Feature extraction and selection algorithms in biomedical data classifiers based on time-frequency and principle component analysis.

Kostka, P.; Tkacz, Ewaryst

doi:10.1007/978-3-540-73044-6_19

Cited by 2 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…is implemented in the ffsaroc engine included in Biomedtk (see Section 3) whereas is used in the ffsa engine. Note that when using RMS there is a direct relation between the individual error measures of the elements of the training set ( ) and the global error ( ) which is given by equation (1) and this is why it can be used by backpropagation-like training algorithms, whereas there is no such direct relation in since , is a global measure of a classified set. It is the fact that simulated annealing does not use individual error measures for each element of the training set that allows us to replace by in a straight forward manner.…”

Section: Roc Az Error With Simulated Annealingmentioning

confidence: 99%

“…To achieve high recognition accuracy, the feature extractor is required to discover salient characteristics suited for classification and the classifier is required to set class boundaries accurately in the feature space. Progress made in sensor technology and data management allows researchers to gather datasets of ever increasing sizes [1].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Introducing ROC Curves as Error Measure Functions: A New Approach to Train ANN-Based Biomedical Data Classifiers

Ramos-Pollán

Guevara-López

Oliveira

2010

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

View full text Add to dashboard Cite

This paper explores the usage of the area (Az) under the Receiver Operating Characteristic (ROC) curve as error measure to guide the training process to build machine learning ANN-based classifiers for biomedical data analysis. Error measures (like root mean square error, RMS) are used to guide training algorithms measuring how far solutions are from the ideal classification, whereas it is well known that optimal classification rates do not necessarily yield to optimal Az's. Our hypothesis is that Az error measures can guide existing training algorithms to obtain better Az's than other error measures. This was tested after training 280 different configurations of ANN-based classifiers, with simulated annealing, using five biomedical binary datasets from the UCI machine learning repository with different test/train data splits. Each ANN configuration was trained both using the Az and RMS based error measures. In average Az was improved in 7.98% in testing data (9.32% for training data) when using 70% of the datasets elements for training. Further analysis reveals interesting patterns (Az improvement is greater when Az are lower). These results encourage us to further explore the usage of Az based error measures in training methods for classifiers in a more generalized manner.

show abstract

Section: Roc Az Error With Simulated Annealingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Introducing ROC Curves as Error Measure Functions: A New Approach to Train ANN-Based Biomedical Data Classifiers

Ramos-Pollán

Guevara-López

Oliveira

2010

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

View full text Add to dashboard Cite

show abstract

“…In order to help in this task, some previous works have addressed the problem of automatic ECG abnormalities detection in different ways. Early approaches were mainly based on time-frequency analysis and features (Alexakis et al 2003, Chazal et al 2004, Christov et al 2006, Mahmoud et al 2006, Kostka and Tkacz 2007, or wavelet and Fourier signal transforms (Martínez et al 2004, Mahmoodabadi et al 2005, Minami et al 1999, Yang and Shen 2013, Aqil et al 2015. Next, fuzzy logic and machine learning techniques were tested in order to detect heart diseases (Vafaie et al 2014, Chen et al 2018.…”

Section: Introductionmentioning

confidence: 99%

From 12 to 1 ECG lead: multiple cardiac condition detection mixing a hybrid machine learning approach with a one-versus-rest classification strategy

et al. 2022

View full text Add to dashboard Cite

Objective. Detecting different cardiac diseases using a single or reduced number of leads is still challenging. This work aims to provide and validate an automated method able to classify ECG recordings. Performance using complete 12-lead systems, reduced lead sets, and single-lead ECGs is evaluated and compared. Approach. Seven different databases with 12-lead ECGs were provided during the PhysioNet/Computing in Cardiology Challenge 2021, where 88 253 annotated samples associated with none, one, or several cardiac conditions among 26 different classes were released for training, whereas 42 896 hidden samples were used for testing. After signal preprocessing, 81 features per ECG-lead were extracted, mainly based on heart rate variability, QRST patterns and spectral domain. Next, a One-versus-Rest classification approach made of independent binary classifiers for each cardiac condition was trained. This strategy allowed each ECG to be classified as belonging to none, one or several classes. For each class, a classification model among two binary supervised classifiers and one hybrid unsupervised-supervised classification system was selected. Finally, we performed a 3-fold cross-validation to assess the system’s performance. Main results. Our classifiers received scores of 0.39, 0.38, 0.39, 0.38, and 0.37 for the 12, 6, 4, 3 and 2-lead versions of the hidden test set with the Challenge evaluation metric ( C M ). Also, we obtained a mean G -score of 0.80, 0.78, 0.79, 0.79, 0.77 and 0.74 for the 12, 6, 4, 3, 2 and 1-lead subsets with the public training set during our 3-fold cross-validation. Significance. We proposed and tested a machine learning approach focused on flexibility for identifying multiple cardiac conditions using one or more ECG leads. Our minimal-lead approach may be beneficial for novel portable or wearable ECG devices used as screening tools, as it can also detect multiple and concurrent cardiac conditions.

show abstract

Feature extraction and selection algorithms in biomedical data classifiers based on time-frequency and principle component analysis.

Cited by 2 publications

References 4 publications

Introducing ROC Curves as Error Measure Functions: A New Approach to Train ANN-Based Biomedical Data Classifiers

Introducing ROC Curves as Error Measure Functions: A New Approach to Train ANN-Based Biomedical Data Classifiers

From 12 to 1 ECG lead: multiple cardiac condition detection mixing a hybrid machine learning approach with a one-versus-rest classification strategy

Contact Info

Product

Resources

About