IncSAR: A Dual Fusion Incremental Learning Framework for SAR Target Recognition by George Karantaidis, Athanasios Pantsios, Ioannis Kompatsiaris, Symeon Papadopoulos

“…IncSAR combines the power of a Vision Transformer (ViT) and a custom-designed Convolutional Neural Network (CNN) in a dual-branch architecture, integrated via a late-fusion strategy. …”
Get full text

Intrusion detection in metaverse environment internet of things systems by metaheuristics tuned two level framework by Milos Antonijevic, Miodrag Zivkovic, Milica Djuric Jovicic, Bosko Nikolic, Jasmina Perisic, Marina Milovanovic, Luka Jovanovic, Mahmoud Abdel-Salam, Nebojsa Bacanin

“…This study revolves around hybrid framework that combines convolutional neural networks (CNN) and machine learning (ML) classifying models, like categorical boosting (CatBoost) and light gradient-boosting machine (LightGBM), further optimized through metaheuristics optimizers for leveraged performance. …”
Get full text

Image Quality Assessment Based on Multi-Scale Representation and Shifting Transformer by Geng Fu, Ziyu Wang, Cuijuan Zhang, Zerong Qi, Mingzheng Hu, Shujun Fu, Yunfeng Zhang

“…Recently, transformer-based algorithms have excelled in computer vision, particularly in image classification, surpassing convolutional neural network (CNN) methods. To enhance IQA using transformers, we propose Swin-MIQT, a multi-scale spatial pooling transformer with shifted windows. …”
Get full text

End-to-end neural automatic speech recognition system for low resource languages by Sami Dhahbi, Nasir Saleem, Sami Bourouis, Mouhebeddine Berrima, Elena Verdú

“…An on-the-fly data augmentation method is applied to these mel-spectrograms, treating them as images from which features are extracted to train a convolutional neural network (CNN) and a bidirectional long short-term memory (BLSTM)-based ASR. …”
Get full text

A Novel Ensemble Classifier Selection Method for Software Defect Prediction by Xin Dong, Jie Wang, Yan Liang

“…The experimental results demonstrate that the DFD ensemble learning-based software defect prediction model outperforms the ten other models, including five common machine learning (ML) classification algorithms (logistic regression (LR), naïve Bayes (NB), K-nearest neighbor (KNN), decision tree (DT), and support vector machine (SVM)), two deep learning (DL) algorithms (multi-layer perceptron (MLP) and convolutional neural network (CNN)), and three ensemble learning algorithms (random forest (RF), extreme gradient boosting (XGB), and stacking). …”
Get full text

Segment anything model for few-shot medical image segmentation with domain tuning by Weili Shi, Penglong Zhang, Yuqin Li, Zhengang Jiang

“…Remarkably, with few training samples, our method consistently outperforms various based on SAM and CNN.…”
Get full text

Ad Click Fraud Detection Using Machine Learning and Deep Learning Algorithms by Reem A. Alzahrani, Malak Aljabri, Rami A. Mustafa Mohammad

“…In parallel, deep learning (DL) models, including Convolutional Neural Network (CNN), Deep Neural Network (DNN), and Recurrent Neural Network (RNN), showcased strong performance. …”
Get full text

Automated Breast Cancer Detection in Mammograms using Transfer Learningbased Deep Learning Models by Preeti Katiyar, Krishna Singh

“…An intricately designed fully connected classifier complements pretrained Convolutional Neural Network (CNN) architectures like ResNet50 and VGG16 in the proposed model. …”
Get full text

A multi-scale rotated ship targets detection network for remote sensing images in complex scenarios by Siyu Li, Fei Yan, Yunqing Liu, Yuzhuo Shen, Lan Liu, Ke Wang

“…To address these issues, this paper proposes a Multi-Scale Rotated Detection Network (MSRO-Net) for detecting rotated ship targets in remote sensing images. The network adopts a CNN-Transformer hybrid architecture for collaborative feature extraction and integrates our proposed Coordinate-Aware Pyramid Feature Aggregation module (CAPP). …”
Get full text

A group scheduling algorithm for massive heterogeneous data in the “dual carbon” digital intelligence monitoring center considering time-varying characteristics and priorities by Wenni Kang, Dongge Zhu, Shuang Zhang, Jia Liu, Rui Ma

“…The functional data analysis (FDA) method is used to convert the massive multi-source heterogeneous data of the “double carbon” digital intelligence monitoring center into continuous functions to solve the problem of frequency inconsistency and unify the data format; through the CNN–LSTM based on the Attention mechanism. The model extracts time-varying features from the data that eliminates heterogeneous characteristics, and implements data grouping in the “dual carbon” digital intelligence monitoring center; by setting differentiated priorities for different groups of data, it combines the data scheduling demand estimation model and delayed response time (RTT) factor and congestion factor, calculate the data priority-oriented data scheduling link similarity (DPLS), allocate the data to be scheduled to the scheduling link with the highest DPLS value for transmission, and realize the “double carbon” digital intelligence monitoring center data group scheduling. …”
Get full text

Multi task opinion enhanced hybrid BERT model for mental health analysis by Md. Mithun Hossain, Md. Shakil Hossain, M. F. Mridha, Mejdl Safran, Sultan Alfarhood

“…Using a hybrid architecture, these embeddings are integrated with the contextual embeddings of BERT, whereby the CNN and BiGRU layers collected local and sequential characteristics. …”
Get full text

THE USE OF ARTIFICIAL INTELLIGENCE ON COLPOSCOPY IMAGES AND SEGMENTAL VOLUMES, CONSTRUCTED FROM MRI AND CT IMAGES, IN THE DIAGNOSIS AND STAGING OF PRECANCERS, CERVICAL CANCERS AND... by Hlescu Cristian Stefan, Tudor Florin Ursuleanu, Roxana Grigorovici, Andreea Roxana Luca, Ramona Elena Teiu, Maria Paula Comanescu, Alina Ionela Calin, Alexandru Grigorovici

“…Materials and methods The optimization of the method will involve the development and training of artificial intelligence models using convolutive neural networks (CNN) to identify precancers and cancers in colposcopic images. …”
Get full text

Fault Diagnosis of Magnetically Controlled On-Column Circuit Breaker Based on Small Sample Condition by He Tian, Chao Liang, Wenpeng Ma, Tianchang Zhang

“…Compared to the VAE-GAN-CNN network, this network shows a 3.6% increase in accuracy.…”
Get full text

A Multistage Detection Framework Based on TFA and Multiframe Correlation for HFSWR by Zongtai Li, Gangsheng Li, Ling Zhang, Lanjun Liu, Q. M. Jonathan Wu

“…In this article, TFA, multiframe correlation, and deep neural networks are integrated to develop a three-stage detection framework. First, faster R-CNN is customized for the preprocessing stage to identify sea clutter regions. …”
Get full text

Integrating Pull Request Comment Analysis and Developer Profiles for Expertise-Based Recommendations in Global Software Development by Sara Zamir, Abdul Rehman, Hufsa Mohsin, Elif Zamir, Assad Abbas, Fuad A. M. Al-Yarimi

“…Impressively, the proposed model significantly outperformed all other text-based classifiers TextCNN, TextRCNN, and Bilstm in this study, showing an accuracy of 91.85%. …”
Get full text

Classification of white blood cells (leucocytes) from blood smear imagery using machine and deep learning models: A global scoping review. by Rabia Asghar, Sanjay Kumar, Arslan Shaukat, Paul Hynds

“…While WBC classification was originally rooted in conventional ML, there has been a notable shift toward the use of DL, and particularly convolutional neural networks (CNN), with 54.4% of identified studies (n = 74) including the use of CNNs, and particularly in concurrence with larger datasets and bespoke features e.g., parallel data pre-processing, feature selection, and extraction. …”
Get full text

AirStrum: A virtual guitar using real-time hand gesture recognition and strumming technique by Beulah ARUL, Shashank PANDA, Tushar NAIR

“…Subsequently, a model based on a Convolutional Neural Network (CNN) is trained and validated using the employed dataset to adeptly recognize and classify guitar chords. …”
Get full text

Archaeological Site Detection: Latest Results from a Deep Learning Based Europe Wide Hillfort Search by Jürgen Landauer, Simon Maddison, Giacomo Fontana, Axel G. Posluschny

“…The methodology utilized the Atlas of Hillforts of Britain and Ireland to train a CNN on LiDAR datasets and tested the model’s transferability to Germany and Italy. …”
Get full text

Advanced Defect Detection on Curved Aeronautical Surfaces Through Infrared Imaging and Deep Learning by Leith Bounenni, Mohamed Arbane, Clemente Ibarra-Castanedo, Yacine Yaddaden, Sreedhar Unnikrishnakurup, Andrew Ngo Chun Yong, Xavier Maldague

“…We achieve a more comprehensive and precise assessment of defects by integrating deep learning with infrared imaging based on the U-net model for segmentation and the CNN model for classification. The proposed model was rigorously tested on both a simulation dataset and an experimental dataset, demonstrating its robustness and effectiveness in accurately identifying and assessing defects on aerospace surfaces. …”
Get full text

Spatial transcriptome reveals histology-correlated immune signature learnt by deep learning attention mechanism on H&E-stained images for ovarian cancer prognosis by Chun Wai Ng, Kwong-Kwok Wong, Barrett C. Lawson, Sammy Ferri-Borgogno, Samuel C. Mok

“…Methods In this study, 773 WSIs of H&E-stained tumor sections from 335 patients with treatment naïve high-grade serous ovarian cancer who were included in The Cancer Genome Atlas (TCGA) Pan-Cancer study were used to train, and validate, and to test a ResNet101 CNN model modified with attention mechanism. WSIs from patients in an independent cohort were used to further evaluate the model. …”
Get full text