High-utility sequential pattern mining (HUSPM) aims to uncover valuable sequential behaviors to support decision making across domains such as e-commerce analytics and Web interaction modeling. Despite extensions to multi-dimensional settings, existing methods remain limited by context-agnostic pruning that inflates candidate sets and degrades runtime performance, list-based utility storage whose memory footprint balloons as dimensionality grows, and the absence of parallel execution and adaptive Top-k control, which together constrain scalability on large datasets. To address these challenges, we propose a family of methods-MEU-Miner, PMEU-Miner, and TKMEU-Miner-for scalable multi-dimensional HUSPM (MDHUSPM) on commodity hardware. MEU-Miner couples bitset-driven context matching with a dimension-level utility bound (DUB) to enable safe pruning and supports incremental updates/caching of matching vectors and bounds; DUB is a safe upper bound guaranteed by the anti-monotonicity of the context lattice, ensuring that no valid multi-dimensional high-utility pattern is ever pruned. PMEU-Miner adopts a shared-memory parallel design (thread pool with work stealing and fine-grained critical sections) to obtain substantial multi-core speedups; and TKMEU-Miner provides threshold-free Top-k mining via an adaptive heap with bound-guided early termination. Our experiments span 19 datasets, including 13 real-world and 6 synthetic databases. Extensive experiments on 19 datasets show that MEU-Miner achieves up to 66 × speedups and reduces candidates by up to 80% over state-of-the-art MDHUSPM baselines; PMEU-Miner accelerates mining by up to 180 × through multi-threaded search; and TKMEU-Miner outperforms Top- k competitors by 10 × to 40 × across different values of k . Our framework also maintains stable memory usage as dimensionality increases, advancing the state of the art and enabling fast, reproducible pattern discovery in context-rich sequential data.

Panchromatic images (PANs) and multispectral (MS) images (MSs) are widely used for dual-source remote sensing image classification, gradually becoming a research hotspot. However, making the most of dual-source image information with insufficiently labeled samples is a significant challenge. This article proposes a progressive semi-distillation model (PSDM) to classify dual-source remote sensing images with insufficient samples. We design a framework of rookie teacher network (RTN)-teaching assistant system (TAS)-student grouping network (SGN) in the case of a traditional teacher network (TN) (i.e., rookie TN (RTN)) that does not provide excellent guidance to student network (SN) due to insufficient samples. The PSDM expands the samples and compresses the space through the RTN-SGN structure to cope with the dilemma of insufficient samples. To make RTN better guide the SGN, we design TAS, which can gradually guide SGN to learn the samples from easy to difficult. It can also further assist SGN training to improve the classification performance of SGN with insufficient samples. We design SGN and add cooperation and correction mechanism to better learn dual- source information. These strategies can eliminate SGN's over-dependence on the RTN, help SGN outperform the RTN, and achieve the effect of semi-distillation. Experimental results and theoretical analysis have sufficiently pointed out the proposed method's accuracy, efficiency, and robustness under insufficient sample situations. Our model is available at https://github.com/MarjordCpz/PSDM.

Advanced Persistent Threat (APT) defense requires the rational allocation of multiple types of security resources. Existing research has deficiencies in the rationality of security resource allocation in multi-stage attacks like APT. Since different attack methods may be adopted in different stages, defenders need to rationally allocate various security detection resources to capture attacking behaviors. Based on the GPLADD(Graph-based Probabilistic Learning Attacker and Dynamic Defender) game and the ATT&CK framework, this paper proposes the Dynamic Collaborative Allocation of Security Resources (DCASR) model to quantify the impact among different types of defense resources. Solutions are derived using evolutionary strategies and Q-learning with sample average approximation, aiming to maximize resource utilization and minimize the consumption of security resources within the defense activity time. The results of simulation experiments show that the generated strategies possess security and economic benefits and can provide theoretical and practical references for the allocation of security resources when defending against APT attacks.

Recently, incorporating knowledge from pretrained language models (PLMs) into decision transformers (DTs) has generated significant attention in offline reinforcement learning (RL). These PLMs perform well in RL tasks, raising an intriguing question: what kind of knowledge from PLMs has been transferred to RL to achieve such good results? This work first dives into this problem by analyzing each head quantitatively and points out Markov head, a crucial component that exists in the attention heads of PLMs. It leads to extreme attention on the last-input token and performs well only in short-term environments. Furthermore, we prove that this extreme attention cannot be changed by re-training embedding layer or fine-tuning. Inspired by our analysis, we propose a general method GPT-DTMA, which equips a pretrained DT with Mixture of Attention (MoA), to enable adaptive learning and accommodate diverse attention requirements during fine-tuning. Extensive experiments demonstrate the effectiveness of GPT-DTMA: it achieves superior performance in short-term environments compared to baselines, significantly reduces the performance gap of PLMs in long-term scenarios, and the experimental results also validate our theorems.

Reliable and continuous high-precision positioning is a fundamental requirement for navigation, guidance, and control of intelligent mobile platforms, such as autonomous vehicles, drones, and robots. However, achieving such positioning in complex urban environments remains a significant challenge due to GNSS signal obstructions and multipath effects. Moreover, traditional visual feature extraction algorithms struggle with variations in lighting, perspectives, and noise, limiting their adaptability. Consequently, relying solely on a single sensor often fails to provide a stable and accurate positioning solution. This paper addresses the challenges encountered in typical urban environments and proposes a Visual-Inertial-GNSS fusion positioning framework, in which deep learning-based feature extraction is applied to the visual front-end process. The deep learning-based feature extraction approach fully exploits image information to derive more accurate and robust features, thereby enabling reliable feature matching. Additionally, we introduce a K-means clustering-based outlier detection method to remove dynamic features and mismatched features, thereby enhancing optical flow tracking and overall positioning accuracy. Experimental results in urban environments demonstrate that the proposed approach achieves high-precision positioning results under challenging GNSS conditions and complex visual environments, with improvements of (29.6%, 10.0%, 7.3%) over SIFT and (47.8%, 7.8%, 15.5%) over ORB in the North-East-Down (N-E-D) directions. Moreover, in dynamic road environments, the proposed outlier detection method achieves accuracy improvements of 19.6%, 3.0%, and 4.0% in the N-E-D directions compared to the RANSAC-based method.

In recent years, with the rapid advancements and widespread application of satellite photography technology, it has become increasingly possible to obtain high-quality panchromatic (PAN) and multispectral (MS) data, which has provided new opportunities and challenges for multisource information fusion and classification research. Remote sensing data have the characteristics of small interclass differences and large intraclass differences, which easily leads to category confusion in network learning. In addition, how to fully tap the advantages of multisource data, better align multisource features, improve classification accuracy, and achieve collaborative classification are key issues that need to be solved urgently. In this article, a dual-path prototype feature decoupling alignment network (DPFDA-Net) is designed to solve the above issues. The network consists of two components: a prototype feature embedding (PFE) module and a feature alignment module (FAM) based on prototype decoupling. In the feature extraction stage, the PFE module uses the prototype concept to learn the discriminative prototype features of each category of the dual-source data separately, making the boundaries between categories more obvious. The FAM operates at the dual-source prototype feature level and achieves feature alignment by decoupling single-source prototype features and performing feature transformation to supplement the missing information of another data source. Finally, we use the aligned features for classification. The results of the experiment demonstrate that our approach has made significant progress in improving classification precision. The code is available athttps://github.com/Xidian-AIGroup190726/DPFDANet.

Large pretrained language models (LLMs) have shown surprising In-Context Learning (ICL) ability. An important application in deploying large language models is to augment LLMs with a private database for some specific task.The main problem with this promising commercial use is that LLMs have been shown to memorize their training data and their prompt data are vulnerable to membership inference attacks (MIA) and prompt leaking attacks. In order to deal with this problem, we treat LLMs as untrusted in privacy and propose a locally differentially private framework of in-context learning (LDP-ICL) in the settings where labels are sensitive. Considering the mechanisms of in-context learning in Transformers by gradient descent, we provide an analysis of the trade-off between privacy and utility in such LDP-ICL for classification. Moreover, we apply LDP-ICL to the discrete distribution estimation problem. In the end, we perform several experiments to demonstrate our analysis results

Recently, remote sensing technology has developed faster and faster, and obtaining high-quality panchromatic (PAN) and multispectral (MS) images has become more accessible. The complementarity between them provides new opportunities in multisource remote sensing image classification. However, solving the problem of the semantic gap between multisource high-level features and, at the same time, utilizing the complementary properties between them to reduce intersource information redundancy is still a challenge. This article constructs an$I^{3}$RL-Net for the multisource remote sensing image classification task. Specifically, we design a cross-source interactive enhanced fusion module (CIEF-Module). For multilevel multisource features, by strengthening the dependencies of intrasource features and conducting intersource enhanced fusion, intrasource correlation features are refined, and the problem of the intersource semantic gap can be effectively alleviated. During the cross-source interaction process, we design a complementary representation supervised learning strategy (CRSL-Strategy). According to the similarities and differences of multisource features, it can adaptively promote complementary feature learning, thus generating a nonredundant multisource representation. The method has been verified to be effective on multiple RS datasets. The code is open source at:https://github.com/Xidian-AIGroup190726/Ping-Pie-I3RL-Net.git.

With the development of remote sensing technology, remote sensing object detection has been widely applied in various fields, but it still faces some thorny challenges, such as the following: 1) the complexity of object scale changes in remote sensing images makes it difficult to improve the performance of small object detection and 2) remote sensing images have complex backgrounds and densely arranged small and weak objects, which pose a serious problem of feature interference. To alleviate these challenges, we propose an end-to-end adaptive feature separation network called AFSNet, which includes a scale-aware module (SAM) and a class-aware module (CAM). The SAM mainly enables feature maps of different resolutions to detect objects of different scales. Shallow feature maps mainly suppress the features of large objects they contain to focus on small object detection, while deep feature maps increase the detailed features of large objects they contain to focus on large object detection. The CAM is mainly used to distinguish the features in the feature map by category, separating the features of different categories into different channels, thus mitigating the problem of inter class feature interference, and blocking background interference. The effectiveness of this article has been proven on the NWPU VHR-10, IPIU-M, DIOR, and DOTA2.0 datasets. It can be widely applied in civilian, military, and other fields. Through experimental verification, our AFSNet achieved 97.70% mAP on the NWPU VHR-10 dataset, 78.9% mAP on the DIOR dataset, and 58.22% mAP on the DOTA2.0 dataset. Our code is available at:https://github.com/Xidian-AIGroup190726/AFSNet.

In recent years, panchromatic (PAN) images and multispectral (MS) images, as a type of multimodal remote sensing data, are attracting increasingly more attention to their classification problems. However, effectively representing size variations of targets in remote sensing images and reducing redundant representations of different modalities’ deep semantic features to enhance classification accuracy remains a challenge. In this article, we propose a semantically nonredundant continuous-scale feature network (SNCF-Net) for PAN and MS classification, consisting of two modules: the texture-enhanced continuous scale input generation module and the cross-modal feature Kernel interaction (CMKI) module. By simulating the human eye’s adjustment of distance to observe objects of different sizes, we employ 3-D convolution to extract continuous-scale images generated by the texture-enhanced continuous-scale input generation (TCIG) module, enabling optimal feature representation of objects in remote sensing images. Additionally, the texture enhancement (TE) strategy in the TCIG module alleviates texture diffusion in scale space, enhancing the network’s ability to represent texture features. Subsequently, the CMKI module utilizes the response differences between different features to generate convolution kernels from deep feature maps, enabling feature interaction between the PAN modal and MS modal. This reduces redundant representations of essential image content information in deep features of two modalities, facilitating a better mapping between dual-modal features and categories. Our results achieve state-of-the-art performance on multiple datasets. The code is available athttps://github.com/Xidian-AIGroup190726/SNCFNet.

To minimize the feature redundancy of multispectral (MS) and panchromatic (PAN) images and maximize the complementary advantages of PAN and MS, a Dual-Stream Transformer with Diff-attention (DSTD)-Net is proposed for PAN and MS classification in this paper. Firstly, in terms of feature extraction, we use Self-attention and Co-attention (SCA) block to extract both specific advantageous features and common essential features. Based on that, a self-attention module strengthened by diff-attention (SSDA) that pays attention to the difference between two specific advantageous features is designed to reduce the essential redundancy in specific features. It can take advantage of the difference between two specific features and reduce the essential redundancy of the specific advantageous features, making them purer and better for classification. Finally, since the specific features and common features of multispectral (MS) and panchromatic (PAN) images make different contributions to classification, a Multi-stage Gated Fusion (MGF) strategy is used. The MGF strategy mainly uses Gated multisource units (GMU) to adapt the weight of different features and fuse them. So, our MGF strategy can strengthen the specific advantageous features beneficial for classification. Above all, the several experiment results verify our proposed networks’ effectiveness and robustness. Our code is available at: https://github.com/blackkiring/DSTD.

The phenomenon of unbalanced regional medical resources has led to large differences in the implementation experience of clinical pathways in hospitals with different medical levels. However, due to the fear of privacy leakage and the lack of sharing motivation, there is a lack of effective collaborative communication channels for clinical pathways among medical institutions. In response to these problems, we propose a blockchain-based sharing incentive scheme for clinical pathway experience, which uses the clinical pathway implementation effect evaluation system to evaluate the quality of clinical pathway experience data. Specifically, we designe a two-phase cross-domain shared transaction model for the transaction of clinical pathway experience data. Moreover, we introduce the shared transaction alliance committee to verify and review the transaction, and solve the problems in the transaction in the arbitration phase. Finally, the functional test results show that the system meets the experience sharing incentive requirements, and the performance test results show that the TPS of sharing clinical pathway experience read and writed can reach around 600 and 1000, and the transaction latency of each phase is within 3 s.