LSTM autoencoder based parallel architecture for deepfake audio detection with dynamic residual encoding and feature fusion by Priyanka Muruganandham, Govardhana Rajan Thangasamy, Sangeetha Jayaraman, Rekha Dharmarajan

“…This study aims to enhance detection performance by addressing limitations in existing models, such as temporal inconsistencies, weak contextual representation, and reconstruction loss. …”
Get full text

Community evolution prediction based on feature change patterns in social networks by Jingyi Ding, Guojing Sun, Tiwen Wang, Licheng Jiao, Junzhao Du, Jianshe Wu, Hongfei Wang, Ruohui Cheng

Get full text

Prediction of rolling bearing performance degradation based on whale optimization algorithm and backpropagation model by Jingyue Wang, Yuntong Han, Haotian Wang, Jianming Ding, Cai Yi

“…Feature data is selected using the correlation coefficient theory to obtain the model inputs. …”
Get full text

Medium-sized protein language models perform well at transfer learning on realistic datasets by Luiz C. Vieira, Morgan L. Handojo, Claus O. Wilke

“…We systematically evaluated the performance of various ESM-style models across multiple biological datasets to assess the impact of model size on transfer learning via feature extraction. …”
Get full text

Predicting congenital syphilis cases: A performance evaluation of different machine learning models. by Igor Vitor Teixeira, Morgana Thalita da Silva Leite, Flávio Leandro de Morais Melo, Élisson da Silva Rocha, Sara Sadok, Ana Sofia Pessoa da Costa Carrarine, Marília Santana, Cristina Pinheiro Rodrigues, Ana Maria de Lima Oliveira, Keduly Vieira Gadelha, Cleber Matos de Morais, Judith Kelner, Patricia Takako Endo

“…Based on a rigorous methodology, we propose six experiments using three feature selection techniques to select the most relevant attributes, pre-process and clean the data, apply hyperparameter optimization to tune the machine learning models, and train and test models to have a fair evaluation and discussion.…”
Get full text

Using Machine Learning and Analytical Modeling to Predict Poly-Crystalline PV Performance in Jordan by Sinan S. Faouri, Salah Abdallah, Dana Helmi Salameh

“…This study investigates the performance prediction of poly-crystalline photovoltaic (PV) systems in Jordan using experimental data, analytical models, and machine learning approaches. …”
Get full text

Advancing blood cell detection and classification: performance evaluation of modern deep learning models by Shilpa Choudhary, Sandeep Kumar, Pammi Sri Siddhaarth, Guntu Charitasri, Monali Gulhane, Nitin Rakesh, Feslin Anish Mon, Amal Al-Rasheed, Masresha Getahun, Ben Othman Soufiene

“…In terms of real-time performance, YOLOv10 outperforms other object detection models with better detection rates and classification accuracy. …”
Get full text

Model-Based Feature Extraction and Classification for Parkinson Disease Screening Using Gait Analysis: Development and Validation Study by Ming De Lim, Tee Connie, Michael Kah Ong Goh, Nor ‘Izzati Saedon

“…The model-based features proved effective in differentiating between normal and PD-affected gait, demonstrating the potential of this approach in early detection. …”
Get full text

A Recognition Model Based on Multiscale Feature Fusion for Needle-Shaped <i>Bidens</i> L. Seeds by Zizhao Zhang, Yiqi Huang, Ying Chen, Ze Liu, Bo Liu, Conghui Liu, Cong Huang, Wanqiang Qian, Shuo Zhang, Xi Qiao

“…., in agricultural production, this paper proposes a model construction idea that combines the advantages of deep residual models in extracting high-level abstract features with multiscale feature extraction fusion, taking into account the depth and width of the network. …”
Get full text

A novel feature fusion model to mimic photographers’ active observation for scenery recomposition toward physical education by Dongyang Tang, Shang Wang

“…We introduce a strategy called Locality-preserved and Observer-like Active Learning (LOAL) that constructs gaze shift paths (GSP) incrementally, allowing user interaction in the feature selection process. The GSPs are processed through a multi-layer aggregating algorithm, producing deep feature representations encoded into a Gaussian mixture model (GMM), which underpins our image retargeting approach. …”
Get full text

Data augmentation using a 1D-CNN model with MFCC/MFMC features for speech emotion recognition by Thomas Mary Little Flower, Thirasama Jaya, Sreedharan Christopher Ezhil Singh

“…The data augmentation with the 1D-CNN (MFMC) model performed best, with an average accuracy of 99.2% for AESDD, 99.5% for CAFE, 97.5% for EmoDB, 92.4% for IEMOCAP and 96.9% for the MESD database. …”
Get full text

Reproducing morphological features of intervertebral disc using finite element modeling to predict the course of cervical spine dorsopathy by Evgeny V. Yakovlev, Artur L. Ovsepyan, Alexander A. Smirnov, Anna A. Safronova, Dmitry A. Starchik, Sergey A. Zhivolupov, Dmitry E. Mokhov, Ekaterina S. Mokhova, Yuriy L. Vasil’ev, Sergey S. Dydykin

“…Intervertebral disc models were developed in two configurations. For each model, we performed a finite element investigation of the stress-strain state with the same loading conditions. …”
Get full text

Features of the inducible nitric oxide synthase expression in paraventricular and supraoptic nuclei of hypothalamus in different models of arterial hypertension by Yu. M. Kolesnyk, N. V. Kuzo, O. V. Hancheva, A. V. Abramov

“…Our purpose was to find out the features of the inducible nitric oxide synthase (iNOS) expression in magnocellular SON and PVN in SHR and endocrine-saline model of hypertension in rats. …”
Get full text

Early PCOS Detection: A Comparative Analysis of Traditional and Ensemble Machine Learning Models With Advanced Feature Selection by Khandaker Mohammad Mohi Uddin, Md. Tofael Ahmed Bhuiyan, Md. Mahbubur Rahman, Md. Manowarul Islam, Md Ashraf Uddin

“…These methods helped us pinpoint the most predictive attributes, which improved the interpretability and efficiency of our models. Hyperparameter tuning was carefully performed through grid search and cross‐validation, ensuring that each model was optimized for the best prediction accuracy. …”
Get full text

The relative importance of model type and input features for water supply forecasting in snow-dominated basins of the southwestern US by Madeline R. Pernat, Joseph Kasprzyk, Edith Zagona, Sydney D. Walker, Ben Livneh

“…Results show that the most important features vary by both basin and model type, and that model types perform similarly when each is trained on its respective Best Feature Set. …”
Get full text

Construction of a feature gene and machine prediction model for inflammatory bowel disease based on multichip joint analysis by Yan Chaosheng, Sun Haowen, Rao Jingjing, Dai Yuanyuan, Duan Wenhui, Sheng Yingyue, Xue Yuzheng

“…On the basis of methods such as artificial neural networks (ANNs), machine learning techniques, and the SHAP model, we developed a diagnostic model for IBD. To select genetic features, we utilized three machine learning algorithms, namely, least absolute shrinkage and selection operator (LASSO), support vector machine (SVM), and random forest (RF), to identify differentially expressed genes. …”
Get full text

SAVL: Scene-Adaptive UAV Visual Localization Using Sparse Feature Extraction and Incremental Descriptor Mapping by Ganchao Liu, Zhengxi Li, Qiang Gao, Yuan Yuan

“…Firstly, to tackle the challenge of inaccurate localization resulting from sparse terrain features, this work proposes a novel feature extraction network grounded in a general visual model, leveraging the robust zero-shot generalization capability of the pre-trained model and extracting sparse features from UAV and satellite imagery. …”
Get full text

Toward Efficient UAV-Based Small Object Detection: A Lightweight Network with Enhanced Feature Fusion by Xingyu Di, Kangning Cui, Rui-Feng Wang

“…Secondly, a new SPPL module is proposed, which combines spatial pyramid pooling rapid fusion (SPPF) with long-distance dependency modeling (LSKA) to improve the robustness of the model to multi-scale targets through cross-level feature association. …”
Get full text

High-Performance stacking ensemble learning for thermoelectric figure-of-merit prediction by Yuelin Wang, Chengquan Zhong, Jingzi Zhang, Honghao Yao, Junjie Chen, Xi Lin

“…By combining five regression models through stacking ensemble learning and introducing 100 coordination number features alongside conventional features, our model achieves a coefficient of determination (R2) value of 0.970. …”
Get full text

FeTT: Class-Incremental Learning with Feature Transformation Tuning by Sunyuan Qiang, Yanyan Liang

“…Then, we propose the feature transformation tuning (FeTT) model, which concurrently alleviates the inadequacy of previous PTM-based CIL in terms of stability and plasticity. …”
Get full text