Mitigating Data Leakage in a WiFi CSI Benchmark for Human Action Recognition

Human action recognition using WiFi channel state information (CSI) has gained attention due to its non-intrusive nature and potential applications in healthcare, smart environments, and security. However, the reliability of methods developed for CSI-based action recognition is often contingent on t...

Full description

Saved in:
Bibliographic Details
Main Author: Domonkos Varga
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/24/8201
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846102734072184832
author Domonkos Varga
author_facet Domonkos Varga
author_sort Domonkos Varga
collection DOAJ
description Human action recognition using WiFi channel state information (CSI) has gained attention due to its non-intrusive nature and potential applications in healthcare, smart environments, and security. However, the reliability of methods developed for CSI-based action recognition is often contingent on the quality of the datasets and evaluation protocols used. In this paper, we uncovered a critical data leakage issue, which arises from improper data partitioning, in a widely used WiFi CSI benchmark dataset. Specifically, the benchmark fails to separate individuals between the training and test sets, leading to inflated performance metrics as models inadvertently learn individual-specific features rather than generalizable action patterns. We analyzed this issue in depth, retrained several benchmarked models using corrected data partitioning methods, and demonstrated a significant drop in accuracy when individuals were properly separated across training and testing. Our findings highlight the importance of rigorous data partitioning in CSI-based action recognition and provide recommendations for mitigating data leakage in future research. This work contributes to the development of more robust and reliable human action recognition systems using WiFi CSI.
format Article
id doaj-art-a64026aecbf44a3cbae17c043c7fd1b3
institution Kabale University
issn 1424-8220
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-a64026aecbf44a3cbae17c043c7fd1b32024-12-27T14:53:18ZengMDPI AGSensors1424-82202024-12-012424820110.3390/s24248201Mitigating Data Leakage in a WiFi CSI Benchmark for Human Action RecognitionDomonkos Varga0Nokia Bell Labs, 1082 Budapest, HungaryHuman action recognition using WiFi channel state information (CSI) has gained attention due to its non-intrusive nature and potential applications in healthcare, smart environments, and security. However, the reliability of methods developed for CSI-based action recognition is often contingent on the quality of the datasets and evaluation protocols used. In this paper, we uncovered a critical data leakage issue, which arises from improper data partitioning, in a widely used WiFi CSI benchmark dataset. Specifically, the benchmark fails to separate individuals between the training and test sets, leading to inflated performance metrics as models inadvertently learn individual-specific features rather than generalizable action patterns. We analyzed this issue in depth, retrained several benchmarked models using corrected data partitioning methods, and demonstrated a significant drop in accuracy when individuals were properly separated across training and testing. Our findings highlight the importance of rigorous data partitioning in CSI-based action recognition and provide recommendations for mitigating data leakage in future research. This work contributes to the development of more robust and reliable human action recognition systems using WiFi CSI.https://www.mdpi.com/1424-8220/24/24/8201WiFi CSIhuman action recognitionmachine learning integrity
spellingShingle Domonkos Varga
Mitigating Data Leakage in a WiFi CSI Benchmark for Human Action Recognition
Sensors
WiFi CSI
human action recognition
machine learning integrity
title Mitigating Data Leakage in a WiFi CSI Benchmark for Human Action Recognition
title_full Mitigating Data Leakage in a WiFi CSI Benchmark for Human Action Recognition
title_fullStr Mitigating Data Leakage in a WiFi CSI Benchmark for Human Action Recognition
title_full_unstemmed Mitigating Data Leakage in a WiFi CSI Benchmark for Human Action Recognition
title_short Mitigating Data Leakage in a WiFi CSI Benchmark for Human Action Recognition
title_sort mitigating data leakage in a wifi csi benchmark for human action recognition
topic WiFi CSI
human action recognition
machine learning integrity
url https://www.mdpi.com/1424-8220/24/24/8201
work_keys_str_mv AT domonkosvarga mitigatingdataleakageinawificsibenchmarkforhumanactionrecognition