Abstract
Smart Homes are generally considered the final solution for living problem, especially for the health care of the elderly and disabled, power saving, etc. Human activity recognition in smart homes is the key to achieving home automation, which enables the smart services to automatically run according to the human mind. Recent research has made a lot of progress in this field; however, most of them can only recognize default activities, which is probably not needed by smart homes services. In addition, low scalability makes such research infeasible to be used outside the laboratory. In this study, we unwrap this issue and propose a novel framework to not only recognize human activity but also predict it. The framework contains three stages: recognition after the activity, recognition in progress, and activity prediction in advance. Furthermore, using passive RFID tags, the hardware cost of our framework is sufficiently low to popularize the framework. In addition, the experimental result demonstrates that our framework can realize good performance in both activity recognition and prediction with high scalability.
Highlights
Over the last few years, the Internet of Things (IoT) has been greatly developed with the help of mobile computing, edge computing, and cloud computing
To enable the smart home platforms to know more about their host, human activity recognition (HAR) has become an urgent challenge for the researchers
Represented by Ordonez’s work [30], they put inertial measurement units on the human body to collect the three-dimensional acceleration data and transform the data to posture by using deep learning algorithms such as Convolutional Neural Network (CNN) and recurrent neural network (RNN)
Summary
Over the last few years, the Internet of Things (IoT) has been greatly developed with the help of mobile computing, edge computing, and cloud computing. These activities cannot be used directly by the smart home system to provide scenario-based services Another way to detect the interaction between human and devices is to attach sensors to objects used extensively by humans [7]. We utilize passive RFID tags to detect the interaction between human and device and recognize a high-level activity by combining those low-level activities. In this stage, we can record the activities of the inhabitants. The strength is that our three-stage framework unwraps the task to recognize the high-level activity from wireless signal data This brings huge flexibility because every stage can be optimized independently or even replaced by other algorithms. The last strength of our framework is that both the cost of RFID tags and the computational complexity are sufficiently low to implement our framework in the current houses without much effort
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have