A fingerprint technique for indoor localization using autoencoder based semi-supervised deep extreme learning machine
- Submitting institution
-
University of East London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 18
- Type
- D - Journal article
- DOI
-
10.1016/j.sigpro.2020.107915
- Title of journal
- Signal Processing
- Article number
- 107915
- First page
- -
- Volume
- 181
- Issue
- -
- ISSN
- 0165-1684
- Open access status
- Compliant
- Month of publication
- -
- Year of publication
- 2020
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
1 - Intelligent Systems
- Citation count
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work is significant because it introduces a semi-supervised method for indoor localization, therefore, the privacy level of the participants in the proposed crowd-sensing process increases dramatically. After this work, a core has been formed at Cognitive Telecommunication Research Group, and several BSc, MSc and PhD students (Amir Mahdi Sazdar, Nasim Alikhani, Parisa Fard Moshiri, Hojjat Navidan, Manoosh Samiei) start to work on different aspects of fingerprinting based indoor localization such as privacy and the application of deep-learning algorithms and several journal and conference papers (10.1109/ACCESS.2019.2932024, 10.1016/j.jisa.2020.102515, 10.1007/s12083-020-00950-1, 10.1109/LSENS.2020.2971555, 10.1504/IJSNET.2020.104459, 10.1145/3341162.3349300, 10.1007/s11277-020-07636-0) were published based on this paper.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -