Results 61 to 70 of about 45,066 (261)
IEEE AccessIn audio recognition, improving the accuracy and generalizability of Pretrained Audio Neural Networks (PANNs) remains challenging. This study introduces Randomized Area Ratio Patch Masking (RARPM), a novel data augmentation technique that applies random ...
Weichun Wong, Yachun Li, Shihan Li
doaj +1 more source
Audio-Visual Classification of Sports Types [PDF]
2015 IEEE International Conference on Computer Vision Workshop (ICCVW), 2015 In this work we propose a method for classification of sports types from combined audio and visual features extracted from thermal video. From audio Mel Frequency Cepstral Coefficients (MFCC) are extracted, and PCA are applied to reduce the feature space to 10 dimensions.
Rikke Gade +3 more
openaire +1 more source
Advanced Intelligent Discovery, EarlyView.Memristors based on trimethylsulfonium (phenanthroline)tetraiodobismuthate have been utilised as a nonlinear node in a delayed feedback reservoir. This system allowed an efficient classification of acoustic signals, namely differentiation of vocalisation of the brushtail possum (Trichosurus vulpecula).
Ewelina Cechosz +4 more
wiley +1 more source
Spectrogram Classification Using Dissimilarity Space
Applied Sciences, 2020 In this work, we combine a Siamese neural network and different clustering techniques to generate a dissimilarity space that is then used to train an SVM for automated animal audio classification. The animal audio datasets used are (i) birds and (ii) cat
Loris Nanni +3 more
doaj +1 more source
A Study of Few-Shot Audio Classification
CoRR, 2020 Presented at GHC ...
Piper Wolters +3 more
openaire +2 more sources
Large Language Model‐Based Chatbots in Higher Education
Advanced Intelligent Systems, Volume 7, Issue 3, March 2025.The use of large language models (LLMs) in higher education can facilitate personalized learning experiences, advance asynchronized learning, and support instructors, students, and researchers across diverse fields. The development of regulations and guidelines that address ethical and legal issues is essential to ensure safe and responsible adaptation
Defne Yigci +4 more
wiley +1 more source
Comprehensive Context Recognizer Based on Multimodal Sensors in a Smartphone
Sensors, 2012 Recent developments in smartphones have increased the processing capabilities and equipped these devices with a number of built-in multimodal sensors, including accelerometers, gyroscopes, GPS interfaces, Wi-Fi access, and proximity sensors.
Sungyoung Lee +3 more
doaj +1 more source
Advanced Intelligent Systems, EarlyView.This paper introduces a resource‐aware Contrastive Scattering Meta‐Learning (CSML) framework for acoustic anomaly detection. By leveraging training‐free wavelet scattering and metric‐based meta‐learning, the model achieves competitive performance with only 50 K learnable parameters—a 98% reduction compared to state‐of‐the‐art frameworks—enabling ...
Rami Zewail, Bassem Mokhtar
wiley +1 more source
JOIV: International Journal on Informatics VisualizationTraffic accidents often result in fatalities for both drivers and bystanders. Traditionally, accident information relies heavily on community reports, which can delay the provision of victim assistance.
Ahmada Haiz Zakiyil Ilahi +2 more
doaj +1 more source
AI &Innovation, EarlyView.ABSTRACT Generative AI is radically transforming how creative authorship is understood, attributed, and governed across the world’s cultural and creative industries. As AI systems increasingly produce outputs that organisations and audiences recognise as creative, foundational assumptions about who authors creative work, who receives credit for it, and
Ololade A. Shonubi
wiley +1 more source