Abstract.To address the threat posed by precision-guided missiles to ground targets in modern warfare, this study focuses on optimizing deployment strategies for smoke screen interference bombs using unmanned aerial vehicles . The research examines two typical scenarios: single-drone-single-bomb and multi-drone-multi-bomb operations. A geometric shielding model based on Newtonian kinematics is established to determine the intersection conditions between smoke cloud clusters and missile-target line-of-sight, enabling precise calculation of shielding duration. For single-drone scenarios, an improved … Read more →

Abstract.This study addresses the challenges of precisely determining dynamic target indicators and optimizing single-resource allocation strategies. For effective coverage of cylindrical targets by resources within a specific airspace, we first establish the kinematic equations governing the motion of missiles, resource carriers, and deployed resources. To accurately calculate effective engagement duration, we construct a cylindrical occlusion indicator function, which determines occlusion status based on the minimum distance between the line-of-sight and the center of the resource cloud. To enhance … Read more →

Abstract.This study aims to quantify the effective duration of concealment provided by a single smoke grenade against an incoming missile, thereby optimizing the deployment strategy for drone smoke decoy grenades. Following a problem decomposition—model construction—precise solution framework, this work employs kinematic modeling and geometric detection. Within a unified coordinate system, it extracts the shielding time window and cumulative shielding duration through time-domain scanning with a fixed time step. To investigate aerodynamic effects, the model performs dynamic comparisons between … Read more →

Abstract.Road distress inspection plays a critical role in pavement-condition assessment and maintenance planning. However, existing studies often address detection, segmentation, or measurement separately, which limits their practical applicability. This paper proposes an integrated deep learning–based framework for road distress detection, pixel-level segmentation, and quantitative evaluation. First, an improved YOLOv7 detector is developed by introducing SE attention, CARAFE-based content-aware upsampling, and a Dynamic Head to enhance multi-scale feature representation and robustness under complex … Read more →

Abstract.With the rapid advancement of artificial intelligence, computer vision, speech recognition, and natural language processing, automatic depression detection based on multimodal data has attracted increasing research attention. Compared with unimodal approaches, multimodal fusion leverages complementary information from speech, text, facial expressions, and other behavioral cues, thereby improving the accuracy and robustness of depression assessment. However, existing multimodal models are often computationally intensive and parameter-heavy, which limits their deployment on resource-constrained … Read more →