A CNN-transformer framework for emotion recognition in code-mixed English–Hindi data by Shreya Patankar, Madhura Phadke

“…Unlike previous approaches that rely solely on monolingual models or pre-trained transformers, our method combines local feature extraction via CNNs with global contextual modeling through Transformers specifically designed for code-mixed structures. …”
Get full text

A transformation uncertainty and multi-scale contrastive learning-based semi-supervised segmentation method for oral cavity-derived cancer by Ran Wang, Chengqi Lyu, Lvfeng Yu

“…Multi-scale contrastive learning enhances class similarity and separability while reducing teacher-student model similarity, encouraging diverse feature representations. …”
Get full text

A comprehensive texture segmentation framework for segmentation of capillary non-perfusion regions in fundus fluorescein angiograms. by Yalin Zheng, Man Ting Kwong, Ian J C Maccormick, Nicholas A V Beare, Simon P Harding

“…Capillary non-perfusion (CNP) in the retina is a characteristic feature used in the management of a wide range of retinal diseases. …”
Get full text

Infrared spectrum target recognition and positioning technology based on image segmentation algorithm by Runming He, Yu Wang, Zhenzhong Yan, Xiaoli Lu

“…Compared with other models, the performance is significantly improved. …”
Get full text

Document-level relation extraction via dual attention fusion and dynamic asymmetric loss by Xiaoyao Ding, Dongyan Ding, Gang Zhou, Jicang Lu, Taojie Zhu

“…Experimental results show that our DASL (Dual Attention fusion and dynamic aSymmetric Loss) obtains superior performance on two public datasets, we further provide extensive experiments to analyze how dual attention fusion and dynamic asymmetric loss guide the model for better extracting multi-label relations among entities.…”
Get full text

Research on morphological knowledge-guided low-resource agglutinative languages-Chinese translation by Gulinigeer Abudouwaili, Sirajahmat Ruzmamat, Kahaerjiang Abiderexiti, Tuergen Yibulayin, Nian Yi, Aishan Wumaier

“…Once again, a dual encoder was introduced in the encoding to improve the model’s ability to extract information. We improved the existing information fusion methods during feature fusion to avoid information loss. …”
Get full text

A study of combination of autoencoders and boosted Big-Bang crunch theory architectures for Land-Use classification using remotely sensed imagery by Qiongbing Xiong, Xuecheng Wu, Cizhen Yu, Hasan Hosseinzadeh

“…The methodology involved utilizing the VGG-19 model for feature extraction, dimensionality reduction, and a stacked autoencoder optimized with a boosted version of the Big Bang Crunch Theory. …”
Get full text

Hierarchical in-out fusion for incomplete multimodal brain tumor segmentation by Fang Liu, YanDuo Zhang, Tao Lu, Jiaming Wang, LiWei Wang

“…Existing multimodal fusion models usually perform intra-modal fusion at both shallow and deep layers relying predominantly on traditional attention fusion. …”
Get full text

Multi-scale convolutional transformer network for motor imagery brain-computer interface by Wei Zhao, Baocan Zhang, Haifeng Zhou, Dezhi Wei, Chenxi Huang, Quan Lan

“…The multi-branch multi-scale CNN structure effectively addresses individual variability in EEG signals, enhancing the model’s generalization capabilities, while the Transformer encoder strengthens global feature integration and improves decoding performance. …”
Get full text

Exploring Kernel Machines and Support Vector Machines: Principles, Techniques, and Future Directions by Ke-Lin Du, Bingchun Jiang, Jiabin Lu, Jingyu Hua, M. N. S. Swamy

“…The kernel method is a tool that converts data to a kernel space where operation can be performed. When converted to a high-dimensional feature space by using kernel functions, the data samples are more likely to be linearly separable. …”
Get full text

Directed Knowledge Graph Embedding Using a Hybrid Architecture of Spatial and Spectral GNNs by Guoqiang Hou, Qiwen Yu, Fan Chen, Guang Chen

“…Furthermore, the experimental results indicate that the homophily and degree of correlation of the nodes significantly influence the classification performance of the model. This finding opens significant avenues for future research.…”
Get full text

Near-Surface Air Temperature Estimation Based on an Improved Conditional Generative Adversarial Network by Jiaqi Zheng, Xi Wu, Xiaojie Li, Jing Peng

“…These results indicate the superior performance of the proposed model for near-surface air temperature estimation.…”
Get full text

WAYVision: A hybrid deep learning approach for recognizing handwritten Kannada Braille using wavelet transformation and attention based YOLOv5 by Bipin Nair B J, Niranjan, Saketh P, Shobha Rani N

“…The proposed system demonstrates exceptional performance in feature extraction, classification accuracy, and addressing spatial misalignments in Braille dots. …”
Get full text

Alleviating the medical strain: a triage method via cross-domain text classification by Xiao Xiao, Shuqin Wang, Feng Jiang, Tingyue Qi, Wei Wang

“…Recently, there have already been some efforts to devote deep-learning techniques or pre-trained language models (PLMs) to triage recommendations. However, these methods may suffer two main limitations: (1) These methods typically require a certain amount of labeled or unlabeled data for model training, which are not always accessible and costly to acquire. (2) These methods have not taken into account the distortion of semantic feature structure and the loss of category discriminability in the model training. …”
Get full text

Assessing ML classification algorithms and NLP techniques for depression detection: An experimental case study. by Giuliano Lorenzoni, Cristina Tavares, Nathalia Nascimento, Paulo Alencar, Donald Cowan

“…<h4>Purpose of the study</h4>This paper tackles such an assessment based on a case study that compares different ML classifiers, specifically in terms of data cleaning and pre-processing, feature selection, parameter setting, and model choices.…”
Get full text

Enhancing Security in CPS Industry 5.0 using Lightweight MobileNetV3 with Adaptive Optimization Technique by Mohammed A. Aleisa

“…The method starts with preprocessing the IoT23 dataset, which includes utilizing Gaussian filters to reduce noise, Mean Imputation to handle missing values, and Min-Max normalization to data scaling. The model uses flow-based, time-based, statistical, and deep feature extraction using ResNet-101 for feature extraction. …”
Get full text

Adaptive malware identification via integrated SimCLR and GRU networks by Faisal S. Alsubaei, Abdulwahab Ali Almazroi, Walid Said Atwa, Abdulaleem Ali Almazroi, Nasir Ayub, N. Z. Jhanjhi

“…The framework also incorporates graph neural network (GNN)-based feature selection to reduce redundancy and optimise Fish School Search (FSS) to fine-tune key hyperparameters for improved learning performance. …”
Get full text

Federated Deep Learning for Scalable and Explainable Load Forecasting in Privacy-Conscious Smart Cities by Ibrahim Alzamil

“…Functional modules such as Dynamic Temporal Refinement (DTR) and Multi-Stage Adaptive Feature Selection (MSAFS) enable adaptive temporal modeling and feature prioritization across non-IID client data. …”
Get full text

OTM-HC: Enhanced Skeleton-Based Action Representation via One-to-Many Hierarchical Contrastive Learning by Muhammad Usman, Wenming Cao, Zhao Huang, Jianqi Zhong, Ruiya Ji

“…We tested the OTM-HC framework across four datasets, demonstrating improved performance over state-of-the-art models. Specifically, OTM-HC achieved improvements of 0.9% and 0.6% on NTU60, 0.4% and 0.7% on NTU120, and 0.7% and 0.3% on PKU-MMD I and II, respectively, surpassing previous leading approaches across these datasets. …”
Get full text

Better Pseudo-Labeling for Semi-Supervised Domain Generalization in Medical Magnetic Resonance Image Segmentation by Liangqing Hu, Zuqiang Meng, Chaohong Tan, Yumin Zhou

“…Moreover, due to variations in MRI machines, ensuring the independence and identical distribution between model training data and real-world data is difficult, which may lead to noisy model predictions and weak generalization ability. …”
Get full text