Support Vector Regression for Mobile Target Localization in Indoor Environments

Trilateration-based target localization using received signal strength (RSS) in a wireless sensor network (WSN) generally yields inaccurate location estimates due to high fluctuations in RSS measurements in indoor environments. Improving the localization accuracy in RSS-based systems has long been the focus of a substantial amount of research. This paper proposes two range-free algorithms based on RSS measurements, namely support vector regression (SVR) and SVR + Kalman filter (KF). Unlike trilateration, the proposed SVR-based localization scheme can directly estimate target locations using field measurements without relying on the computation of distances. Unlike other state-of-the-art localization and tracking (L&T) schemes such as the generalized regression neural network (GRNN), SVR localization architecture needs only three RSS measurements to locate a mobile target. Furthermore, the SVR based localization scheme was fused with a KF in order to gain further refinement in target location estimates. Rigorous simulations were carried out to test the localization efficacy of the proposed algorithms for noisy radio frequency (RF) channels and a dynamic target motion model. Benefiting from the good generalization ability of SVR, simulation results showed that the presented SVR-based localization algorithms demonstrate superior performance compared to trilateration- and GRNN-based localization schemes in terms of indoor localization performance.

An Investigation of Adaptive Radius for the Covariance Localization in Ensemble Data Assimilation

The covariance matrix estimated from the ensemble data assimilation always suffers from filter collapse because of the spurious correlations induced by the finite ensemble size. The localization technique is applied to ameliorate this issue, which has been suggested to be effective. In this paper, an adaptive scheme for Schur product covariance localization is proposed, which is easy and efficient to implement in the ensemble data assimilation frameworks. A Gaussian-shaped taper function is selected as the localization taper function for the Schur product in the adaptive localization scheme, and the localization radius is obtained adaptively through a certain criterion of correlations with the background ensembles. An idealized Lorenz96 model with an ensemble Kalman filter is firstly examined, showing that the adaptive localization scheme helps to significantly reduce the spurious correlations in the small ensemble with low computational cost and provides accurate covariances that are similar to those derived from a much larger ensemble. The investigations of adaptive localization radius reveal that the optimal radius is model-parameter-dependent, vertical-level-dependent and nearly flow-dependent with weather scenarios in a realistic model; for example, the radius of model parameter zonal wind is generally larger than that of temperature. The adaptivity of the localization scheme is also illustrated in the ensemble framework and shows that the adaptive scheme has a positive effect on the assimilated analysis as the well-tuned localization.

Adaptive Fading Extended Kalman Filtering for Mobile Robot Localization Using a Doppler–Azimuth Radar

In this paper, the localization problem of a mobile robot equipped with a Doppler–azimuth radar (D–AR) is investigated in the environment with multiple landmarks. For the type (2,0) robot kinematic model, the unknown modeling errors are generally aroused by the inaccurate odometer measurement. Meanwhile, the inaccurate odometer measurement can also give rise to a type of unknown bias for the D–AR measurement. For reducing the influence induced by modeling errors on the localization performance and enhancing the practicability of the developed robot localization algorithm, an adaptive fading extended Kalman filter (AFEKF)-based robot localization scheme is proposed. First, the robot kinematic model and the D–AR measurement model are modified by considering the impact caused by the inaccurate odometer measurement. Subsequently, in the frame of adaptive fading extended Kalman filtering, the way to the addressed robot localization problem with unknown biases is sought out and the stability of the developed AFEKF-based localization algorithm is also discussed. Finally, in order to testify the feasibility of the AFEKF-based localization scheme, three different kinds of modeling errors are considered and the comparative simulations are conducted with the conventional EKF. From the comparative simulation results, it can be seen that the average localization error under the developed AFEKF-based localization scheme is [0.0245m0.0224m0.0039rad]T and the average localization errors using the conventional EKF are [1.0405m2.2700m0.1782rad]T, [0.4963m0.3482m0.0254rad]T and [0.2774m0.3897m0.0353rad]T, respectively, under the three cases of the constant bias, the white Gaussian stochastic bias and the bounded uncertainty bias.

AI-Aided Individual Emergency Detection System in Edge-Internet of Things Environments

Recently, many disasters have occurred in indoor places. In order to rescue or detect victims within disaster scenes, vital information regarding their existence and location is needed. To provide such information, some studies simply employ indoor positioning systems to identify each mobile device of victims. However, their schemes may be unreliable, since people sometimes drop their mobile devices or put them on a desk. In other words, their methods may find a mobile device, not a victim. To solve this problem, this paper proposes a novel individual monitoring system based on edge intelligence. The proposed system monitors coexisting states with a user and a smart mobile device through a user state detection mechanism, which could allow tracking through the monitoring of continuous user state switching. Then, a fine-grained localization scheme is employed to perceive the precise location of a user who is with a mobile device. Hence, the proposed system is developed as a proof-of-concept relying on off-the-shelf WiFi devices and reusing pervasive signals. The smart mobile devices of users interact with hierarchical edge computing resources to quickly and safely collect and manage sensing data of user behaviors with encryption by cipher-block chaining, and user behaviors are analyzed via the ensemble paradigm of three machine learning technologies. The proposed system shows 98.82% prevision for user activity recognition, and 96.5% accuracy for user localization accuracy is achieved.

Analysis of the Effect of Robots in the Treatment of Pancreatic Cancer Based on Smart Medicine

In order to study the effect of robots in the treatment of pancreatic cancer in the context of smart medical, this paper improves the robot recognition technology and data processing technology and improves the system kernel algorithm through the hash algorithm. Unlike the traditional sequencing method that directly uses the gray average value as a feature, the hash algorithm calculates the gray three-average value of each frame block and uses the difference of the three-average value of adjacent frame blocks to perform detection. Moreover, this paper proposes a detection and localization scheme based on hash local matching, which consists of two parts: coarse matching and fine matching. In addition, this paper designs a control experiment to analyze the effect of robots in the treatment of pancreatic cancer, counts multiple sets of data, and uses mathematical statistics to process and visually display the experimental data. The research shows that the robot has a good clinical effect in the treatment of pancreatic cancer.

A Novel Joint TDOA/FDOA Passive Localization Scheme Using Interval Intersection Algorithm

Due to the large measurement error in the practical non-cooperative scene, the passive localization algorithms based on traditional numerical calculation using time difference of arrival (TDOA) and frequency difference of arrival (FDOA) often have no solution, i.e., the estimated result cannot meet the localization background knowledge. In this context, this paper intends to introduce interval analysis theory into joint FDOA/TDOA-based localization algorithm. The proposed algorithm uses the dichotomy algorithm to fuse the interval measurement of TDOA and FDOA for estimating the velocity and position of a moving target. The estimation results are given in the form of an interval. The estimated interval must contain the true values of the position and velocity of the radiation target, and the size of the interval reflects the confidence of the estimation. The point estimation of the position and the velocity of the target is given by the midpoint of the estimation interval. Simulation analysis shows the efficacy of the algorithm.