Abstract
During the training phase of the supervised learning, it is not feasible to collect all the datasets of labelled data in an outdoor environment for the localization problem. The semi-supervised transfer learning is consequently used to pre-train a small number of labelled data from the source domain to generate a kernel knowledge for the target domain. The kernel knowledge is transferred to a target domain to transfer some unlabelled data into the virtual labelled data. In this paper, we have proposed a new outdoor localization scheme using a semi-supervised transfer learning for LoRaWANs. In the proposed localization algorithm, a grid segmentation concept is proposed so as to generate a number of virtual labelled data through learning by constructing the relationship of labelled and unlabelled data. The labelled-unlabelled data relationship is repeatedly fine-tuned by correctly adding some more virtual labelled data. Basically, the more the virtual labelled data are added, the higher the location accuracy will be obtained. In the real implementation, three types of signal features, RSSI, SNR, and timestamps, are used for training to improve the location accuracy. The experimental results illustrate that the proposed scheme can improve the location accuracy and reduce the localization error as opposed to the existing outdoor localization schemes.
Highlights
The location-based service (LBS) technology is very useful in many IoT-based locationaware applications [1,2,3,4,5,6]
Some localization results are reported for long-range IoT networks or LoRaWANs [2,3,4,5,6,13,14] by only using one or more signal parameters, such as received signal strength indicator (RSSI), time different of arrival (TDOA), etc
The regression models can achieve around 77% accuracy and 46 m location error, and the machine learning models can achieve around 81.12% accuracy and 41.5 m location error—while, in the indoor environments, the regression models can achieve around 83.25% accuracy and 13.5 m location error, and the machine learning models can achieve around 87% accuracy and 11.78 m location error
Summary
The location-based service (LBS) technology is very useful in many IoT-based locationaware applications [1,2,3,4,5,6]. The LBS has already been widely provided, such as navigation, location-based communication, and location-based data collection. The LoRaWANs technology [3] has the advantages of the long-distance, low-cost, and low-power characteristics of LPWA (Low Power Wide Area) networks. GPS-free localization technique is an innovative way to provide the location information for the low-cost location-aware applications in the rural and urban outdoor environment. LoRa [3,4] is one of the LPWA communication technologies which uses the chirp spread spectrum modulation (CSS) to support long distance communication with low power consumption. These characteristics provide an alternate way to support localization in the outdoor environment. When the LoRa packet from an end-node device is picked up by three or more gateways, the received signal strength indicator (RSSI) and the time different of arrival (TDOA) collected in LoRa gateways [5] can be used for localization
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
