Deep Multiple Metric Learning for Time Series Classification

Chen, Zhi; Liu, Yongguo; Zhu, Jiajing; Zhang, Yun; Li, Qiaoqin; Jin, Rongjiang; He, Xia

doi:10.1109/access.2021.3053703

Cited by 5 publications

(2 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DML has classically been employed in discrete highdimensional data types, such as images, rather than in the time series domain. This has not been due to a lack of theoretical grounding [45], [46], [47], but relates more to the difficulty of building discrete class pairings for signals when components have variable temporal dynamics, which may explain the lack of DML methods for neurophysiological signal processing in the literature. However, when the independent factors in the generative process have relatively short and stereotyped responses, such as spiking neurons, it becomes straightforward to break the signal into windows centered on each activation.…”

Section: Related Workmentioning

confidence: 99%

Deep Metric Learning With Locality Sensitive Mining for Self-Correcting Source Separation of Neural Spiking Signals

Clarke

Farina

2024

IEEE Trans. Cybern.

View full text Add to dashboard Cite

Automated source separation algorithms have become a central tool in neuroengineering and neuroscience, where they are used to decompose neurophysiological signal into its constituent spiking sources. However, in noisy or highly multivariate recordings these decomposition techniques often make a large number of errors. Such mistakes degrade online humanmachine interfacing methods and require costly post-hoc manual cleaning in the offline setting. In this article we propose an automated error correction methodology using a deep metric learning (DML) framework, generating embedding spaces in which spiking events can be both identified and assigned to their respective sources. Furthermore, we investigate the relative ability of different DML techniques to preserve the intraclass semantic structure needed to identify incorrect class labels in neurophysiological time series. Motivated by this analysis, we propose locality sensitive mining, an easily implemented sampling-based augmentation to typical DML losses which substantially improves the local semantic structure of the embedding space. We demonstrate the utility of this method to generate embedding spaces which can be used to automatically identify incorrectly labeled spiking events with high accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Metric Learning With Locality Sensitive Mining for Self-Correcting Source Separation of Neural Spiking Signals

Clarke

Farina

2024

IEEE Trans. Cybern.

View full text Add to dashboard Cite

show abstract

“…The learning in the model space transforms the original series to a recurrent neural networks (RNN), tries to calculate the 'distance' between RNNs, and conducts the learning in the RNN space [26]- [28]. The representation and discrimination abilities have been investigated later [29] and the multi-objective version has been proposed [30]. Compared with this proposed method, these methods are lack of the modeling of interactions between the human body and participating objects, which is critical for complicated human activity recognition.…”

Section: Related Workmentioning

confidence: 99%

Learning Dynamic Spatio-Temporal Relations for Human Activity Recognition

et al. 2020

View full text Add to dashboard Cite

Human activity, which usually consists of several actions (sub-activities), generally covers interactions among persons and/or objects. In particular, human actions involve certain spatial and temporal relationships, are the components of more complicated activity, and evolve dynamically over time. Therefore, the description of a single human action and the modeling of the evolution of successive human actions are two major issues in human activity recognition. In this paper, we develop a method for human activity recognition that tackles these two issues. In the proposed method, an activity is divided into several successive actions represented by spatio-temporal patterns, and the evolution of these actions are captured by a sequential model. A refined comprehensive spatio-temporal graph is utilized to represent a single action, which is a qualitative representation of a human action incorporating both the spatial and temporal relations of the participant objects. Next, a discrete hidden Markov model is applied to model the evolution of action sequences. Moreover, a fully automatic partition method is proposed to divide a longterm human activity video into several human actions based on variational objects and qualitative spatial relations. Finally, a hierarchical decomposition of the human body is introduced to obtain a discriminative representation for a single action. Experimental results on the Cornell Activity Dataset demonstrate the efficiency and effectiveness of the proposed approach, which will enable long videos of human activity to be better recognized.

show abstract

Deep multi-metric training: the need of multi-metric curve evaluation to avoid weak learning

Mamalakis,

Banerjee,

Ray

et al. 2024

Neural Comput & Applic

View full text Add to dashboard Cite

The development and application of artificial intelligence-based computer vision systems in medicine, environment, and industry are playing an increasingly prominent role. Hence, the need for optimal and efficient hyperparameter tuning strategies is more than crucial to deliver the highest performance of the deep learning networks in large and demanding datasets. In our study, we have developed and evaluated a new training methodology named deep multi-metric training (DMMT) for enhanced training performance. The DMMT delivers a state of robust learning for deep networks using a new important criterion of multi-metric performance evaluation. We have tested the DMMT methodology in multi-class (three, four, and ten), multi-vendors (different X-ray imaging devices), and multi-size (large, medium, and small) datasets. The validity of the DMMT methodology has been tested in three different classification problems: (i) medical disease classification, (ii) environmental classification, and (iii) ecological classification. For disease classification, we have used two large COVID-19 chest X-rays datasets, namely the BIMCV COVID-19+ and Sheffield hospital datasets. The environmental application is related to the classification of weather images in cloudy, rainy, shine or sunrise conditions. The ecological classification task involves a classification of three animal species (cat, dog, wild) and a classification of ten animals and transportation vehicles categories (CIFAR-10). We have used state-of-the-art networks of DenseNet-121, ResNet-50, VGG-16, VGG-19, and DenResCov-19 (DenRes-131) to verify that our novel methodology is applicable in a variety of different deep learning networks. To the best of our knowledge, this is the first work that proposes a training methodology to deliver robust learning, over a variety of deep learning networks and multi-field classification problems.

show abstract

Deep Multiple Metric Learning for Time Series Classification

Cited by 5 publications

References 54 publications

Deep Metric Learning With Locality Sensitive Mining for Self-Correcting Source Separation of Neural Spiking Signals

Deep Metric Learning With Locality Sensitive Mining for Self-Correcting Source Separation of Neural Spiking Signals

Learning Dynamic Spatio-Temporal Relations for Human Activity Recognition

Deep multi-metric training: the need of multi-metric curve evaluation to avoid weak learning

Contact Info

Product

Resources

About