Lenka Lhotska

Robot Path Planning using Particle Swarm Optimization of Ferguson Splines

Robot path planning problem is one of most important task mobile robots. This paper proposes an original approach using a path description by string of cubic splines. Such path is easy executable and natural for car-like robot. Furthermore, it is possible to ensure smooth derivation in connections of particular splines. In this case, the path planning is equivalent to optimization of parameters of splines. An evolutionary technique called particle swarm optimization (PSO) was used hereunder due to its relatively fast convergence and global search character. Various settings of PSO parameters were tested and the best setting was compared to two classical mobile robot path planning algorithms.

Open access intrapartum CTG database

BackgroundCardiotocography (CTG) is a monitoring of fetal heart rate and uterine contractions. Since 1960 it is routinely used by obstetricians to assess fetal well-being. Many attempts to introduce methods of automatic signal processing and evaluation have appeared during the last 20 years, however still no significant progress similar to that in the domain of adult heart rate variability, where open access databases are available (e.g. MIT-BIH), is visible. Based on a thorough review of the relevant publications, presented in this paper, the shortcomings of the current state are obvious. A lack of common ground for clinicians and technicians in the field hinders clinically usable progress. Our open access database of digital intrapartum cardiotocographic recordings aims to change that.DescriptionThe intrapartum CTG database consists in total of 552 intrapartum recordings, which were acquired between April 2010 and August 2012 at the obstetrics ward of the University Hospital in Brno, Czech Republic. All recordings were stored in electronic form in the OB TraceVue®;system. The recordings were selected from 9164 intrapartum recordings with clinical as well as technical considerations in mind. All recordings are at most 90 minutes long and start a maximum of 90 minutes before delivery. The time relation of CTG to delivery is known as well as the length of the second stage of labor which does not exceed 30 minutes. The majority of recordings (all but 46 cesarean sections) is – on purpose – from vaginal deliveries. All recordings have available biochemical markers as well as some more general clinical features. Full description of the database and reasoning behind selection of the parameters is presented in the paper.ConclusionA new open-access CTG database is introduced which should give the research community common ground for comparison of results on reasonably large database. We anticipate that after reading the paper, the reader will understand the context of the field from clinical and technical perspectives which will enable him/her to use the database and also understand its limitations.

Using nonlinear features for fetal heart rate classification

Highlights • We analyzed fetal heart rate of normal and acidemic fetuses. • We used conventional and nonlinear features for the signal analysis. • Addition of nonlinear features improves accuracy of classification. • The best nonlinear features are: Lempel Ziv complexity and Sample entropy. • Combination of conventional and nonlinear features provides the best accuracy. Abstract Fetal heart rate (FHR) is used to evaluate fetal well-being and enables clinicians to detect ongoing hypoxia during delivery. Routine clinical evaluation of intrapartum FHR is based on macroscopic morphological features visible to the naked eye. In this paper we evaluated conventional features and compared them to the nonlinear ones in the task of intrapartum FHR classification. The experiments were performed using a database of 217 FHR records with objective annotations, i.e. pH measurement. We have proven that the addition of nonlinear features improves accuracy of classification. The best classification results were achieved using a combination of conventional and nonlinear features with sensitivity of 73.4%, specificity of 76.3%, and F -measure of 71.9%. The best selected nonlinear features were: Lempel Ziv complexity, Sample entropy, and fractal dimension estimated by Higuchi method. Since the results of automatic signal evaluation are easily reproducible, the process of FHR evaluation can become more objective and may enable clinicians to focus on additional non-cardiotocography parameters influencing the fetus during delivery.

Automatic evaluation of intrapartum fetal heart rate recordings: a comprehensive analysis of useful features

Cardiotocography is the monitoring of fetal heart rate (FHR) and uterine contractions (TOCO), used routinely since the 1960s by obstetricians to detect fetal hypoxia. The evaluation of the FHR in clinical settings is based on an evaluation of macroscopic morphological features and so far has managed to avoid adopting any achievements from the HRV research field. In this work, most of the features utilized for FHR characterization, including FIGO, HRV, nonlinear, wavelet, and time and frequency domain features, are investigated and assessed based on their statistical significance in the task of distinguishing the FHR into three FIGO classes. We assess the features on a large data set (552 records) and unlike in other published papers we use three-class expert evaluation of the records instead of the pH values. We conclude the paper by presenting the best uncorrelated features and their individual rank of importance according to the meta-analysis of three different ranking methods. The number of accelerations and decelerations, interval index, as well as Lempel-Ziv complexity and Higuchis fractal dimension are among the top five features.

A new approach to automated assessment of fractionation of endocardial electrograms during atrial fibrillation

Complex fractionated atrial electrograms (CFAEs) may represent the electrophysiological substrate for atrial fibrillation (AF). Progress in signal processing algorithms to identify sites of CFAEs is crucial for the development of AF ablation strategies. A novel algorithm for automated description of fractionation of atrial electrograms (A-EGMs) based on the wavelet transform has been proposed. The algorithm was developed and validated using a representative set of 1.5 s A-EGM (n = 113) ranked by three experts into four categories: 1-organized atrial activity; 2-mild; 3-intermediate; 4-high degree of fractionation. A tight relationship between a fractionation index and expert classification of A-EGMs (Spearman correlation rho = 0.87) was documented with a sensitivity of 82% and specificity of 90% for the identification of highly fractionated A-EGMs. This operator-independent description of A-EGM complexity may be easily incorporated into mapping systems to facilitate CFAE identification and to guide AF substrate ablation.

Automatic Detection of Sleep Stages in Neonatal EEG Using the Structural Time Profiles

The new method for automatic sleep stages detection in neonatal EEG was developed. The procedure is based on processing of time profiles computed by adaptive segmentation and subsequent classification of signal graphoelements. The time profiles, functions of the class membership in the course of time, reflect the dynamic EEG structure and may be used for indication of changes in the neonatal sleep stages

Examining cross-database global training to evaluate five different methods for ventricular beat classification.

The detection of ventricular beats in the holter recording is a task of great importance since it can direct clinicians toward the parts of the electrocardiogram record that might be crucial for determining the final diagnosis. Although there already exists a fair amount of research work dealing with ventricular beat detection in holter recordings, the vast majority uses a local training approach, which is highly disputable from the point of view of any practical-real-life-application. In this paper, we compare five well-known methods: a classical decision tree approach and its variant with fuzzy rules, a self-organizing map clustering method with template matching for classification, a back-propagation neural network and a support vector machine classifier, all examined using the same global cross-database approach for training and testing. For this task two databases were used-the MIT-BIH database and the AHA database. Both databases are required for testing any newly developed algorithms for holter beat classification that is going to be deployed in the EU market. According to cross-database global training, when the classifier is trained with the beats from the records of one database then the records from the other database are used for testing. The results of all the methods are compared and evaluated using the measures of sensitivity and specificity. The support vector machine classifier is the best classifier from the five we tested, achieving an average sensitivity of 87.20% and an average specificity of 91.57%, which outperforms nearly all the published algorithms when applied in the context of a similar global training approach.

Classification of Long-Term EEG Recordings

Computer assisted processing of long-term EEG recordings is gaining a growing importance. To simplify the work of a physician, that must visually evaluate long recordings, we present a method for automatic processing of EEG based on learning classifier. This method supports the automatic search of long-term EEG recording and detection of graphoelements – signal parts with characteristic shape and defined diagnostic value. Traditional methods of detection show great percent of error caused by the great variety of non-stationary EEG. The idea of this method is to break down the signal into stationary sections called segments using adaptive segmentation and create a set of normalized discriminative features representing segments. The groups of similar patterns of graphoelements form classes used for the learning of a classifier. Weighted features are used for classification performed by modified learning classifier fuzzy k – Nearest Neighbours. Results of classification describe classes of unknown segments. The implementation of this method was experimentally verified on a real EEG with the diagnosis of epilepsy.

Wrapper feature selection for small sample size data driven by complete error estimates

This paper focuses on wrapper-based feature selection for a 1-nearest neighbor classifier. We consider in particular the case of a small sample size with a few hundred instances, which is common in biomedical applications. We propose a technique for calculating the complete bootstrap for a 1-nearest-neighbor classifier (i.e., averaging over all desired test/train partitions of the data). The complete bootstrap and the complete cross-validation error estimate with lower variance are applied as novel selection criteria and are compared with the standard bootstrap and cross-validation in combination with three optimization techniques - sequential forward selection (SFS), binary particle swarm optimization (BPSO) and simplified social impact theory based optimization (SSITO). The experimental comparison based on ten datasets draws the following conclusions: for all three search methods examined here, the complete criteria are a significantly better choice than standard 2-fold cross-validation, 10-fold cross-validation and bootstrap with 50 trials irrespective of the selected output number of iterations. All the complete criterion-based 1NN wrappers with SFS search performed better than the widely-used FILTER and SIMBA methods. We also demonstrate the benefits and properties of our approaches on an important and novel real-world application of automatic detection of the subthalamic nucleus.

Hybridized Swarm Metaheuristics for Evolutionary Random Forest Generation

In many industry and research areas, data mining is a crucial process. This paper presents an evolving structure of classifiers (random forest) where the trees are generated by hybrid method combining ant colony metaheuristics and evolutionary computing technique. The method benefits from the stochastic process and population approach, which allows the algorithm to evolve more efficiently than each method alone. As the method is similar to random forest generation, it can be also used for feature selection. The paper also discusses the parameter estimation for the method. Tests on real data (UCI and real biomedical data) have been performed and evaluated. The average accuracy of the method over MIT-BIH database with normalized data and equalized classes is sensitivity 93.22 % and specificity 87.13 %.