Hybrid Deep Learning and Discrete Wavelet Transform-Based ECG Biometric Recognition for Arrhythmic Patients and Healthy Controls.

The intrinsic and liveness detection behavior of electrocardiogram (ECG) signals has made it an emerging biometric modality for the researcher with several applications including forensic, surveillance and security. The main challenge is the low recognition performance with datasets of large populations, including healthy and heart-disease patients, with a short interval of an ECG signal. This research proposes a novel method with the feature-level fusion of the discrete wavelet transform and a one-dimensional convolutional recurrent neural network (1D-CRNN). ECG signals were preprocessed by removing high-frequency powerline interference, followed by a low-pass filter with a cutoff frequency of 1.5 Hz for physiological noises and by baseline drift removal. The preprocessed signal is segmented with PQRST peaks, while the segmented signals are passed through Coiflets' 5 Discrete Wavelet Transform for conventional feature extraction. The 1D-CRNN with two long short-term memory (LSTM) layers followed by three 1D convolutional layers was applied for deep learning-based feature extraction. These combinations of features result in biometric recognition accuracies of 80.64%, 98.81% and 99.62% for the ECG-ID, MIT-BIH and NSR-DB datasets, respectively. At the same time, 98.24% is achieved when combining all of these datasets. This research also compares conventional feature extraction, deep learning-based feature extraction and a combination of these for performance enhancement, compared to transfer learning approaches such as VGG-19, ResNet-152 and Inception-v3 with a small segment of ECG data.

Discovery of Knowledge in the Incidence of a Type of Lung Cancer for Patients through Data Mining Models.

This paper presents the research results on the contribution of user-centered data mining based on the standard principles, focusing on the analysis of survival and mortality of lung cancer cases. Researchers used anonymized data from previously diagnosed instances in the health database to predict the condition of new patients who have not had their results yet. Medical professionals specializing in this field provided feedback on the usefulness of the new software, which was constructed using WEKA data mining tools and the Naive Bayes method. The results of this article provide elements of interest to discuss the value of identifying or discovering relationships in apparently "hidden" information to propose strategies to counteract health problems or prevent future complications and thus contribute to improving the quality of care. Life of the population, as would be the case of data mining in the health area, has shown applicability in the early detection and prevention of diseases for the analysis of genetic markers to determine the probability of a satisfactory response to medical treatment, and the most accurate model was Naive Bayes (91.1%). The Naive Bayes algorithm's closest competitor, bagging, came in second with 90.8%. The analysis found that the ZeroR algorithm had the lowest success rate at 80%.