End-to-end discrete cosine transform integration in spectral convolutional neural networks for resource-efficient deep learning
- 14 January 2026
- journal article
- Published by Elsevier in Applied Soft Computing
- Vol. 191
Abstract
No abstract availableFunding Information
- Universiti Teknologi Malaysia
- University of Toronto Mississauga (10G05)
- University of Toronto Mississauga (10G09)
This publication has 30 references indexed in Scilit:
- Lightweight and high-precision spectral convolutional neural network model for custom 94-class ASCII character recognitionNeural Computing and Applications, 2025
- A lightweight visual mamba network for image recognition under resource-limited environmentsApplied Soft Computing, 2024
- Comparative analysis of machine learning and deep learning models for improved cancer detection: A comprehensive review of recent advancements in diagnostic techniquesExpert Systems with Applications, 2024
- A Lightweight Task-Agreement Meta Learning for Low-Resource Speech RecognitionNeural Processing Letters, 2024
- A frequency-domain approach with learnable filters for image classificationApplied Soft Computing, 2024
- Deploying an energy efficient, secure & high-speed sidechain-based TinyML model for soil quality monitoring and management in agricultureExpert Systems with Applications, 2023
- 2D-wavelet encoded deep CNN for image-based ECG classificationMultimedia Tools and Applications, 2023
- Computation and memory optimized spectral domain convolutional neural network for throughput and energy-efficient inferenceApplied Intelligence, 2022
- An LSTM-based model for the compression of acoustic inventories for corpus-based text-to-speech synthesis systemsComputers and Electrical Engineering, 2022
- Highly-compacted DCT coefficientsSignal, Image and Video Processing, 2009