Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Gesture recognition offers considerable promise for enhancing the naturalness, intuitiveness, and efficiency of human-computer interaction. In this paper, a novel hand gesture recognition system based on a single-mode, multimode, multicore optical fiber sensing structure is presented. By leveraging deep learning to analyze fiber specklegrams and training a simplified six-layer ResNet network, accurate and efficient hand gesture recognition was realized with minimal hardware requirements and high stability. Its compact design further supports integration into wearable devices, highlighting its significance for practical applications.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1364/OE.546834 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Multi-component collaborative design yields robust hydrogel sensors with superior environmental adaptability for machine learning-assisted gesture recognition.
J Colloid Interface Sci
September 2025
Key Laboratory of Urban Rail Transit Intelligent Operation and Maintenance Technology & Equipment of Zhejiang Province, College of Engineering, Zhejiang Normal University, Jinhua 321004, China. Electronic address:
Developing high-performance wearable flexible sensors that can adapt well to complex environments has become a hotspot. Herein, a polyvinyl alcohol based composite hydrogel sensor with high mechanical strength, desirable frost/swelling resistance, and highly sensitive sensing performance was proposed by a multi-component collaborative design strategy. Meanwhile, an intelligent gesture recognition system was established by combining machine learning algorithm.
View Article and Find Full Text PDFDeep Learning-Assisted Organogel Pressure Sensor for Alphabet Recognition and Bio-Mechanical Motion Monitoring.
Nanomicro Lett
September 2025
Nanomaterials & System Lab, Major of Mechatronics Engineering, Faculty of Applied Energy System, Jeju National University, Jeju, 63243, Republic of Korea.
Wearable sensors integrated with deep learning techniques have the potential to revolutionize seamless human-machine interfaces for real-time health monitoring, clinical diagnosis, and robotic applications. Nevertheless, it remains a critical challenge to simultaneously achieve desirable mechanical and electrical performance along with biocompatibility, adhesion, self-healing, and environmental robustness with excellent sensing metrics. Herein, we report a multifunctional, anti-freezing, self-adhesive, and self-healable organogel pressure sensor composed of cobalt nanoparticle encapsulated nitrogen-doped carbon nanotubes (CoN CNT) embedded in a polyvinyl alcohol-gelatin (PVA/GLE) matrix.
View Article and Find Full Text PDFEnergy Dissipation Mediated by Multiple Noncovalent Interactions in Hydrogen-Bonded Organic Frameworks-Based Hydrogels for Wearable Gesture-to-Recognition Translation.
Angew Chem Int Ed Engl
September 2025
Hebei Key Laboratory of Functional Polymer, School of Chemical Engineering and Technology, Hebei University of Technology, Tianjin, 300130, China.
Hydrogels hold great promises in intelligent wearable gesture-to-recognition translation devices, but high mechanical robustness usually encounters low sensitivity and poor cycling stability, it is pivotal and challenging to balance energy dissipation and conductivity. Herein, the soft-hard multiphase hydrogels have been proposed for the first time through noncovalently threading polymerizable deep eutectic solvent (PDES) into hydrogen-bonded organic frameworks (HOFs). Fluorine groups on HOF (HOF-F) are presented as the hydrogen bond acceptors to form multiple noncovalent interactions between HOF-F and PDES, which expedites the energy dissipation with synchronous increment of ion transport in hydrogels.
View Article and Find Full Text PDFMSFI: Multi-timescale spatio-temporal features integration in spiking neural networks.
Neural Netw
August 2025
College of Information Science and Technology, Jinan University, Guangzhou, Guangdong, 511436, China. Electronic address:
Dynamic vision sensors (DVS) asynchronously encode the polarity of brightness changes with high temporal resolution and a wide dynamic range, making them ideal for capturing temporal information. Spiking neural networks (SNNs) are well-suited for handling such event streams due to their inherent temporal information processing capability. However, existing SNNs only transmit membrane potential across timesteps, neglecting spatial dependencies and failing to extract complex temporal features.
View Article and Find Full Text PDFIdentity Needs in Intergroup Relations: Between the Age of Apology and Victimhood Culture.
Annu Rev Psychol
September 2025
2Department of Psychology, University of Zurich, Zurich, Switzerland.
Around the turn of the millennium, the social representation of minorities in Western societies shifted from marginalized deviants to victims of injustice, prompting calls for recognition and reparation. Drawing on the social identity tradition, we argue that this shift in representation gave rise to new identity needs, with victim groups seeking to restore their agentic identity and perpetrator groups their moral identity. We review two research trends that emerged from this shift in representation and its relationship to identity needs.
View Article and Find Full Text PDF