Tomáš Peterek

Comparison of Classification Algorithms for Physical Activity Recognition

The main aim of this work is to compare different algorithms for human physical activity recognition from accelerometric and gyroscopic data which are recorded by a smartphone. Three classification algorithms were compared: the Linear Discriminant Analysis, the Random Forest, and the K-Nearest Neighbours. For better classification performance, two feature extraction methods were tested: the Correlation Subset Evaluation Method and the Principal Component Analysis. The results of experiment were expressed by confusion matrixes.

Human activity recognition on raw sensor data via sparse approximation

Human physical activity monitoring is a relatively new problem drawing much attention over the last years due to its wide application in medicine, homecare systems, prisoner monitoring etc. This paper presents Orthogonal Matching Pursuit based classifier as a method for activity recognition and proposes a modification to the classifier that significantly increases recognition accuracy. Both methods show promising results in both total recognition and differentiation between certain activities achieving up to 99.60% recognition accuracy even without any prior data processing. A comparison with other methods is also provided.

Pattern Recognition in EEG Cognitive Signals Accelerated by GPU

Analysing of Electroencephalography (EEG) cognitive signals becomes more popular today due to availability of essential hardware (EEG headsets) and sufficient computation power of common computers. Fast and precise pattern matching of acquired signals represents one of the most important challenges. In this article, a method for signal pattern matching based on Non-negative Matrix Factorization is proposed. We also utilize short-time Fourier transform to preprocess EEG data and Cosine Similarity Measure to perform query-based classification. The recognition algorithm shows promising results in execution speed and is suitable for implementation on graphics processors to achieve real-time processing, making the proposed method suitable for real-world, real-time applications. In terms of recognition accuracy, our experiments show that accuracy greatly depends on the choice of input parameters.

Principal component analysis and fuzzy clustering of SA HRV during the Orthostatic challenge

The Orthostatic challenge (OSCH) is the most useful test for the determination of a humans autonomic dysregulation. It is used in many branches of medicine, for example in Neurology, Cardiology and Diabetology. The main aim of this paper is to describe the changes of the autonomic nervous system (ANS) during the orthostatic challenge. These changes are subsequently quantified and classified to clusters. The distinction of the ANS behavior could bring better understanding of this difficult system.

A new method for identification of the significant point in the Plethysmografical record

Photopletysmography (PPG) is a non-invasive, and easy to diagnostic method. It is used in many branches of medicine such as industrial medicine, intensive care, angiology or rheumatology. This examination makes it possible to assess the peripheral blood circulation in the vessel bed. It can be helpful in qualitative evaluation of the blood system.[3] Unfortunately, there is not a universal method to assess uniform valuation of the PPG due to the strong variability of the signal and therefore we try to propose an algorithm for systematical diagnostics of plethysmographical record. New algorithm designed for identification of the significant points in the PPG record is described in the paper. The algorithm is based on the continuous wavelet transform (CWT).

Human Fetus Health Classification on Cardiotocographic Data Using Random Forests

Pregnancy and fetus development is an extremely complex biological process that, while generally successful and without complications, can go wrong. One of the methods to determine if the fetus is developing according to expectations is cardiotocography. This diagnostic technique’s purpose is to measure the heartbeat of the fetus and uterine contractions of its mother, usually during the third trimester of pregnancy when the fetus’ heart is fully functional. Outputs of a cardiotocogram are usually interpreted as belonging to one of three states: physiological, suspicious and pathological. Automatic classification of these states based on cardiotocographic data is the goal of this paper. In this research, the Random Forest method is show to perform very well, capable of classifying the data with 94.69% accuracy. A comparison with the Classification and Regression Tree and Self-organizing Map methods is also provided.

Performance evaluation of Random Forest regression model in tracking Parkinson's disease progress

In this paper, capabilities of the Random Forest algorithm are tested with application to the Parkinsons disease progression that can be determined from speech. Results are compared with the linear regression model and the Classification and Regression Tree method. Mean Squared Error and Mean Absolute Error values were calculated and compared for each of the approaches. The Random Forest algorithm belongs to the group model category and usually improves the results achieved by regression trees, making it more suitable for fighting the disease.

Reconstruction of ECG Precordial Leads by PCA and Neural Networks

The paper describes possibilities of simplifying the measurement set-up for ECG recordings, by reducing the number of leads. The study proposes a technique to reduce the number of measurements or to reconstruct ECG leads by neural networks. The results are encouraging and show how it is possible to reconstruct ECG leads. The goal of this work is in the possibilities of reconstruction ECG precordial leads and the algorithm of reconstruction.

Baseline wander elimination by Fourier series

During ECG recording it comes to loss of information due to external interferences such as movement artifacts of a patient, the public power supply system distortion or interference of other electrophysiological signals. Main disadvantages of these artifacts are modifications of the original ECG. These artifacts may cause difficult ECG diagnostic reading. One of these artifacts is a baseline wander. This paper describes the new algorithm for elimination of baseline wander. [1][2]

Recognition of pathological beats in ECG signals based on Singular Value Decomposition of wavelet coefficients and support vector machine

The main goal of this work is to describe possibilities of the Singular Value Decomposition in the task of arrhythmia recognition. Many approaches try to recognize pathological beats in the time domain, our approach transforms an ECG signal from time to frequency domain, where it is reduced by Singular Value Decomposition. The new feature subspace was classified by three basic algorithms: Support Vector Machine, Linear Discriminant Analysis and Classification tree. The results were compared. Our approach increases the quality of classification and the obtained results are comparable with the results available in literature. The main aim of the proposed solution is to differentiate between physiological and pathological beats such as Premature Ventricular Contraction, Right Bundle Branch Block and Left Bundle Branch Block beats.