Human activity recognition using sensor data has become a research hotspot in the field of ubiquitous computing and has a wide range of application scenarios in real life. Effectively extracting and fusing the rich spatiotemporal information contained in the sensor data from various sensors and multiple wearable devices is a challenging task. Moreover, for practical deployment applications, the limited computational and storage resources of edge devices also impose requirements on the model size and inference speed. Hence, we propose STFNet, an enhanced and lightweight spatiotemporal fusion network for wearable human activity recognition. In which, we innovatively divide the extraction and fusion process of spatiotemporal features into three stages, including sensing feature extraction, temporal feature extraction, and channel fusion, to learn incrementally and reduce information loss. We first extract shallow intra-channel features and learn local inter-channel information by using a lightweight local attention mechanism. Then, the learned features are fed into a hierarchical convolution structure with residual connections to extract multi-scale and comprehensive temporal features. Finally, we use graph convolutions to further fuse the deep inter-channel information. By replacing the conventional global attention mechanism with a local one and using hierarchical convolution to replace dilated or multi-kernel convolution, STFNet achieves the purpose of lightweight design. In the experiments, STFNet performs better on public datasets than the selected WHAR models published in recent years and demonstrates its lightweight characteristics on edge device deployment.

With the rapid development of modern information technology, e-commerce has become an integral part of our daily life, which demands intelligent and highly efficient logistics systems. Currently, fixed partitioning methods are widely adopted. To optimize delivery efficiency, this work introduces a changing distribution partitioning network. The core of this network is the concept of reachable distance, whose use enables us to well balance delivery workloads of couriers. The optimization problem addressed in this work consists of two classic NP-hard problems: Distribution Partitioning and Vehicle Routing ones. To solve it, we propose a Simulated-Annealing-Assisted Artificial Hummingbird Algorithm (SAHA), such that its total transportation cost is minimized. Through experimental validation, we determine that setting the reachable distance to 40% of the distance to the nearest distribution center yields optimal or near-optimal performance. Compared to the traditional community logistics algorithm, SAHA reduces the total transportation distance by approximately 8% and shortens the convergence time by 59%. Additionally, we confirm the robustness of SAHA across both small-scale suburban and high-density urban environments. These results underscore the strong potential of SAHA to enhance operational efficiency and adaptability in smart logistics systems.

With the advancement of internet technology, there has been a surge in network communication and applications, accompanied by an increasing prevalence of cybersecurity issues. The detection of encrypted traffic stands as a critical measure for ensuring network security, and its significance is self-evident. While current deep learning-based techniques for encrypted traffic detection have achieved high detection precision, several shortcomings remain to be addressed. First, most approaches rely primarily on packet-level features, neglecting valuable session-level traffic features, which limits detection performance. Second, while a few studies have explored session-level detection, they are often restricted to fixed-length traffic and require extensive preprocessing, reducing practicality and adaptability. In light of these issues, we propose a novel encrypted traffic detection approach, EMLF-ETD, which facilitates the detection of variable-length encrypted traffic by fusing multi-level network traffic features. EMLF-ETD innovatively proposes the concept of a hierarchical information network traffic graph, which enhances the flexibility of data input forms for encrypted traffic, thereby facilitating the representation of intra-packet information at the packet level and inter-packet relationships at the session level. It further incorporates a Traffic Packet Embedding module and a Traffic Session Embedding module, designed to extract and fuse packet- and session-level features from graph-structured data. The proposed architecture effectively overcomes the limitations of prior methods in handling variable-length traffic. To ascertain the effectiveness of the EMLF-ETD approach, we conducted experiments on various public datasets. The results demonstrate that our approach outperforms baseline techniques in terms of detection precision and data adaptability.