# CNN Autoencoders for Hierarchical Feature Extraction and Fusion in Multi-sensor Human Activity Recognition

arXiv: https://arxiv.org/abs/2502.04489 · HTML: https://mlsanity.com/paper/2502.04489/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 63 references that are in the map.
- First posted on arXiv 6 Feb 2025.

## Builds on (most cited first, 12 of 12)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Learning Factorized Multimodal Representations](https://mlsanity.com/paper/1806.06176/) (2018)
- [Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark](https://mlsanity.com/paper/2109.14545/) (2021)
- [Semi-supervised Deep Generative Modelling of Incomplete Multi-Modality Emotional Data](https://mlsanity.com/paper/1808.02096/) (2018)
- [Human Activity Recognition using Inertial, Physiological and Environmental Sensors: a Comprehensive Survey](https://mlsanity.com/paper/2004.08821/) (2020)
- [A practical tutorial on autoencoders for nonlinear feature fusion: Taxonomy, models, software and guidelines](https://mlsanity.com/paper/1801.01586/) (2018)
- [Attention-based Convolutional Neural Network for Weakly Labeled Human Activities Recognition with Wearable Sensors](https://mlsanity.com/paper/1903.10909/) (2019)
- [Human Activity Recognition Using Tools of Convolutional Neural Networks: A State of the Art Review, Data Sets, Challenges and Future Prospects](https://mlsanity.com/paper/2202.03274/) (2022)
- [Sequential Weakly Labeled Multi-Activity Localization and Recognition on Wearable Sensors using Recurrent Attention Networks](https://mlsanity.com/paper/2004.05768/) (2020)
- [Robust Multimodal Fusion for Human Activity Recognition](https://mlsanity.com/paper/2303.04636/) (2023)

## Built on by (most cited first, 2 of 2)

- [MoPFormer: Motion-Primitive Transformer for Wearable-Sensor Activity Recognition](https://mlsanity.com/paper/2505.20744/) (2025)
- [Memory-Augmented LSTM Autoencoder for Unsupervised Activity Recognition with IMU Sensor Fusion](https://mlsanity.com/paper/2606.28377/) (2026)

## Abstract (arXiv)

Deep learning methods have been widely used for Human Activity Recognition (HAR) using recorded signals from Iner-tial Measurement Units (IMUs) sensors that are installed on various parts of the human body. For this type of HAR, sev-eral challenges exist, the most significant of which is the analysis of multivarious IMU sensors data. Here, we introduce a Hierarchically Unsupervised Fusion (HUF) model designed to extract, and fuse features from IMU sensors data via a hybrid structure of Convolutional Neural Networks (CNN)s and Autoencoders (AE)s. First, we design a stack CNN-AE to embed short-time signals into sets of high dimensional features. Second, we develop another CNN-AE network to locally fuse the extracted features from each sensor unit. Finally, we unify all the sensor features through a third CNN-AE architecture as globally feature fusion to create a unique feature set. Additionally, we analyze the effects of varying the model hyperparameters. The best results are achieved with eight convolutional layers in each AE. Furthermore, it is determined that an overcomplete AE with 256 kernels in the code layer is suitable for feature extraction in the first block of the proposed HUF model; this number reduces to 64 in the last block of the model to customize the size of the applied features to the classifier. The tuned model is applied to the UCI-HAR, DaLiAc, and Parkinson's disease gait da-tasets, achieving the classification accuracies of 97%, 97%, and 88%, respectively, which are nearly 3% better com-pared to the state-of-the-art supervised methods.