A Review of Developments and Metrology in Machine Learning and Deep Learning for Wearable IoT Devices by Minh Long Hoang

“…The work presents case studies, highlighting AI applications in smart devices, such as stress detection via Heart Rate Variability, personalized exercise guidance, muscular activity monitoring, and real-time image recognition. …”
Get full text

CMHFE-DAN: A Transformer-Based Feature Extractor with Domain Adaptation for EEG-Based Emotion Recognition by Manal Hilali, Abdellah Ezzati, Said Ben Alla

“…The architecture tackles key challenges in EEG emotion recognition, including generalisability, inter-subject variability, and temporal dynamics modelling. The results highlight the effectiveness of combining convolutional feature learning with adversarial domain adaptation for robust EEG-ER.…”
Get full text

From Image to Sequence: Exploring Vision Transformers for Optical Coherence Tomography Classification by Amirali Arbab, Aref Habibi, Hossein Rabbani, Mahnoosh Tajmirriahi

“…Current methods for OCT image classification encounter specific challenges, such as the inherent complexity of retinal structures and considerable variability across different OCT datasets. Methods: This paper introduces a novel hybrid model that integrates the strengths of convolutional neural networks (CNNs) and vision transformer (ViT) to overcome these obstacles. …”
Get full text

SVM-enhanced attention mechanisms for motor imagery EEG classification in brain-computer interfaces by Zhenis Otarbay, Zhenis Otarbay, Abzal Kyzyrkanov

“…Motor imagery (MI)-based BCIs, utilizing non-invasive electroencephalography (EEG), face challenges due to high signal variability, noise, and class overlap. Deep learning architectures, such as CNNs and LSTMs, have improved EEG classification but still struggle to fully capture discriminative features for overlapping motor imagery classes. …”
Get full text

Automated high precision PCOS detection through a segment anything model on super resolution ultrasound ovary images by S. Reka, T. Suriya Praba, Mukesh Prasanna, Vanipenta Naga Nithin Reddy, Rengarajan Amirtharajan

“…Nevertheless, manual ultrasound image analysis is often challenging and time-consuming, resulting in inter-observer variability. To effectively treat PCOS and prevent its long-term effects, prompt and accurate diagnosis is crucial. …”
Get full text

Multi-Branch CNN-LSTM Fusion Network-Driven System With BERT Semantic Evaluator for Radiology Reporting in Emergency Head CTs by Selene Tomassini, Damiano Duranti, Abdallah Zeggada, Carlo Cosimo Quattrocchi, Farid Melgani, Paolo Giorgini

Get full text

Dataset Dependency in CNN-Based Copy-Move Forgery Detection: A Multi-Dataset Comparative Analysis by Potito Valle Dell’Olmo, Oleksandr Kuznetsov, Emanuele Frontoni, Marco Arnesano, Christian Napoli, Cristian Randieri

“…Our experimental analysis highlighted a significant variability of the results, with an accuracy ranging from 95.90% on CoMoFoD to 27.50% on Coverage. …”
Get full text

A hybrid deep learning-based approach for optimal genotype by environment selection by Zahra Khalilzadeh, Motahareh Kashanian, Saeed Khaki, Lizhi Wang

“…The ability to accurately predict the yields of different crop genotypes in response to weather variability is crucial for developing climate resilient crop cultivars. …”
Get full text

Bearing Fault Diagnosis Method Based on Improved VMD and Parallel Hybrid Neural Network by Wuyi Chen, Huafeng Cai, Qiu Sun

Get full text

Advanced Brain Tumor Segmentation With a Multiscale CNN and Conditional Random Fields by Ala Guennich, Mohamed Othmani, Hela Ltifi

“…In this study, we present a novel 9-layer multiscale architecture designed specifically for the semantic segmentation of 3D medical images, with a particular focus on brain tumor images, using convolutional neural networks. Our innovative solution incorporates several significant enhancements, including the use of variable-sized filters between layers and the early incorporation of residual connections from the very first layer. …”
Get full text

Prediction of Carbonate Reservoir Porosity Based on CNN-BiLSTM-Transformer by Yingqiang Qi, Shuiliang Luo, Song Tang, Jifu Ruan, Da Gao, Qianqian Liu, Sheng Li

“…This model is applied to the Moxi gas field in the Sichuan Basin, using conventional logging curves as input feature variables for porosity prediction. Root mean square error (RMSE), mean absolute error (MAE), and the coefficient of determination (R²) are used as evaluation metrics for comprehensive analysis and comparison. …”
Get full text

Central Pixel-Based Dual-Branch Network for Hyperspectral Image Classification by Dandan Ma, Shijie Xu, Zhiyu Jiang, Yuan Yuan

“…Recent deep learning (DL) methods combining Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) have demonstrated exceptional performance. …”
Get full text

gamUnet: designing global attention-based CNN architectures for enhanced oral cancer detection and segmentation by Jinyang Zhang, Hongxin Ding, Hongxin Ding, Runchuan Zhu, Weibin Liao, Weibin Liao, Junfeng Zhao, Junfeng Zhao, Min Gao, Xiaoyun Zhang

“…Conventional diagnosis relies on manual evaluation of hematoxylin and eosin (H&E)-stained slides, a time-consuming process requiring specialized expertise and prone to variability. While deep learning methods, especially convolutional neural networks (CNNs), have advanced automated analysis of histopathological images for cancerous tissues in various body parts, OSCC presents unique challenges. …”
Get full text

Enhanced Pollen Classification via Hybrid Neural Network With Attention Mechanism and View Separation: An Equatorial and Polar Approach by Julio Cesar da Silva Soares, Kelson Romulo Teixeira Aires, Juliana do Nascimento Bendini, Wesley Vitor Barbosa Brandao, Rodrigo de Melo Souza Veras

Get full text

A hybrid compound scaling hypergraph neural network for robust cervical cancer subtype classification using whole slide cytology images by Pooja Govindaraj, Sasikaladevi Natarajan, Pradeepa Sampath, Akilesh Thimma Suresh, Rengarajan Amirtharajan

“…Manual cytological examination is time-consuming, error-prone and subject to inter-observer variability. Automated and robust classification of the whole slide cytology images for cervical cancer is essential for detecting precancerous and malignant lesions. …”
Get full text

Computational methods and technical means of processing signals of side electromagnetic emanation by Danil A. Shinyaev, Leonid N. Kessarinskiy, Egor A. Simakhin

“…In future studies, it is planned to train the model on an updated dataset with other neural network analogues in order to optimize the process of predicting variables in the regression model.…”
Get full text

Suppression strategies for pyrolysis gas parameter fluctuations in small pyrolysis-combustion coupled reactors for MSW by Shuhui Wang, Jianxiong Zhang, Jun Fu, Lin Wang, Zhifeng He, Zheng Yan

Get full text

Review of Synthetic Aperture Radar Automatic Target Recognition: A Dual Perspective on Classical and Deep Learning Techniques by Jakub Slesinski, Damian Wierzbicki

“…What makes SAR imagery particularly unique are problems, such as speckle noise, target variability, and clutter, for which there are specialized solutions described in this article. …”
Get full text

Enhancing skin lesion classification: a CNN approach with human baseline comparison by Deep Ajabani, Zaffar Ahmed Shaikh, Amr Yousef, Karar Ali, Marwan A. Albahar

“…This approach offers a scalable, resource-efficient solution to address variability in medical image analysis, effectively harnessing the complementary strengths of expert humans and CNNs.…”
Get full text

Artificial intelligence in acoustic ecology: Soundscape classification in the Cerrado by Bruno Daleffi da Silva, Linilson Rodrigues Padovese

“…Five statistical models were developed and evaluated, utilizing both traditional Machine Learning and Deep Learning, with Mel Frequency Cepstral Coefficients (MFCCs) and spectrogram images as input variables. The performance comparison of these models revealed the superiority of the Convolutional Neural Network (CNN), which, although requiring higher computational costs and training time, provided high accuracy in classifications and valuable insights through the application of the LIME explainability technique. …”
Get full text