Intelligent Transportation Systems (ITS) utilises the growing trend of both communication technologies and intelligent analytics to make transportation systems more smart and efficient. Federated Learning, a privacy-preserving machine learning paradigm shows promise in being applied in this field. However, the data and device heterogeneity, and highly dynamic environment in ITS pose challenges to the performance of federated learning. One of the recent approaches to address the challenges are to choose proper participants from available clients during training. However, this research field is not fully investigated yet, and many works are still based on the classic random-based selection scheme. In this paper, we present Newt, an enhanced federated learning approach. On one hand, it includes a new client selection utility that explores the trade-off between accuracy performance in each round and system progress. On the other hand, it highlights a feedback control on the selector. Specifically, we implement a control on the selection frequency as a new dimension of client selection method design. We evaluate the proposed system with DNN training tasks on large scale FEMNIST-based datasets that are of different heterogeneity properties. The experiments show that our method outperforms the other baseline methods by as large as 20%.

As targets floating on the sea surface get more invisible, it is becoming vital and challenging to effectively detect small targets from strong sea clutter. Besides, fitting the distribution of sea clutter is a hard task because of the complex characteristics of clutter. Classic model-based detectors are prone to suffer from the mismatch problem and a high probability of false alarm (PFA). In this paper, a PFA controllable and data-driven detection method based on an attention-enhanced convolutional neural network (CNN) is proposed. Different from mainstream CNN-based detectors, the proposed method takes time-frequency maps obtained by the Wigner-Ville distribution (WVD) as inputs. Then time-frequency maps are converted into feature images as inputs to the designed CNN strengthened with representation powers and feature refinement abilities. The designed CNN is capable of automatically learning and classifying different features between targets and clutter. Meanwhile, a PFA control unit is employed to ensure an expected actual PFA. Results with the IPIX database show that the probability of detection of the proposed method is about 0.9066 with the PFA being 10 ^-3 and the observation time being 1.024 s. Compared with five typical feature-based detectors, the proposed method achieves better detection performance. Besides, results with the Sea-detecting Radar Data-sharing Program database also verify the feasibility and superiority of the proposed detector. The source codes are available at https://github.com/quqizhe-whu/ADN.

The target detection method based on multi-dimensional feature space is commonly used for detecting small maritime targets in sea clutter. However, existing methods do not fully explore and utilize the correlation information between features, limiting their detection performance. To address this limitation, this paper proposes a target detection method in sea clutter based on feature re-expression using Spearman correlation. First, a generalized linear grouping method based on Spearman correlation is proposed to strengthen the linear relationships within groups while reducing inter-group feature correlations. Second, intra-group feature re-expression based on Bhattacharyya distance is introduced, yielding new features with superior classification capabilities and complementary informational relationships. Third, a tri-feature concave hull detection algorithm based on dual distance weights is designed to enhance detection performance while controlling the false alarm rate. Testing with measured data from three public datasets demonstrates that the proposed detection method exhibits significant improvements in detection performance compared to existing feature-based detection methods.

Traditional radar target detection algorithms are mostly based on statistical theory. They have weak generalization capabilities for complex sea clutter environments and diverse target characteristics, and their detection performance would be significantly reduced. In this paper, the range-azimuth-frame information obtained by scanning radar is converted into plain position indicator (PPI) images, and a novel Radar-PPInet is proposed and used for marine target detection. The model includes CSPDarknet53, SPP, PANet, power non-maximum suppression (P-NMS), and multi-frame fusion section. The prediction frame coordinates, target category, and corresponding confidence are directly given through the feature extraction network. The network structure strengthens the receptive field and attention distribution structure, and further improves the efficiency of network training. P-NMS can effectively improve the problem of missed detection of multi-targets. Moreover, the false alarms caused by strong sea clutter are reduced by the multi-frame fusion, which is also a benefit for weak target detection. The verification using the X-band navigation radar PPI image dataset shows that compared with the traditional cell-average constant false alarm rate detector (CA-CFAR) and the two-stage Faster R-CNN algorithm, the proposed method significantly improved the detection probability by 15% and 10% under certain false alarm probability conditions, which is more suitable for various environment and target characteristics. Moreover, the computational burden is discussed showing that the Radar-PPInet detection model is significantly lower than the Faster R-CNN in terms of parameters and calculations.

Under the framework of feature-based detection of small targets on sea surface, existing feature extraction methods only use the echo data of current frame while ignoring the influence of historical echo data. Nevertheless, due to the non-stationarity of sea clutter, it may lead to unstable extraction of detection features, and then affect detection performance. To solve this problem, this paper designs a feature extraction method based on a priori information for small target detection. It firstly obtains a priori information from historical echo data by kernel density estimation (KDE) method. Then, the corresponding feature estimation method is utilized to obtain improved feature according to the relationship between current frame data and a priori information. Finally, the feature information of current frame is integrated into a priori information to prepare next feature extraction. Measured data are utilized to verify the performance of proposed method and the results reveal that, this method can effectively improve detection performance especially when sea clutter and target echo have good separability. In addition, the complexity of algorithm is analyzed to prove that proposed method has certain application potential.

Feature-based target detection methods are predominantly used to determine the presence or absence of detection targets under sea clutter conditions, but they exhibit a deficiency in making nuanced classification judgments for the different categories of detected targets. Both ship targets and marine surface floating small objects display specific sea clutter characteristics to various degrees. Given the periodic consistency of transient power and the Doppler centroid bandwidth observed in sea clutter, this article examines the manifestation level of this characteristic in both categories of targets, drawing on their respective motion mechanisms. The ability to distinguish between these two categories of targets using this characteristic has been validated through the analysis of empirical data, subsequently leading to the formulation of discriminant statistics that facilitate target classification. The data confirm the effectiveness of this approach, illustrating its robust classification performance.