BIOSIGNALS 2018 Abstracts

Full Papers Short Papers
Full Papers
Paper Nr: 1
Title:

Effects of Age, BMI, Anxiety and Stress on the Parameters of a Stochastic Model for Heart Rate Variability Including Respiratory Information
Authors:

Rachele Anderson, Peter Jönsson and Maria Sandsten
Abstract: Recent studies have focused on investigating different factors that may affect heart rate variability (HRV), pointing especially to the effects of age, gender and stress level. Other findings raise the importance of considering the respiratory frequency in the analysis of HRV signals. In this study, we evaluate the effect of several covariates on the parameters of a stochastic model for HRV. The data was recorded from 47 test participants, whose breathing was controlled by following a metronome with increasing frequency. This setup allows for a controlled acquisition of respiratory related HRV data covering the frequency range in which adults breathe in different everyday situations. A stochastic model, known as Locally Stationary Chirp Process, accounts for the respiratory signal information and models the HRV data. The model parameters are estimated with a novel inference method based on the separability features possessed by the process covariance function. Least square regression analysis using several available covariates is used to investigate the correlation with the stochastic model parameters. The results show statistically significant correlation of the model parameters with age, BMI, State and Trait Anxiety as well as stress level.
Download
Paper Nr: 3
Title:

Unsupervised Learning for Mental Stress Detection - Exploration of Self-organizing Maps
Authors:

Dorien Huysmans, Elena Smets, Walter De Raedt, Chris Van Hoof, Katleen Bogaerts, Ilse Van Diest and Denis Helic
Abstract: One of the major challenges in the field of ambulant stress detection lies in the model validation. Commonly, different types of questionnaires are used to record perceived stress levels. These only capture stress levels at discrete moments in time and are prone to subjective inaccuracies. Although, many studies have already reported such issues, a solution for these difficulties is still lacking. This paper explores the potential of unsupervised learning with Self-Organizing Maps (SOM) for stress detection. In unsupervised learning settings, the labels from perceived stress levels are not needed anymore. First, a controlled stress experiment was conducted during which relax and stress phases were alternated. The skin conductance (SC) and electrocardiogram (ECG) of test subjects were recorded. Then, the structure of the SOM was built based on a training set of SC and ECG features. A Gaussian Mixture Model was used to cluster regions of the SOM with similar characteristics. Finally, by comparison of features values within each cluster, two clusters could be associated to either relax phases or stress phases. A classification performance of 79.0% (5:16) was reached with a sensitivity of 75.6% (11:2). In the future, the goal is to transfer these first initial results from a controlled laboratory setting to an ambulant environment.
Download
Paper Nr: 23
Title:

Real-time Low SNR Signal Processing for Nanoparticle Analysis with Deep Neural Networks
Authors:

Jan Eric Lenssen, Anas Toma, Albert Seebold, Victoria Shpacovitch, Pascal Libuschewski, Frank Weichert, Jian-Jia Chen and Roland Hergenröder
Abstract: In this work, we improve several steps of our PLASMON ASSISTED MICROSCOPY OF NANO-SIZED OBJECTS (PAMONO) sensor data processing pipeline through application of deep neural networks. The PAMONObiosensor is a mobile nanoparticle sensor utilizing SURFACE PLASMON RESONANCE (SPR) imaging for quantification and analysis of nanoparticles in liquid or air samples. Characteristics of PAMONO sensor data are spatiotemporal blob-like structures with very low SIGNAL-TO-NOISE RATIO (SNR), which indicate particle bindings and can be automatically analyzed with image processing methods. We propose and evaluate deep neural network architectures for spatiotemporal detection, time-series analysis and classification. We compare them to traditional methods like frequency domain or polygon shape features classified by a Random Forest classifier. It is shown that the application of deep learning enables our data processing pipeline to automatically detect and quantify 80 nm polystyrene particles and pushes the limits in blob detection with very low SNRs below one. In addition, we present benchmarks and show that real-time processing is achievable on consumer level desktop GRAPHICS PROCESSING UNITs (GPUs).
Download
Paper Nr: 24
Title:

Simultaneous Measurement of a Blood Flow and a Contact Pressure

Authors:

Ryo Inoue, Hirofumi Nogami, Eiji Higurashi and Renshi Sawada
Abstract: Although a number of laser Doppler blood flow sensors have been developed over the past few decades, they remain uncommon in practice. This is because the contact pressure between the skin and the sensor is not measured simultaneously with blood flow, despite the fact that blood flow is greatly affected by contact pressure. Thus, reliable and highly reproducible measurement of blood flow could not yet be realized. In addition, changes in beam conditions or body temperature also have an effect on blood flow measurement. Therefore, we fabricated a micro electro mechanical system (MEMS) blood flow sensor which can measure contact pressure, beam power, and body temperature, for reliable and highly reproducible measurement.
Download
Paper Nr: 26
Title:

Face/Fingerphoto Spoof Detection under Noisy Conditions by using Deep Convolutional Neural Network
Authors:

Masakazu Fujio, Yosuke Kaga, Takao Murakami, Tetsushi Ohki and Kenta Takahashi
Abstract: Most of the generic camera based biometrics systems, such as face recognition systems, are vulnerable to print/photo attacks. Spoof detection, which is to discriminate between live biometric information and attacks, has received increasing attentions recently. However, almost all the previous studies have not concerned the influence of the image distortion caused by the camera defocus or hand movements during image capturing. In this research, we first investigate local texture based anti-spoofing methods including existing popular methods (but changing some of the parameters) by using publicly available spoofed face/finger photo/video databases. Secondly, we investigate the spoof detection under the camera defocus or hand movements during image capturing. To simulate image distortion caused by camera defocus or hand movements, we create blurred test images by applying image filters (Gaussian blur or motion blur filters) to the test datasets. Our experimental results demonstrate that modifications of the existing methods (LBP, LPQ, DCNN) or the parameter tuning can achieve less than 1/10 of HTER（half total error rate）compared to the existing results. Among the investigated methods, the DCNN (AlexNet) can achieve the stable accuracy under the increasing intensity of the blurring noises.
Download
Paper Nr: 29
Title:

Objective Evaluation of Bradykinesia in Parkinson’s Disease using Evolutionary Algorithms
Authors:

Siti Anizah Muhamed, Rachel Newby, Stephen L. Smith, Jane Alty, Stuart Jamieson and Peter Kempster
Abstract: Bradykinesia, a slowing of movement, is the fundamental motor feature of Parkinson’s disease (PD) and the only physical sign that is obligatory for diagnosis. The complex nature of Bradykinesia makes it difficult to reliably identify, particularly as the early stages of the disease. This paper presents an extension of previous studies, applying evolutionary algorithms to movement data obtained from the standard clinical finger tapping (FT) test to characterise Bradykinesia. In this study, hand pronation-supination (PS) and hand opening-closing (HO) tasks are also considered. Cartesian Genetic Programming (CGP), is the evolutionary algorithm used to train and validate classifiers using features extracted from movement recordings of 20 controls and 22 PD patients. Features were selected based on the current clinical definition of Bradykinesia. The results show the potential of HO and PS to be used as effective classifiers with an accuracy of 84%. Discriminative features were also investigated with the possibility of informing clinical assessment.
Download
Paper Nr: 35
Title:

Feasibility of Labor Induction Success Prediction based on Uterine Myoelectric Activity Spectral Analysis

Authors:

C. Benalcazar Parra, A. I. Tendero, Y. Ye-Lin, J. Alberola-Rubio, A. Perales Marin, J. Garcia-Casado and G. Prats-Boluda
Abstract: Labor induction using prostaglandins (PG) is a common practice to promote uterine contractions and to facilitate cervical ripening. However, not all cases of labor inductions result in vaginal deliveries and it has been associated with an increased risk of cesarean delivery. This last situation is associated to a greater healthcare economic impact and to an increment in the maternal and fetal mortality and morbidity. Obstetricians face different scenarios daily during a labor induction and it would be advantageous to be able to infer the result of the labor induction for a better labor management. Uterine electrohysterogram (EHG) has been proven to play an outstanding role in monitoring uterine dynamics and in characterizing the uterine myoelectrical activity. Therefore, the aim of this study was to characterize and to compare the response of uterine myoelectrical activity to labor induction drugs for different labor induction outcomes by obtaining and analyzing the evolution of spectral parameters from EHG records picked up during the first 4 hours after labor induction onset. Specifically, deciles from the EHG-bursts’ power spectral density (PSD) were worked out. Our results showed that deciles D8 and D9 are able to discriminate between women who achieved active phase of labor and those who did not. For women who achieved active phase of labor, D5 makes it possible to separate women who delivered vaginally and those who underwent a cesarean section; finally D2-D6 enabled us to distinguish vaginal deliveries within 24 hours after induction onset from the other outcomes. Thus, deciles computed from EHG PSD are potentially useful to discriminate the different outcomes of a labor induction, suggesting the feasibility of induction success prediction based on EHG recording.
Download
Paper Nr: 47
Title:

Protecting the ECG Signal in Cloud-based User Identification System - A Dissimilarity Representation Approach
Authors:

Diana Batista, Helena Aidos, Ana Fred, Joana Santos, Rui Cruz Ferreira and Rui César das Neves
Abstract: Biometric recognition has become a popular approach for user identification and authentication. However, since in ECG-based biometrics users cannot change their authentication/identification signal (unlike in password-based methods), its applicability is seriously constrained for cloud-based systems: a hacker could potentially retrieve the stored ECG signal, eternally disabling ECG-based biometrics for the attacked user. To overcome such an issue, new methodologies must be devised to enable cloud-based authentication/ identification systems without requiring the transmission and storage of the user’s ECG signal on remote servers. In this paper we propose an ECG biometric approach that relies on non-linear irreversible dissimilarity spaces to encode (encrypt) the user’s ECG. We show how to construct the dissimilarity space, and also evaluate the system’s accuracy with the dimensionality of the dissimilarity space. We show that the proposed biometric system retains similar identification errors as an equivalent system relying on the Euclidean space, while the latter can potentially be broken by using triangulation techniques to uncover the users original ECG signal.
Download
Short Papers
Paper Nr: 2
Title:

A Robust and Adaptive Algorithm for Real-time Muscle Activity Interval Detection using EMG Signals
Authors:

Rabya Bahadur and Saeed ur Rehman
Abstract: Detection of Muscle Activity Interval plays a pivotal role in the design and implementation of real-time Myoelectric controlled devices and their applications. This paper presents an algorithm for real-time detection of onset/offset points in the muscles activity by employing adaptive threshold technique on the Correlation Coefficient of Taeger Kaiser Energy Operator using low cost hardware. Performance of the algorithm has also been evaluated through real-time tests carried out under various constrained scenarios and different signal to noise ratios, revealing very promising results with a maximum accuracy of 99.9% using medium or no external forces.
Download
Paper Nr: 4
Title:

Wearable Sensor Node for Cardiac Ischemia Detection
Authors:

Piotr Augustyniak
Abstract: Detection of cardiac ischemia based on early repolarization ECG markers has been widely recognized since three decades. It is also employed as a safety marker in exercise testing and cardiac rehabilitation. It assumes a standardized load applied to a patient in laboratory conditions, which diminishes patients’ responsiveness and lowers the medical outcome statistics. A remedy consists in detecting ischemia markers during daily living activities in context of instantaneous physical load. Patients more willingly participate in diagnostics or rehabilitation, but the procedure requires specialized sensors and processors of ECG dedicated to use in domestic conditions. To this point we designed a small and lightweight autonomous two-lead ECG sensor node including heart rate and ST-segment processing algorithm and secure Bluetooth Low Energy connectivity to a supervising Wearable Sensor Network. In laboratory exercise tests with 50 ischemic patients the sensor issued alerts well coinciding with the output of a standard 12-lead system (with 2 fp and 1 fn cases). Moreover, in a two-lead setup the electrodes can be randomly applied to the skin in location best corresponding the ischemic region. Low power-oriented design and low transmission duty cycle result in continuous operation of the sensor for over a month with one coin battery.
Download
Paper Nr: 7
Title:

Excellent Potential of Geometric Brownian Motion (GBM) as a Random Process Model for Level of Drowsiness Signals
Authors:

Pouyan Ebrahimbabaie and Jacques G. Verly
Abstract: We show that Geometric Brownian Motion (GBM) appears to be an excellent choice of random process model to describe mathematically the real-life signals that represent the evolution with time of the level of drowsiness (LoD) of an individual, such as a driver. We collected data from thirty (30) healthy participants, who each underwent three tests (either driving in a simulator or performing Psychomotor Vigilance Tests) at successive levels of sleep deprivation. During each test, the LoD was produced by a photooculography (POG) based device designed and built by our team. We so obtained a total of 90 LoD signals. For each, we applied statistical methods to determine whether a GBM was a valid model for it. All 90 signals passed statistical tests of normality and independency, meaning that each can be modeled by GBM, thereby showing the excellent potential of GBM as a random process model for LoD signals. This finding could lead to the development of a number of innovative means for predicting the evolution of the LoD and the occurrence of related events beyond the present moment. The resulting technology should help reduce the number of accidents due to drowsy driving.
Download
Paper Nr: 10
Title:

A Sensor Which Can Be Varied in Humidity Sensitivity - A First Experience Paving the Way to New Chemical Sensors?
Authors:

Giovanni Saggio, Arnaldo D'Amico, Vito Errico, Giovanni Costantini, Giorgio Pennazza, Alessandro Zompanti and Marco Santonico
Abstract: During last decades, a number of different sensors have been developing for different analytics to detect. A key aspect of those sensors is that each of them results with a fixed particular sensitivity. Consequently, at occurrence, it is necessary to use a plurality of sensors to arrange measures with different levels of sensitivity. This work intends to investigate the possibility to obtain different sensitivity, in particular with respect to humidity, from one sensor only. To this aim we investigated the resistive flex sensor, which has been already used for other applications but, as far as we know, never investigated for its potential properties as a chemical sensor. Results demonstrated how the resistive flex sensor behaves with different sensitivity values and different sensitivity curves for different bend conditions.
Download
Paper Nr: 11
Title:

Cytoprotective Effect of Elf-Emf120hz on Early Chemical Hepatocarcinogenesis through Quantum Measurements on Enzymatic Interaction
Authors:

Juan José Godina-Nava, Eduardo López Sandoval, Arturo Rodolfo Samana, Paulo Eduardo Ambrosio and Dany Sanchez Dominguez
Abstract: Using the concept of quantum measures, we depict the mechanism in which the cytoprotective effect of ELF-EMF-120Hz on early hepatocarcinogenesis chemically induced in rats matches with the theory. We used the traditional Haberkorn approximation to evaluate the quantum yields at the rate of recombination production of singlet spin state populations, assessing with this information, the magnetic field effect. In this work, we study the system RP-Hepatocyte simply applying dynamic mapping.
Download
Paper Nr: 12
Title:

A New Approach to Gait Variability Quantification using Cyclograms
Authors:

Slavka Viteckova, Patrik Kutilek, Radim Krupicka, Zoltan Szabo, Martina Hoskovcova and Evzen Ruzicka
Abstract: Human gait is cyclic movement and its properties are not constant. Gait variability is widely assessed by fluctuation in spatio-temporal parameters. Since this method operate on a single parameter of the gait cycle, the cycle signal in its entirety does not affect the result. The objective of this work is to present new gait variability assessment method. In order to quantify the variability of entire gait cycle, we have proposed and tested the method based on synchronized cyclograms. The novel approach showed the ability to assess gait variability. The method is not restricted to gait variability assessment and would be beneficial in different areas of cyclic movement variability analysis.
Download
Paper Nr: 13
Title:

Electrolytic Wire as an Alternative Bio Interface: A Case Study in Plant Tissue
Authors:

Ernane José Xavier Costa, Luciana Vieira Piza and Ana Carolina de Sousa Silva
Abstract: One of challenge in physiological research is how to reconnect bioelectricity or turn on the transduction of signals in biological systems such as nerves and other tissues after some injuries or degenerative process. The electrical interactions in biological system can be understood by looking into the extracellular space between cells. In such spaces, contain ions and several charged organic molecules. Despite the fact that the common way to artificially link biological systems reported in the literature is by using metallic wires or bio-potentials electrodes, this paper present the hypothesis that an electrolytic conductor is more efficient to transmit information between biological systems when compared to the transmission carried out using electronic conductors. To test this hypothesis an experiment was conducted using two leaves of ornamental plant (Agave atenuata) connected by means of electronic and electrolytic wire and stimulated with electrical square waves with 1V of amplitude at 20Hz. The quality of signal transmitted using electronic conductor was compared to the signal transmitted using electrolytic conductor by measuring the distortion of the signal transmitted. The results shown that the transmission of stimuli using electrolytic wire is less disturbed than by using electronic wire.
Download
Paper Nr: 20
Title:

Knee Kinematics Feature Selection for Surgical and Nonsurgical Arthroplasty Candidate Characterization
Authors:

M. A. Ben Arous, M. Dunbar, S. Arfaoui, A. Mitiche, Y. Ouakrim, A. Fuentes, G. Richardson and N. Mezghani
Abstract: The purpose of this study is to investigate a method to select a set of knee kinematic data features to characterize surgical vs nonsurgical arthroplasty subjects. The kinematic features are generated from 3D knee kinematic data patterns, namely, rotations of flexion-extension, abduction-adduction, and tibial internal-external recorded during a walking task on a dedicated treadmill. The discrimination features are selected using three types of statistical complexity measures: the Fisher discriminant ratio, volume of overlap region, and feature efficiency. The interclass distance measurements which the features thus selected induce demonstrate their effectiveness to characterize surgical and nonsurgical subjects for arthroplasty.
Download
Paper Nr: 21
Title:

Artifact Detection of Wrist Photoplethysmograph Signals
Authors:

Kaat Vandecasteele, Jesús Lázaro, Evy Cleeren, Kasper Claes, Wim Van Paesschen, Sabine Van Huffel and Borbála Hunyadi
Abstract: There is a growing interest in monitoring of vital signs through wearable devices, such as heart rate (HR). A comfortable and non-invasive technique to measure the HR is pulse photoplethysmography (PPG) with the use of a smartwatch. This watch records also triaxial accelerometry (ACM). However, it is well known that motion and noise artifacts (MNA) are present. A MNA detection method, which classifies into a clean or MNA segment, is trained and tested on a dataset of 17 patients, each with a recording duration of 24 hours. PPG-and ACM-derived features are extracted and classified with a LS-SVM classifier. A sensitivity and specificity of respectively 85.50 % and 92.36 % are obtained. For this dataset, the ACM features do not improve the performance, suggesting that ACM recording could be avoided from the point of view for detecting MNA in PPG signals during daily life.
Download
Paper Nr: 33
Title:

Real-Time Approach to HRV Analysis
Authors:

Guilherme Ramos, Miquel Alfaras and Hugo Gamboa
Abstract: In this paper, we present the assessment of heart rate variability (HRV) applied to real-time processing of electrocardiographic (ECG) signals. A general approach for R-peak detection is described based on the computational implementation of Pan and Tompkins algorithm, used in the offline version. Besides feature extraction (from temporal and frequency domain), the paper presents the development steps taken towards online real-time biosignal processing. The functional basis of the online approach consists in the implementation of a simple adaptive double-threshold algorithm for peak detection and a sliding window mechanism along acquisition that provides a dynamically generated tachogram for the features to be successively extracted, highlighting the new application opportunities for continuous observation of HRV parameters.
Download
Paper Nr: 37
Title:

New Cluster Detection using Semi-supervised Clustering Ensemble Method
Authors:

Huaying Li and Aleksandar Jeremic
Abstract: In the recent years there has been tremendous development of data acquisition system resulting in a whole new set of so called big data problems. Since these data structures are inherently dynamic and constantly changing the number of clusters is usually unknown. Furthermore the ”true” number of clusters can depend on the constraints and/or perception (biases) set by experts, users, customers, etc., which can also change. In this paper we propose a new cluster detection algorithm based on a semi-supervised clustering ensemble method. Information fusion techniques have been widely applied in many applications including clustering, classification, detection, etc. Although clustering is unsupervised and it does not require any training data, in many applications, expert opinions are usually available to label a portion of data observations. These labels can be viewed as the guidance information to combine the cluster labels that are generated by different local clusters. It consists of two major steps: the base clustering generation and the fusion. Since the step of generating base clusterings is unsupervised and the step of combining base clusterings is supervised, in the context of this paper, we name the algorithm as the semi-supervised clustering ensemble algorithm. We then propose to detect a new cluster utilizing the average association vector computed for each data point by the semi-supervised method.
Download
Paper Nr: 41
Title:

Distributed Clustering using Semi-supervised Fusion and Feature Reduction Preprocessing
Authors:

Huaying Li and Aleksandar Jeremic
Abstract: In the recent years there has been tremendous development of data acquisition system resulting in a whole new set of so called big data problems. In addition to other techniques data analysis of these data sets involves significant amount of clustering and/or classification. Due to a heterogeneous nature of the data sets the performance of these algorithms can vary significantly in different applications. In our previous work we proposed semi-supervised information fusion system and demonstrated its performance in various applications. In this paper we proposed to improve the performance of the proposed system by applying data preprocessing algorithms using feature reduction as well as various base clustering techniques. We demonstrate the applicability of the proposed techniques using real data sets.
Download
Paper Nr: 44
Title:

Validated Assessment of Gait Sub-Phase Durations in Older Adults using an Accelerometer-based Ambulatory System
Authors:

Mohamed Boutaayamou, Sophie Gillain, Cédric Schwartz, Vincent Denoël, Jean Petermans, Jean-Louis Croisier, Bénédicte Forthomme, Jacques G. Verly, Olivier Brüls and Gaëtan Garraux
Abstract: Validated extraction of gait sub-phase durations using an ambulatory accelerometer-based system is a current unmet need to quantify subtle changes during the walking of older adults. In this paper, we describe (1) a signal processing algorithm to automatically extract not only durations of stride, stance, swing, and double support phases, but also durations of sub-phases that refine the stance and swing phases from foot-worn accelerometer signals in comfortable walking of older adults, and (2) the validation of this extraction using reference data provided by a gold standard system. The results show that we achieve a high agreement between our method and the reference method in the extraction of (1) the temporal gait events involved in the estimation of the phase/sub-phase durations, namely heel strike (HS), toe strike (TS), toe-off (TO), maximum of heel clearance (MHC), and maximum of toe clearance (MTC), with an accuracy and precision that range from ‒3.6 ms to 4.0 ms, and 6.5 ms to 12.0 ms, respectively, and (2) the gait phase/sub-phase durations, namely stride, stance, swing, double support phases, and HS to TS, TO to MHC, MHC to MTC, and MTC to HS sub-phases, with an accuracy and precision that range from ‒4 ms to 5 ms, and 9 ms to 15 ms, respectively, in comfortable walking of a thirty-eight older adults ( (mean ± standard deviation) 71.0 ± 4.1 years old). This demonstrates that the developed accelerometer-based algorithm can extract validated temporal gait events and phase/sub-phase durations, in comfortable walking of older adults, with a promising degree of accuracy/precision compared to reference data, warranting further studies.
Download
Paper Nr: 45
Title:

Segmentation of Cell Membrane and Nucleus using Branches with Different Roles in Deep Neural Network
Authors:

Tomokazu Murata, Kazuhiro Hotta, Ayako Imanishi, Michiyuki Matsuda and Kenta Terai
Abstract: We propose a segmentation method of cell membrane and nucleus by integrating branches with different roles in a deep neural network. When we use the U-net for segmentation of cell membrane and nucleus, the accuracy is not sufficient. It may be difficult to classify multi-classes by only one network. Thus, we designed a deep network with multiple branches that have different roles. We give each branch a role which segments only cell membrane or nucleus or background, and probability map is generated at each branch. Finally, the generated probability maps by three branches are fed into the convolution layer to improve the accuracy. The final convolutional layer calculates the posterior probability by integrating the probability maps of three branches. Experimental results show that our method improved the segmentation accuracy in comparison with the U-net.
Download
Paper Nr: 48
Title:

ASK: A Framework for Data Acquisition and Activity Recognition
Authors:

Hui Liu and Tanja Schultz
Abstract: This work puts forward a framework for the acquisition and processing of biosignals to indicate strain on the knee inflicted by human everyday activities. Such a framework involves the appropriate equipment in devices and sensors to capture factors that inflict strain on the knee, the long-term recording and archiving of corresponding multi-sensory biosignal data, the semi-automatic annotation and segmentation of these data, and the person-dependent or person-adaptive automatic recognition of strain. In this paper we present first steps toward our goal, i.e. person-dependent recognition of a small set of human everyday activities. The focus here is on the fully automatic end-to-end processing from signal input to recognition output. The framework was applied to collect and process a small pilot dataset from one person for a proof-of-concept validation and achieved 97% accuracy in recognizing instances of seven daily activities.
Download
Paper Nr: 50
Title:

Biomarkers of Neurodegenerative Progression from Spontaneous Speech Recorded in Mobile Devices: An Approach based on Articulation Speed Estimation - A Study of Patients Suffering from Amyotrophic Lateral Sclerosis
Authors:

Ana Londral, Pedro Gómez Vilda and Andrés Gómez-Rodellar
Abstract: A majority of patients with Amyotrophic Lateral Sclerosis (ALS) experiment a rapid evolution of symptoms related to a progressive decline in movement function that affects different systems. Clinical assessment is based on measures of progression for identifying the need and the pace of medical decisions, and to measure also the effects of novel therapies. But assessment is limited to the periodicity of clinical appointments that are increasingly difficult for patients due to progressive mobility impairments. In this paper, we present a novel method to assess neurodegeneration process through speech analysis. An articulation kinematic model is proposed to identify markers of neuromotor functional progression in speech. We analysed speech samples that were collected with a mobile device, in 3-month intervals, from a group of six subjects with ALS. Results suggest that the method proposed is sensitive to the symptoms of the disease, as rated by observational clinical scales, and it may contribute to assist clinicians and researchers with better and continuous measures of disease progression.
Download
Paper Nr: 14
Title:

An Investigation of How Wavelet Transform Can Affect the Correlation Performance of Biomedical Signals - The Correlation of EEG and HRV Frequency Bands in the Frontal Lobe of the Brain
Authors:

Ronakben Bhavsar, Neil Davey, Yi Sun and Na Helian
Abstract: Recently, the correlation between biomedical signals, such as electroencephalograms (EEG) and electrocardiograms (ECG) time series signals, has been analysed using the Pearson Correlation method. Although Wavelet Transformations (WT) have been performed on time series data including EEG and ECG signals, so far the correlation between WT signals has not been analysed. This research shows the correlation between the EEG and HRV, with and without WT signals. Our results suggest electrical activity in the frontal lobe of the brain is best correlated with the HRV. We assume this is because the frontal lobe is related to higher mental functions of the cerebral cortex and responsible for muscle movements of the body. Our results indicate a positive correlation between Delta, Alpha and Beta frequencies of EEG at both low frequency (LF) and high frequency (HF) of HRV. This finding is independent of both participants and brain hemisphere.
Download
Paper Nr: 15
Title:

An Investigation of Signal Characteristics and T1 Relaxation Time in Brain MR Images of Young versus Old Healthy Adults
Authors:

Hayriye Aktaş Dinçer and Didem Gökçay
Abstract: During healthy aging, the brain undergoes several structural changes such as atrophy and volumetric changes. Although less evident, changes in tissue concentration also occur. Such differences in brain tissues introduce prominent low contrast effects to the MRI images of the aging population, causing segmentation problems in the data processing pipeline. Measures of tissue characteristics such as T1 provide unique and complementary information to widely used measures of brain signal characteristics. In this study, multiple Fast Low Angle Shot (FLASH) images are collected for T1 mapping of whole brains from young and old adults. Tissue signal characteristics are evaluated on predefined regions and compared across Magnetization Prepared Rapid Gradient Echo (MPRAGE) and T1 maps. Additionally, segmentation performance is analyzed. As a result, we found that T1 maps are superior to MPRAGE protocol in terms of contrast, especially within sub-cortical areas. Furthermore, degradation of grey-white-ratio (GWR) due to aging processes is observed to be less pronounced in T1 estimated whole brain images. Moreover, sensitivity of T1 maps (54.6%) are higher than MPRAGE images (34.4%) in detection of sub-cortical gray matter. In sum we concur that T1 maps provide better avenues to investigate age related morphological changes in the brain.
Download
Paper Nr: 17
Title:

Assessment of Gait Harmony in Older and Young People
Authors:

Manuel Gnucci, Marco Flemma, Marco Tiberti, Mariachiara Ricci, Antonio Pallotti and Giovanni Saggio
Abstract: Recent studies have found that in normal human walking the stance and swing phases are approximately in proportion to , the golden ratio. This could provide an interesting tool in human gait analysis, in diagnosing pathological conditions or in analysing the walking performance of a subject. However, the assessment of gait harmony was provided in previous studies by means of optical systems, which are not ideal for clinicians, because of non-portability, high-costs, and necessity of expert supervisor skills. In addition, the assessment regarded mostly middle-aged or aged people. Differently, this work is based on wearable technology to sense human walking, and reports a comparison between elder and young people. Results demonstrate how elders adopt a walking style which better minimizes the energy expenditure.
Download
Paper Nr: 18
Title:

Adaptive Filtering for Electromyographic Signal Processing in Scoliosis Indexes Estimation
Authors:

Eleonora Sulas, Luigi Raffo, Marco Monticone and Danilo Pani
Abstract: Adolescent idiopathic scoliosis is defined as a three-dimensional deformity of the spine and trunk occurring in about 2.5% of most populations. It is usually analyzed radiographically, but electromyography (EMG) can be also used, since muscles activity is correlated to deformity progression. EMG ratio is a numerical index used in the literature to provide information about scoliosis progression. Trunk EMG recordings are strongly affected by the electrocardiogram (ECG) of the subject. Previous studies removed this interference from the EMG signal by blanking the QRS complexes of the ECG but, as a consequence, several segments of the signal are removed. Furthermore, the other relevant ECG waves such as P and T are not cancelled and can invalidate the computation of parameters such as the EMG ratio. The aim of this study is to evaluate the possibility, by means of a modified recording protocol including further electrodes, to completely remove the ECG interference by adopting a multi-reference recursive least square (RLS) adaptive filter. The results of the study reveal how the complete clearing of the ECG from the EMG channels leads to different numerical values of the index, compared to the QRS blanking, more reliable and meaningful for the clinicians.
Download
Paper Nr: 19
Title:

Acoustic Analysis of Chronic Laryngitis - Statistical Analysis of Sustained Speech Parameters
Authors:

João Paulo Teixeira, Joana Fernandes, Filipe Teixeira and Paula Odete Fernandes
Abstract: This paper describes the statistical analysis of a set of features extracted from the speech of sustained vowels of patients with chronic laryngitis and control subjects. The idea is to identify which features can be useful in a classification intelligent system to discriminate between pathologic and healthy voices. The set of features analysed consist in the Jitter, Shimmer Harmonic to Noise Ratio (HNR), Noise to Harmonic Ratio (NHR) and Autocorrelation extracted from the sound of a sustained vowels /a/, /i/ and /u/ in a low, neutral and high tones. The results showed that besides the absolute Jitter, no statistical significance exist between male and female voices, considering the classification between pathologic or healthy. Any of the analysed parameters is likely to be a statistical difference between control and Chronic Laryngitis groups. This is an important information that these features can be used in an intelligent system to classify healthy from Chronic Laryngitis voices.
Download
Paper Nr: 30
Title:

Parametrization of Physical Activity Aggregation
Authors:

Monika Šimaityte, Andrius Petrėnas and Vaidotas Marozas
Abstract: This work introduces a novel approach to parametrization of physical activity profile. The proposed parameter, named as physical activity aggregation, is useful for evaluating a distribution of daily or weekly physical activity. The parameter takes a large value for a highly accumulated physical activity, whereas is much lower for an evenly spread activity over the monitoring period. The parameter was investigated on step data obtained using a smart wristband on a group of 71 participants with cardiovascular disease. The results of the pilot study show that the proposed parameter is capable of discriminating among different physical activity profiles, including sedentary behaviour, going to and from work, walking in a park and being active the entire day. Moreover, the results demonstrate the tendency that middle-aged and older women are associated with lower aggregation values, suggesting that they probably spend less time in sedentary behaviour compared to men of the same age. The proposed parameter has potential to be useful for characterizing physical activity profile, as well as, for investigating its relation to health outcomes, e.g., during ambulatory rehabilitation after major cardiovascular events.
Download
Paper Nr: 31
Title:

Investigation of a Multichannel Surface Electromyogram Analysis Method Considering Superimposed Waveforms in a Elbow Flexion Movement
Authors:

Jun Akazawa and Ryuhei Okuno
Abstract: The purpose of this study was to develop a method of decomposing the surface motor unit acton potential (SMUAP) of a biceps brachii short head muscle when the distance from the surface electrodes to the motor units (MUs) changes during voluntary isovelocity elbow flexion. In the preparatory study, a subject’s elbow flexion movement had changed the shape of the SMUAP, which was probably made by a single MU larger than the previous study. Thus, we had to develop a SMUAP decomposition method that focused on tracking the SMUAP waveform changes and superimposed signals. The developed SMUAP decomposition algorithm was based on a sequentially modified template matching method, considering the superimposed signals. This was applied to the measured SMUAPs. The MU firing rates calculated with our algorithm were almost the same as those of previous physiological studies; our algorithm was capable of decomposing SMUAPs when the waveform of the SMUAP was generated from a single MU and responded with each change in firing time.
Download
Paper Nr: 32
Title:

Wavelet Correlation of Neural Activity Bursts Generating Spikes
Authors:

S. V. Bozhokin, I. B. Suslova and D. A. Tarakanov
Abstract: We study neural activity synchronization on the basis of instantaneous wavelet correlation function and simple mathematical model of brain bursts carrying several spikes. The approach allows us to obtain analytical solution for two neurons generating a given number of spikes and estimate the coupled behavior of neurons at different time moments. Neural activity is simulated as a superposition of elementary nonstationary Gaussian signals with some given parameters. Time-frequency properties of neural signals are studied by continuous wavelet transform with adaptive Morlet mother wavelet function.
Download
Paper Nr: 34
Title:

Segmentation of Cell Membrane and Nucleus by Improving Pix2pix
Authors:

Masaya Sato, Kazuhiro Hotta, Ayako Imanishi, Michiyuki Matsuda and Kenta Terai
Abstract: We propose a semantic segmentation method of cell membrane and nucleus by improving pix2pix. We use pix2pix which is an improved method of DCGAN. Pix2pix generates good segmentation result by the competition of generator and discriminator but pix2pix uses generator and discriminator independently. If generator knows the criterion for classifying real and fake images, we can improve the accuracy of generator furthermore. Thus, we propose to use the feature maps of the discriminator into generator. In experiments on segmentation of cell membrane and nucleus, our proposed method outperformed the conventional pix2pix.
Download
Paper Nr: 38
Title:

Quantitative Measurement of Bradykinesia in Parkinson's Disease using Commercially Available Leap Motion
Authors:

Yusuf Özgür Çakmak, S. Can Ölçek, Burak Özsoy and Didem Gökçay
Abstract: Parkinson’s Disease (PD) is a neurodegenerative disease caused by the depletion of dopamine in the brain. Tremor, bradykinesia, rigidity and postural stability are the four major symptoms. Like other symptoms, bradykinesia causing unnatural stillness/slowness in motions affects the daily life of the patients. The levels of these symptoms are clinically assessed by a scoring system based on Unified Parkinson’s Disease Rating Scale (UPDRS). However, UPDRS relies on the visual observations of physicians rather than a test based on quantitative measurements. This makes it not only difficulty to repeat but also subjective. Because of these two major disadvantages, researchers build custom devices for their studies. But this leads to the reliability issues and non-standard measurements. Thus, 24 PD patients were bilaterally UPDRS III (motor subsection) scored and recorded for finger motion (pinching) by using commercially available off-the-shelf (COTS) product called Leap Motion. The various features extracted from recordings and UPDRS III scores were analyzed for correlation. After the analysis, a linear model was created to estimate UPDRS III score. The study revealed that Leap Motion, a COTS device, can be used to estimate bradykinesia of a patient with PD.
Download
Paper Nr: 43
Title:

Detection of Abnormal Heart Conditions from the Analysis of ECG Signals
Authors:

Mohamed Hammad, Asmaa Maher, Khan Adil, Feng Jiang and Kuanquan Wang
Abstract: Actual classification of Electrocardiogram (ECG) signals is vital and necessary for detection of abnormal heart conditions from the analysis of ECG signals. In this paper, we have proposed a classifier that simulates the diagnosis of the cardiologist to classify ECG signals data into two classes: normal and abnormal classes from single lead ECG signals and better than other well-known classifiers. The proposed classifier solved most of well-known classifiers problems also, overcomes the misdiagnosis problems that face many cardiologists. The proposed algorithm is validated using 48 records from the MIT-BIH arrhythmia database, where 25 records for normal class and 23 records for abnormal class. Two Neural Network (NN) classifiers: Feed Forward Network (FFN) and Multi-layered Perceptron (MLP), four Support Vector Machine (SVM) classifiers: Linear-SVM, Gaussian Radial Base function (RBF), Polynomial-SVM and Quadratic-SVM and K-Nearest Neighbour (KNN) classifier are employed to classify the ECG signals and compared with the proposed classifier. The total 13 features extracted from each ECG signal used in the proposed algorithm and set as input to the other classifiers. Experimental results show that the proposed classifier demonstrates better performance than other classifiers in terms of accuracy and computing time.