Machine learning approach in predicting nanofluid viscosity of alumina, copper oxide, silicon dioxide, and titanium dioxide using physics constraint-based XGBoost model Shekhar, Koj Sambyo, Seema Tinker Journal of Applied Physics, 2025 Nanofluids are essential colloidal suspensions composed of base fluids with suspended nanoparticles. They possess enhanced thermophysical properties, making them useful for various applications, including heat exchangers, solar collectors, and cooling systems. Although viscosity is a key property that affects heat transfer in nanofluids, it is difficult to predict accurately. Experimental methods provide precise viscosity values but are costly and time-consuming. Therefore, machine learning models have been developed to predict the viscosity of nanofluids more efficiently. The purpose of this research is to develop a Physics-Guided Extreme Gradient Boosting (XGBoost) model (PGXGB) for estimating nanofluid viscosity by incorporating physics-based relationships into the conventional loss functions of XGBoost algorithm. The model is applied to predict the viscosity of water-based Al2O3, TiO2, SiO2, and CuO nanofluids using 792 experimental data points. The results are compared with other machine learning models such as Gradient Boosting Regressor, Extra Tree Regressor, and Nu-Support Vector Regressor. The proposed PGXGB model accurately predicts all data points, demonstrating excellent accuracy and very low prediction error (R2 = 0.992 248, RMSE = 0.0559 336). Furthermore, statistical and graphical error evaluations demonstrate that the PGXGB model outperforms widely cited empirical, theoretical, and soft computing models in terms of both accuracy and validity range. Sensitivity analysis is also conducted to determine the input factors that most significantly affect prediction accuracy. Among the individual variables, nanoparticle volume fraction is found to have the greatest influence.
Deep learning approaches for diagnosing Alzheimer's Disease: A Comparative Study of ResNet50, CNN, and MobileNet Shekhar, Seema Tinker, Deepak Dembla, Sunil Kumar Gupta, Ajay Kumar, Ashish Kumar Handbook of Deep Learning Models for Healthcare Data Processing Disease Prediction Analysis and Applications, 2025 Alzheimer’s disease (AD) is a neurodegenerative condition that gradually impairs cognitive functions and memory and is the leading cause of dementia in the elderly. With an increasingly aging global population, AD is projected to affect 12.7 million adults aged sixty-five and older by 2050. This disease poses a particularly severe challenge in countries like China, where it is the fifth leading cause of death, affecting over fifteen million people aged sixty and over. The financial burden associated with AD treatment is also expected to rise dramatically. In this chapter, the authors propose three deep learning models—ResNet50, CNN, and MobileNet—for the accurate diagnosis of AD. Leveraging the power of deep learning and transfer learning, they aim to enhance the effectiveness of detecting AD at various stages. Performance evaluations reveal that ResNet50 achieved the highest accuracy at 92%, outperforming CNN and MobileNet, which showed accuracy of 85% and 89%, respectively. ResNet50 provides the most balanced precision, recall, and F1 scores across all stages of dementia, while CNN requires optimization. MobileNet, although not as effective as ResNet50, shows potential as a viable option in resource-constrained environments. These results underscore the importance of model selection for early and accurate AD diagnosis, paving the way for timely intervention and improved patient outcomes. Future work should focus on enhancing CNN performance and exploring ensemble methods to further improve classification accuracy.
Predicting viscosity of multi-walled carbon nanotube/water nanofluids using gaussian process regression and emperor penguin optimizer algorithm Shekhar, Koj Sambyo Engineering Research Express, 2025 Thermal management is essential in many industries like energy, transportation, and HVAC systems. Since thermal management is so important, there is a need for improved heat transfer fluids, such as nanofluids. The current study uses machine learning (ML) approaches to predict the viscosity of multi-walled carbon nanotube (MWCNT)-water nanofluids. The dataset comprised 446 experimental data points with characteristics such as weight concentration, temperature, shear time, shear stress, and viscosity were used in current research. The dataset was evaluated with a Gaussian Process Regression (GPR) model and the hyperparameters were further optimized via Emperor Penguin Optimizer (EPO). With the achieved values of R2 of 0.9995, RMSE of 0.0016, and MAPE of 1.89%, the proposed model GPR-EPO, yielded better predictive performance than other machine learning models such as Gradient Boosting Regressor, XGBoost, and Extra Trees Regressor. Additionally, for validation the GPR-EPO model was compared with conventional model like Batchelor and Einstein, it was found more precise and yielded better predictive performance. This study highlights the significant role of AI-driven technique in predicting nanofluid viscosity with accuracy as well as reducing the experimental efforts. The GPR method was found to have the best performance by using radial basis function (RBF) kernel and optimized the hyperparameters with EPO algorithm. Such models can serve as a valuable tool for engineers and researchers to investigate nanofluids and develop efficient thermal management systems.
Extra tree regressor and Tree-structured parzen estimator based machine learning model for predicting nanofluid’s Nusselt number Shekhar, Koj Sambyo, Sunil Kumar Gupta Engineering Research Express, 2025 Boiling is a very effective method of heat transfer process, which is characterized by phase change, due to phase change high transfer rates of heat occur at much smaller temperature differences between the heated surface and the fluid. By introducing nanofluids, which is a dispersion of nanoparticles in basic fluids when incorporated in flow boiling systems, it can be convenient to enhance energy efficiency and ultimately reduce world energy consumption. The intent of this research is to evaluate the practicality of using machine learning (ML) models as a substitute for Computational Fluid Dynamics (CFD) in heat transfer simulation. This research uses Extra Tree Regressor (ETR) with Tree-structured Parzen Estimator algorithm (TPE) to estimate the Nusselt number in water-based nanofluids that consist of Al2O3 and TiO2, nanoparticles. ETR is tree based machine learning algorithm and TPE is used to tune the hyper parameter of ETR. The ETR-TPE model is used to establish a correlation among nanoparticle parameters such as type of nanofluids, Reynolds number, size, volume percentage and Nusselt number. Various statistical measures and scatter plots are used to compare and estimate the performance of the proposed ETR-TPE model. The model has excellent predictive accuracy, as shown by a R2 value of 0.980381 and 0.986313 for Al2O3 and TiO2 respectively. The Root Mean Square Error (RMSE) is computed and found to be 12.96 and 10.01 for Al2O3 and TiO2 respectively. The proposed ETR-TPE model demonstrates a strong correlation in accurately estimating the Nusselt Number based on experimental data.
Implementation of advanced authentication system using OpenCv by capturing motion images Akanksha Sharma, Deepak Dembla, Shekhar 2017 International Conference on Advances in Computing Communications and Informatics Icacci 2017, 2017 Authentication means preserving the systems and information from unwanted unauthorized access, usage, disclosure, disruption, integration, inspection, modification or destruction of the information. The studies have shown that the text passwords are more vulnerable to shoulder surfing, brute force, and dictionary attacks. The password with images are hard to guess and will provide a more secure way to access the recourse, with much more security but they are still vulnerable to shoulder surfing attacks. In proposed system the video is used as a password. OpenCv (open source computer vision) is used, which is an open source to capture video and will extract the frames out of the videos and these frames are stored in an encrypted form using AES(advanced encryption standard) and in turn to authenticate the user JAMA(numerical linear algebra library) is used. Java is used for implementation which is platform independent. The proposed method can be used where the password protection is required like in banking, educational systems, social accounts, Gmail, email, desktops and in every field where the information is required to be protected.
RECENT SCHOLAR PUBLICATIONS
Machine learning approach in predicting nanofluid viscosity of alumina, copper oxide, silicon dioxide, and titanium dioxide using physics constraint-based XGBoost model K Sambyo, S Tinker Journal of Applied Physics 138 (14) , 2025 2025 Citations: 1
Handbook of Deep Learning Models for Healthcare Data Processing: Disease Prediction, Analysis, and Applications A Kumar, D Dembla, S Tinker, SB Khan CRC Press , 2025 2025 Citations: 3
Predicting viscosity of multi-walled carbon nanotube/water nanofluids using gaussian process regression and emperor penguin optimizer algorithm Shekhar, K Sambyo Engineering Research Express 7 (1), 015281 , 2025 2025 Citations: 2
Extra Tree Regressor and Tree-structured Parzen Estimator based Machine Learning Model for Predicting Nanofluid’s Nusselt Number S Shekhar, K Sambyo, SK Gupta Engineering Research Express , 2025 2025 Citations: 3
Predicting nanofluid density in ethylene glycol-based oxide nanoparticles using machine learning approach: GBR–GSO models Shekhar, S Koj, RP Sharma, Mishra SR Journal of Thermal Analysis and Calorimetry, 1-18 , 2025 2025 Citations: 4
Nusselt number estimation using a GBR-GSO-based machine learning predictive model in alumina and titania nanofluids in a boiling process M Dadhich, Shekhar, K Sambyo, V Sharma, G Jain Journal of Thermal Analysis and Calorimetry 148 (24), 14225-14242 , 2023 2023 Citations: 5
Object Detection and Tracking Techniques: A Review S Akanksha Sharma, Dr. Deepak Dembla International Journal of Innovative Research in Computer and Communication … , 2017 2017
New stegnography technique using dct quantization with rsa encryption algorithm DST Shekhar Chander 2nd International Conference on Advance Trends in Engg. & Technology (ICATET … , 2014 2014
Stegnography technique using dct quantization and modified Fibonacci series decoder SC Dr. Shiv Kumar 2nd International Conference on Advance Trends in Engg. & Technology (ICATET … , 2014 2014
A New Encryption Decryption Algorithm for data hiding S Chander RAICS ,JNIT college,Jaipur , 2012 2012
Implementation of advanced authentication system using opencv by capturing motion images 2017 Citations: 2
MOST CITED SCHOLAR PUBLICATIONS
Nusselt number estimation using a GBR-GSO-based machine learning predictive model in alumina and titania nanofluids in a boiling process M Dadhich, Shekhar, K Sambyo, V Sharma, G Jain Journal of Thermal Analysis and Calorimetry 148 (24), 14225-14242 , 2023 2023 Citations: 5
Predicting nanofluid density in ethylene glycol-based oxide nanoparticles using machine learning approach: GBR–GSO models Shekhar, S Koj, RP Sharma, Mishra SR Journal of Thermal Analysis and Calorimetry, 1-18 , 2025 2025 Citations: 4
Handbook of Deep Learning Models for Healthcare Data Processing: Disease Prediction, Analysis, and Applications A Kumar, D Dembla, S Tinker, SB Khan CRC Press , 2025 2025 Citations: 3
Extra Tree Regressor and Tree-structured Parzen Estimator based Machine Learning Model for Predicting Nanofluid’s Nusselt Number S Shekhar, K Sambyo, SK Gupta Engineering Research Express , 2025 2025 Citations: 3
Predicting viscosity of multi-walled carbon nanotube/water nanofluids using gaussian process regression and emperor penguin optimizer algorithm Shekhar, K Sambyo Engineering Research Express 7 (1), 015281 , 2025 2025 Citations: 2
Implementation of advanced authentication system using opencv by capturing motion images 2017 Citations: 2
Machine learning approach in predicting nanofluid viscosity of alumina, copper oxide, silicon dioxide, and titanium dioxide using physics constraint-based XGBoost model K Sambyo, S Tinker Journal of Applied Physics 138 (14) , 2025 2025 Citations: 1
Object Detection and Tracking Techniques: A Review S Akanksha Sharma, Dr. Deepak Dembla International Journal of Innovative Research in Computer and Communication … , 2017 2017
New stegnography technique using dct quantization with rsa encryption algorithm DST Shekhar Chander 2nd International Conference on Advance Trends in Engg. & Technology (ICATET … , 2014 2014
Stegnography technique using dct quantization and modified Fibonacci series decoder SC Dr. Shiv Kumar 2nd International Conference on Advance Trends in Engg. & Technology (ICATET … , 2014 2014
A New Encryption Decryption Algorithm for data hiding S Chander RAICS ,JNIT college,Jaipur , 2012 2012
