Optimal Trained Deep Neural Network for Localization in Wireless Sensor Network

This chapter describes one of the major challenges in technology advancement of Wireless Sensor Networks (WSNs), i.e., Localization in WSNs. In recent years, sensor node localization is an emerging research area in WSNs. The sensor data become useless, if we do not know the location of the reporting node. Coordinates determination of the sensor node is a challenging problem and it is referred as localization problem. The nodes which has unknown coordinates is termed as target Nodes. Various localization methods can be utilized to find out the location of sensor nodes, those coordinates are not known in a system/network. Efficient WSN localization can be treated as multi-dimensional optimization problem which can be addressed through population based stochastic techniques, which involves the minimization of a function of differences between Euclidean and measured distance between sensor nodes. In this chapter various connectivity, range information and mobility based localization algorithms have been discussed. For optimizing the results of these algorithms, various computational intelligence (CI) based optimizing algorithms like Particle Swarm Optimization, Biogeography Based Optimization, Firefly Algorithm and Genetic Algorithm have been discussed. A choice between these algorithm is influenced by the localization accuracy expected to be and convergence rate.

SummaryIndoor localization in wireless sensor networks is a challenging task. Static localization and moving target monitoring are addressed using ensemble learning method and received signal strength indicator. The suggested strategy combines several regression trees to have better performance. This solution has been experimentally evaluated using real measurements in an office room. The performance results have been analyzed through a comparison with learning‐based localization algorithms currently available in the literature. The analysis shows that the adopted solution is simple in term of computation, accurate and robust to environmental variation.

In this paper, we design a new distributed angle estimation method for localization in wireless sensor networks (WSNs) under multipath propagation environment. We employ a two-antenna anchor that can emit two linear chirp waves simultaneously, and propose to estimate the angle of departure (AOD) of the emitted waves at each receiving node via frequency measurement of the local received signal strength indication (RSSI) signal. An improved estimation method is further proposed where multiple parallel arrays are adopted to provide the space diversity. The proposed methods rely only on radio transceivers and do not require frequency synchronization or precise time synchronization between the transceivers. More importantly, the angle is estimated at each sensor in a completely distributed manner. The performance analysis is derived and simulations are presented to corroborate the proposed studies.

Source positioning using hybrid angle-of-arrival (AOA) estimation and received signal strength indicator (RSSI) is attractive because no synchronization is required among unknown nodes and anchors. Conventionally, hybrid AOA/RSSI localization combines the same number of these measurements to estimate the agents’ locations. However, since AOA estimation requires anchors to be equipped with large antenna arrays and complicated signal processing, this conventional combination makes the wireless sensor network (WSN) complicated. This paper proposes an unbalanced integration of the two measurements, called 1AOA/nRSSI, to simplify the WSN. Instead of using many anchors with large antenna arrays, the proposed method only requires one master anchor to provide one AOA estimation, while other anchors are simple single-antenna transceivers. By simply transforming the 1AOA/1RSSI information into two corresponding virtual anchors, the problem of integrating one AOA and N RSSI measurements is solved using the least square and subspace methods. The solutions are then evaluated to characterize the impact of angular and distance measurement errors. Simulation results show that the proposed network achieves the same level of precision as in a fully hybrid nAOA/nRSSI network with a slightly higher number of simple anchors.

Localization technology based on received signal strength indication (RSSI) is a low cost and low complexity technology, and it is widely applied in distance-based localization of wireless sensor networks (WSNs). The error of existed localization technologies is great. This paper presents an N-times trilateral centroid weighted localization algorithm (NTCWLA), which reduces the error greatly. Considering the instability of RSSI, we use the weighted average of many RSSIs as an indicator of the current RSSI. To improve the accuracy we select n (n=3) reliable beacon nodes to increase the localization times. Then we calculate the distances between reliable beacon nodes and the mobile node using an empirical formula. This new algorithm locates the mobile node N times with the trilateral centroid algorithm. Finally, we take the weighted average of the filtered reference coordinates as the mobile node's coordinates. We experiment with the STM32W108 chip, which supports the IEEE802.15.4 protocol. Our experimental results indicate that this new algorithm is more accurate than the trilateral centroid algorithm.

In the wireless sensor network (WSN) localization methods based on Received Signal Strength Indicator (RSSI), it is usually required to determine the parameters of the radio signal propagation model before estimating the distance between the anchor node and an unknown node with reference to their communication RSSI value. And finally we use a localization algorithm to estimate the location of the unknown node. However, this localization method, though high in localization accuracy, has weaknesses such as complex working procedure and poor system versatility. Concerning these defects, a self-adaptive WSN localization method based on least square is proposed, which uses the least square criterion to estimate the parameters of radio signal propagation model, which positively reduces the computation amount in the estimation process. The experimental results show that the proposed self-adaptive localization method outputs a high processing efficiency while satisfying the high localization accuracy requirement. Conclusively, the proposed method is of definite practical value.

The localization of wireless sensor networks (WSN) is an important field of research study, that is gaining considerable attention. This growth in wireless sensor network installations is expected to expand more in the future. Indoor localization based on the Received Signal Strength Indicators (RSSI) is a well-known localization technique used in WSN systems due to its availability and simplicity. Radio location fingerprinting is one of the most effective of the many indoor positioning techniques due to its accuracy and low cost. In this study, we investigate the possibility of applying RSSI fingerprinting based Artificial Neural Network (ANN) jointly to determine the correct location of an object or person in indoor environments. According to our analysis and experiment result, Fingerprinting techniques can achieve accurate localization with high interference in a computer laboratory. In addition, this research uses a small-structure neural network (one hidden layer) to provide efficient computation with restricted resource requirements.

Indoor localization is an important issue in wireless sensor networks for a very large number of applications. Recently, localization techniques based on the received signal strength indicator (RSSI) have been widely used due to their simple and low cost implementation. In this paper, we propose an algorithm for localization in wireless sensor networks based on radio-location fingerprinting and kernel methods. The proposed method is compared to another well-known localization algorithm in the case of real data collected in an indoor environment where RSSI measures are affected by noise and other interferences.

This paper considers the problem of decentralized localization in wireless sensor networks (WSNs). The problem is set by combining both radio-fingerprints and accelerometer information. It is then resolved in a decentralized manner where the surveillance area is divided into several zones equipped with calculators. The proposed algorithm consists of computing first estimates using received signal strength indicator (RSSI)-fingerprints, then correcting them using accelerometer information leading to more accurate estimates. Computations are performed using the interval analysis and the Kalman filter in a simulated environment.

An accurate prediction method for moving target localization and tracking in wireless sensor networks

We propose a novel approach to the source localization and tracking problem in wireless sensor networks. By applying minimax approximation and semidefinite relaxation, we transform the traditionally nonlinear and nonconvex problem into convex optimization problems for two different source localization models involving measured distance and received signal strength. Based on the problem transformation, we develop a fast low-complexity semidefinite programming (SDP) algorithm for two different source localization models. Our algorithm can either be used to estimate the source location or be used to initialize the original nonconvex maximum likelihood algorithm.

Recently deep-learning (DL) techniques have been widely adopted in side-channel power analysis. A DL-assisted SCA generally consists of two phases: a deep neural network (DNN) training phase and a follow-on attack phase using the trained DNN. However, currently the two phases are not well aligned, as there is no conclusion on what metric used in the training can result in the most effective attack in the second phase. When traditional loss functions such as negative log-likelihood (NLL) are used in training a DNN, the trained model does not yield optimal follow-on attack. Recently some information theoretical SCA leakage metrics are proposed, either as the validation metric to stop the DNN training with traditional loss functions, or as both the validation metric and the training loss function. None of those proposed metrics, however, directly measures the SCA effectiveness. We propose to conduct DNN training directly with a common SCA effectiveness metric, Guessing Entropy (GE). We overcome the prior practical difficulty of using GE in DNN training by utilizing the GEEA estimation algorithm introduced in CHES 2020. We show that using GEEA as either the validation metric or the loss function produces DNN models that lead to much more effective follow-on attacks. Our work consolidates the DL-assisted SCA framework with a consistent metric, which shows great potential to be adopted as the universal SCA-oriented DNN training framework.

Localization is one of the most challenging and important issues in wireless sensor networks (WSNs), especially if cost-effective approaches are demanded. In this paper, we present intensively discuss and analyze approaches relying on the received signal strength indicator (RSSI). The advantage of employing the RSSI values is that no extra hardware (e.g. ultrasonic or infra-red) is needed for network-centric localization. We studied different factors that affect the measured RSSI values. Finally, we evaluate two methods to estimate the distance; the first approach is based on statistical methods. For the second one, we use an artificial neural network to estimate the distance.

Received Signal Strength Indicator (RSSI)-based indoor localization is attractive for its low cost and ease of deployment, yet its accuracy is often compromised by multipath propagation, non-line-of-sight conditions, and environmental noise. Traditional filtering approaches, such as Kalman and particle filters, rely on precise noise models and struggle under sparse sensing or model mismatch. In this study, we recast RSSI localization as a sequential state estimation problem and propose a reinforcement learning-based reduced-order estimator (RL-ROE). By combining model-driven dynamics with data-driven policy correction, the method achieves improved accuracy and robustness under noisy indoor environments, demonstrating its potential as a scalable solution for real-time localization in wireless sensor networks.

Target localization and tracking problems in Wireless Sensor Networks (WSNs) have received considerable attention recently, driven by the need to achieve high localization accuracy, with the minimum cost possible. A wide range of proposed approaches regarding the localization area have emerged, however most of them suffer from either requiring an extra sensor, high power consumption, inaccessible indoors, or offer high localization error. This paper presents a research and development of a hybrid WSN tracking system using the Received Signal Strength Indicator (RSSI) and the inertial system. The proposed system is an efficient indoors, where it offers reasonable localization accuracy (0.1 - 0.7) meters, and achieves low power consumption. A number of real experiments have been conducted to test the efficiency of the proposed system using XBee modules.