Agricultural robots are one of the important means to promote agricultural modernization and improve agricultural efficiency. With the development of artificial intelligence technology and the maturity of Internet of Things (IoT) technology, people put forward higher requirements for the intelligence of robots. Agricultural robots must have intelligent control functions in agricultural scenarios and be able to autonomously decide paths to complete agricultural tasks. In response to this requirement, this paper proposes a Residual-like Soft Actor Critic (R-SAC) algorithm for agricultural scenarios to realize safe obstacle avoidance and intelligent path planning of robots. In addition, in order to alleviate the time-consuming problem of exploration process of reinforcement learning, this paper proposes an offline expert experience pre-training method, which improves the training efficiency of reinforcement learning. Moreover, this paper optimizes the reward mechanism of the algorithm by using multi-step TD-error, which solves the probable dilemma during training. Experiments verify that our proposed method has stable performance in both static and dynamic obstacle environments, and is superior to other reinforcement learning algorithms. It is a stable and efficient path planning method and has visible application potential in agricultural robots.

The Maritime Internet of Things (MIoT) consists of offshore equipment such as ships, consoles, and base stations, which are used for maritime information sharing to assist driving decision-making. However, with the increase in the number of MIoT access devices, the risks of information security and data reliability have also significantly increased. In this paper, we describe a maritime Dynamic Ship Federated Information Security Sharing Model (DSF-ISS) in Maritime Internet of Vessels (MIoV) based on maritime 5G broadcasting technology. The main object of this study is to solve the problem of maritime information isolated island under the condition of low communication between maritime ship nodes. In this model, maritime ship nodes cooperation is based on the Contract Network Protocol (CNP), which considers task types, spatial, and temporal distribution of different vessels. We then propose an improved federated learning approach for local dynamic nodes based on maritime 5G broadcasting technology. Moreover, this study designs a proof of membership (PoM) to share local task model information in global blockchain. The results showed that DSF-ISS has a positive effect in maritime transportation work. It effectively realizes the secure sharing of information and protects the privacy of node data.

Object detection and target localization are important technologies in image processing and computer vision, which have a wide range of applications in agricultural systems. By fusing the YOLOv5 algorithm and monocular vision-based method, a target localization algorithm is proposed to accurately identify and locate the various objects in agricultural scenes. The GPS information of the target object can be obtained by means of processing the attitude angle information of the unmanned aerial vehicle (UAV) at the time when it takes pictures. The superiority of the proposed method is demonstrated through the test on the agricultural scenario dataset taken by UAV, with the experimental results showing the algorithm’s satisfactory speed and accuracy.

The Internet of Things (AIoT) is supporting the revolution of many industries. However, AIoT systems require a large amount of computing resources and electricity consumption as support, which leads to significant carbon emissions and energy consumption, which is not conducive to sustainable energy development. Reducing the demand for data in artificial intelligence through active learning (AL) is an effective solution. In this study, based on the interpretability of neural networks, we propose an interpretable AL algorithm. By improving the traditional heatmap display method, we use predicted probability entropy and posterior probability entropy to form an information class activation map information visualization method, thereby providing an explanation for the sources of information in AL. Meanwhile, we propose a Similarity-Loss AL sampling strategy to evaluate the information content of samples. The experimental results show that our proposed method has achieved good results in terms of interpretability and optimization of sampling in AL. In addition, the proposed Similarity-Loss sampling strategy has achieved the highest performance in current AL scenarios, contributing to achieving low-carbon and sustainable AIoT.

The perimeter security system based on distributed optical fiber sensing is of great significance for the monitoring and security of military and key industrial areas. Most of the existing recognition methods for distributed optical fiber disturbance signal rely on artificial feature extraction method based on time domain or frequency domain, combined with decision tree or support vector machine to perform the recognition operation. However, these methods usually have the problem of long recognition time and high error rate, which brings great obstacles to the practical application of perimeter security system. To solve the above problems, this paper proposes a multi-scale residual network with strip pooling module (SP-MSResNet), which takes into account the advantages of traditional signal frequency domain analysis methods, and the powerful feature extraction capability of deep network model. Firstly, the original one-dimensional (1D) intrusion disturbance signal is decomposed into five levels in the frequency domain by discrete wavelet transform (DWT), and the obtained five approximate horizontal coefficients are connected in parallel with the original signal to form a new two-dimensional (2D) data. Then the 2D data was applied to the SP-MSResNet for the training of recognition task. The experimental results show that the average recognition accuracy reaches 99.17% on the dataset of 6 types of intrusion disturbance signals (wind blowing, light rain, heavy rain, knocking, impacting and slapping), which has more advantages compared with other methods mentioned in the literature.

Remote sensing image analysis plays a vital role in achieving intelligent agricultural monitoring. However, the acquisition of high-resolution agricultural remote sensing data can be resource-intensive, resulting in an imbalance between training samples and artificial intelligence model parameters. In order to achieve accurate agricultural land recognition of limited-resolution remote sensing images, this article proposes a joint network of super-resolution and active learning (AL). The network introduces a pretrained image super-resolution model and optimizes this for remote sensing classification tasks. It effectively detects detailed features and completes the reconstruction. Based on the reconstructed data, an AL algorithm is proposed with a DBSS. It balances the contributions between interclass and boundary samples. Furthermore, we propose a semisupervisory assistance strategy based on consistency, it fully utilizes the predictive power of deep learning models aiming to reduce labeling costs. This framework is proved effective by experiments on an agricultural remote sensing image dataset, it reduces the cost of agricultural data annotation and improves the efficiency of model learning for low-resolution agricultural remote sensing.