Recurrent neural networks (RNNs), recognized for their high accuracy and strong robustness. However, the adoption of RNN-based solutions for array signal beamforming is still in its infancy, as RNNs are very sensitive to noise and cannot easily overcome the impact of environmental noise on the solution. To address these limitations, this study proposes the dynamic integrated enhanced neural network (DIENN) for array signal beamforming, which incorporates an error integral feedback mechanism. This mechanism enhances the robustness and noise immunity of the model, enabling it to maintain stable performance under dynamic noise environments. Compared with state-of-the-art (SOTA) methods, the proposed model has higher stability in beamforming tasks while providing excellent results under three interference conditions where the other algorithms of the comparison failed. The residual accuracy achieved in the case of time-varying disturbance was$10^{-15}$. The feasibility of the model was verified by applying it to experimental data. To our knowledge, this is the first work to develop a zero-reset RNN for array signal processing.

Traditional vital sign monitoring devices typically involve direct contact with the skin using electrodes, making them unsuitable for daily vital sign monitoring due to the discomfort and skin damage. Remote detection technology provides an effective solution to these issues. This article introduces an efficient and robust algorithm for estimating vital signs using frequency-modulated continuous-wave (FMCW) radar. The integration of this method with emerging technologies, such as the Internet of Things (IoT), enables long-term and contactless vital sign monitoring, which facilitates a new model of self-management for chronic diseases and their prevention. While the breathing estimation accuracy is typically constrained by noise, heart rate (HR) estimation is primarily hindered by strong interference from the breathing signal and its higher-order harmonics. A maximum likelihood estimator based on the Newton’s method is derived and proposed in this article to accurately assess the breathing and heartbeat frequencies by enhancing the precision of vital sign parameter estimation. The proposed algorithm is validated utilizing a 77 GHz FMCW radar and compared with a reliable reference sensor. Experimental results from eight subjects demonstrate that the proposed method enhances the estimation accuracy, outperforming both conventional spectral estimation and other methods. Specifically, the root mean-square error between the reference sensor measurements and the estimations is lower than 1 beats per minute (bpm) for breathing rates and 1.5 bpm for HRs. Additionally, the Bland-Altman plots demonstrate a high level of agreement between these estimations and the reference measurements.

A safe and reliable task planning method is a prerequisite for the collaborative execution of ocean observation data collection tasks by multiple unmanned surface vessels (multi-USVs). Deep Reinforcement Learning (DRL) combines the powerful nonlinear function-fitting capabilities of deep neural networks with the decision-making and control abilities of reinforcement learning, providing a novel approach to solving the multi-USV task planning problem. However, when applied to the field of multi-USV task planning, it faces challenges such as a vast exploration space, extended training times, and unstable training process. To this end, this paper proposes a multi-USV task planning method based on improved deep reinforcement learning. The proposed method draws on the idea of a value decomposition network, breaking down the multi-USV task planning problem into two subproblems: task allocation and autonomous collision avoidance. Different state spaces, action spaces, and reward functions are designed for the various subproblems. Based on this, a deep neural network is used to map the state space of each subproblem to the action space of each USV, and the generated strategy of the deep neural network is assessed based on the corresponding reward function. This successfully integrates task allocation and path planning into a comprehensive task planning framework. Deep neural networks consist of the Actor networks and the Critic networks. During the training phase of the Critic network, different methods are used to train different Critic networks to improve the convergence speed of the algorithm. An improved temporal difference error method is specifically applied to train the Critic network for evaluating autonomous collision avoidance strategies, resulting in improving the autonomous collision avoidance ability of USVs. At the same time, to improve the efficiency of task allocation, hierarchical mechanisms, and regional division mechanisms are introduced to construct sub-system task planning models, which further decompose the task planning problem. A combination of successor features and an improved temporal difference error method is specifically applied to train another Critic network for evaluating the sub-systems task allocation schemes and collaborative motion trajectories, aiming to enhance the allocation efficiency of the sub-systems. Furthermore, transfer learning is employed to merge the sub-system task planning, using it as a constraint to direct the exploration and assessment of both the cluster task allocation schemes and the cluster collaborative motion trajectories. This enables rapid and accurate learning for task allocation within the multi-USV cluster. During the training phase of the Actor network, the introduction of the experience replay method and target network technique is employed to enhance the proximal policy optimization algorithm. This facilitates distributed joint training of the Actor network, thereby improving the accuracy of the algorithm. Simulation results validate the effectiveness and superiority of this method.

With the advent of the Internet of Things (IoT) era, the multiunmanned aerial vehicle (UAV) networks have attracted great attention in the fields of source detection and localization. However, as the real-time signal processing performance of the UAV is limited by the computing speed and accuracy of the embedded hardware, the effectiveness of source localization is greatly reduced. Aiming at improving the accuracy and computational efficiency of source localization, a Cramer–Rao bound (CRB) weighted multi-UAV network source localization method is proposed based on the deep neural networks (DNNs) and spatial-spectrum fitting (SSF). The proposed source localization system is composed of UAVs equipped with a radar array. The source location can be achieved using the direction of arrival (DOA) of the source signals of UAVs, but the accuracy and real-time performance of the conventional DOA estimation algorithms are not satisfactory, and the data fusion strategy of the conventional cross-location framework needs further improvement. In the proposed method, a DNN-based SSF, denoted as the deep SSF (DeepSSF), is designed to achieve accurate DOA estimation. In the DeepSSF, the DOA estimation performance is guaranteed by the DNN’s strong nonlinear fitting ability and highly parallel structure. In addition, based on the obtained DOA information, the source is located once by every two UAVs. Finally, the source localization is realized based on the weighted CRB according to the principle that the more the DOA distribution deviates from zero, the lower the estimation accuracy. The simulation results verify the efficiency of the proposed method.