The Surface Morphology of CdTe Thin Films Obtained by Open Evaporation in Vacuum by Y.P.В Saliy, L.I.В Nykyruy, R.S.В Yavorskyi, S.Adamiak

“…The different thicknesses CdTe thin films were obtained by method of open evaporation in vacuum on glass and silicon (100) substrates. …”
Get full text

Beyond Granularity: Enhancing Continuous Sign Language Recognition with Granularity-Aware Feature Fusion and Attention Optimization by Yao Du, Taiying Peng, Xiaohui Hu

“…We introduce a feature fusion method for integrating visual features of disparate granularities and refine the metric of attention to enhance the Transformer’s comprehension of video content. …”
Get full text

Offline reinforcement learning combining generalized advantage estimation and modality decomposition interaction by Kaixin Jin, Lifang Wang, Xiwen Wang, Wei Guo, Qiang Han, Xiaoqing Yu

“…However, existing Transformer-based methods face limitations, such as ineffective trajectory stitching and the neglect of deep interactions within and between multimodal information in trajectories. …”
Get full text

Workflow Detection with Improved Phase Discriminability by ZHANG, M., HU, H., LI, Z.

“…Specifically, temporal self-attention is firstly designed to learn the relationship between different positions of feature sequence. Then, multi-scale Transformer is introduced to encode pyramid features, which fuses multiple context cues for discriminative feature representation. …”
Get full text

Crop field extraction from high resolution remote sensing images based on semantic edges and spatial structure map by Liegang Xia, Ruiyan Liu, Yishao Su, Shulin Mi, Dezhi Yang, Jun Chen, Zhanfeng Shen

“…This method relies on good connectivity to repair fragmented edges that may appear in semantic edge detection. …”
Get full text

MCGFE-CR: Cloud Removal With Multiscale Context-Guided Feature Enhancement Network by Qiang Bie, Xiaojie Su

“…The experimental results demonstrate that this method has higher spectral fidelity and richer structural texture information in reconstructing various types of ground information and optical images with different cloud coverage areas.…”
Get full text

Numerous Multi-Wave Solutions of the Time-Fractional Boussinesq-like System via a Variant of the Extended Simple Equations Method (SEsM) by Elena V. Nikolova, Mila Chilikova-Lubomirova

“…The key developments over the original SEsM in the proposed analytical framework include the following: (1) an extension of the original SEsM by constructing the solutions of the studied FNPDEs as complex composite functions which combine two single composite functions, comprising the power series of the solutions of two simple equations or two special functions with different independent variables (different wave coordinates); (2) an extension of the scope of fractional wave transformations used to reduce the studied FNPDEs to different types of ODEs, depending on the physical nature of the studied FNPDEs and the type of selected simple equations. …”
Get full text

Fabrication of superparamagnetic adsorbent based on layered double hydroxide as effective nanoadsorbent for removal of Sb (III) from water samples by Rokhsareh Motallebi, Ali Moghimi, Hamidreza Shahbazi, Hakim Faraji

“…Abstract In this study, the superparamagnetic adsorbent as Fe@Mg‐Al LDH was synthesised by different methods with two steps for the removal of heavy metal ions from water samples. …”
Get full text

Public preferences for health and non-health outcomes of Universal Basic Income and alternative income-based policies: A mixed-method feasibility study by Neil McHugh, David Bomark, Rachel Baker, Verity Watson, Neil Craig, Ruth Lightbody, Clare Bambra, Victoria McGowan, Cam Donaldson

“…All methods adopted a socially inclusive perspective. …”
Get full text

Slipping Trend Prediction Based on Improved Informer by Jingchun Huang, Sheng He, Haoxiang Feng, Yongjiang Yu

“…The TCU records time series data with a step length of 1 s. The transformer-based Informer algorithm performs well in time series prediction and analysis. …”
Get full text

DCAI: a dual cross-attention integration framework for benign-malignant classification of pulmonary nodules by Shuling Wang, Suixue Wang, Rongdao Sun

“…These features are encoded using Transformer models, and then a dual cross-attention module is proposed to dynamically align and interact with the complementary information between the different modalities. …”
Get full text

BLTTNet: feature fusion based on BiLSTM-Transfomer-TCN for prediction of remaining useful life of aircraft engines by Yixu Yang, Xiaoying Su, Chaoyong Wang, Hongxi Liu, Kunhao Fu, Tao Xie, Zishuo Zhang

“…Specifically, DCEFormer with a Transformer structure enhances the allocation of feature weights by processing the contributions of different features in both the time step dimension and the sensor dimension, thereby improving the accuracy of RUL prediction for mechanical equipment. …”
Get full text

Boundary Value Problems on a Star Thermal Graph and their Solutions by L.A. Alexeyeva, A.N. Dadayeva, D.A. Prikazchikov, N.Zh. Ainakeyeva

“…Based on the generalized function method, a unified technique for solving boundary value problems on such graphs is developed. …”
Get full text

LEM-Detector: An Efficient Detector for Photovoltaic Panel Defect Detection by Xinwen Zhou, Xiang Li, Wenfu Huang, Ran Wei

“…To address these challenges, this paper proposes the LEM-Detector, an efficient end-to-end photovoltaic panel defect detector based on the transformer architecture. To address the low detection accuracy for Crack and Star crack defects and the imbalanced dataset, a novel data augmentation method, the Linear Feature Augmentation (LFA) module, specifically designed for linear features, is introduced. …”
Get full text

Evaluation of Soil and Water Ecological Security for Mining Cities in Anhui Province Based on VIKOR Model by He Gang, Hou Xiaoyu, Wang Xiaodong, Zhao Shuhang

“…The multiplicative normalization method was used to combine the optimized G1 and CRITIC weighting methods to achieve subjective and objective weight assignment. …”
Get full text

Multi-Head Graph Attention Adversarial Autoencoder Network for Unsupervised Change Detection Using Heterogeneous Remote Sensing Images by Meng Jia, Xiangyu Lou, Zhiqiang Zhao, Xiaofeng Lu, Zhenghao Shi

“…This bilateral structure mitigates the information loss associated with one-way mappings, enabling more accurate style transformation and reducing false change detections caused by sensor heterogeneity, which represents a key advantage over existing unidirectional methods. …”
Get full text

Image Classification Model Based on Contrastive Learning With Dynamic Adaptive Loss by Quandeng Gou, Jingxuan Zhou, Zi Li, Fangrui Zhang, Yuheng Ren

“…Most existing mainstream image classification models use the Convolutional Neural Network (CNN), the Transformer, or a combination of both as the backbone. …”
Get full text

Enhanced brain tumor diagnosis using combined deep learning models and weight selection technique by Karim Gasmi, Najib Ben Aoun, Najib Ben Aoun, Khalaf Alsalem, Ibtihel Ben Ltaifa, Ibrahim Alrashdi, Lassaad Ben Ammar, Manel Mrabet, Abdulaziz Shehab

“…Brain tumor classification is a critical task in medical imaging, as accurate diagnosis directly influences treatment planning and patient outcomes. Traditional methods often fall short in achieving the required precision due to the complex and heterogeneous nature of brain tumors. …”
Get full text

NMT-translation – basic models, quality assessment by I. A. Borunov

“…In order to achieve this goal, the following tasks were formulated: to review and analyze the main NMT models, including Seq2Seq, Transformer, BERT and their variations, in order to identify their peculiarities and applicability to the translation of different types of texts; to study and evaluate the quality of translation made with the help of modern NMT systems; to carry out a comparative analysis of the translation of legal texts using the methods of contextual analysis, structural-semantic and comparative-comparative analysis; to determine the limitations of the existing NMT models; to identify the advantages and limitations of the existing NMT models for the translation of legal texts. …”
Get full text

Predicting bone metastasis risk of colorectal tumors using radiomics and deep learning ViT model by Guanfeng Chen, Wenxi Liu, Yingmin Lin, Jie Zhang, Risheng Huang, Deqiu Ye, Jing Huang, Jieyun Chen

“…Materials and methods: We conducted a retrospective analysis of 155 colorectal cancer patients, including 81 with bone metastasis and 74 without. …”
Get full text