An accurate noise power spectral density (PSD) tracker is an indispensable component of a single-channel speech enhancement system. Bayesian-motivated minimum mean-square error (MMSE) noise PSD estimators have been the most prominent in recent time. However, they lack the ability to track highly non-stationary noise sources due to current methods of a priori signal-to-noise (SNR) estimation. This is caused by the underlying assumption that the noise signal changes at a slower rate than the speech signal. As a result, MMSE noise PSD trackers exhibit a large tracking delay and produce noise PSD estimates that require bias compensation. Motivated by this, we propose an MMSE noise PSD tracker that employs a deep residual network (ResNet) a priori SNR estimator. The proposed noise PSD tracker, called DeepMMSE makes no assumptions about the characteristics of the noise or the speech, exhibits no tracking delay, and produces an accurate estimate that requires no bias correction. Our extensive experimental investigation shows that the proposed DeepMMSE method outperforms state-of-the-art noise PSD trackers and demonstrates the ability to track abrupt changes in the noise level. Furthermore, when employed in a speech enhancement framework, the proposed DeepMMSE method is able to outperform state-of-the-art noise PSD trackers, as well as multiple deep learning approaches to speech enhancement.

The trend of global Sea Surface Temperature (SST) has attracted widespread attention in several ocean-related fields such as global warming, marine environmental protection and marine biodiversity. Sea surface temperature is influenced by climate change; with the accumulation of data from ocean remote sensing observations year by year, many scholars have started to use deep learning methods for SST prediction. In this paper, we use a dynamic region partitioning approach to process ocean big data and design a framework applied to a global SST short-term prediction system. On the architecture of a Long Short-Term Memory (LSTM) network, two deep learning multi-region SST prediction models are proposed, which extract temporal and spatial information of SST by encoding, using feature transformation and decoding to predict future multi-step states. The models are tested using OISST data and the model performance is evaluated by different metrics. The proposed MR-EDLSTM model and MR-EDConvLSTM model obtained the best results for short-term prediction, with RMSE ranging from 0.2712 °C to 0.6487 °C and prediction accuracies ranging from 97.60% to 98.81% for ten consecutive days of prediction. The results show that the proposed MR-EDLSTM model has better prediction performance in coastal areas, while the MR-EDConvLSTM model performs better in predicting the sea area near the equator. In addition, the proposed deep learning model has a smaller RMSE compared to the forecasting system based on the ocean model, indicating that the deep learning method has certain advantages in predicting global SST.

Ship detection based on remote sensing images holds significant importance in both military and economic domains. Ships within such images exhibit diverse scales, dense distributions, arbitrary orientations, and narrow shapes, which pose challenges for accurate recognition. This paper introduces an improved S²A-Net (Single-shot Alignment Network) based oriented object detection algorithm for ship detection. In network structure, pyramid squeeze attention is embedded in order to focus on key features and a context information module is designed to enhance the context understanding capability of the network. In the training strategy, considering the distortion problems such as blurring and low contrast in remote sensing images, a fog density and depth decomposition-based unpaired image dehazing network D4 is adopted to improve the image quality, besides, an image weight sampling strategy is proposed to enhance the training opportunities of small and difficult samples, thereby mitigating the issue of imbalanced ship category distribution. Experimental results demonstrate that the improved S²A-Net algorithm achieves the mean average precision of 77.27% for ship detection in the FAIR1M dataset, which is 5.6% better than the original S²A-Net algorithm, and outperforms the current common object detection algorithms.

As a classic positioning algorithm with a simple principle and low computational complexity, the trilateration positioning algorithm utilizes the coordinates of three anchor nodes to determine the position of an unknown node, which is widely applied in various positioning scenes. However, due to the environmental noise, environmental interference, the distance estimation error, the uncertainty of anchor nodes’ coordinates, and other negative factors, the positioning error increases significantly. For this problem, we propose a new trilateration algorithm based on the combination and K-Means clustering to effectively remove the positioning results with significant errors in this paper, which makes full use of the position and distance information of the anchor nodes in the area. In this method, after analyzing the factors affecting the optimization of the trilateration and selecting optimal parameters, we carry out experiments to verify the effectiveness and feasibility of the proposed algorithm. We also compare the positioning accuracy and positioning efficiency of the proposed algorithm with those of other algorithms in different environments. According to the comparison of the least-squares method, the maximum likelihood method, the classical trilateration and the proposed trilateration, the results of the experiments show that the proposed trilateration algorithm performs well in the positioning accuracy and efficiency in both light-of-sight (LOS) and non-light-of-sight (NLOS) environments. Then, we test our approach in three realistic environments, i.e., indoor, outdoor and hall. The experimental results show that when there are few available anchor nodes, the proposed localization method reduces the mean distance error compared with the classical trilateration, the least-squares method, and the maximum likelihood.

This article proposes a cognitive radar (CR) framework to improve the performance of the estimation and recognition for range-extended targets. To overcome the angular uncertainty and exploit the temporal correlation of target signatures, we introduce the static multimodel approach and the exponential correlation model to describe the dynamics of target signatures. The estimate of target signatures and the probability distribution of target hypotheses are updated recursively in response to the latest echo, ruled by the Bayesian theory. A waveform optimization module is integrated into the framework, which designs the waveform for the next emission according to the knowledge extracted from the echo history. A design criterion based on mutual information (MI) is derived, which implies the average estimation capability for all target hypotheses and the mean between-hypotheses divergence. The proposed method is examined using both synthetic data and electromagnetic (EM) simulation data of realistic targets.

In wireless sensor networks, due to the significance of the location information of mobile nodes for many applications, location services are the basis of many application scenarios. However, node state and communication uncertainty affect the distance estimation and position calculation of the range-based localization method, which makes it difficult to guarantee the localization accuracy and the system robustness of the distributed localization system. In this paper, we propose a distributed localization method based on anchor nodes selection and particle filter optimization. In this method, we first analyze the uncertainty of error propagation to the least-squares localization method. According to the proportional relation between localization error and uncertainty propagation, anchor nodes are selected optimally in real-time during the movement of mobile nodes. Then we use the ranging and position of the optimally selected anchor nodes to obtain the location information of the mobile nodes. Finally, the particle filter (PF) algorithm is utilized to gain the optimal estimation of the localization results. The experimental evaluation results verified that the proposed method effectively improves the localization accuracy and the robustness of the distributed system.