This paper presents a vehicle detection and classification system using distributed fiber-optic acoustic sensing (DAS) technology and describes a comprehensive classification method including signal processing and feature extraction. This sensing device is based on Rayleigh scattering light and is used for real-time vehicle detection, classification, and speed estimation. Distributed acoustic signals from an arbitrary point can be detected and located through DAS technology which can provide fully distributed acoustic information along the entire fiber link. This technology utilizes sensing fiber in the form of distributed sensors to collect traffic vibration signals and then extracts several features from the signals to estimate the vehicle count and identify vehicle categories. According to the vehicle vibration signal characteristics, the wavelet-denoising algorithm and dual-threshold algorithm are improved. The improved algorithm is used to reconstruct the signal for feature extraction, and the vehicle count and speed are obtained. When all features have been extracted, the classification of vehicle types is implemented by a support vector machine classifier. The validation data (using a distributed fiber-optic acoustic sensor) demonstrate that the vehicle detection accuracy is higher than 80%, the speed estimation error is less than 5%, and the vehicle classification accuracy is higher than 70%.

Distributed Acoustic Sensing (DAS) is a novel technology that uses fiber optics to sense and monitor vibrations. It has demonstrated immense potential for various applications, including seismology research, traffic vibration detection, structural health inspection, and lifeline engineering. DAS technology transforms long sections of fiber optic cables into a high-density array of vibration sensors, providing exceptional spatial and temporal resolution for real-time monitoring of vibrations. Obtaining high-quality vibration data using DAS requires a robust coupling between the fiber optic cable and the ground layer. The study utilized the DAS system to detect vibration signals generated by vehicles operating on the campus road of Beijing Jiaotong University. Three distinct deployment methods were employed: the uncoupled fiber on the road, the underground communication fiber optic cable ducts, and the cement-bonded fixed fiber optic cable on the road shoulder, and compared for their outcomes. Vehicle vibration signals under the three deployment methods were analyzed using an improved wavelet threshold algorithm, which was verified to be effective. The results indicate that for practical applications, the most effective deployment method is the cement-bonded fixed fiber optic cable on the road shoulder, followed by the uncoupled fiber on the road, and the underground communication fiber optic cable ducts are the least effective. This has important implications for the future development of DAS as a tool for various fields.

In engineering applications, many complex problems can be formulated as mathematical optimization challenges, and efficiently solving these problems is critical. Metaheuristic algorithms have proven highly effective in addressing a wide range of engineering issues. The Snake Optimization Algorithm (SO) is a novel metaheuristic method with widespread use. However, SO has limitations, including reduced search efficiency in later stages and a tendency to get trapped in local optima, preventing full exploration of the solution space. To overcome these, this paper introduces the Multi-strategy Improved Snake Optimization Algorithm (ISO), which integrates six key strategies. First, the Sobol sequence is used for population initialization, ensuring uniform distribution and enhancing global exploration. Second, the RIME algorithm accelerates convergence and improves exploitation. Lens reverse learning further promotes exploration, avoiding local optima. Levy flight facilitates large random steps, balancing exploration and refinement. Adaptive step-size adjustment dynamically tunes the step size based on fitness, optimizing exploration-exploitation. Lastly, the Brownian random walk introduces local perturbations to fine-tune solutions. These strategies collectively improve convergence speed, stability, and optimization capability, ensuring an effective balance between exploration and exploitation. The ISO population distribution was evaluated using three uniformity algorithms: Average Nearest Neighbor Distance, Star Discrepancy, and Sum of Squared Deviations (SSD). ISO demonstrated improvements of 63.08%, 26.09%, and 8.88%, respectively, over SO. Its exploration-exploitation balance and convergence were analyzed on the 30-dimensional CEC-2017 benchmark functions. Additionally, ISO was tested on 23 classic benchmark functions, CEC-2011, and CEC-2017 benchmark functions. Results showed ISO’s superior performance in convergence speed, stability, and global optimization. Furthermore, ISO was successfully applied in four engineering domains: UAV path planning, robot path planning, wireless sensor network node deployment, and pressure vessel design. In all cases, ISO outperformed SO with rapid convergence and strong robustness, achieving performance improvements of 5.69%, 34.61%, 20.73%, and 7.8%, respectively, underscoring its superior efficacy in practical applications.

In aerospace, robotics, network engineering and mechanical engineering, there exist complex and urgent challenges that can be abstracted into mathematical optimization problems. Therefore, exploring solutions to these optimization problems is a crucial task. Metaheuristic algorithms have been applied across various fields.The Snake Optimization Algorithm (SO) is an innovative metaheuristic method recognized for its efficient solving capabilities.However, this algorithm encounters challenges such as diminished search efficiency in the later stages and a propensity to become ensnared in local optima. To mitigate these issues, this paper introduces an enhanced Snake Optimization Algorithm (ISO). ISO integrates the RIME Algorithm(RIME)and introduces two effective enhancement strategies to improve its capability to evade local optima.To assess the effectiveness of ISO,the population distribution state was first measured using three algorithms, including Star Discrepancy, and the exploration and exploitation performance was analyzed using the CEC2017 test functions. Subsequently, utilized 23 benchmark functions for testing.The evaluation outcomes indicate that ISO exhibits outstanding performance in terms of convergence velocity and robustness.Additionally, it was applied to engineering fields including UAV path planning,Robot path planning, Wireless sensor network node deployment and Pressure vessel design.In comparison to the SO algorithm, the ISO algorithm demonstrates superior stability, converges earlier, and improves its ability to solve for optimal .These findings highlight the significant potential of the ISO algorithm in diverse test functions and a wide range of interdisciplinary problems.

Traditional Agent-based Models (ABMs) often struggle to capture the nuance of adaptive human decision-making during complex crises due to their reliance on static, predefined rules. Large Language Models (LLMs) offer a transformative solution by acting as cognitive engines that empower agents with human-like common-sense reasoning. In this paper, we introduce an LLM-driven Multi-Agent Simulation framework to investigate coupled epidemic–economic dynamics, incorporating a Perception-Deliberation-Action (PDA) loop. Agents, acting as heterogeneous cognitive entities, utilize Chain-of-Thought processes to autonomously balance health risks against economic necessities. This approach endogenously generates adaptive behaviors without explicit scripting. Extensive experiment results across diverse LLM backends confirm the framework’s robustness, revealing divergent socio-economic trajectories under distinct macroscopic conditions and effectively quantifying the trade-offs between public health and economic stability. This approach establishes a high-fidelity computational laboratory for investigating complex scenarios under distinct macroscopic conditions, effectively bridging the gap between micro-level cognition and macro-level societal outcomes.