KMITL

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

Browse

Search Results

Now showing 1 - 6 of 6

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 m2 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
A comparison of decision tree based techniques for indoor positioning system
(2018-04-19)
Chanama, Lummanee
;
Wongwirat, Olarn
Currently, an indoor positioning system based on a fingerprint technique for wireless networks under IEEE 802.11 standard uses a method to collect a received signal strengths (RSS) to create a radio map in an offline phase. Then, it detects the RSS in an online phase to compare and find the position. However, while detecting and gathering the RSS, there are some variations of the RSS that affect the accuracy of position estimation. Therefore, there are several methods used to estimate the position in order to improve the accuracy, but the one focused in this paper is a decision tree based classification. The decision tree based classification method is found that it can provide better improvement in accuracy than the others, e.g., K-Nearest Neighbor (K-NN), Bayesian, and Neural networks. However, the techniques used to construct the decision tree are varied depending on the algorithm used to implement. Therefore, this paper is a comparison of decision tree based techniques using typical decision tree (DT) and Gradient boosted tree algorithms for estimating the position indoor. In the study, the RSSs collected from access points in the experimental area are used as the training and testing data. The decision tree models are created by using typical DT and Gradient boosted algorithms based on the training data obtained. There are two factors to consider in the comparative study, i.e., the number of training data and the number of reference radio signals. The testing results from the experiment showed that the decision tree based on Gradient boosted algorithm yielded more accurate results than typical DT, where the amount of 19 reference radio signals and 50 samples of training data gave the best result.
Some of the metrics are blocked by your
consent settings
Soft-clustering technique for fingerprint-based localization
(2018-01-01)
Cherntanomwong, Panarat
;
Sooraksa, Pitikhate
In this paper, the soft-clustering algorithm for the fingerprint-based localization technique is proposed. In an indoor environment, the fingerprint-based localization technique is usually employed since it can deal with signal fluctuation. Its basic principle is to find the target location by comparing its signal parameters with a previously recorded database of knownlocation- signal parameters. Here, the received signal strength indicator (RSSI) provided by the wireless sensor network (WSN) is used as the signal parameter. The high accuracy of location estimation requires a very fine spatial resolution of the database, corresponding to the time consumed for pattern matching. To reduce the calculation time, clustering can be applied because it can reduce the database size by grouping similar data in the same cluster. The accuracy of the algorithm to cluster the target location and fingerprint locations is the main concern. The result shows that the clustering technique used can successfully cluster the target sensing node into an appropriate cluster. This implies that, by using soft clustering with the fingerprint technique, the target location can be estimated faster than by using classical fingerprint techniques since the target location can be estimated within a small set of fingerprints in the cluster, not with all fingerprints in the database.
Some of the metrics are blocked by your
consent settings
Indoor localization system based on fingerprint technique using RFID passive tag
(2013-09-02)
Phimmasean, Sisongkham
;
Chuenurajit, Thanapong
;
Cherntonomwong, Panarat
Radio Frequency Identification (RFID) technology is one of emerging technologies in which many countries in the world pay attention to. Many applications of localization use RFID technology. In the present date, there are many papers of localization reviewed. However, indoor localization system for real applications is still limited. This research proposes indoor localization system using fingerprint technique to find the estimated location of the target. This technique is compared its signal (or ID information) pattern with a previously recorded database of known signal (or ID information)-location data. The Dot Product is applied as the pattern matching method. The maximum and 2nd maximum values of the dot product are considered. The fingerprint locations providing the maximum and 2nd maximum values of the dot product are averaged. This average location is referred to as the location of the target. The average error distance is approximately 75 cm. This result shows a good estimation results since the error of the target estimation are not more than the gap between two fingerprint locations (120 cm). From the result, we can conclude that our proposed method can be applied in the real situation and application. © 2013 IEEE.
Some of the metrics are blocked by your
consent settings
Signal subspace interpolation from discrete measurement samples In constructing a database for location fingerprint technique
(2009-01-01)
Cherntanomwong, Panarat
;
Takada, Jun Ichi
;
Tsuji, Hiroyuki
In this paper, a method of the signal subspace interpolation to constructing a continuous fingerprint database for radio localization is proposed. When using the fingerprint technique, enhancing the accuracy of location estimation requires very fine spatial resolution of the database, which entails much time in collecting the data to build up the database. Interpolated signal subspace is presented to achieve a fine spatial resolution of the fingerprint database. The angle of arrival (AOA) and the measured signal subspace at known locations are needed to obtain the interpolated signal subspaces. The effectiveness of this method is verified by an outdoor experiment and the estimated location using this method was compared with those using the geometrically calculated fingerprint and the measured signal subspace fingerprint techniques. Copyright © 2009 The Institute of Electronics, Information and Communication Engineers.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results