Available online at www.ijournalse.org Emerging Science Journal Vol. 4, Special Issue "IoT, IoV, and Blockchain", (2020, 2021) Page | 167 Fingerprint Database Enhancement by Applying Interpolation and Regression Techniques for IoT-based Indoor Localization Dwi Joko Suroso 1 , Farid Yuli Martin Adiyatma 2 , Panarat Cherntanomwong 1* , Pitikhate Sooraksa 1 1 School of Engineering, King Mongkut’s Institute of Technology Ladkrabang, 1, Soi Chalongkrung 1, Bangkok 10520, Thailand 2 Department of Nuclear Engineering and Engineering Physics, Universitas Gadjah Mada, Jl. Grafika No. 2, Yogyakarta 55281, Indonesia Abstract Most applied indoor localization is based on distance and fingerprint techniques. The distance-based technique converts specific parameters to a distance, while the fingerprint technique stores parameters as the fingerprint database. The widely used Internet of Things (IoT) technologies, e.g., Wi-Fi and ZigBee, provide the localization parameters, i.e., received signal strength indicator (RSSI). The fingerprint technique advantages over the distance-based method as it straightforwardly uses the parameter and has better accuracy. However, the burden in database reconstruction in terms of complexity and cost is the disadvantage of this technique. Some solutions, i.e., interpolation, image-based method, machine learning (ML)-based, have been proposed to enhance the fingerprint methods. The limitations are complex and evaluated only in a single environment or simulation. This paper proposes applying classical interpolation and regression to create the synthetic fingerprint database using only a relatively sparse RSSI dataset. We use bilinear and polynomial interpolation and polynomial regression techniques to create the synthetic database and apply our methods to the 2D and 3D environments. We obtain an accuracy improvement of 0.2m for 2D and 0.13m for 3D by applying the synthetic database. Adding the synthetic database can tackle the sparsity issues, and the offline fingerprint database construction will be less burden. Keywords: Indoor Localization; Internet of Things; Zigbee; Fingerprint Technique; Fingerprint Database; Interpolation; Regression; Polynomial. Article History: Received: 09 September 2021 Revised: 31 December 2021 Accepted: 05 January 2022 Published: 16 January 2022 1- Introduction Internet of Things (IoT) technology advancement has been flourishing in the last decades [1, 2]. Its implementation cannot be excluded from our everyday life. One of the features that are frequently used is positioning. As the well- established global positioning system (GPS) is most used for positioning, especially in the outdoor environment, it fails to give the proper accuracy positioning in the indoor environment [3, 4]. Therefore, some IoT-based technologies, i.e., Wi-Fi [5, 6], ZigBee [7], Bluetooth Low Energy (BLE) [8], Ultra-wideband (UWB) [4, 9], Radio Frequency Identification (RFID) [10], can be applied for Indoor Positioning Systems (IPS) instead of GPS's utilization indoor [5]. More commonly stated as indoor localization, IPS can be achieved by applying the technologies mentioned above and specific methods or techniques. Wireless sensor networks (WSNs), also based on IoT technology, are known as one of the most used for indoor localization implementation [4, 11, 12]. This paper considers the low-cost and straightforward implementation of WSNs- based indoor localization using the ZigBee standard [13]. Compared to other technologies such as Wi-Fi, the ZigBee can have a more flexible setup and deployment of the WSNs system. On the other hand, indoor localization techniques include algorithms to identify the target's location based on several signal properties based on the technologies offered. * CONTACT: panarat.ch@kmitl.ac.th DOI: http://dx.doi.org/10.28991/esj-2021-SP1-012 © 2020 by the authors. Licensee ESJ, Italy. This is an open access article under the terms and conditions of the Creative Commons Attribution (CC-BY) license (https://creativecommons.org/licenses/by/4.0/).