Fault diagnosis process
This study proposed a transformer fault diagnosis method based on Gramian Angular Field and optimized parallel ShuffleNetV2, the diagnosis process is illustrated in the Fig. 6.
Offline model training
First, the…

This study proposed a transformer fault diagnosis method based on Gramian Angular Field and optimized parallel ShuffleNetV2, the diagnosis process is illustrated in the Fig. 6.
First, the…

Here, we define the ‘emergence year’ Ye as being the start of a period in which precipitation consistently exceeds the maximum value obtained during the historical period in each continuous experiment from past to…

This manuscript presents an EMDD-ADLMOA technique. The proposed method relies on improving malicious domain detection in cybersecurity. The EMDD-ADLMOA model has data pre-processing, feature subset selection, attack classification, and parameter…

The comparative analysis of Logistic Boosting, Random Forest (RF), and Support Vector Machines (SVM) on 15,000 industrial IoT instances (17.4% anomaly prevalence) revealed significant performance differences. Logistic…

Accurately classifying dermatological conditions relies on the morphological characteristics and visual representation of cutaneous lesions. The diagnostic process of dermatoses and skin disorders necessitates the combination of various data…

In this section, all the results extracted from the experimental analysis, simulation, and ML model are presented. Firstly, the optoelectronic model used in extracting the degradation coefficient is trained and validated agonist experimental…

Our research problem is to reprogram the original feature space into a new feature space that further improve the performance of downstream tasks while avoiding the exposure of sensitive features in a traceable and interpretable…

The VAR model’s lag order is set to 1 based on the AIC, BIC, and HQIC criteria (see Appendix A for details). Following Tiwari et al.68 the forecast horizon for variance decomposition is set to 100 steps….

We integrated two datasets for epidemiological modelling. The first was spatiotemporal population data that consisted of hourly population estimates for each 125-metre-square grid cell. The population…

In this subsection, the proposed model’s parameters estimation and performance have been done using two software failure data sets. The first data set (DSI) is collected from testing a medium-size software system26 and…