Location Fingerprinting Research Articles

EXPERIMENTAL EVALUATION OF MACHINE LEARNING ALGORITHMS FOR FINGERPRINTING INDOOR LOCALIZATION

One of the most preferred range-free indoor localization methods is the location fingerprinting. In the fingerprinting localization phase machine learning algorithms have widespread usage in estimating positions of the target node. The real challenge in indoor localization systems is to find out the proper machine learning algorithm. In this paper, three different machine learning algorithms for training the fingerprint database were used. We analysed the localization accuracy depending on a fingerprint density and number of line-of-sight (LOS) anchors. Experiments confirmed that Gaussian processes algorithm is superior to all other machine learning algorithms. The results prove that the localization accuracy can be achieved with a sub-decimetre resolution under typical real-world conditions.

An Indoor Navigation Algorithm Using Multi-Dimensional Euclidean Distance and an Adaptive Particle Filter.

The inertial navigation system has high short-term positioning accuracy but features cumulative error. Although no cumulative error occurs in WiFi fingerprint localization, mismatching is common. A popular technique thus involves integrating an inertial navigation system with WiFi fingerprint matching. The particle filter uses dead reckoning as the state transfer equation and the difference between inertial navigation and WiFi fingerprint matching as the observation equation. Floor map information is introduced to detect whether particles cross the wall; if so, the weight is set to zero. For particles that do not cross the wall, considering the distance between current and historical particles, an adaptive particle filter is proposed. The adaptive factor increases the weight of highly trusted particles and reduces the weight of less trusted particles. This paper also proposes a multidimensional Euclidean distance algorithm to reduce WiFi fingerprint mismatching. Experimental results indicate that the proposed algorithm achieves high positioning accuracy.

Measurement and Analysis of RSS Using Bluetooth Mesh Network for Localization Applications

Bluetooth low energy (BLE)-based location service technology has become one of the fastest growing applications for Bluetooth. Received signal strength (RSS) is often used in localization techniques for ranging or location fingerprinting. However, RSS-based localization solutions have poor performance in multipath environments. In this paper, we present a measurement system designed using multiple ESP32 BLE modules and the Bluetooth mesh networking technology, which is capable of exploiting the space, time, and frequency diversities in measurements. To enable channel-aware multi-device RSS measurements, we also designed a communication protocol to associate channel ID information to advertising messages. Based on channel measurement and analysis, we demonstrate that with a six-receiver configuration and space-time-frequency diversity combining, we can significantly reduce the residual linear regression fitting errors in path loss models. Such a reduction leads to more accurately correlating RSS measurements to the distance between the transmitter and receiver devices and thus to achieving improved performance with the RSS-based localization techniques. More importantly, the reduction in the fitting errors is achieved without differentiating the three advertising channels, making it possible to conveniently implement the proposed six-receiver configuration using commercially available BLE devices and the standard Bluetooth mesh networking protocol stack.

A universal Wi-Fi fingerprint localization method based on machine learning and sample differences

Wi-Fi technology has become an important candidate for localization due to its low cost and no need of additional installation. The Wi-Fi fingerprint-based positioning is widely used because of its ready hardware and acceptable accuracy, especially with the current fingerprint localization algorithms based on Machine Learning (ML) and Deep Learning (DL). However, there exists two challenges. Firstly, the traditional ML methods train a specific classification model for each scene; therefore, it is hard to deploy and manage it on the cloud. Secondly, it is difficult to train an effective multi-classification model by using a small number of fingerprint samples. To solve these two problems, a novel binary classification model based on the samples’ differences is proposed in this paper. We divide the raw fingerprint pairs into positive and negative samples based on each pair’s distance. New relative features (e.g., sort features) are introduced to replace the traditional pair features which use the Media Access Control (MAC) address and Received Signal Strength (RSS). Finally, the boosting algorithm is used to train the classification model. The UJIndoorLoc dataset including the data from three different buildings is used to evaluate our proposed method. The preliminary results show that the floor success detection rate of the proposed method can reach 99.54% (eXtreme Gradient Boosting, XGBoost) and 99.22% (Gradient Boosting Decision Tree, GBDT), and the positioning error can reach 3.460 m (XGBoost) and 4.022 m (GBDT). Another important advantage of the proposed algorithm is that the model trained by one building’s data can be well applied to another building, which shows strong generalizable ability.

Fingerprinting localization of cross-temporal transferred and multi-source wireless signal fusion

Fingerprinting localization of cross-temporal transferred and multi-source wireless signal fusion

Indoor Localization Based on CSI Fingerprint by Siamese Convolution Neural Network

In this paper, a novel indoor localization system with channel state information (CSI) fingerprints is proposed, which learns the spatial and frequency features of CSI in the fifth-generation (5G) cellular network by a Siamese convolution neural network. In particular, considering that the CSI continuously collected by a moving target possesses the implicit spatial association, we locate the target by the successive CSI data gathered within a time interval which can be regarded as an information subspace of the fingerprint database. Therefore, the fingerprint localization can be modeled as a subspace matching problem and solved by the Siamese network-based similarity learning. In the proposed system, we design a structure of CSI fingerprint which includes the information from multiple base stations in spatial and frequency domains. Then, the proposed Siamese architecture extracts the CSI feature and estimates the location of the target by feature similarity comparison. Compared with the existing algorithms, it can increase the positioning accuracy significantly by the feature relevance among the CSI data collected at different positions. The field tests indicate that compared to other CSI fingerprint-based positioning methods, our proposed algorithm can effectively reduce the localization error.

Discrete Environment-Driven GPU-Based Ray Launching: Validation and Applications

In this work, the Discrete, Environment-Driven Ray Launching (DED-RL) algorithm, which makes use of parallelization on Graphic Processing Units, fully described in a previous paper, has been validated versus a large set of measurements to evaluate its performance in terms of both computational efficiency and accuracy. Three major urban areas have been considered, including a very challenging scenario in central San Francisco that was used as a benchmark to test an image-ray tracing algorithm in a previous work. Results show that DED-RL is as accurate as ray tracing, despite the much lower computation time, reduced by more than three orders of magnitude with respect to ray tracing. Moreover, the accuracy level only marginally depends on discretization pixel size, at least for the considered pixel size range. The unprecedented computational efficiency of DED-RL opens the way to numerous applications, ranging from RF coverage optimization of drone-aided cellular networks to efficient fingerprinting localization applications, as briefly discussed in the paper.

Outdoor Node Localization Using Random Neural Networks for Large-Scale Urban IoT LoRa Networks

Accurate localization for wireless sensor end devices is critical, particularly for Internet of Things (IoT) location-based applications such as remote healthcare, where there is a need for quick response to emergency or maintenance services. Global Positioning Systems (GPS) are widely known for outdoor localization services; however, high-power consumption and hardware cost become a significant hindrance to dense wireless sensor networks in large-scale urban areas. Therefore, wireless technologies such as Long-Range Wide-Area Networks (LoRaWAN) are being investigated in different location-aware IoT applications due to having more advantages with low-cost, long-range, and low-power characteristics. Furthermore, various localization methods, including fingerprint localization techniques, are present in the literature but with different limitations. This study uses LoRaWAN Received Signal Strength Indicator (RSSI) values to predict the unknown X and Y position coordinates on a publicly available LoRaWAN dataset for Antwerp in Belgium using Random Neural Networks (RNN). The proposed localization system achieves an improved high-level accuracy for outdoor dense urban areas and outperforms the present conventional LoRa-based localization systems in other work, with a minimum mean localization error of 0.29 m.

DRVAT: Exploring RSSI series representation and attention model for indoor positioning

Although Bluetooth Low Energy (BLE) fingerprinting localization has become a hot research topic with encouraging results, it is difficult to predict the location depending on a short duration received signal strength indication (RSSI) sequence in realistic scenarios due to the severe fluctuation of RSSI. We introduce a new perspective to view the indoor positioning problem by radio map fingerprint. We argue that even though beacons may be independently deployed, the RSSI series bear certain spatial relation because of their copresence in the same physical space. The latent relation implicitly conveyed by the coexistence of their signals at various indoor locations. Unlike existing approaches that try to find a direct mapping between sensed signals and the corresponding location, we explore the spatial relation of beacons from the input data to estimate location. We propose a deep learning localization system, termed DRVAT, which is based on the distributed representation vector (DRV) and self-attention (AT) among the pairs of MAC-RSSI. First, we obtain DRVs which represent dense features in low dimensionality through pre-training on all MAC-RSSIs. Then we exploit self-attention mechanism to learn the latent spatial relation of beacons. Finally, MAC-RSSIs labeled with locations are used to fine-tune the model for estimating location. Localization accuracy results demonstrated the superior performance as compared with other positioning methods, and the visualization of DRV and attention mechanism are consistent with the spatial deployment of BLE.

WiFi Fingerprinting Indoor Localization Based on Dynamic Mode Decomposition Feature Selection with Hidden Markov Model.

Over the years, WiFi received signal strength indicator (RSSI) measurements have been widely implemented for determining the location of a user’s position in an indoor environment, where the GPS signal might not be received. This method utilizes a huge RSSI dataset collected from numerous access points (APs). The WiFi RSSI measurements are nonlinear with distance and are largely influenced by interference in the indoor environment. Therefore, machine learning (ML) techniques such as a hidden Markov model (HMM) are generally utilized to efficiently identify a trend of RSSI values, which corresponds to locations around a region of interest. Similar to other ML tools, the performance and computing cost of the HMM are dependent on the feature dimension since a large quantity of RSSI measurements are required for the learning process. Hence, this article introduces a feature extraction method based on dynamic mode decomposition (DMD) for the HMM to effectively model WiFi fingerprint indoor localization. The DMD is adopted since it decomposes RSSIs to meaningful spatial and temporal forms over a given time. Here, the mode forms are analytically reconstructed to produce low-dimensional feature vectors, which are used with the HMM. The localization performance of the proposed HMM-DMD is compared with other well-known ML algorithms for WiFi fingerprinting localization using simulations. The results show that the HMM-DMD algorithm yields a significant localization performance improvement, accuracy, and reasonable processing time in comparison with the state-of-the-art algorithms.

Peptide Location Fingerprinting Reveals Tissue Region-Specific Differences in Protein Structures in an Ageing Human Organ.

In ageing tissues, long-lived extracellular matrix (ECM) proteins are susceptible to the accumulation of structural damage due to diverse mechanisms including glycation, oxidation and protease cleavage. Peptide location fingerprinting (PLF) is a new mass spectrometry (MS) analysis technique capable of identifying proteins exhibiting structural differences in complex proteomes. PLF applied to published young and aged intervertebral disc (IVD) MS datasets (posterior, lateral and anterior regions of the annulus fibrosus) identified 268 proteins with age-associated structural differences. For several ECM assemblies (collagens I, II and V and aggrecan), these differences were markedly conserved between degeneration-prone (posterior and lateral) and -resistant (anterior) regions. Significant differences in peptide yields, observed within collagen I α2, collagen II α1 and collagen V α1, were located within their triple-helical regions and/or cleaved C-terminal propeptides, indicating potential accumulation of damage and impaired maintenance. Several proteins (collagen V α1, collagen II α1 and aggrecan) also exhibited tissue region (lateral)-specific differences in structure between aged and young samples, suggesting that some ageing mechanisms may act locally within tissues. This study not only reveals possible age-associated differences in ECM protein structures which are tissue-region specific, but also highlights the ability of PLF as a proteomic tool to aid in biomarker discovery.

Improved Indoor Fingerprinting Localization Method Using Clustering Algorithm and Dynamic Compensation

Many indoor fingerprinting localization methods are based on signal-domain distances with large localization error and low stability. An improved fingerprinting localization method using a clustering algorithm and dynamic compensation was proposed. In the offline stage, the fingerprint database was built and clustered based on offline hybrid distance and an affinity propagation clustering algorithm. Furthermore, clusters were adjusted using transition regions and a given radius, as well as updating the corresponding position and fingerprint of the cluster centroid. In the online stage, the lost received signal strength (RSS) in the reference fingerprint would be dynamically compensated by using a minimum RSS value, rather than a fixed one. Online signal-domain distance was calculated for cluster identification based on RSS readings and compensated reference fingerprint. Then, K reference points with minimum online signal-domain distances were selected, and affinity propagation clustering was reused by position-domain distances to choose the position-concentrated sub-cluster for location estimation. Experimental results show that the proposed method outperforms state-of-the-art fingerprinting methods, with the mean error of 2.328 m, the root mean square error of 1.865 m and the maximum error of 10.722 m in a testbed of 3200 square meters. The improvement rates, in terms of accuracy and stability, are more than 21% and 13%, respectively.

Single-site indoor fingerprint localization based on MIMO-CSI

In order to achieve higher accuracy and lower cost of indoor localization, we propose a positioning method using multiple input and multiple output (MIMO) channel state information (CSI) as a fingerprint. The method can be divided into three stages, feature extraction, offline training and online localization. In the feature extraction, the segmented average and principal component analysis (PCA) are used to reduce the data dimension and decrease system complexity. In the offline training, the deep neural network (NN) model is trained to implement the position classification. In the online localization, the data are input into the trained NN model first, and then its output is further processed by weighted k-nearest neighbor (WKNN) technology to estimate the position. Experimental results show that the proposed method can significantly reduce the positioning error compared to other methods and the average error is 1.39m in a complex indoor environment.

Predicting and characterising protein damage in the extracellular matrix

Chronic UVR exposure of human skin can result in photo-ageing which manifests both externally and internally (as remodelling of skin layers including the extracellular matrix-rich dermis). However, the intermittent nature of UVR exposure over a timescale of decades combined with the longevity of many structural dermal proteins makes the identification of dermal photo-ageing targets and mechanisms challenging. Over the past ten years work in our group has demonstrated that: (i) proteins which are rich in amino acid chromophores are susceptible to physiologically relevant doses of solar simulated radiation, (ii) this protein degradation is mediated primarily by the photodynamic production of reaction oxygen species and (iii) UVR-chromophore rich proteins are located in tissue regions where they may act as endogenous sunscreens. We have also shown that ECM proteases selectively degrade UVR-damaged assemblies in vitro and have developed new machine learning-based models to predict protease cleavage sites and hence relative protease susceptibilities in the human skin proteome. The recent development of peptide location fingerprinting applied to conventional mass spectrometry datasets has allowed the identification of novel candidate biomarkers of UVR-induced damage as a consequence of photo-ageing. For example, this approach is able to identify structure-associated modifications in collagen VI alpha chains, although collagen VI remodeling is not evident by conventional histological analysis. These methods and resources (skin proteome database, protein susceptibility prediction and peptide location fingerprinting analysis) are available for use at www.manchesterproteome.manchester.ac.uk. Key areas for future research include using peptide location fingerprinting to: (i) characterise the structural hallmarks of ageing and photo-ageing mechanisms across different phototypes and (ii) evaluate the efficacy of rejuvenating treatments against novel protein biomarkers.

Deep Nearest Neighbor Website Fingerprinting Attack Technology

By website fingerprinting (WF) technologies, local listeners are enabled to track the specific website visited by users through an investigation of the encrypted traffic between the users and the Tor network entry node. The current triplet fingerprinting (TF) technique proved the possibility of small sample WF attacks. Previous research methods only concentrate on extracting the overall features of website traffic while ignoring the importance of website local fingerprinting characteristics for small sample WF attacks. Thus, in the present paper, a deep nearest neighbor website fingerprinting (DNNF) attack technology is proposed. The deep local fingerprinting features of websites are extracted via the convolutional neural network (CNN), and then the k-nearest neighbor (k-NN) classifier is utilized to classify the prediction. When the website provides only 20 samples, the accuracy can reach 96.2%. We also found that the DNNF method acts well compared to the traditional methods in coping with transfer learning and concept drift problems. In comparison to the TF method, the classification accuracy of the proposed method is improved by 2%–5% and it is only dropped by 3% when classifying the data collected from the same website after two months. These experiments revealed that the DNNF is a more flexible, efficient, and robust website fingerprinting attack technology, and the local fingerprinting features of websites are particularly important for small sample WF attacks.

INDOOR POSITIONING FOR SMART DEVICES BASED ON SENSOR FUSION WITH PARTICLE FILTER: LOCALIZATION AND MAP UPDATING

Abstract. With every new generation of smart devices, new sensors are introduced, such as depth camera or UWB sensors. Combined with the rapidly growing number of smart mobile devices, indoor positioning systems (IPS) have seen increasing interest due to numerous indoor location-based services (ILBS) and mobile applications at large. Wi-Fi Received Signal Strength (RSS) based fingerprinting positioning (WF) techniques are popularly used in many IPS as the widespread deployment of IEEE 802.11 WLAN (Wi-Fi) networks, as this technique requires no line-of-sight to the access points (APs), and it is easy to extract Wi-Fi signal from 802.11 networks with smart devices. However, WF techniques have problems with fingerprint variance, i.e., fluctuation of the sensed signal, and efficient map updating due to the frequently changing environment. To address these problems, we propose a novel framework of IPS which uses particle filter to fuse WF and state-of-the-art CNN-based visual localization method to better adapt to changing indoor environment. The suggested system was tested with real-world crowdsourced data collected by multiple devices in an office hallway. The experimental results demonstrate that the system can achieve robust localization at a 0.3~1.5 m mean error (ME) accuracy, and map updating with a 79% correction rate.

A Wireless Fingerprint Positioning Method Based on Wavelet Transform and Deep Learning

As the demand for location services increases, research on location technology has aroused great interest. In particular, signal-based fingerprint location positioning technology has become a research hotspot owing to its high positioning performance. In general, the received signal strength indicator (RSSI) will be used as a location feature to build a fingerprint database. However, at different locations, this feature distinction may not be obvious, resulting in low positioning accuracy. Considering the wavelet transform can get valuable features from the signals, the long-term evolution (LTE) signals were converted into wavelet feature images to construct the fingerprint database. To fully extract the signal features, a two-level hierarchical structure positioning system is proposed to achieve satisfactory positioning accuracy. A deep residual network (ResNet) rough locator is used to learn useful features from the wavelet feature fingerprint image database. Then, inspired by the transfer learning idea, a fine locator based on multilayer perceptron (MLP) is leveraged to further learn the features of the wavelet fingerprint image to obtain better localization performance. Additionally, multiple data enhancement techniques were adopted to increase the richness of the fingerprint dataset, thereby enhancing the robustness of the positioning system. Experimental results indicate that the proposed system leads to improved positioning performance in outdoor environments.

Clustering-Based Noise Elimination Scheme for Data Pre-Processing for Deep Learning Classifier in Fingerprint Indoor Positioning System.

Wi-Fi-based indoor positioning systems have a simple layout and a low cost, and they have gradually become popular in both academia and industry. However, due to the poor stability of Wi-Fi signals, it is difficult to accurately decide the position based on a received signal strength indicator (RSSI) by using a traditional dataset and a deep learning classifier. To overcome this difficulty, we present a clustering-based noise elimination scheme (CNES) for RSSI-based datasets. The scheme facilitates the region-based clustering of RSSIs through density-based spatial clustering of applications with noise. In this scheme, the RSSI-based dataset is preprocessed and noise samples are removed by CNES. This experiment was carried out in a dynamic environment, and we evaluated the lab simulation results of CNES using deep learning classifiers. The results showed that applying CNES to the test database to eliminate noise will increase the success probability of fingerprint location. The lab simulation results show that after using CNES, the average positioning accuracy of margin-zero (zero-meter error), margin-one (two-meter error), and margin-two (four-meter error) in the database increased by 17.78%, 7.24%, and 4.75%, respectively. We evaluated the simulation results with a real time testing experiment, where the result showed that CNES improved the average positioning accuracy to 22.43%, 9.15%, and 5.21% for margin-zero, margin-one, and margin-two error, respectively.

Moving Target Localization in Sports Image Sequence Based on Optimized Particle Filter Hybrid Tracking Algorithm

This paper proposes a fusion stadium positioning algorithm, which uses self-optimizing particle filter to integrate the improved athlete dead reckoning and WiFi position fingerprint algorithm for stadium positioning. In order to determine the initial absolute position of the stadium positioning, for athletes entering the stadium from the outside, a seamless switching algorithm outside the stadium is proposed, using the characteristics of high-altitude satellite GPS to find a suitable switching point as the initial absolute position. If in the stadium, WiFi static positioning determines the initial absolute position. Then, aiming at the problem that the poorly diversified particles cannot be better integrated and localized, a self-optimized particle filter algorithm is proposed. After resampling and retaining high-weight particles, the characteristics of low-weight particles are embedded in the copied high-weight particles. This can improve diversity, and we finally carry out fusion positioning. The target tracking algorithm based on Mean Shift has a fixed-scale tracking window, and the tracking effect of variable-size targets is not ideal. In this paper, an affine transformation algorithm is introduced to improve it. First, we iterate the adjacent image frames in reverse Mean Shift to determine the center position of the target and then use the corner matching method to perform template matching on the target to adjust the size of the tracking window. Through simulation verification, it is proved that the optimized particle filter hybrid tracking algorithm can achieve the ideal result when the target size changes. For the image sequence S1, the tracking window of the 20th frame and the 40th frame has a small offset, but the optimal position can be quickly found by Mean Shift iteration. For the image sequence S2, between the 40th frame and the 60th frame, the target occlusion causes the accuracy of the target template to decrease, and the Bhattacharyya coefficient is at a relatively low value. For the image sequence S3, the tracking effect of the optimized particle filter hybrid tracking algorithm meets the requirements.

Accurate Guidance Method and App Development for Assigning Parking Spaces Based on Indoor Wi-Fi

Existing parking guidance systems only provide road guidance outside the parking lot but do not provide accurate guidance to specific parking spaces inside the parking lot. By using a Kalman filter, the Grubbs test, and a neural network algorithm to improve the RSSI-based location fingerprint identification technology, an accurate location method based on indoor Wi-Fi is obtained, which implements precise route guidance and a reverse search function for parking spaces. We utilize Beidou positioning to develop a Gaode map for outdoor navigation and use an integrated system of ultrasonic detector/indicators and ground locks to manage parking spaces. Through the secondary development of an Android system and the application of a MySql database, an app for precise parking guidance was developed. The system makes full use of the Internet and parking information, eliminates information asymmetry, improves the utilization ratio of the urban static traffic resources, allocates parking spaces in real-time, breaks information islands, provides parking search and recommendation functions for users, achieves parking information-sharing, and effectively improves parking efficiency and the parking utilization ratio.