Ensemble and transfer learning of soil inorganic carbon with visible near-infrared spectra by Yu Wang, Keyang Yin, Bifeng Hu, Yongsheng Hong, Songchao Chen, Jing Liu, Lili Yang, Jie Peng, Zhou Shi

“…The stacking model consists of 10 base models (support vector machine (SVM), partial least squares algorithm (PLSR), multi-layer perceptron (MLP), etc.). …”
Get full text

Hybrid Deep Learning for Fault Diagnosis in Photovoltaic Systems by Mouaad Bougoffa, Samir Benmoussa, Mohand Djeziri, Olivier Palais

“…The model was rigorously validated using real-world PV datasets, encompassing diverse fault types such as partial shading, open circuits, and module degradation under dynamic environmental conditions. …”
Get full text

Prediction of lymph node metastasis in lung adenocarcinoma using a PET/CT radiomics-based ensemble learning model and its pathological basis by Shulin Li, Shulin Li, Fang Chen, Lei Wang, Lei Wang, Zhiming Xiang

“…Despite the absence of FDR-significant radiomic-pathomic correlations (all q > 0.05), exploratory analysis revealed nominal associations (uncorrected P < 0.05) for partial feature pairs. Crucially, radiomic features demonstrated strong associations with Ki-67 expression: PET_GLRLM_LongRunHigh GreyLevelEmphasis (r = 0.610, q < 0.001) and CT_INTENSITY-BASED_Intensity BasedEnergy (r = 0.332, q = 0.004).ConclusionsThe stacking ensemble learning model based on 18F-FDG PET/CT radiomics demonstrates potential for predicting LNM in lung adenocarcinoma, and the quantitative analysis of radiomic features holds significant biological significance.…”
Get full text

A three parallel branches harmonic model with adaptive capability of operating state variation by Youhang Yang, Shaorong Wang, Jiaxuan Ren, Yao Guo, Siyuan Chen, Mingming Shi, Xian Zheng

“…Furthermore, an adaptive TPBM for harmonic source operating state variations based on Stacking ensemble learning technology is proposed, the construction process and training strategy of the Stacking model are also elaborated. …”
Get full text

Hardening an amorphous-crystal dual-phase Ni–Mo–W alloy with atomic-scale planar faults by Dongsong Zeng, Jiongxian Li, Yinong Shi, Xiuyan Li

“…Inspired by thermally-triggered grain boundary relaxation in nanograined alloys, we introduce an innovative approach to incorporate an ultrahigh density of atomic-scale planar faults, including stacking faults and twins, into nanocrystals in an amorphous-crystal dual-phase nanostructure realized via in-situ primary crystallization in a concentrated amorphous Ni-26.6 at.% Mo-3.5 at.% W alloy. …”
Get full text

Phase Transformation and Deformation Mechanisms of 304L Stainless Steel Under Tensile and Charpy Impact Testing at Varying Temperatures by Gang-Ho Lee, Gwangjoo Jang, Byoungkoo Kim, Changyong Choi, Hee-Sang Park, Jong-Bae Jeon, Changwoo Lee, Sanghoon Noh, Byung Jun Kim

“…The high strain rate during Charpy impact testing induced localized adiabatic heating, partially suppressing SIMT and modifying fracture behavior by enhancing localized plasticity. …”
Get full text

Unveiling the Strengthening and Ductility Mechanisms of a CoCr₀.₄NiSi₀.₃ Medium-Entropy Alloy at Cryogenic Temperatures by Li Zhang, Lingwei Zhang, Xiang Chen

“…At −75 °C, the a/6<112> Shockley partial dislocation interacts with the L1₂ phase to form antiphase boundaries (APBs) approximately 3 nm thick. …”
Get full text

Deformation twinning and hcp-to-fcc phase transformations of CP-Ti induced by long-term static compressive stresses at ambient temperatures by Tong Yin, Lingfeng Pan, Zijie Zhou, Zhenhua Dan, Hui Chang, Lian Zhou

“…This hcp-to-fcc phase transformation is facilitated by the stacking faults and gliding of the 1/3<101‾0 > Shockley partial dislocations on the basal plane of hcp Ti via the interfacial stacking faults, which could effectively coordinate the large creep plastic strains.…”
Get full text

Trajectory Aware Deep Reinforcement Learning Navigation Using Multichannel Cost Maps by Tareq A. Fahmy, Omar M. Shehata, Shady A. Maged

“…Deep reinforcement learning (DRL)-based navigation in an environment with dynamic obstacles is a challenging task due to the partially observable nature of the problem. While DRL algorithms are built around the Markov property (assumption that all the necessary information for making a decision is contained in a single observation of the current state) for structuring the learning process; the partially observable Markov property in the DRL navigation problem is significantly amplified when dealing with dynamic obstacles. …”
Get full text

Infrared Moving Small Target Detection Based on Spatial&#x2013;Temporal Feature Fusion Tensor Model by Deyong Lu, Wei An, Haibo Wang, Qiang Ling, Dong Cao, Miao Li, Zaiping Lin

“…In this article, a novel method based on the spatial&#x2013;temporal feature fusion tensor model is proposed to solve these problems. By directly stacking raw infrared images, the sequence can be transformed into a third-order tensor, where the spatial&#x2013;temporal features are not reduced or destroyed. …”
Get full text

A Modular Step-Up DC/DC Converter for Electric Vehicles by Ahmed Darwish

“…A step-up DC/DC converter is required to match the fuel cell’s stack voltage with the DC-link capacitor of the propulsion system in fuel cell-based electric vehicles (FCEVs). …”
Get full text

Adaptive seismic ground roll attenuation using the double density dual tree discrete wavelet transform (DWT) method by Ali Goudarzi, M A Riahi

“…Many methods have been used to removenoise types, each being partially effective. None of the transforms have been ideal and, even at the point of transform, noise becomes added to data. …”
Get full text

Imaging the evolution of lithium-solid electrolyte interface using operando scanning electron microscopy by Lihong Zhao, Min Feng, Chaoshan Wu, Liqun Guo, Zhaoyang Chen, Samprash Risal, Qing Ai, Jun Lou, Zheng Fan, Yue Qi, Yan Yao

“…Abstract The quality of Li–solid electrolyte interface is crucial for the performance of solid-state lithium metal batteries, particularly at low stack pressure, but its dynamics during cell operation remain poorly understood due to a lack of reliable operando characterization techniques. …”
Get full text

Prediction of biological evolution following blood product transfusion during liver transplantation: the contribution of machine learning to decision-making by Jacques Creteur, Thibault Martinez, Valerio Lucidi, Turgay Tuna, Florian Blanchard, Olivier Duranteau, Benjamin Popoff, Axel Abels, Eric Savier, Patrizia Loi, Desislava Germanova, Anne Demulder

“…This study aimed to develop machine learning models to predict the biological effects of blood product transfusions, assisting clinicians in selecting optimal therapeutic combinations.Methods Using data from two cohorts over 20 years from two academic hospitals, 10 supervised machine learning models were trained and validated on four biomarkers: fibrinogen, haemoglobin, prothrombin time and activated partial thromboplastin time ratio. Models were evaluated using R², root mean squared error and SD metrics, with external validation performed on the second cohort.Results The results indicated that while certain models, such as the stack model for late fibrinogen (R²=0.63) or the extra trees model for late prothrombin time (R²=0.66), demonstrated promising predictive capacity, the overall external validation performance was suboptimal. …”
Get full text

Development and verification of a convolutional neural network-based model for automatic mandibular canal localization on multicenter CBCT images by Xiao Pan, Chengtao Wang, Xuhui Luo, Qi Dong, Haiyang Sun, Wentao Zhang, Hongyan Qu, Runzhi Deng, Zitong Lin

“…The convolution module was built using a stack of Conv + InstanceNorm + LeakyReLU. Average symmetric surface distance (ASSD) and symmetric mean curve distance (SMCD) were used for quantitative evaluation of this model for both internal testing data and partial external testing data. …”
Get full text

Petrogenetic link between metasedimentary rocks, migmatites and granitoids in the Variscan basement of the Pontgibaud area, French Massif Central – implications for the crustal str... by Passos do Carmo Caliméria, Vanderhaeghe Olivier, Laurent Oscar, Berger Julien, Bellanger Mathieu, Leisen Mathieu, Chmeleff Jérôme

“…The architecture of the crust in the French Massif Central (FMC) is described as a nappe stack composed, from top to bottom, of the Upper Gneiss Unit (UGU), the Lower Gneiss Unit (LGU), and the Para-Autochthonous Unit (PAU), which are intruded by Carboniferous granitic plutons. …”
Get full text

A Review of Segmented Stator and Rotor Designs in AC Electric Machines: Opportunities and Challenges by Bhuvan Khoshoo, Anmol Aggarwal, Shanelle Foster

“…Parasitic air gaps between segments and an increased number of cut edges in the assembled stack can alter the magnetic properties of the machine, potentially leading to degraded performance. …”
Get full text

Enhancing Autonomous Driving in Urban Scenarios: A Hybrid Approach with Reinforcement Learning and Classical Control by Rodrigo Gutiérrez-Moreno, Rafael Barea, Elena López-Guillén, Felipe Arango, Fabio Sánchez-García, Luis M. Bergasa

“…Specifically, the authors address the Decision Making problem by employing a Partially Observable Markov Decision Process formulation and offer a solution through the use of Deep Reinforcement Learning algorithms. …”
Get full text

Direct Observation of Sulfate Explosive Growth in Wet Plumes Emitted From Typical Coal‐Fired Stationary Sources by Xiang Ding, Qing Li, Di Wu, Xiaoyan Wang, Mei Li, Tao Wang, Lin Wang, Jianmin Chen

“…When the rapidly formed sulfate in wet plumes is included, a notable amount of underestimated sulfate (∼0.24 Tg in 2017) is emitted from industrial stacks in China and can partially explain the “missing sulfate” on driving most particle pollution episodes. …”
Get full text

An air quality assessment in the industrialised western Bushveld Igneous Complex, South Africa by Andrew Venter, Ville Vakkar, Johan Beukes, Pieter van Zyl, Heikki Laakso, Desmond Mabaso, Petri Tiitta, Miroslav Josipovic, Markku Kulmala, Jacobus Pienaar, Lauri Laakso

“…The major sources of SO2 were identified as high-stack industry emissions, while household combustion from semi-formal and informal settlements was identified as the predominant source of NO2 and CO. …”
Get full text