Results 71 to 80 of about 1,688 (176)

Comparative Evaluation of Deep Learning Architectures for Printed and Handwritten Farsi OCR [PDF]

Journal of Artificial Intelligence and Data Mining
Farsi optical character recognition remains challenging due to the script’s cursive structure, positional glyph variations, and frequent diacritics. This study conducts a comparative evaluation of five foundational deep learning architectures widely used
Fatemeh Asadi-Zeydabadi, Ali Afkari-Fahandari, Elham Shabaninia, Hossein Nezamabadi-pour   +3 more
doaj   +1 more source

Effective Variable‐Speed Bearing Fault Diagnosis From Motor Current Signals Using Kurtosis‐Guided VMD and Multi‐Branch Convolutional Neural Network

IET Control Theory &Applications, Volume 20, Issue 1, January/December 2026.
This study presents a novel deep learning‐based fault classification framework utilising Variational Mode Decomposition (VMD) for adaptive feature extraction and a Multi‐branch Convolutional Neural Network (M1D‐CNN) architecture for classification. The VMD hyperparameters were optimised based on kurtosis to ensure the extraction of the most informative
Seyyid Ahmed Djellouli, Mounir Djeddi, Aissa Kheldoun, Nima Khosravi, Adel Oubelaid   +4 more
wiley   +1 more source

Hybrid Deep Learning Frameworks for License Plate Recognition in Complex Environments: A Comprehensive Survey and Research Outlook

IET Computer Vision, Volume 20, Issue 1, January/December 2026.
This survey systematically reviews state‐of‐the‐art license plate recognition methods, with a focus on hybrid CNN‐transformer frameworks and the joint optimisation of detection and recognition for real‐world deployment. It further analyses existing datasets, highlights persistent challenges, such as domain generalisation, and outlines pathways towards ...
SanXing Deng, Ewe Lay Sheng, Tiong Sieh Kiong, MengMeng Yang   +3 more
wiley   +1 more source

On the Accuracy of CRNNs for Line-Based OCR: A Multi-Parameter Evaluation

CoRR, 2020
We investigate how to train a high quality optical character recognition (OCR) model for difficult historical typefaces on degraded paper. Through extensive grid searches, we obtain a neural network architecture and a set of optimal data augmentation settings.
Bernhard Liebl, Manuel Burghardt
openaire   +2 more sources

Comprehensive Study of DC Microgrids Protection: Challenges, Cutting‐Edge Techniques, Machine‐Learning‐Driven Solutions

IET Renewable Power Generation, Volume 20, Issue 1, January/December 2026.
ABSTRACT This paper provides a comprehensive examination of the evolving protection challenges within DC microgrids powered by renewable resources and energy storage systems. It begins by delineating the methodological framework of conventional protection, critically assessing schemes based on current, voltage, and impedance to expose their limitations
Mohamed Elmadawy, Ahmed Shahin, Abdelhady Ghanem, Almoataz Y. Abdelaziz, Fujin Deng, Ahmad S. Ayub, Abdalbaset Mnider, Sayed Abulanwar   +7 more
wiley   +1 more source

A Hybrid Dynamic Sand Cat Swarm Optimisation (HD‐SCSO) Approach for Resource Allocation in Wireless Sensor Networks

IET Wireless Sensor Systems, Volume 16, Issue 1, January/December 2026.
The hybrid dynamic sand cat swarm optimisation (HD‐SCSO) approach introduces a bioinspired method to enhance energy efficiency, data transmission and resource fairness in WSNs. Through adaptive clustering, intelligent node selection and real‐time adjustments, HD‐SCSO ensures optimised performance, extended network lifetime and seamless IoT integration,
Samer Sindian, Ziad Osman, Abdallah AL‐Sabbagh   +2 more
wiley   +1 more source

High-Resolution Land-Cover Mapping Based on a Cross-Resolution Deep Learning Framework and Available Low-Resolution Labels

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
High-resolution land cover mapping (LCM) is pivotal in numerous disciplines but still challenging to be acquired because traditional supervised methods require a substantial number of high-resolution labels that is labouring and expensive. To this issue,
Xiaoman Qi, Junhuan Peng, Yuebin Wang, Xiaotong Qi, Yun Peng   +4 more
doaj   +1 more source

Digging Deeper into CRNN Model in Chinese Text Images Recognition

CoRR, 2020
16 pages, 10 ...
Kunhong Yu, Yuze Zhang
openaire   +2 more sources

Towards cross-modal pre-training and learning tempo-spatial characteristics for audio recognition with convolutional and recurrent neural networks

EURASIP Journal on Audio, Speech, and Music Processing, 2020
In this paper, we investigate the performance of two deep learning paradigms for the audio-based tasks of acoustic scene, environmental sound and domestic activity classification.
Shahin Amiriparian, Maurice Gerczuk, Sandra Ottl, Lukas Stappen, Alice Baird, Lukas Koebe, Björn Schuller   +6 more
doaj   +1 more source

Multichannel source counting with CRNN : analysis of the performance

, 2020
In this work we focus on the problem of estimating the number of concurrent speaker in an audio recording. This information is often a prerequisite in several audio processing tasks such as speaker separation, localization and tracking. In a previous work, we proposed to tackle this problem by using a convolutional recuurrent neural network (CRNN) with
Grumiaux, Pierre-Amaury, Kitic, Srdan, Girin, Laurent, Guérin, Alexandre   +3 more
openaire   +2 more sources