Automatic detection of indoor occupancy based on improved YOLOv5 model.

Indoor occupancy detection is essential for energy efficiency control and Coronavirus Disease 2019 traceability. The number and location of people can be accurately identified and determined through classroom surveillance video analysis. This information is used to manage environmental equipment such as HVAC and lighting systems to reduce energy use. However, the mainstream one-stage YOLO algorithm still uses an anchor-based mechanism and couples detection heads to predict. This results in slow model convergence and poor detection performance for densely occluded targets. Therefore, this paper proposed a novel decoupled anchor-free VariFocal loss convolutional network algorithm DFV-YOLOv5 for occupancy detection to tackle these problems. The proposed method uses the YOLOv5 algorithm as a baseline. It uses the anchor-free mechanism to reduce the number of design parameters needing heuristic tuning. Afterwards, to reduce the coupling of the model, speed up the model's convergence ability, and improve the model detection performance, the detection head is decoupled based on the YOLOv5 model. It can resolve the conflict between classification and regression tasks. In addition, we use the VariFocal loss to assign more weights to difficult data points to optimize the class imbalance problem and use the training target q to measure positive samples, treating positive and negative samples asymmetrically. The total loss function is redesigned, the L 1 loss is increased, and the ablation experiment verifies the effect of the improved loss. By applying a hybrid activation function of the sigmoid linear unit and rectified linear unit, we improved the model's nonlinear representation and reduced the model's inference time. Finally, a classroom dataset was constructed to validate the occupancy detection performance of the model. The proposed model was compared with mainstream target detection models regarding average mean precision, memory allocation, execution time, and the number of parameters on the VOC2012, CrowdHuman and self-built datasets. The experimental results show that the method significantly improves the detection accuracy and robustness, shortens the inference time, and proves the practicality of the algorithm in occupancy detection compared with the mainstream target detection model and related variants of the model.

The Establishment and Practice of Pharmacy Care Service Based on Internet Social Media: Telemedicine in Response to the COVID-19 Pandemic.

Objective: For patients with chronic diseases requiring long-term use of medications who are quarantined at home, the management of medication therapy during the COVID-19 pandemic is a problem that pharmacists urgently need to discuss and solve. The study aims to establish and launch a telepharmacy framework to implement pharmaceutical care during the COVID-19 pandemic. Methods: To establish a remote pharmacy service model based on a medication consultation service platform under the official account of the "Beijing Pharmacists Association" on the social software WeChat app, obtain the medication consultation records from February 28 to April 27, 2020, during the worst period of the epidemic in China, and to perform a statistical analysis of the information about the patients seeking consultation, consultation process, content and follow-up results. Results: The medication consultation service system and telepharmacy service model based on social software were established in February 2020. The "Cloud Pharmacy Care" platform had 1,432 views and 66 followers and completed 39 counseling cases in 2 months. Counseling was available for patients of all ages. Of the 39 cases, 82.05% of patients were young and middle-aged. During the COVID-19 pandemic, the long-term medication usage problems of patients with chronic disease were effectively addressed using "Cloud Pharmacy Care". In the consultation, 35 cases (89.7%) were related to the use of medicines or health products, and 4 cases (10.3%) involved disease state management and the use of supplements. The top five drug-related issues included the selection of medications, the dosage and usage of drugs, medications for special populations, medication therapy management of chronic diseases, and adverse drug reactions. All consultations were completed within 4 h, with a positive review rate of 97.4%. Conclusion: During the COVID-19 pandemic, a remote pharmacy service "Cloud Pharmacy Care" based on the social software WeChat app was quickly constructed and applied to solve the medication-related problems of patients and the public during home quarantining. The significance of the study lies in the timely and interactive consultation model helps to carry out medication therapy management for chronically ill patients and improves patients' medication compliance, improves medical quality, and plays a positive role in promoting the popularization of safe medication knowledge.