Search

Rapid progress in the development of technological and computational tools has motivated substantial changes in the educational approach to the different disciplines of signal, image, and video processing. Moreover, the parallel evolution of sensor systems, data acquisition methods, and computational intelligence has emphasized the importance of signal processing and information engineering, particularly its role in integrating different scientific disciplines through the use of a common set of tools and underlying mathematics. Modern educational courses follow these trends and generally combine the teaching of fundamental computational methods of signal and system modeling with applications to selected case studies. The unifying idea is to apply similar mathematical methods for data processing in completely diverse areas. Emerging methods used in education contribute to this progress, and they provide opportunities to bring together specialists from different disciplines. New technologies facilitate real or virtual activities through excursions to remote laboratories, allowing the demonstration of robotic and speech recognition systems, for example. Participation in seminars, videoconferences, and discussions during colloquia meetings, when included in educational courses, can form further progressive and attractive teaching methods for the rapidly developing interdisciplinary area of signal processing.

Motion pattern analysis uses methods for the recognition of physical activities recorded by wearable sensors, video-cameras, and global navigation satellite systems. This paper presents the motion analysis during cycling, using data from a heart rate monitor, accelerometric signals recorded by a navigation system, and the sensors of a mobile phone. The set of real cycling experiments was recorded in a hilly area with each route about 12 km long. The associated signals were analyzed with appropriate computational tools to find the relationships between geographical and physiological data including the heart rate recovery delay studied as an indicator of physical and nervous condition. The proposed algorithms utilized methods of signal analysis and extraction of body motion features, which were used to study the correspondence of heart rate, route profile, cycling speed, and cycling cadence, both in the time and frequency domains. Data processing included the use of Kohonen networks and supervised two-layer softmax computational models for the classification of motion patterns. The results obtained point to a mean time of 22.7 s for a 50 % decrease of the heart rate after a heavy load detected by a cadence sensor. Further results point to a close correspondence between the signals recorded by the body worn accelerometers and the speed evaluated from the GNSSs data. The accuracy of the classification of downhill and uphill cycling based upon accelerometric data achieved 93.9 % and 95.0 % for the training and testing sets, respectively. The proposed methodology suggests that wearable sensors and artificial intelligence methods form efficient tools for motion monitoring in the assessment of the physiological condition during different sports activities including cycling, running, or skiing. The use of wearable sensors and the proposed methodology finds a wide range of applications in rehabilitation and the diagnostics of neurological disorders as well. Author, Research through the Development of Advanced Computational Algorithms for Evaluating Post-Surgery Rehabilitation [LTAIN19007]; National Sustainability Programme of the Ministry of Education, Youth and Sports of the Czech Republic [LO1303 (MSMT-7778/2014)]; Ethics commission, Neurocentre Caregroup, Center for Neurological Care in Rychnov nad Kneznou, Czech Republic, Ministerstvo Školství, Mládeže a Tělovýchovy, MŠMT: LO1303, MSMT-7778/2014

Analysis of brain activities in language perception for individuals with different musical backgrounds can be based upon the study of multichannel electroencephalograhy (EEG) signals acquired in different external conditions. The present paper is devoted to the study of the relationship of mental processes and the perception of external stimuli related to the previous musical education. The experimental set under study included 38 individuals who were observed during perception of music and during listening to foreign languages in four stages, each of which was 5 min long. The proposed methodology is based on the application of digital signal processing methods, signal filtering, statistical methods for signal segment selection and active electrode detection. Neural networks and support vector machine (SVM) models are then used to classify the selected groups of linguists to groups with and without a previous musical education. Our results include mean classification accuracies of 82.9% and 82.4% (with the mean cross-validation errors of 0.21 and 0.22, respectively) for perception of language or music and features based upon EEG power in the beta and gamma EEG frequency bands using neural network and SVM classification models.

The paper is devoted to computer simulations of the distribution and time evolution of the temperature in a wooden house in summer. The goal of simulations was to assess the effect of covering walls inside the house with a PCM (phase change material) on its passive cooling, which prevents the undesired overheating of the house and provides the required thermal comfort for the occupants under warm summer days. Computer simulations were performed by the COMSOL Multiphysics software (COMSOL Inc., Stockholm, Sweden). A model of a house without the PCM coverage was compared with models of houses in which the PCM was located on all walls, except a floor, and on a wall opposite the window. Results of simulations proved that the wood wall thickness and PCMs location influence overheating the wooden house. Under studied conditions, the coverage of a wall opposite the window best eliminated extremes of the air temperature inside the house. The maximum temperature decrease was 3.9 degrees C (i.e., drop of 31.1%) comparing the house which wall opposite the window was covered by the PCM and the house without the PCM coverage., European Regional Development Fund under the project CEBIA-Tech Instrumentation [CZ.1.05/2.1.00/19.0376]; Ministry of Education, Youth and Sports of the Czech Republic within the National Sustainability Programme [LO1303 (MSMT-7778/2014)]

Multimodal signal analysis based on sophisticated noninvasive sensors, efficient communication systems, and machine learning, have a rapidly increasing range of different applications. The present paper is devoted to pattern recognition and the analysis of physiological data acquired by heart rate and thermal camera sensors during rehabilitation. A total number of 56 experimental data sets, each 40 min long, of the heart rate and breathing temperature recorded on an exercise bike have been processed to determine the fitness level and possible medical disorders. The proposed general methodology combines machine learning methods for the detection of the changing temperature ranges of the thermal camera and adaptive image processing methods to evaluate the frequency of breathing. To determine the individual temperature values, a neural network model with the sigmoidal and the probabilistic transfer function in the first and the second layers are applied. Appropriate statistical methods are then used to find the correspondence between the exercise activity and selected physiological functions. The evaluated mean delay of 21 s of the heart rate drop related to the change of the activity level corresponds to results obtained in real cycling conditions. Further results include the average value of the change of the breathing temperature (167 s) and breathing frequency (49 s).

The paper is devoted to the analysis of multichannel biomedical signals acquired in the sleep laboratory. The data analyzed represent polysomnographic records of (i) 33 healthy individuals, (ii) 25 individuals with sleep apnea, and (iii) 18 individuals with sleep apnea and restless leg syndrome. The initial statistical analysis of the sleep segments points to an increase in the number of Wake stages and the decrease in REM stages with increase in age. The goal of the study is visualization of features associated with sleep stages as specified by an experienced neurologist and in their adaptive classification. The results of the support vector machine classifier are compared with those obtained by the k-nearest neighbors method, decision tree and neural network classification using sigmoidal and Bayesian transfer functions. The achieved accuracy for the classification into two classes (to separate the Wake stage from one of NonREM and REM stages) is between 85.6 and 97.5% for the given set of patients with sleep apnea. The proposed models allow adaptive modification of the model coefficients during the learning process to increase the diagnostic efficiency of sleep disorder analysis, in both the clinical and home environments.

Background and Objective. Needle electromyography can be used to detect the number of changes and morphological changes in motor unit potentials of patients with axonal neuropathy. General mathematical methods of pattern recognition and signal analysis were applied to recognize neuropathic changes. This study validates the possibility of extending and refining turns-amplitude analysis using permutation entropy and signal energy. Methods. In this study, we examined needle electromyography in 40 neuropathic individuals and 40 controls. The number of turns, amplitude between turns, signal energy, and “permutation entropy” were used as features for support vector machine classification. Results. The obtained results proved the superior classification performance of the combinations of all of the above-mentioned features compared to the combinations of fewer features. The lowest accuracy from the tested combinations of features had peak-ratio analysis. Conclusion. Using the combination of permutation entropy with signal energy, number of turns and mean amplitude in SVM classification can be used to refine the diagnosis of polyneuropathies examined by needle electromyography.

Analysis of motion symmetry constitutes an important area with many applications in engineering, robotics, neurology and biomedicine. This paper presents the use ofmicroelectromechanical sensors (MEMS), including accelerometers and gyrometers, to acquire data via mobile devices so as to monitor physical activities and their irregularities. Special attention is devoted to the analysis of the symmetry of the motion of the body when the same exercises are performed by the right and the left limb. The analyzed data include the motion of the legs on a home exercise bike under different levels of load. The method is based on signal analysis using the discrete wavelet transform and the evaluation of signal segment features such as the relative energy at selected decomposition levels. The subsequent classification of the evaluated features is performed by k-nearest neighbours, a Bayesian approach, a support vector machine, and neural networks. The highest average classification accuracy attained is 91.0% and the lowest mean cross-validation error is 0.091, resulting from the use of a neural network. This paper presents the advantages of the use of simple sensors, their combination and intelligent data processing for the numerical evaluation of motion features in the rehabilitation and monitoring of physical activities. © 2019 by the authors., Ministry of Health of the Czech Republic [FN HK 00179906]; Charles University in Prague, Czech Republic [PROGRES Q40]; project PERSONMED - European Regional Development Fund (ERDF) [CZ.02.1.010.00.017_0480007441]; governmental budget of the Czech Republic

This paper addresses the use of multichannel signal processing methods in analysis of heart rate changes during cycling using the global positioning system (GPS) to record the route conditions. The main objectives of this work are in monitoring of physiological activities, cycling features extraction, their classification and visualization. Real data were acquired from 41 cycling rides of the same 11.48-km long route divided into 2460 segments of approximately 60 s. The data were recorded with a varying sampling period within the range of 1–22 s depending on the route profile. The pre-processing stage included preparatory analysis, filtering and resampling of the data to a constant sampling rate. The proposed algorithm includes the evaluation of the cross-correlation between the heart rate and the altitude gradient as recorded by a GPS satellite system. A Bayesian approach was then applied to classify the cycling segment features into two classes (specifying cycling up and down) with the classification accuracy better than 93 %. A comparison with other classification methods is presented in the paper as well. The results include the following relationships: (1) the heart rate and altitude gradient, which shared a positive correlation coefficient of 0.62; (2) the heart rate and speed, which shared a negative correlation coefficient of −0.72 over all of the analysed segments; and (3) the mean heart rate change delay (6.8–11.5 s) in relation to the changes in the altitude gradients associated with cycling up and down. The paper forms a contribution to the use of computational intelligence and visualization for data processing both in cycling and fitness physical activities as well.

This paper presents the contactless measuring of breathing using the MS Kinect depth sensor and compares the results obtained with records of breathing taken by polysomnography (PSG). We explore the methods of signal denoising, resampling, and spectral analysis of acquired data as well as feature extraction and their Bayesian classification. The proposed methodology was applied for analysis of the long-term monitoring of individuals who were observed simultaneously by PSG and MS Kinect in the sleep laboratory. After time synchronization of polysomnographic and MS Kinect video data, features were extracted from both signals and compared. The average error of the frequency while being evaluated by MS Kinect that was related to that obtained by PSG was 3.75 %. The mean accuracy of the Bayesian classification of features into two classes (i.e. wake or sleep) was 88.90 and 88.95 % for the PSG and MS Kinect measurements, respectively. The strong likeness of features supports the hypothesis that contactless techniques may represent a valid alternative to the present approach of sleep monitoring, thereby allowing data acquisition in the home environment as well.

The brain is a complex organ responsible for memory storage and reasoning; however, the mechanisms underlying these processes remain unknown. This paper forms a contribution to a lot of theoretical studies devoted to regular or chaotic oscillations of interconnected neurons assuming that the smallest information unit in the brain is not a neuron but, instead, a coupling of inhibitory and excitatory neurons forming a simple oscillator. Several coefficients of variation for peak intervals and correlation coefficients for peak interval histograms are evaluated and the sensitivity of such oscillator units is tested to changes in initial membrane potentials, interconnection signal delays, and changes in synaptic weights based on known histologically verified neuron couplings. Results present only a low dependence of oscillation patterns to changes in initial membrane potentials or interconnection signal delays in comparison to a strong sensitivity to changes in synaptic weights showing the stability and robustness of encoded oscillating patterns to signal outages or remoteness of interconnected neurons. Presented simulations prove that the selected neuronal couplings are able to produce a variety of different behavioural patterns, with periodicity ranging from milliseconds to thousands of milliseconds between the spikes. Many detected different intrinsic frequencies then support the idea of possibly large informational capacity of such memory units.

This paper is devoted to modelling of temperature distribution and its time evolution in rooms with specific thermal insulation and heat transfer for different external conditions. The simulation results should help to design the room architecture and wall materials to reduce energy losses due to heating or cooling, and to increase the inside thermal comfort. For this purpose, a methodological procedure using real data processing in the COMSOL Multiphysics modelling environment and spatial visualization of temperature evolution is proposed. This paper describes a mathematical model for simulation of the temperature evolution inside a space with thermally insulated walls under selected outside conditions. Computer simulations are then used to assess the temperature distribution inside the room and the heat flow through the room walls. Results of the simulations are used for subsequent determination of the time needed for the desired decrease of air temperature inside the tested room during its cooling due to the low ambient temperature, which is related to the thermal stability of the building, specific heat capacity, and thickness of the thermal insulation. Under the studied conditions, the time to reach the temperature drops by 20 percent in a room with windows was from 1.4 to 1.8 times lower than that in the room without windows. The proposed methodology shows the flexibility of computer modelling in the design of insulated building systems. The mesh density testing was performed by comparing the air temperature evolution in the model of the selected mesh density and the model with its maximum value enabled by the size of computer memory. The maximum temperature deviation calculated for the mesh of the presented model was 0.57%. © 2018 by the authors., European Regional Development Fund under the project CEBIA-Tech Instrumentation [CZ.1.05/2.1.00/19.0376]; Ministry of Education, Youth and Sports of the Czech Republic within the National Sustainability Programme [LO1303 (MSMT-7778/2014)]

This paper presents a novel method of Bayesian gait recognition using Microsoft (MS) Kinect image and depth sensors and skeleton tracking in three-dimensional space. Although video sequences acquired by a complex camera system enable a very precise data analysis, it is possible to use much simpler technical devices to analyze video frames with sufficient accuracy for many applications. The use of the MS Kinect allows a simple 3-D modeling using its image and depth sensors for data acquisition, resulting in a matrix of 640 × 480 elements used for spatial modeling of a moving body. The experimental part of the paper is devoted to the study of three data sets: (i) 18 individuals with Parkinson's disease, (ii) 18 healthy age-matched controls, and (iii) 15 trained young individuals forming the second reference set. The proposed algorithm involves methods for the estimation of the average stride length and gait speed of individuals in these sets. Digital signal processing methods and Bayesian probability classification algorithms are then used for gait feature analysis to recognize individuals suspected of having Parkinson's disease. The results include the estimation of the characteristics of selected gait features for patients with Parkinson's disease and for individuals from the reference sets, presentation of decision boundaries, and comparison of classification efficiency for different features. The achieved accuracy of the probabilistic classification was 94.1%.

This paper presents new methods of orthodontic body segmentation using digital records of their plaster cast models under different types of illumination. Selected light conditions are used for the data acquisition to provide more clearly defined contours of the image components. The preliminary stage of the data processing uses the circular Hough transform, digital de-noising, and a separation of the orthodontic objects from their backgrounds employing Otsu’s thresholding method. The region-growing method using multiple seed points in a convex hull is then applied. The proposed general method identifies the common boundary of two neighboring and overlapping orthodontic objects with results enabling the efficient segmentation of digital data and their analysis through the computer network.

This paper proposes a new multiplicative noise removal method using a sparse analysis model. Apart from a data fidelity term, two regularizers are employed in the proposed approach: a regularizer using a learned analysis dictionary and a smoothness regularizer defined on pixel-wise differences.To address the resulting optimization problem, we adapt the alternating direction method of multipliers (ADMM) framework, and present a new optimization method.Experimental results demonstrate the improved performance of the proposed method as compared with several recent baseline methods, especially for relatively high noise levels. The multiplicative noise removal problem for a corrupted image has recently been considered under the framework of regularization based approaches, where the regularizations are typically defined on sparse dictionaries and/or total variation (TV). This framework was demonstrated to be effective. However, the sparse regularizers used so far are based overwhelmingly on the synthesis model, and the TV based regularizer may induce the stair-casing effect in the reconstructed image. In this paper, we propose a new method using a sparse analysis model. Our formulation contains a data fidelity term derived from the distribution of the noise and two regularizers. One regularizer employs a learned analysis dictionary, and the other regularizer is an enhanced TV by introducing a parameter to control the smoothness constraint defined on pixel-wise differences. To address the resulting optimization problem, we adapt the alternating direction method of multipliers (ADMM) framework, and present a new method where a relaxation technique is developed to update the variables flexibly with either image patches or the whole image, as required by the learned dictionary and the enhanced TV regularizers, respectively. Experimental results demonstrate the improved performance of the proposed method as compared with several recent baseline methods, especially for relatively high noise levels.

Multimodal signal analysis based on sophisticated sensors, efficient communication systems and fast parallel processing methods has a rapidly increasing range of multidisciplinary applications. The present paper is devoted to pattern recognition, machine learning, and the analysis of sleep stages in the detection of sleep disorders using polysomnography (PSG) data, including electroencephalography (EEG), breathing (Flow), and electro-oculogram (EOG) signals. The proposed method is based on the classification of selected features by a neural network system with sigmoidal and softmax transfer functions using Bayesian methods for the evaluation of the probabilities of the separate classes. The application is devoted to the analysis of the sleep stages of 184 individuals with different diagnoses, using EEG and further PSG signals. Data analysis points to an average increase of the length of the Wake stage by 2.7% per 10 years and a decrease of the length of the Rapid Eye Movement (REM) stages by 0.8% per 10 years. The mean classification accuracy for given sets of records and single EEG and multimodal features is 88.7% ( standard deviation, STD: 2.1) and 89.6% (STD:1.9), respectively. The proposed methods enable the use of adaptive learning processes for the detection and classification of health disorders based on prior specialist experience and man–machine interaction.

The paper deals with fusion of physiological and GPS data acquired during cycling and their analysis using general methods of multichannel signal processing. Experimental data were acquired during 17 identical cycling routes each about 12 km long including more then 1100 segments of the length 60 s recorded with the varying sampling period. The proposed algorithm includes their initial analysis, de-nosing using selected digital filters, interpolation and resampling in the first stage followed by evaluation of the cross-correlation between the heart rate and the altitude gradient of positioning data recorded by the GPS system. Results obtained present (i) relation between the heart rate and the slope with the positive regression coefficient 6.04 and (ii) the heart rate and speed with the negative regression coefficient −1.67 over all segments analyzed.

The paper presents in its initial part historical notes to the development of digital signal and image processing methods. The following case studies are devoted to their application in biomedicine and they include the use of computational intelligence in EEG and EMG signal processing, image segmentation and registration in orthodontia, the human-machine interaction and the three-dimensional modelling using MS Kinect in diagnostics and treatment of human motion disorders and neurological diseases. Associated comments include remarks and references to the development of modern computational tools, biosensors, wireless communication and data fusion used in assistive technologies and robotic systems. Mathematical tools common to all these applications form the next part of the paper that includes notes to spectral analysis, functional transforms, digital filtering, image enhancement, classification of multi-dimensional signal components and optimization using neural networks. Final remarks emphasize the interdisciplinary significance of the digital signal processing forming the integrating basis of many diverse research areas.

Computational intelligence and signal analysis of multi-channel data form an interdisciplinary research area based upon general digital signal processing methods and adaptive algorithms. The chapter is restricted to their use in biomedicine and particularly in electroencephalogram signal processing to find specific components of such multi-channel signals. Methods presented include signal de-noising, evaluation of their fundamental components and segmentation based upon feature detection in time-frequency and time-scale domains using both the discrete Fourier transform and the discrete wavelet transform. Resulting pattern vectors are then classified by self-organizing neural networks using a specific statistical criterion proposed to evaluate distances of individual feature vector values from corresponding cluster centers. Results achieved are compared for different data sets and selected mathematical methods to detect segments features. Proposed methods verified in the MATLAB environment using distributed data processing are accompanied by the appropriate graphical user interface that enables convenient and user friendly time-series processing.

Signal analysis of multi-channel data form a specific area of general digital signal processing methods. The paper is devoted to application of these methods for electroencephalogram (EEG) signal processing including signal de-noising, evaluation of its principal components and segmentation based upon feature detection both by the discrete wavelet transform (DWT) and discrete Fourier transform (DFT). The self-organizing neural networks are then used for pattern vectors classification using a specific statistical criterion proposed to evaluate distances of individual feature vector values from corresponding cluster centers. Results achieved are compared for different data sets and selected mathematical methods to detect and to classify signal segments features. Proposed methods are accompanied by the appropriate graphical user interface (GUI) designed in the MATLAB environment.

The paper is devoted to a novel method for detecting the back-loop regulation of coupling and decoupling between cortical neurones from electroencephalogram (EEG) signals. In this method, a linear time-scale quantifier of the multivariate relationship between simultaneously observed time series takes advantage of unique properties of complex wavelets such as shift invariance, substantially reduced aliasing and non-oscillating magnitude. The quantifier provides correlation between amplitude of complex wavelet coefficients for different frequencies (controlled by the scale factor) at different times (controlled by the time shift). Biological interpretation of this measure is derived from a priori information about presence of inhibitory back-loop connections between cortical neurones in short distance while the long range excitatory connections do not appear to target or effectively excite inhibitory interneurons and analysis of sample pairs of EEG signals.

Segmentation, feature extraction and classification of signal components belong to very common problems in various engineering, economical and biomedical applications. The paper is devoted to the use of discrete wavelet transform (DWT) both for signal preprocessing and signal segments feature extraction as an alternative to the commonly used discrete Fourier transform (DFT). Feature vectors belonging to separate signal segments are then classified by a competitive neural network as one of methods of cluster analysis and processing. The paper provides a comparison of classification results using different methods of feature extraction most appropriate for EEG signal components detection. Problems of multichannel segmentation are mentioned in this connection as well.

Wavelet functions form an essential tool of modern signal analysis and modelling in various engineering, biomedical and environmental systems. The paper is devoted to selected aspects of construction of wavelet functions and their properties enabling their use for time-scale signal analysis and noise rejection. The main part of the paper presents the basic principles of signal decomposition in connection with fundamental signal components detection and approximation. The methods are verified for simulated signals at first and then used for real signal analysis representing air pollution inside a given region of North Bohemia covered by several measuring stations. The following part of the chapter is devoted to comparison of linear and non-linear signal modelling and prediction for original and de-noised signals. The paper emphasizes the algorithmic approach to methods of signal analysis and prediction and it presents the use of wavelet functions both for signal analysis and modelling.