Soil moisture dominates gross primary productivity variation during severe droughts in Central Asia by Tao Yu, Guli Jiapaer, Anming Bao, Ye Yuan, Jiayu Bao, Tim Van de Voorde

“…P-model simulations indicate that SM deficits dominated the decline in GPP in 2008 and 2021, affecting regions covering 31 % and 17 % of CA, respectively, with GPP reductions exceeding 5 %. RF predictions also indicated that during severe drought, SM had a significant effect on GPP, while Srad, Tem, and VPD had a slight effect on GPP.…”
Get full text

Spatially Explicit Model for Assessing the Impacts of Groundwater Protection Measures in the Vicinity of the Hranice Abyss by Jozef Sedláček, Hana Vavrouchová, Kryštof Chytrý, Ondřej Ulrich, Petra Oppeltová, Milan Geršl, Kristýna Kohoutková, Radim Klepárník, Petr Kučera, Vítězslav Vlček, Jana Šimečková, Eva Žallmannová

“…The model employs a multi-criteria decision analysis, integrated with hydrological modeling and a high-resolution random forest-based prediction algorithm, to downscale land surface temperature (LST) in order to obtain high-resolution 1 × 1 m spatial results. …”
Get full text

Evaluation of LSRB Pathfinding Performance in an Autonomous Obstacle-Avoiding Robot by Usran Usran, Muh. Rafly Rasyid, Wawan Firgiawan

“…This study presents an evaluation of the performance of the Left-Straight-Right-Back (LSRB) algorithm implemented in an autonomous obstacle-avoiding robot. …”
Get full text

Parallel Simulation Multi-Sample Task Scheduling Approach Based on Deep Reinforcement Learning in Cloud Computing Environment by Yuhao Xiao, Yping Yao, Feng Zhu

“…In a real cloud environment, the proposed method demonstrates runtime reductions of 4–11% and execution cost savings of 11–22% compared to the Round-Robin algorithm, Best Fit algorithm, and genetic algorithm.…”
Get full text

ADAPTATION OF ARTIFICIAL NEURAL NETWORKS FOR CUDA-TECHNOLOGY APPLICATION by O. S. Hilko, S. P. Kundas, V. I. Kovalenko

Get full text

Correlation of Tracks from Different Radars in Information Processing by Attraction Method by U. A. Aparovich, A. V. Shevchenko

Get full text

User Random Access Technology Based on Beam Hopping Satellite Communication System by Zixuan HUANG, Jiaxi ZHOU, Jing ZHANG, Zhengyu ZHANG

“…On the basis of geosynchronous earth orbit multi-beam satellite communication systems, this paper designed the process of user random access to the network and specifi c signaling interaction under the agile beam mechanism, and proposed the scheduling strategy and allocation scheme of the agile signaling beam.This scheme increased the fl exibility of access resource allocation under the premised of ensured that all users could accessed the network, eff ectively improved the utilization rate of satellite network resources.The request of user access to the satellite communication network belongs to the burst type, it is more suitable to use the random competition access, so this paper based on the general random competition access strategy, proposed an adaptive random competition access algorithm based on the heat value, based on the heat value predicted by the network side, the user selects diff erent random access strategies for access.Through the simulation and analysis of the optimization algorithm, it is proved that the algorithm could eff ectively reduced the probability of access collision under various network loads, so as to achieved the purpose of users quickly accessing the network.…”
Get full text

Assessing the Effectiveness of DL-Clustering for Energy Optimization in Wireless Sensor Networks by Shailaja S. Halli, Poornima G Patil

“…In order to find the ideal choice for the input, the algorithm classifies system decisions, mobile data collectors, routing, and mobility. …”
Get full text

Realtime Precise Orbit Determination Technology for LEO Mega-Constellation by Zhen LI, Chuang SHI

“…Supported by GNSS, it analyzed the advantages and disadvantages of solving LEO satellite orbit on the ground or onboard the satellites.The high-fidelity non-conservative force models were applied to the real-time orbit determination algorithm.To separate the kinematic and dynamic orbit determination process had been a great advantage for LEO satellites with much frequent orbital maneuvers.The test results showed that the accuracy of accelerations computed from the radiation pressure and atmospheric drag non-conservation force models were around 5 nm/s².Use the broadcast ephemeris, the real-time orbit determination algorithm could get an accuracy of 0.8 m in the satellites′ positions and 1.1 mm/s accuracy in the satellites′ velocity.When the real-time precise ephemeris of GNSS satellites were provided, the algorithm could get an accuracy of 8 cm in the LEO satellites′ position and 0.1 mm/s in the velocity.The method for real-time orbit determination and orbit prediction in this paper could be used to support the construction of navigation system with the mega-constellations.…”
Get full text

Study of model construction of fuel production from waste plastic pyrolysis based on machine learning by CHEN Sihan, YUAN Zhilong, WANG Ye, SUN Yifei*

“…The Gradient Boosting Regression (GBR) algorithm has the best fitting performance for predicting oil yield (R^2=0.91, RMSE=7.78), while the adaptive boosting algorithm (AdaBoost) has the best fitting performance for predicting gas yield (R^2=0.83, RMSE=6.42), enabling accurate prediction of reaction conditions. …”
Get full text

Informative Path Planning Using Physics-Informed Gaussian Processes for Aerial Mapping of 5G Networks by Jonas F. Gruner, Jan Graßhoff, Carlos Castelar Wembers, Kilian Schweppe, Georg Schildbach, Philipp Rostalski

“…Physics-informed mean functions, including a detailed ray-tracing simulation, are integrated into the GP models to enhance the extrapolation performance of the GP prediction. As a central element of the GP prediction, a quantitative evaluation of different mean functions is conducted. …”
Get full text

Investigation on the Temperature Distribution of Asphalt Overlay on the Existing Cement Concrete Pavement in Hot-Humid Climate in Southern China by Zuzhong Li, Yayun Zhang, Chunguang Fa, Xiaoming Zou, Haiwei Xie, Huaxin Chen, Rui He

“…This research is to analyze the impact of meteorological factors on temperature at 2 cm depth in asphalt overlay by ReliefF algorithm and also obtain the temperature prediction model using MATLAB. …”
Get full text

PFML: Self-Supervised Learning of Time-Series Data Without Representation Collapse by Einari Vaaras, Manu Airaksinen, Okko Rasanen

“…This paper introduces a novel SSL algorithm for time-series data called Prediction of Functionals from Masked Latents (PFML). …”
Get full text

Improving the Accuracy in Classification of Blood Pressure from Photoplethysmography Using Continuous Wavelet Transform and Deep Learning by Jiaze Wu, Hao Liang, Changsong Ding, Xindi Huang, Jianhua Huang, Qinghua Peng

“…We have established a new algorithm with high accuracy to predict BP classification from PPG via matching of CWT type and segment length, which is a promising solution for rapid prediction of BP classification from real-time processing of PPG signal on a wearable device.…”
Get full text

FocusDet: an efficient object detector for small object by Yanli Shi, Yi Jia, Xianhe Zhang

“…SIOU multi-dimension accurately locates the prediction box, and SoftNMS uses the Gaussian algorithm to remove redundant prediction boxes. …”
Get full text

The Sentiment Analysis Reviewing Indosat Services from Twitter Using the Naive Bayes Classifier by Febri Astiko, Achmad Khodar

“…This sentiment analysis uses machine learning to get patterns an model that can be used again to predict new data. …”
Get full text

Height of Hydraulic Fracture Zone Based on PSO_LSSVM Model by Hebin Zhang, Tingting Wang, Bin Wu, Haijun Feng

“…At the same time, this study develops a particle swarm optimization algorithm based on adaptive inertia weight and a least squares support vector machine model to achieve height prediction of water conducting fracture zones. …”
Get full text

Multi-Factor Modeling Method of the Load Sharing Ratio under Moving Train Loads by Yong Liu, Shiyu Zhang, Yang Jin, Yuxiang Song

“…At the same time, a procedure for establishing the LSR multi-factor prediction model is put forward, namely, we (1) determine the LSR function form and the fitting algorithm; (2) perform parameter sensitivity analysis to determine the main influencing parameters of the LSR function; and (3) design a quadratic regression orthogonal test to obtain the prediction formula of the LSR function coefficients. …”
Get full text

Transfer Learning of High-Dimensional Stochastic Frontier Model via Elastic Net by Jiahao Chen, Wenjun Chen, Yunquan Song

“…When the target data is limited, transfer learning improves the accuracy of model estimation and prediction by transferring the source data. When the transferable source is known, a transfer learning algorithm for a high-dimensional stochastic frontier model is proposed based on Elastic Net. …”
Get full text

Analysis method of software failure modes in command information system based on complex networks by WANG Bo, JIANG Xuping, JING Huiqian

“…Based on a weighted undirected connected graph, this paper constructs a static model of the complex network for the command information system software, proposes a hierarchical centrality algorithm for the multi-layer neighbor influence of nodes, realizes the prediction of software network fault sources, and mines the fault propagation path based on the ant colony system algorithm. …”
Get full text