Cherntanomwong, Panarat

Loading...
Thumbnail Image
Preferred name
Cherntanomwong, Panarat
Main Affiliation
Email
panarat.ch@kmitl.ac.th

Settings

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    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.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Dynamic Ensemble Learning With Received Signal Strength Transformation for Robust Multi-Floor Wi-Fi Indoor Localization
    (2026-01-01)
    Yuli Martin Adiyatma, Farid
    ;
    Cherntanomwong, Panarat
    ;
    Joko Suroso, Dwi
    Received Signal Strength (RSS)-based Wi-Fi localization offers a cost-effective solution for multi-floor indoor location estimation. However, its accuracy is often degraded by signal fading, multipath propagation, and device heterogeneity, posing major challenges to reliable localization. Recent studies have increasingly employed deep neural networks due to their ability to extract meaningful patterns from RSS data; however, these models require substantial computational resources and extensive parameter tuning, which limits their adaptability across diverse dynamic environments. To address these limitations, we propose DELLoc-RT, a localization framework integrating Dynamic Ensemble Learning (DELLoc) with RSS Transformation (RT) for accurate, efficient, and adaptable multi-floor indoor localization. The RT module applies Sigmoid-scaled normalization and confidence weighting to convert RSS values into compact, learnable features. DELLoc employs multiple base learners optimized via the Tree-structured Parzen Estimator with a pruning strategy (TPE-PS) that accelerates convergence by focusing on promising configurations. Additionally, Iterative Ensemble Optimization with Stepwise Selection (IEO-SS) selects complementary learners to enhance overall performance. Experimental results demonstrate that DELLoc-RT achieves floor classification accuracies of 93.32%, 94.38%, and 94.02% on the UJIIndoorLoc, UTSIndoorLoc, and Tampere datasets, respectively, with mean Euclidean errors (MEE) of 10.63 m, 7.87 m, and 8.19 m. These results highlight the model’s strong adaptability across diverse datasets. Evaluation on a self-constructed dataset further confirms that DELLoc-RT delivers high accuracy and efficiency while substantially reducing the need for manual tuning, enabling rapid deployment in practical scenarios.