Recommendation of Electronic Mobile Gadgets Using Infused Decision Score With Mobile Radiation and Federated Sentiment Score

Specific Absorption Rate (SAR), is a measure of the amount of Radio-frequency (RF) energy absorbed by the body when using a mobile phone or other wireless devices. Some studies have suggested that high levels of RF energy may be harmful to human health in many aspects. Besides this, the use of smart mobiles for routine activities by individuals is already on the hike. This paper proposed a new framework utilizing the mobile SAR values analysis with the sentiment scores computed with federated learning to recommend mobiles. The proposed framework infused the two learning aspects to generate the decision score. The electronic device having the highest decision score will be recommended as the final product. For decision-making and model validation, various different mobile models are tested for their SAR and Microwave radiations. Also, mobile consumer sentiment is collected using the questionnaire for different locations. Finally, using federated learning the global model is utilized to compute the sentiment score. The experimentation result predicts the appropriate mobile device based on consumers’ preferences having the lowest SAR. In experimentation, four mobile devices were taken into consideration based on the market values and user preferences. The proposed approach provides the decision score of these devices as Samsung - 0.60, Apple - 0.57, Realme - 0.51, Xiaomi - 0.48, and OnePlus - 0.42. The results of the proposed study can help the electronics market to understand customer trends and help them update mobile devices with the lowest SAR for next-generation computing. The executable code of the proposed approach is uploaded on
https://github.com/AnkitVidyarthi/Recommendation
.