Comparative study of morphological ECG features classificators: An application on athletes undergone to acute physical stress

Abstract

Several methods for automatic heartbeat classification have been developed, but few efforts have been devoted to the recognition of the small ECG changes occurring in healthy people as a response to stimuli. Herein, we describe a procedure for the extraction, selection and classification of features summarizing morphological ECG changes. The proposed procedure is composed by the following stages: 1) extraction of a set of heartbeat morphological features; 2) selection of a subset of features; 3) subject normalization 4) classification. The selection of a subset of features enabled us to summarize ECG changes with only three non redundant features. In addition we performed a comparison between four classificators: k-nearest-neighbors (k-NN), artificial neural networks (ANN), support vector machines (SVM) and naive Bayes classifiers (nB). In order to cope with the possible non linear separation problem, we evaluated two strategies: a subject factor normalization on feature space and the usage of kernel functions for classifiers. The results of the comparison recommended the usage of subject normalization, irrespectively from the classificator: with or without normalization we had the best performance of classification for the linear-SVM and AN

A Classification method for eye movements direction during REM sleep trained on wake electro-oculographic recordings

“…The first one is the K-nearest neighbor algorithm (KNN): the classification of each new object is based on the classes of the k objects closest to it in the feature-space. As a case study, we adopt k = 5 and the Euclidean distance as metric [6].…”

The Athlete’s Heart and Machine Learning: A Review of Current Implementations and Gaps for Future Research

“…Each study was then assigned to one of these four groups using the criteria outlined in Table 2. "Predictive Modelling" made up most of the studies with 10 (36%) [14,16,21,22,26,27,31,32,34,40] being assigned to this group. "Reviews" was the next single largest group with eight (29%) studies [15,17,18,23,29,30,35,38].…”

“…The first and most popular type of approach implemented was to use ML to learn from the data and make predictions on what class each patient/participant should be classified as automatically. Eight of the studies [14,16,21,22,26,27,34,40] use this approach, applying ML algorithms in varying levels of complexity, from linear discriminant analysis (LDA) to ANN. A more in-depth discussion of the individual methods which were used and their respective applications can be found in the section "Machine learning approaches used".…”

“…A common theme throughout the studies is that in the majority of cases, the key features pre-extracted from the modality are analysed instead of the raw data itself. The features can either be extracted manually by a healthcare professional, such as the physical measurements [21,22,26], or by using a technique to generate statistical features instead [14,40]. The only study that bucks this trend was by Castillo-Atoche et al [37], where they developed their model on ECGs in an image format instead.…”

A novel BCI-SSVEP based approach for control of walking in Virtual Environment using a Convolutional Neural Network

“…Neural networks are used in many field of research such as on-line torque prediction and control of robot joints using surface electromyography [19], compute kinematic and control of a prosthesis [20], automatic heartbeat classification [21], medical diagnosis [22], modelling injection system [23], breast cancer classification problem [24] and much more.…”