Explainable Offline‐Online Training of Neural Networks for Parameterizations: A 1D Gravity Wave‐QBO Testbed in the Small‐Data Regime by Hamid A. Pahlavan, Pedram Hassanzadeh, M. Joan Alexander

“…A 12‐layer convolutional NN that predicts GW forcings for given wind profiles, when trained offline in a big‐data regime (100‐year), produces realistic QBOs once coupled to the 1D model. …”
Get full text

Detecting network intrusions in cyber-physical systems using deep autoencoder-based dimensionality reduction approach anddeep neural networks by A. E. Ibor, D. O. Egete, A. O. Otiko, D. U. Ashishie

“… Cyber-Physical Systems (CPSs) that integrate computational and physical processes are the foundation of reliability in prominent areas of critical infrastructure, including transportation, energy, and manufacturing. …”
Get full text

Crypto Deep Ring Topology Firewall in Sensitive Data Transmission and Retrieval in Cloud by Vikas K. Soman, V. Natarajan

“…The data transmission and data retrieval process from the cloud is a critical issue because of cyber-attacks. …”
Get full text

Fine Particle pH and Sensitivity to NH3 and HNO3 over South Korea During KORUS-AQ by Ifayoyinsola Ibikunle, Andreas Beyersdorf, Pedro Campuzano-Jost, Chelsea Corr, John D. Crounse, Jack Dibb, Glenn Diskin, Greg Huey, Jose-Luis Jimenez, Michelle J. Kim, Benjamin A. Nault, Eric Scheuer, Alex Teng, Paul O. Wennberg, Bruce Anderson, James Crawford, Rodney Weber, Athanasios Nenes

“…Using a new approach that constrains thermodynamic modeling of aerosol composition with measured gas-to-particle partitioning of inorganic nitrate, we estimate the acidity levels for aerosol sampled in the South Korean planetary boundary layer during the NASA/NIER KORUS-AQ field campaign. …”
Get full text

Transparent PZT Capacitors on Glass for Actuating Applications by Franklin Pavageau, Christel Dieppedale, Kevin Benedetto, Christophe Licitra, Laurent Frey, Fabrice Casset, Gwenaël Le Rhun

“…Fully integrated transparent ITO/PZT/ITO capacitors on glass were obtained thanks to a recently developed wafer-to-wafer layer-transfer process to bypass the thermal budget issue associated with the high crystallization temperature of PZT (~700 °C). …”
Get full text

Rolling Force Prediction of Hot Rolling Based on GA-MELM by Jingyi Liu, Xinxin Liu, Ba Tuan Le

“…In the modeling process, GA is used to determine the optimal number of hidden layers and the optimal number of hidden nodes, and PSO is used to search for the optimal input weights and biases. …”
Get full text

Experimental and numerical investigation on mechanical properties change of HDPE in various aging conditions by Lu Wang, Zhengpan Qi, Chao Yang, Xiangyan Ding, Qibo Deng, Bo Yang, Ning Hu

“…The aging process is confined to the specimen surface, resulting in an aged layer hundreds of micrometers thick and slight changes in the overall mechanical properties of the specimen, as indicated by tensile test results and FEM simulations. …”
Get full text

SIMULATION OF HYDRODYNAMIC DEPASSIVATION IN ELECTROCHEMICAL CUTTING USING THIN ROD-TYPE ELECTRODE WITH HELICAL GROOVES by Elisaveta Craciun, Margareta Coteata, Vasile Ermolai, Marius Andrei Mihalache, Laurentiu Slatineanu

“…To highlight how the rotation of the tool electrode contributes to the recirculation of the electrolyte, a modeling of the process using the finite element method was resorted to. …”
Get full text

Exploring the Effects of Light–Water Interaction in Plant Factory to Improve the Yield and Quality of <i>Panax notoginseng</i> (Burkill) F. H. Chen by Jing Wang, Zhe Han, Junjie He, Hongwei Kang, Qinghua Li, Haomin Chen, Xuan Zhang, Wanying Miao, Xiaojian Shang, Wenting Chen, Zhiyong Gao

“…The best performance in terms of plant height (15.3 cm), stem diameter (3.45 mm), leaf length (8.6 cm), fresh weight (3.382 g), and total ginsenoside content (3.8%) was observed when the red-to-blue light ratio was 4:1 (A Treatment), the field water capacity was 50%, and the shading level was three layers. Based on this, the Pearson correlation analysis was used to identify eight highly correlated indicators, and the entropy-weighted TOPSIS model was applied to comprehensively evaluate the cultivation schemes. …”
Get full text

Machine Learning-Based Weld Classification for Quality Monitoring by Rojan Ghimire, Rajiv Selvam

“…This study trains the model on the welding dataset, using five convolutional layers followed by five pooling layers and, finally, three fully connected layers. …”
Get full text

Ocean waves across the Arctic: Attenuation due to dissipation dominates over scattering for periods longer than 19 s by Fabrice Ardhuin, Peter Sutherland, Martin Doble, Peter Wadhams

“…Details of the dissipation process remain uncertain. Average dissipation rates are consistent with creep effects but are 12 times those expected for a laminar boundary layer under a smooth solid ice plate.…”
Get full text

A Mobile Agent Routing Algorithm in Dual-Channel Wireless Sensor Network by Kui Liu, Sanyang Liu, Hailin Feng

“…A mobile agent routing algorithm (MARA) is presented in this paper, and then based on the dual-channel communication model, the two-layer network combination optimization strategy is also proposed. …”
Get full text

The global distribution of Earth's critical zone and its controlling factors by Xianli Xu, Wen Liu

Get full text

THERMAL STRESS ANALYSIS OF OPTICAL FIBER IN FLEXIBLE PTOELECTRONIC INTERCONNECTION PRINTED CIRCUIT BOARD BASED ON FINITE ELEMENT METHOD by WANG WeiYin, WU ZhaoHua, CHEN GuDi, WANG ZhiQi, CHEN XiaoYong

“…The three-dimensional model of flexible photovoltaic substrate was established. …”
Get full text

Ballistic Penetration of Small-Caliber Bullet in Double-Arrow Honeycomb Core Structures with Negative Poisson’s Ratio by LIU Yangzuo, XU Cheng, MA Wuning, REN Jie, ZHANG Zhendong

“…The simulation results show that when the thickness of the upper and lower layers are kept constant and only the double-arrow angle of the core layer is increased, the ballistic limit of the honeycomb sandwich structure is subsequently reduced. …”
Get full text

A visual SLAM loop closure detection method based on lightweight siamese capsule network by Yuhan Zhou, Mingli Sun

“…Traditional loop closure detection algorithms rely on the bag-of-words model, which involves a complex process, has slow loading speeds, and is sensitive to changes in illumination or viewing angles. …”
Get full text

6G oriented blockchain based Internet of things data sharing and storage mechanism by Yu’na JIANG, Xiaohu GE, Yang YANG, Chengxiang WANG, Jie LI

“…Considering the heterogeneity of various IoT system and the single point failure of centralized data-processing platform,a decentralized IoT data sharing and storage method based on blockchain technology was proposed.The block consensus and decentralized storage of shared data were realized through the PoS consensus mechanism.A block layered propagation mechanism between consensus node and verified node was proposed based on the Gossip protocol.The block propagation delay model and decentralization evaluation model of blockchain networks were derived.The trade-off between the block propagation delay and the decentralization degree of networks was analyzed.The simulation results demonstrate that the block propagation delay and degree of network decentralization decrease with the increase of minimal capabilities of consensus nodes.As an application example,in the trajectory data sharing scenario of confirmed patients,the data sharing smart contract is implemented and tested based on the Ethereum development platform.…”
Get full text

Experimental Study on the Permeability of a Soil-Rock Mixture Based on the Threshold Control Method by Xiaohua Ding, Xuyang Shi, Wei Zhou, Boyu Luan

“…Therefore, during the reclamation process of the open-pit mine, the water-retaining layer below the humus should be compacted, and RBP should be increased to lower permeability and achieve better water retention.…”
Get full text

Enterprise Tax Assessment and Risk Avoidance Based on Deep Learning by Yali Lan

“…The cumulative taxable input risks are updated based on the previous inputs and their claimable part to improve the risk prediction. In this prediction process, deep learning is employed; this learning model is designed with two conditional layers. …”
Get full text

Leveraging spatial dependencies and multi-scale features for automated knee injury detection on MRI diagnosis by Jianhua Sun, Ye Cao, Ying Zhou, Baoqiao Qi

“…The integration of Grad-CAM visualizations enhances the interpretability of KneeXNet, enabling radiologists to understand and validate the model’s decision-making process.…”
Get full text