선택한 단어 수는 입니다.
최소 단어 이상 선택하여야 합니다.
최소 단어 이상 선택하여야 합니다.
선택한 단어 수는 30입니다.
최대 10 단어까지만 선택 가능합니다.
최대 10 단어까지만 선택 가능합니다.
제안 방법
- In this paper we propose a novel method applied on an independent mobile phone to extract changes from built-in accelerometer, orientation sensor and detect fall activity. Ourproposed approach ensures simplicity and high efficiency because the algorithm can be implemented easily on popular phones and the fall activity is detected on time.
- In this paper, we use an easy way with popular Google Nexus phone included built-in accelerometer and orientation sensor to observe the changes of acceleration and orientation based on characteristics of fall event and then propose a novel method based on acceleration thresholds and orientation and then measure similarity of new sample with typical collected falling sample to detect a fall event. The result from proposed algorithm shows the method can detect the falls effectively.
- Each experiment was repeated 20 times for each category. The experiment in daily life activity was performed five times including walking, running, and climbing up/down stair. The result is summarized in Table 4.
대상 데이터
- Fall detection experiments were done on 4 proposed categories. Five people aged over 23 years were recruited to evaluate our developed system. There have better experiments if we study on elderly people, but it is not easy because the risk of our experiment can harm to their health.
- After the human lying down on the ground, it causes acceleration return around 1G in 3rd step. The 4 young volunteers, (age 22-30) with height from 1.6m to 1.75m are selected to attend experiment while bringing Google Nexus One phone. We collect data from the proposed categories to observe variation of acceleration in the steps.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.