Optimizing Class Imbalance in Facial Expression Recognition Using Dynamic Intra-Class Clustering by Qingdu Li, Keting Fu, Jian Liu, Yishan Li, Qinze Ren, Kang Xu, Junxiu Fu, Na Liu, Ye Yuan

“…By comparing with existing methods, we demonstrate that the DICC method can help the model achieve superior performance across various facial expression datasets. …”
Get full text

Published population pharmacokinetic models of mycophenolate sodium: a systematic review and external evaluation in a Chinese sample of renal transplant recipients by Tong Gao, Wen Xu, Xiao Li, Qie Guo, Donghua Liu, Xiaolei Zhang, Ping Leng, Jialin Sun

“…Model prediction performance was evaluated using three metrics: the goodness-of-fit method based on model prediction, prediction error test method and visual predictive checks method based on model simulation.ResultsA total of 186 drug concentration data of 31 patients in our hospital were collected, and 4 literature were retrieved, among which 1 were one-compartment models and 3 were two-compartment models. …”
Get full text

Wavelet Transform-Based 3D Landscape Design and Optimization for Digital Cities by Yang Chen, Xiaolin Wang, Chang Zhang

“…Finally, the simulation experimental results show that the proposed denoising method in this article can better retain the texture details in the images and the denoised images have better visual effects; the proposed information fusion model has higher accuracy compared with the traditional methods. …”
Get full text

Research on Early Fault Identification of Cables Based on the Fusion of MTF-GAF and Multi-Head Attention Mechanism Features by Hao Wu, Dan Tang, Yuan Cai, Chaowen Zheng

“…At the same time, the classification results of cable early faults are visualized using the t-distributed Stochastic Neighbor Embedding (t-SNE) method to visually observe the classification effect of the hybrid neural network. …”
Get full text

Large multimodal model for open vocabulary semantic segmentation of remote sensing images by Bing Liu, Xiaohui Chen, Anzhu Yu, Fan Feng, Jiaying Yue, Xuchu Yu

“…Inspired by the success of large multimodal models, we propose an open vocabulary segmentation method for remote sensing images. The proposed method uses the large multimodal model LLAVA and the vision large model SAM to achieve segmentation of open vocabulary. …”
Get full text

Multi-spectral fusion power equipment fault recognition based on prompt learning by YAO Yiyang, DU Zexing, ZHOU Guoqing, WANG Qing

“…Ablation experiments and visual results further validate the effectiveness of the method. …”
Get full text

Industrial Computed Tomography Image Denoising Network Based on Channel Attention Mechanism by Yu HE, Chengxiang WANG, Wei YU

“…Experimental results demonstrate that the proposed method significantly reduces the noise and effectively preserves edge details, outperforming other comparative methods in both visual quality and quantitative values.…”
Get full text

Primary retinotomy in the surgical treatment of complicated rhegmatogenous retinal detachment with severe proliferative vitreoretinopathy by D.O. Shkvorchenko, B.E. Malyugin, A.Yu. Kornienko, E.S. Khrisanfova, O.B. Klepinina

“…Material and methods. 12 patients (12 eyes) with the diagnosis of rhegmatogenous retinal detachment with severe proliferative retinopathy were operated using developed method of two-stage surgical treatment with a reduced volume of laser endophotocoagulation. …”
Get full text

NaDyNet: A toolbox for dynamic network analysis of naturalistic stimuliNaDyNet is open-source and freely available at by Junjie Yang, Zhe Hu, Junjing Li, Xiaolin Guo, Xiaowei Gao, Jiaxuan Liu, Yaling Wang, Zhiheng Qu, Wanchun Li, Zhongqi Li, Wanjing Li, Yien Huang, Jiali Chen, Hao Wen, Binke Yuan

“…To this end, we have developed a user-friendly graphical interface toolbox called NaDyNet (Naturalistic Dynamic Network Toolbox), which integrates existing dynamic brain network analysis methods and their improved versions. The main features of NaDyNet are: 1) extracting signals of interest from naturalistic fMRI signals; 2) incorporating six commonly used dynamic analysis methods and three static analysis methods; 3) improved versions of these dynamic methods by adopting inter-subject analysis to eliminate the effects of non-interest signals; 4) performing K-means clustering analysis to identify temporally reoccurring states along with their temporal and spatial attributes; 5) Visualization of spatiotemporal results. …”
Get full text

Digital Staining Algorithm for Multi-Domain Transformation of Unstained Images by Dong-Bum Kim, Jong-Ha Lee

“…These findings indicate that the proposed model achieves digital staining that closely replicates the conventional H&E staining method. Additionally, the visual assessment results revealed that the proposed method provides clearer differentiation between background and cytoplasmic boundaries. …”
Get full text

THE MATRIX OF COGNITIVE FILTERS AS A TOOL FOR THE ANALYSIS OF LINGUOCREATEMES IN MODERN ENGLISH DISCOURSE by Maria P. Taymour

“…Monomodal verbal and multimodal linguocreatemes (more than 18,000 units) were selected with a continuous sampling method from English-language Internet resources, visual and verbal corpora. …”
Get full text

Design support for product architecture considering supply chain (Evaluation model based on delivery capacity every transportation means) by Shuho YAMADA, Yuki KOMATSU, Masato INOUE

“…This paper newly proposes an evaluation model that incorporates the production capacity of each supplier, the delivery capacity of each transportation mode, and the on-time delivery rate with consideration of above component connections. The proposed method supports the selection of an architecture and its supply chain by visualizing the characteristics, such as the trade-off between evaluation indicators depending on the degree of modularization. …”
Get full text

Application of Multi-Objective Optimization for Path Planning and Scheduling: The Edible Oil Transportation System Framework by Chin S. Chen, Chia J. Lin, Yu J. Lin, Feng C. Lin

“…This study proposes a multi-objective optimization scheduling method for edible oil transportation in smart manufacturing, focusing on centralized control and addressing challenges such as complex pipelines and shared resource constraints. …”
Get full text

Transformer With Regularized Dual Modal Meta Metric Learning for Attribute-Image Person Re-Identification by Xianri Xu, Rongxian Xu

“…During training, data are initially divided into a single-modal support set with images and a dual-modal query set containing both attributes and images. The RDM3L method introduces an attribute-image transformer (AIT) as a novel feature extraction backbone, extending the visual transformer concept. …”
Get full text

Face super-resolution via iterative collaboration between multi-attention mechanism and landmark estimation by Chang-Teng Shi, Meng-Jun Li, Zhi Yong An

“…Specifically, in the 8 $$\times $$ × super-resolution experiment, the PSNR/SSIM/LPIPS on CelebA dataset is 27.68dB/ 0.8112/0.0866, outperforming existing state-of-the-art methods in terms of both accuracy and visual quality.…”
Get full text

Image instance segmentation based on diffusion model improved by step noisy by Hui Ma, Wanchun Sun, Shujia Li, Jinjun Zhang

“…Abstract In visual tasks, image instance segmentation has always been one of the most crucial core technologies in various fields, such as autonomous driving, and medical image analysis. …”
Get full text

Cluster Analysis Algorithm in the Analysis of College Students’ Mental Health Education by Wanting Zheng

“…In this work, a method of student behavior analysis and statistical tools are used to collect mental health data to find common features of different groups of students, in order to better visualize and investigate the mental health of these students on a scientific basis. …”
Get full text

Improved ADRC With ILC Control of a CCD-Based Tracking Loop for Fast Steering Mirror System by Quanrui Dong, Yongkai Liu, Yuliang Zhang, Shijie Gao, Tao Chen

“…This method has a very high application value in the field of visual axis stability, adaptive optics, and other fields.…”
Get full text

A Novel Qualitative and Quantitative Biofilm Assay Based on 3D Soft Tissue by Bodil Hakonen, Linnea K. Lönnberg, Eva Larkö, Kristina Blom

“…In conclusion, a novel method was developed combining visual rapid screening and quantitative evaluation of the antimicrobial activity in both tissue and devices. …”
Get full text

Design and Development of an Application for Recording Income and Expenditure Data at Darrel's Cake Shop Prabumulih City by Nadyah Seftivia, Muchlis, Nurmayanti

“…Waterfall development method. This application was built on the basis of the Visual Basic programming language. …”
Get full text