1. A novel framework is proposed to recognize and predict human activity in a smart home using passive RFID tags.
2. The framework consists of three stages: recognition after the activity, recognition in progress, and activity prediction in advance.
3. The experimental result demonstrates that the framework can realize good performance in both activity recognition and prediction with high scalability.
The article is generally reliable and trustworthy as it provides evidence for its claims through experiments conducted by the authors. The authors have also provided a detailed description of their methodology, which makes it easier to understand the results of their experiments. Furthermore, the authors have discussed potential risks associated with their proposed framework, such as privacy concerns due to the use of RFID tags. However, there are some points that could be improved upon in terms of trustworthiness and reliability. For example, the authors do not provide any information about how they selected participants for their experiments or what criteria were used to evaluate the performance of their proposed framework. Additionally, there is no discussion about possible counterarguments or alternative approaches that could be used instead of the proposed framework. Finally, there is no mention of any ethical considerations related to using RFID tags for human activity recognition and prediction in a smart home environment.