TY - GEN
T1 - Combining heterogeneous features for time series prediction
AU - Chu, Charles
AU - Brownlow, James
AU - Meng, Qinxue
AU - Fu, Bin
AU - Culbert, Ben
AU - Zhu, Min
AU - Xu, Guandong
AU - He, Xuezhong
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/7/1
Y1 - 2017/7/1
N2 - Time series prediction is a challenging task in reality, and various methods have been proposed for it. However, only the historical series of values are exploited in most of existing methods. Therefore, the predictive models might be not effective in some cases, due to: (1) the historical series of values is not sufficient usually, and (2) features from heterogeneous sources such as the intrinsic features of data samples themselves, which could be very useful, are not take into consideration. To address these issues, we proposed a novel method in this paper which learns the predictive model based on the combination of dynamic features extracted from series of historical values and static features of data samples. To evaluate the performance of our proposed method, we compare it with linear regression and boosted trees, and the experimental results validate our method's superiority.
AB - Time series prediction is a challenging task in reality, and various methods have been proposed for it. However, only the historical series of values are exploited in most of existing methods. Therefore, the predictive models might be not effective in some cases, due to: (1) the historical series of values is not sufficient usually, and (2) features from heterogeneous sources such as the intrinsic features of data samples themselves, which could be very useful, are not take into consideration. To address these issues, we proposed a novel method in this paper which learns the predictive model based on the combination of dynamic features extracted from series of historical values and static features of data samples. To evaluate the performance of our proposed method, we compare it with linear regression and boosted trees, and the experimental results validate our method's superiority.
UR - http://www.scopus.com/inward/record.url?scp=85050572636&partnerID=8YFLogxK
U2 - 10.1109/BESC.2017.8256383
DO - 10.1109/BESC.2017.8256383
M3 - Conference Proceeding
AN - SCOPUS:85050572636
T3 - Proceedings of 4th International Conference on Behavioral, Economic, and Socio-Cultural Computing, BESC 2017
SP - 1
EP - 2
BT - Proceedings of 4th International Conference on Behavioral, Economic, and Socio-Cultural Computing, BESC 2017
A2 - Demazeau, Yves
A2 - Gao, Jianbo
A2 - Xu, Guandong
A2 - Kozlak, Jaroslaw
A2 - Muller, Klaus
A2 - Razzak, Imran
A2 - Chen, Hao
A2 - Gu, Yanhui
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 4th International Conference on Behavioral, Economic, and Socio-Cultural Computing, BESC 2017
Y2 - 16 October 2017 through 18 October 2017
ER -