Deep learning-based recognition of Chinese dishes in a waiterless restaurant

The outbreak of COVID-19 makes it danger going out dining. Building waiterless restaurants becomes meaningful and urgent. Because automate and accurate recognition of dishes is indispensable for ordering and charging self-served food, this study investigates the feasibility of a prototype system that uses deep networks for recognizing Chinese dishes in a self-serving restaurant. Specifically, ≈ 17,000 images and 45,000 instances of 28 categories of dishes are collected using a fixed micro-camera equipment, and 5 deep learning networks are explored for dish recognition. Experimental results on the prototype system reveal that 3 transferred deep learning networks achieve high performance, and the accuracy, mean average precision and recall are larger than 97.0%. Real-time, accurate dish recognition in an automate fashion is highly related to a great customer experience, and the real-life evaluation in this study suggests that transferred deep networks are promising to fulfill this task. © 2022 IEEE.

From the Perspective of Social Design: Research on the Construction of Mass Epidemic Prevention Media System for Elderly Groups

The first case of the NOVEL CORONAVIRUS disease (COVID-19) patient appeared in China in December 2019, besides this, it spread widely with a large proportion of elderly among the newly diagnosed cases last year. To confirm whether the mass media’s epidemic prevention education needs to be improved in its spread among middle-aged and elderly people, The research was conducted on 2582 Chinese people, who were asked about personal risk perception, self-efficacy, the effectiveness of protective equipment, availability of protective equipment and so on. Logistic binary analysis and logistic ordered analysis were employed to determine how favorably respondents of different age groups received epidemic prevention education, as well as predictions of implications of acceptance on epidemic prevention behavior. The results indicate that epidemic prevention education can improve individuals’ ability to protect themselves in public health emergencies, also shows that the mass media’s epidemic prevention education has a greater connection with individual prevention measures, but has slimmer coverage among the middle-aged and elderly, which needs to be improved. Therefore, the research suggests forward several topics which are valuable of application in the construction of the mass epidemic prevention media system while the process of combining design and sociology. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Medical Staff Scheduling Problem in Chinese Mobile Cabin Hospitals During Covid-19 Outbreak

In this paper, we discuss the medical staff scheduling problem in the Mobile Cabin Hospital (MCH) during the pandemic outbreaks. We investigate the working contents and patterns of the medical staff in the MCH of Wuhan during the outbreak of Covid-19. Two types of medical staff are considered in the paper, i.e., physicians and nurses. Besides, two different types of physicians are considered, i.e., the expert physician and general physician, and the duties vary among different types of physicians. The objective of the studied problem is to get the minimized number of medical staff required to accomplish all the duties in the MCH during the planning horizon. To solve the studied problem, a general Variable Neighborhood Search (general VNS) is proposed, involving the initialization, the correction strategy, the neighborhood structure, the shaking procedure, the local search procedure, and the move or not procedure. The mutation operation is adopted in the shaking procedure to make sure the diversity of the solution and three neighborhood structure operations are applied in the local search procedure to improve the quality of the solution. © 2021, Springer Nature Switzerland AG.

Spatial Joint Upsampling Based Crowd Counting

Crowd counting are playing an important role in controlling public crowd flow, maintaining public safety order, and controlling novel coronavirus (2019-nCoV). In recent years, researchers have proposed many excellent crowd counting methods, but these methods still have some problems such as insufficient information obtained in the output density map. Based on it, this paper proposed a crowd counting method based on Spatial Joint Upsampling(SJU). The method uses VGG-16 as the backbone of front-end. Meanwhile the back-end network extracts rich pixel details and spatial context information by adding cascaded joint upsampling model to combine multi-layer high-resolution feature maps, which ultimately have reached the effect of reducing the computational complexity and lifting the accuracy. Experimental results show that SJU has better performance than most crowd counting methods. This method has achieved MAE/MSE of 62.1/99.8 and 7.6/11.5 on the two parts of the public dataset ShanghaiTech A and B, respectively. The MAE/MSE after conducting curriculum learning on this dataset is 61.3/99.2. In addition, this method has also achieved excellent results on the large-scale complex crowd dataset NWPU-Crowd, with a MAE/MSE of 105.1/419.3, indicating that the Spatial Joint Upsampling(SJU) network has outstanding performance in the task of crowd counting in complex scenes.