Characterization and Selection of WiFi Channel State Information Features for Human Activity Detection in a Smart Public Transportation System
Robust methods are needed to detect how people are moving in smart public transportation systems. This paper proposes and characterizes effective means to accurately detect passengers. We analyze a public WiFi-based activity recognition (WiAR) dataset to extract human activity features from Channel...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of Intelligent Transportation Systems |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10332939/ |
| _version_ | 1797360154238255104 |
|---|---|
| author | Roya Alizadeh Yvon Savaria Chahe Nerguizian |
| author_facet | Roya Alizadeh Yvon Savaria Chahe Nerguizian |
| author_sort | Roya Alizadeh |
| collection | DOAJ |
| description | Robust methods are needed to detect how people are moving in smart public transportation systems. This paper proposes and characterizes effective means to accurately detect passengers. We analyze a public WiFi-based activity recognition (WiAR) dataset to extract human activity features from Channel State Information (CSI) data. To do so, CSI power changes caused by nearby human activity are analyzed. Our method first extracts multi-dimensional features using a Short-Time Fourier Transform (STFT) of CSI data to capture the relevant signal features. Since the environment of a transportation system changes dynamically and non-deterministically, we propose analyzing these changes with a heuristic algorithm that leverages a decision tree to automate a decision-making solution for feature selection. Principal Component Analysis (PCA) is performed before the decision tree algorithm. Reported results are compared with those obtained from the existing methods. Based on these results, we explore the effectiveness of various features such as the chirp rate, delta band power, spectral flux, and frequency of movement. This allows identifying and recommending the most effective features for the explored detection task according to observed variability, information gain, and correlation between features. The reported classification results show that using only the chirp rate estimated from CSI information as a feature, we achieve precision = 83%, True Positive <inline-formula> <tex-math notation="LaTeX">$(TP)=94\%$ </tex-math></inline-formula>, True Negative <inline-formula> <tex-math notation="LaTeX">$(TN)= 91\%$ </tex-math></inline-formula> and F1-score = 87%. Considering delta band power as an additional feature adds more information and allows getting higher performance with precision = 100%, <inline-formula> <tex-math notation="LaTeX">$TP=97\%$ </tex-math></inline-formula>, <inline-formula> <tex-math notation="LaTeX">$TN = 95\%$ </tex-math></inline-formula> and F1-score = 95%. |
| first_indexed | 2024-03-08T15:35:10Z |
| format | Article |
| id | doaj.art-03c5e70f83564ea2bae5966eac388137 |
| institution | Directory Open Access Journal |
| issn | 2687-7813 |
| language | English |
| last_indexed | 2024-03-08T15:35:10Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Intelligent Transportation Systems |
| spelling | doaj.art-03c5e70f83564ea2bae5966eac3881372024-01-10T00:06:17ZengIEEEIEEE Open Journal of Intelligent Transportation Systems2687-78132024-01-015556910.1109/OJITS.2023.333679510332939Characterization and Selection of WiFi Channel State Information Features for Human Activity Detection in a Smart Public Transportation SystemRoya Alizadeh0https://orcid.org/0009-0008-5444-3620Yvon Savaria1https://orcid.org/0000-0002-3404-9959Chahe Nerguizian2https://orcid.org/0000-0002-4971-5723Department of Electrical and Computer Engineering, École Polytechnique de Montréal, Montreal, CanadaDepartment of Electrical and Computer Engineering, École Polytechnique de Montréal, Montreal, CanadaDepartment of Electrical and Computer Engineering, École Polytechnique de Montréal, Montreal, CanadaRobust methods are needed to detect how people are moving in smart public transportation systems. This paper proposes and characterizes effective means to accurately detect passengers. We analyze a public WiFi-based activity recognition (WiAR) dataset to extract human activity features from Channel State Information (CSI) data. To do so, CSI power changes caused by nearby human activity are analyzed. Our method first extracts multi-dimensional features using a Short-Time Fourier Transform (STFT) of CSI data to capture the relevant signal features. Since the environment of a transportation system changes dynamically and non-deterministically, we propose analyzing these changes with a heuristic algorithm that leverages a decision tree to automate a decision-making solution for feature selection. Principal Component Analysis (PCA) is performed before the decision tree algorithm. Reported results are compared with those obtained from the existing methods. Based on these results, we explore the effectiveness of various features such as the chirp rate, delta band power, spectral flux, and frequency of movement. This allows identifying and recommending the most effective features for the explored detection task according to observed variability, information gain, and correlation between features. The reported classification results show that using only the chirp rate estimated from CSI information as a feature, we achieve precision = 83%, True Positive <inline-formula> <tex-math notation="LaTeX">$(TP)=94\%$ </tex-math></inline-formula>, True Negative <inline-formula> <tex-math notation="LaTeX">$(TN)= 91\%$ </tex-math></inline-formula> and F1-score = 87%. Considering delta band power as an additional feature adds more information and allows getting higher performance with precision = 100%, <inline-formula> <tex-math notation="LaTeX">$TP=97\%$ </tex-math></inline-formula>, <inline-formula> <tex-math notation="LaTeX">$TN = 95\%$ </tex-math></inline-formula> and F1-score = 95%.https://ieeexplore.ieee.org/document/10332939/Feature extraction and analysisclassificationhuman activity recognitionchannel state information (CSI)chirp ratesmart public transportation systems |
| spellingShingle | Roya Alizadeh Yvon Savaria Chahe Nerguizian Characterization and Selection of WiFi Channel State Information Features for Human Activity Detection in a Smart Public Transportation System IEEE Open Journal of Intelligent Transportation Systems Feature extraction and analysis classification human activity recognition channel state information (CSI) chirp rate smart public transportation systems |
| title | Characterization and Selection of WiFi Channel State Information Features for Human Activity Detection in a Smart Public Transportation System |
| title_full | Characterization and Selection of WiFi Channel State Information Features for Human Activity Detection in a Smart Public Transportation System |
| title_fullStr | Characterization and Selection of WiFi Channel State Information Features for Human Activity Detection in a Smart Public Transportation System |
| title_full_unstemmed | Characterization and Selection of WiFi Channel State Information Features for Human Activity Detection in a Smart Public Transportation System |
| title_short | Characterization and Selection of WiFi Channel State Information Features for Human Activity Detection in a Smart Public Transportation System |
| title_sort | characterization and selection of wifi channel state information features for human activity detection in a smart public transportation system |
| topic | Feature extraction and analysis classification human activity recognition channel state information (CSI) chirp rate smart public transportation systems |
| url | https://ieeexplore.ieee.org/document/10332939/ |
| work_keys_str_mv | AT royaalizadeh characterizationandselectionofwifichannelstateinformationfeaturesforhumanactivitydetectioninasmartpublictransportationsystem AT yvonsavaria characterizationandselectionofwifichannelstateinformationfeaturesforhumanactivitydetectioninasmartpublictransportationsystem AT chahenerguizian characterizationandselectionofwifichannelstateinformationfeaturesforhumanactivitydetectioninasmartpublictransportationsystem |