With the development of artificial intelligence technology, UAVs have the ability to perceive the environment. UAV combined with target detection technology for road environment perception has received extensive attention. However, the complexity and variability of real-world road environments pose challenges for target detection. To address these challenges, we propose a UAV small target detection algorithm AS-YOLOV5 with adaptive feature fusion and improved attention mechanism. In the feature extraction phase, AS-YOLOV5 employs soft pooling to bolster the feature extraction network, mitigating the loss of critical edge information of small targets inherent in standard down-sampling techniques. Our feature fusion method incorporates learnable parameters, effectively rebalancing feature layers to ensure small target information remains significant during the fusion process and is not obscured by large target features. The subspace attention module is optimized to enhance the representation of small target features while suppressing background interference. To ensure the detection branch captures essential shallow information about small objects, we introduce an additional feature extraction layer for feature fusion. Simulation results show that the proposed method outperforms the existing algorithms. AS-YOLOV5 achieved a mean average precision (mAP) of 56.36% on the BDD100K data set and an impressive 93.33% on the KITTI data set with an Intersection over Union (IoU) threshold of 0.5.

In cross-border transactions, the transmission and processing of logistics information directly affect the trading experience and efficiency. The use of Internet of Things (IoT) technology can make this process more intelligent, efficient, and secure. However, most traditional IoT logistics systems are provided by a single logistics company. These independent systems need to withstand high computing loads and network bandwidth when processing large-scale data. Additionally, due to the complex network environment of cross-border transactions, the platform’s information security and system security are difficult to guarantee. To address these challenges, this paper designs and implements an intelligent cross-border logistics system platform that combines serverless architecture and microservice technology. This system can uniformly distribute the services of all logistics companies and divide microservices based on actual business needs. It also studies and designs corresponding Application Programming Interface (API) gateways to solve the interface exposure problem of microservices, thereby ensuring the system’s security. Furthermore, asymmetric encryption technology is used in the serverless architecture to ensure the security of cross-border logistics data. The experiments show that this research solution validates the advantages of combining serverless architecture and microservices, which can significantly reduce the operating costs and system complexity of the platform in cross-border logistics scenarios. It allows for resource expansion and billing based on application program requirements at runtime. The platform can effectively improve the security of cross-border logistics service processes and meet cross-border transaction needs in terms of data security, throughput, and latency.

Internet of Things (IoT) finance extends financial services to the whole physical commodity society with the help of IoT technology to realize financial automation and intelligence. However, the security of IoT finance still needs to be improved. Blockchain has the characteristics of decentralization, immutability, faster settlement, etc., and has been gradually applied to the field of IoT finance. Blockchain is also considered to be an effective way to resolve the problems of the traditional supply chain finance industry, such as the inability to transmit core enterprise credit, the failure of full-chain business information connections and the difficulty of clearing and settlement. Supply chain finance allows the strongest enterprise in the supply chain to apply for credit guarantee from the bank to obtain bank loans, and use the funds for circulation in the supply chain to ensure that each enterprise in the whole supply chain can obtain working capital to realize profits, so as to maximize common interests. In this paper, a financial management platform based on the integration of blockchain and supply chain has been designed and implemented. Blockchain is used to integrate supply chain finance to synchronize the bank account payment system, realize the automatic flow of funds, process supervision and automatically settle account periods based on smart contracts. The four functional modules of the system are designed using unified modeling language (UML), and the model view controller (MVC) architecture is selected as the main architecture of the system. The results of the system test show that the proposed platform can effectively improve the system security, and can use the information in the blockchain to provide multi-level financing services for enterprises in supply chain finance.

The rapid development of Internet of Things (IoT) communication devices has brought about significant convenience. However, simultaneously, the destruction of communication infrastructure in emergency situations often leads to communication disruptions and challenges in information dissemination, severely impacting rescue operations and the safety of the affected individuals. To address this challenge, IoT big data analytics and unmanned aerial vehicle (UAV) technologies have emerged as key elements in the solution. By analyzing large-scale sensor data, user behavior, and communication traffic, IoT big data analytics can provide real-time communication demand prediction and network optimization strategies, offering decision support for post-disaster communication reconstruction. Given the unique characteristics of post-disaster scenarios, this paper proposes a UAV-assisted communication coverage strategy based on IoT big data analytics. This strategy employs UAVs in a cruising manner to assist in communication by partitioning the target area into multiple cells, each satisfying the minimum data requirements for user communication. Depending on the distribution characteristics of users, flight–communication or hover-communication protocols are selectively employed to support communication. By optimizing the UAV’s flight speed and considering the coverage index, fairness index, and average energy efficiency of the mission’s target area, the Inner Spiral Cruise Communication Coverage (IS-CCC) algorithm is proposed to plan the UAV’s cruising trajectory and achieve UAV-based communication coverage. Simulation results demonstrate that this strategy can achieve energy-efficient cruising communication coverage in regions with complex user distributions, thereby reducing energy consumption in UAV-based communication.

With the rapid advancement of Unmanned Aerial Vehicle (UAV) technology, UAV swarms are being extensively applied in various fields, such as intelligent transportation, search and rescue, logistics delivery, and aerial mapping. However, the utilization of UAV swarms in sustainable transportation also presents some challenges, such as inefficient task allocation and data transmission security issues, highlighting the importance of privacy protection in this context. To address these issues, this study applies blockchain technology to multi-UAV tasks and proposes a blockchain-based multi-UAV task processing system for situation awareness and real-time decisions. The primary objective of this system is to enhance the efficiency of UAV swarm task scheduling, bolster data transmission security, and address privacy protection concerns. Utilizing the highly secure features of blockchain technology, the system constructs a distributed task processing network. System tasks are stored in the blockchain through smart contracts, ensuring the immutability and verifiability of task information. Smart contracts have an automatic execution capability, whereby the system can efficiently coordinate tasks and maintain the consistency of task execution information through consensus mechanisms. Additionally, adopting the Pointer Network structure for intelligent path planning based on task allocation results leads to the attainment of the shortest service routes, consequently expanding the service coverage of sustainable transportation systems while reducing energy consumption. This further advances the realization of urban sustainable transportation. Through experimental results, we verify that the proposed system enables real-time task scheduling and collaborative processing for multiple UAVs, significantly enhancing the efficiency, security, and privacy protection level of UAV swarm task execution in the context of sustainable transportation. It makes a positive contribution to building more sustainable urban transportation systems.

Abnormal electricity consumption behavior not only affects the safety of power supply but also damages the infrastructure of the power system, posing a threat to the secure and stable operation of the grid. Predicting future electricity consumption plays a crucial role in resource management in the energy sector. Analyzing historical electricity consumption data is essential for improving the energy service capabilities of end-users. To forecast user energy consumption, this paper proposes a method that combines adaptive noise-assisted complete ensemble empirical mode decomposition (CEEMDAN) with long short-term memory (LSTM) networks. Firstly, considering the challenge of directly applying prediction models to non-stationary and nonlinear user electricity consumption data, the adaptive noise-assisted complete ensemble empirical mode decomposition algorithm is used to decompose the signal into trend components, periodic components, and random components. Then, based on the CEEMDAN decomposition, an LSTM prediction sub-model is constructed to forecast the overall electricity consumption by using an overlaying approach. Finally, through multiple comparative experiments, the effectiveness of the CEEMDAN-LSTM method is demonstrated, showing its ability to explore hidden temporal relationships and achieve smaller prediction errors.