M2Caps: learning multi-modal capsules of optical and SAR images for land cover classification by Haodi Zhang, Anzhu Yu, Kuiliang Gao, Xuanbei Lu, Xuefeng Cao, Wenyue Guo, Weiqi Lian

“…M²Caps outperformed state-of-the-art models, improving mean intersection over union (mIoU) by 2.86% – 12.9% on the WHU-OPT-SAR dataset and 3.91% – 12.3% on the GF-2 and GF-3 Pohang datasets, demonstrating its effectiveness in high-precision LCC in complex environments.…”
Get full text

Biodegradable porous iron versus titanium interference screws in porcine ACL reconstruction model: a one-year observational study by Wen-Chih Liu, Hao-Wei Chang, Shin-I Huang, Kuo-Yi Yang, Pei-I Tsai, Chung-Hwan Chen, Yan-Hsiung Wang, Chun-Hsien Ma, Chih-Yu Chen, Yin-Chih Fu

“…Fe implants showed significantly greater bone volume fraction, bone surface density, and intersection-to-total surface area (P = 0.025, 0.047, 0.021). …”
Get full text

Improvement of surgical treatment of an acute biliary pancreatitis at elderly and senile patients by V. I. Midlenko, A. L. Charyshkin, O. V. Midlenko, I. I. Midlenko, V. Yu. Shchegolev

“…To estimate various variants of surgical treatment of acute biliary pancreatitis at patients of over 60 years old, to develop a method of cholecystectomy at the large Hartmann pouch adherent to biliary tracts, to decrease such complications, as bleeding, bile leakage, damage (intersection) of common bile or common hepatic duct.Material and methods. …”
Get full text

WGCNA combined with machine learning for analysis of diagnostic markers of preeclampsia associated with the hedgehog signaling pathway by Xiaofeng Wang, Yichi Xu, Junpeng Dong, Jinwen Zhang, Wei Gu, Xiaoli Qin

“…WGCNA was utilized to identify Hh pathway-related genes. Following the intersection of the two genes, key genes were screened by using LASSO, SVM-RFE, and RF. …”
Get full text

An oxidative stress related gene signature predicts prognosis in cholangiocarcinoma by Han Fan, Peng Qiu, Yun Lu, Zhengdong Deng, Li Tian

“…Methods Using data from 66 tumors and 36 control samples obtained from the TCGA and GEO databases, we identified 3,632 differentially expressed genes (DEGs). Intersection with oxidative stress-related genes revealed 122 OSRGs, from which 10 key prognostic genes were selected through univariate Cox and LASSO regression analyses. …”
Get full text

Autonomous unmanned aerial vehicles exploration for semantic indoor reconstruction using 3D Gaussian splatting by Hao Xuan Zhang, Yilin Yang, Zhengbo Zou

“…Results show that the ICON drone could: (1) explore all three scenes autonomously, (2) generate absolute scale point clouds with F1-score of 0.5806, 0.6638, and 0.8167 compared to point clouds collected using a high-fidelity terrestrial LiDAR scanner, and (3) label the point cloud with corresponding building components and material with mean intersection over union of 0.588 and 0.629. The reconstruction algorithm is further evaluated on ScanNet, and results show that our method outperforms previous methods by a large margin on 3D reconstruction quality.…”
Get full text

AI microscope facilitates accurate interpretation of HER2 immunohistochemical scores 0 and 1+ in invasive breast cancer by Zong La, Jie Chen, Xunxi Lu, Chuanfen Lei, Fengling Li, Lin Zhao, Yuhao Yi

“…Model I achieved mean intersection over union (MIoU) scores of 0.879 and 0.880 at 20× and 40× magnifications, and Model II’s F1-scores were 0.866 and 0.878. …”
Get full text

Tree semantic segmentation from aerial image time series by Venkatesh Ramesh, Arthur Ouaknine, David Rolnick

“…Our best model achieves a mean Intersection over Union (mIoU) of 55.97%, outperforming single-image approaches particularly for deciduous trees where phenological changes are most noticeable. …”
Get full text

FragMangro: A cross-domain zero-shot model for monitoring fragmented mangrove ecosystems by Ruoxin Zhang, Angela An, Mingcan Cen, Chong Zhang, Aimee Huangfu, Sunny Vinnakota, Shuxiang Song

“…The results demonstrate that FragMangro achieves over 98% accuracy, an average F1 Score exceeding 85%, and the Intersection over Union(IoU) surpassing 74%, significantly outperforming conventional methods such as support vector machines (SVM), random forests (RF), and k-nearest neighbors (KNN). …”
Get full text

Bioinformatics analysis of Rho-signal transduction genes in postmenopausal osteoporosis and periodontitis by Jing Qi, E. Liu, Yunqing Pang, Yu Wang, Jing Wang

“…After PCA-based outlier removal, differentially expressed genes were identified using limma, followed by intersection analysis, KEGG enrichment, PPI network construction, and Rho pathway screening. …”
Get full text

Multiscale Analysis of a Non-Supercell Tornado in Yunnan by Yixue DENG, Tiangui XIAO, Liyun XIAO

“…Based on reanalysis data， multi-source observation data， and Wenshan Doppler radar data， a study was conducted on the circulation background， environmental potential， evolution process， and formation mechanism of a EF0 tornado that occurred in Guangnan County， Wenshan Prefecture， Yunnan Province， in the afternoon of May 31， 2021.The results showed that： （1） The tornado occurred in the western flow at edge of subtropical anticyclone， the 700 hPa wind speed convergence region， and the 850 hPa shear line.There was a dry and cold air intrusion in the middle atmosphere， and having the necessary thermal and water vapor conditions for a tornado to occur.However， the dynamic conditions were not conducive to the occurrence of a tornado， that is， the low-level and deep vertical wind shear were significantly weaker than that of non-supercell tornadoes in the central and eastern regions of China.（2） Higher ground temperatures， water vapor boundaries on cloud images， and mesoscale convergence lines jointly triggered convective storms in southeastern Yunnan Province.Affected by complex terrain， the convective cells appeared to be split and strengthened， and continued to advance towards the Guangnan County， which has a higher elevation in the northwest.（3） The possible mechanism for the formation of the tornado is that the high ground temperature in the Guangnan Basin created convective instability， and the cold pool outflow below the convective cells on the eastern side of the basin entered the basin and expanded westward.The intersection of warm and cold air caused new cells to begin triggering along the convergence shear line， and the temperature difference between the cold pool and the surrounding environment below it was conducive to the formation of the tornado.Subsequently， the convective cells developed into a narrow and long shape along the terrain on the western side of the basin， then an initial vortex formed in the lower level of the storm.The topographic forcing enhanced the uplift motion above the initial vortex， causing it to tilt and stretch while increasing vorticity， ultimately forming this tornado.…”
Get full text

Re-Parameterization After Pruning: Lightweight Algorithm Based on UAV Remote Sensing Target Detection by Yang Yang, Pinde Song, Yongchao Wang, Lijia Cao

“…In addition, the focal and efficient intersection over union (FocalEIoU) is used to improve the regression performance of the algorithm and reduce the false-negative rate. …”
Get full text

Multi-scale attention-enhanced deep learning approach for detecting seven trunk pests and diseases in Shanghai’s urban plane trees by Tianyang Song, Guohua Hu, Tianci Yu, Xing Meng, Yanting Zhang, Ruiqing Yang, Benyao Wang, Xia Li

“…Trained on 3,983 annotated samples from Shanghai, the model achieved a 3.8% increase in mean Average Precision at a 50% Intersection over Union threshold (mAP50) and a significant reduction in missed detections compared to the baseline YOLOv8. …”
Get full text

Prediction Method for Anisotropy and Fracture Parameters of Reservoirs with Vertical Fractures Based on Acoustic Logging by MENG Jikun, QI Qiaomu, LI Linxin, LI Xiaobin, ZHENG Qinren

“…Furthermore, the identification of gas-filled fracture can be carried out by the intersection of the fracture normal-tangential compliance ratio and the porosity curve. …”
Get full text

Neuroeducation: understanding neural dynamics in learning and teaching by K. Pradeep, Rajalakshmi Sulur Anbalagan, Asha Priya Thangavelu, S. Aswathy, V. G. Jisha, V. S. Vaisakhi

“…Neuroeducation, an emerging interdisciplinary field at the intersection of neuroscience and education, investigates into the complex processes underpinning learning which offering novel insights and methodologies. …”
Get full text

Simplifying Two-Stage Object Detectors for On-Board Remote Sensing by Jaemin Kang, Hoeseok Yang, Hyungshin Kim

“…We apply a method to determine the threshold for positive anchors based on the intersection over union (IoU), with the k anchors closest to the object. …”
Get full text

VMMT-Net: A Dual-Branch Parallel Network Combining Visual State Space Model and Mix Transformer for Land–Sea Segmentation of Remote Sensing Images by Jiawei Wu, Zijian Liu, Zhipeng Zhu, Chunhui Song, Xinghui Wu, Haihua Xing

“…Specifically, the model achieves mean F1-scores of 98.48% (GF-HNCD) and 98.53% (BSD) and mean intersection-over-union values of 97.02% (GF-HNCD) and 97.11% (BSD). …”
Get full text

Risk prediction in dental implants with bone substitutes using a hybrid neutrosophic-logistic model: Managing uncertainty in clinical and biomechanical variables by Mónica Sofía Pallo Sarabia, Darwin Josué Cubi Masaquiza, Favio Nicholas Zúñiga Calderón, Luis Miguel Acosta Rueda

“…Thus, while the traditional logistic regression can predict success or failure based on pure facts and findings, this neutrosophic intersection model improves risk assessment when information is lacking or subjectively fluctuating. …”
Get full text

Integrative machine learning and bioinformatics analysis to identify cellular senescence-related genes and potential therapeutic targets in ulcerative colitis and colorectal cancer by Tianle Xue, Yunpeng Chen, Xiaomeng Li, Zhixiang Zhou, Qiyang Chen

“…Weighted gene co-expression network analysis (WGCNA) was employed to delineate modules significantly associated with UC and CRC, and the intersection of DEGs, key module genes, and senescence‐related genes from the CellAge database yielded 112 candidate genes. …”
Get full text

Silkworm segmentation based on encoder-decoder structure by Huimin Zhuang, Zicheng Liu, Jianping Dong, Dequan Guo, Guoquan Yuan, Bo Liu, Yu Liu

“…Experimental results show that the improved model achieved an Intersection over Union (IoU) of 80.74 % and a Dice similarity coefficient (Dice) of 88.96 %, with an inference time of only 5.93 ms per image. …”
Get full text