reproducibility of pulse pressure profile and arterial stiffness indicators, i.e., Augmentation Index (AIx), Subendocardial Viability Ratio (SEVR), maximum rate of pressure change (dP/dtmax), Ejection Time Index (ETI), as measured using a contactless optical system. Reproducibility was evaluated in 13 healthy subjects by two senior operators (‘A’ and ‘B’) that acquired signals in alternate order (ABAB or BABA). The PWV result showed a good inter and intra-operator reproducibility. The mean difference between the two operators is 0.1570 m/s with a SD of 0.8160 m/s, this difference represents approximately 3.49% of the arithmetic average of the means obtained by each operator per trial. Between trials, differences of less than 8% of the mean PWV value for each operator were obtained. PWA repeatability results are considered high for HR, strong for Aix and moderate for dP/dtmax. The newly developed optical system showed good reproducibility as evaluated by both inter-operator and intra-operator methods.
Download
Paper Nr: 49
Title:

Modeling of Neuronal Population Activation under Electroconvulsive Therapy
Authors:

Fadi N. Karameh, Mohamad Awada, Firas Mourad, Karim Zahed, Ibrahim Abou-Faycal and Ziad Nahas
Abstract: Electroconvulsive therapy (ECT) is a procedure that involves the induction of seizures in the brain of patients with severe psychiatric disorders. The efficacy and therapeutic outcome of electrically-induced seizures is dependent upon both the stimulus intensity and the electrode placement over the scalp, with potentially significant memory loss as side effect. Over the years, ECT modeling aimed to understand current propagation in the head medium with increasingly realistic geometry and conductivity descriptions. The utility of these models remain limited since seizure propagation in the active neural tissue has largely been ignored. Accordingly, a modeling framework that combines head conductivity models with active neural models to describe observed EEG signals under ECT is highly desirable. We present herein a simplified multi-area active neural model that describes (i) the transition from normal to seizure states under external stimuli with particular emphasis on disinhibition and (ii) the initiation and propagation of seizures between multiple connected brain areas. A simulation scenario is shown to qualitatively resemble clinical EEG recordings of ECT. Fitting model param- eters is then performed using modern nonlinear state estimation approaches (cubature Kalman filters). Future work will integrate active models with passive volume conduction approaches to explore seizure induction and propagation.
Download
Paper Nr: 50
Title:

The Rectus Femoris Muscle Fatigue through Mechanomyographic Time-Frequency Response in Paraplegic Subject - Preliminary Results
Authors:

Eddy Krueger, Eduardo M. Scheeren, Guilherme N. Nogueira-Neto, Agnelo Denis Vieira and Percy Nohama
Abstract: The purpose of this study is the evaluation of mechanomyographic (MMG) time-frequency response of rectus femoris muscle of a paraplegic subject during an isometric electrically-elapsed fatigue protocol. An accelerometer sensor was used to measure the vibration of muscle during voltage-controlled functional electrical stimulation application at 1 kHz pulse frequency (20% duty cycle) 70 Hz modulated frequency (20% duty cycle). A load cell (50 kgf) measured the force signal with the participant seated on a bench with the hip and knee angle set to 90º. During the protocol the electrical output voltage was adjusted to keep the force at 30% of maximal stimulated contraction (MSC). When the electrical stimulation was unable to keep the force above approximately 10% of MSC the protocol was ceased. Ten seconds with unfatigued (initial period) and fatigued (final period) muscle, MMG signal was processed with Cauchy wavelet transformation (bandpass 5-100 Hz). For fatigue conditions of paraplegic subject, MMG signal presents concentration energy to lower frequencies mainly to 11.31 Hz band frequency.
Download
Paper Nr: 52
Title:

A Different Statistical Approach Aiming at EEG Parameter Investigation for Brain Machine Interface Use
Authors:

Maria Claudia F. de Castro and Fabio Gerab
Abstract: A lot of effort has been made to investigate EEG features that could better represent signal characteristics. The results are usually based on the best mean recognition rates and statistical analysis is done only when different methods are compared. In this work, we propose a new approach that applies multiple rate intercomparisons based on large samples aiming at detecting differences among treatments in order to recognize their importance for the classification rates. Ten frequency band compositions expressed by power spectral density averages were extracted from 8 EEG channels during 4 motor imageries, and spatial feature selections were also considered during the recognition process. Classification rate in large samples can be represented by a normal distribution and, for multiple rate inter-comparisons, the level of significance was corrected based on the Bonferroni Method. The variables were considered to be independents and the test was performed as non paired samples in a very conservative approach. The results showed that there are significant differences among cases of spatial feature selection and thus the considered electrodes are important parameters. On the other hand, considering or not the Delta and Theta bands along with different arrangements for Gamma band resulted in no significant difference.
Download
Paper Nr: 54
Title:

Convex Hull Area in Triaxial Mechanomyography during Functional Electrical Stimulation
Authors:

Guilherme N. Nogueira-Neto, Eddy Krueger, Eduardo M. Scheeren, Vera L. S. N. Button and Percy Nohama
Abstract: This study employed the convex hull in the analysis of triaxial mechanomyography (MMG) to determine hull area variations along prolonged muscle contractions elicited by functional electrical stimulation (FES). Closed-loop FES systems may need real-time adjustments in control parameters. Such systems may need to process small sample sets. The convex hull area can be applied to small sample sets and it does not suffer with non-stationarities. The MMG sensor used a triaxial accelerometer and the acquired samples were projected onto all planes. The hull determined the smallest convex polygon surrounding all points and its area was computed. Four spinal cord injured volunteers participated in the experiment. The quadriceps femoral muscle was stimulated in order to cause a full knee extension. FES parameters: 1 kHz pulse frequency and a 20 Hz burst frequency. Adjustments in the stimuli amplitude were controlled by a technician to sustain the extension. The results showed that the convex hull area decreased over time. Since the polygons are related to MMG amplitude, decreasing areas were related to muscle fatigue. The convex hull area can be a candidate to follow muscle fatigue during FES-elicited contractions and analysis of short length epochs.
Download
Paper Nr: 56
Title:

Neuro-fuzzy Indirect Blood Pressure Estimation during Bruce Stress Test
Authors:

Soheil Mottaghi, Mohammad Hassan Moradi, Mahmoud Moghavvemi, Leyla Roohisefat and Eshwar C. V. Sagar
Abstract: An accurate blood pressure monitoring method during the course of an exercise stress test is paramount. This is due to the fact that the patients are under intense physical pressure, and most of the time, are usually afflicted with cardiovascular problems. Exercise or intense physical activities elevates blood pressures, which renders cuff-based measuring systems highly inaccurate, but convenient for lesser artifacts. Much research has been conducted on The Pulse Arrival Time (PAT), and it was concluded that it is inexplicably linked to blood pressure. In this study, we propose a novel approach using a neuro-fuzzy system (Fuzzy Type I) and Adaptive neuro-fuzzy inference system (ANFIS)for cuffless blood pressure estimation before, during, and after the stress test. Systolic BP and diastolic BP estimation were carried out in this study as well. There are no significant advantages in having lower error rate and/or higher correlation coefficients between the fuzzy systems. However it has been shown that the results of the non-linear fuzzy estimators possess higher correlation and lower errors than the Least Squared regression introduced in previous studies.
Download
Paper Nr: 62
Title:

Active Contour Segmentation based on Approximate Entropy - Application to Cell Membrane Segmentation in Confocal Microscopy
Authors:

Aymeric Histace, Elizabeth Bonnefoye, Luis Garrido, Bogdan J. Matuszewski and Mark Murphy
Abstract: Segmentation of cellular structures is of primary interest in cell imaging for cell shape reconstruction and to provide crucial information about possible cell morphology changes during radiotherapy for instance. From the particular perspective of predictive oncology, this paper reports on a novel method for membrane segmentation from single channel actin tagged fluorescence confocal microscopy images, which remains a challenging task. Proposed method is based on the use of the Approximate Entropy formerly introduced by Pincus embedded within a Geodesic Active Contour approach. Approximate Entropy can be seen as an estimator of the regularity of a particular sequence of values and, consequently, can be used as an edge detector. In this prospective study, a preliminary study on Approximate Entropy as an edge detector function is first proposed with a particular focus on the robustness to noise, and some promising membrane segmentation results obtained on confocal microscopy images are also shown.
Download
Paper Nr: 66
Title:

Advancements in Computer Aided Methods for EEG-based Epileptic Detection
Authors:

Malik Anas Ahmad, Waqas Majeed and Nadeem Ahmad Khan
Abstract: During the diagnosis of epilepsy, computer aided methods can significantly supplement a neurologist by automatically identifying the epileptic patterns in an EEG. In the last decade immense amount of work has been done in the field of EEG based computer aided diagnosis of epilepsy. Even after so much work these tools are not getting used up to their full potential. In this paper we have very briefly discussed some of the previously used signal processing and machine learning techniques which are proposed for epileptic pattern detection. We have concluded this paper by suggesting some additions in the previous method which can make these systems more helpful, detailed and precise for the neurologist.
Download
Paper Nr: 70
Title:

Optimal Treatment Selection for Hip Fracture Patients using a Hybrid Decision Making System
Authors:

Aleksandar Jeremic, Natasa Radosavljevic, Dejan Nikolic and Milica Lazovic
Abstract: Hip fractures are most frequent cause of hospitalization after the fall in older population and consequently have been subject of great interest in medicine and biomedical engineering. It has been observed that the incidence of hip fractures is rising at the approximate rate of 1-3% per year, with subsequent mortality rates at approximately 33% in first year after the fracture. Although in some cases the hydrotherapy may be improve recovery of patients it may not be easily accessible due to limited resources. To this purpose we propose a hybrid decision making system consisting of computer-aided decision combined with an expert opinion. We then evaluate and compare the performance of the proposed algorithms using a data sample consisting of 413 patients that have been admitted to the Institute for Rehabilitation, Belgrade, Serbia.
Download