Deep neural networks (DNNs) greatly enable the task of automatic modulation classification (AMC) by virtue of their powerful feature extraction capability. However, extensive research has shown that DNNs are highly vulnerable to adversarial attacks, which can lead them to confidently output incorrect results with high confidence scores. Existing adversarial attack methods often focus solely on temporal characteristics of signals while neglecting frequency domain information, resulting in adversarial examples with poor transferability and inadequate performance in the closed-box scenario. An adversarial attack method based on frequency domain feature enhanced and integral gradient (FEIG) for AMC task is proposed in this paper. The approach utilizes techniques such as translation interpolation and Inverse Fast Fourier Transform to enhance the frequency domain information of original examples, thereby constructing enhanced baseline examples. Subsequently, these generated enhanced baseline examples are used as new inputs for gradient integration to obtain adversarial examples. Compared to traditional methods, the generated adversarial examples exhibit stronger transferability. Furthermore, in order to improve the defense performance of the model, an enhanced hybrid adversarial training (EH-AT) framework is proposed in this paper. The original clean example and the adversarial example generated by the proposed attack method are trained with joint loss constraints, which greatly enhances the robustness of the model. Experimental results demonstrate the effectiveness of the FEIG attack method and the EH-AT framework.

Inferring the fine-grained urban flows based on the coarse-grained flow observations is practically important to many smart city-related applications. Adequate data is usually a prerequisite for existing machine learning methods, especially most deep learning models. However, many cities still suffer from the data scarcity issue due to the unbalanced city development levels. To mitigate this issue, we propose a novel cross-city fine-grained urban flow inference model named FGITrans, which aims to effectively transfer the knowledge from the data-rich cities to the data-scarce cities. Specifically, we design a weight-sharing triple-branch transformer framework which adopts self-attention and cross-attention for source/target city feature learning and domain alignment, respectively. Then, we propose a novel spatio-temporal adaptive embedding (STAE) layer for our transformer framework, and introduce a cross-city knowledge distillation (CKD) loss to narrow the cross-city disparities. The CKD loss explicitly enforces the framework to learn the discriminative domain-specific and domain-invariant representations simultaneously. Extensive experiments conducted on four large real-world datasets validate the effectiveness of FGITrans compared with the state-of-the-art baselines.

Inferring the fine-grained urban traffic flows based on the coarse-grained traffic flow observations is practically important to many real applications for smart city. Existing approaches mostly rely on a large number of high quality urban flow data, but neglect the data sparsity issue which is common in real-world scenarios. Therefore, the performance of existing methods may not be promising towards cities that lack sufficient traffic flow data. How to design a more generalizable urban flow inference model that is able to effectively transfer knowledge across multiple cities is challenging and remains as an open research problem. In this paper, we propose a novel fine-grained urban flow inference model named AdaTM, which leverages the city-specific and city-invariant knowledge extracted from multiple cities. Specifically, we first propose a transformer-based urban feature extraction network named UBFormer to comprehensively extract the spatial-temporal features of multiple source cities. Then, we incorporate a learnable integrator to fuse the city-invariant and city-specific feature representations for the target city with sparse traffic flow data. Finally, we construct the feature representation of the target city through adaptive feature fusion and infer its fine-grained urban flows through the designed urban flow upsampler. Extensive experiments conducted on four large real-world datasets demonstrate the effectiveness of our approach.

Clustering is a fundamental task in data mining , aiming to group similar objects together based on their features or attributes. With the rapid increase in data analysis volume and the growing complexity of high-dimensional data distribution , clustering has become increasingly important in numerous applications, including image analysis, text mining, and anomaly detection . DBSCAN is a powerful tool for clustering analysis and is widely used in density-based clustering algorithms . However, DBSCAN and its variants encounter challenges when confronted with datasets exhibiting clusters of varying densities in intricate high-dimensional spaces affected by significant disturbance factors . A typical example is multi-density clustering connected by a few data points with strong internal correlations, a scenario commonly encountered in the analysis of crowd mobility. To address these challenges, we propose a Self-adaptive Density-Based Clustering Algorithm for Varying Densities Datasets with Strong Disturbance Factor (SADBSCAN). This algorithm comprises a data block splitter, a local clustering module, a global clustering module, and a data block merger to obtain adaptive clustering results . We conduct extensive experiments on both artificial and real-world datasets to evaluate the effectiveness of SADBSCAN. The experimental results indicate that SADBSCAN significantly outperforms several strong baselines across different metrics, demonstrating the high adaptability and scalability of our algorithm.