Preserving specificity in federated graph learning for fMRI-based neurological disorder identification DOI
Junhao Zhang, Qianqian Wang, Xiaochuan Wang

et al.

Neural Networks, Journal Year: 2023, Volume and Issue: 169, P. 584 - 596

Published: Nov. 7, 2023

Language: Английский

CVANet: Cascaded visual attention network for single image super-resolution DOI
Weidong Zhang, Wenyi Zhao, Jia Li

et al.

Neural Networks, Journal Year: 2023, Volume and Issue: 170, P. 622 - 634

Published: Nov. 24, 2023

Language: Английский

Citations

72
Deep learning-based encryption for secure transmission digital images: A survey DOI

Soniya Rohhila,

Amit Kumar Singh

Computers & Electrical Engineering, Journal Year: 2024, Volume and Issue: 116, P. 109236 - 109236

Published: April 8, 2024

Language: Английский

Citations

9
An automatic classification framework for identifying type of plant leaf diseases using multi-scale feature fusion-based adaptive deep network DOI

Bathula Nagachandrika,

R. Prasath,

Praveen Joe I R

et al.

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 95, P. 106316 - 106316

Published: April 26, 2024

Language: Английский

Citations

8
Machine learning-assisted development of gas separation membranes: A review DOI Creative Commons

An Li,

Jianchun Chu, Shaoxuan Huang

et al.

Carbon Capture Science & Technology, Journal Year: 2025, Volume and Issue: 14, P. 100374 - 100374

Published: Jan. 30, 2025

Language: Английский

Citations

1
A patch distribution-based active learning method for multiple instance Alzheimer's disease diagnosis DOI
Tianxiang Wang, Qun Dai

Pattern Recognition, Journal Year: 2024, Volume and Issue: 150, P. 110341 - 110341

Published: Feb. 14, 2024

Language: Английский

Citations

6
DAX-Net: A dual-branch dual-task adaptive cross-weight feature fusion network for robust multi-class cancer classification in pathology images DOI Creative Commons
Doanh C. Bui, Boram Song, Kyungeun Kim

et al.

Computer Methods and Programs in Biomedicine, Journal Year: 2024, Volume and Issue: 248, P. 108112 - 108112

Published: March 7, 2024

Multi-class cancer classification has been extensively studied in digital and computational pathology due to its importance clinical decision-making. Numerous tools have proposed for various types of classification. Many them are built based on convolutional neural networks. Recently, Transformer-style networks shown be effective Herein, we present a hybrid design that leverages both transformer architecture obtain superior performance

Language: Английский

Citations

6
Elevating Mobile Robotics: Pioneering Applications of Artificial Intelligence and Machine Learning DOI Creative Commons

Haider Sahib Nasrallah,

Ivan V. Stepanyan,

Karrar Sahib Nassrullah

et al.

Revue d intelligence artificielle, Journal Year: 2024, Volume and Issue: 38(1), P. 351 - 363

Published: Feb. 29, 2024

The present study delves into the utilization of subsumption architecture for modeling mobile robot behaviors, particularly those that respond adaptively to environmental dynamics and inaccuracies in sensor measurements.Central this investigation is deployment reactive controller networks, wherein each node-representing a distinct state-is governed by sensor-triggered conditions dictate state transitions.The methodology adopted comprises thorough literature review, encompassing sources from IEEE Xplore, ScienceDirect, ACM Digital Library, which discuss integration realm control.Through effectiveness crafting robotic behaviors underscored.It has been established augmented finite machines (AFSMs), are integral possess internal timing mechanisms, pivotal managing temporal aspects transitions.Additionally, technique layering-merging multiple simple networks form intricate behavior patterns-emerges as significant finding, accentuating architecture's capability facilitate complex behavioral constructs.The prime contribution body work lies identifying elucidating strategic role enhancing adaptability robustness robots.The insights gleaned not only advance our understanding control systems but also hold implications amplification industrial efficiency through application sophisticated AI machine learning techniques robotics.

Language: Английский

Citations

5
Three novel cost-sensitive machine learning models for urban growth modelling DOI Creative Commons
Mohammad Ahmadlou, Mohammad Karimi,

Saad Sh. Sammen

et al.

Geocarto International, Journal Year: 2024, Volume and Issue: 39(1)

Published: Jan. 1, 2024

This article addresses the class imbalance problem in urban gain modelling (UGM) of Tabriz and Isfahan megacities Iran by proposing novel cost-sensitive machine learning models, namely support vector (CSVM), random forest (CRF) artificial neural network (CANN). Random sampling, a frequently utilized method, fails to effectively tackle this issue biasing models towards no change samples, which outnumber samples. The results showed that CRF exhibited highest accuracy (AUC = 0.560), followed CANN 0.557) CSVM 0.448) Isfahan. In Tabriz, 0.809) 0.818) excelled, outperforming balanced sampling constructed with ANN, RF SVM AUROC ANN boosted 15% 2% validation. By emphasizing significance addressing appropriately, research highlights improvement outcomes achievable through especially case.

Language: Английский

Citations

4
DIFLF: A domain-invariant features learning framework for single-source domain generalization in mammogram classification DOI
Wanfang Xie, Zhenyu Liu,

Litao Zhao

et al.

Computer Methods and Programs in Biomedicine, Journal Year: 2025, Volume and Issue: 261, P. 108592 - 108592

Published: Jan. 6, 2025

Language: Английский

Citations

0
Weakly-supervised thyroid ultrasound segmentation: Leveraging multi-scale consistency, contextual features, and bounding box supervision for accurate target delineation DOI
Mohammed Aly

Computers in Biology and Medicine, Journal Year: 2025, Volume and Issue: 186, P. 109669 - 109669

Published: Jan. 13, 2025

Language: Английский

Citations

0