Soil Porosity Detection Method Based on Ultrasound and Multi-Scale Feature Extraction by Hang Xing, Zeyang Zhong, Wenhao Zhang, Yu Jiang, Xinyu Jiang, Xiuli Yang, Weizi Cai, Shuanglong Wu, Long Qi

“…Since the collected ultrasonic signals belong to long-time series data and there are different frequency and sequence features, this study constructs a multi-scale CNN-LSTM deep neural network model using large convolution kernels based on the idea of multi-scale feature extraction, which uses multiple large convolution kernels of different sizes to downsize the collected ultra-long time series data and extract local features in the sequences, and combining the ability of LSTM to capture global and long-term dependent features enhances the feature expression ability of the model. …”
Get full text

Deep Learning with Dual-Channel Feature Fusion for Epileptic EEG Signal Classification by Bingbing Yu, Mingliang Zuo, Li Sui

“…The model’s performance was evaluated on the publicly available Bonn EEG dataset. …”
Get full text

Optimal Statistical Feature Subset Selection for Bearing Fault Detection and Severity Estimation by Chhaya Grover, Neelam Turk

“…The performance of bearing fault detection systems based on machine learning techniques largely depends on the selected features. …”
Get full text

Surface Roughness Prediction of Bearing Ring Precision Grinding Based on Feature Extraction by Chaoyu Shi, Bohao Chen, Yao Shi, Jun Zha

Get full text

Heart Disease Diagnostics Using Meta-Learning-Based Hybrid Feature Selection by Kaushalya Dissanayake, Md Gapar Md Johar

“…The proposed hybrid technique has been tested on the heart disease dataset, and the results show that the meta-learning-based hybrid feature selection approach performs exceptionally well in terms of performance metrics. …”
Get full text

Peritumoral features for assessing invasiveness of lung adenocarcinoma manifesting as ground-glass nodules by Xiao Wang, Hui Xue, Wei Ding, Fei Huang, Yu Zhang, Xin Pang

“…Abstract We evaluated the predictive value of radiomics features from different peritumoral ranges for the invasiveness of ground-glass nodular lung adenocarcinoma using various machine learning models. …”
Get full text

Modification of a model of non-alcoholic fat liver disease in rats with a сombination of a hypercaloric diet and hypodynamia by A. V. Bunjat, O. M. Spasenkova, V. E. Karev, A. V. Karavaeva, D. Ju. Ivkin, A. N. Kulikov, S. V. Okovityi, N. V. Kirillova

“…An urgent task is to find and develop an optimal model of NAFLD in laboratory animals, which would reproduce all the features of this disease in the clinic.Aim. …”
Get full text

Image super-resolution reconstruction network combining asymmetric convolution and feature distillation by ZHU Lei, FENG Da, ZHU Qiwei, ZHAO Han, WANG Qianqian

“…Finally, BAM was added to the reconstruction module to further improve the final reconstruction performance of the network. The experimental results show that compared with advanced lightweight networks such as RLFN and SMSR, the proposed ACDN can reconstruct high-quality images with richer texture details on five standard data sets, improve the peak signal-to-noise ratio and structural similarity index of reconstructed images, and achieve a better balance between the number of parameters and the performance of the network model.…”
Get full text

Simulation Analysis on Active Frequency Support Features of Grid-Forming Wind Turbine by QU Sheng, TANG Jianping, LI Yangtao, LIU Hongwen, PANG Jiameng, HU Peng

“…Subsequent verification was conducted on technical aspects, including the key parameters and features of active frequency support. The results showed good response performance in inertia support for the virtual synchronization control mode, due to its imitation on synchronizer characteristics. …”
Get full text

Wind speed forecasting approach using conformal prediction and feature importance selection by Cesar Vinicius Zuege, Stefano Frizzo Stefenon, Cristina Keiko Yamaguchi, Viviana Cocco Mariani, Gabriel Villarrubia Gonzalez, Leandro dos Santos Coelho

“…The proposed method considers the conformal prediction approach and, based on Shapley values, uses optimal selection of features given their importance. Furthermore, a Bayesian Optimization with Tree-structured Parzen Estimators (BO-TPE) will be used to tune the hyperparameters of the models. …”
Get full text

Task-Oriented Local Feature Rectification Network for Few-Shot Image Classification by Ping Li, Xiang Zhu

“…Therefore, the few-shot learning model is easily disturbed by class-irrelevant features, which results in a decrease in accuracy. …”
Get full text

An integrated approach of feature selection and machine learning for early detection of breast cancer by Jing Zhu, Zhenhang Zhao, Bangzheng Yin, Canpeng Wu, Chan Yin, Rong Chen, Youde Ding

“…In the datasets, 26 features were filtered using our recommended algorithm, the LightGBM-PSO model demonstrated an outstanding performance. …”
Get full text

A scoping review of feedback features during clinical education for anaesthesia trainees by Santosh Patel, Franklin Dexter

Get full text

Rock fracture type recognition based on deep feature learning of microseismic signals by LI Dianze, XU Huajie, ZHANG Bo

“…However, conventional machine learning methods for microseismic signal analysis exhibited limited feature extraction capabilities and were highly susceptible to noise, leading to reduced classification accuracy and poor generalization performance. …”
Get full text

Swin Transformer With Late-Fusion Feature Aggregation for Multi-Modal Vehicle Reidentification by Reza Fuad Rachmadi, Supeno Mardi Susiki Nugroho, I. Ketut Eddy Purnama

“…Vehicle image data from low-light environments is very challenging for reidentification tasks, and multi-modal data (visible, near-infrared, and thermal) is often used to improve model performance. In this paper, we proposed a Swin Transformer classifier with late-fusion feature aggregation networks called SAFA (Self-Attention Feature Aggregation) for multi-modal vehicle reidentification problems. …”
Get full text

Transferable Feature Representation for Visible-to-Infrared Cross-Dataset Human Action Recognition by Yang Liu, Zhaoyang Lu, Jing Li, Chao Yao, Yanzi Deng

“…In the proposed framework, we first construct a novel Cross-Dataset Feature Alignment and Generalization (CDFAG) framework to map the infrared data and visible light data into a common feature space, where Kernel Manifold Alignment (KEMA) and a dual aligned-to-generalized encoders (AGE) model are employed to represent the feature. …”
Get full text

Multimodal Feature-Driven Deep Learning for the Prediction of Duck Body Dimensions and Weight by Wenbo Xiao, Qiannan Han, Gang Shu, Guiping Liang, Hongyan Zhang, Song Wang, Zhihao Xu, Weican Wan, Chuang Li, Guitao Jiang, Yi Xiao

“…A dataset of 1023 Linwu ducks, comprising over 5000 samples with diverse postures and conditions, was collected to support model training. The proposed method innovatively employs PointNet++ to extract key feature points from point clouds, extracts and computes corresponding 3D geometric features, and fuses them with multi-view convolutional 2D features. …”
Get full text

Highly Accurate Brain Tumor Segmentation and Classification Using Multiple Feature Sets by Megha Sunil Borse, Murali Prasad R, Tummala Ranga Babu

“…Statistical and Local Binary Patterns (LBP) features are extracted from the preprocessed images to perform the classification process. …”
Get full text

Decoding ’Eligibility Unknown’: transparent classification and feature-based reclassification in CAFV analysis by Muhammad Amir Khan, Mona A. Alkhattabi, Sheikh Muhammad Saqib, Tehseen Mazhar, Tariq Shahzad, Asim Seedahmed Ali Osman, Abdul Khader Jilani Saudagar, Habib Hamam

“…The model is trained on a refined dataset—reduced from over 177,000 entries to 546 unique records after de-duplication—and interpreted using SHAP and LIME to ensure transparency and control overfitting.Although the model achieves perfect performance metrics on this cleaned dataset, we emphasize dataset preparation and interpretability rather than predictive perfection. …”
Get full text

Attention-based interactive multi-level feature fusion for named entity recognition by Yiwu Xu, Yun Chen

“…Our model is composed of four parts: the input, feature extraction, feature fusion, and sequence-labeling layers. …”
Get full text