Analysis and Visualization of Deep Neural Networks in Device-Free Wi-Fi Indoor Localization
Device-free Wi-Fi indoor localization has received significant attention as a key enabling technology for many Internet of Things (IoT) applications. Machine learning-based location estimators, such as the deep neural network (DNN), carry proven potential in achieving high-precision localization per...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8721646/ |
| _version_ | 1819174681414991872 |
|---|---|
| author | Shing-Jiuan Liu Ronald Y. Chang Feng-Tsun Chien |
| author_facet | Shing-Jiuan Liu Ronald Y. Chang Feng-Tsun Chien |
| author_sort | Shing-Jiuan Liu |
| collection | DOAJ |
| description | Device-free Wi-Fi indoor localization has received significant attention as a key enabling technology for many Internet of Things (IoT) applications. Machine learning-based location estimators, such as the deep neural network (DNN), carry proven potential in achieving high-precision localization performance by automatically learning discriminative features from the noisy wireless signal measurements. However, the inner workings of the DNNs are not transparent and not adequately understood, especially in the indoor localization application. In this paper, we provide quantitative and visual explanations for the DNN learning process as well as the critical features that the DNN has learned during the process. Toward this end, we propose to use several visualization techniques, including 1) dimensionality reduction visualization, to project the high-dimensional feature space to the 2D space to facilitate visualization and interpretation, and 2) visual analytics and information visualization, to quantify relative contributions of each feature with the proposed feature manipulation procedures. The results provide insightful views and plausible explanations of the DNN in device-free Wi-Fi indoor localization using the channel state information (CSI) fingerprints. |
| first_indexed | 2024-12-22T20:42:50Z |
| format | Article |
| id | doaj.art-15049cbefe3e42df82172ccdbd62bfd1 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T20:42:50Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-15049cbefe3e42df82172ccdbd62bfd12022-12-21T18:13:18ZengIEEEIEEE Access2169-35362019-01-017693796939210.1109/ACCESS.2019.29187148721646Analysis and Visualization of Deep Neural Networks in Device-Free Wi-Fi Indoor LocalizationShing-Jiuan Liu0Ronald Y. Chang1https://orcid.org/0000-0003-4620-6824Feng-Tsun Chien2Research Center for Information Technology Innovation, Academia Sinica, Taipei, TaiwanResearch Center for Information Technology Innovation, Academia Sinica, Taipei, TaiwanInstitute of Electronics, National Chiao Tung University, Hsinchu, TaiwanDevice-free Wi-Fi indoor localization has received significant attention as a key enabling technology for many Internet of Things (IoT) applications. Machine learning-based location estimators, such as the deep neural network (DNN), carry proven potential in achieving high-precision localization performance by automatically learning discriminative features from the noisy wireless signal measurements. However, the inner workings of the DNNs are not transparent and not adequately understood, especially in the indoor localization application. In this paper, we provide quantitative and visual explanations for the DNN learning process as well as the critical features that the DNN has learned during the process. Toward this end, we propose to use several visualization techniques, including 1) dimensionality reduction visualization, to project the high-dimensional feature space to the 2D space to facilitate visualization and interpretation, and 2) visual analytics and information visualization, to quantify relative contributions of each feature with the proposed feature manipulation procedures. The results provide insightful views and plausible explanations of the DNN in device-free Wi-Fi indoor localization using the channel state information (CSI) fingerprints.https://ieeexplore.ieee.org/document/8721646/Wireless indoor localizationfingerprintingchannel state information (CSI)machine learningdeep neural networks (DNN)Internet of Things (IoT) |
| spellingShingle | Shing-Jiuan Liu Ronald Y. Chang Feng-Tsun Chien Analysis and Visualization of Deep Neural Networks in Device-Free Wi-Fi Indoor Localization IEEE Access Wireless indoor localization fingerprinting channel state information (CSI) machine learning deep neural networks (DNN) Internet of Things (IoT) |
| title | Analysis and Visualization of Deep Neural Networks in Device-Free Wi-Fi Indoor Localization |
| title_full | Analysis and Visualization of Deep Neural Networks in Device-Free Wi-Fi Indoor Localization |
| title_fullStr | Analysis and Visualization of Deep Neural Networks in Device-Free Wi-Fi Indoor Localization |
| title_full_unstemmed | Analysis and Visualization of Deep Neural Networks in Device-Free Wi-Fi Indoor Localization |
| title_short | Analysis and Visualization of Deep Neural Networks in Device-Free Wi-Fi Indoor Localization |
| title_sort | analysis and visualization of deep neural networks in device free wi fi indoor localization |
| topic | Wireless indoor localization fingerprinting channel state information (CSI) machine learning deep neural networks (DNN) Internet of Things (IoT) |
| url | https://ieeexplore.ieee.org/document/8721646/ |
| work_keys_str_mv | AT shingjiuanliu analysisandvisualizationofdeepneuralnetworksindevicefreewifiindoorlocalization AT ronaldychang analysisandvisualizationofdeepneuralnetworksindevicefreewifiindoorlocalization AT fengtsunchien analysisandvisualizationofdeepneuralnetworksindevicefreewifiindoorlocalization |