Ranging methods using received signal strength (RSS) information are widely used for indoor localization because they can be easily implemented without conducting site surveys. However, range estimation with a single pathloss model produces considerable errors, which degrade the positioning performance. This problem mainly arises because the single pathloss model cannot reflect diverse indoor radio wave propagation characteristics. In this study, we develop a new overlapping multi-state model to consider multiple candidates of pathloss models including line-of-sight (LOS) and non-line-of-sight (NLOS) states, and propose an efficient way to select a proper model for each reference node involved in the localization process. To this end, we formulate a cost function whose value varies widely depending on the choice of pathloss model of each access point. Because the computational complexity to find an optimal channel model for each reference node exponentially increases with the number of reference nodes, we apply a genetic algorithm to significantly reduce the complexity so that the proposed method can be executed in real-time. Experimental validations with ray-tracing simulations and RSS measurements at a real site confirm the improvement of localization accuracy for Wi-Fi in indoor environments. The proposed method achieves up to 1.92 m mean positioning error under a practical indoor environment and produces a performance improvement of 31.09% over the benchmark scenario.

Deep neural networks (DNNs) are widely used for fault classification using partial discharges (PDs) to evaluate various electrical apparatuses and achieve high classification accuracy pertaining to trained PD faults. However, there is a risk of false alarm in the case of untrained PD faults because it is difficult for DNNs to predict data that were not included in the training process. In this paper, we research classification problems of unknown classes using PDs in gas-insulated switchgears (GISs) and propose a deep ensemble model to obtain the confidence of output probability and determine thresholds to detect unknown fault classes. The proposed model was verified by real-world phase-resolved PD (PRPD) experiments using online ultra-high frequency (UHF) PD measurement systems. The experimental results show that the proposed model achieves better unknown detection performance for the untrained PD faults and retains the classification performance for the trained PD faults.

Automotive sensors are essential to autonomous driving, which performs various functions to perceive the surrounding environment. Among the various functions of the automotive sensors, the estimation of vehicle orientation is considered significant in responding to unpredictable situations in a dynamic driving environment. In this article, we propose a method of estimating the vehicle orientation using a cascaded multiple-input multiple-output (MIMO) frequency-modulated continuous-wave (FMCW) radar system. The radar signal is collected by varying the orientation angle of the vehicle, and the point cloud data corresponding to the vehicle are extracted through signal preprocessing. Because the processed point cloud data are distributed along the axis of vehicle orientation, the orientation angle can be estimated by applying regression algorithms. We used the principal component analysis (PCA), decision tree, and convolutional neural network (CNN) algorithms for regression and compared their performances. The comparison of various estimation methods showed that the proposed method of using the CNN framework can accurately estimate the orientation angle of a vehicle within a root mean square error (RMSE) of 4°.

This paper proposes a distributed localization algorithm in wireless sensor networks. The algorithm considers the position uncertainty of reference nodes which have been ignored in the past research in which an imperfect position information of reference nodes intensifies the error accumulation phenomenon. The algorithm calculates position uncertainty by the dilution of precision (DOP) and presents a balance point between range errors and position errors by applying the modified spring mass method. We verify the feasibility of the proposed algorithm by changing multiple parameters under various circumstance. The result prove that overall performance of localization is enhanced by considering the position uncertainty.

In this paper, we propose a hybrid localization algorithm to boost the accuracy of range-based localization by improving the ranging accuracy under indoor non-line-of-sight (NLOS) conditions. We replaced the ranging part of the rule-based localization method with a deep regression model that uses data-driven learning with dual-band received signal strength (RSS). The ranging error caused by the NLOS conditions was effectively reduced by using the deep regression method. As a consequence, the positioning error could be reduced under NLOS conditions. The performance of the proposed method was verified through a ray-tracing-based simulation for indoor spaces. The proposed scheme showed a reduction in the positioning error of at least 22.3% in terms of the median root mean square error compared to the existing methods. In addition, we verified that the proposed method was robust to changes in the indoor structure.

In automotive frequency-modulated continuous wave radar systems, targets with similar ranges and velocities might be detected as a single target because their target information overlaps on the range-velocity (RV) plane. When the information of multiple targets overlaps on the RV plane, target classification cannot be performed accurately. Therefore, we propose a method to decompose the overlapped target information on the RV plane for effective target classification. To separate each target’s radar signal, we use an orthogonal projection, in which the steering vector formed from the angle information of the desired target is projected onto the kernel space composed of other steering vectors. To verify the performance of the proposed method, a convolutional neural network-based target classification is performed on the decomposed radar signals. Compared to the angle-fast Fourier transform (FFT)-based signal decomposition, the orthogonal projection-based signal decomposition shows higher classification accuracy, which implies that the target information overlapped on the RV plane is effectively separated. When information of two targets is overlapped, the classification accuracy of the proposed method is 5.9%p higher than that of the conventional method. Moreover, when the information of three targets is overlapped, the accuracy is improved by 25.5%p.