AERed: An Autoencoder–Decoder Dimensionality Reduction Method for Wearable-Based Human Activity Recognition

Human activity recognition (HAR) is the process of identifying a person’s activities accurately. It is possible by placing sensors on the subject’s body and obtaining data from a variety of high-dimensional physiological signals. Recently, sensors such as an accelerometer and gyroscopes have been incorporated directly into wearable devices, making activity identification fairly straightforward. High dimensionality makes it necessary to use an optimization method that might reduce the number of features used in the dataset while taking less time to make activity recognition successful in wearable devices with limited battery life. In this study, we propose the autoencoder reduction method (AERed), a dimensionality reduction (DR) technique based on the symmetric design of a typical autoencoder (AE). With the new structure, there are fewer weights that must be tweaked, which lowers the computational cost. This work makes use of a public-domain dataset from the UCI repository. The dataset’s features were reduced from 561 to 256 using the AERed method. The reduced features are classified using a random Bayesian filter support vector machine classifier and reported 95.95% F1-score. This method also consumed a lot less time than baseline methods at the DR stage. The proposed method is validated by performing parameter sensitivity analysis, complexity analysis, and visualization performance analysis.

• Publication year

  2023

• Venue

  IEEE Sensors Journal

• Publication date

  2023-12-01

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/JSEN.2023.3323328
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Inception inspired CNN-GRU hybrid network for human activity recognition

  2022cited by this paper
• A Hybrid Deep Learning-Based Approach for Brain Tumor Classification

  2022cited by this paper
• A multibranch CNN-BiLSTM model for human activity recognition using wearable sensor data

  2021influential reference
• Detection of Epileptic Seizures on EEG Signals Using ANFIS Classifier, Autoencoders and Fuzzy Entropies

  2021cited by this paper
• Deep ensemble learning approach for lower extremity activities recognition using wearable sensors

  2021cited by this paper
• Training Design, Performance Analysis, and Talent Identification—A Systematic Review about the Most Relevant Variables through the Principal Component Analysis in Soccer, Basketball, and Rugby

  2021cited by this paper
• Incremental learning framework for real‐world fraud detection environment

  2021cited by this paper
• Feature learning using convolutional denoising autoencoder for activity recognition

  2021cited by this paper
• An optimized feature selection using bio-geography optimization technique for human walking activities recognition

  2021cited by this paper
• A novel dimensionality reduction approach for ECG signal via convolutional denoising autoencoder with LSTM

  2021cited by this paper
• Incremental Neural-Network Learning for Big Fraud Data

  2020cited by this paper
• Feature learning for Human Activity Recognition using Convolutional Neural Networks

  2020influential reference
• EnsemConvNet: a deep learning approach for human activity recognition using smartphone sensors for healthcare applications

  2020cited by this paper
• Guided autoencoder for dimensionality reduction of pedestrian features

  2020cited by this paper
• Using Smartphones and Wearable Devices to Monitor Behavioral Changes During COVID-19

  2020cited by this paper
• A CNN-LSTM Approach to Human Activity Recognition

  2020influential reference
• LSTM-CNN Architecture for Human Activity Recognition

  2020cited by this paper
• A deep adversarial variational autoencoder model for dimensionality reduction in single-cell RNA sequencing analysis

  2020cited by this paper
• Human action recognition with deep learning and structural optimization using a hybrid heuristic algorithm

  2020cited by this paper
• Human Activity Recognition on Smartphones Using a Bidirectional LSTM Network

  2019influential reference
• Deep Learning Models for Real-time Human Activity Recognition with Smartphones

  2019influential reference
• A Human Activity Recognition Algorithm Based on Stacking Denoising Autoencoder and LightGBM

  2019cited by this paper
• Features Dimensionality Reduction Approaches for Machine Learning Based Network Intrusion Detection

  2019cited by this paper
• Attention-Based Convolutional Neural Network for Weakly Labeled Human Activities’ Recognition With Wearable Sensors

  2019influential reference
• Human Activity Recognition Based on Wearable Sensor Using Hierarchical Deep LSTM Networks

  2019influential reference
• Stacked Lstm Network for Human Activity Recognition Using Smartphone Data

  2019influential reference
• Human Activity Recognition Using Smartphones

  2018cited by this paper
• Deep Residual Bidir-LSTM for Human Activity Recognition Using Wearable Sensors

  2017influential reference
• An overview of the supervised machine learning methods

  2017cited by this paper
• Auto-encoder based dimensionality reduction

  2016cited by this paper
• Comparison among dimensionality reduction techniques based on Random Projection for cancer classification

  2016cited by this paper
• Novel segmented stacked autoencoder for effective dimensionality reduction and feature extraction in hyperspectral imaging

  2016cited by this paper
• Recognition of Human Activities Using Continuous Autoencoders with Wearable Sensors

  2016cited by this paper
• Diversity-aware classifier ensemble selection via f-score

  2016cited by this paper
• Bearing Fault Diagnosis Based on Statistical Locally Linear Embedding

  2015cited by this paper
• A Survey of Online Activity Recognition Using Mobile Phones

  2015cited by this paper
• Neural Network-Based User-Independent Physical Activity Recognition for Mobile Devices

  2015cited by this paper
• A Review of Dimensionality Reduction Techniques

  2015cited by this paper
• A survey of dimensionality reduction techniques

  2014cited by this paper
• A Public Domain Dataset for Human Activity Recognition using Smartphones

  2013cited by this paper
• Dimensionality Reduction in the Wild : Gaps and Guidance

  2012cited by this paper
• Adaptive Control Processes

  2010cited by this paper
• The Curse of Dimensionality in Data Mining and Time Series Prediction

  2005cited by this paper
• Manifold learning, a promised land or work in progress?

  2005cited by this paper
• The Problem of Overfitting

  2004cited by this paper
• Global Versus Local Methods in Nonlinear Dimensionality Reduction

  2002cited by this paper
• A global geometric framework for nonlinear dimensionality reduction.

  2000cited by this paper
• Nonlinear dimensionality reduction by locally linear embedding.

  2000cited by this paper
• Detection of posture and motion by accelerometry : a validation study in ambulatory monitoring

  1999cited by this paper

• A constrained reinforcement learning based approach for cooperative control of multi-UAV in dense obstacle environments

  2026cites this paper
• Latent Space Representation of Adversarial AutoEncoder for Human Activity Recognition: Application to a low-cost commercial force plate and inertial measurement units

  2025cites this paper
• ECG Heartbeat Classification Using CNN Autoencoder Feature Extraction and Attention-Augmented BiLSTM Classifier

  2025cites this paper
• Real-Time IMU-Based Kinematics in the Presence of Wireless Data Drop

  2024cites this paper