Uncertainty-Aware Active Meta-Learning for Few-Shot Text Classification by Sanghyun Seo, Hiskias Dingeto, Juntae Kim

“…By quantifying the prediction uncertainty of the model for the input data, we provide a loss function and learning strategy that can adjust the influence of the input data on the model’s learning. …”
Get full text

A theory and data-driven method for rapid bottom hole pressure calculation in UGS by Yang Li, Haiwei Guo, Xianfeng Gong, Naixin Lu, Kairui Zhang

“…Finally, by integrating the wellbore flow equations under different well conditions, using theoretical models to generate samples, and establishing a loss function guided by real samples, a theory and data-driven neural network model (TDDNN) has been successfully developed, achieving rapid and accurate calculation of bottom hole pressure. …”
Get full text

SDFA-Net: Synergistic Dynamic Fusion Architecture With Deformable Attention for UAV Small Target Detection by Yunsong Qi, Hengwei Cao

“…In feature processing, a Dynamic Sampling Feature Enhancement Module (Dysample-SDI) is innovatively constructed to realize the refinement of multiscale features; whereas the Shallow Detail Fusion Module (SDFM) is designed to enhance the characterization ability of shallow features. In terms of the optimization strategy, the composite bounding box regression loss function (Focaler-MPD-IOU) was proposed to integrate the advantages of the multi-dimensional positioning evaluation index. …”
Get full text

A Physics-Informed Neural Network Solution for Rheological Modeling of Cement Slurries by Huaixiao Yan, Jiannan Ding, Chengcheng Tao

“…The PINN-based approach incorporates physical laws into the loss function, offering mesh-free solutions with strong generalization ability. …”
Get full text

Pharmacological and therapeutic effects of natural products on liver regeneration-a comprehensive research by Chang Tian, Yuhan Wang, Ran Wang, Linxin Pan, Tao Xu

“…Abstract Liver regeneration (LR) refers to the physiological process by which hepatocytes undergo cellular proliferation to restore the structure and function of the liver following significant hepatocyte loss due to injury or partial hepatectomy (PH). …”
Get full text

Robust Optical and SAR Image Matching via Attention-Guided Structural Encoding and Confidence-Aware Filtering by Qi Kang, Jixian Zhang, Guoman Huang, Fei Liu

“…Additionally, a match-aware multi-task loss function jointly enforces spatial consistency, affine invariance, and structural coherence for end-to-end optimization. …”
Get full text

Relationship between periodontitis and systemic health conditions: a narrative review by Min-Young Kim, Eun-Kyoung Pang

“…Beyond its local effects, including gingival inflammation, periodontal pocket formation, and alveolar bone loss, periodontitis is associated with various systemic conditions. …”
Get full text

The modified asymmetric chondro-perichondrial island graft in type I tympanoplasty: A retrospective analysis of 784 patients by Fetih Furkan Şahin, İsa Kaya, Hakan Ceylan, Tayfun Kirazlı

“…Conclusion: Tympanoplasty offers a well-established surgical approach for restoring hearing function and preventing recurrent otorrhea. The asymmetric cartilage-perichondrium island graft design has emerged as a promising technique to achieve optimal functional and anatomical outcomes in tympanoplasty. …”
Get full text

A novel mechanism-guided residual network for accurate modelling of scroll expander under noisy and sparse data conditions by Xiaoshuang Lv, Xin Ma, Wei Peng, Ke Li, Chengdong Li

“…This framework is based on the architecture of residual network, where the mechanistic laws are embedded as constraints in the training of the network through an improved loss function. Then, a hybrid optimization algorithm is detailed, which can achieve efficient and accurate updating of the parameters of the network and mechanistic equations. …”
Get full text

Strategies to Improve the Efficiency of Transplantation with Mesenchymal Stem Cells for the Treatment of Ischemic Stroke: A Review of Recent Progress by Yongchang Li, Wei Zhong, Xiangqi Tang

“…Cerebral ischemia is a common global disease that is characterized by a loss of neurological function and a poor prognosis in many patients. …”
Get full text

Specifics of Epidural Compression Syndrome Surgery in Patients with Spinal Malignancy by O. I. Kit, D. E. Zakondyrin, E. E. Rostorguev, S. V. Yundin

“…The AA cohort revealed a statistical difference by intraoperative blood loss. A Karnofsky performance status was statistically improved post- vs. pre-surgery (p < 0.05) at no significant change of Frankel neurological function status (p > 0.05). …”
Get full text

REHABILITATION AND HEALTH-RELATED QUALITY OF LIFE AND FATIGUE IN PATIENTS WITH LUNG CANCER - EFFECTS OF EXERCISE by Morten Quist

“…Lung cancer is a leading cause of cancer-related deaths worldwide, with symptoms like dyspnea, chronic cough, fatigue, and weight loss signifcantly affecting patients' health-related quality of life (HRQoL). …”
Get full text

MicroRNA: sex steroids, hormonal carcinogenesis, hormonal sensitivity of tumor tissue by A. V. Malek, L. M. Bershtein

“…The prospects for development and introduction into clinical practice innovative methods of diagnosis, prediction and optimization of therapy of breast and prostate cancers are discussed as well.…”
Get full text

Incorporating Topological Priors Into Low-Dimensional Visualizations Through Topological Regularization by Edith Heiter, Robin Vandaele, Tijl de Bie, Yvan Saeys, Jefrey Lijffijt

“…We introduce a class of topological loss functions and demonstrate that optimizing an embedding loss together with one of these loss functions as a regularizer results in embeddings that consider not only local proximities but also the desired topological structure. …”
Get full text

Evaluating the efficacy of basiliximab versus no induction in low-immunological-risk kidney transplant recipients: a propensity score matched analysis by Dahao Zhang, Jiqiu Wen, Jianhui Dong, Rong Ma, Shijian Li, Jihua Wu, Ning Wen, Zhiying Lei, Haibin Li, Jun Yin, Xuyong Sun

“…Additionally, this group exhibited reduced infection-related hospitalizations (respiratory infections: 7.32 vs. 29.1%, p = 0.008) and hematological complications (thrombocytopenia: 0.00% vs. 12.8%, p = 0.014). Mortality and graft loss rates were similar between groups.Conclusion In low-immunological-risk KTRs, no induction therapy achieves comparable AR prevention and renal function outcomes to BSX while reducing infection and hematological complications. …”
Get full text

Decreasing cytosolic translation is beneficial to yeast and human Tafazzin-deficient cells by Maxence de Taffin de Tilques, Jean-Paul Lasserre, François Godard, Elodie Sardin, Marine Bouhier, Marina Le Guedard, Roza Kucharczyk, Patrice X. Petit, Eric Testet, Jean-Paul di Rago, Déborah Tribouillard-Tanvier

“…Loss-of-function mutations in the TAZ gene are responsible for the Barth syndrome (BTHS), a rare X-linked cardiomyopathy, presumably because of a diminished OXPHOS capacity. …”
Get full text

Diseño de un Software de Intermediación de Comunicación para Sistemas Distribuidos de Tiempo Real Críticos en Java by Daniel Tejera, Alejandro Alonso, Miguel A. de Miguel

“…The JRMP protocol was modified to include two phases, non-functional parameters, and message size optimizations. …”
Get full text

Mussel-inspired superhydrophobic coating via self-assembled polydopamine/SiO2 for enhancing the durability of marine concrete by Jiang Du, Kexin Zhang, Jianting Zhou, Xiuman Wang, Zhongya Zhang, Yang Zou, Dunyi Liu, Soroush Mahjoubi, Jun Yang

“…Characterization confirms uniform nanospheres incorporation and successful PFDT functionalization. Compared to uncoated concrete, the coating reduces carbonation depth by > 70 %, suppresses ice accretion by 99 %, and lowers steel corrosion mass loss by 87.5 %. …”
Get full text

SDDGRNets: Level–Level Semantically Decomposed Dynamic Graph Reasoning Network for Remote Sensing Semantic Change Detection by Zhuli Xie, Gang Wan, Yunxia Yin, Guangde Sun, Dongdong Bu

“…In addition, the edge constraint module is used to constrain boundary pixels and reduce semantic ambiguity. The weighted loss function supervises and optimizes each module separately to enable the network to acquire the optimal feature representation. …”
Get full text

Prox-STA-LSTM: A Sparse Representation for the Attention-Based LSTM Networks for Industrial Soft Sensor Development by Yurun Wang, Yi Huang, Dongsheng Chen, Longyan Wang, Lingjian Ye, Feifan Shen

“…The <inline-formula> <tex-math notation="LaTeX">$\ell _{1}$ </tex-math></inline-formula>-regularization, which is a popular means to promote sparsity, is introduced into the loss function of the STA-LSTM. The <inline-formula> <tex-math notation="LaTeX">$\ell _{1}$ </tex-math></inline-formula>-regularized formulation is a non-smooth optimization problem, which cannot be well solved by common gradient descent approaches. …”
Get full text