.png){kind=icon}
返回
Dynamic Multi-Scale Convolutional Neural Network for Time Series Classification
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2020.3002095.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Time series classification is an essential task in many real-world application domains. As a popular deep learning network, convolutional neural networks have achieved excellent performance in time series classification tasks. The filters of the convolutional neural networks are fixed length and shared by each sample. However, each time series usually has different time scale features. Therefore, convolutional neural networks are not capable of extracting multi-scale features for each sample flexibly. In this paper, we propose dynamic multi-scale convolutional neural network to extract multi-scale feature representations existing in each time series dynamically. Specifically, we design a variable-length filters generator to produce a set of variable-length filters conditioned on the input time series. To make model differentiable, we use the learnable soft masks to control the lengths of variable-length filters. Therefore, the feature representations of different time scales can be captured through the variable-length filters. Then, the max-over-time pooling is used to select the most discriminative local patterns. Finally, the fully connected layer with softmax output is employed to calculate the final probability distribution for each class. Experiments conducted on extensive time series datasets show that our approach can improve the performance of time series classification through the learning of variable-length filters. Furthermore, we demonstrate the effectiveness of dynamically learning variable-length filters for each sample through the visualization analysis.
Keyword:
Time series analysis
Task analysis
Feature extraction
Convolutional neural networks
Generators
Deep learning
Convolutional neural networks
multi-scale temporal features
time series classification
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
.png){kind=icon}
分享收藏Time-Series Classification with COTE: The Collective of Transformation-Based EnsemblesCOTE的时间序列分类: 基于变换的集合OAAI
OAAI分享收藏分享收藏
查看更多内容