Search

Energy management strategies (EMSs) are one of the key technologies for the development of plug-in hybrid electric buses (PHEBs). This paper addresses the issue of optimal energy distribution for PHEBs under significant variations in passenger load at different bus stations, which cannot be solved by a single equivalent factor equivalent fuel consumption minimization energy management strategy (ECMS). An adaptive equivalent factor equivalent fuel consumption minimization energy management strategy (A-ECMS) considering passenger load is proposed. First, the powertrain system of the PHEB is modeled, and the accuracy of the model is verified in a simulation environment. Then, the reference SOC descent trajectory of the battery is obtained using a dynamic programming (DP) algorithm, the recursive least squares (RLS) method is employed to identify the passenger load, and the influence of different loads on the state of charge (SOC) trajectory under a single equivalent factor is analyzed. Finally, a genetic algorithm (GA) is used to establish the correspondence between passenger load, bus station, and equivalent factor, enabling the actual SOC to follow the reference SOC descent trajectory, thereby achieving optimal energy distribution. Simulation results demonstrate that the A-ECMS reduces fuel consumption of the PHEB per 100 km by 2.59% and 10.10% compared to the ECMS and rule-based EMS, respectively, validating the effectiveness of the proposed strategy.

The field of computer vision has shown great potential for the identification of crops at large scales based on multispectral images. However, the challenge in designing crop identification networks lies in striking a balance between accuracy and a lightweight framework. Furthermore, there is a lack of accurate recognition methods for non-large-scale crops. In this paper, we propose an improved encoder-decoder framework based on DeepLab v3+ to accurately identify crops with different planting patterns. The network employs ShuffleNet v2 as the backbone to extract features at multiple levels. The decoder module integrates a convolutional block attention mechanism that combines both channel and spatial attention mechanisms to fuse attention features across the channel and spatial dimensions. We establish two datasets, DS1 and DS2, where DS1 is obtained from areas with large-scale crop planting, and DS2 is obtained from areas with scattered crop planting. On DS1, the improved network achieves a mean intersection over union (mIoU) of 0.972, overall accuracy (OA) of 0.981, and recall of 0.980, indicating a significant improvement of 7.0%, 5.0%, and 5.7%, respectively, compared to the original DeepLab v3+. On DS2, the improved network improves the mIoU, OA, and recall by 5.4%, 3.9%, and 4.4%, respectively. Notably, the number of parameters and giga floating-point operations (GFLOPs) required by the proposed Deep-agriNet is significantly smaller than that of DeepLab v3+ and other classic networks. Our findings demonstrate that Deep-agriNet performs better in identifying crops with different planting scales, and can serve as an effective tool for crop identification in various regions and countries.

Integrating multi-omics data for cancer subtype recognition is an important task in bioinformatics. Recently, deep learning has been applied to recognize the subtype of cancers. However, existing studies almost integrate the multi-omics data simply by concatenation as the single data and then learn a latent low-dimensional representation through a deep learning model, which did not consider the distribution differently of omics data. Moreover, these methods ignore the relationship of samples. To tackle these problems, we proposed SADLN: A self-attention based deep learning network of integrating multi-omics data for cancer subtype recognition. SADLN combined encoder, self-attention, decoder, and discriminator into a unified framework, which can not only integrate multi-omics data but also adaptively model the sample’s relationship for learning an accurately latent low-dimensional representation. With the integrated representation learned from the network, SADLN used Gaussian Mixture Model to identify cancer subtypes. Experiments on ten cancer datasets of TCGA demonstrated the advantages of SADLN compared to ten methods. The Self-Attention Based Deep Learning Network (SADLN) is an effective method of integrating multi-omics data for cancer subtype recognition.

Objectives: Investigate the biomechanical characteristics in tracheostomized patients with aspiration following acquired brain injury (ABI) and further explore the relationship between the biomechanical characteristics and aspiration. Methods: This is a single-center cross-sectional study. The tracheostomized patients with aspiration following ABI and age-matched healthy controls were recruited. The biomechanical characteristics, including velopharynx (VP) maximal pressure, tongue base (TB) maximal pressure, upper esophageal sphincter (UES) residual pressure, UES relaxation duration, and subglottic pressure, were examined by high-resolution manometry and computational fluid dynamics simulation analysis. The penetration–aspiration scale (PAS) score was evaluated by a videofluoroscopic swallowing study. Results: Fifteen healthy subjects and fifteen tracheostomized patients with aspiration following ABI were included. The decreased VP maximal pressure, increased UES residual pressure, and shortened UES relaxation duration were found in the patient group compared with the control group (p < 0.05). Furthermore, the subglottic pressure significantly decreased in patients (p < 0.05), while no significant difference was found in TB maximal pressure between groups (p > 0.05). In addition, in the patient group, VP maximal pressure (rs = −0.439; p = 0.015), UES relaxation duration (rs = −0.532; p = 0.002), and the subglottic pressure (rs = −0.775; p < 0.001) were negatively correlated with the PAS score, while UES residual pressure (rs = 0.807; p < 0.001) was positively correlated with the PAS score (p < 0.05), the correlation between TB maximal pressure and PAS score (rs = −0.315; p = 0.090) did not reach statistical significance. Conclusions: The biomechanical characteristics in tracheostomized patients with aspiration following ABI might manifest as decreased VP maximal pressure and subglottic pressure, increased UES residual pressure, and shortened UES relaxation duration, in which VP maximal pressure, UES relaxation duration, subglottic pressure, and UES residual pressure were correlated with aspiration.

In the theory of traditional Chinese medicine, acupoints refer to special points and areas on the meridian line of the human body. Traditional Chinese medicine believes that the application of unique techniques such as pressing, kneading, rubbing, pushing, and patting to acupoints or massage with the help of specific tools has the effects of promoting blood circulation, dredging meridians, and eliminating fatigue. At present, most automatic massage devices are for large-area massage of the trunk, and few are specifically for acupoint massage of the limbs. First, this paper analyzes the characteristics of traditional Chinese medical acupoint massage and then obtains the design index of an automatic acupoint massage device. After that, based on the principle of a series elastic actuating mechanism, a flexible uni-acupoint massage device and control system, imitating the acupoint massage technique of traditional Chinese medicine, were designed. In order to analyze the massage force of the massage device, the man–machine contact dynamic model of the massage device was established, and the force of the massage device was simulated and analyzed. Finally, an experimental platform was built to verify the massage force and massage process of the massage device. The experimental results show that the massage device designed in this paper meets the indexes of traditional Chinese medical massage, in terms of the massage process and massage force, and verify the rationality of the design.