Multi-dimensional water quality indicators forecasting from IoT sensors: A tensor decomposition and multi-head self-attention mechanism. by Li Bo, Lv Junrui, Luo Xuegang

“…To overcome these limitations, we propose TGMHA (Tensor Decomposition and Gated Neural Network with Multi-Head Self-Attention), a novel hybrid model that integrates three key innovations: 1) Tensor-based Feature Extraction: We combine Standard Delay Embedding Transformation (SDET) with Tucker tensor decomposition to reconstruct raw time series into low-rank tensor representations, capturing latent spatio-temporal patterns while suppressing sensor noise. 2) Multi-Head Self-Attention for Inter-Indicator Dependencies: A multi-head self-attention mechanism explicitly models complex inter-dependencies among diverse water quality indicators (e.g., pH, dissolved oxygen, conductivity) via parallel feature subspace learning. 3) Efficient Long-Term Dependency Modeling: An encoder-decoder architecture with gated recurrent units (GRUs), optimized by adaptive rank selection, ensures efficient modeling of long-term dependencies without compromising computational performance. …”
Get full text

Research on foreign object intrusion detection in railway tracks based on MSL-YOLO by Hongxia Niu, Dingchao Feng, Tao Hou

“…This integration improves multi-scale feature representation and model efficiency. In addition, a Lightweight Shared Convolutional Detection Head (LSCD) is employed to replace the original head, reducing complexity while maintaining detection accuracy. …”
Get full text

Advancing Rice Disease Detection in Farmland with an Enhanced YOLOv11 Algorithm by Hongxin Teng, Yudi Wang, Wentao Li, Tao Chen, Qinghua Liu

“…Experiments on a rice disease dataset extracted from agricultural operation videos demonstrate that, compared to YOLOv11n, the algorithm improves mAP50 and mAP50-95 by 2.7% and 11.5%, respectively, while reducing the model parameters by 4.58 M and the computational load by 1.1 G. …”
Get full text

Automatic Classification of 5G Waveform-Modulated Signals Using Deep Residual Networks by Haithem Ben Chikha, Alaa Alaerjan, Randa Jabeur

“…To our knowledge, this is the first application of deep learning in the classification of such a diverse set of complex 5G waveforms. The proposed model combines the deep learning capabilities of DRNs for feature extraction with Principal Component Analysis (PCA) for dimensionality reduction and feature refinement. …”
Get full text

Transfer learning and single-polarized SAR image preprocessing for oil spill detection by Nataliia Kussul, Yevhenii Salii, Volodymyr Kuzin, Bohdan Yailymov, Andrii Shelestov

Get full text

Deuteron interaction with 124Sn nuclei at sub-barrier energies by Yu.N. Pavlenko, V.P. Verbytskyi, O.I. Rundel, O.V. Babak, O.K. Gorpinich, V.V. Ostashko, Yu.Ya. Karlyshev, O.D. Grygorenko, .A. Korzina, A.V. Stepaniuk, I. P. Dryapachenko, E. M. Mozhzhukhin

“…The measurements of cross sections for deuteron elastic scattering and (d,p) reaction on 124Sn nuclei have been performed with aim to study the features of sub-barrier deuteron interaction with heavy nuclei. …”
Get full text

Swincloud: a hybrid network for cloud detection in thermal infrared remote sensing images by Long Gao, Liyuan Li, Jianing Yu, Xiaoxuan Zhou, Lu Zou, Nan Fang, Xiaofeng Su, Fansheng Chen

“…Specifically, we augment the Swin Transformer's window attention module with a CNN-based parallel pathway to effectively model global-local information. We employ a feature fusion module before the final upsampling module in the decoder to better integrate low-level spatial information and high-level semantic information. …”
Get full text

Exploring the potential associations between single and mixed volatile compounds and preserved ratio impaired spirometry using five different approaches by Chenyuan Deng, Yu Jiang, Yuechun Lin, Hengrui Liang, Wei Wang, Ying Huang, Jianxing He

“…Additionally, the LightGBM model exhibited the highest predictive performance, with an AUC of 0.839. …”
Get full text

YOLO-Wheat: A More Accurate Real-Time Detection Algorithm for Wheat Pests by Yongkang Liu, Qinghao Wang, Qi Zheng, Yong Liu

“…YOLO-Wheat also performs better than other popular object detection algorithms (YOLOv5, YOLOv10, RT-DETR), and the model is successfully deployed for simple real-time detection. …”
Get full text

Non-Invasive Multiclass Diabetes Classification Using Breath Biomarkers and Machine Learning with Explainable AI by Alberto Gudiño-Ochoa, Julio Alberto García-Rodríguez, Raquel Ochoa-Ornelas, Eduardo Ruiz-Velazquez, Sofia Uribe-Toscano, Jorge Ivan Cuevas-Chávez, Daniel Alejandro Sánchez-Arias

“…To enhance classification performance, we introduced a novel biomarker, the alcohol-to-acetone ratio, through a feature engineering approach. …”
Get full text

Whole paternal uniparental disomy of chromosome 4 with a novel homozygous IDUA splicing variant, c.159‐9T>A, in a Chinese patient with mucopolysaccharidosis type I by Lulu Yan, Shuxia Ding, Yan He, Bin Fu, Changshui Chen, Haibo Li

“…Single‐nucleotide polymorphism (SNP) array was subsequently performed to confirm uniparental disomy (UPD). Minigene assay was performed to analyze the effect on splicing of mRNA. …”
Get full text

Bioinformatics-Based Management of Vitellogenin-like Protein’s Role in Pathogen Defense in <i>Nicotiana tabacum</i> L. by Hanan Maoz, Amir Elalouf, Amit Yaniv Rosenfeld

“…Through integrated computational approaches, we determined evolutionary relationships, and structural modeling of the selected protein was performed using different modeling software, followed by validation through multiple metrics, including stereochemical checks (Ramachandran plot), MolProbity analysis, and Z-scores. …”
Get full text

Future climate projections for South Aegean and Salzburg region based on statistical and dynamical downscaling - similarities and discrepancies by Marianne Bügelmayer-Blaschek, Kristofer Hasel, Darío Redolat, César Paradinas, Robert Monjo

“…Furthermore, the dynamical downscaling is performed down to convection permitting scale, therefore providing information on a 4 km ^2 grid and enabling the representation of local features, as is the case when training a statistical model with observations. …”
Get full text

Moxibustion ameliorates abnormal subchondral bone remodeling by promoting ACSL1-mediated autophagy to degrade NLRP3 in osteoarthritis by Xuelan Chen, Liping Fu, Yu Huang, Qing Liao, Binhua Zou, Lixia Yuan, Gang Liu

“…Methods Anterior cruciate ligament transection (ACLT) surgery was performed on mice to establish an OA model, and moxibustion intervention for 4 weeks. …”
Get full text

Functional representation of language play techniques in french advertising by Ekaterina Shapenko

“…The various techniques of the language game place special emphasis on one of the six components of the communicative act and therefore perform one of the linguistic functions. Language games seek to show the features of the product, presenting it in a favourable light (referential function), to convey positive emotions from the advertised product (emotive function), to cause interest, establish and maintain contact with the potential buyer (phatic function), to infl uence him or her, to motivate to purchase (conative function); in order to achieve this, advertising appeals to the shared cultural code (metalinguistic function). …”
Get full text

CD133 expression and the prognosis of colorectal cancer: a systematic review and meta-analysis. by Shicai Chen, Xinming Song, Zhihui Chen, Xinxin Li, Mingzhe Li, Haiying Liu, Jianchang Li

“…In this study, we aimed to evaluate the association between the expression of CD133 and clinicopathological features and the outcome of CRC patients by performing a meta-analysis.…”
Get full text

Advancing breast cancer diagnosis: Integrating deep transfer learning and U-Net segmentation for precise classification and delineation of ultrasound images by Divine Senanu Ametefe, Dah John, Abdulmalik Adozuka Aliu, George Dzorgbenya Ametefe, Aisha Hamid, Tumani Darboe

“…Among the CNN models, VGG19 achieved the best performance, with the highest weighted accuracy, precision, and recall. …”
Get full text

Spatial navigation entropy suggests allocentric dysfunction in PPPD by Felipe Faúndez, Camilo Arévalo-Romero, Karen Villarroel, Claudio Lavín, Kevin Alarcón, Kevin Alarcón, Gustavo Vial, Francisco Artus, Pablo Billeke, Paul H. Delano, Paul H. Delano, Paul H. Delano, Hayo A. Breinbauer, Hayo A. Breinbauer

“…All underwent a virtual Morris Water Maze (vMWM) task in both, non-immersive (NI) and virtual reality (VR) modalities, assessing spatial navigation performance, gaze behavior, and head kinematics.ResultsPPPD patients exhibited significantly worse navigation performance than both control groups across all metrics, with greater impairments in predominantly allocentric tasks. …”
Get full text

Integrated analysis of single-cell and bulk transcriptomic data reveals altered cellular composition and predictive cell types in ectopic endometriosis by Meihong Chen, Meihong Chen, Liqun Wang, Yuanting Chen, Ting Wang, Guanqun Jiang, Qi Chen, Qi Chen

“…Enriched signaling pathways were primarily associated with epithelial-mesenchymal transition (EMT), cell migration, and inflammatory responses. A random forest model, based on cell-type proportions, has been shown to achieve excellent diagnostic performance (AUC = 0.932), with MUC5B+ epithelial cells identified as the top predictive feature. …”
Get full text

The learning process of physical education lessons in education through virtual education by mahyar yarahmadi, Habib Honari, Meysam Shabaninia

“…In order to analyze the effective factors in the virtual education of physical education in Iran, the quantitative approach of interpretive structural modeling was used, and the MICMAC diagram was used for effectiveness and influence. …”
Get full text