Consumer Behavior Prediction During Covid-19 Pandemic Conditions Using Sentiment Analytics

Covid-19 pandemic created a global shift in the way how consumers purchase. Restrictions to movements of individuals and commodities created a big challenge on day today life. Due to isolation, social media usage has increased substantially, and these platforms created significant impact carrying news and sentiments instantaneously. These sentiments impacted the purchase behavior of consumers and online retailers witnessed variations in their sales. Retailers used various customer behavior prediction models such as Recommendation systems to influence consumers and increasing their sales. Due to Covid-19 pandemic, these models may not perform the same way due to changes in consumer behavior. By integrating consumer sentiments from online social media platform as another feature in the prediction machine learning models such as recommendation systems, retailers can understand consumer behavior better and create Recommendations appropriately. This provides the consumers with appropriate choice of products in essential and non-essential categories based on pandemic condition restrictions. This also helps retailers to plan their operations and inventory appropriately. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Optimization of Object Detection CNN with Weight Quantization and Scale Factor Consolidation

Due to the current Covid-19 pandemic, Convolutional Neural Networks (CNN) models attract attention in the applications to identify people with no masks. Developing an optimal CNN model is a challenging task especially for embedded deceives with limited hardware resources. To overcome the above challenge, we present a weight quantization technique aimed to produce compact CNN model for detection of people with mask or no mask. Its weights and feature maps are optimized using minimal fixed-point quantization at little or no sacrifice of its detection accuracy. The proposed weight quantization has been evaluated using a modified tiny-YOLOv2 model with the Mask and no-mask. Furthermore, we modified the internal model architecture to further reduce the model size and inference calculation by optimizing the order of max-pooling layers, consolidating the scale factors of batch normalization into only two pre-calculated parameters, and modifying the leaky ReLU activation function. The evaluation demonstrated that it saves more than 50 % of parameter memory and 56.21 % of inference computation. © 2021 IEEE.