Unstaffed retail shops have emerged recently and been noticeably changing our shopping styles. In terms of these shops, the design of vending machine is critical to user shopping experience. The conventional design typically uses weighing sensors incapable of sensing what the customer is taking. In the present study, a smart unstaffed retail shop scheme is proposed based on artificial intelligence and the internet of things, as an attempt to enhance the user shopping experience remarkably. To analyze multiple target features of commodities, the SSD (300×300) algorithm is employed; the recognition accuracy is further enhanced by adding sub-prediction structure. Using the data set of 18, 000 images in different practical scenarios containing 20 different type of stock keeping units, the comparison experimental results reveal that the proposed SSD (300×300) model outperforms than the original SSD (300×300) in goods detection, the mean average precision of the developed method reaches 96.1% on the test dataset, revealing that the system can make up for the deficiency of conventional unmanned container. The practical test shows that the system can meet the requirements of new retail, which greatly increases the customer flow and transaction volume.

Emotional abnormality may be brought out by physiological fatigue. In order to solve the problem, an emotion detection method based on deep learning in medical and health data is proposed in this paper. First of all, the related content of emotional fatigue is studied. The concept and the classification of emotional fatigue are introduced. Then, a multi-modal data emotional fatigue detection system is designed. In the system, multi-channel convolutional aotoencoder neural network is used to extract electrocardiograms (ECG) data features and emotional text features for emotional fatigue detection. Secondly, the network structure of learning ECG features by multi-channel convolutional aotoencoder model is introduced in detail. And the network structure of learning emotional text features by convolutional aotoencoder model is also described in detail. Finally, multi-modal data features are combined for emotional detection. It is shown by the experimental results that the proposed model has an average accuracy of more than 85% in predicting emotional fatigue. INDEX TERMS Emotion detection model, multi-channel convolutional aotoencoder (MCAE), medical health, deep learning, emotional text features, intelligent data analysis.