Road damage detection is an important task to ensure road safety and realize the timely repair of road damage. The previous manual detection methods are low in efficiency and high in cost. To solve this problem, an improved YOLOv5 road damage detection algorithm, MN-YOLOv5, was proposed. We optimized the YOLOv5s model and chose a new backbone feature extraction network MobileNetV3 to replace the basic network of YOLOv5, which greatly reduced the number of parameters and GFLOPs of the model, and reduced the size of the model. At the same time, the coordinate attention lightweight attention module is introduced to help the network locate the target more accurately and improve the target detection accuracy. The KMeans clustering algorithm is used to filter the prior frame to make it more suitable for the dataset and to improve the detection accuracy. To improve the generalization ability of the model, a label smoothing algorithm is introduced. In addition, the structure reparameterization method is used to accelerate model reasoning. The experimental results show that the improved YOLOv5 model proposed in this paper can effectively identify pavement cracks. Compared with the original model, the mAP increased by 2.5%, the F1 score increased by 2.6%, and the model volume was smaller than that of YOLOv5. 1.62 times, the parameter was reduced by 1.66 times, and the GFLOPs were reduced by 1.69 times. This method can provide a reference for the automatic detection method of pavement cracks.

Background Even though tofu is a traditional Chinese food loved by Asian people the wastewater generated during the production of tofu can pollute the environment, and the treatment of this generated wastewater can increase the operating cost of the plant. In this study, the production of nattokinase could be achieved by using the nitrogen source in tofu processing wastewater (TPW) instead of using the traditional nattokinase medium. This meets the need for the low-cost fermentation of nattokinase and at the same time addresses the environmental pollution concerns caused by the wastewater. Bacillus subtilis 13,932 is, a high yielding strain of nattokinase, which is stored in our laboratory. To increase the activity of nattokinase in the tofu process wastewater fermentation medium, the medium components and culture parameters were optimized. Nattokinase with high enzymatic activity was obtained in 7 L and 100 L bioreactors when TPW was used as the sole nitrogen source catalyzed by Bacillus subtilis. Such a result demonstrates that the production of nattokinase from TPW fermentation using B. subtilis can be implemented at an industrial level. Results The peptide component in TPW is a crucial factor in the production of nattokinase. Box–Behnken design (BBD) experiments were designed to optimize various critical components, i.e., Glucose, TPW, MgSO4·7H2O, CaCl2, in nattokinase fermentation media. A maximum nattokinase activity was recorded at 37 °C, pH 7.0, 70 mL liquid medium, and 200 rpm. The highest nattokinase activities obtained from 7 to 100 L bioreactors were 8628.35 ± 113.87 IU/mL and 10,661.97 ± 72.47 IU/mL, respectively. Conclusions By replacing the nitrogen source in the original medium with TPW, there was an increase in the enzyme activity by 19.25% after optimizing the medium and culture parameters. According to the scale-up experiment from conical flasks to 100 L bioreactors, there was an increase in the activity of nattokinase by 47.89%.

In recent years, the urbanization process has brought modernity while also causing key issues, such as traffic congestion and parking conflicts. Therefore, cities need a more intelligent "brain" to form more intelligent and efficient transportation systems. At present, as a type of machine learning, the traditional clustering algorithm still has limitations. K-means algorithm is widely used to solve traffic clustering problems, but it has limitations, such as sensitivity to initial points and poor robustness. Therefore, based on the hybrid architecture of Quantum Annealing (QA) and brain-inspired cognitive computing, this study proposes QA and Brain-Inspired Clustering Algorithm (QABICA) to solve the problem of urban taxi-stand locations. Based on the traffic trajectory data of Xi'an and Chengdu provided by Didi Chuxing, the clustering results of our algorithm and K-means algorithm are compared. We find that the average taxi-stand location bias of the final result based on QABICA is smaller than that based on K-means, and the bias of our algorithm can effectively reduce the tradition K-means bias by approximately 42%, up to approximately 83%, with higher robustness. QA algorithm is able to jump out of the local suboptimal solutions and approach the global optimum, and brain-inspired cognitive computing provides search feedback and direction. Thus, we will further consider applying our algorithm to analyze urban traffic flow, and solve traffic congestion and other key problems in intelligent transportation.

No abstract