Building consistency in explanations: Harmonizing CNN attributions for satellite-based land cover classification by Timo T. Stomberg, Lennart A. Reißner, Martin G. Schultz, Ribana Roscher

“…However, a key challenge is that different attribution methods often produce different outcomes undermining trust in their results. …”
Get full text

Estimating Subsurface Geostatistical Properties from GPR Reflection Data Using a Supervised Deep Learning Approach by Yu Liu, James Irving, Klaus Holliger

“…Tests on a wide range of realistic synthetic GPR data generated using a finite-difference time-domain (FDTD) solution of Maxwell’s equations, as well as a comparison with the results of the traditional Monte Carlo approach on a pertinent field dataset, confirm the viability of the proposed method, even in the presence of significant levels of data noise. …”
Get full text

Monitoring of vegetation chlorophyll content in photovoltaic areas using UAV-mounted multispectral imaging by Ming Li, Weiyi Wang, Haoran Li, Zekun Yang, Jianjun Li

“…The results indicated that both vegetation indices and texture features exhibited significant correlations with chlorophyll content, with the strongest correlation observed between the green normalized difference vegetation index (GNDVI) and the NIR_Mean (Pearson coefficients of 0.82 and 0.65, respectively). …”
Get full text

Modeling Terrestrial Net Ecosystem Exchange Based on Deep Learning in China by Zeqiang Chen, Lei Wu, Nengcheng Chen, Ke Wan

“…The results show that the normalized difference vegetation index, the enhanced vegetation index, and the leaf area index play a dominant role at most sites. …”
Get full text

Development and validation of CNN-MLP models for predicting anti-VEGF therapy outcomes in diabetic macular edema by Xiangjie Leng, Ruijie Shi, Zhaorui Xu, Hai Zhang, Wenxuan Xu, Keyin Zhu, Xuejing Lu

“…In this study, both the training set and the validation set exhibited a consistent decreasing trend in MAE, MSE, and MSLE. No statistical difference was found between the actual and predicted values in all clinical indicators. …”
Get full text

Force output in giant-slalom skiing: A practical model of force application effectiveness. by Matt R Cross, Clément Delhaye, Jean-Benoit Morin, Maximilien Bowen, Nicolas Coulmy, Frédérique Hintzy, Pierre Samozino

“…Ski athletes (N = 15) were equipped with ski-mounted force plates and a global navigation satellite system to compute the following variables over 14 turns: path length (L), velocity normalized energy dissipation [Δemech/vin], radial force [Fr], total force (both limbs [Ftot], the outside limb, and the difference between limbs), and a ratio of force application (RF = Fr/Ftot). …”
Get full text

Adoption of Compound Echocardiography under Artificial Intelligence Algorithm in Fetal Congenial Heart Disease Screening during Gestation by Guowei Han, Tianliang Jin, Li Zhang, Chen Guo, Hua Gui, Risu Na, Xuesong Wang, Haihua Bai

“…The abnormal distribution of fetal heart and the difference of cardiac Z score between group II and group I were analyzed, and the diagnostic value of group C and group W for CHD was compared. …”
Get full text

WCMU-net: An Effective Method for Reducing the Impact of Speckle Noise in SAR Image Change Detection by Yu Duan, Kaimin Sun, Wangbin Li, Jinjiang Wei, Song Gao, Yingjiao Tan, Wanghui Zhou, Jun Liu, Junyi Liu

“…For C-band SAR images, different satellite imaging and ground object reflections can produce varying levels of noise, necessitating a network design adaptable to different noise levels. …”
Get full text

Deep learning on medical image analysis by Jiaji Wang, Shuihua Wang, Yudong Zhang

“…The paper covers the structure of CNN and its advances and explores the different types of transfer learning strategies as well as classic pre‐trained models. …”
Get full text

Computer Vision-Based Lane Detection and Detection of Vehicle, Traffic Sign, Pedestrian Using YOLOv5 by Raşit Köker, Osman Eldoğan, Gülyeter Öztürk

“…The right and left lanes within the driving area of the vehicle are identified, and the drivable area of the vehicle is highlighted with a different color. To detect traffic signs, pedestrians, cars, and bicycles around the vehicle, we utilize the YOLOv5 model, which is based on Convolutional Neural Networks. …”
Get full text

Dynamic Cascade Detector for Storage Tanks and Ships in Optical Remote Sensing Images by Tong Wang, Bingxin Liu, Peng Chen

“…Some studies have shown that different stages should have different Intersections of Union (IoU) thresholds to distinguish positive and negative samples because each stage has different IoU distributions. …”
Get full text

A method for identifying gully-type debris flows based on adaptive multi-scale feature extraction by Qiuyu Liu, Ting Wang, Zhijie Zheng, Baoyun Wang

“…Next, during the multi-scale feature map output stage, feature maps from different scales are fused by adaptively updating their weights. …”
Get full text

An Intrusion Detection System over the IoT Data Streams Using eXplainable Artificial Intelligence (XAI) by Adel Alabbadi, Fuad Bajaber

“…DL models are needed to train enormous amounts of data and produce promising results. Three different DL models, i.e., customized 1-D convolutional neural networks (1-D CNNs), deep neural networks (DNNs), and pre-trained model TabNet, are proposed. …”
Get full text

Flexible integration of spatial and expression information for precise spot embedding via ZINB-based graph-enhanced autoencoder by Jiacheng Leng, Jiating Yu, Ling-Yun Wu, Hongyang Chen

“…However, most domain identification methods do not adequately integrate expression and spatial information to flexibly identify different types of domains. To address these issues, we introduce Spot2vector, a computational framework that leverages a graph-enhanced autoencoder integrating zero-inflated negative binomial distribution modeling, combining both graph convolutional networks and graph attention networks to extract the latent embeddings of spots. …”
Get full text

Connected and automated vehicle control at unsignalized intersection based on deep reinforcement learning in vehicle-to-infrastructure environment by Juan Chen, Vijayan Sugumaran, Peiyan Qu

“…The proposed method is validated in a simulation environment with different traffic flow and market penetration under the mixed traffic conditions of automated vehicles and human-driving vehicles. …”
Get full text

Vocal performance evaluation of the intelligent note recognition method based on deep learning by Dongyun Chang

“…The accuracy of the model under different feature inputs is compared. The results indicate that different models show obvious differences in F-value, accuracy, precision, and recall. …”
Get full text

Intelligent Fault Diagnosis of Inter-Turn Short Circuit Faults in PMSMs for Agricultural Machinery Based on Data Fusion and Bayesian Optimization by Mingsheng Wang, Wuxuan Lai, Hong Zhang, Yang Liu, Qiang Song

“…Firstly, synchronizing data from different signals extracted by different devices presents a significant challenge. …”
Get full text

A Voxelized Transformer-Based Neural Network for 3D Reconstruction From Multi-Energy SEM Backscattered Electrons by Caizhi Zheng, Ronghan Hong, Hao-Jie Hu, Qing Huo Liu

“…Two numerical cases are used to respectively verify the inversion performance of the proposed method for different depths and different feature scales. The reconstruction results show that the proposed BSE-VoxNets can reach a resolution of 2 nm in both the horizontal and vertical dimensions.…”
Get full text

Impact of large language models and vision deep learning models in predicting neoadjuvant rectal score for rectal cancer treated with neoadjuvant chemoradiation by Hyun Bin Kim, Hong Qi Tan, Wen Long Nei, Ying Cong Ryan Shea Tan, Yiyu Cai, Fuqiang Wang

“…For CT scans, two different approaches with convolutional neural network were utilized to tackle the 3D scan entirely or tackle it slice by slice. …”
Get full text

Automatic Quantification of Atmospheric Turbulence Intensity in Space-Time Domain by Damián Gulich, Myrian Tebaldi, Daniel Sierra-Sosa

“…These representations are then fed into a Convolutional Neural Network for classification. This network effectively learns to discriminate between different turbulence regimes based on the spatio-temporal features extracted from a real-world experiment captured in video slices.…”
Get full text