Non-convex optimization with using positive-negative moment estimation and its application for skin cancer recognition with a neural network by P.A. Lyakhov, U.A. Lyakhova, R.I. Abdulkadirov

“…These approaches allow the loss function to more accurately converge in the neighborhood of the global minimum in a smaller number of iterations. …”
Get full text

DDD++: Exploiting Density map consistency for Deep Depth estimation in indoor environments by Giovanni Pintore, Marco Agus, Alberto Signoroni, Enrico Gobbetti

“…To further enhance structural consistency, we introduce a novel loss function that assesses density map consistency by projecting points from the predicted depth map onto a horizontal plane and a cylindrical proxy. …”
Get full text

Design of Real-Time Demodulation for FBG Sensing Signals Based on All-Dielectric Subwavelength Gratings Edge Filters by Jingliang Lin, Ping Tang, Kaihao Chen, Jiancai Xue, Ziming Meng, Jinyun Zhou

“…The designed edge-filter-based demodulation system incorporates dual single-point detectors to simultaneously monitor the transmitted and reflected signals. …”
Get full text

Control of 3′ splice site selection by the yeast splicing factor Fyv6 by Katherine A Senn, Karli A Lipinski, Natalie J Zeps, Amory F Griffin, Max E Wilkinson, Aaron A Hoskins

“…These results show that loss of Fyv6 results in activation of non-consensus, branch point (BP) proximal 3ʹ SS transcriptome-wide. …”
Get full text

Neural Field-Based Space Target 3D Reconstruction with Predicted Depth Priors by Tao Fu, Yu Zhou, Ying Wang, Jian Liu, Yamin Zhang, Qinglei Kong, Bo Chen

“…To minimize excessive noise from unseen viewpoints, we also incorporate a confident modeling mechanism with relative depth ranking loss functions. Experimental results demonstrate that the proposed method achieves superior 3D reconstruction quality under sparse input, outperforming traditional NeRF and DS-NeRF models in terms of perceptual quality and geometric accuracy.…”
Get full text

Democracy Adrift and the Trajectories of the Political Parties in São Tomé and Príncipe by NASCIMENTO Аugusto

“…Factors undermining democracy are highlighted, for example, the growing political and social entropy, discouragement and the feeling of loss of determination of individual and collective futures, and even temptations of authoritarian drifts. …”
Get full text

A probabilistic approach for building disease phenotypes across electronic health records by David Vidmar, Jessica De Freitas, Will Thompson, John M. Pfeifer, Brandon K. Fornwalt, Noah Zimmerman, Riccardo Miotto, Ruijun Chen

“…Compared to output scores from Snorkel OSS, LEVI provides better probabilistic performance (expected calibration error of 0.04 vs. 0.12), ROC AUC estimates (interval score [loss] of 0.03 vs. 0.10), and operating point selection (equal-cost net benefit of 0.18 vs. 0.15). …”
Get full text

Failure behavior of tantalum electrolytic capacitors under extreme dynamic impact: Mechanical–electrical model and microscale characterization by Xiangyu Han, Da Yu, Cheng Chen, Keren Dai

“…The latter are high-value ammunition used to strike strategic targets, and precision in their blast point is ensured through the use of penetration fuzes as control systems. …”
Get full text

Techno-economic analysis of cement-based composite mortars for energy-efficient buildings by Jeanne Leclerc, Abdul Wasy Zia

“…Their performance is assessed as a function of percentage sand replacement, thermal conductivity, compressive strength, density, and cost. …”
Get full text

DRR-YOLO: A Study of Small Target Multi-Modal Defect Detection for Multiple Types of Insulators Based on Large Convolution Kernel by Mingming Hu, Jun Liu, Junfu Liu

“…Firstly, a new module DRR is proposed based on Dilated Re-param Block (DRB) and Dilation-wise Residual (DWR), which is combined with the C2f module of the YOLOv8 model to enhance the model’s detection effect for targets at different scales; Secondly, the Large Separable Kernel Attention SPPF (LSPPF) module is proposed to replace the SPPF in the original model, which enables the model to better preserve the feature information of the target while streamlining the structure; In addition, the advantages of MPDIoU and Inner-IoU are combined, and the loss function of the original model is replaced with Inner-MPDIoU. …”
Get full text

Industrial data-driven machine learning soft sensing for optimal operation of etching tools by Feiyang Ou, Henrik Wang, Chao Zhang, Matthew Tom, Sthitie Bom, James F. Davis, Panagiotis D. Christofides

“…Two types of models with different loss functions are tested to compare the effects of the Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE) loss functions on model performance. …”
Get full text

Intestinal Fut2 deficiency exacerbated alcohol‐related liver disease by disrupting nicotinamide metabolism by Liuying Chen, Zhongwei Yin, Luorui Shang, Hang Yuan, Wenkang Gao, Shuhan Wang, Shuyan Wang, Xiaohua Hou, Shenglan Yang, Huikuan Chu

“…Conclusion These findings reveal a gut microbiota–Fut2–pncA axis that modulates alcoholic liver injury in mice, which may offer insights into microbial contributions to alcoholic liver disease in people. Key points Loss of intestinal epithelial fucosylation exacerbates alcohol‐related liver injuries. …”
Get full text

ISPANet: A Pyramid Self-Attention Network for Single-Frame High-Resolution Infrared Small Target Detection With a Large-Scale Dataset SHR-IRST by Wenjing Wang, Chengwang Xiao, Haofeng Dou, Ruixiang Liang, Huaibin Yuan, Guanghui Zhao, Zhiwei Chen, Yuhang Huang

“…Finally, we propose a new loss function Focal Soft-IoU (F-SIoU). F-SIoU loss makes the network more concerned about the hard positive examples. …”
Get full text

Treatment-related toxicity, utility and patient-reported outcomes of head and neck cancer patients treated with proton therapy: A longitudinal study by Yi Hsuan Chen, Michiel Kroesen, Mischa Hoogeman, Matthijs Versteegh, Carin Uyl-de Groot, Hedwig M. Blommestein

“…At the end of PT, the patients’ utility decreased significantly (0.12 points) compared to the baseline. The loss in utility was recovered after six months and a further improvement was seen one year after the treatment. …”
Get full text

Enhancing Drone Detection via Transformer Neural Network and Positive–Negative Momentum Optimizers by Pavel Lyakhov, Denis Butusov, Vadim Pismennyy, Ruslan Abdulkadirov, Nikolay Nagornov, Valerii Ostrovskii, Diana Kalita

“…The developed algorithms for training NN architectures improved the accuracy of drone detection by achieving the global extremum of the loss function in fewer epochs using positive–negative pulse-based optimization algorithms. …”
Get full text

Defective glutamate and K+ clearance by cortical astrocytes in familial hemiplegic migraine type 2 by Clizia Capuani, Marcello Melone, Angelita Tottene, Luca Bragina, Giovanna Crivellaro, Mirko Santello, Giorgio Casari, Fiorenzo Conti, Daniela Pietrobon

“…A subtype of migraine with aura (familial hemiplegic migraine type 2: FHM2) is caused by loss‐of‐function mutations in α2 Na+,K+ ATPase (α2 NKA), an isoform almost exclusively expressed in astrocytes in adult brain. …”
Get full text

YOLO-SAATD: An efficient SAR airport and aircraft target detector by Daobin Ma, Zhanhong Lu, Zixuan Dai, Yangyue Wei, Li Yang, Haimiao Hu, Wenqiao Zhang, Dongping Zhang

“…Fine granularity: A ”ScaleNimble Neck” integrates feature reshaping and scale-aware aggregation to enhance detail detection and feature capture in multi-scale SAR images. 3. Precision: Wise-IoU loss function is used to optimize bounding box localization and enhance detection accuracy. …”
Get full text

Bifurcation in the healing or fibrotic response in a network model of fibrosis: role of the initial injury structure by Ethan Israel, Joseph K. Hall, Yuqing Deng, Jason H. T. Bates, Béla Suki

“…IntroductionPulmonary fibrosis (PF) is a heterogeneous progressive lung disease characterized by excessive extracellular matrix (ECM) deposition and cross-linking, leading to irreversible tissue stiffening and loss of function. Previous evidence suggests that percolation behavior, where increasing local stiffness facilitates the emergence of stiff regions that span the tissue, underlies the stiffening of the ECM and drives the irreversible mechanical dysfunction. …”
Get full text

YOLO-BOS: An Emerging Approach for Vehicle Detection with a Novel BRSA Mechanism by Liang Zhao, Lulu Fu, Xin Jia, Beibei Cui, Xianchao Zhu, Junwei Jin

“…Lastly, we introduce Shape-IOU, a new loss function that significantly enhances the accuracy and robustness of detection results for vehicles of varying sizes. …”
Get full text

MAHGA: Multi-Aspect Heterogeneous Graph Analysis for Harmful Speech Detection on Social Networks by Ryo Yoshida, Soh Yoshida, Mitsuji Muneyasu

“…Furthermore, a correlation-based loss function maintains the independence of learned features, enhancing the model’s ability to recognize nuanced harmful content. …”
Get full text