Alok Singh Chauhan

Dr. Alok Singh Chauhan

Department of Computer Application, SCSE, Galgotias University, Greater Noida, India
orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 April 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Alok Singh ChauhanAlok Singh Chauhan
Alok Singh Chauhan
ULUmesh Kumar Lilhore
Umesh Kumar Lilhore
AGAmit Kumar Gupta
Amit Kumar Gupta
PMPoongodi M.
Poongodi M.
RGRuchi Rani Garg
Ruchi Rani Garg
Kaamran RaahemifarKaamran Raahemifar
Kaamran Raahemifar
Although Kyphosis, an excessive forward rounding of the upper back, can occur at any age, adolescence is the most common time for Kyphosis. Surgery is frequently performed on Kyphosis patients; however, the condition may persist after the operation. The tricky part is figuring out, based on the patient’s traits, if the Kyphosis condition will continue after the treatment. There have been numerous models employed in the past to predict the Kyphosis disease, including Logistic Regression (LR), Naive Bayes (NB), Random Forest (RF), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Deep Neural Network (DNN), and others. Unfortunately, the precision was overestimated. Based on the dataset received from Kaggle, we investigated how to predict Kyphosis disorders more accurately by using these models with Hyperparameter tuning. While the calculations were being performed, certain variables were modified. The accuracy was increased by optimizing the fit parameters based on Hyperparameter tuning. Accuracy, recall or sensitivity, specificity, precision, balanced accuracy score, F1 score, and AUC-ROC score of all models, including the Hyperparameter tuning, were compared. Overall, the Hyperparameter-tuned DNN models excelled over the other models. The DNN models’ accuracy was 87.72% with 5-fold cross-validation and 87.64% with 10-fold cross-validation. It is advised that when a patient has a clinical procedure, the DNN model be trained to detect and foresee Kyphosis disease. Medical experts can use this study’s findings to correctly predict if a patient will still have Kyphosis after surgery. We propose that deep learning should be adopted and utilized as a crucial and necessary tool throughout the broad range of resolving biological queries.

13 May 2023 in Polyhedron International Journal in Mathematics Education
Verified
Journal Article
Open access
PDF file
SSSudirman Sudirman
Sudirman Sudirman
CRCamilo Andrés Rodríguez-Nieto
Camilo Andrés Rodríguez-Nieto
ZDZwelithini Bongani Dhlamini
Zwelithini Bongani Dhlamini
Alok Singh ChauhanAlok Singh Chauhan
Alok Singh Chauhan
UBUmida Baltaeva
Umida Baltaeva
MAMela Andriani
Mela Andriani
Each student has their own characteristics and way of doing 3D geometric thinking. The way of thinking that students do influences the resulting understanding of the concept of 3D geometry. Therefore, this study aims to investigate students' geometric thinking based on the level of achievement of students in completing the 3D geometric thinking ability test (3D GTA). This study uses an exploratory case study design. The participants who voluntarily participated were 33 junior high school students (14 boys, 19 girls) in one of the schools in Indramayu Regency, Indonesia. Data obtained from the process of observation, tests, interviews, and documentation were analyzed qualitatively using Atlas. ti 8 software. The findings revealed that students with low 3D GTA achievements experienced difficulties in representing and calculating the surface area and volume of 3D shapes. In addition, students with moderate 3D GTA achievements experienced difficulties in representing 3D shapes but were able to translate 2D shapes from 3D shapes. Furthermore, students with high 3D GTA achievements experienced difficulties in calculating the surface area and volume of 3D shapes, but were able to use appropriate formulas and were able to interpret the comparisons of 3D geometric shapes well. The results of this study have implications for helping teachers identify student characteristics in understanding the concept of 3D geometry and connections with 2D geometry.

8 February 2024 in Journal of Integrated Science and Technology
Verified
Journal Article
Open access
PDF file
Alok Singh ChauhanAlok Singh Chauhan
Alok Singh Chauhan
JSJyoti Singh
Jyoti Singh
SKSumit Kumar
Sumit Kumar
NSNeeru Saxena
Neeru Saxena
MGMeghna Gupta
Meghna Gupta
PVPoonam Verma
Poonam Verma
Deep learning techniques have recently demonstrated promising outcomes in the segmentation of brain tumors from MRI images. Due to its capability to handle high-resolution images and segment the entire tumor region, the U-Net model is one of them and is frequently utilized. For the analysis and planning of brain tumors treatments, accurate segmentation of brain tumors using multi-contrast MRI images is essential. Deep learning models including U-Net, PSPNet, DeepLabV3+, and ResNet50 have demonstrated encouraging outcomes in the segmentation of brain tumors. Using the BraTS 2018 dataset, we compare these models in this research. We evaluate the models using a variety of measures, including the Hausdorff Distance (HD), the Absolute Volume Difference (AVD), and the Dice Similarity Coefficient (DSC), and we look into how data augmentation and transfer learning approaches affect the models' performance. The findings demonstrate that the 3D U-Net model performed the best, with a DSC of 0.90, HD of 10.69mm, and AVD of 11.15%. The PSPNet model achieved comparable performance, with a DSC of 0.89, HD of 11.37mm, and AVD of 12.24%. The DeepLabV3+ and ResNet50 models achieved lower performance, with DSCs of 0.85 and 0.83, respectively. Based on the discoveries and analysis, the 3D U-Net model with data augmentation and transfer learning is suggested for brain tumors segmentation utilizing multi-contrast MRI images. URN:NBN:sciencein.jist.2024.v12.793

2 February 2024 in Journal of Luminescence
Verified
Journal Article
Closed access
MNMega Novita
Mega Novita
Alok Singh ChauhanAlok Singh Chauhan
Alok Singh Chauhan
RURizky Muliani Dwi Muliani Dwi Ujianti
Rizky Muliani Dwi Muliani Dwi Ujianti
DMDian Marlina
Dian Marlina
HKHaryo Kusumo
Haryo Kusumo
Mikhail G. BrikMikhail G. Brik
Mikhail G. Brik

1 November 2024 in Journal of Integrated Science and Technology
Verified
Journal Article
Open access
PDF file
NSNarendra Kumar Sharma
Narendra Kumar Sharma
Alok Singh ChauhanAlok Singh Chauhan
Alok Singh Chauhan
SFShahnaz Fatima
Shahnaz Fatima
SSSwati Saxena
Swati Saxena
Cardiovascular disease is one of the main reasons for the demise of people in the world today, whether it is a developed country or a developing country. It is not only affecting the people living in the urban but it has also affected the people of rural areas. If we know it at the primary stage, then its side effects can be avoided by reducing the chances of heart disease. So, the correct prediction of heart disease is an imperative task to assist doctors and medical experts to take decision and make effective treatment policies to save the lives of people. In this paper, we use and combine multiple classification method of data mining and machine learning to perk up the precision of classifier. For this, we have used the ensemble machine learning method which combines multiple models into a single predictive model that utilizes the advantages of multiple base models usually called weak learners to compensate for each model’s weakness. We intend an iterative ensemble approach to integrate various low-performance classifiers to form a strong classifier with high precision. We took a dataset from the IEEE data port for its implementation which contains around 1190 instances with 11 features of heart disease. We examine on the basis of initial symptoms even the patient has heart disease or not. We explore the application of classification and ensemble machine learning techniques to augment healthcare decision-making for heart disease. By bridging the gap between data-driven insights and clinical decision-making, these techniques pave the means for a more proactive and patient-centric approach to cardiovascular health management.

29 May 2023 in Materials
Verified
Journal Article
Open access
PDF file
MNMega Novita
Mega Novita
SRSigit Ristanto
Sigit Ristanto
ESErnawati Saptaningrum
Ernawati Saptaningrum
SSSlamet Supriyadi
Slamet Supriyadi
DMDian Marlina
Dian Marlina
MBMikhail G. Brik
Mikhail G. Brik
The crystals of Mn4+-activated fluorides, such as those of the hexafluorometallate family, are widely known for their luminescence properties. The most commonly reported red phosphors are A2XF6: Mn4+ and BXF6: Mn4+ fluorides, where A represents alkali metal ions such as Li, Na, K, Rb, Cs; X=Ti, Si, Ge, Zr, Sn, B = Ba and Zn; and X = Si, Ge, Zr, Sn, and Ti. Their performance is heavily influenced by the local structure around dopant ions. Many well-known research organizations have focused their attention on this area in recent years. However, there has been no report on the effect of local structural symmetrization on the luminescence properties of red phosphors. The purpose of this research was to investigate the effect of local structural symmetrization on the polytypes of K2XF6 crystals, namely Oh-K2MnF6, C3v-K2MnF6, Oh-K2SiF6, C3v-K2SiF6, D3d-K2GeF6, and C3v-K2GeF6. These crystal formations yielded seven-atom model clusters. Discrete Variational Xα (DV-Xα) and Discrete Variational Multi Electron (DVME) were the first principles methods used to compute the Molecular orbital energies, multiplet energy levels, and Coulomb integrals of these compounds. The multiplet energies of Mn4+ doped K2XF6 crystals were qualitatively reproduced by taking lattice relaxation, Configuration Dependent Correction (CDC), and Correlation Correction (CC) into account. The 4A2g→4T2g (4F) and 4A2g→4T1g (4F) energies increased when the Mn-F bond length decreased, but the 2Eg → 4A2g energy decreased. Because of the low symmetry, the magnitude of the Coulomb integral became smaller. As a result, the decreasing trend in the R-line energy could be attributed to a decreased electron–electron repulsion.