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.

Wearable sensor-based Human Activity Recognition (WHAR) is an important application field that uses sensors for measurement, especially the broad application scenarios in human-computer interaction. Despite the strides made by deep learning-based approaches, practical issues like deployment on edge devices are often overlooked due to their dependence on massive network layers that require extensive computational and storage resources. This paper proposes a novel approach named Eff-WHAR, which aims to improve recognition accuracy and reduce computational burden in the context of WHAR, especially for practical applications on edge devices. The overall approach consists of two parts: Multiscale Temporal Embedding Network and Channel Mixing Network . The first part involves utilizing convolution operations with varying receptive fields in the temporal dimension to extract and merge features from the input data. It facilitates a more comprehensive understanding of different behaviors, resulting in enhanced accuracy. In the second part, features are extracted and fused in the sensing channel dimension through a combination of intra-channel and inter-channel convolutions. It is better to reduce computational cost and model size by replacing the traditional 2D convolution and attention mechanisms, which are commonly used but require a lot of computing power and storage, making them unsuitable for devices with limited resources. We validated Eff-WHAR on eight commonly used WHAR datasets, obtaining outstanding performance compared with SOTA approaches. In addition, we conducted experiments in actual edge devices, verifying the practicality and efficiency of our approach.

Harmful Algal Blooms (HAB), a significant environmental concern on a global scale, are damaging to ecosystem functions and pose challenges to environmental management. The key to HAB management is to classify the local representative species. However, the widespread adoption of automated monitoring devices such as the Imaging FlowCytobot (IFCB) is cost-prohibitive and often cannot be efficiently utilized. An algae classification algorithm based on transfer learning designed to classify local algal species with limited low-cost microscope-based algae images is developed to offer a cost-effective and practical solution for HAB management. The model is tested on the Macau representative freshwater algae dataset. The training process of the transfer learning model is based on the automatically captured open-source dataset and IFCB-based Hong Kong tropical algal dataset. The results demonstrated the exceptional performance of our method, achieving up to 100% accuracy in the classification of single algal species. Furthermore, when compared with commonly used deep learning models in experimental comparisons, our method exhibited superior performance. We also conducted ablation experiments on transfer learning, which validated the effectiveness of our transfer learning approach.

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.