KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 10 of 15

Some of the metrics are blocked by your
consent settings
C-MEL: Consensus-Based Multiple Ensemble Learning for Indoor Device-Free Localization Through Fingerprinting
(2024-01-01)
Suroso, Dwi Joko
;
Adiyatma, Farid Yuli Martin
The rise of location-aware services is enhancing the effectiveness of our daily tasks, especially within indoor environments where most activities take place. Wireless indoor localization systems are the predominant method for estimating locations indoors. These systems utilize two primary approaches: device-based and device-free. Device-based techniques are attracting considerable research attention due to their ability to offer highly accurate localization in most scenarios. Conversely, device-free techniques are increasingly popular because they can determine a target's location without the target carrying a device. This capability makes them suitable for certain applications such as elderly monitoring and intruder tracking. The most popular technique for both approaches is fingerprinting, which uses the uniqueness of spatial information to predict a target's location. This spatial information is stored in a fingerprint database, containing locations and their associated parameters. However, in device-free methods, the fingerprint technique encounters challenges in accurately recognizing the complexity of each parameter combination pattern, thus impacting the accuracy of the estimation. To overcome this issue, we introduce a novel indoor device-free localization (IDFL) pattern matching algorithm named Consensus-based Multiple Ensemble Learning (C-MEL). This algorithm incorporates consensus strategies, i.e., majority voting and average strategy, to integrate outputs from various ensemble learning algorithms, such as Random Forest, Gradient Boosting, XGBoost, and LightGBM. We validate our algorithm in an 18 m2 office space featuring stainless steel partitions, tables, chairs, and cabinets. Experimental results show that C-MEL using the average strategy (C-MEL-AV) enhances accuracy by up to 44.51%, 11.26%, and 37.85%, while C-MEL with majority voting (C-MEL-MV) improves by up to 40.56%, 4.95%, and 33.44% compared to Decision Tree, Gradient Boosting, and 1D CNN-BLSTM, respectively. Based on these results, C-MEL-AV emerges as a reliable approach for accurate IDFL based on the fingerprint technique, while C-MEL-MV remains a viable alternative for IDFL systems.
Some of the metrics are blocked by your
consent settings
Implementation of Wi-Fi-based indoor positioning system: Challenges and future possibilities
(2023-11-20)
Suroso, Dwi Joko
;
Adiyatma, Farid Yuli Martin
;
Cherntanomwong, Panarat
;
Sooraksa, Pitikhate
Radiofrequency (RF)-based technologies are utilized as the core of indoor positioning system (IPS), i.e., Wi-Fi, Bluetooth, radio frequency identification (RFID), ultrawideband (UWB), and ZigBee standard. Wi-Fi is the most promising technology because of its wide availability on any smart or personal device and comes at a relatively low cost. Considering Wi-Fi technology as the core of IPS, there are several challenges related to positioning performance in its research and implementation. Nowadays, most real applications and implementations of Wi-Fi-based indoor positioning use the received power signal, the received signal strength indicator (RSSI). The position and time accuracy can determine the IPS system's performance. In the actual implementation, we must consider the specific position at that specific time (real-time system). From some references on IPS systems, most research is likely divided into two types; the algorithm development is somehow not a real-time implementation and proposal to implement in an actual application. This paper aims to study the real implementation of Wi-Fi-based IPS development, its recent advances, methods, performance requirements, challenges, and limitations, and, finally, offer the possibility for the prospective IPS research topics. Some future possibilities include the signal optimization algorithm, the new method with artificial intelligence, machine, or deep learning for Wi-Fi-based device-free IPS.
Some of the metrics are blocked by your
consent settings
3D range-based indoor localization by using only two beacons
(2023-05-22)
Suroso, Dwi Joko
;
Krisnawan, Aditya Bagus
;
Sooraksa, Pitikhate
;
Cherntanomwong, Panarat
Indoor localization has been active research in the past decade. The lack of a general model and the demand for high accuracy push the research forward. Some researchers have proposed unique variations and combinations to answer the challenges from the technologies to techniques. Some publications considered the low-cost equipment to the simple algorithm or model to the advanced, robust, and sophisticated system. Almost all of them use the two basics technique; range-based and range-free techniques. Each technique has advantages and disadvantages, including how the technique can efficiently handle the indoor multipath propagation effects. Most of the papers published are also considered the same room or single room indoor environment as the indoor localization system measurement campaign. This paper proposes a three-dimensional (3D) indoor localization for multi-story buildings using simple technology and technique and using only two beacons. We utilized the received signal strength indicator (RSSI) from ESP8266 based on the Wireless-Fidelity (Wi-Fi) standard as the localization parameter. We employ the range-based technique of min-max and least-square. We also compare both techniques to observe which one is suitable for the multi-story building implementation. We also emphasized the challenge of using only two beacons as our contribution. Our system performance results show that the mean error accuracy for min-max is 1.93m, while the least-square yields the mean error of 5.48m. The minimum error of min-max and least-square are 0.33m and 0.77m, respectively. The maximum error of least-square can reach more than 10m, while the min-max gives the maximum error of 4.38m. The results prove that RSSI-based min-max can be applied in a particular condition using only two beacons in the multi-story building.
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
Fingerprint-based Indoor Localization via Deep Learning
(2023-03-24)
Suroso, Dwi Joko
;
Cherntanomwong, Panarat
;
Sooraksa, Pitikhate
Deep learning (DL) application is proven helpful in a vast research field. One recent trend is to employ DL in radio frequency (RF)-based indoor localization. The fingerprint technique is the most used indoor localization technique known for its accuracy and performance. However, the fingerprint technique pays a high cost and effort in offline database construction, while its performance solely depends on the database density. Moreover, to apply deep learning, we also need a large dataset for it to learn efficiently. We propose to implement a DL-based fingerprint technique to tackle both problems of dataset scarcity and localization performance. We propose the DL's discriminative model, i.e., multilayer perceptron (MLP), for classification tasks. For the fingerprint database augmentation, we employed the generative model, i.e., Generative adversarial networks (GANs). We considered using a received signal strength indicator (RSSI) from a measurement campaign based on Wi-Fi devices for the database. The total area of interest is 25 m<sup>2</sup> inside the typical classroom environment, and we consider the 25 fingerprint locations as labels. We have a dataset of 1,250 rows x 8 columns (from 8 reference points). From the results, by using only 50% of actual data combined with the 125 synthetic data, we can improve the accuracy by more than 200% compared to only using 50% of actual data and show a 60% improvement in the loss. The combination of 100% actual data and 125 synthetic data gives the best accuracy and loss performance of 0.76 and 0.85, respectively. It gives an improvement of 144% in accuracy and 200% loss performance. By implementing deep learning for fingerprint techniques for data augmentation and classification, we can achieve good performance and reduce the workload of fingerprint database construction.
Some of the metrics are blocked by your
consent settings
Synthesis of a Small Fingerprint Database through a Deep Generative Model for Indoor Localisation
(2023-01-01)
Suroso, Dwi Joko
;
Cherntanomwong, Panarat
;
Sooraksa, Pitikhate
In deep learning (DL), the deep generative model is helpful for data augmentation objectives to tackle the lack of datasets that have a significant impact on learning performance. Data augmentation or synthesis is expected to solve the issue in a small/sparse database. The problem of databasing also exists in the fingerprint-based indoor localisation system. The dense offline fingerprint database must be constructed with the accuracy requirement. However, this will affect the high cost, massive laborious work, and increase the complexity of the system. Therefore, this paper proposes to address these issues by generating synthetic data via a deep generative model. The generative adversarial network (GAN) is selected to generate the synthetic fingerprint database for indoor localisation. Our database consideration consists of power-based parameters, i.e., the received signal strength indicator (RSSI) from Wi-Fi devices obtained from the actual measurement campaign. Some of the literature mainly discusses how GAN works in a vast and complex dataset. Here, we consider applying GAN in a relatively small dataset and for a simple setup. Our results show that by only using the 20 % fraction of actual RSSI data combined with the synthetic RSSI, the accuracy validation performance is slightly higher than when using all actual data usage. Moreover, in only 60 % of actual data usage and in combination with 625 samples of synthetic data, the accuracy performance is improved to 0.73 (1.37 times higher than the use of all actual data, 0.53). Thus, this result proves that the challenges of offline fingerprint databases can be alleviated by data synthesis through GAN by using only a small dataset.
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
Machine Learning-Based Multi-Room Indoor Localization Using Fingerprint Technique
(2023-01-01)
Adiyatma, Farid Yuli Martin
;
Suroso, Dwi Joko
;
Cherntanomwong, Panarat
Nowadays, developing Wi-Fi-based indoor localization systems has become an attractive research topic due to the growing need for pervasive location determination. The fingerprint technique offers higher positioning accuracy in indoor localization than the distance-based technique. Fingerprint-based techniques via machine learning have been proposed for many years to provide high-accuracy indoor localization services. These works attempt to establish the optimal correlation between the user fingerprint and a pre-defined set of grid points on a radio map. In this paper, a comparative analysis of selected machine learning algorithms is conducted within the context of online phase fingerprint techniques for localization, focusing on implementation in a multi-room case. The experiment involves measurements using a Wi-Fi module in a laboratory, an aisle, a lobby, and a typical classroom, resulting in a small-sized fingerprint database covering a total area of 573.71 m2. The results reveal that Naïve Bayes (NB) obtains the highest localization accuracy in the laboratory and classroom. Meanwhile, Support Vector Machine (SVM) outperforms other algorithms in the aisle, while K-Nearest Neighbor (KNN) delivers the best accuracy in the lobby. In summary, NB, KNN, and SVM are suitable pattern-matching algorithms for multi-room indoor localization and relatively small fingerprint databases.
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
Is Deep Diffusion Probabilistic Model Applicable for Fingerprint-based Indoor Localization?
(2022-01-01)
Suroso, Dwi Joko
;
Sooraksa, Pitikhate
;
Cherntanomwong, Panarat
The latest deep learning (DL) phenomenon is the Denoising Diffusion Model (DDM). DDM is in a class of latent variable models of the deep generative model (DGM) along with the big name of Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs). Moreover, in a recent finding, DDM beats GANs in image synthesis. This paper presents the prospective applicability discussion of DDM for indoor localization research as previous models, e.g., GANs and VAEs, which are successfully implemented. Here, we focus more on how DDM can synthesize localization parameters with the help of fingerprinting technique's database enhancement. The fingerprint technique needs a preconstructed database which has the main drawbacks of its cost, time inefficient, and high complexity. We found valuable works of literature on this specific topic for GANs and VAEs. However, there are few DDM applications for discrete data types, and as the authors' concern, there is no attempt to apply them to indoor localization yet. DDM implementation is to generate continuous data domains, e.g., image, text, and audio data. A radio map or fingerprint database is essentially needed for fingerprint-based indoor localization. Learning this database pattern helps increase the system's performance. Obtaining a high-density and quality database is expensive and challenging to implement. Then, it raises a question, is DDM applicable for synthesizing this database and alleviating this problem?

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results