Machine Learning and Deep Learning for Medical Analysis—A Case Study on Heart Disease Data

Swetha, A.M.; Santhi, B.; Brindha, G.

doi:10.1002/9781119821908.ch8

Cited by 3 publications

(1 citation statement)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The algorithm connects the scalar response with one (or more) inputs by linear dependence, which means that the response can be estimated using a linear combination of the input. Techniques such as simple linear regression, ordinary least squares, gradient descent, regularisation are used for model training [23,25]. Another algorithm is logical regression, which is used in classification problems because its output is a discrete value.…”

Section: Introductionmentioning

confidence: 99%

Applying the Machine Learning Method to Improve Calibration Quality of TDR Measuring Technique

Mikušová,

Suchorab,

Paśnikowska-Łukaszuk

et al. 2024

Adv. Sci. Technol. Res. J.

View full text Add to dashboard Cite

The article presents the application of the time domain reflectometry (TDR) technique for measuring the moisture of porous building materials used in construction. The work is focused on using the potential of artificial intelligence to improve the quality of TDR measurements through a new approach to the interpretation of data obtained from the TDR readings. Machine learning is a data analysis technique, used nowadays in many scientific disciplines. The authors performed a measurement data analysis using the artificial intelligence algorithms to assess moisture of aerated concrete samples tested with a TDR multimeter using two non-invasive sensors which differ in thickness. Data analysis was carried out using supervised machine learning to analyse a series of reflectograms obtained during the measurement. For the data achieved by the classical and machine learning method interpretation, correlation analysis was conducted to confirm the potential of artificial intelligence to improve the quality of TDR measurement. The summary of the work discusses the obtained analytical results and highlights the effectiveness of moisture assessment using the Gaussian process regression method, which allowed achieving a level of 0.2-0.3% of the RMSE errors value, which is about 10 times lower than the traditional approach.

show abstract

Section: Introductionmentioning

confidence: 99%

Applying the Machine Learning Method to Improve Calibration Quality of TDR Measuring Technique

Mikušová,

Suchorab,

Paśnikowska-Łukaszuk

et al. 2024

Adv. Sci. Technol. Res. J.

View full text Add to dashboard Cite

show abstract

A comparative analysis of meta-heuristic optimization algorithms for feature selection on ML-based classification of heart-related diseases

Ekinci

Garip

2023

J Supercomput

View full text Add to dashboard Cite

Multilevel hybrid accurate handcrafted model for myocardial infarction classification using ECG signals

Barua

Aydemir

Doğan

et al. 2022

Int. J. Mach. Learn. & Cyber.

View full text Add to dashboard Cite

Myocardial infarction (MI) is detected using electrocardiography (ECG) signals. Machine learning (ML) models have been used for automated MI detection on ECG signals. Deep learning models generally yield high classification performance but are computationally intensive. We have developed a novel multilevel hybrid feature extraction-based classification model with low time complexity for MI classification. The study dataset comprising 12-lead ECGs belonging to one healthy and 10 MI classes were downloaded from a public ECG signal databank. The model architecture comprised multilevel hybrid feature extraction, iterative feature selection, classification, and iterative majority voting (IMV). In the hybrid handcrafted feature (HHF) generation phase, both textural and statistical feature extraction functions were used to extract features from ECG beats but only at a low level. A new pooling-based multilevel decomposition model was presented to enable them to create features at a high level. This model used average and maximum pooling to create decomposed signals. Using these pooling functions, an unbalanced tree was obtained. Therefore, this model was named multilevel unbalanced pooling tree transformation (MUPTT). On the feature extraction side, two extractors (functions) were used to generate both statistical and textural features. To generate statistical features, 20 commonly used moments were used. A new, improved symmetric binary pattern function was proposed to generate textural features. Both feature extractors were applied to the original MI signal and the decomposed signals generated by the MUPTT. The most valuable features from among the extracted feature vectors were selected using iterative neighborhood component analysis (INCA). In the classification phase, a one-dimensional nearest neighbor classifier with ten-fold cross-validation was used to obtain lead-wise results. The computed lead-wise results derived from all 12 leads of the same beat were input to the IMV algorithm to generate ten voted results. The most representative was chosen using a greedy technique to calculate the overall classification performance of the model. The HHF-MUPTT-based ECG beat classification model attained excellent performance, with the best lead-wise accuracy of 99.85% observed in Lead III and 99.94% classification accuracy using the IMV algorithm. The results confirmed the high MI classification ability of the presented computationally lightweight HHF-MUPTT-based model.

show abstract

Machine Learning and Deep Learning for Medical Analysis—A Case Study on Heart Disease Data

Cited by 3 publications

References 21 publications

Applying the Machine Learning Method to Improve Calibration Quality of TDR Measuring Technique

Applying the Machine Learning Method to Improve Calibration Quality of TDR Measuring Technique

A comparative analysis of meta-heuristic optimization algorithms for feature selection on ML-based classification of heart-related diseases

Multilevel hybrid accurate handcrafted model for myocardial infarction classification using ECG signals

Contact Info

Product

Resources

About