Evaluating Sparse Feature Selection Methods: A Theoretical and Empirical Perspective by Monica Fira, Liviu Goras, Hariton-Nicolae Costin

“…The analysis shows that embedded methods strike a balance between accuracy and efficiency by selecting features during the model training, unlike filtering methods, which ignore feature interactions. …”
Get full text

A problem-agnostic approach to feature selection and analysis using SHAP by John T. Hancock, Taghi M. Khoshgoftaar, Qianxin Liang

“…SHapley Additive exPlanations (SHAP) can be used to provide a feature importance ranking for models built with labeled or unlabeled data. …”
Get full text

Evaluating Feature Selection Methods for Accurate Diagnosis of Diabetic Kidney Disease by Valeria Maeda-Gutiérrez, Carlos E. Galván-Tejada, Jorge I. Galván-Tejada, Miguel Cruz, José M. Celaya-Padilla, Hamurabi Gamboa-Rosales, Alejandra García-Hernández, Huizilopoztli Luna-García, Klinge Orlando Villalba-Condori

“…After selecting suitable features detected by the methodologies, they are included in the random forest classifier, obtaining four models. …”
Get full text

FRANet: A Feature Refinement Attention Network for SAR Image Denoising by Shuaiqi Liu, Yu Lei, Qi Hu, Ming Liu, Bing Li, Weiming Hu, Yu-Dong Zhang

“…Second, a feature attention encoder–decoder network is constructed for deep feature extraction. …”
Get full text

Wireless Authentication Method Based on Near-Field Feature Fusion Network by QIU Jiefan, ZHOU Kezhong, ZHU Dongfu, ZHANG Jinhong, CHI Kaikai

“…To address this issue, this paper proposes a novel WiFi-based authentication method tailored for narrow-space environments, which integrates gait dynamic features and LOS features for improved performance.MethodsA WiFi Feature Fusion Network (WFFN) was proposed to enhance identity recognition accuracy by fusing gait dynamic features with near-field LOS features. …”
Get full text

Remote sensing semantic segmentation based on multimodal feature alignment and fusion by B. Chang, T. Balz

“…In comparison to traditional single-modal segmentation techniques, models based on multi-modal fusion have demonstrated superior performance and have been the subject of considerable attention in recent years. …”
Get full text

Advancing Hyperspectral Image Classification with Deep Features Learning and Evolutionary Algorithms by M. B. Amri, M. B. Amri, D. Yedjour, M. E. A. Larabi, F. Berrichi

“…In addition, the experiments conducted on simulated benchmarks validate the superior performance of the proposed approach compared to the baseline ML model in terms of prediction accuracy and F1-score.…”
Get full text

Leveraging modality‐specific and shared features for RGB‐T salient object detection by Shuo Wang, Gang Yang, Qiqi Xu, Xun Dai

“…Extensive experiments on three public datasets show that the MSTNet outperforms 14 state‐of‐the‐art methods, demonstrating that this method can extract and utilise the multi‐modality information more adequately and extract more complete and rich features, thus improving the model's performance. The code will be released at https://github.com/JOOOOKII/MSTNet.…”
Get full text

Optimizing Feature Selection for IOT Intrusion Detection Using RFE and PSO by zahraa mehssen agheeb Alhamdawee

“…RF improves decision-making by focusing on the most informative features, resulting in better overall performance. …”
Get full text

Lightweight interactive feature inference network for single-image super-resolution by Li Wang, Xing Li, Wei Tian, Jianhua Peng, Rui Chen

“…However, these networks commonly construct complex structures, having huge model parameters and high computational costs, to boost reconstruction performance. …”
Get full text

GCNTrack: A Pig-Tracking Method Based on Skeleton Feature Similarity by Zhaoyang Yin, Zehua Wang, Junhua Ye, Suyin Zhou, Aijun Xu

“…Three identical FOV sets of data that separately included long, medium, and short duration videos were used to test the model and verify its performance. The GcnTrack method achieved a Multiple Object Tracking Accuracy (MOTA) of 84.98% and an identification F1 Score (IDF1) of 82.22% for the first set of videos (short duration, 87 s to 220 s). …”
Get full text

Feature Integration Strategies for Neural Speaker Diarization in Conversational Telephone Speech by Juan Ignacio Alvarez-Trejos, Alicia Lozano-Diez, Daniel Ramos

“…Moreover, through comprehensive ablation studies of GeMAPS features, we identify optimal acoustic parameters and temporal contexts for diarization tasks, achieving a reduced feature set that maintains performance while decreasing computational complexity. …”
Get full text

Inferring internal states across mice and monkeys using facial features by Alejandro Tlaie, Muad Y. Abd El Hay, Berkutay Mert, Robert Taylor, Pierre-Antoine Ferracci, Katharine Shapcott, Mina Glukhova, Jonathan W. Pillow, Martha N. Havenith, Marieke L. Schölvinck

“…The relationship of the identified states to task performance is comparable between mice and monkeys. …”
Get full text

Feature Selection Using Pearson Correlation for Ultra-Wideband Ranging Classification by Gita Indah Hapsari, Rendy Munadi, Bayu Erfianto, Indrarini Dyah Irawati

“…The Random Forest and Gradient Boosting models exhibit superior performance, maintaining classification accuracy above 90%. …”
Get full text

Multi-feature Fusion Network for Classification of Pipeline Magnetic Leakage Signals by WEI Yuanyuan, LIU Ruiping, FU Shimo, WANG Yaoli

“…Findings Experimental results demonstrate that the MMF network achieves a precision of 98.86% in anomaly classification, with an AUC evaluation result of 99.25%. Additionally, the model is more streamlined, exhibiting higher computational efficiency, and is capable of delivering satisfactory performance within a relatively short training period.…”
Get full text

Genetic algorithm feature selection resilient to increasing amounts of data imputation by Maryam Kebari, Annie S Wu

“…Feature selection can be beneficial in predictive modeling to reduce computational costs and potentially improve performance. …”
Get full text

CDFA: Calibrated deep feature aggregation for screening synergistic drug combinations by Xiaorui Kang, Xiaoyan Liu, Quan Zou, Quan Zou, Tiantian Li, Ximei Luo, Ximei Luo

“…Concretely, CDFA utilizes a novel cell line representation based on the protein information and gene expression capturing complementary biological determinants of drug response. Besides, a novel feature aggregation network is proposed based on the Transformer to model the intricate interactions between drug pairs and cell lines through multi-head attention mechanisms, enabling discovery of non-linear synergy patterns. …”
Get full text

Improving Moving Insect Detection with Difference of Features Maps in YOLO Architecture by Angel Gomez-Canales, Javier Gomez-Avila, Jesus Hernandez-Barragan, Carlos Lopez-Franco, Carlos Villaseñor, Nancy Arana-Daniel

“…Insect detection under real-field conditions remains a challenging task due to factors such as lighting variations and the small size of insects that often lack sufficient visual features for reliable identification by deep learning models. …”
Get full text

Molecular and cellular features of femoral head avascular necrosis: in vivo study by N. A. Shabaldin, A. V. Sinitskaya, L. A. Bogdanov, A. A. Lobov, E. A. Repkin, A. V. Shabaldin

“…To study the molecular and cellular features of femoral head avascular necrosis in the rat model.Materials and Methods. …”
Get full text

Extensive Feature-Inferring Deep Network for Hyperspectral and Multispectral Image Fusion by Abdolraheem Khader, Jingxiang Yang, Sara Abdelwahab Ghorashi, Ali Ahmed, Zeinab Dehghan, Liang Xiao

“…This fusion problem can be accomplished by formulating a mathematical model and solving it either analytically or iteratively. …”
Get full text