# Too Good To Be True: performance overestimation in (re)current practices for Human Activity Recognition

arXiv: https://arxiv.org/abs/2310.11950 · HTML: https://mlsanity.com/paper/2310.11950/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 55 references that are in the map.
- First posted on arXiv 18 Oct 2023.

## Builds on (most cited first, 9 of 9)

- [Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks](https://mlsanity.com/paper/1810.02244/) (2018)
- [Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearables](https://mlsanity.com/paper/1604.08880/) (2016)
- [UniMiB SHAR: a new dataset for human activity recognition using acceleration data from smartphones](https://mlsanity.com/paper/1611.07688/) (2016)
- [Protecting Sensory Data against Sensitive Inferences](https://mlsanity.com/paper/1802.07802/) (2018)
- [Human Activity Recognition Based on Wearable Sensor Data: A Standardization of the State-of-the-Art](https://mlsanity.com/paper/1806.05226/) (2018)
- [Fully Convolutional Network Bootstrapped by Word Encoding and Embedding for Activity Recognition in Smart Homes](https://mlsanity.com/paper/2012.02300/) (2020)
- [Deep Transfer Learning with Graph Neural Network for Sensor-Based Human Activity Recognition](https://mlsanity.com/paper/2203.07910/) (2022)
- [Sensor Data Augmentation by Resampling for Contrastive Learning in Human Activity Recognition](https://mlsanity.com/paper/2109.02054/) (2021)
- [Subject Cross Validation in Human Activity Recognition](https://mlsanity.com/paper/1904.02666/) (2019)

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

- [A foundation model for electrodermal activity data](https://mlsanity.com/paper/2603.16878/) (2026)
- [Knowledge Distillation for Reservoir-based Classifier: Human Activity Recognition](https://mlsanity.com/paper/2505.22985/) (2025)

## Abstract (arXiv)

Today, there are standard and well established procedures within the Human Activity Recognition (HAR) pipeline. However, some of these conventional approaches lead to accuracy overestimation. In particular, sliding windows for data segmentation followed by standard random k-fold cross validation, produce biased results. An analysis of previous literature and present-day studies, surprisingly, shows that these are common approaches in state-of-the-art studies on HAR. It is important to raise awareness in the scientific community about this problem, whose negative effects are being overlooked. Otherwise, publications of biased results lead to papers that report lower accuracies, with correct unbiased methods, harder to publish. Several experiments with different types of datasets and different types of classification models allow us to exhibit the problem and show it persists independently of the method or dataset.