No description available.

The availability of a scalable and explainable rule extraction technique via motif discovery is crucial for identifying the health states of a system. Such a technique can enable the creation of a repository of normal and abnormal states of the system and identify the system’s state as we receive data. In complex systems such as ECG, each activity session can consist of a long sequence of motifs that form different global structures. As a result, applying machine learning algorithms without first identifying the local patterns is not feasible and would result in low performance. Thus, extracting unique local motifs and establishing a database of prototypes or signatures is a crucial first step in analyzing long temporal data that reduces the computational cost and overcomes imbalanced data. The present research aims to streamline the extraction of motifs and add explainability to their analysis by identifying their differences. We have developed a novel framework for unsupervised motif extraction. We also offer a robust algorithm to identify unique motifs and their signatures, coupled with a proper distance metric to compare the signatures of partially similar motifs. Defining such distance metrics allows us to assign a degree of semblance between two motifs that may have different lengths or contain noise. We have tested our framework against five different datasets and observed excellent results, including extraction of motifs from 100 million samples in 8.02 seconds, 99.90% accuracy in self-supervised ECG data classification, and an average error of 16.66% in RUL prediction of bearing failure.

This work is devoted to the creation of a study of human cardiac pathologies based on ECG data using machine learning. The purpose of the study was to develop an effective model for assessing human cardiac pathologies. To achieve this goal, it is planned to analyze modern methods of machine learning. Select suitable tools for implementing the model, select a dataset with ECG data, conduct experiments with training various machine learning models and draw conclusions about the work done. The study of changes in human health based on ECG data using machine learning, proposed in the work, has significant potential for the timely detection of human pathologies based on ECG data. The created model has a high accuracy of assessment. / Данная работа посвящена созданию исследованию сердечных патологий человека на основе данных ЭКГ с использованием машинного обучения. Цель исследования заключалась в разработке эффективной модели оценки сердечных патологий человека. Для достижения этой цели предполагается провести анализ современных методов машинного обучения. Выбрать подходящие инструменты для реализации модели, выбрать датасет с данными ЭКГ, провести эксперименты с обучением различных моделей машинного обучения и сделать выводы о проделанной работе. Исследование изменения состояния здоровья человека на основе данных ЭКГ с использованием машинного обучения, предложенная в работе, обладает значительным потенциалом для своевременного выявления патологий человека на основе данных ЭКГ. Созданная модель имеет высокую точность оценки.