Falls are one of the main causes of elderly injuries. If the faller can be found in time, further injury can be effectively avoided. In order to protect personal privacy and improve the accuracy of fall detection, this paper proposes a fall detection algorithm using the CNN-Casual LSTM network based on three-axis acceleration and three-axis rotation angular velocity sensors. The neural network in this system includes an encoding layer, a decoding layer, and a ResNet18 classifier. Furthermore, the encoding layer includes three layers of CNN and three layers of Casual LSTM. The decoding layer includes three layers of deconvolution and three layers of Casual LSTM. The decoding layer maps spatio-temporal information to a hidden variable output that is more conducive relative to the work of the classification network, which is classified by ResNet18. Moreover, we used the public data set SisFall to evaluate the performance of the algorithm. The results of the experiments show that the algorithm has high accuracy up to 99.79%.

Human pose estimation is a complex detection task in which the network needs to capture the rich information contained in the images. In this paper, we propose MSTPose (Multi-Scale Transformer for human Pose estimation). Specifically, MSTPose leverages a high-resolution convolution neural network (CNN) to extract texture information from images. For the feature maps from three different scales produced by the backbone network, each branch performs the coordinate attention operations. The feature maps are then spatially and channel-wise flattened, combined with keypoint tokens generated through random initialization, and fed into a parallel Transformer structure to learn spatial dependencies between features. As the Transformer outputs one-dimensional sequential features, the mainstream two-dimensional heatmap method is abandoned in favor of one-dimensional coordinate vector regression. The experiments show that MSTPose outperforms other CNN-based pose estimation models and demonstrates clear advantages over CNN + Transformer networks of similar types.

Recognizing fatigue drivers is essential for improving road safety. Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) have been applied to identify the state of drivers. However, these models frequently encounter various challenges, including a vast number of parameters and low detection effectiveness. To address these challenges, we propose Dual-Lightweight-Swin-Transformer (DLS) for driver drowsiness detection. We also propose the Spatial-Temporal Fusion Model (STFM) and Global Saliency Fusion Model (GSFM), where STFM fuses the spatial-temporal features and GSFM fuses the features from different layers of STFM to enhance detection efficiency. Simulation results show that DLS increases accuracy by 0.33% and reduces the computational complexity by 49.3%. The running time per test epoch of DLS is reduced by 33.1%.

The application of deep reinforcement learning (DRL) has become a hot research topic in unmanned aerial vehicle (UAV) path planning and resource allocation. However, current DRL methods do not consider coordination among spectrum, path and power, leading to a waste of spectrum resources. A coordinated routing and resource allocation Q network (CRRQN) algorithm with low computing complexity in multiple UAVs scenarios is proposed, and a co-optimization module is proposed to enhance coordination among path planning, spectrum and power allocation in CRRQN by designing their reward functions. Moreover, double deep Q network (DDQN) is employed to guarantee its stability. The simulation shows that the CRRQN algorithm reduces the flight time by about 4% and improves the channel capacity by about 15% compared to the existing algorithms. The running time per test epoch of CRRQN reduces by about 35%.

Human pose estimation is a complex detection task in which the network needs to capture the rich information contained in the images. In this paper, we propose MSTPose (Multi-Scale Transformer for human Pose estimation). Specifically, MSTPose leverages a high-resolution Convolution neural network (CNN) to extract texture information from images. For the feature maps from three different scales produced by the backbone network, each branch performs the coordinate attention operations. The feature maps are then spatially and channel-wise flattened, combined with keypoint tokens generated through random initialization, and fed into a parallel Transformer structure to learn spatial dependencies between features. As the Transformer outputs one-dimensional sequential features, the mainstream two-dimensional heatmap method is abandoned in favor of one-dimensional coordinate vector regression. The experiments show that MSTPose outperforms other CNN-based pose estimation models and demonstrates clear advantages over CNN + Transformer networks of similar types.

A novel temporal convolution network-gated recurrent unit (NTCN-GRU) algorithm is proposed for the greatest of constant false alarm rate (GO-CFAR) frequency hopping (FH) prediction, integrating GRU and Bayesian optimization (BO). GRU efficiently captures the semantic associations among long FH sequences, and mitigates the phenomenon of gradient vanishing or explosion. BO improves extracting data features by optimizing hyperparameters besides. Simulations demonstrate that the proposed algorithm effectively reduces the loss in the training process, greatly improves the FH prediction effect, and outperforms the existing FH sequence prediction model. The model runtime is also reduced by three-quarters compared with others FH sequence prediction models.