Aiming at the path planning problem of unmanned aerial vehicle (UAV) base stations when performing search tasks, this paper proposes a Double DQN-state splitting Q network (DDQN-SSQN) algorithm that combines state splitting and optimal state to complete the optimal path planning of UAV based on the Deep Reinforcement Learning DDQN algorithm. The method stores multidimensional state information in categories and uses targeted training to obtain optimal path information. The method also references the received signal strength indicator (RSSI) to influence the reward received by the agent, and in this way reduces the decision difficulty of the UAV. In order to simulate the scenarios of UAVs in real work, this paper uses the Open AI Gym simulation platform to construct a mission system model. The simulation results show that the proposed scheme can plan the optimal path faster than other traditional algorithmic schemes and has a greater advantage in the stability and convergence speed of the algorithm.

Burn is a common traumatic disease. After severe burn injury, the human body will increase catabolism, and burn wounds lead to a large amount of body fluid loss, with a high mortality rate. Therefore, in the early treatment for burn patients, it is essential to calculate the patient’s water requirement based on the percentage of the burn wound area in the total body surface area (TBSA%). However, burn wounds are so complex that there is observer variability by the clinicians, making it challenging to locate the burn wounds accurately. Therefore, an objective, accurate location method of burn wounds is very necessary and meaningful. Convolutional neural networks (CNNs) provide feasible means for this requirement. However, although the CNNs continue to improve the accuracy in the semantic segmentation task, they are often limited by the computing resources of edge hardware. For this purpose, a lightweight burn wounds segmentation model is required. In our work, we constructed a burn image dataset and proposed a U-type spiking neural networks (SNNs) based on retinal ganglion cells (RGC) for segmenting burn and non-burn areas. Moreover, a module with cross-layer skip concatenation structure was introduced. Experimental results showed that the pixel accuracy of the proposed reached 92.89%, and our network parameter only needed 16.6 Mbytes. The results showed our model achieved remarkable accuracy while achieving edge hardware affinity.

Snoring is a widespread occurrence that impacts human sleep quality. It is also one of the earliest symptoms of many sleep disorders. Snoring is accurately detected, making further screening and diagnosis of sleep problems easier. Snoring is frequently ignored because of its underrated and costly detection costs. As a result, this research offered an alternative method for snoring detection based on a long short-term memory based spiking neural network (LSTM-SNN) that is appropriate for large-scale home detection for snoring. We designed acquisition equipment to collect the sleep recordings of 54 subjects and constructed the sleep sound database in the home environment. And Mel frequency cepstral coefficients (MFCCs) were extracted from these sound signals and encoded into spike trains by a threshold encoding approach. They were classified automatically as non-snoring or snoring sounds by our LSTM-SNN model. We used the backpropagation algorithm based on an alternative gradient in the LSTM-SNN to complete the parameter update. The categorization percentage reached an impressive 93.4%, accompanied by a remarkable 36.9% reduction in computer power compared to the regular LSTM model.

Large-scale deep learning algorithms have emerged as the primary technology for underwater target detection, demonstrating exceptional inference effectiveness and accuracy. However, the real-time capabilities of these high-accuracy algorithms rely heavily on high-performance computing resources like CPUs and GPUs. It presents a challenge for deploying them on underwater embedded devices, where communication is limited and computational and energy resources are constrained. To overcome this, this paper focuses on constructing a lightweight yet highly accurate deep learning model suitable for real-time underwater target detection on edge devices. We develop a new lightweight model, named YOLO-TN, for real-time underwater object recognition on edge devices using a self-constructed image dataset captured by an underwater unmanned vehicle. This model is obtained by compressing the classical YOLO-V5, utilizing a globally differentiable deep neural architecture search method and a network pruning technique. Experimental results show that the YOLO-TN achieves a mean average precision (mAP) of 0.5425 and an inference speed of 28.6 FPS on embedded devices, while its parameter size is between 0.4 M and 0.6 M. This performance is a fifth of the parameter size and twelve times the FPS of the YOLO-V5 model, with almost no loss in inference accuracy. In conclusion, this framework significantly enhances the feasibility of deploying large-scale deep learning models on edge devices with high precision and compactness, ensuring real-time inference and offline deployment capabilities. This research is pivotal in addressing the computational challenges faced in underwater operations.

In recent years, with the development of artificial intelligence, smart catering has become one of the most popular research fields, where ingredients identification is a necessary and significant link. The automatic identification of ingredients can effectively reduce labor costs in the acceptance stage of the catering process. Although there have been a few methods for ingredients classification, most of them are of low recognition accuracy and poor flexibility. In order to solve these problems, in this paper, we construct a large-scale fresh ingredients database and design an end-to-end multi-attention-based convolutional neural network model for ingredients identification. Our method achieves an accuracy of 95.90% in the classification task, which contains 170 kinds of ingredients. The experiment results indicate that it is the state-of-the-art method for the automatic identification of ingredients. In addition, considering the sudden addition of some new categories beyond our training list in actual applications, we introduce an open-set recognition module to predict the samples outside the training set as the unknown ones. The accuracy of open-set recognition reaches 74.6%. Our algorithm has been deployed successfully in smart catering systems. It achieves an average accuracy of 92% in actual use and saves 60% of the time compared to manual operation, according to the statistics of actual application scenarios.

Large-scale deep learning models have produced significant results in underwater visual image target detection. However, deploying these models on underwater embedded devices poses a series of issues and challenges. Firstly, underwater devices have limited communication capabilities and carry relatively short supply of energy, resulting in constrained computing power for edge devices. Secondly, the large scale of deep neural networks creates a conflict in power demands with unmanned underwater equipment. Thirdly, insufficient underwater light and turbid water quality will lead to degradation problems in the images acquired by the device. In this paper, we build an offline system to complete the task of underwater scene target recognition. This paper introduces several innovations: 1) The new YOLO-TN model is developed by compressing the target recognition model based on YOLO-V5. The model use a model compression algorithm replace the YOLO-V5’s backbone network with a lightweight network, then perform parameter pruning on the model detection head, while reduce the size of the input image. The model uses a Teacher-guided Neural Architecture Search method based on YOLO-V5, named as YOLO-TN. 2)A method for constructing and processing real underwater environment data sets is designed. The datasets are all captured using underwater unmanned vehicles in real underwater environments, addressing issues present in existing underwater datasets, such as unbalanced target volume and single-image environment. Experimental results demonstrate that the YOLO-TN model significantly reduces the model size while maintaining the original recognition accuracy. Furthermore, it achieves 28.6 FPS on embedded devices, which is 12 times that of the original model.