Improved and Interpretable Solar Flare Predictions With Spatial and Topological Features of the Polarity Inversion Line Masked Magnetograms by Hu Sun, Ward Manchester IV, Yang Chen

“…We found that using the new features can improve the skill scores of the flare classification model and new features tend to have higher feature importance, especially the spatial statistics features. …”
Get full text

Graph feature selection for enhancing radiomic stability and reproducibility across multiple institutions in head and neck cancer by Hajar Moradmand, Jason Molitoris, Xiao Ling, Lisa Schumaker, Erin Allor, Hannah Thomas, Danielle Arons, Matthew Ferris, Rebecca Krc, William Silva Mendes, Phuoc Tran, Amit Sawant, Ranee Mehra, Daria A. Gaykalova, Lei Ren

“…We investigate a Graph-Based Feature Selection (Graph-FS) approach that models feature interdependencies to identify stable radiomic signatures for head and neck squamous cell carcinoma (HNSCC) across institutions. …”
Get full text

An interpretable machine learning method for fault diagnosis of oil-immersed transformers based on edge inference by Dong Hu, Yong Yang, Hao Dai, Chao Tang, Jufang Xie

“…To address these issues, this study proposes an interpretable fault diagnosis model for edge deployment. First, a filtered feature extraction algorithm based on real domain rough set theory is proposed to optimize feature extraction before model input. …”
Get full text

High-Precision Heterogeneous Satellite Image Manipulation Localization: Feature Point Rules and Semantic Similarity Measurement by Ruijie Wu, Wei Guo, Yi Liu, Chenhao Sun

“…The feature point constraint module mitigates the effects of lighting and seasonal variations in the images by performing feature point matching, applying filtering rules to conduct an initial screening to identify candidate tampered patches. …”
Get full text

AuxDepthNet: Real-Time Monocular 3D Object Detection with Depth-Sensitive Features by Ruochen Zhang, Hyeung-Sik Choi, Dongwook Jung, Phan Huy Nam Anh, Sang-Ki Jeong, Zihao Zhu

“…To overcome these limitations, we propose AuxDepthNet, an efficient framework for real-time monocular 3D object detection that eliminates the reliance on external depth maps or pre-trained depth models. AuxDepthNet introduces two key components: the Auxiliary Depth Feature (ADF) module, which implicitly learns depth-sensitive features to improve spatial reasoning and computational efficiency, and the Depth Position Mapping (DPM) module, which embeds depth positional information directly into the detection process to enable accurate object localization and 3D bounding box regression. …”
Get full text

Enhancing Hybrid Classification for Plant Diseases With Deep Feature Selection Based on Analytical Entropy and Statistical Method by Phanthawat Phiphatkamtorn, Sutasinee Jitanan

“…For tomatoes, ResNet-34 is the best model, achieving an excellent accuracy of 99.94% with 98 features. …”
Get full text

Automated Search and Analysis of the Stylometric Features that Describe the Style of the Prose 19th-21st Centuries by Ksenia V. Lagutina, Alla M. Manakhova

“…These features model the style of a text and are the indicators of the time when the text was created.Calculations of all the features are performed completely automatically, so it allows to conduct the large-scale experiments with artworks of a large volume and speeds up the work of a linguist. …”
Get full text

Developing an alternative data-driven model to resemble geomorphologic rainfall-runoff models by Pin-Chun Huang, Kwan Tun Lee

“…The proposed artificial intelligence (AI) model, which incorporates a classification algorithm for preprocessing input features prior to training a model based on the recurrent neural network, exhibits outstanding performance in runoff discharge prediction. …”
Get full text

Agricultural Greenhouse Extraction Based on Multi-Scale Feature Fusion and GF-2 Remote Sensing Imagery by Yuguang Chang, Xiaoyu Yu, Xu Yang, Zhengchao Chen, Pan Chen, Xuan Yang, Yongqing Bai

“…Using GF-2 satellite imagery over Weifang City, China, the model achieved a recall of 92.44%, precision of 91.47%, intersection-over-union of 85.13%, and F1-score of 91.95%. …”
Get full text

Downhole Coal–Rock Recognition Based on Joint Migration and Enhanced Multidimensional Full-Scale Visual Features by Bin Jiao, Chuanmeng Sun, Sichao Qin, Wenbo Wang, Yu Wang, Zhibo Wu, Yong Li, Dawei Shen

“…A Transformer-based architecture is employed to capture global dependencies within the image and perform reflectance component denoising. Additionally, a multi-scale luminance adjustment module is integrated to merge features across perceptual ranges, mitigating localized brightness anomalies such as overexposure. …”
Get full text

Magnetic resonance imaging features for diagnosing adhesive capsulitis of the shoulder: a systematic review and meta-analysis by Jian Xiang, Xiaona Zhou, Yinqi Liu, Weiyin Vivian Liu, Muqin Luo, Hui Gao, Kun Zhang

“…To identify and summarize the diagnostic accuracy of these features, a systematic review and meta-analysis were performed. …”
Get full text

Integrative multi-omics analysis and machine learning refine global histone modification features in prostate cancer by XiaoFeng He, QinTao Ge, QinTao Ge, WenYang Zhao, Chao Yu, HuiMing Bai, XiaoTong Wu, Jing Tao, WenHao Xu, WenHao Xu, Yunhua Qiu, Lei Chen, JianFeng Yang

Get full text

Expression of the IL-18-related gene PTX3 correlates with clinicopathological features and prognosis in glioma patients by Delin Wang, Cuimei Liu, Bohao Sun, Xiaodong Zhang, Yejun Zhou, Zhonglin Hu, Duanzheng Cao, Jing Zhang, Jinfang Xu

“…The relationship between PTX3 expression and clinicopathological features was also examined. Prognostic relevance was evaluated using univariate and multivariate Cox regression models, and Kaplan–Meier survival analysis was performed. …”
Get full text

Clinicopathologic and genomic features associated with brain metastasis after resection of lung adenocarcinomaCentral MessagePerspective by Elizabeth G. Dunne, MD, Cameron N. Fick, MD, Brooke Mastrogiacomo, MS, Kay See Tan, PhD, Nicolas Toumbacaris, MSPH, Stijn Vanstraelen, MD, Gaetano Rocco, MD, Jaime E. Chaft, MD, Puneeth Iyengar, MD, Daniel Gomez, MD, Prasad S. Adusumilli, MD, Bernard J. Park, MD, James M. Isbell, MD, Matthew J. Bott, MD, Smita Sihag, MD, Daniela Molena, MD, James Huang, MD, David R. Jones, MD

“…A subset of patients had broad-based panel next-generation sequencing performed on their tumors. Fine-Gray models for the development of brain metastasis were constructed, with death without brain metastasis as a competing risk. …”
Get full text

Efficient CNN architecture with image sensing and algorithmic channeling for dataset harmonization by Khadija Kanwal, Khawaja Tehseen Ahmad, Aiza Shabir, Li Jing, Helena Garay, Luis Eduardo Prado Gonzalez, Hanen Karamti, Imran Ashraf

“…The proposed approach integrates DenseNet with ResNet-50, VGG-19, and GoogLeNet using an innovative bonding process that establishes algorithmic channeling between these models. The goal targets compact efficient image feature vectors that process data in parallel regardless of input color or grayscale consistency and work across different datasets and semantic categories. …”
Get full text

Mobility model detection method based on birth and death model in DTN environment by ENGGuang-hong D, AOWan-hua C, HANGJian Z, HENGXiong C, ENGLi F

“…A mobility model detection method based on birth and death model (MMD-BDM) in DTN environment was proposed.It first computed the connected channel capacity of sampling times according to the data traffic during the data transfer process,and then constructed the time varying intercommunication metrics at local,which composed of channel capacity between local node and others.Based on these,the connection birth and death mode of nodes based on connected edges was deduced,and then the birth and death features of the connected nodes was analyzed to detect the mobility model,which used to improve the routing strategy during the packages deliver process.Ultimately,the mobility model detection method was put into use in spray and wait routing (SWR) method and random network coding routing (RNCR) method to experiment,the simulation results show that,it can improve the opportunity routing performance of the data deliver rate and transfer latency in DTN environment.…”
Get full text

Integrating pathomics and deep learning for subtyping uveal melanoma: identifying high-risk immune infiltration profiles by Qi Wan, Ran Wei, Hongbo Yin, Jing Tang, Ying-ping Deng, Ke Ma

“…The relationship between histopathological features and genomics was explored.ResultsThe study achieved accurate prediction and classification of UVM patients using deep learning models and machine learning techniques. …”
Get full text

Dosiomic predictors of biochemical failure in patients with localized prostate cancer treated with Iodine-125 low-dose-rate brachytherapy by Masahiro Nakano, Shizuo Kaji, Shogo Kawakami, Hideyasu Tsumura, Toshikazu Imae, Yuichi Tanaka, Kyohei Fujii, Takuro Kainuma, Ryosuke Yamazaki, Ayaka Uchida, Hijiri Kaneko, Mako Fujino, Chizu Hata, Yu Murakami, Masatoshi Hashimoto, Hiromichi Ishiyama

“…The Boruta algorithm was used to eliminate less important features. Two analyses were performed: Analysis A performed a multivariate logistic regression analysis using data from the validation cohort to identify significant features. …”
Get full text

Predictive modeling for step II therapy response in periodontitis - model development and validation by Elias Walter, Tobias Brock, Pierre Lahoud, Nils Werner, Felix Czaja, Antonin Tichy, Caspar Bumm, Andreas Bender, Ana Castro, Wim Teughels, Falk Schwendicke, Matthias Folwaczny

“…Models accurately predicted that healthy sites stay healthy, but performed suboptimally for diseased sites. …”
Get full text

Deep Mining on the Formation Cycle Features for Concurrent SOH Estimation and RUL Prognostication in Lithium-Ion Batteries by Dongchen Yang, Weilin He, Xin He

“…By integrating diverse datasets with advanced algorithms and models, we perform correlation analyses of parameters such as capacity, voltage, temperature, pressure, and strain, enabling precise SOH estimation and RUL prediction. …”
Get full text