# LSTM-Autoencoder based Anomaly Detection for Indoor Air Quality Time Series Data

arXiv: https://arxiv.org/abs/2204.06701 · HTML: https://mlsanity.com/paper/2204.06701/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 36 references that are in the map.
- First posted on arXiv 14 Apr 2022.

## Builds on (most cited first, 1 of 1)

- [A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencoder](https://mlsanity.com/paper/1711.00614/) (2017)

## Built on by (most cited first, 19 of 19)

- [A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directions](https://mlsanity.com/paper/2307.05638/) (2023)
- [Deep Learning Advancements in Anomaly Detection: A Comprehensive Survey](https://mlsanity.com/paper/2503.13195/) (2025)
- [Decomposition-based multi-scale transformer framework for time series anomaly detection](https://mlsanity.com/paper/2504.14206/) (2025)
- [Reconstruction-based LSTM-Autoencoder for Anomaly-based DDoS Attack Detection over Multivariate Time-Series Data](https://mlsanity.com/paper/2305.09475/) (2023)
- [Contaminated Multivariate Time-Series Anomaly Detection with Spatio-Temporal Graph Conditional Diffusion Models](https://mlsanity.com/paper/2308.12563/) (2023)
- [A Bi-LSTM Autoencoder Framework for Anomaly Detection -- A Case Study of a Wind Power Dataset](https://mlsanity.com/paper/2303.09703/) (2023)
- [Self-evolving Autoencoder Embedded Q-Network](https://mlsanity.com/paper/2402.11604/) (2024)
- [Creation of AI-driven Smart Spaces for Enhanced Indoor Environments -- A Survey](https://mlsanity.com/paper/2412.14708/) (2024)
- [Rogue Cell: Adversarial Attack and Defense in Untrusted O-RAN Setup Exploiting the Traffic Steering xApp](https://mlsanity.com/paper/2505.01816/) (2025)
- [Label Assisted Autoencoder for Anomaly Detection in Power Generation Plants](https://mlsanity.com/paper/2302.02896/) (2023)
- [Calibrated Unsupervised Anomaly Detection in Multivariate Time-series using Reinforcement Learning](https://mlsanity.com/paper/2502.03245/) (2025)
- [Anomaly Detection in Complex Dynamical Systems: A Systematic Framework Using Embedding Theory and Physics-Inspired Consistency](https://mlsanity.com/paper/2502.19307/) (2025)
- [Hybrid Temporal Differential Consistency Autoencoder for Efficient and Sustainable Anomaly Detection in Cyber-Physical Systems](https://mlsanity.com/paper/2504.06320/) (2025)
- [The Application of Transformer-Based Models for Predicting Consequences of Cyber Attacks](https://mlsanity.com/paper/2508.13030/) (2025)
- [On the Tradeoffs of On-Device Generative Models in Federated Predictive Maintenance Systems](https://mlsanity.com/paper/2605.07860/) (2026)
- [ODBAE: a high-performance model identifying complex phenotypes in high-dimensional biological datasets](https://mlsanity.com/paper/2211.03054/) (2022)
- [A Novel Spatiotemporal Correlation Anomaly Detection Method Based on Time-Frequency-Domain Feature Fusion and a Dynamic Graph Neural Network in Wireless Sensor Network](https://mlsanity.com/paper/2503.00036/) (2025)
- [A New Spatiotemporal Correlation Anomaly Detection Method that Integrates Contrastive Learning and Few-Shot Learning in Wireless Sensor Networks](https://mlsanity.com/paper/2506.00420/) (2025)
- [Anomaly Detection for Electro-Hydrostatic Actuators using LSTM Autoencoder](https://mlsanity.com/paper/2606.05274/) (2026)

## Abstract (arXiv)

Anomaly detection for indoor air quality (IAQ) data has become an important area of research as the quality of air is closely related to human health and well-being. However, traditional statistics and shallow machine learning-based approaches in anomaly detection in the IAQ area could not detect anomalies involving the observation of correlations across several data points (i.e., often referred to as long-term dependences). We propose a hybrid deep learning model that combines LSTM with Autoencoder for anomaly detection tasks in IAQ to address this issue. In our approach, the LSTM network is comprised of multiple LSTM cells that work with each other to learn the long-term dependences of the data in a time-series sequence. Autoencoder identifies the optimal threshold based on the reconstruction loss rates evaluated on every data across all time-series sequences. Our experimental results, based on the Dunedin CO2 time-series dataset obtained through a real-world deployment of the schools in New Zealand, demonstrate a very high and robust accuracy rate (99.50%) that outperforms other similar models.