Gated Res2Net for Multivariate Time Series Analysis

Yang, Chao; Jiang, Mingxing; Liu, Yuan

doi:10.1109/ijcnn48605.2020.9207178

Cited by 7 publications

(10 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Res2Net [53]: this is a CNN backbone that uses group convolution and hierarchical residual-like connections between convolutional filter groups to achieve multi-scale receptive fields. • GRes2Net [31]: this work incorporates gates in Res2Net, where the gates' values are calculated based on a different method from ours-it additionally takes into account the original feature map before it is divided into groups when calculating gates' values. • Res2Net+SE: this work combines Res2Net with a Squeeze-and-Excitation Block (SE) [52] to leverage the effectiveness of attention modules.…”

Section: Baseline Methodsmentioning

confidence: 99%

“…Commonly used DL architectures include Recurrent Neural Net-works (RNNs), Gated Recurrent Unit (GRU) [18], Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) [17], and Transformer [16]. And recent studies heavily rely on CNNs to overcome the efficiency and scalability issues with recurrent models (e.g., RNN, LSTM, and GRU) [30][31][32].…”

Section: Multivariate Time Series Classificationmentioning

confidence: 99%

“…This, in turn, mitigates the problem of vanishing gradients without having to take long delays. To this end, we introduce the gating mechanism [31] into Res2Net at the convolutional stage to enhance feature extraction. Specifically, in our model (shown in Fig.…”

Section: Convolution Stagementioning

confidence: 99%

“…Note that, we only use the precedent output feature map y i−1 and the current input feature map x i to calculate the gate-this is different from the gating mechanism in [31]. More specifically, we omit the undivided feature map X as it contains redundant information and does not significantly improve the performance.…”

Section: Convolution Stagementioning

confidence: 99%

See 3 more Smart Citations

Attentional Gated Res2Net for Multivariate Time Series Classification

Yang

Wang

Yao

et al. 2022

Neural Process Lett

Self Cite

View full text Add to dashboard Cite

Multivariate time series classification is a critical problem in data mining with broad applications. It requires harnessing the inter-relationship of multiple variables and various ranges of temporal dependencies to assign the correct classification label of the time series. Multivariate time series may come from a wide range of sources and be used in various scenarios, bringing the classifier challenge of temporal representation learning. We propose a novel convolutional neural network architecture called Attentional Gated Res2Net for multivariate time series classification. Our model uses hierarchical residual-like connections to achieve multi-scale receptive fields and capture multi-granular temporal information. The gating mechanism enables the model to consider the relations between the feature maps extracted by receptive fields of multiple sizes for information fusion. Further, we propose two types of attention modules, channel-wise attention and block-wise attention, to better leverage the multi-granular temporal patterns. Our experimental results on 14 benchmark multivariate time-series datasets show that our model outperforms several baselines and state-of-the-art methods by a large margin. Our model outperforms the SOTA by a large margin, the classification accuracy of our model is 10.16% better than the SOTA model. Besides, we demonstrate that our model improves the performance of existing models when used as a plugin. Further, based on our experiments and analysis, we provide practical advice on applying our model to a new problem.

show abstract

Section: Baseline Methodsmentioning

confidence: 99%

Section: Multivariate Time Series Classificationmentioning

confidence: 99%

Section: Convolution Stagementioning

confidence: 99%

Section: Convolution Stagementioning

confidence: 99%

See 2 more Smart Citations

Attentional Gated Res2Net for Multivariate Time Series Classification

Yang

Wang

Yao

et al. 2022

Neural Process Lett

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the paper [14], they have developed a unified architecture of Res2Net and a gated mechanism called GRes2Net for analysing time series data with multiple time-dependent variables. The gated mechanism is used to control the flow of feature maps from the prior step to the next input.…”

Section: Literature Reviewmentioning

confidence: 99%

Time Series Classification using ResNet Ensemble

Monisha¹,

P²

2023

Preprint

View full text Add to dashboard Cite

One of the vital tasks in Time Series analysis is classifying time series data. This has attracted considerable interest and huge efforts in the past decades. This is still a challenging problem because of the complexity and nature of time series data. They are huge, complex, and constantly updated. There is an increasing demand to extract knowledge from time-series data. The time series has a natural feature that helps humans to visualize the structure of data. Increased interest in studying this particular data type has been sparked by the growth of recorded data, leading to a wealth of unique techniques for encoding, indexing, grouping, and categorising time series, among other tasks. To enhance the performance of traditional feature-based approaches, deep learning techniques were explored. Deep Neural Networks have revolutionized computer vision with their innovative deeper architec-tures like Residual Neural Networks and Convolutional Neural Networks. In this paper, the proposed deep learning architecture improves the performance of Residual Network for time series classification.

show abstract

MAG-Res2Net: a novel deep learning network for human activity recognition

Liu,

Zhao,

Dai

et al. 2023

Physiol. Meas.

View full text Add to dashboard Cite

Objective. Human activity recognition (HAR) has become increasingly important in healthcare, sports, and fitness domains due to its wide range of applications. However, existing deep learning based HAR methods often overlook the challenges posed by the diversity of human activities and data quality, which can make feature extraction difficult. To address these issues, we propose a new neural network model called MAG-Res2Net, which incorporates the Borderline-SMOTE data upsampling algorithm, a loss function combination algorithm based on metric learning, and the Lion optimization algorithm. Approach. We evaluated the proposed method on two commonly utilized public datasets, UCI-HAR and WISDM, and leveraged the CSL-SHARE multimodal human activity recognition dataset for comparison with state-of-the-art models. Main results. On the UCI-HAR dataset, our model achieved accuracy, F1-macro, and F1-weighted scores of 94.44%, 94.38%, and 94.26%, respectively. On the WISDM dataset, the corresponding scores were 98.32%, 97.26%, and 98.42%, respectively. Significance. The proposed MAG-Res2Net model demonstrates robust multimodal performance, with each module successfully enhancing model capabilities. Additionally, our model surpasses current human activity recognition neural networks on both evaluation metrics and training efficiency. Source code of this work is available at: https://github.com/LHY1007/MAG-Res2Net.

show abstract

Gated Res2Net for Multivariate Time Series Analysis

Cited by 7 publications

References 29 publications

Attentional Gated Res2Net for Multivariate Time Series Classification

Attentional Gated Res2Net for Multivariate Time Series Classification

Time Series Classification using ResNet Ensemble

MAG-Res2Net: a novel deep learning network for human activity recognition

Contact Info

Product

Resources

About