Cherntanomwong, Panarat

Preferred name

Main Affiliation

School of Engineering

panarat.ch@kmitl.ac.th

Now showing 1 - 6 of 6

Some of the metrics are blocked by your
consent settings
Deep Generative Model-based RSSI Synthesis for Indoor Localization
(2022-01-01)
Suroso, Dwi Joko
;
Cherntanomwong, Panarat
;
Sooraksa, Pitikhate
Indoor localization via deep learning (DL) is attracting researchers' attention. DL is mainly used for fingerprinting-based indoor localization as it generally employs a vast offline database to ensure its reliability. However, the long effort and high cost of constructing this database are the disadvantages of this technique. This paper implements variational autoencoders (VAE), one of the popular deep generative models, to alleviate the drawbacks of offline database issues. Our proposal works using the received signal strength indicator (RSSI); unfortunately, it is known for its fluctuation and instability. Thus, instead of using RSSI directly as a localization parameter, we learn its distribution via VAE to generate the synthetic RSSI values. We utilized the RSSI from an actual measurement campaign. The VAE implementation results show that we can obtain the RSSI synthesis by exploring the latent distribution learned from the input distribution. Thus, the offline database density grids can be enhanced. We validated the results by varying epochs to map the learned latent distribution. However, we still have relatively low accuracy in the synthetic RSSI values, especially when applying a small number of epochs, i.e., 10 and 100. When we applied epoch number 1000, the error was relatively low (-3dBm average error) in the sampled position. Our preliminary assumption is that the dataset is small for VAE learning, and probably the 3-by-3 RSSI-to-image size assumption could still be inadequate.
Some of the metrics are blocked by your
consent settings
Fingerprint Database Enhancement using Spatial Interpolation for IoT-based Indoor Localization
(2022-01-01)
Martin Adiyatma, Farid Yuli
;
Joko Suroso, Dwi
;
Cherntanomwong, Panarat
The widespread adoption of the internet of things (IoT) drives indoor location-based service (ILBS) applications forward. The core parameter of ILBS is indoor localization. Generally, indoor localization is divided into two techniques, distance-based, i.e., triangulation, and distance-free, i.e., fingerprint technique. This paper discusses the fingerprint technique because of some advantages, i.e., higher accuracy performance compared to the distance-based technique. However, the fingerprint technique has drawbacks in offline database construction: extraordinarily time-consuming and labor-intensive, which hinders its application in the real world. Furthermore, the fingerprint database needs to be updated regularly in a dynamic environment. Therefore, we propose fingerprint database enhancement based on various spatial interpolations to tackle the issues of fingerprint database construction. We apply Inverse Distance Weighted (IDW), Quadratic Spline, Cubic Spline, and Ordinary Kriging Interpolation methods to generate the synthetic database. We have conducted a measurement campaign to obtain Received Signal Strength Indicator (RSSI) as the fingerprint-based localization parameter. From our results, the interpolation methods show that the generated synthetic RSSI can provide a lower prediction error. Our proposed methods can have similar accuracy performance compared to manual fingerprints using actual data. Moreover, the synthetic RSSI data has a 0 dBm error for the best prediction and not more than 6 dBm for the worst prediction. Thus, we conclude that our proposed methods can enhance the fingerprint database and have proven to increase localization performance.
Some of the metrics are blocked by your
consent settings
Distance-based indoor localization system utilizing general path loss model and RSSI
(2020-11-01)
Suroso, Dwi Joko
;
Arifin, Muhammad
;
Cherntanomwong, Panarat
Wireless sensor networks (WSNs) have a vital role in indoor localization development. As today, there are more demands in location-based service (LBS), mainly indoor environments, which put the researches on indoor localization massive attention. As the global-positioning-system (GPS) is unreliable indoor, some methods in WSNs-based indoor localization have been developed. Path loss model-based can be useful for providing the power-distance relationship the distance-based indoor localization. Received signal strength indicator (RSSI) has been commonly utilized and proven to be a reliable yet straightforward metric in the distance-based method. We face issues related to the complexity of indoor localization to be deployed in a real situation. Hence, it motivates us to propose a simple yet having acceptable accuracy results. In this research, we applied the standard distance-based methods, which are is trilateration and min-max or bounding box algorithm. We used the RSSI values as the localization parameter from the ZigBee standard. We utilized the general path loss model to estimate the traveling distance between the transmitter (TX) and receiver (RX) based on the RSSI values. We conducted measurements in a simple indoor lobby environment to validate the performance of our proposed localization system. The results show that the min-max algorithm performs better accuracy compared to the trilateration, which yields an error distance of up to 3m. By these results, we conclude that the distance-based method using ZigBee standard working on 2.4 GHz center frequency can be reliable in the range of 1-3m. This small range is affected by the existence of interference objects (IOs) lead to signal multipath, causing the unreliability of RSSI values. These results can be the first step for building the indoor localization system, which low-cost, low-complexity, and can be applied in many fields, especially indoor robots and small devices in internet-of-things (IoT) world's today.
Some of the metrics are blocked by your
consent settings
Regression-based Path Loss Model Correction to Construct Fingerprint Database for Indoor Localization
(2023-03-24)
Adiyatma, Farid Yuli Martin
;
Suroso, Dwi Joko
;
Cherntanomwong, Panarat
The fingerprint-based indoor localization has been widely used due to its simple hardware setup and high positioning accuracy, especially using Received Signal Strength Indicator (RSSI). However, the fingerprint database has main drawbacks in database construction, requiring a lot of effort and time. This paper presents an approach for reducing the effort of manual fingerprint database construction for indoor localization using path loss model enhancement via simple regression, i.e., Linear and Polynomial Regression for RSSI-based fingerprint technique. We used the public dataset to evaluate our proposal, which was collected in a small room with low interference using three wireless technologies (Wi-Fi, ZigBee, and Bluetooth Low Energy). The K-nearest neighbors (KNN) is applied to locate the target. We compared the results from the original path loss model (O-PLM), the linear regression-path loss model (LR-PLM), and the polynomial regression path loss model (PR-PLM) with the actual RSSI values to validate our approach. The results showed that the Original Path Loss Model database and the Polynomial Regression Path Loss Model database improved the localization accuracy for Wi-Fi devices. The Linear Regression Path Loss Model can perform well in the ZigBee device case.
Some of the metrics are blocked by your
consent settings
TLB and WC-TLB-MM: The Improved Min-Max Algorithms for Multi Targets Indoor Localization
(2023-01-01)
Adiyatma, Farid Yuli Martin
;
Suroso, Dwi Joko
;
Cherntanomwong, Panarat
Internet of Things (IoT)-based Indoor localization is the most commonly used system to determine target locations indoors. It applies to various purposes, e.g., indoor navigation, asset tracking in warehouse management, and tracking people in hospitals. Distance-based techniques using the Received Signal Strength Indicator (RSSI), e.g., Min-Max, are widely applied because they can be directly implemented without prerequisite work such as site surveys. However, a challenging indoor environment with high numbers of interiors and people can obstruct signal propagation. This obstruction can reduce the accuracy of translating RSSI to distance using the path loss model, which will degrade the localization accuracy. In this paper, we introduce two improved Min-Max (MM) algorithms, i.e., Three Layer Bounding Box Min-Max (TLB-MM) and Weighted Centroid TLB-MM (WC-TLB-MM), to alleviate the issue and achieve higher localization accuracy. The novelty of the proposed TLB-MM is incorporating RSSI error functions to generate three-layer bounding boxes: the inner, middle, and outer in the Min-Max algorithm. Meanwhile, WC-TLB-MM enhanced the TLB-MM algorithm by integrating the Weighted Centroid Localization Algorithm (WCLA) in the calculation process. We validate our proposal by conducting various experiments using Wi-Fi at 2.4 GHz deployed in a laboratory room of 10.17 m ×9.12 m. Experimental results demonstrate that TLB-MM improved the accuracy performance to 55.78% and 30.86%, while WC-TLB-MM gave 40.93% and 7.65% compared to Min-Max and WCLA, respectively. From these results, our proposed methods are proven simple yet applicable to RSSI-based indoor localization systems.
Some of the metrics are blocked by your
consent settings
Indoor Device-free Localization Using Received Signal Strength Indicator and Illuminance Sensor for Random-forest-based Fingerprint Technique
(2021-01-01)
Suroso, Dwi Joko
;
Cherntanomwong, Panarat
;
Sooraksa, Pitikhate
Indoor device-free localization (IDFL) offers more flexibility than conventional indoor localization (device-based) systems, as the targets or objects need not be equipped with any device to be located. In the process of IDFL, the target is passive, enabling applications such as monitoring of elderly people, security systems to detect intruders, and indoor navigation. Despite having more flexibility than device-based systems, IDFL is still inferior in terms of localization performance. The most commonly used technique for IDFL is the fingerprint technique, which uses the uniqueness of spatial information to predict the target's location. The spatial information is a fingerprint database containing information on locations and their corresponding parameters. The most specific parameter for the fingerprint database is the received signal strength indicator (RSSI). RSSI can be obtained directly from many low-cost devices, i.e., Wi-Fi-based devices, without the need to install additional hardware. The fingerprint technique is a two-phase process: The database is constructed in the offline phase, and a matching process to compare the target's current parameter with those in the database is performed in the online phase. We propose fingerprint-technique-based IDFL using RSSI and illumination from an illuminance sensor as the additional parameters of the fingerprint database. Both parameters are recorded by considering two scenarios: An empty room and a person standing in the fingerprint grids. The constructed database is the person-filled room subtracted from the empty room database. We use random forest, one of the machine learning (ML) algorithms, as the pattern-matching algorithm. We evaluate its performance by comparison with two other ML algorithms: K-nearest neighbor (k-NN) and neural networks (NN). The results show that k-NN has better accuracy than the random forest for learning and testing in terms of the root mean square error (RMSE). On the other hand, the random forest has better accuracy than NN and better precision than either k-NN or NN for learning and testing in terms of the standard deviation (STD). The results show the possibility of improving the IDFL performance by adding more parameters to the fingerprint database and using an ML-based pattern-matching algorithm.

Cherntanomwong, Panarat

Filters

Settings

Sort By

Results per page