Different signal representations show different unique features for classification. In this paper, a feature fusion method with attention mechanism based on multiple signal representations is proposed for Φ-OTDR event classification with buried optical fiber. Each signal representation is fused after feature extraction to get richer and better features. With the help of a layer pruning method based on attention mechanism, the network size can be kept and avoid computation increase. Experiment results show that this method with 3 signal representations can improve the recognition accuracy to 97.93%, with 3.52% improvement compared to single representation approach. It also shows higher recognition accuracy than the tradition multiple signal representations fusion methods at the input stage. Furthermore, when it is used to fuse four representations, the recognition accuracy can be further improved to 99.11%.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1364/OE.472794 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Exploring the relationship between upwelling intensity and socio-ecological attributes of marine exploitation areas for benthic resources (MEABRs), along the southern Humboldt Current system.
J Environ Manage
January 2025
Departamento de Ecología y Biodiversidad, Facultad de Ciencias de la Vida, Universidad Andres Bello, Santiago, Chile; Centro de Investigaciones Marinas de Quintay, Universidad Andres Bello, Chile. Electronic address:
The Eastern Boundary Upwelling Systems (EBUS) sustains some of the most productive marine systems on Earth. Within each of these systems, the upwelling process exhibits spatial and temporal variation resulting in marked differences in upwelling intensity and seasonality along extensive coastlines. The study of this variation is well needed, given the magnitude of the services provided by upwelling, and the impending impacts of global warming on EBUS.
View Article and Find Full Text PDFImageless imagery in aphantasia revealed by early visual cortex decoding.
Curr Biol
January 2025
Key Laboratory of Brain, Cognition and Education Sciences, Ministry of Education, School of Psychology, South China Normal University, Guangzhou 510631, China; Center for Studies of Psychological Application, Guangdong Key Laboratory of Mental Health and Cognitive Science, School of Psychology, South China Normal University, Guangzhou 510631, China. Electronic address:
Activity in the early visual cortex is thought to tightly couple with conscious experience, including feedback-driven mental imagery. However, in aphantasia (a complete lack of visual imagery), the state of mental imagery, what takes its place, or how any activity relates to qualia remains unknown. This study analyzed univariate (amplitude) and multivariate (decoding) blood-oxygen-level-dependent (BOLD) signals in primary visual cortex during imagery attempts.
View Article and Find Full Text PDFVision-based postural balance assessment of sit-to-stand transitions performed by younger and older adults.
Gait Posture
January 2025
Department of Industrial Engineering and Management, Yuan Ze University, 135 Yuan Tung Road, Chungli District, Taoyuan, Taiwan. Electronic address:
Background: The use of inertial measurement units (IMUs) in assessing fall risk is often limited by subject discomfort and challenges in data interpretation. Additionally, there is a scarcity of research on attitude estimation features. To address these issues, we explored novel features and representation methods in the context of sit-to-stand transitions.
View Article and Find Full Text PDFIntermodulation frequencies reveal common neural assemblies integrating facial and vocal fearful expressions.
Cortex
December 2024
Institute of Research in Psychology (IPSY) & Institute of Neuroscience (IoNS), Louvain Bionics Center, University of Louvain (UCLouvain), Louvain-la-Neuve, Belgium; School of Health Sciences, HES-SO Valais-Wallis, The Sense Innovation and Research Center, Lausanne & Sion, Switzerland. Electronic address:
Effective social communication depends on the integration of emotional expressions coming from the face and the voice. Although there are consistent reports on how seeing and hearing emotion expressions can be automatically integrated, direct signatures of multisensory integration in the human brain remain elusive. Here we implemented a multi-input electroencephalographic (EEG) frequency tagging paradigm to investigate neural populations integrating facial and vocal fearful expressions.
View Article and Find Full Text PDFCircWaveDL: Modeling of optical coherence tomography images based on a new supervised tensor-based dictionary learning for classification of macular abnormalities.
Artif Intell Med
December 2024
Medical Image and Signal Processing Research Center, Isfahan University of Medical Sciences, Isfahan 81746-73461, Iran. Electronic address:
Modeling Optical Coherence Tomography (OCT) images is crucial for numerous image processing applications and aids ophthalmologists in the early detection of macular abnormalities. Sparse representation-based models, particularly dictionary learning (DL), play a pivotal role in image modeling. Traditional DL methods often transform higher-order tensors into vectors and then aggregate them into a matrix, which overlooks the inherent multi-dimensional structure of the data.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!