Federated learning has achieved significant advancements in edge artificial intelligence (AI) by addressing issues related to data privacy and communication overload. Moreover, hierarchical federated learning over space-air-ground integrated networks (FedSAG), which consists of low-Earth orbit (LEO) satellites, unmanned aerial vehicles (UAVs), and edge devices, aims to provide AI services in sparsely populated regions lacking ground communication infrastructure. However, previous studies have overlooked the essential sensing process required for acquiring training data, potentially compromising training efficiency and model accuracy. In this paper, we propose an integrated sensing-communication-computation (ISCC) enabled FedSAG system, which allows remote edge devices to collect data via wireless sensing and collaboratively train a global model without sharing local data. We then analyse the convergence of the ISCC-enabled FedSAG and formulate two optimization problems. The first aims to minimize sensing variance under energy and time constraints, while the second seeks to reduce transmission energy through optimal route selection between UAVs and LEO satellite. We reformulate the problems to a minimum spanning tree and propose a Chu-Liu-Edmonds algorithm based a two-stage optimization. Simulation results demonstrate that our proposed algorithm significantly enhances convergence performance and reduces energy consumption.

As the core component of aero engines, compressor blades in turbine engines have complex surface geometry requirements. With the rapid iteration of the turbine power system, the compressor blades used are constantly updated. An accurate prediction model that can quickly adapt to new blade production on manufacturing processes is urgently needed. However, most of the existing technologies cannot meet the high precision requirements of blade manufacturing, and the lack of data for newer blades makes training a predictive model in a new machining task a high time and economic cost. In this paper, we propose a domain generalization-based quality prediction framework for high-precision compressor blade manufacturing processes. The framework can make full use of the relevant manufacturing process data of historical blades to build a domain generalization model for adapting to the prediction of processing accuracy of new blades that have not been processed before. In particular, this study proposes a non-invasive generalization solution that meets accuracy requirements. Coordinate measuring machine (CMM) data is used as input features for prediction, rather than retrofitting sensors onto machinery after installation. To evaluate the effectiveness of the proposed framework, experiments were conducted on four series of aerospace compressor blades from Wuxi Turbine Blade Co., Ltd., China. CMM data from key stages such as blade root milling and integrated precision milling are used as input to predict final geometric errors. Comparison results verify that the proposed framework achieves the smallest prediction error at 0.037 mm, 0.013 mm, 0.021 mm, and 0.016 mm for four blades respectively.

Artificial intelligence (AI) is critical in evolving 5G and developing 6G networks, running on edge devices, and solving resource management challenges. The burgeoning number of edge devices draws attention to the potential of low-earth orbit (LEO) satellite networks with their onboard computing capabilities for edge inference. This paper explores LEO scenarios where multiple remote sensing edge AI inference tasks concurrently process data from a single source. However, due to there being parts with the same functions between different AI applications, traditional monolithic edge AI architecture must be deployed repeatedly and falls short in efficiently harnessing the heterogeneous resources of LEO satellite networks. To solve this problem, we utilize the microservice architecture to decouple a single AI application into several independent microservices to reuse these same functions. However, due to the high latency caused by multiple microservices’ communication, we need to design a deployment strategy to fully utilize resources to reduce the service latency. We present a microservice deployment model to minimize the total service latency across all AI applications and meet resource constraints with the constraints of hardware, energy, and memory limitations. This latency optimization problem is rewritten as a Markov decision process (MDP) to effectively deal with the challenge posed by the time-varying transmission rate caused by satellite mobility. To increase the training data utilization, we employ a Proximal Policy Optimization (PPO) based reinforcement learning algorithm to meet the dynamic environment challenge. Finally, we obtain a sub-optimal solution with minimal accuracy loss and an acceptable solution time.

Video analytics plays a pivotal role in public safety (e.g., criminal suspect detection, traffic flow count, and illegal parking management), which assists the polices in monitoring all anomalous events in the street. In this paper, we consider the scenario with multiple video analytics applications from a single video stream. However, traditional monolithic architecture based video analytics applications shall seriously increase the response latency due to the resource contention of repetitive components. Therefore, we utilize the microservice architecture based video analytics (MAVA) to share the universal microser-vices in different applications, which shall decrease the response latency by reducing the computation load and increasing the resource utilization. To further achieve fast and accurate video analytics, the video analytics microservices are deployed in the edge closing to the cameras and users, and artificial intelligence (AI) methods are used in the microservices to realize specified functions. Therefore, an edge AI enabled MAVA (EAI-MAVA) architecture is proposed to achieve accurate video analytics in real-time. Furthermore, we formulate a microservice deployment problem to determine the location of each microservice in EAI-MAVA, which minimizes the response latency of all applications by considering the resource demands of microservices and the resource constraints of heterogeneous edge devices. Finally, a greedy-based heuristic algorithm is proposed to solve the non-convex microservice deployment problem, which obtains a sub-optimal solution with small loss of accuracy and reduces the solution time obviously.

Abstract More accurate methods for crop row detection benefit intelligent operation of agricultural machinery, especially avoiding mishandling or crushing crops. For achieving such a target, a traditional method combining the ExGR exponents, Otsu algorithm, Canny method, Hough transform and DBSCAN clustering analysis is proposed so that centerlines of crop rows can be detected effectively without manual intervention. Specifically, ExGR exponents are first adopted to gray green plants. The threshold of binarization will be further obtained by the Otsu algorithm. Further adopting the edge detection algorithm (Canny), edges of crops can be determined. Finally, combining the Hough transform and DBSCAN clustering analysis, the crop row detection is effectively available. Utilizing these methods, numerical simulation and their comparisons with existing methods are also achieved. For example, the Canny algorithm is relatively accurate than the Suzuki algorithm as well as their combinations with a geometric center extraction method if the density of weed is high. Compared with the K‐means clustering method, the DBSCAN algorithm is more suitable to characterize crop rows optimally in more complex conditions. It is validated from experiments that the combination of Canny algorithm, Hough transform and DBSCAN clustering is better than other mentioned traditional methods.

The safety-critical scenarios of artificial intelligence (AI), such as autonomous driving, Internet of Things, smart healthcare, etc., have raised critical requirements of trustworthy AI to guarantee the privacy and security with reliable decisions. As a nascent branch for trustworthy AI, federated learning (FL) has been regarded as a promising privacy preserving framework for training a global AI model over collaborative devices. However, security challenges still exist in the FL framework, e.g., Byzantine attacks from malicious devices, and model tampering attacks from malicious server, which will degrade or destroy the accuracy of trained global AI model. In this article, we shall propose a decentralized blockchain-based FL (B-FL) architecture by using a secure global aggregation algorithm to resist malicious devices, and deploying a practical Byzantine fault tolerance consensus protocol with high effectiveness and low energy consumption among multiple edge servers to prevent model tampering from the malicious server. However, to implement B-FL system at the network edge, multiple rounds of cross-validation in blockchain consensus protocol will induce long training latency. We thus formulate a network optimization problem that jointly considers bandwidth and power allocation for the minimization of long-term average training latency consisting of progressive learning rounds. We further propose to transform the network optimization problem as a Markov decision process and leverage the deep reinforcement learning (DRL)-based algorithm to provide high system performance with low computational complexity. Simulation results demonstrate that B-FL can resist malicious attacks from edge devices and servers, and the training latency of B-FL can be significantly reduced by the DRL-based algorithm compared with the baseline algorithms.

This paper establishes the convergence rates for fitting a polynomial neural network with quadratic activation function via the mini-batch Stochastic Gradient Descent (SGD) algorithm. Specifically, we focus on the parallel implementation of calculating mini-batch gradients on a distributed computing platform. We first illustrate that the SGD converges at a linear rate to the optimal solution, and the convergence rate can be characterized as a function of mini-batch sizes. Next, we deploy the SGD with a distributed approach across multiple processors, where the partial mini-batch gradient is calculated and quantized to send to a master processor in each iteration, yielding a Quantized Stochastic Gradient Descent (QSGD) algorithm. This scheme can effectively reduce the communication overhead by the quantization strategy. Furthermore, we reveal that QSGD provably maintains a similar convergence rate of SGD to a globally optimal solution while significantly reduces the communication cost. In particular, the number of bits required for quantization and the mini-batch size affect the convergence rate of QSGD.