ScaleNet-multiscale neural-network architecture for time series prediction

计算机科学 时间序列 人工神经网络 系列(地层学) 人工智能 建筑 机器学习 生物 艺术 古生物学 视觉艺术
作者
Amir B. Geva
出处
期刊:IEEE Transactions on Neural Networks [Institute of Electrical and Electronics Engineers]
卷期号:9 (6): 1471-1482 被引量:134
标识
DOI:10.1109/72.728396
摘要

The effectiveness of a multiscale neural-network (NN) architecture for the time series prediction of nonlinear dynamic systems has been investigated. The prediction task is simplified by decomposing different scales of past windows into different scales of wavelets (local frequencies), and predicting the coefficients of each scale of wavelets by means of a separate multilayer perceptron NN. The short-term history (short past windows) is decomposed into the lower scales of wavelet coefficients (high frequencies) which are utilized for "detailed" analysis and prediction, while the long-term history (long past window) is decomposed into higher scales of wavelet coefficients (low frequencies) that are used for the analysis and prediction of slow trends in the time series. These coordinated scales of time and frequency provides an interpretation of the series structures, and more information about the history of the series, using fewer coefficients than other methods. The prediction's results concerning all the different scales of time and frequencies are combined by another "expert" perceptron NN which learns the weight of each scale in the goal-prediction of the original time series. Each network is trained by the backpropagation algorithm using the Levenberg-Marquadt method. The weights and biases are initialized by a new clustering algorithm of the temporal patterns of the time series, which improves the prediction results as compared to random initialization. Three main sets of data were analyzed: the sunspots' benchmark, fluctuations in a farinfrared laser and a nonlinear numerically generated series. Taking the ultimate goal to be the accuracy of the prediction, we found that the suggested multiscale architecture outperforms the corresponding single-scale architectures. The employment of improved learning methods for each of the ScaleNet networks can further improve the prediction results.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
李健的应助被科研通管家采纳,获得10
刚刚
灵兰完成签到,获得积分10
刚刚
桐桐的应助被科研通管家采纳,获得10
刚刚
刚刚
刚刚
null的应助被科研通管家采纳,获得10
刚刚
刚刚
1秒前
思源的应助被科研通管家采纳,获得10
1秒前
研友_VZG7GZ的应助被科研通管家采纳,获得10
1秒前
1秒前
852的应助被科研通管家采纳,获得10
1秒前
清秀送终发布了新的文献求助30
1秒前
彭于晏的应助被科研通管家采纳,获得10
1秒前
123完成签到,获得积分10
1秒前
1秒前
1秒前
星辰大海的应助被科研通管家采纳,获得10
1秒前
秋风的应助被科研通管家采纳,获得10
1秒前
2秒前
没素质的香菜完成签到 ,获得积分10
2秒前
脑洞疼的应助被科研通管家采纳,获得10
2秒前
Orange的应助被科研通管家采纳,获得10
2秒前
Litty完成签到,获得积分10
2秒前
大个的应助被科研通管家采纳,获得10
2秒前
烟花的应助被科研通管家采纳,获得10
2秒前
edk完成签到,获得积分10
2秒前
2秒前
杀手Sasy完成签到,获得积分10
3秒前
3秒前
Lxy_zb完成签到 ,获得积分10
3秒前
ccxr完成签到,获得积分10
3秒前
4秒前
打打的应助被苹果思天采纳,获得10
5秒前
7秒前
雯雯发布了新的文献求助10
7秒前
干就完发布了新的文献求助10
7秒前
叶瑶完成签到 ,获得积分10
8秒前
个性天晴完成签到 ,获得积分10
8秒前
浮云客发布了新的文献求助10
9秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183792
求助须知:如何正确求助?哪些是违规求助? 9573020
关于积分的说明 21828776
捐赠科研通 7780959
什么是DOI,文献DOI怎么找? 3434116
关于科研通互助平台的介绍 2558301
邀请新用户注册赠送积分活动 2480611