# Lightweight Multi-Scale Anomaly Detection for Resource-Constrained Edge Devices

arXiv: https://arxiv.org/abs/2607.12599 · HTML: https://mlsanity.com/paper/2607.12599/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 30 references that are in the map.
- First posted on arXiv 14 Jul 2026.

## Builds on (most cited first, 13 of 13)

- [Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy](https://mlsanity.com/paper/2110.02642/) (2021)
- [Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications](https://mlsanity.com/paper/1802.03903/) (2018)
- [LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection](https://mlsanity.com/paper/1607.00148/) (2016)
- [Time-Series Anomaly Detection Service at Microsoft](https://mlsanity.com/paper/1906.03821/) (2019)
- [Deep Learning for Time Series Anomaly Detection: A Survey](https://mlsanity.com/paper/2211.05244/) (2022)
- [Evaluating Real-time Anomaly Detection Algorithms - the Numenta Anomaly Benchmark](https://mlsanity.com/paper/1510.03336/) (2015)
- [TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks](https://mlsanity.com/paper/2009.07769/) (2020)
- [TAnoGAN: Time Series Anomaly Detection with Generative Adversarial Networks](https://mlsanity.com/paper/2008.09567/) (2020)
- [Collective Anomaly Detection based on Long Short Term Memory Recurrent Neural Network](https://mlsanity.com/paper/1703.09752/) (2017)
- [DeepEdgeBench: Benchmarking Deep Neural Networks on Edge Devices](https://mlsanity.com/paper/2108.09457/) (2021)
- [Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspective](https://mlsanity.com/paper/2402.02820/) (2024)
- [Generative Adversarial Networks (GANs): An Overview of Theoretical Model, Evaluation Metrics, and Recent Developments](https://mlsanity.com/paper/2005.13178/) (2020)
- [WaveRoRA: Wavelet Rotary Route Attention for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2410.22649/) (2024)

## Abstract (arXiv)

Time-series anomaly detection is increasingly important in IoT systems, sensor networks, and edge monitoring applications, where models must operate under strict constraints on memory, latency, and power consumption. While recent deep-learning approaches have improved detection accuracy, many remain computationally expensive and often fail to capture subtle anomalies due to limited multi-scale sensitivity. Autoencoders are widely used for anomaly detection because they reconstruct normal patterns well, leading to elevated reconstruction errors for anomalous inputs. Their simplicity and efficiency also make them suitable lightweight backbones for handling multi-scale inputs. To address these challenges, we propose a Lightweight MultiScale AutoEncoder (LMSAE) network for univariate time-series anomaly detection, designed to be compact and computationally efficient. LMSAE leverages the Discrete Wavelet Transform (DWT) to extract multi-scale features and employs a multi-scale loss function to improve sensitivity to subtle or hidden anomalies. Experiments on benchmark datasets demonstrate competitive or superior detection performance despite using significantly fewer parameters and a model size of less than 500 KB. LMSAE also achieves low-latency, low-power inference on the NVIDIA Jetson Nano, with 9x reduction in inference latency and 2x reduction in power consumption, making it ideal for edge deployment.