An AI-Driven Approach to Industrial Testing: From Time Series to Supervised Classification through Dynamic Thresholds

<b>Dynamic Time Series Modeling with AI-Assisted Data Labeling</b> is a pipeline for analyzing time-series data. It integrates deep learning and machine learning techniques to detect anomalies, dynamically label data, and classify observations. The workflow includes:<b>Deep LSTM Autoencoder</b>: Extracts latent features from time-series data to capture temporal patterns.<b>Supervised Data Labeling</b>: Uses Ridge Regression with dynamic thresholds to label windows.<b>Data Augmentation</b>: Balances the dataset with SMOTE and under-sampling techniques.<b>CNN Classification</b>: Classifies time-series windows into categories with high accuracy.<b>Evaluation and Visualization</b>: Provides insights through regression plots, feature importance, and ROC curves.<b>System Architecture</b>This modular approach ensures scalability, interpretability, and robust performance for time-series modeling and classification.