Dynamically Tunable Multidimensional Feature Focusing and Diffusion Networks for Water Surface Debris Detection by Chong Zhang, Jie Yue, Jianglong Fu

“…This approach significantly improved feature expression capability and overall model performance. …”
Get full text

A Deep Learning Approach Based on Interpretable Feature Importance for Predicting Sports Results by Bendiaf Messaoud, Khelifi Hakima, Mohdeb Djamila, Belazzoug Mouhoub, Saifi Abdelhamid

“…Then, we applied multiple machine learning algorithms to compare the performance of those different models, and choose the one that performs the best. …”
Get full text

Cross-social-network user alignment research based on multi-dimensional user features by Tao Zhao, Heng Gao, Zecheng Wang, Dianjie Bi, Xuemin Chen

“…To address these challenges, we introduce a cross-social network user alignment model based on multi-dimensional user features (MDUF). …”
Get full text

Adaptive Fusion of LiDAR Features for 3D Object Detection in Autonomous Driving by Mingrui Wang, Dongjie Li, Josep R. Casas, Javier Ruiz-Hidalgo

“…In such scenarios, the model demonstrates superior performance in detecting small objects like pedestrians compared to mainstream perception methods while also improving the cooperative perception accuracy for medium and large objects such as vehicles. …”
Get full text

Deep Feature Fusion via Transfer Learning for Multi-Class Network Intrusion Detection by Sunghyuk Lee, Donghwan Roh, Jaehak Yu, Daesung Moon, Jonghyuk Lee, Ji-Hoon Bae

“…The proposed architecture integrates convolutional neural networks (CNNs) with an attention mechanism to extract and aggregate salient features, thereby enhancing the model’s discriminative capacity between normal traffic and various network attack categories. …”
Get full text

The Improved Kurdish Dialect Classification Using Data Augmentation and ANOVA-Based Feature Selection by Karzan J. Ghafoor, Sarkhel H. Karim, Karwan M. Hama Rawf, Ayub O. Abdulrahman

“…The model showed a very strong performance, reaching a remarkable accuracy of 99.42%. …”
Get full text

Research on Feature Extraction Method of Engine Misfire Fault Based on Signal Sparse Decomposition by Canyi Du, Fei Jiang, Kang Ding, Feng Li, Feifei Yu

“…Firstly, in order to highlight resonance regions related with impact features, the vibration signal is performed with a high-pass filter process. …”
Get full text

Classification of SERS spectra for agrochemical detection using a neural network with engineered features by Mateo Frausto-Avila, Monserrat Ochoa-Elias, Jose Pablo Manriquez-Amavizca, María del Carmen González-López, Gonzalo Ramírez-García, Mario Alan Quiroz-Juárez

“…The model demonstrates strong predictive performance, achieving high precision and recall values across all classes, with an overall classification accuracy of 98.5% for organophosphate pesticides and their mixtures. …”
Get full text

SmartRipen: LSTM-GRU feature selection& XGBoost-CNN for fruit ripeness detection by Archana Ganesh Said, Bharti Joshi

“…It will be tested for adaptability to other fruit types and real-time applications using low-complexity feature sets along with advanced methods like Q-Learning as well as Auto Encoders that will enhance dynamical performance.…”
Get full text

Identity Hides in Darkness: Learning Feature Discovery Transformer for Nighttime Person Re-Identification by Xin Yuan, Ying He, Guozhu Hao

“…In particular, to reduce noise disturbance and discover pedestrian identity details, the FRM utilizes the Discrete Haar Wavelet Transform to acquire the high- and low-frequency components for learning person features. Furthermore, to avoid high-frequency components being over-smoothed by low-frequency ones, we propose a novel Normalized Contrastive Loss (NCL) to help the model obtain the identity details in high-frequency components for extracting discriminative person features. …”
Get full text

Prediction of Promotors in Agrobacterium and Klebsiella Using Novel Feature Engineering and Ensemble Learning Approach by Nagwan Abdel Samee, Rawan Talaat, Ali Raza, Hadil Shaiba, Souham Meshoul

“…These features were then used to train an ensemble learning model, combining the strengths of multiple classifiers to enhance prediction accuracy. …”
Get full text

Multi-Feature Fusion for Estimating Above-Ground Biomass of Potato by UAV Remote Sensing by Guolan Xian, Jiangang Liu, Yongxin Lin, Shuang Li, Chunsong Bian

“…The results indicate the following: (1) The newly proposed variety-dependent indicator growth process ratio (GPR) can improve the model accuracy by over 20%. (2) The fusion of vegetation indices, canopy cover, growing degree days, and GPR achieved higher accuracy to estimate AGB at all growth stages compared with single feature model. (3) RF model performed best for the estimation of AGB during the whole growth period with R² 0.79 and rRMSE 0.24 ton/ha. …”
Get full text

Citrus Disease Detection Based on Dilated Reparam Feature Enhancement and Shared Parameter Head by Xu Guo, Xingmeng Wang, Wenhao Zhu, Simon X. Yang, Lepeng Song, Ping Li, Qinzheng Li

“…This study presents YOLOv8n-DE, an improved lightweight YOLOv8-based model for enhanced citrus disease detection. It introduces the DR module structure for effective feature enhancement and the Detect_Shared architecture for parameter efficiency. …”
Get full text

Research on Fine-Grained Visual Classification Method Based on Dual-Attention Feature Complementation by Min Huang, Ke Li, Xiaoyan Yu, Chen Yang

“…This model obtains dual-dimensional enhanced features through cross-attention in two dimensions and allows the network to explore other potential discriminative areas by suppressing the enhanced features. …”
Get full text

Can Implicit Solvation Methods Capture Temperature Effects on the Infrared Features of Astrophysical Ices? by Daniel A. B. Oliveira, Víctor S. A. Bonfim, Felipe Fantuzzi, Sergio Pilling

“…We investigate the ability of implicit solvation approaches to capture temperature-dependent infrared spectral features of CO₂ molecules embedded in astrophysical ice analogues, comparing their performance to that of explicit ice models and experimental data. …”
Get full text

Aircraft Detection from VHR Images Based on Circle-Frequency Filter and Multilevel Features by Feng Gao, Qizhi Xu, Bo Li

“…To accurately distinguish aircrafts from background, a circle-frequency filter (CF-filter) is used to extract the candidate locations of aircrafts from a large size image. A multi-level feature model is then employed to represent both local appearance and spatial layout of aircrafts by means of Robust Hue Descriptor and Histogram of Oriented Gradients. …”
Get full text

Transfer learning based feature selection for feedforward neural network for speech emotion classifier by D. V. Krasnoproshin, M. I. Vashkevich

“…This technique allowed us to significantly reduce initial feature vector size while increasing models’ prediction quality. …”
Get full text

Software Defect Prediction Using Deep Q-Learning Network-Based Feature Extraction by Qinhe Zhang, Jiachen Zhang, Tie Feng, Jialang Xue, Xinxin Zhu, Ningyang Zhu, Zhiheng Li

“…Unfortunately, all the previous research conducted without effective feature reduction suffers from high-dimensional data, leading to unsatisfactory prediction performance measures. …”
Get full text

Invariant Feature Matching in Spacecraft Rendezvous and Docking Optical Imaging Based on Deep Learning by Dongwen Guo, Shuang Wu, Desheng Weng, Chenzhong Gao, Wei Li

“…The number of successfully matched feature points per frame consistently reaches the hundreds, the successful rate remains 100%, and the average processing time is maintained below 0.18 s per frame, an overall performance which far exceeds other methods. …”
Get full text

Semi-Supervised Remote Sensing Building Change Detection with Joint Perturbation and Feature Complementation by Zhanlong Chen, Rui Wang, Yongyang Xu

“…However, these methods primarily focus on utilizing unlabeled data through various training strategies, neglecting the impact of pseudo-changes and learning bias in models. When dealing with limited labeled data, abundant low-quality pseudo-labels generated by poorly performing models can hinder effective performance improvement, leading to the incomplete recognition results of changes to buildings. …”
Get full text