Convolutional Neural Networks (CNNs) have achieved remarkable results in the computer vision field. However, the newly proposed network architecture has deeper network layers and more parameters, which is more prone to overfitting, resulting in reduced recognition accuracy of the CNNs. To improve the recognition accuracy of the model of image recognition used in CNNs and overcome the problem of overfitting, this paper proposes an improved data augmentation approach based on mosaic algorithm, named Dynamic Mosaic algorithm, to solve the problem of the information waste caused by the gray background in mosaic images. This algorithm improves the original mosaic algorithm by adding a dynamic adjustment step that reduces the proportion of gray background in the mosaic image by dynamically increasing the number of spliced images. Moreover, to relieve the problem of network overfitting, also a Multi-Type Data Augmentation (MTDA) strategy, based on the Dynamic Mosaic algorithm, is introduced. The strategy divides the training samples into four parts, and each part uses different data augmentation operations to improve the information variance between the training samples, thereby preventing the network from overfitting. To evaluate the effectiveness of the Dynamic Mosaic algorithm and the MTDA strategy, we conducted a series of experiments on the Pascal VOC dataset and compared it with other state-of-the-art algorithms. The experimental results show that the Dynamic Mosaic algorithm and MTDA strategy can effectively improve the recognition accuracy of the model, and the recognition accuracy is better than other advanced algorithms.

Data security and user privacy are two main security concerns in the cold-chain logistics system (CCLS). Many security issues exist in traditional CCLS, destroying data security and user privacy. The digital signature can provide data verification and identity authentication based on the mathematical difficulty problem for logistics data sharing in CCLS. This paper first established a blockchain-enabled cold-chain logistics system (BCCLS) based on union blockchain technology, which can provide secure data sharing among different logistics nodes and guarantee logistics data security with the untampered blockchain ledger. Meanwhile, a lattice-based undeniable signature scheme is designed to strengthen the security of logistics data and user privacy against quantum attacks. This scheme is based on the lattice assumption, which can provide anti-quantum security for BCCLS in the future quantum computer age. It also establishes the undeniable mechanism that guarantees that the actual signer cannot deny a valid signature. Then, security proof shows that this undeniable signature scheme is correct and safe, and an efficiency comparison shows that it is more efficient than other schemes in similar literature. The performance evaluations of transaction throughput and latency show that the proposed BCCLS is efficient and practical. This work can improve the security and efficiency of logistics data management and promote the reform and development of the logistics industry.

Exploring the spatiotemporal evolution of urban and rural settlements in African countries could provide critical insights into the patterns of urbanization, regional disparities, and sustainable development in the context of rapid socio-economic and demographic changes. Using global human settlement data alongside multi-source socio-economic and environmental datasets, this study investigates the spatiotemporal dynamics of human settlements in Tanzania from 1975 to 2020. A combination of methods, including hotspot analysis, standard deviation ellipse analysis, and geographic detectors, is employed to examine the characteristics of settlement evolution and the underlying factors contributing to regional differentiation. The findings reveal that over the past 45 years, the expansion of urban centers and urban clusters in Tanzania has significantly accelerated, while rural areas have experienced a corresponding decline, reflecting a shift from low-density to high-density settlements and a transformation from rural to urban landscapes. Dar es Salaam, Mwanza, and Arusha have consistently been hotspots for urban center growth, while Kagera has emerged as a primary hotspot for urban clusters. The distribution of rural hotspots and coldspots generally mirrors that of urban clusters. The spatial distribution of urban centers, urban clusters, and rural areas follows a northwest–southeast orientation, with the spatial distribution of urban centers gradually stabilizing. However, the development gap between urban clusters in the northwest and rural areas in the southeast is widening and narrowing, respectively. Socio-economic factors exert a stronger influence on the development of settlements than natural environmental factors. Population density, GDP density, and road network density are significant drivers of settlement patterns, with their influence intensifying over time.