Durability is considered as one of the main technical obstacles to the large-scale commercialization of proton exchange membrane fuel cells (PEMFCs), which can be effectively improved through degradation prediction techniques. This article proposes a stacked echo state network (ESN) based on the genetic algorithm (GA) to predict the future degradation trend of PEMFCs. By alternately using the projection layer and the encoding layer, the proposed method can make full use of the temporal kernel property of the ESN to encode the multiscale and multilevel dynamics of the stack voltage, thereby obtaining more robust generalization performance and higher accuracy than the existing methods. Specifically, a stack voltage time series of PEMFCs is projected into the high-dimensional echo state space of the reservoir. Then, an autoencoder projects the echo state representation into the low-dimensional feature space. After that, the GA is utilized to optimize the hyperparameters of the developed model. Based on two open-source datasets of PEMFCs with different accelerated test conditions, this article systematically tested the proposed degradation prediction methods based on different model structures. Test results demonstrate that the proposed method is superior to traditional prediction methods in terms of accuracy and generalization performance.

Given that transportation contributes to 23% of global energy-related greenhouse gas emissions, the electrification of the transport sector is an inevitable trend. This paper presents a hybrid energy management method that utilizes the Deep Deterministic Policy Gradient (DDPG) algorithm. To enhance its exploration capability and balance exploration and exploitation, the Locality Sensitive Hashing (LSH) algorithm and Prioritized Experience Replay (PER) algorithm are introduced. DDPG, being a deterministic strategy, typically explores the environment by adding noise to the action space, which lacks effective exploration capability. Therefore, the LSH algorithm is employed for approximate counting of state variables in high-dimensional continuous state spaces. This encourages agents to explore less frequently occurring state variables, thereby improving the algorithm’s exploration ability. Additionally, the integration of the PER algorithm enables more efficient utilization of limited sample data during experience replay, leading to improved learning efficiency and stability. In addition, periodic updates are used to compensate for the additional computational consumption caused by counting. Simulation results on driving cycles from the typical road conditions demonstrate that the proposed algorithm has stronger exploration ability and better management performance comparing with EMSs based on DDPG, DQN and Q-Learning. The LSH-PER-DDPG based EMS achieves a significant 8.5% reduction in lithium battery power consumption, a 6.25% increase in supercapacitor recovery, and a substantial 15.7% reduction in instantaneous fluctuation of lithium battery output current.

Cotton diseases cause low cotton production and fiber quality. Disease detection methods based on deep learning can integrate feature extraction and improve identification accuracy. We present an automatic cotton disease detection method to improve the identification accuracy of cotton disease. Cotton images are collected using a quadruped robot. ConvNeXt integrates the convolution neural network architecture with intrinsic superiority of transformer. The multiscale spatial pyramid attention (MSPA) module can help ConvNeXt concentrate on important regions of feature maps. ConvNeXt with the MSPA module shows the best recognition results of 97.2%, 99.7% and 100.0% on one competition dataset and two cotton datasets, respectively, with little increase in inference time. It indicates that the proposed model performs well in recognition accuracy with fast detection speed.

Durability and reliability are the major bottlenecks of the proton-exchange-membrane fuel cell (PEMFC) for large-scale commercial deployment. With the help of prognostic approaches, we can reduce its maintenance cost and maximize its lifetime. This paper proposes a hybrid prognostic method for PEMFCs based on a decomposition forecasting framework. Firstly, the original voltage data is decomposed into the calendar aging part and the reversible aging part based on locally weighted regression (LOESS). Then, we apply an adaptive extended Kalman filter (AEKF) and long short-term memory (LSTM) neural network to predict those two components, respectively. Three-dimensional aging factors are introduced in the physical aging model to capture the overall aging trend better. We utilize the automatic machine-learning method based on the genetic algorithm to train the LSTM model more efficiently and improve prediction accuracy. The aging voltage is derived from the sum of the two predicted voltage components, and we can further realize the remaining useful life estimation. Experimental results show that the proposed hybrid prognostic method can realize an accurate long-term voltage-degradation prediction and outperform the single model-based method or data-based method.

Nowadays, major depressive disorder (MDD) has become a crucial mental disease that endangers human health. Good results have been achieved by electroencephalogram (EEG) signals in the detection of depression. However, EEG signals are time-varying, and the distributions of the different subjects’ data are non-uniform, which poses a bad influence on depression detection. In this paper, the deep learning method with domain adaptation is applied to detect depression based on EEG signals. Firstly, the EEG signals are preprocessed and then transformed into pictures by two methods: the first one is to present the three channels of EEG separately in the same image, and the second one is the RGB synthesis of the three channels of EEG. Finally, the training and prediction are performed in the domain adaptation model. The results indicate that the domain adaptation model can effectively extract EEG features and obtain an average accuracy of 77.0 ± 9.7%. This paper proves that the domain adaptation method can effectively weaken the inherent differences of EEG signals, making the diagnosis of different users more accurate.

Pedestrian detection is an important branch of object detection due to its various applications. It plays a vital role in many fields such as intelligent surveillance systems. The recognition, identification and tracking modules of surveillance are based on efficient and accurate pedestrian detection. Our paper proposes an efficient model to solve real-time pedestrian detection with high accuracy based on modified ShuffleNet and YOLOv3 models. We provide a method to pick the dimensions and number of anchor boxes for predicting bounding boxes accurately. Then we use two improved shuffle units to lightweight the backbone of YOLOv3, which reduces the 67.5% floating point operations per second (FLOPs) and 65.1% parameters. We validate our model on CrowdHuman detection data set and get 62.7 mAP for face and 62.0 mAP person with 0.748 average IOU. Our network processes images in real-time at 186.1 frames per second for network and 12.5 frames per second for the entire model on CrowdHuman.