Time Series Classification using ResNet Ensemble

One of the vital tasks in Time Series analysis is classifying time series data. This has attracted considerable interest and huge efforts in the past decades. This is still a challenging problem because of the complexity and nature of time series data. They are huge, complex, and constantly updated. There is an increasing demand to extract knowledge from time-series data. The time series has a natural feature that helps humans to visualize the structure of data. Increased interest in studying this particular data type has been sparked by the growth of recorded data, leading to a wealth of unique techniques for encoding, indexing, grouping, and categorising time series, among other tasks. To enhance the performance of traditional feature-based approaches, deep learning techniques were explored. Deep Neural Networks have revolutionized computer vision with their innovative deeper architec-tures like Residual Neural Networks and Convolutional Neural Networks. In this paper, the proposed deep learning architecture improves the performance of Residual Network for time series classification.