Mobile Networks and Applications最新文献

With the rapid development of computer hardware, its size continues to shrink, but its price continues to decrease, driving the vigorous development of wearable devices. Among them, wearable devices have enormous application prospects in medical diagnosis and military reconnaissance. With the continuous diversification and miniaturization of sensors, wearable devices are also emerging endlessly. This article proposes a wearable motion recognition device and studies a series of motion recognition algorithms for inertial signals based on this device. Wearable motion recognition devices combined with optical devices are used for non-invasive monitoring and analysis of athletes' body dynamics, obtaining high-definition video images, and real-time tracking of athletes' position and movement trajectory through the analysis of video images. This article analyzes and organizes experimental data to obtain relevant data on outdoor sports monitored by the system. The monitoring results show that the monitoring system in this article has advantages such as portability, ease of operation, and practicality, which can meet the needs of outdoor sports teams for data monitoring during training in different venues. In the practical application of this monitoring system, coaches can effectively analyze and organize the current data, thereby improving the work efficiency of coaches and the technical and tactical level of outdoor athletes.

With the widespread deployment of dense Low Earth Orbit (LEO) constellations, satellites can serve as an alternative solution to the lack of proximal multi-access edge computing (MEC) servers for mobile Internet of Things (IoT) devices in remote areas. Simultaneously, leveraging federated learning (FL) to address data privacy concerns in the context of satellite-terrestrial cooperative IoT is a prudent choice. However, in the traditional satellite-ground FL framework where model aggregation occurs solely on satellite onboard terminals, challenges of insufficient satellite computational resources and congested core networks are encountered. Hence, we propose a cost-efficient satellite-terrestrial assisted hierarchical federated edge learning (STA-HFEL) architecture in which the satellite edge server performs as intermediaries for partial FL aggregation between IoT devices and the remote cloud. We further introduced an innovative communication scheme between satellites based on Intra-plane ISLs in this paper. Accordingly, considering the resource constraints of battery-limited devices, we define a joint computation and communication resource optimization problem for device users to achieve global cost minimization. By decomposing it into local training computational resource allocation subproblem and local model uploading communication resource subproblem, we used a distributed Jacobi-Proximal ADMM (JPADMM) algorithm to tackle the formulated problem iteratively. Extensive performance evaluations demonstrate that the potential of STA-HFEL as a cost-efficient and privacy-preserving approach for machine learning tasks across distributed remote environments.

In order to solve the problem of false detection of the moving liquid level caused by the vibration of the constant temperature water bath, this paper combines the Type-2 Fuzzy Gaussian Mixture Model (T2-FGMM) and Markov Random Field (MRF) to study a new background modeling method for detecting the moving liquid level in dynamic scenes. The method first considers the output of T2-FGMM as the initial labeling domain of MRF, and then combines the local energy of the labeling domain with the observation energy. The key of this method is to combine the spatiotemporal prior of T2-FGMM with the observation. Comparative experimental results show that the proposed algorithm has better dynamic background detection effect than traditional frame difference method and Vibe algorithm, and can effectively eliminate the influence of the vibration of the constant temperature water bath on the detection of the moving liquid level of the viscometer.

Traditional software distribution systems are highly inefficient for the needs of Artificial Intelligence of Things (AIoT) devices. The processing power and other resources of modern AIoT devices enable the use of general-purpose operating systems (i.e., Linux) and thick stacks of libraries to implement specific functionalities at a high level of abstraction. However, these advantages do not come for free. General-purpose software is not inherently optimized in terms of performance and energy efficiency; a significant portion of resources is consumed for system functioning and maintenance; the complexity of the system potentially jeopardizes its stability and security, among other issues. However, one of the main drawbacks of this approach is the need for frequent software updates, which involves distributing a large amount of data to the devices and storing it on them. In this paper, we introduce a new approach to software distribution in the form of a just-in-time file-system model, which retains the functionalities of existing software management systems but significantly reduces the amount of data copied to the device (initially or during updates), thereby conserving resources and speeding up the update process. The research presented in this paper indicates that during software updates, up to 90% of files are unnecessarily replaced with identical copies. Therefore, by implementing the proposed file system, significant savings could be achieved in terms of communication channel usage, external memory capacity and durability, as well as processor time required for updates, although as a trade-off in system autonomy and dependence on network connectivity.

The quality of life and the development of urban areas are impacted by traffic-related issues. The delayed response of priority and emergency vehicles, such as police cars and ambulances, jeopardizes public safety and well-being. Further, repeated episodes of congestion affect driver’s temperament by wasting time and causing frustration. Prevailing forecasting techniques are inadequate to address the complexities of urban infrastructure that include autonomous vehicles, connected infrastructure, and integrated public transport. In this article, a new model has been proposed using heuristic methods for real-time traffic management and control applications. The adaptive weighted features are utilized in the atrous convolution-based hybrid attention network for efficient traffic congestion prediction. The features are optimally selected by Mean Square Error of Grass Fibrous Root Optimization (MSE-GFRO) and combined with the optimal weights and thus, are offered the adaptive weighted features. The prediction model combines deep Temporal Convolutional Network (DTCN) and gated recurrent unit (GRU) based on an attention mechanism to predict traffic congestion on the basis of adaptive weighted features. Experimental analysis is performed over distinct optimization models and classifiers to demonstrate the efficiency of the implemented model.