Read more
This volume LNCS 14343 constitutes the refereed proceedings of the 8th ECML PKDD Workshop, AALTD 2023, in Turin, Italy, in September 2023.
The 20 full papers were carefully reviewed and selected from 28 submissions. They are organized in the following topical section as follows: Machine Learning; Data Mining; Pattern Analysis; Statistics to Share their Challenges and Advances in Temporal Data Analysis.
List of contents
Human Activity Segmentation Challenge.- Human Activity Segmentation Challenge@ECML/PKDD'23.- Change points detection in multivariate signal applied to human activity segmentation.- Change Point Detection via Synthetic Signals.- Oral Presentation.- Clustering time series with k-medoids based algorithms.- Explainable Parallel RCNN with Novel Feature Representation for Time Series Forecasting.- RED CoMETS: an ensemble classifier for symbolically represented multivariate time series.- Deep Long Term Prediction for Semantic Segmentation in Autonomous Driving.- Extracting Features from Random Subseries: A Hybrid Pipeline for Time Series Classification and Extrinsic Regression.- ShapeDBA: Generating Effective Time Series Prototypes using ShapeDTW Barycenter Averaging.- Poster Presentation.- Temporal Performance Prediction for Deep Convolutional Long Short-Term Memory Networks.- Evaluating Explanation Methods for Multivariate Time SeriesClassification.- tGLAD: A sparse graph recovery based approach for multivariate time series segmentation.- Designing a New Search Space for Multivariate Time-Series Neural Architecture Search.- Back to Basics: A Sanity Check on Modern Time Series Classification Algorithms.- Do Cows Have Fingerprints? Using Time Series Techniques and Milk Flow Profiles to Characterise Cow Behaviours and Detect Health Issues.- Exploiting Context and Attention with Recurrent Neural Network for Sensor Time Series Prediction.- Rail Crack Propagation Forecasting Using Multi-horizons RNNs.- Electricity Load and Peak Forecasting: Feature Engineering, Probabilistic LightGBM and Temporal Hierarchies.- Time-aware Predictions of Moments of Change in Longitudinal User Posts on Social Media.
