SRCLoc: Synthetic Radio Map Construction Method for Fingerprinting Outdoor Localization in Hybrid Networks

Getaneh Berie Tarekegn, Rong Terng Juang, Hsin Piao Lin, Li Chia Tai, Yirga Yayeh Munaye, Mekuanint Agegnehu Bitew

Research output: Contribution to journalArticlepeer-review


A precise localization system is a key enabling technology for Internet of Things (IoT) applications and location-based services. Fingerprint-based localization methods are well-known and widely used solutions. These methods, however, are time-consuming and laborious for radio map construction during an offline site survey in large-scale applications. In this article, we presented a novel semi-supervised deep convolutional generative adversarial network-based radio map construction method for real-time device localization. The proposed synthetic radio map construction method for fingerprinting outdoor localization (SRCLoc) combined the hybrid support vector machine and deep gated recurrent unit algorithms sequentially. The SRCLoc reduced the workload of site surveying required to build the fingerprint database by up to 85.7%. The results show that the average positioning error of SRCLoc is less than 39 cm, and more than 90% of the errors are less than 82 cm. That is, numerical results proved that, in comparison to traditional methods, the proposed SRCLoc method can significantly improve positioning performance and reduce radio map construction costs.

Original languageEnglish
Pages (from-to)1
Number of pages1
JournalIEEE Sensors Journal
StateAccepted/In press - 2022


  • Feature extraction
  • fingerprint positioning
  • Fingerprint recognition
  • Gated recurrent network
  • generative adversarial network
  • Location awareness
  • Logic gates
  • radio signal
  • Sensors
  • support vector machine
  • Support vector machines
  • Wireless LAN


Dive into the research topics of 'SRCLoc: Synthetic Radio Map Construction Method for Fingerprinting Outdoor Localization in Hybrid Networks'. Together they form a unique fingerprint.

Cite this