In recent years, You Only Look Once (YOLO) models have gradually been applied to medical image object detection tasks due to their good scalability and excellent generalization performance, bringing new perspectives and approaches to this field. However, existing models overlook the impact of numerous consecutive convolutions and the sampling blur caused by bilinear interpolation, resulting in excessive computational costs and insufficient precision in object detection. To address these problems, we propose a YOLOv8-based model using Efficient modulation and dynamic upsampling (YOLO-ED) to detect lung cancer in CT images. Specifically, we incorporate two innovative modules, the Efficient Modulation module and the DySample module, into the YOLOv8 model. The Efficient Modulation module employs a weighted fusion strategy to extract features from input CT images, effectively reducing model parameters and computational overhead. Furthermore, the DySample module is designed to replace the conventional upsampling component in YOLO, thereby mitigating information loss when expanding feature maps. The dynamic bilinear interpolation introduced by this module increases random bias, which helps minimize errors in feature extraction. To validate the effectiveness of YOLO-ED, we compared it with baselines on the LUNG-PET-CT-DX lung cancer diagnosis dataset and the LUNA16 lung nodule dataset. The results show that YOLO-ED significantly improves precision and reduces computational cost on these two datasets, demonstrating its superiority in the detection of medical images.

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.

Using wearable sensors to identify human activities has elicited significant interest within the discipline of ubiquitous computing for everyday facilitation. Recent research has employed hybrid models to better leverage the modal information of sensors and temporal information, enabling improved performance for wearable human activity recognition. Nevertheless, the lack of effective exploitation of human structural information and limited capacity for cross-channel fusion remains a major challenge. This study proposes a generic design, called GT-WHAR, to accommodate the varying application scenarios and datasets while performing effective feature extraction and fusion. Firstly, a novel and unified representation paradigm, namely Body-Sensing Graph Representation , has been proposed to represent body movement by a graph set, which incorporates structural information by considering the intrinsic connectivity of the skeletal structure. Secondly, the newly designed Body-Node Attention Graph Network employs graph neural networks to extract and fuse the cross-channel information within the graph set. Eventually, the graph network has been embedded in the proposed Bidirectional Temporal Learning Network , facilitating the extraction of temporal information in conjunction with the learned structural features. GT-WHAR outperformed the state-of-the-art methods in extensive experiments conducted on benchmark datasets, proving its validity and efficacy. Besides, we have demonstrated the generality of the framework through multiple research questions and provided an in-depth investigation of various influential factors.

The security of the Internet of Vehicles (IoV) has always been a concern. The constantly changing IoV data under varying traffic conditions made it unsuitable for the IoV to adopt traditional anti-attack techniques. In the absence of protections, attackers can use in-car communication as a target to compromise the safety of passengers, hence the instancy to detect the security state of the IoV. However, currently available solutions require modifications to the original hardware of the IoV and are therefore very limited in applicability. In this paper, we propose a security assessment method for IoV based on Microcontroller Unit (MCU) chip temperature, called SAMCT. Specifically, we first record the MCU chip temperatures of IoV device in different security states and analyze the relationship between them. Second, the fingerprint dataset is built using the temperature residuals. Third, to forecast the security standing of IoV devices, an integration regression model based on Self-Encoders is suggested. Lastly, in order to facilitate the effectiveness of the SAMCT, a Cloud-Edge-End framework is designed with the technology of model adaptive partitioning. Results from the experiments, which were carried out on the Raspberry Pi 4B and Stm32 hardware platforms, demonstrate that the Mean Squared Error (MSE) of the SAMCT is only 0.00104 and that the execution efficiency improvement under the Cloud-Edge-End framework is significant. Note to Practitioners —This paper was inspired by security concerns in Internet of Vehicles communication systems. The core of this work is to provide a novel security assessment method for IoV devices based on MCU temperature, which can detect the security status of IoV devices in real-time without modifying the original hardware. To this end, the different skills from scheme design to detection and validation are explained. One crucial part of this work is to regard the MCU temperature of the IoV device as a security reference and fully integrate the critical techniques in deep learning. In addition, the proposed scheme is universal and can be applied to various scenarios such as the autonomous driving and the industrial internet of things.

In the 5G era and beyond, new applications (APPs) have more stringent requirements for low latency. The cloud radio access network (C-RAN) with TDM-PON-based mobile fronthaul (MFH) and multi-access edge computing (MEC) has been regarded as an efficient architecture for serving latency-critical APPs. Many studies have focused on latency optimization issues in the MFH or MEC segment. However, the ultimate latency from the end-user’s perspective is end-to-end (E2E) latency, which includes the latency in both the MFH and MEC segments. When coordinating MFH with MEC, the E2E latency optimization may be mismatched and inefficient. To address this issue, we propose an APP-aware MAC scheduling scheme that allocates uplink time resources based on the MEC-backed conditions and APPs’ traffic dynamics. Accordingly, we introduce an AI-based traffic prediction approach to capture traffic fluctuations in various APPs. Simulations show that our proposed scheme improves the performances of latency violation ratio and average E2E latency by up to 30% and 8%, respectively.