IEEE

FTHAR: A Dual-Modal Deep Learning Model with Feature Filtering for Human Activity Recognition on Wearable Devices

Abstract: Human activity recognition (HAR) based on wearable devices enables real-time monitoring of human activities via sensor data from smartphones and smartwatches, which is crucial for ...
IEEE

Bidirectional Transfer Learning Between Activity and User Identity Recognition via 2D CNN-LSTM Model for Wearables

Abstract: We implement transfer learning (TL) to attain efficiency in training and feature extraction by freezing the connection weights of shallow layers of deep learning (DL) models, already trained ...
Frontiers

Mechanisms linking school physical education policies to college students’ physical activity: an empirical test of a moderated mediation model

School physical education policies (SPEPs) promote college students’ physical activity and fitness, but the mechanisms linking policy to behavior are under-explored. This study explores how SPEPs ...
GitHub

Replication package for the paper 'Nowcasting economic activity in European regions using a mixed-frequency dynamic factor model'

Software version: R version 4.5.1 (2025-06-13) -- "Great Square Root" The out-of-sample forecast exercise and in-sample results were obtained on a high-performance cluster which allows for parallel ...