Time series classification (TSC) is a supervised task in which time series data are associated with predefined classes. Time ordering and correlations of the samples should be considered and observations can have different lengths. Therefore, learning compact and useful representations is an important approach for TSC. Fuzzy time series (FTS) methods have the ability to find temporal patterns and transition rules. Probabilistic Weighted FTS (PWFTS) uses the empirical probabilities to find the model of a TS. Despite its good performance, this method has been used exclusively for forecasting problems. Therefore, in this study we propose a novel TSC method using the PWFTS representation learning weights as features in conjuction to a classifier algorithm. We show that PWFTS method is able to learn useful representations for time series in low computational time. Our algorithm was tested in 24 datasets available in the UCR Time Series Classification Archive and compared with state of the art methods: fuzzy cognitive maps (FCM), Rocket, and TS2Vec in combination to the classifiers random forest (RF) and support vector machine (SVM). The classification accuracy and execution time required to find the features were evaluated. The results show that our fuzzy-probabilistic representation learning method is similar in accuracy to the other methods, and the time consumption for PWFTS computation was two to five orders of magnitude faster than the other methods. The results suggest that our approach can be used in time sensitive applications and in systems with hardware limitations.
Time series classification (TSC) has numerous applications across various domains. This research introduces a federated hybrid TSC method that combines image-based time series representation techniques with Convolutional Neural Networks (CNNs) in a decentralized framework. Specifically, three image representation techniques—Motif representation of numerical time series (NMotif), Motif representation of fuzzy time series (FTSMotif), and Polar—are utilized to convert raw data into image representations, which are then used as inputs for CNNs. Federated Learning (FL) enables collaborative training across distributed clients while ensuring data privacy. The method’s effectiveness is evaluated using 40 datasets from the UCR Archive. The results show that the FL model surpasses traditional baselines by up to 1.9% while enabling collaborative learning and preserving privacy. Although centralized state-of-the-art (SOTA) models such as Rocket and ResNet achieve higher overall accuracy, the proposed approach offers a competitive and practical alternative for real-world scenarios where centralized training is infeasible due to privacy constraints. These findings highlight the potential of our proposed federated image-based TSC as a scalable and privacy-aware solution for time series analysis.
Federated learning (FL) is a cutting-edge technology in artificial intelligence that preserves data privacy and security while reducing the cost of computation and communication. It transforms traditional centralized machine learning and deep learning approaches to enable decentralized model training without the need for data exchange. This work presents Flautim, the first implementation of an FL platform in Brazil and all around Latin America based on Kubernetes (K8S) and Flower framework. Flautim is designed for academic use, enabling researchers without a technical background to conduct FL experiments on this platform easily. Also, this platform allows for the development of applications involving data gathered from connected vehicles. Thus, this study aims to introduce this new FL platform, providing comprehensive details of its architecture.