Small object detection in UAV imagery remains challenging due to complex aerial perspectives and the presence of dense, small targets with blurred boundaries. To address these challenges, we propose ACD-DETR, an adaptive end-to-end Transformer detector tailored for UAV-based small object detection. The framework introduces three core modules: the Multi-Scale Edge-Enhanced Feature Fusion Module (MSEFM) to preserve fine-grained details; the Omni-Grained Boundary Calibrator (OG-BC) for boundary-aware semantic fusion; and the Dynamic Position Bias Attention-based Intra-scale Feature Interaction (DPB-AIFI) to enhance spatial reasoning. Furthermore, we introduce ACD-DETR-SBA+, a fusion-enhanced variant that removes OG-BC and DPB-AIFI while deploying densely connected Semantic–Boundary Aggregation (SBA) modules to intensify boundary–semantic fusion. This design sacrifices computational efficiency in exchange for higher detection precision, making it suitable for resource-rich deployment scenarios. On the VisDrone2019 dataset, ACD-DETR achieves 50.9% mAP@0.5, outperforming the RT-DETR-R18 baseline by 3.6 percentage points, while reducing parameters by 18.5%. ACD-DETR-SBA+ further improves accuracy to 52.0% mAP@0.5, demonstrating the benefit of SBA-based fusion. Extensive experiments on the VisDrone2019 and DOTA datasets demonstrate that ACD-DETR achieves a state-of-the-art trade-off between accuracy and efficiency, while ACD-DETR-SBA+ achieves further performance improvements at higher computational cost. Ablation studies and visual analyses validate the effectiveness of the proposed modules and design strategies.

The development of 5G technology has driven the rise of e‐commerce, social networking, and the Internet of Things. Under the high‐speed transmission, the data volume increases, and the user demand also changes. Personalized customization has become the mainstream trend of network development. However, as the speed of the Internet increases, a series of problems also arise. The increase in data volume results in a reduction of bandwidth, a growth of the central processor’s pressure, and a higher risk of data leakage. A search system and a recommendation platform are the tools to improve people’s search efficiency. However, providing personalized recommendations to different users according to their needs is still an urgent problem. Simultaneously, the big data volume means that attackers can also get more information. They can use background knowledge and various reasoning methods to deduce the user’s private information using nonprivate items. In this paper, the solutions to safe and reliable recommendation services are the main problem explored. Based on this idea, this paper proposed short‐term dynamic recommendation model based on local differential privacy (SDRM‐LDP). This model uses a small amount of user information to construct short‐term user preference behaviors and provides recommendations for users based on the similarity between items. We consider that an attacker uses nonprivate items to derive privacy items. Therefore, we randomly replace the original data in the same category. At the same time, the local differential privacy (LDP) is added to the privacy item query to make the private data available and protect the privacy information. In this paper, two real‐world datasets, ML‐100K and ML‐10M, are used for experiments. Experimental results show that the results of SDRM‐LDP are superior to other models.

The rapid development of the Global Positioning System (GPS) devices and location‐based services (LBSs) facilitates the collection of huge amounts of personal information for the untrusted/unknown LBS providers. This phenomenon raises serious privacy concerns. However, most of the existing solutions aim at locating interference in the static scenes or in a single timestamp without considering the correlation between location transfer and time of moving users. In this way, the solutions are vulnerable to various inference attacks. Traditional privacy protection methods rely on trusted third‐party service providers, but in reality, we are not sure whether the third party is trustable. In this paper, we propose a systematic solution to preserve location information. The protection provides a rigorous privacy guarantee without the assumption of the credibility of the third parties. The user’s historical trajectory information is used as the basis of the hidden Markov model prediction, and the user’s possible prospective location is used as the model output result to protect the user’s trajectory privacy. To formalize the privacy‐protecting guarantee, we propose a new definition, L&A‐location region, based on k‐anonymity and differential privacy. Based on the proposed privacy definition, we design a novel mechanism to provide a privacy protection guarantee for the users’ identity trajectory. We simulate the proposed mechanism based on a dataset collected in real practice. The result of the simulation shows that the proposed algorithm can provide privacy protection to a high standard.

With the explosive growth of mobile data, mobile crowd sensing (MCS) has become a popular paradigm for large-scale data collection. The difficulty of data collection and the gaps in workers’ sensing capabilities are key factors to consider in worker recruitment and task assignment. To address these issues, we designed a two-stage cooperative incentive mechanism. In the first stage, a shelving level is introduced to assess task difficulty. Tasks are divided into high-quality and low-quality groups based on quality scores, while workers are categorized into high-ability and low-ability groups based on their historical performance. The improved chaotic particle swarm optimization (ICPSO) algorithm is then applied to generate optimal task combinations. In the second stage, we address benefit distribution among cooperating workers by introducing time-dependent rewards and employing Stackelberg game theory to analyze the optimal completion time for both high-ability and low-ability workers. This analysis determines the optimal reward distribution and ability value allocation, with proof of the existence and uniqueness of a Nash equilibrium. Comparative experiments conducted on real-world datasets demonstrate that our cooperative task mechanism outperforms existing task bundling methods, validating its rationality and effectiveness.

To elevate AI tutors from simple chatbots to genuine pedagogical partners, this study introduces a novel diagnosis-driven methodology for adaptive Socratic teaching. Current LLM-based tutors often lack the deep diagnostic capabilities required for authentic Socratic dialogue, resulting in superficial interactions. Our approach overcomes this by tightly coupling a real-time, multi-dimensional student cognitive model with the dialogue generation process. This methodology is implemented within a multi-agent system where: a Planner Agent first dynamically structures learning paths from raw documents; a Diagnoser Agent continuously assesses student mastery to create precise cognitive reports; and a Tutor Agent leverages these reports to conduct targeted, high-quality Socratic questioning. Experimental results demonstrate the superiority of our diagnosis-driven method. In blind comparisons, Our system achieved an average win rate of 82% against baseline systems, showing decisive advantages in "Socratic style" and teaching effectiveness. This study confirms that a deep diagnostic mechanism is the key to unlocking personalized and effective Socratic teaching in AI tutors.