Abstract:The performance of an Artificial Neural Network (ANN)-based algorithm is subject to the way the feature data is extracted. This is a common issue when applying the ANN to indoor fingerprinting-based localization where the signal is unstable. To date, there is not adequate feature extraction method that can significantly mitigate the influence of the receiver signal strength indicator (RSSI) variation that degrades the performance of the ANN-based indoor fingerprinting algorithm. In this work, a wavelet scatter… Show more
“…It is surprising that the RMSE of an RSS-based indoor positioning system could achieve sub-metre level accuracy. The second best is Soro and Lee (2018) which uses multiple ANNs to achieve RMSE of 1.39 m. The mean RMSE of all covered papers is 4.18 m.…”
Section: Performance Comparisons Of Systems Employing Deep Learning As a Feature Extraction Methodsmentioning
confidence: 99%
“…Though it is not common for indoor positioning systems to achieve sub-metre level accuracy only using WiFi RSS, certain systems could still get very astonishing results by carefully modified models, for example Belmonte-Hernández et al (2019), Own et al (2019), G. Zhang et al (2019, Xue et al (2020), Hoang et al (2019, Soro and Lee (2019) and D. V. Nguyen et al (2018). The results of these systems are summarised in Table 3.…”
Section: Performance Comparisons Of Systems Employing Deep Learning As a Feature Extraction Methodsmentioning
One of the most popular approaches for indoor positioning is WiFi fingerprinting, which has been intrinsically tackled as a traditional machine learning problem since the beginning, to achieve a few metres of accuracy on average. In recent years, deep learning has emerged as an alternative approach, with a large number of publications reporting sub-metre positioning accuracy. Therefore, this survey presents a timely, comprehensive review of the most interesting deep learning methods being used for WiFi fingerprinting. In doing so, we aim to identify the most efficient neural networks, under a variety of positioning evaluation metrics for different readers. We will demonstrate that despite the new emerging WiFi signal measures (i.e. CSI and RTT), RSS produces competitive performances under deep learning. We will also show that simple neural networks outperform more complex ones in certain environments.
“…It is surprising that the RMSE of an RSS-based indoor positioning system could achieve sub-metre level accuracy. The second best is Soro and Lee (2018) which uses multiple ANNs to achieve RMSE of 1.39 m. The mean RMSE of all covered papers is 4.18 m.…”
Section: Performance Comparisons Of Systems Employing Deep Learning As a Feature Extraction Methodsmentioning
confidence: 99%
“…Though it is not common for indoor positioning systems to achieve sub-metre level accuracy only using WiFi RSS, certain systems could still get very astonishing results by carefully modified models, for example Belmonte-Hernández et al (2019), Own et al (2019), G. Zhang et al (2019, Xue et al (2020), Hoang et al (2019, Soro and Lee (2019) and D. V. Nguyen et al (2018). The results of these systems are summarised in Table 3.…”
Section: Performance Comparisons Of Systems Employing Deep Learning As a Feature Extraction Methodsmentioning
One of the most popular approaches for indoor positioning is WiFi fingerprinting, which has been intrinsically tackled as a traditional machine learning problem since the beginning, to achieve a few metres of accuracy on average. In recent years, deep learning has emerged as an alternative approach, with a large number of publications reporting sub-metre positioning accuracy. Therefore, this survey presents a timely, comprehensive review of the most interesting deep learning methods being used for WiFi fingerprinting. In doing so, we aim to identify the most efficient neural networks, under a variety of positioning evaluation metrics for different readers. We will demonstrate that despite the new emerging WiFi signal measures (i.e. CSI and RTT), RSS produces competitive performances under deep learning. We will also show that simple neural networks outperform more complex ones in certain environments.
“…T1 is the location error using one mapping route, T2 and T3 are the location error using five and ten routes respectively. To evaluate the quality of the constructed radio map, two online localization experiments were implemented by using the weighted K-nearest neighbor (KNN) approach [44] and Deep neural network (DNN) approach [45], respectively. The number of used mapping routes (for constructing radio map) was taken as a variable for the two experiments.…”
Section: Performance Of Radio Map Constructionmentioning
Low cost and high reproducible is a key issue for sustainable location-based services. Currently, Wi-Fi fingerprinting based indoor positioning technology has been widely used in various applications due to the advantage of existing wireless network infrastructures and high positioning accuracy. However, the collection and construction of signal radio map (a basis for Wi-Fi fingerprinting-based localization) is a labor-intensive and time-cost work, which limit their practical and sustainable use. In this study, an indoor signal mapping approach is proposed, which extracts fingerprints from unknown signal mapping routes to construct the radio map. This approach employs special indoor spatial structures (termed as structure landmarks) to estimate the location of fingerprints extracted from mapping routes. A learning-based classification model is designed to recognize the structure landmarks along a mapping route based on visual and inertial data. A landmark-based map matching algorithm is also developed to attach the recognized landmarks to a map and to recover the location of the mapping route without knowing its initial location. Experiment results showed that the accuracy of landmark recognition model is higher than 90%. The average matching accuracy and location error of signal mapping routes is 96% and 1.2 m, respectively. By using the constructed signal radio map, the indoor localization error of two algorithms can reach an accuracy of 1.6 m.
“…The foundation of a WSN, the wavelet scattering transform, is itself an effective instrument in feature extraction due to its provision of translation invariance, stability, and the ability to linearize small diffeomorphisms that result from its layered architecture of scattering wavelets. It is even used as a preprocessing measure wherein a WSN performs preliminary feature extraction prior to the training of a deep neural network (DNN) for localization [ 30 ]. The freedom of choosing an appropriate kernel of a linear transform has been exploited fully, which is generally known as the adaptive wavelet transform [ 31 ].…”
Section: Introductionmentioning
confidence: 99%
“…A wavelet scattering transform was used to extract reliable features that are stable to small deformation and are rotation-invariant when applying an artificial neural network (ANN) to indoor fingerprinting-based localization, where the signal is inherently unstable [ 30 ]. The extracted features were used by a DNN model to predict the location.…”
The need to classify targets and features in high-resolution imagery is of interest in applications such as detection of landmines in ground penetrating radar and tumors in medical ultrasound images. Convolutional neural networks (CNNs) trained using extensive datasets are being investigated recently. However, large CNNs and wavelet scattering networks (WSNs), which share similar properties, have extensive memory requirements and are not readily extendable to other datasets and architectures—and especially in the context of adaptive and online learning. In this paper, we quantitatively study several quantization schemes on WSNs designed for target classification using X-band synthetic aperture radar (SAR) data and investigate their robustness to low signal-to-noise ratio (SNR) levels. A detailed study was conducted on the tradeoffs involved between the various quantization schemes and the means of maximizing classification performance for each case. Thus, the WSN-based quantization studies performed in this investigation provide a good benchmark and important guidance for the design of quantized neural networks architectures for target classification.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.