In this paper, we have proposed and designed DPHK （data prediction based on HMM according to activity pattern knowledge mined from trajectories）, a real-time distributed predicted data collection system to solve the...In this paper, we have proposed and designed DPHK （data prediction based on HMM according to activity pattern knowledge mined from trajectories）, a real-time distributed predicted data collection system to solve the congestion and data loss caused by too many connections to sink node in indoor smart environment scenarios （like Smart Home, Smart Wireless Healthcare and so on）. DPHK predicts and sends predicted data at one time instead of sending the triggered data of these sensor nodes which people is going to pass in several times. Firstly, our system learns the knowl- edge of transition probability among sensor nodes from the historical binary motion data through data mining. Secondly, it stores the corresponding knowledge in each sensor node based on a special storage mechanism. Thirdly, each sensor node applies HMM （hidden Markov model） algorithm to pre- dict the sensor node locations people will arrive at according to the received message. At last, these sensor nodes send their triggered data and the predicted data to the sink node. The significances of DPHK are as follows： （a） the procedure of DPHK is distributed; （b） it effectively reduces the connection between sensor nodes and sink node. The time complexities of the proposed algorithms are analyzed and the performance is evaluated by some designed experiments in a smart environment.展开更多
基金The work was supported by the National Natural Science Foundation of China （Grant No. 61672115） and the Fundamental Research Funds for the Central Universities （CDJZR12180006）.
文摘In this paper, we have proposed and designed DPHK （data prediction based on HMM according to activity pattern knowledge mined from trajectories）, a real-time distributed predicted data collection system to solve the congestion and data loss caused by too many connections to sink node in indoor smart environment scenarios （like Smart Home, Smart Wireless Healthcare and so on）. DPHK predicts and sends predicted data at one time instead of sending the triggered data of these sensor nodes which people is going to pass in several times. Firstly, our system learns the knowl- edge of transition probability among sensor nodes from the historical binary motion data through data mining. Secondly, it stores the corresponding knowledge in each sensor node based on a special storage mechanism. Thirdly, each sensor node applies HMM （hidden Markov model） algorithm to pre- dict the sensor node locations people will arrive at according to the received message. At last, these sensor nodes send their triggered data and the predicted data to the sink node. The significances of DPHK are as follows： （a） the procedure of DPHK is distributed; （b） it effectively reduces the connection between sensor nodes and sink node. The time complexities of the proposed algorithms are analyzed and the performance is evaluated by some designed experiments in a smart environment.
