Collaborative driving can significantly reduce the computation offloading from autonomous vehicles (AVs) to edge computing devices (ECDs) and the computation cost of each AV. However, the frequent information exchanges between AVs for determining the members in each collaborative group will consume a lot of time and resources. In addition, since AVs have different computing capabilities and costs, the collaboration types of the AVs in each group and the distribution of the AVs in different collaborative groups directly affect the performance of the cooperative driving. Therefore, how to develop an efficient collaborative autonomous driving scheme to minimize the cost for completing the driving process becomes a new challenge. To this end, we regard collaboration as a service and propose a digital twins (DT)-based scheme to facilitate the collaborative and distributed autonomous driving. Specifically, we first design the DT for each AV and develop a DT-enabled architecture to help AVs make the collaborative driving decisions in the virtual networks. With this architecture, an auction game-based collaborative driving mechanism (AG-CDM) is then designed to decide the head DT and the tail DT of each group. After that, by considering the computation cost and the transmission cost of each group, a coalition game-based distributed driving mechanism (CG-DDM) is developed to decide the optimal group distribution for minimizing the driving cost of each DT. Simulation results show that the proposed scheme can converge to a Nash stable collaborative and distributed structure and can minimize the autonomous driving cost of each AV.

Purpose: Existing studies on human activity recognition using inertial sensors mainly discuss single activities. However, human activities are rather concurrent. A person could be walking while brushing their teeth or lying while making a call. The purpose of this paper is to explore an effective way to recognize concurrent activities. Design/methodology/approach: Concurrent activities usually involve behaviors from different parts of the body, which are mainly dominated by the lower limbs and upper body. For this reason, a hierarchical method based on artificial neural networks (ANNs) is proposed to classify them. At the lower level, the state of the lower limbs to which a concurrent activity belongs is firstly recognized by means of one ANN using simple features. Then, the upper-level systems further distinguish between the upper limb movements and infer specific concurrent activity using features processed by the principle component analysis. Findings: An experiment is conducted to collect realistic data from five sensor nodes placed on subjects’ wrist, arm, thigh, ankle and chest. Experimental results indicate that the proposed hierarchical method can distinguish between 14 concurrent activities with a high classification rate of 92.6 per cent, which significantly outperforms the single-level recognition method. Practical implications: In the future, the research may play an important role in many ways such as daily behavior monitoring, smart assisted living, postoperative rehabilitation and eldercare support. Originality/value: To provide more accurate information on people’s behaviors, human concurrent activities are discussed and effectively recognized by using a hierarchical method.

Purpose: In sensor-based activity recognition, most of the previous studies focused on single activities such as body posture, ambulation and simple daily activities. Few works have been done to analyze complex concurrent activities. The purpose of this paper is to use a statistical modeling approach to classify them. Design/methodology/approach: In this study, the recognition problem of concurrent activities is explored with the framework of parallel hidden Markov model (PHMM), where two basic HMMs are used to model the upper limb movements and lower limb states, respectively. Statistical time-domain and frequency-domain features are extracted, and then processed by the principal component analysis method for classification. To recognize specific concurrent activities, PHMM merges the information (by combining probabilities) from both channels to make the final decision. Findings: Four studies are investigated to validate the effectiveness of the proposed method. The results show that PHMM can classify 12 daily concurrent activities with an average recognition rate of 93.2 per cent, which is superior to regular HMM and several single-frame classification approaches. Originality/value: A statistical modeling approach based on PHMM is investigated, and it proved to be effective in concurrent activity recognition. This might provide more accurate feedback on people’s behaviors. Practical implications: The research may be significant in the field of pervasive healthcare, supporting a variety of practical applications such as elderly care, ambient assisted living and remote monitoring.

Accelerometer is a motion sensor, which can sense motion change in any of its three axes. It is known that accelerometers inevitably suffer from multiple noise effects, and hence a six-position calibration method is usually applied to estimate the deterministic sensor errors. However, for the traditional six-position calibration method, a high-precision turntable is needed, which is relatively expensive and fixed in place, and thus not available for many research groups and for use as a portable tool. Therefore, this paper improves the traditional six-position method by introducing a rotation matrix to achieve the goal of a turntable. The improved method can still maintain the effectiveness of accelerometer calibration without using any auxiliary equipment. This paper proves the reliability of the improved six-position method through detailed derivation and comparative experiments.

Sleep quality is paramount for human physical and mental health, where accurate sleep staging is crucial for its assessment. While polysomnography (PSG) offers high accuracy, its complexity and inconvenience hinder widespread practicality. In contrast, non-wearable devices offer simplicity and comfort but suffer from limited monitoring capabilities, allowing only indirect assessment of sleep status, thereby posing challenges for predictive methods. To overcome these limitations, this paper introduces an automatic sleep staging model leveraging a convolutional-bidirectional gated recurrent neural network. By monitoring a select set of physiological parameters through non-wearable devices, the model achieves sleep staging accuracy approaching that of PSG, while significantly enhancing user comfort. Despite the experimental results not yet being fully optimized, the method's application potential and promising future directions are well-established.