Loading...
Please wait, while we are loading the content...
Similar Documents
Multivariate LSTM-FCNs for time series classification
| Content Provider | Scilit |
|---|---|
| Author | Karim, Fazle Majumdar, Somshubra Darabi, Houshang Harford, Samuel |
| Copyright Year | 2019 |
| Description | Journal: Neural Networks Over the past decade, multivariate time series classification has received great attention. We propose transforming the existing univariate time series classification models, the Long Short Term Memory Fully Convolutional Network (LSTM-FCN) and Attention LSTM-FCN (ALSTM-FCN), into a multivariate time series classification model by augmenting the fully convolutional block with a squeeze-and-excitation block to further improve accuracy. Our proposed models outperform most state-of-the-art models while requiring minimum preprocessing. The proposed models work efficiently on various complex multivariate time series classification tasks such as activity recognition or action recognition. Furthermore, the proposed models are highly efficient at test time and small enough to deploy on memory constrained systems. |
| Related Links | http://arxiv.org/pdf/1801.04503 |
| Ending Page | 245 |
| Page Count | 9 |
| Starting Page | 237 |
| ISSN | 08936080 |
| DOI | 10.1016/j.neunet.2019.04.014 |
| Journal | Neural Networks |
| Volume Number | 116 |
| Language | English |
| Publisher | Elsevier BV |
| Publisher Date | 2019-05-04 |
| Access Restriction | Open |
| Subject Keyword | Journal: Neural Networks Information Systems Convolutional Neural Network Long Short Term Memory Recurrent Neural Network Multivariate Time Series Classification |
| Content Type | Text |
| Resource Type | Article |
| Subject | Artificial Intelligence Cognitive Neuroscience |
