Zhengjian Li

The rapid growth of sensor data in IoT and Digital Twins necessitates high-performance spatial indexing. Traditional indexes like Rtrees suffer from high storage overhead, while state-of-the-art learned indexes like GLIN encounter a “Refinement Bottleneck” due to coarse-grained Minimum Bounding Rectangle (MBR) filtering. Furthermore, existing solutions often trade update throughput for query accuracy, failing in dynamic IoT workloads with concurrent reads and writes. We propose DyGLIN (Dynamic Generate Learning-Based Index), a dynamic, read-optimized learned spatial index tailored for high-frequency sensor streams. DyGLIN introduces a decoupled leaf architecture separating query processing from data maintenance. To accelerate queries, we implement a hierarchical filtering pipeline using hierarchical MBRs (HMBR) and Cuckoo Filters to aggressively prune false positives. For maintenance, a Delta Buffer mechanism amortizes update costs, while logical deletion ensures high throughput. Experiments on real-world datasets show that DyGLIN reduces query latency by 26.4% [95% CI: 20.1%, 38.6%] compared to GLIN. It achieves 30.0% [95% CI: 21.4%, 35.9%] higher insertion throughput and superior deletion performance, with only an 18.5% [95% CI: 16.8%, 19.8%] increase in memory overhead.

In recent years, autonomous underwater vehicles (AUVs) have become a key tool for consumer-facing ocean applications, gaining widespread popularity among consumers. AUVs have the characteristics of small size, high autonomy, strong flexibility, and long endurance, and consumers can apply them to environmental monitoring, underwater detection, and recreational diving. However, achieving efficient underwater path planning and obstacle avoidance requires a significant amount of computing resources, which leads to the typically high costs of AUVs and poses a significant barrier to their widespread adoption. To solve this challenge, this paper proposes a low-cost path planning framework that integrates edge computing and deep reinforcement learning, aiming to achieve efficient path planning of AUV in the computing resource-constrained ocean environment. By embedding a lightweight edge computing module in the AUV, we developed a Kalman filter-based obstacle ranging algorithm that enables intelligent real-time processing of imaging sonar data streams. We conducted experiments on the ROS-Gazebo simulation platform that can simulate interactive scenarios involving ocean currents and obstacles. We constructing a realistic marine environment model and an AUV model equipped with imaging sonar. The experimental results show that the proposed method achieves efficient and reliable path planning in dynamic ocean environments with both obstacle and current interference.

The digital elevation model (DEM) provides important data support for geographic information analysis. However, due to the limitation of measurement cost and complex terrain, the collected DEMs often have randomly missing under-sampled points and low sampling density. Neural networks have been shown to have the potential to reconstruct low-resolution DEM data into high-resolution data. Given that general images and DEMs have similar structural features, some researchers have attempted to directly apply general image super-resolution methods to DEM super-resolution tasks, and achieve better results compared to traditional interpolation-based methods. However, DEM data and general images have unique characteristics and fundamental differences, making it inappropriate to directly apply image-based super resolution methods to extract terrain features. Meanwhile, the general spatial interpolation algorithms based on deep learning usually have low model complexity and lack the specific designed loss function, which usually leads to significant interpolation errors. In order to solve these problems, we conducted in-depth research on the terrain feature patterns of DEMs and proposed a DEM super-resolution reconstruction network with terrain feature-aware, named D-ResDCN. The network integrates deep residual module, deformable convolution module and upsampling module, which are used to extract deep terrain features, adaptive terrain features and improve the resolution of DEM data respectively. Furthermore, to accurately reconstruct the local detailed features of DEMs, we constructed a joint loss function with adaptive weight adjustment, which incorporates content loss, perceptual loss, and terrain feature loss. Experimental results show that compared with traditional spatial interpolation and classical super-resolution networks (SRCNN, SRResNet, SRGAN, and ESRGAN), our D-ResDCN model is not far behind the best-performing SRCNN method on PSNR and SSIM, while the performance on MAE and RMSE is 10.5% and 10.1% lower than the SRResNet method, respectively.

An autonomous underwater vehicle (AUV) has shown impressive potential and promising exploitation prospects in numerous marine missions. Among its various applications, the most essential prerequisite is path planning. Although considerable endeavors have been made, there are several limitations. A complete and realistic ocean simulation environment is critically needed. As most of the existing methods are based on mathematical models, they suffer from a large gap with reality. At the same time, the dynamic and unknown environment places high demands on robustness and generalization. In order to overcome these limitations, we propose an information-assisted reinforcement learning path planning scheme. First, it performs numerical modeling based on real ocean current observations to establish a complete simulation environment with the grid method, including 3-D terrain, dynamic currents, local information, and so on. Next, we propose an information compression (IC) scheme to trim the mutual information (MI) between reinforcement learning neural network layers to improve generalization. A proof based on information theory provides solid support for this. Moreover, for the dynamic characteristics of the marine environment, we elaborately design a confidence evaluator (CE), which evaluates the correlation between two adjacent frames of ocean currents to provide confidence for the action. The performance of our method has been evaluated and proven by numerical results, which demonstrate a fair sensitivity to ocean currents and high robustness and generalization to cope with the dynamic and unknown underwater environment.

The frequent outbreak of crop pests is one of the main factors affecting crop yield. The accurate identification of pests is significant for effective pest control, which is the basis for the safe growth of crops and is also an important guarantee for high crop quality and crop yield. Computer vision based on supervised deep learning enables intelligent identification of pests, whose success is still inseparable from a large amount of labeled data, causing a large number of resource consumption due to data labeling. Therefore, an in-depth study on maximizing the value of data is essential when lacking labeled data. A new data evaluation method based on Mahalanobis distance and entropy is proposed to address the problem of lacking labeled data in intelligent pest identification. This method enables filtering high-value data, thus achieving effective pest identification performance with a small data volume. The experiment is conducted on a dataset we collected called PD-20, which shows the proposed method achieves baseline accuracy of 100% using only about 60% of the original data. Moreover, the proposed method can save at least 10% of the data volume compared with three comparison methods. To facilitate the deep integration of smart agriculture with artificial intelligence (AI), we designed an interactive framework of active learning for pest identification based on the proposed method, which lays the foundation for the application of AI in direction of agriculture.

Internet of Things (IoT) has extended its coverage to various spatial domains and has established interconnection to serve widespread applications of a larger spatial scale. Such IoT is called the space–air–ground–ocean-integrated network (SAGOI-Net), which consists of multiple battery-powered heterogeneous devices. Hence, energy efficiency is the key point of SAGOI-Net to be stably operated for a long time without manual maintenance. This article proposes a novel scheme of energy-efficient autonomous and decentralized SAGOI-Net establishment using an intelligent autonomous underwater glider (AUG) to serve marine applications. The proposed SAGOI-Net is energy efficient because the energy consumption is minimized by: 1) employing nonpropeller-driven AUG; 2) navigating AUG under water without acoustic sensor or extra energy-consuming vision sensors; and 3) equipping the self-navigation (SN) system based on lightweight neural network model to save the energy consumption of onboard computing resource. Moreover, assuming the AUG navigation problem as time-series regression, the proposed scheme designs SAGOI-Net to be autonomous and decentralized with the aid of lightweight long short-term memory (LSTM) network-based SN (SN-LSTM) system of AUG. The lightweight SN-LSTM model is trained end-to-end on dynamically modeled AUG motion information along with numerically modeled ocean environment data to quantitatively analyze the impact of the ocean environment on AUG. The simulation results demonstrate a superior performance of the AUG SN along with energy efficiency of the proposed SAGOI-Net.

Autonomous underwater vehicle (AUV) shows great potential in the Internet of Underwater Things (IoUT) system, in which the path planning algorithm plays a fundamental role. However, the complex underwater environment brings greater challenges to AUV path planning, especially the ocean current, which has a profound impact on time and energy consumption. This article focuses on the complex ocean current condition and proposes an underwater path planning method based on proximal policy optimization (UP4O). In this novel method, a deep reinforcement network is constructed to serve as a decision control to plan the moving direction of AUV. An information encoding module is developed to extract the features of the local obstacles. Furthermore, UP4O integrates the obstacle features with the current state information, including relative position, ocean current, and velocity, enabling the AUV to focus on the global direction and local obstacles at the same time. Additionally, to further adapt to the ocean current and shorten the time cost, UP4O expands the action space of AUV, realizing a fine and flexible action adjustment. The wide applicability of UP4O has been proved by numerous experiments. The proposed algorithm can always plan the time-saving and collision-free paths in complex underwater environments with various terrains and ocean current.

The new generation of artificial intelligence technology has improved the autonomous monitoring capabilities of marine equipment. The ocean monitoring platform based on edge computing realizes the autonomous collaboration of multi-agent equipment groups. Autonomous Underwater Glider (AUG) is a new type of energy-saving marine equipment that can realize long-range ocean exploration. However, the non-negligible power constraints, time delays, communication failures and other unfavorable factors in the special underwater working environment have brought great challenges to the underwater monitoring operations of multi-AUG systems. This research establishes an improved artificial potential field method scheme based on the Maritime Internet of Things, which is based on the AUG leader's edge device to control multi-AUGs. In this process, an improved artificial potential field method is designed to solve the local optimal problem through behavior-based path optimization. Then, multi-AUGs are controlled to adapt to the task team plan based on the edge computing of the AUG leader. From the experimental results, it effectively realizes the AUG group cooperative control in the leader mode. Meanwhile, we established a marine communication model and AUG physics engine control model to complete a digital twin of multi-AUG monitoring tasks.