Search

This article deals with the problem of saving network energy in the field of distributed target tracking in underwater wireless sensor networks (UWSNs). Specifically, a modified distributed extended Kalman filter (DEKF) is proposed for distributed target tracking. To reduce the energy cost during the tracking process, the stochastic node communication scheme is introduced, where each node communicates with its neighboring sensors according to certain probabilities. By minimizing the estimation error, the optimal filter gain with stochastic node communications is derived. Considering the fact that the calculations of cross-covariance and the estimation of compensation matrix are impractical in UWSNs, a suboptimal Kalman gain is derived by matrix scaling. In addition, the estimation error of the modified DEKF is proved to be exponentially bounded in mean square. Finally, simulations and real-world experiments are carried out to reveal the effectiveness of the proposed algorithm.

The estimation of target positions from angle-of-arrival (AOA) measurements has been extensively researched, and various estimators have been proposed to tackle this challenge. Among these, the maximum likelihood estimator (MLE) is notable for its well-recognized properties, including asymptotic unbiasedness and efficiency. However, traditional MLEs, such as the Gauss-Newton algorithm, often encounter difficulties due to the need for a first-order linearization step in computing the Jacobian matrix. This requirement introduces the potential for significant errors and convergence issues, especially in highly nonlinear systems. To overcome this limitation, this paper introduces a learning framework to address the maximum likelihood estimation problem, where the iterative increments are treated as the output of the agent's actions. Building upon this framework, we develop a learning-based MLE. Comprehensive numerical simulation results demonstrate the effectiveness and superiority of our approach. First, it effectively resolves convergence issues associated with linearization in traditional MLEs. Second, it exhibits robust adaptability by successfully solving both two-dimensional and three-dimensional AOA localization problems. Last, the proposed method significantly enhances localization accuracy compared to existing estimators.

In mobile phone screen defect inspection, unknown anomalies may emerge as data accumulates or the industrial environment changes. Open-set recognition (OSR) is needed to classify known defects and identify unknowns. This provides clues to identify familiar problematic processes and warns of the emergence of new problematic processes. However, most OSR methods either lack adaptive and explicit thresholds required for practical applications or are designed for natural datasets with low-resolution images and numerous categories. Such characteristics make them unsuitable for defect datasets. Hence, this article proposes a novel threshold-adaptive open-set classification model incorporating a negative-guided augmented prototype generator. The prototype generator adaptively utilizes diverse information to learn. During inference, it can generate the input-adaptive negative prototype that represents the opposite of known categories. This provides an adaptive threshold with discriminative power against unknowns without calibration. In addition, a feature-focused generative adversarial network (GAN) equipped with a class-wise similarity loss is designed to generate open-set data for high-resolution images. Augmenting the training set with this data enhances the classification model’s ability to handle high-resolution defect images. Our method outperforms other OSR methods on the mobile phone screen defect dataset, achieving 99.1% closed-set accuracy (ClosedACC), 99.3% area under the receiver-operator curve (AUROC), 98.6% OSCR, and 96.2% both-set accuracy (BothACC). The code is available at https://github.com/CFZ1/OSR_Screen.

Targets in water usually have the characteristics of wideband or multifrequency. Affected by the multipath effect and the interference of random noise, a target in water will generate multiple direction observations based on the passive nodes of an underwater sensor network (UWSN), which will also produce multiple localization measurements. The Gaussian mixture (GM) probability hypothesis density (PHD) filter is an effective method for tracking targets with uncertain measurements. By analyzing the features of underwater noncooperative targets, the feature-aided method is proposed in this article to deal with the problem of tracking unknown targets. A feature-aided measurement partition (FAMP) algorithm is used to obtain underwater sufficient and effective measurements. The traditional GM PHD method is improved by feature-aiding, and the threshold of selecting components is adjusted adaptively in the tracking process. The simulation results show that our method improves the accuracy of estimating the number of underwater unknown targets by about 20% and has a better performance in tracking compared with the original filter.