Mechanism of rock burst vertical damage induced by layered crack structures of the steeply inclined extremely thick coal seams by Taoping Zhong, Zhenlei Li, Dazhao Song, Majid Khan, Xueqiu He, Zemin Chen, Chao Zhou, Xudong Liu, Panfei Feng

Get full text

Contrastive learning-driven framework for neuron morphology classification by Yikang Jiang, Hao Tian, Quanbing Zhang

“…To address issues of data scarcity and imbalance, we designed a tailored data augmentation strategy that simulates diverse morphological variations, enhancing model robustness. Experiments conducted on three public datasets—BIL, JML, and ACT—demonstrate that PRT-net achieves classification accuracies of 78.45%, 67.11%, and 58.95%, respectively, significantly surpassing existing state-of-the-art methods. …”
Get full text

Quantum-enhanced intelligent system for personalized adaptive radiotherapy dose estimation by Radhey Lal, Rajiv Kumar Singh, Dinesh Kumar Nishad, Saifullah Khalid

“…Quantum-enhanced Monte Carlo simulations, employing algorithms such as Harrow-Hassidim-Lloyd (HHL) and Variational Quantum Eigensolver (VQE), achieve computational speedups of 8–15 times compared to classical methods while maintaining high accuracy. …”
Get full text

One-Shot Learning from Prototype Stock Keeping Unit Images by Aleksandra Kowalczyk, Grzegorz Sarwas

“…Traditional methods require large supervised datasets to train deep neural networks, which can be costly and impractical. …”
Get full text

22 Advancing clinical trial reporting and AI integration: Optimizing protocol data extraction using LLMs and regulatory best practices by Ramya Sri Baluguri, Nicholas Anderson

“…We developed a pilot web-based architecture to capture variations in categorization, labeling, and reporting style and compared generated extraction data. …”
Get full text

Automated Detection of Recent Mud Extrusions Using UAV Imagery and Deep Learning: A Comparative Analysis of Traditional and CNN-Based Approaches by M. Guastella, M. Guastella, A. Pisciotta, R. Martorana, A. D’Alessandro

“…This strategy introduced controlled and random variations to simulate real-world imaging conditions, such as varying viewpoints and lighting, ensuring the models generalization, moreover it also minimized data leakage by presenting distinct image variations throughout training. …”
Get full text

SAT: Spectrum-Adaptive Transformer with Spatial Awareness for UAV Target Tracking by Wanying Xu, Haijiang Sun, Shuai Wang

“…Additionally, we introduce a spectrum-adaptive attention module, allowing the network to adapt to UAV targets with dynamic scale variations. Experimental results demonstrate that our algorithm achieves a 9.4% increase in success rate and a 12.1% improvement in precision compared to baseline methods on the UAV target datasets, demonstrating superior performance in handling scale variations and complex tracking scenarios. …”
Get full text

Free Drying Shrinkage of Wood: A Review by Mingyang Zhao, Lin Yang

Get full text

Simultaneous Incomplete Traffic Data Imputation and Similarity Pattern Discovery with Bayesian Nonparametric Tensor Decomposition by Yaxiong Han, Zhaocheng He

“…Furthermore, we develop an efficient variational inference algorithm to learn the model. …”
Get full text

CVNet: Lightweight Cross-View Vehicle ReID with Multi-Scale Localization by Wenji Yin, Baixuan Han, Yueping Peng, Hexiang Hao, Zecong Ye, Yu Shen, Yanjun Cai, Wenchao Kang

“…This design effectively captures both unique and shared cross-view features, ensuring efficient and robust feature representation. We also release a new CVPair v1.0 dataset, the first benchmark for cross-view ReID, containing 14,969 images of 894 vehicle identities, offering results of traditional and lightweight methods. …”
Get full text

Foundation neural-networks quantum states as a unified Ansatz for multiple hamiltonians by Riccardo Rende, Luciano Loris Viteritti, Federico Becca, Antonello Scardicchio, Alessandro Laio, Giuseppe Carleo

“…Unlike specialized architectures tailored for individual Hamiltonians, FNQS can generalize to physical Hamiltonians beyond those encountered during training, offering a unified framework adaptable to various quantum systems and tasks. FNQS enable the efficient estimation of quantities that are traditionally challenging or computationally intensive to calculate using conventional methods, particularly disorder-averaged observables. …”
Get full text

YOLO-SR: An optimized convolutional architecture for robust ship detection in SAR Imagery by Chi Kien Ha, Hoanh Nguyen, Vu Duc Van

“…Abstarct: Accurate and efficient ship detection in synthetic aperture radar (SAR) imagery remains a challenging task due to speckle noise, scale variations, and the low contrast of small vessels. …”
Get full text

Green System Effects on Energy Environmental Sustainability of Urban Built-Up Areas by Carla Balocco, Giacomo Pierucci, Cristina Piselli

“…This work presents a methodological approach for the assessment of the combined effects of air enthalpy variations due to the presence of green systems and building thermodynamics. …”
Get full text

Least-squares Smoothed Shape Functions for Constructing Field-Consistent Timoshenko Beam Elements by Foek Tjong Wong, Henokh G. Tjahyono, Sugiyono Hartono, Timothy A. Setiabudi

“…The LSS shape function approach offers a practical and efficient alternative for achieving field consistency in Timoshenko beam elements, with potential applications in enhanced finite element methods (FEMs) such as isogeometric FEM and Kriging-based FEM. …”
Get full text

Análisis de películas biopoliméricas de almidón para potencial aplicación en optoelectrónica. by Hariana Farfán Benavides, Karol Roa Bohórquez, Raúl Sánchez Alarcón, Ricardo Paredes Roa

“…Research into energy-efficient materials, such as perovskites, has increased due to their characteristics, low cost, and variety of production methods, which allow for the development of optoelectronic devices. …”
Get full text

Implementation of a Breast Phantom with Acoustic Properties for Ultrasonic Thermometry by Ruth Valeria Acero Mendoza, Ivonne Bazán, Alfredo Ramírez-García

“…Early detection is critical for improving patient outcomes, making the development of accurate and efficient detection methods essential for facilitating timely treatment and enhancing patients’ quality of life. …”
Get full text

The Pollen Representation of Vegetation and Climate Along an Altitudinal Gradient on the Eastern Tibetan Plateau by Weihe Ren, Min Liu, Feng Qin, Quan Li, Guitian Yi, Weiyu Chen, Shuming Li, Zijian Liu, Qing Peng, Chen Liang, Yan Zhao

“…The results revealed that (1) vegetation types along the altitudinal gradient can be effectively differentiated by comparing pollen assemblages, discriminant analysis, and indicator species analysis; (2) the conifer/broadleaf pollen ratio (C/B) efficiently distinguished coniferous forests (C/B > 5) from mixed forests (C/B < 5); and (3) variations in modern pollen assemblages are primarily influenced by temperature, with pollen ratios, such as <i>Artemisia</i>/Cyperaceae (<i>Art</i>/Cy) and <i>Tsuga</i>/(<i>Tsuga</i> + <i>Abies</i> + <i>Picea</i>) (T/TAP), displaying notable altitudinal and temperature differences. …”
Get full text

Evapotranspiration and crop coefficients of Moringa oleifera under semi-arid conditions in Pernambuco by Célia S. dos Santos, Abelardo A. de A. Montenegro, Márcio A. L. dos Santos, Elvira M. R. Pedrosa

“…ABSTRACT Efficient water use in agriculture is fundamental, especially in semi-arid regions where water scarcity is intense. …”
Get full text

Annealed Importance Sampling for Neural Mass Models. by Will Penny, Biswa Sengupta

“…To date, however, Bayesian methods have been largely restricted to the Variational Laplace (VL) algorithm which assumes that the posterior distribution is Gaussian and finds model parameters that are only locally optimal. …”
Get full text

One-dimensional time-frequency dual-channel visual transformer for bearing fault diagnosis under strong noise and limited data conditions by Shaobin Cai, Yuchen Wang, Wanchen Cai, Yuchang Mo, Liansuo Wei

“…The model adopts a dual-branch design: the time-domain branch incorporates spatial and channel attention to capture both local and global features, while the frequency-domain branch uses FFT to extract spectral information and fuses it with temporal features for efficient multi-scale modeling. To further enhance sensitivity to local patterns and periodic variations, a cross-scale convolution module and a periodic feedforward network are introduced. …”
Get full text