Rough Set Theory and Soft Computing Methods for Building Explainable and Interpretable AI/ML Models by Sami Naouali, Oussama El Othmani

“…This study introduces a novel framework leveraging Rough Set Theory (RST)-based feature selection—MLReduct, MLSpecialReduct, and MLFuzzyRoughSet—to enhance machine learning performance on uncertain data. …”
Get full text

Seismic Shear Strength Prediction of Reinforced Concrete Shear Walls by Stacking Multiple Machine Learning Models by Siming Tian, Xiangyong Ni, Yang Wang

“…To this end, a shear capacity test database containing 583 RCSW specimens was first established and characterized, and then the database was employed to train single, ensemble, and deep learning models for the shear strength of shear walls and combined with hyper-parameter tuning to enhance each model’s prediction performance, after which the prediction performance of each model was compared. …”
Get full text

Leveraging LLMs for optimised feature selection and embedding in structured data: A case study on graduate employment classification by Radiah Haque, Hui-Ngo Goh, Choo-Yee Ting, Albert Quek, M.D. Rakibul Hasan

“…The baseline model (without feature selection and embedding) achieved the highest accuracy with the ANN model (79%). …”
Get full text

RST-YOLOv8: An Improved Chip Surface Defect Detection Model Based on YOLOv8 by Wenjie Tang, Yangjun Deng, Xu Luo

“…This integration effectively optimizes feature representation capabilities while significantly reducing the model’s parameter count. …”
Get full text

A scoping review of the use of artificial intelligence models in automated OCT analysis and prediction of treatment outcomes in diabetic macular oedema by Mohaimen Al-Zubaidy, Agnieszka Stankiewicz, Matthew Anderson, Jordan Reed, Veronica Corona, Rebecca Pope, Boguslaw Obara, Maged S. Habib, David H. Steel

Get full text

Individual Identification Using Radar-Measured Respiratory and Heartbeat Features by Haruto Kobayashi, Yuji Tanaka, Takuya Sakamoto

“…This study proposes a method for radar-based identification of individuals using a combination of their respiratory and heartbeat features. In the proposed method, the target individual’s respiratory features are extracted using the modified raised-cosine-waveform model and their heartbeat features are extracted using the mel-frequency cepstral analysis technique. …”
Get full text

SLG-Net: Small-Large-Global Feature-Based Multilevel Feature Extraction Network for Ultrasound Image Segmentation by Xinya Fan, Jianwen Hu, Kai Hu

“…However, it is essential to extract large-scale context features for large targets in images. To enhance the capability of feature extraction of the model for targets with various sizes and improve segmentation performance, we propose an effective multilevel feature extraction network (SLG-Net) which can extract features from local small details, large-scale context to global dependencies. …”
Get full text

UAV target tracking method based on global feature interaction and anchor-frame-free perceptual feature modulation. by Yuanhong Dan, Jinyan Li, Yu Jin, Yong Ji, Zhihao Wang, Dong Cheng

“…In this study, in order to refine the feature representation and reduce the computational effort to improve the efficiency of the tracker, we perform feature fusion in deep inter-correlation operations and introduce a global attention mechanism to enhance the model's field of view range and feature refinement capability to improve the tracking performance for small targets. …”
Get full text

Enhanced Infrared Defect Detection for UAVs Using Wavelet-Based Image Processing and Channel Attention-Integrated SSD Model by Jining Zhao, RuiZhi Zhang, Shaogong Chen, Yanbo Duan, Zhiyuan Wang, Qingchen Li

“…These findings suggest that the SSD-CA model proposed in this paper not only effectively extracts and enhances defect features but also intelligently suppresses non-essentia feature information in the background, thereby enabling real-time automatic detection of infrared image defects. …”
Get full text

Developing a high-performance AI model for spontaneous intracerebral hemorrhage mortality prediction using machine learning in ICU settings by Xiao-Han Vivian Yap, Kuan-Chi Tu, Nai-Ching Chen, Che-Chuan Wang, Chia-Jung Chen, Chung-Feng Liu, Tee-Tau Eric Nya, Ching-Lung Kuo

“…The study utilized 37 features related to mortality. Predictive models were developed using logistic regression, Random forest, LightGBM, XGBoost, and Multi-layer Perceptron (MLP), with assessments of feature importance, and Area under the curve (AUC). …”
Get full text

Machine learning-selected minimal features drive high-accuracy rule-based antibiotic susceptibility predictions for Staphylococcus aureus via metagenomic sequencing by Xuefeng Jia, Yongfen Xiong, Yanping Xu, Fangyuan Chen, Peng Han, Jieming Qu, Quanli He, Guanhua Rao

“…Traditional culture-based AST methods are slow, while existing whole-genome sequencing (WGS)-based models often suffer from overfitting, poor interpretability, and diminished performance on clinical metagenomic data. …”
Get full text

Assessing the performance of zero-shot visual question answering in multimodal large language models for 12-lead ECG image interpretation by Tomohisa Seki, Yoshimasa Kawazoe, Yoshimasa Kawazoe, Hiromasa Ito, Yu Akagi, Toru Takiguchi, Kazuhiko Ohe, Kazuhiko Ohe

“…Even when the answers were correct, erroneous descriptions of image features were common. These findings suggest a need for improved control over image hallucination and indicate that performance evaluation using the percentage of correct answers to multiple-choice questions may not be sufficient for performance assessment in VQA tasks.…”
Get full text

Advancing tourism demand forecasting in Sri Lanka: evaluating the performance of machine learning models and the impact of social media data integration by Isuru Udayangani Hewapathirana

“…Design/methodology/approach – Two sets of experiments are performed in this research. First, the predictive accuracy of three ML models, support vector regression (SVR), random forest (RF) and artificial neural network (ANN), is compared against the seasonal autoregressive integrated moving average (SARIMA) model using historical tourist arrivals as features. …”
Get full text

A novel RFE-GRU model for diabetes classification using PIMA Indian dataset by Mahmoud Y. Shams, Zahraa Tarek, Ahmed M. Elshewey

“…To achieve the classification for the PIDD, a new model called Recursive Feature Elimination-GRU (RFE-GRU) is proposed in this paper. …”
Get full text

Automatic Registration of Multi-Temporal 3D Models Based on Phase Congruency Method by Chaofeng Ren, Kenan Feng, Haixing Shang, Shiyuan Li

“…The first experiment demonstrates that the method proposed in this study performs remarkably well in improving the positioning accuracy of feature point coordinates, effectively reducing the mean error of the systematic error to below 0.001 m. …”
Get full text

A self evolving high performance sharded consortium blockchain designed for secure and trusted resource sharing for 6G networks by Xiaorong Zhu, Zhiwei Yuan, Qinyin Ni

“…Abstract The rapid development of 6G networks is transforming the traditional mobile network service model from operator-centric to a more open and collaborative ecosystem. …”
Get full text

AI-Powered Convolutional Neural Network Surrogate Modeling for High-Speed Finite Element Analysis in the NPPs Fuel Performance Framework by Salvatore A. Cancemi, Andrius Ambrutis, Mantas Povilaitis, Rosa Lo Frano

Get full text

Prediction of HER2 expression in breast cancer patients based on multi-parametric MRI intratumoral and peritumoral radiomics features combined with clinical and imaging indicators by Xiaoxiao Li, Xiaoxiao Li, Junfang Fang, Fuqian Wang, Lin Zhang, Xingyue Jiang, Xijin Mao

“…Univariate and multivariate logistic regression was used to identify the independent risk factors in clinical, pathological and conventional MRI data for constructing the clinical imaging model. The combined model was built from radiomics and clinical imaging features. …”
Get full text

A Semantic Weight Adaptive Model Based on Visual Question Answering by Li Huimin, Li Xuan, Chen Yan

“…The crux of this model lies in its ability to automatically extract task-relevant information from questions to dynamically guide the fusion process of multimodal features. …”
Get full text

An Enhanced Multiple Object Tracking Method With Improved Feature Fusion and Cross-Camera Trajectory Matching for Closed Scenes by Fengjun Chen, Guangxun Zhu, Zhenyu Lv, Ke Wang, Ruiyan Xu, Jian Liu

“…An improved scale-aware attention network (ISAAN) is employed to minimize information loss and feature distortion during feature fusion. Furthermore, a hierarchical association method based on ambiguous assignment modeling (HAAM) is proposed to improve the stability and robustness of object tracking in time series. …”
Get full text