Skip to content
Research on indoor localization
Python Jupyter Notebook Shell
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
data Fix the name of data set to "UJIIndoorLoc". Oct 16, 2017
python Update multi-label classification and SIMO models. Jul 17, 2019
results
tools
.gitattributes Add .gitattributes to control line endings. Jan 25, 2018
.gitignore Add '.gitignore'. Aug 13, 2017
README.md Add a summary of publications with corresponding python programs. Jan 3, 2018
README.org Turn off table of contents. Aug 19, 2017

README.md

This is a repository for research on indoor localization based on wireless fingerprinting techniques. For more details, please visit XJTLU SURF project home page.

2018-01-03

  • A summary of the publications based on the work in this repository:
    • Kyeong Soo Kim, Sanghyuk Lee, and Kaizhu Huang "A scalable deep neural network architecture for multi-building and multi-floor indoor localization based on Wi-Fi fingerprinting," submitted to Big Data Analytics, Dec. 5, 2017. (arXiv)
    • Kyeong Soo Kim, Ruihao Wang, Zhenghang Zhong, Zikun Tan, Haowei Song, Jaehoon Cha, and Sanghyuk Lee, "Large-scale location-aware services in access: Hierarchical building/floor classification and location estimation using Wi-Fi fingerprinting based on deep neural networks," Proc. Fiber Optics in Access Networks (FOAN) 2017, Munich, Germany Nov. 7, 2017. (arXiv)

2017-08-18

  • Implement a multi-label classifier to address the issues described on 2017-08-17: 3 building and 5 floor identifiers are one-hot encoded into an 8-dimensional vector (e.g., '001|01000') and classified with different class weights (e.g., 30 for buidlings and 1 for floors); the resulting one-hot-encoded vector is split into 3-dimensional building and 5-dimensional floor vectors and the index of a maximum value of each vector is returned as a classified class (results).
    • Still, need to optimize parameters a lot.

2017-08-17

  • Implement a new program, which calculates accuracies separately for building and floor classification, to investigate the hierarchical nature of the classification problem at hand; the deep-learning-based place recognition system described in the key paper1 does not take into account this and carries out classification based on flattened labels (i.e., (building, floor) -> 'building-floor'). We are now considering two options to guarantee 100% accuracy for the building classification:
    • Hierarchical classifier with a tree structure and multiple classifiers and data sets, which is a conventional approach and a reference for this investigation.
    • One classifier with a weighted loss function2. In our case, however, the loss function does not give a closed-form gradient function, which forces us to use evolutionary algorithms (e.g., genetic algorithm) for training of neural network weights or multi-label classification with different class weights (i.e., higher weights for buildings in our case).

2017-08-15

  • Today, we further simplified the building/floor classification system by removing a hidden layer from the classifier (therefore no dropout), resulting in the configuration of '520-64-4-13' (including input and output layers) with loss=7.050603e-01 and accuracy=9.234923e-01 (results). This might mean that the 4-dimensional data from the SAE encoder (64-4) can be linearly separable. Due to training of SAE encoder weights for the combined system, however, it needs further investigation.

2017-08-14

  • We investigated whether a couple of strong RSSs in a fingerprint dominate the classification performance in building/floor classification. After many trials with different configurations, we could obtain more than 90% accuracies with the stacked-autoencoder (SAE) having 64-4-64 hidden layers (i.e., just 4 dimension) and the classifier having just one 128-node hidden layer (results). This implies that a small number of RSSs from access points (APs) deployed in a building/floor can give enough information for the building/floor classification; the localization on the same floor, by the way, would be quite different, where RSSs from possibly many APs have a significant impact on the localization performance.

2017-08-13

2017-08-12

Footnotes

1 M. Nowicki and J. Wietrzykowski, "Low-effort place recognition with WiFi fingerprints using deep learning," arXiv:1611.02049v2 [cs.RO] (arXiv)

2 T. Yamashita et al., "Cost-alleviative learning for deep convolutional neural network-based facial part labeling," IPSJ Transactions on Computer Vision and Applications, vol. 7, pp. 99-103, 2015. (DOI)

You can’t perform that action at this time.