This paper studies UAV detection by multiple collaborative base stations in an integrated sensing and communication (ISAC) manner. In particular, we propose a computationally efficient UAV 3D localization and velocity estimation approach based on matched filtering (MF) to process the orthogonal frequency division multiplexing (OFDM) sensing signals. The proposed method consists of two main steps: a MF-based preprocessing step at each single base station to efficiently estimate distance, velocity, and angle parameters, and a symbol-level fusion step using a grid searching approach to integrate results from multiple base stations. Compared with traditional multiple signal classification (MUSIC)-based fusion techniques, our approach reduces the overall computational complexity by more than 98.5%. Meanwhile, it demonstrates significantly higher robustness in low SNR conditions (SNR ≤ 0 dB), as evidenced by a reduction in localization error from meter-level to centimeter-level accuracy. In positive SNR conditions (SNR > 0 dB), it also improves the localization and velocity estimation accuracy by approximately 33.5% and 26.3%, respectively. These results demonstrate the practical advantage of the proposed method in real-time UAV sensing application.

Point-to-Hyperplane Nearest Neighbor Search (P2HNNS) is a fundamental yet challenging problem, and it has plenty of applications in various fields. Existing hyperplane hashing schemes enjoy sub-linear query time and achieve excellent performance on applications such as large-scale active learning with Support Vector Machines (SVMs). However, they only conditionally deal with this problem with a strong assumption that all of the data objects are normalized, located at the unit hypersphere. Those hyperplane hashing schemes may be arbitrarily bad without this assumption. In this paper, we introduce a new asymmetric transformation and develop the first two provable hyperplane hashing schemes, Nearest Hyperplane hashing (NH) and Furthest Hyperplane hashing (FH), for high-dimensional P2HNNS beyond the unit hypersphere. With this asymmetric transformation, we demonstrate that the hash functions of NH and FH are locality-sensitive to the hyperplane queries, and both of them enjoy quality guarantee on query results. Moreover, we propose a data-dependent multi-partition strategy to boost the search performance of FH. NH can perform the hyperplane queries in sub-linear time, while FH enjoys a better practical performance. We evaluate NH and FH over five real-life datasets and show that we are around $3 \sim 100 \times$ faster than the best competitor in four out of five datasets, especially for the recall in $[20%, 80%]$. Code is available at \urlhttps://github.com/HuangQiang/P2HNNS.

Locality-Sensitive Hashing (LSH) is one of the most popular methods for c-Approximate Nearest Neighbor Search (c-ANNS) in high-dimensional spaces. In this paper, we propose a novel LSH scheme based on the Longest Circular Co-Substring (LCCS) search framework (LCCS-LSH) with a theoretical guarantee. We introduce a novel concept of LCCS and a new data structure named Circular Shift Array (CSA) for k-LCCS search. The insight of LCCS search framework is that close data objects will have a longer LCCS than the far-apart ones with high probability. LCCS-LSH is LSH-family-independent, and it supports c-ANNS with different kinds of distance metrics. We also introduce a multi-probe version of LCCS-LSH and conduct extensive experiments over five real-life datasets. The experimental results demonstrate that LCCS-LSH outperforms state-of-the-art LSH schemes.

Rare behaviors indicate important events and situations in maritime surveillance applications. State-of-the-art methods provide many effective solutions to detect anomalous behaviors. Meanwhile, most solutions are parameter-laden and too costly to identify useful rare behaviors with human knowledge in a visual analytics manner. This paper is concerned with a scheme cross trajectories, vessel attributes and the movement context for detecting rare behaviors through preprocessing, kNN-based clustering, and verification. Although the scheme involves several parameters, we demonstrate that they are able to be tackled in thresholds. As a result, a rare behavior factor is the single parameter that affect the detecting results. The proposed scheme is evaluated via a simulated data set for performance and a real life AIS data for effectiveness. Results show that high accuracy to labelled anomalies and useful rare behaviors can be achieved.

Nearest Neighbor Search (NNS) over generalized weighted space is a fundamental problem which has many applications in various fields. However, to the best of our knowledge, there is no sublinear time solution to this problem. Based on the idea of Asymmetric Locality-Sensitive Hashing (ALSH), we introduce a novel spherical asymmetric transformation and propose the first two novel weight-oblivious hashing schemes SL-ALSH and S2-ALSH accordingly. We further show that both schemes enjoy a quality guarantee and can answer the NNS queries in sublinear time. Evaluations over three real datasets demonstrate the superior performance of the two proposed schemes.