-
861
-
862
Influence of the nature of organic solvents on the process of separation of antioxidative additive in a transformer oil by a gas-chromatographic method
Published 2021-03-01“…The sample was dosed into the gas-liquid chromatograph injector using an automatic liquid dispenser DAZH-23, designed for entering up to twenty-three samples of sorbates and controlled by a computer with the appropriate software.METHODS. …”
Get full text
Article -
863
DiffGAN: A Fault Diagnosis Data Augmentation Method for Hydropower Units Based on Adversarial Training and Diffusion Model
Published 2025-01-01“…It takes diffusion noise as the input for adversarial training, enhances the generator’s high-speed generation capability through adversarial training, optimizes the efficiency of the reverse generation process in traditional denoising diffusion models, and mitigates gradient vanishing and mode collapse issues in generative adversarial networks. Experiments were conducted on an actual hydropower unit dataset, and the results demonstrate that DiffGAN can efficiently generate fault data and significantly improve the sample distribution in imbalanced datasets. …”
Get full text
Article -
864
Research on Four-Quadrant Input Over-current Fault Diagnosis of Electric Locomotive Based on Recursive 2-Classification Method
Published 2019-03-01“…Reliable classification model was constructed by gradient boosting decision tree (GBDT) based on ensemble learning, and multi-label data was classified and diagnosed recursively by recursive 2-classification. Experiments on four-quadrant input over-current fault data files showed that this method could improve the classification and diagnosis of fault samples.…”
Get full text
Article -
865
-
866
Accelerated Testing of High Power Transistors for Long Operation when Solving Problems of Prediction of their Reliability by the Method of Imitation Simulation
Published 2022-06-01“…The simulation model is obtained with the help of preliminary studies (training experiment) of a training sample of semiconductor devices of the type of interest with the volume of approximately 50 ... 100 copies. …”
Get full text
Article -
867
An Anomaly Node Detection Method for Wireless Sensor Networks Based on Deep Metric Learning with Fusion of Spatial–Temporal Features
Published 2025-05-01“…The existing anomaly detection methods fail to fully capture correlations in multi-node, multi-modal time series data, limiting their effectiveness. …”
Get full text
Article -
868
Transformer fault diagnosis using machine learning: a method combining SHAP feature selection and intelligent optimization of LGBM
Published 2025-04-01“…Following this, the bald eagle search (BES) intelligent optimization algorithm is utilized to optimize the hyperparameters of the light gradient boosting machine (LGBM) model, further improving its predictive capability. Comparative experiments with various traditional machine learning models validate the effectiveness of the proposed method. …”
Get full text
Article -
869
Development of an immune-related gene signature applying Ridge method for improving immunotherapy responses and clinical outcomes in lung adenocarcinoma
Published 2025-05-01“…Considering the critical role of tumor infiltrating lymphocytes in effective immunotherapy, this study was designed to screen molecular markers related to tumor infiltrating cells in LUAD, aiming to improve immunotherapy response during LUAD therapy. Methods The ConsensusClusterPlus method was used for clustering immune molecular subtypes of LUAD. …”
Get full text
Article -
870
Graph-Based Few-Shot Learning for Synthetic Aperture Radar Automatic Target Recognition with Alternating Direction Method of Multipliers
Published 2025-03-01“…However, the scarcity of annotated SAR data significantly limits the performance of conventional data-driven methods. To address this challenge, we propose a novel few-shot learning (FSL) framework: the alternating direction method of multipliers–graph convolutional network (ADMM-GCN) framework. …”
Get full text
Article -
871
-
872
Effect of using flat hierarchical method on some aspects of muscular strength and straight serve skill for nascent tennis players
Published 2020-11-01“…Therefore, the researcher tried to diversify and experiment in the training process through the use of a training method suitable for the youth category and taking into account their level. …”
Get full text
Article -
873
Investigate the composition effect of Cu-Nb-B-Fe soft magnetic metallic glasses using deep learning method
Published 2025-09-01“…In this paper, we introduced a universal method to predict if a composition can succeed in amorphous glass without sample preparation. …”
Get full text
Article -
874
Predicting user's movement path in indoor environments using the stacked deep learning method and the fuzzy soft‐max classifier
Published 2022-07-01“…Experiments were conducted on the MovementAAL_RSS dataset. …”
Get full text
Article -
875
Research Note: Development of a reverse transcriptase recombinase-aided amplification method for detection of Parrot Borna Virus 4
Published 2024-12-01“…The coefficient of variation for the 3 repeatability experiments was below 10%. Tissue samples from 28 suspected cases of PaBV related deaths in parrots were analyzed using both RT-RAA and RT-qPCR methods. …”
Get full text
Article -
876
Sound quality control method of 110 kV transformer based on distributed variable stiffness dynamic vibration absorber
Published 2025-07-01“…To measure the actual impact of transformer noise on humans more effectively, this paper proposes to introduce the sound quality evaluation method into the evaluation of transformer noise. First, the field noise of a 110 kV transformer was measured, and the objective parameters and subjective scores of the noise samples were analyzed, and a subjective prediction model of sound quality was established using the multiple linear regression method. …”
Get full text
Article -
877
A multi-task allocation method for coal gangue sorting robots based on the integration of greedy strategy and scheduling rules
Published 2025-04-01“…A time-varying raw coal flow simulation environment with different maximum coal throughput was set up for multi-robot coal gangue sorting task allocation simulation experiments. The results showed that for time-varying raw coal flow samples with maximum coal throughput of 120 and 150 kg/s, the coal gangue sorting rates were 97.69% and 89.10%, respectively, when using the proposed multi-task allocation method with a greedy strategy and scheduling rules, which was an improvement of 6.82% and 5.67%, respectively, compared to the single scheduling rule method. …”
Get full text
Article -
878
Controlling pore size during the synthesis of hydroxyapatite nanoparticles using CTAB by the sol–gel hydrothermal method and their biological activities
Published 2024-12-01“…Nanorod and nanosphere hydroxyapatite (HAP) particles were synthesized by the sol–gel hydrothermal method. The size of the synthesized HAP nanoparticles was controlled using cetyltrimethylammonium bromide (CTAB) as a templating agent with molar concentrations (HAP + 0.01 M CTAB, HAP + 0.03 M CTAB, and HAP + 0.1 M CTAB). …”
Get full text
Article -
879
Large-area urban TomoSAR method with limited a priori knowledge and a complex deep learning model
Published 2025-05-01“…However, existing TomoSAR height inversion methods do not fully leverage a priori knowledge, compromising the accuracy of deformation estimation; deep learning-based methods involve the integration of multiple steps, complicating the process. …”
Get full text
Article -
880