Yi Zhang

Edge intelligence, which manifests itself as the combination of edge computing and artificial intelligence, has emerged as a promising solution to delivering high-quality and low-latency computing services for many intelligent applications. Oriented toward an Age-of-Information (AoI)-centric edge intelligence system, this paper studies the problem of joint optimization of sampling and model partitioning that minimizes the maximum system response AoI through decision making on the sampling policy and model partition point. We formulate this joint sampling and offloading problem as a combinatorial optimization model that aims at minimizing the maximum system response AoI by determining the optimal sampling policy and model partitioning strategy. We analyze the impact of model partition point on sampling decision in a theoretical manner and, accordingly, establish a sampling rule for making the sampling decision. We propose a cost-effective heuristic algorithm that relies on the sampling rule to explore the AoI-minimized sampling and model partitioning solution to the formulated problem. Experimental results on a real-world edge intelligence system justify the advantage of the joint optimization algorithm in reducing system response AoI.

Low-rank representation is a popularly used method in remote sensing and image processing systems. Existing low-rank representation-based algorithms often neglect the varying sensitivities of different pixels to the dictionary which may lead to inaccurate detection. Also, the dense iterative computations involved in these algorithms could induce high computation overheads. This paper proposes an efficient low-rank representation method for hyperspectral anomaly detection on a CPU-FPGA hybrid computing platform. The proposed method starts with segmenting the hyperspectral image into superpixels based on the selected number of dictionary categories. The image is divided into center and edge parts using a sliding window along the segmentation boundaries. Then, we use a low-rank and sparse representation to process center pixels that are well-adapted to the dictionary, and a weighted low-rank and collaborative representation model to process edge pixels that are less adaptive to the dictionary. The aforementioned two representation models are integrated to obtain the final reconstructed image. Moreover, we propose the Nesterov acceleration method by incorporating an adaptive step size into the linearized alternating direction method with adaptive penalty. At the hardware level, the acceleration method is deployed on CPU-FPGA platform to speed up the proposed hyperspectral anomaly detection flow. Experimental results demonstrate that the proposed method outperforms most existing methods in detection accuracy and achieves significant improvement in computational efficiency.

Hyperspectral anomaly detection (AD), as a frontier research topic in the field of remotely sensed data processing, aims to identify targets of interest from complex and vast images. Existing AD methods typically involve complex models and many parameters, posing challenges in meeting the requirements of computational efficiency in hyperspectral AD. To address this issue, this paper presents an AD acceleration algorithm based on the multivariate Gaussian model as well as its field programmable gate array (FPGA) implementation. By exploiting the parallel processing capabilities of FPGA, we introduce an innovative spectral dimensionality reduction method in which the data processing flow can be accomplished in a distributed manner. Then, we employ an improved linear rotation strategy based on correlation coefficients to accelerate the convergence rate of the proposed AD algorithm. The rotation of Gaussianization in the improved strategy is independent of eigenvalue decomposition, thereby substantially reducing the computational complexity involved during the rotation procedure. Furthermore, we apply a pipeline parallel mechanism to facilitate the FPGA implementation of the AD algorithm and to significantly enhance the computational efficiency. Experimental results on an embedded FPGA platform demonstrate that the FPGA implementation of the hyperspectral AD algorithm proposed in this paper achieves significant acceleration rate with guaranteed high detection accuracy.

Hyperspectral image super-resolution aims to fuse a low spatial resolution hyperspectral image (LR-HSI) and a high spatial resolution multispectral image (HR-MSI) to obtain a high-resolution hyperspectral image (HR-HSI). Tensor-based methods have demonstrated their outstanding ability in constructing the relationship between the LR-HSI and the HR-MSI. This paper introduces a nonlocal hierarchical Tucker decomposition (HTD) model for hyperspectral and multispectral image (HSI-MSI) fusion. First, similar nonlocal patch tensors are clustered according to their similarity in the HR-MSI. Next, the spatial/spectral relationship between the LR-HSI and the HR-MSI is extracted through HTD. The alternating direction method of multipliers (ADMM) is employed to solve the proposed model. Furthermore, to overcome the high computational complexity of the model solver, we propose an efficient distributed and parallel method to accelerate the fusion process. Experimental results demonstrate that the proposed method not only substantially outperforms state-of-the-art HSI-MSI fusion methods, but also achieves a significant acceleration rate.

Target detection for hyperspectral images (HSIs) is one of the significant techniques in remote sensing data processing. Targets generally comprise various object categories with complex features and of varying sizes. Target detection is often used in complex application scenarios in which accurately and efficiently acquiring detection results can be challenging. The development of advanced target detection approaches is becoming increasingly necessary in both military and civilian fields. This article proposes an alternating direction method of multiplier (ADMM) based parallel approach for hyperspectral target detection. Different from existing methods performing target detection solely on hyperspectral images, our approach performs the fusion of hyperspectral and multispectral data to leverage both spectral and spatial information prior. For each task or data partition, the parallel processing of the computation load on multiple computing nodes can substantially reduce the computation time. In addition, we introduce a novel weighted ADMM, which takes the influence of different variables on convergence into account, to further enhance the computational efficiency of the target detection model. Experiments on real-world HSI datasets demonstrate that our proposed parallel method not only produces more accurate detection results than direct detection methods, but also achieves significant acceleration ratio compared with the serial processing flow.

Due to the constrained processing capabilities of real-time detection techniques in remote sensing applications, it is often difficult to obtain detection results with high accuracy in practice. To address this problem, we introduce a new real-time anomaly detection algorithm for hyperspectral images called cloud–edge RX (CE-RX). The algorithm combines the advantages of cloud and edge computing. During the data acquisition process, the edge performs real-time detection on the data just captured to obtain a coarse result and find the suspicious anomalies. At regular intervals, the suspicious anomalies are sent to the cloud for further detection with a highly accurate algorithm, then the cloud sends back the (high-accuracy) results to the edge for information updating. After receiving the results from the cloud, the edge updates the information of the detector in the real-time algorithm to improve the detection accuracy of the next acquired piece of data. Our experimental results demonstrate that the proposed cloud–edge collaborative algorithm can obtain more accurate results than existing real-time detection algorithms.

Mobile crowdsourcing is a new computing paradigm that enables outsourcing computation tasks to mobile crowd nodes by means of offloading the tasks from the user to a mobile edge computing (MEC) server. This article studies the problem of scheduling security-critical tasks of crowdsourcing applications in a multiserver MEC environment. We formulate this scheduling problem as an integer program and propose a family of convergent grey wolf optimizer (CGWO) metaheuristic algorithms to seek for the best scheduling solutions. Our proposed CGWO uses a task permutation to represent a candidate solution to the formulated scheduling problem, and employs a probability-based mapping scheme to map each search agent in grey wolf optimizer (GWO) onto a valid task permutation. We introduce a new position update strategy for generating the next generation of grey wolf population after each round of search. With this strategy, we prove our proposed CGWO guarantees its convergence to the global best solution. More importantly, we provide a thorough analysis on the movement trajectories of grey wolves during the evolutionary procedure, in order to determine appropriate parameter values such that CGWO would not be trapped in local optima. Experimental results justify the superiority of CGWO metaheuristics over the standard GWO in solving the crowdsourcing task scheduling problem.

This article gives a survey of state-of-the-art methods for processing remotely sensed big data and thoroughly investigates existing parallel implementations on diverse popular high-performance computing platforms. The pros/cons of these approaches are discussed in terms of capability, scalability, reliability, and ease of use. Among existing distributed computing platforms, cloud computing is currently the most promising solution to efficient and scalable processing of remotely sensed big data due to its advanced capabilities for high-performance and service-oriented computing. We further provide an in-depth analysis of state-of-the-art cloud implementations that seek for exploiting the parallelism of distributed processing of remotely sensed big data. In particular, we study a series of scheduling algorithms (GSs) aimed at distributing the computation load across multiple cloud computing resources in an optimized manner. We conduct a thorough review of different GSs and reveal the significance of employing scheduling strategies to fully exploit parallelism during the remotely sensed big data processing flow. We present a case study on large-scale remote sensing datasets to evaluate the parallel and distributed approaches and algorithms. Evaluation results demonstrate the advanced capabilities of cloud computing in processing remotely sensed big data and the improvements in computational efficiency obtained by employing scheduling strategies.

As the volume of remotely sensed data grows significantly, content-based image retrieval (CBIR) becomes increasingly important, especially for cloud computing platforms that facilitate processing and storing big data in a parallel and distributed way. This paper proposes a novel parallel CBIR system for hyperspectral image (HSI) repository on cloud computing platforms under the guide of unmixed spectral information, i.e., endmembers and their associated fractional abundances, to retrieve hyperspectral scenes. However, existing unmixing methods would suffer extremely high computational burden when extracting meta-data from large-scale HSI data. To address this limitation, we implement a distributed and parallel unmixing method that operates on cloud computing platforms in parallel for accelerating the unmixing processing flow. In addition, we implement a global standard distributed HSI repository equipped with a large spectral library in a software-as-a-service mode, providing users with HSI storage, management, and retrieval services through web interfaces. Furthermore, the parallel implementation of unmixing processing is incorporated into the CBIR system to establish the parallel unmixing-based content retrieval system. The performance of our proposed parallel CBIR system was verified in terms of both unmixing efficiency and accuracy.