Umangbhai Soni
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Umangbhai Soni has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Abdulkarem Hussein Mohammed Almawgani
Electrical Engineering Department, College of Engineering, Najran University, Najran, Saudi Arabia
4 shared publications - Vishal Sorathiya
Faculty of Engineering and Technology, Parul Institute of Engineering and Technology, Parul University, Vadodara, Gujarat, India.
4 shared publications - Adam Reda Hasan Alhawari
Electrical Engineering Department, College of Engineering, Najran University, Najran, Saudi Arabia
2 shared publications - Gordhan Jethava
Department of Information Technology, Parul Institute of Engineering & Technology, FET, Parul University, Vadodara, India
2 shared publications - Jaysheel Golani
Science and Engineering Research Center, Najran University, Najran, Saudi Arabia
2 shared publications - Yahya Ali Abdelrahman Ali
Information Systems Department, College of Computer Sciences and Information Systems, Najran University, Najran, Saudi Arabia
2 shared publications
Latest Publications
- Open Access
- 31 March 2026
- Published by University Library in Kragujevac in Advanced Engineering Letters
- Vol. 5 (1)
A Machine Learning Approach for Bearing Fault Identification Using IFWHT, GLCM, and Feature Ranking
Time–frequency analysis is necessary for condition monitoring of rotating machinery; comparatively limited attention has been given to image- based texture feature analysis derived from time–frequency representations. A bearing fault diagnosis model is proposed that combines the Inverse Fast Walsh-Hadamard Transform (IFWHT), texture feature extraction, feature ranking, and machine learning classification. First, IFWHT transforms vibration signals into time-frequency images, thereby improving the effective representation of transient and fault- related data. Based on these images, two-dimensional texture attributes are derived from the Gray Level Co-occurrence Matrix (GLCM), which records the spatial relationships and structural patterns of various bearing health conditions. The ReliefF algorithm ranks and selects the most discriminative features, reducing feature redundancy and improving classification performance. Machine learning classifiers are then trained and evaluated using the ranked feature set. The findings show that the suggested ranked feature-based framework provides consistent and good-quality fault classification performance. Fine KNN and Cubic SVM are among the compared models, where the former will reach a maximum classification accuracy of 93.8%, and the latter will reach an accuracy of 91.7% at various combinations of faults. The methodology suggested offers a strong and adaptable approach in the context of fault diagnosis, which effectively promotes predictive maintenance by lessening unforeseen downtimes and increasing the dependability of operations in industries.
- 31 March 2026
- Published by University Library in Kragujevac in Advanced Engineering Letters
- Vol. 5 (1)
Open AccessA Machine Learning Approach for Bearing Fault Identification Using IFWHT, GLCM, and Feature Ranking
Time–frequency analysis is necessary for condition monitoring of rotating machinery; comparatively limited attention has been given to image- based texture feature analysis derived from time–frequency representations. A bearing fault diagnosis model is proposed that combines the Inverse Fast Walsh-Hadamard Transform (IFWHT), texture feature extraction, feature ranking, and machine learning classification. First, IFWHT transforms vibration signals into time-frequency images, thereby improving the effective representation of transient and fault- related data. Based on these images, two-dimensional texture attributes are derived from the Gray Level Co-occurrence Matrix (GLCM), which records the spatial relationships and structural patterns of various bearing health conditions. The ReliefF algorithm ranks and selects the most discriminative features, reducing feature redundancy and improving classification performance. Machine learning classifiers are then trained and evaluated using the ranked feature set. The findings show that the suggested ranked feature-based framework provides consistent and good-quality fault classification performance. Fine KNN and Cubic SVM are among the compared models, where the former will reach a maximum classification accuracy of 93.8%, and the latter will reach an accuracy of 91.7% at various combinations of faults. The methodology suggested offers a strong and adaptable approach in the context of fault diagnosis, which effectively promotes predictive maintenance by lessening unforeseen downtimes and increasing the dependability of operations in industries.
- Open Access
- 21 January 2026
- Published by Springer Nature in Discover Artificial Intelligence
- Vol. 6 (1)
Enhancing credit risk prediction via voting classifier and meta-dynamic ensemble selection on imbalanced data
- 21 January 2026
- Published by Springer Nature in Discover Artificial Intelligence
- Vol. 6 (1)
Open AccessEnhancing credit risk prediction via voting classifier and meta-dynamic ensemble selection on imbalanced data
- Open Access
- 1 December 2024
- Published by Walter de Gruyter GmbH in Cybernetics and Information Technologies
- Vol. 24 (4) , 22-44
Latest Advancements in Credit Risk Assessment with Machine Learning and Deep Learning Techniques
A loan is vital for individuals and organizations to meet their goals. However, financial institutions face challenges like managing losses and missed opportunities in loan decisions. A key issue is the imbalanced datasets in credit risk assessment, hindering accurate predictions of defaulters. Previous research has utilized machine learning techniques, including single or multiple classifier systems, ensemble methods, and class-balancing approaches. This review summarizes various factors and machine learning methods for assessing credit risk, presented in a tabular format to provide valuable insights for researchers. It covers data complexity, minority class distribution, sampling techniques, feature selection, and meta-learning parameters. The goal is to help develop novel algorithms that outperform existing methods. Even a slight improvement in defaulter prediction rates could significantly influence society by saving millions for lenders.
- 1 December 2024
- Published by Walter de Gruyter GmbH in Cybernetics and Information Technologies
- Vol. 24 (4) , 22-44
Open AccessLatest Advancements in Credit Risk Assessment with Machine Learning and Deep Learning Techniques
A loan is vital for individuals and organizations to meet their goals. However, financial institutions face challenges like managing losses and missed opportunities in loan decisions. A key issue is the imbalanced datasets in credit risk assessment, hindering accurate predictions of defaulters. Previous research has utilized machine learning techniques, including single or multiple classifier systems, ensemble methods, and class-balancing approaches. This review summarizes various factors and machine learning methods for assessing credit risk, presented in a tabular format to provide valuable insights for researchers. It covers data complexity, minority class distribution, sampling techniques, feature selection, and meta-learning parameters. The goal is to help develop novel algorithms that outperform existing methods. Even a slight improvement in defaulter prediction rates could significantly influence society by saving millions for lenders.
- 4 October 2024
- Published by Springer Nature in Plasmonics
- Vol. 20 (6) , 3505-3522
Multi-layered MXene and GST Material–Based Reflective Index Sensor: Numerical Study and Predication of Behaviour Using Machine Learning
- 4 October 2024
- Published by Springer Nature in Plasmonics
- Vol. 20 (6) , 3505-3522
Multi-layered MXene and GST Material–Based Reflective Index Sensor: Numerical Study and Predication of Behaviour Using Machine Learning
- 22 February 2024
- Published by IOP Publishing in Physica Scripta
- Vol. 99 (3) , 036007
Highly sensitive Borophene-metal-Si based multilayered Terahertz frequency spectrum based refractive index sensor
We presented the numerical investigation of a multilayered borophne-metal-Si-based refractive index sensor for the wide range of the THz frequency. The proposed structure is worked for the frequency range of 1 to 15 THz. The structure is formed to identify reflectance variation, resonating frequency and other physical parameters over the broad frequency spectrum. The overall structure is simulated using FEM (Finite element method) computational techniques with a periodic boundary condition-based two-port model. The resonance effect of the structure is also investigated for the different shapes of the top metal resonator structure, which significantly influences the overall frequency shift. The proposed structure is investigated for the X and Y polarized input incident condition for the entire frequency band where the oblique angle incident stability is observed up to 80°. The proposed structure offers the maximum variation in sensitivity up to 3.5 THz/RIU (∼ 11600 nm/RIU) for X-polarized and 5.5 THz/RIU (∼10600 nm/RIU) for Y-polarized incident wave conditions. We have applied the artificial neural network algorithm (ANN) to predict the overall behaviour of the structure from the data points generated in the simulated results. We used the Relu optimizer to train the model, generating promising results for our collected data. The machine learning model gives RMSE = 0.049422, MAE = 0.018531, MSE = 0.00328 and R2 = 0.93768 for the testing data set. Similarly, the model generated the minimum RMSE values = 0.045955, MAE = 0.017392, MSE = 0.00295, and R2 = 0.97673 for the training data set for 2500 epochs. The proposed results in the manuscript give the future scope to design borophene a wide range of refractive index (RI) sensor designs used in biosensors, gas sensors and other environment sensors where the refractive index range is between 1 and 2.4.
- 22 February 2024
- Published by IOP Publishing in Physica Scripta
- Vol. 99 (3) , 036007
Highly sensitive Borophene-metal-Si based multilayered Terahertz frequency spectrum based refractive index sensor
We presented the numerical investigation of a multilayered borophne-metal-Si-based refractive index sensor for the wide range of the THz frequency. The proposed structure is worked for the frequency range of 1 to 15 THz. The structure is formed to identify reflectance variation, resonating frequency and other physical parameters over the broad frequency spectrum. The overall structure is simulated using FEM (Finite element method) computational techniques with a periodic boundary condition-based two-port model. The resonance effect of the structure is also investigated for the different shapes of the top metal resonator structure, which significantly influences the overall frequency shift. The proposed structure is investigated for the X and Y polarized input incident condition for the entire frequency band where the oblique angle incident stability is observed up to 80°. The proposed structure offers the maximum variation in sensitivity up to 3.5 THz/RIU (∼ 11600 nm/RIU) for X-polarized and 5.5 THz/RIU (∼10600 nm/RIU) for Y-polarized incident wave conditions. We have applied the artificial neural network algorithm (ANN) to predict the overall behaviour of the structure from the data points generated in the simulated results. We used the Relu optimizer to train the model, generating promising results for our collected data. The machine learning model gives RMSE = 0.049422, MAE = 0.018531, MSE = 0.00328 and R2 = 0.93768 for the testing data set. Similarly, the model generated the minimum RMSE values = 0.045955, MAE = 0.017392, MSE = 0.00295, and R2 = 0.97673 for the training data set for 2500 epochs. The proposed results in the manuscript give the future scope to design borophene a wide range of refractive index (RI) sensor designs used in biosensors, gas sensors and other environment sensors where the refractive index range is between 1 and 2.4.
- 26 December 2023
- Published by Springer Nature in Optical and Quantum Electronics
- Vol. 56 (2) , 1-24
Numerical investigation of MXene-based ultrawideband solar absorber with behaviour prediction using machine learning
- 26 December 2023
- Published by Springer Nature in Optical and Quantum Electronics
- Vol. 56 (2) , 1-24
Numerical investigation of MXene-based ultrawideband solar absorber with behaviour prediction using machine learning
- 2 October 2023
- Published by Springer Nature in Plasmonics
- Vol. 19 (3) , 1211-1226
Borophene-Ge2Sb2Te5 (GST)-Based Refractive Index Sensor: Numerical Study and Behaviour Prediction Using Machine Learning
- 2 October 2023
- Published by Springer Nature in Plasmonics
- Vol. 19 (3) , 1211-1226
Borophene-Ge2Sb2Te5 (GST)-Based Refractive Index Sensor: Numerical Study and Behaviour Prediction Using Machine Learning