Saurabh Pratap Singh Rathore
Saurabh Pratap Singh Rathore has a total of 82 co-authors. Here are the top co-authors by number of shared publications:
- Priyanka Kaushik
NIMS University Rajasthan,Dept. of Computer Science Engineering, Marik NIET,Jaipur,India
9 shared publications Priyanka Kaushik
Department of Computer Science & Engineering, Marik & NIET, NIMS University Rajasthan, Jaipur, India
3 shared publications- Rachna Rathore
Jiwaji University
3 shared publications Bhawesh Kumawat
Madhav University,Faculty of Engineering Technology,Aburoad,Rajasthan,India
2 shared publicationsDafik
Universitas Jember
2 shared publications- Pooja Bhardwaj
Maitreyi College,Delhi,India
2 shared publications
Latest Publications
- Open Access
- 6 June 2026
- Published by Elsevier in Journal of the Formosan Medical Association
Comment on “Developing machine learning-enhanced WHODAS 2.0 short forms for persons with dementia”
- 6 June 2026
- Published by Elsevier in Journal of the Formosan Medical Association
Open AccessComment on “Developing machine learning-enhanced WHODAS 2.0 short forms for persons with dementia”
- Open Access
- 29 April 2026
- Published by International Consortium of Academic Professionals for Scientific Research
- p. 01-87
Blue Algorithms: AI in Aquatic Systems
Blue Algorithms: AI in Aquatic Systems is a broad and perspective-looking study on water bodies as dynamic and adaptive natural systems that are complex interactions of physical, chemical, biological, and anthropogenic processes. Going beyond the traditional hydrological views, the book places rivers, lakes, oceans, wetlands, and groundwater systems in the role of constantly evolving entities with self-regulating characteristics and feedback-based responses, and resiliency to environmental factors. The book applies artificial intelligence and hydrology, aquatic ecology, geospatial science, and environmental engineering to reveal how data-driven and hybrid AI models are changing the ways in which the spatial and temporal aspects of aquatic systems are observed, interpreted, and managed. The book focuses on mechanistic knowledge and predictive intelligence and how machine learning, digital twins, and sophisticated sensing technologies can be used to provide better insights about processes, early warning signs, and adaptive decision-making. Governance, ethics and data stewardship are also accorded equal attention, which considers the impacts of digital water infrastructures on the societies. In general, the book presents a scientifically sound system of resilience, clarity and future readiness of water management in the era of climate change, urbanization, and global environmental transformation.
- 29 April 2026
- Published by International Consortium of Academic Professionals for Scientific Research
- p. 01-87
Open AccessBlue Algorithms: AI in Aquatic Systems
Blue Algorithms: AI in Aquatic Systems is a broad and perspective-looking study on water bodies as dynamic and adaptive natural systems that are complex interactions of physical, chemical, biological, and anthropogenic processes. Going beyond the traditional hydrological views, the book places rivers, lakes, oceans, wetlands, and groundwater systems in the role of constantly evolving entities with self-regulating characteristics and feedback-based responses, and resiliency to environmental factors. The book applies artificial intelligence and hydrology, aquatic ecology, geospatial science, and environmental engineering to reveal how data-driven and hybrid AI models are changing the ways in which the spatial and temporal aspects of aquatic systems are observed, interpreted, and managed. The book focuses on mechanistic knowledge and predictive intelligence and how machine learning, digital twins, and sophisticated sensing technologies can be used to provide better insights about processes, early warning signs, and adaptive decision-making. Governance, ethics and data stewardship are also accorded equal attention, which considers the impacts of digital water infrastructures on the societies. In general, the book presents a scientifically sound system of resilience, clarity and future readiness of water management in the era of climate change, urbanization, and global environmental transformation.
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4th, 1-5
Design and Implementation of an Intelligent Vision-Based System for Plant Leaf Disease Recognition and Classification Using Advanced Learning Models
Plant leaf diseases pose a grave challenge to the agricultural output that causes huge losses in quality and quantity of crops produce. The outdated detection mechanisms primarily rely on the manual inspection of the agricultural experts who are both period overwhelming, prone to humanoid error and inapplicability in the large-scale farming environment. To solve these problems, the current research paper will focus on how advanced machine learning methods can be applied to image processing to perform the precise and automatic recognition of plant leaf illnesses. The suggested model will be based on a stepwise workflow including the collection of images, their preprocessing and feature extraction, and classification with a significant accent on the use of convolutional neural networks. Publicly available datasets, such as Plant Village, are utilized in order to compare the performance of various strategies in learning. Furthermore, the study explains why the data augmentation strategy and transfer learning are important to enhance the strength of the models, prevent overfitting, and improve their overall classification performance. The experimental results show that the developed method is correct in identifying diseases with over 98 percent and its computational potentials are adequate to be used in real time. These findings are a pointer that the proposed system is dependable, scalable, and cost-effective to perform automated diagnosis of plant diseases. This framework enables one to make informed decisions in a manner that would result in the advancement of sustainable and precision-based agri-farming practices since it enables identification of the problem and timely solutions to the same through the integration of evidence-based data in agricultural management.
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4th, 1-5
Design and Implementation of an Intelligent Vision-Based System for Plant Leaf Disease Recognition and Classification Using Advanced Learning Models
Plant leaf diseases pose a grave challenge to the agricultural output that causes huge losses in quality and quantity of crops produce. The outdated detection mechanisms primarily rely on the manual inspection of the agricultural experts who are both period overwhelming, prone to humanoid error and inapplicability in the large-scale farming environment. To solve these problems, the current research paper will focus on how advanced machine learning methods can be applied to image processing to perform the precise and automatic recognition of plant leaf illnesses. The suggested model will be based on a stepwise workflow including the collection of images, their preprocessing and feature extraction, and classification with a significant accent on the use of convolutional neural networks. Publicly available datasets, such as Plant Village, are utilized in order to compare the performance of various strategies in learning. Furthermore, the study explains why the data augmentation strategy and transfer learning are important to enhance the strength of the models, prevent overfitting, and improve their overall classification performance. The experimental results show that the developed method is correct in identifying diseases with over 98 percent and its computational potentials are adequate to be used in real time. These findings are a pointer that the proposed system is dependable, scalable, and cost-effective to perform automated diagnosis of plant diseases. This framework enables one to make informed decisions in a manner that would result in the advancement of sustainable and precision-based agri-farming practices since it enables identification of the problem and timely solutions to the same through the integration of evidence-based data in agricultural management.
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4th, 1-6
Autonomous CNC Machine Tools Powered by AI for Proactive Maintenance and Self-Restoration
In the modern manufacturing environment, ensuring the efficient operation of CNC (Computer Numerical Control) machines is vital for reducing downtime and improving productivity. This study introduces an innovative framework that combines artificial intelligence (AI) with digital twin technology to support predictive maintenance in CNC systems. Using IoT (Internet of Things) sensors, continuous operational data are gathered from CNC machines to build a dynamic digital twin that mirrors real-time machine behavior and performance. Advanced machine learning methods, particularly XGBoost, are applied to both historical and live data to identify early signs of failure and to optimize maintenance planning. The proposed approach improves the reliability of maintenance predictions while substantially lowering maintenance expenses and unexpected machine outages. This work advances smart manufacturing research and emphasizes the significance of AI-based solutions in strengthening predictive maintenance practices in industrial applications.
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4th, 1-6
Autonomous CNC Machine Tools Powered by AI for Proactive Maintenance and Self-Restoration
In the modern manufacturing environment, ensuring the efficient operation of CNC (Computer Numerical Control) machines is vital for reducing downtime and improving productivity. This study introduces an innovative framework that combines artificial intelligence (AI) with digital twin technology to support predictive maintenance in CNC systems. Using IoT (Internet of Things) sensors, continuous operational data are gathered from CNC machines to build a dynamic digital twin that mirrors real-time machine behavior and performance. Advanced machine learning methods, particularly XGBoost, are applied to both historical and live data to identify early signs of failure and to optimize maintenance planning. The proposed approach improves the reliability of maintenance predictions while substantially lowering maintenance expenses and unexpected machine outages. This work advances smart manufacturing research and emphasizes the significance of AI-based solutions in strengthening predictive maintenance practices in industrial applications.
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4th, 1-6
Smart Farming Through Real-Time Deep Learning-Based Crop Intelligence and Yield Analytics
The paper offers a research on the use of machine learning techniques to predict the harvest of rice crop using sensor based data of temperature, humidity, and water. Several models are experimented according to accuracy, precision, recall and F1-score, which are a random Forest, Support Vector machines, Gradient Boosting and Neural networks. The results indicate that machine learning is useful in predicting yield of rice, and the highest performance is associated with theRandom Forest. The paper explains the importance of good data in sensors, selection of a model, and large and diverse data sets in the higher precision of prediction. A combination of sensor technology and machine learning will see the realization of data-driven agriculture, improved irrigation planning, better resource management, and improved sustainable farming practice.
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4th, 1-6
Smart Farming Through Real-Time Deep Learning-Based Crop Intelligence and Yield Analytics
The paper offers a research on the use of machine learning techniques to predict the harvest of rice crop using sensor based data of temperature, humidity, and water. Several models are experimented according to accuracy, precision, recall and F1-score, which are a random Forest, Support Vector machines, Gradient Boosting and Neural networks. The results indicate that machine learning is useful in predicting yield of rice, and the highest performance is associated with theRandom Forest. The paper explains the importance of good data in sensors, selection of a model, and large and diverse data sets in the higher precision of prediction. A combination of sensor technology and machine learning will see the realization of data-driven agriculture, improved irrigation planning, better resource management, and improved sustainable farming practice.
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4th, 1-6
Personalized Alzheimer's Disease Treatment Planning Through Predictive Modeling and Explainable Artificial Intelligence
This study presents a predictive modeling framework designed to support personalized treatment planning for Alzheimer's disease (AD) through the use of machine learning and natural language processing (NLP). Alzheimer's disease is a steadily worsening neurodegenerative condition that demands individualized therapeutic strategies for effective care. The proposed system combines a fine-tuned OPT-350M language model with an XGBoost classifier to determine dementia severity, achieving a high classification accuracy of 97.36%. The framework incorporates important clinical and genetic indicators such as Mini-Mental State Examination (MMSE) scores, Clinical Dementia Rating (CDR), APOE4 genotype status, and polygenic risk scores (PRS) to produce tailored treatment recommendations. To improve model performance and ensure interpretability, the approach employs advanced methods including polynomial feature generation, hyperparameter tuning, and SHAP-based explainability analysis. In addition, the system offers both medication-based and lifestyle-focused intervention suggestions, enabling transparent, data-driven clinical decision support. Overall, this framework shows strong promise in assisting healthcare providers with delivering patient-specific care, enhancing clinical outcomes, and improving the quality of life for individuals living with Alzheimer's disease.
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4th, 1-6
Personalized Alzheimer's Disease Treatment Planning Through Predictive Modeling and Explainable Artificial Intelligence
This study presents a predictive modeling framework designed to support personalized treatment planning for Alzheimer's disease (AD) through the use of machine learning and natural language processing (NLP). Alzheimer's disease is a steadily worsening neurodegenerative condition that demands individualized therapeutic strategies for effective care. The proposed system combines a fine-tuned OPT-350M language model with an XGBoost classifier to determine dementia severity, achieving a high classification accuracy of 97.36%. The framework incorporates important clinical and genetic indicators such as Mini-Mental State Examination (MMSE) scores, Clinical Dementia Rating (CDR), APOE4 genotype status, and polygenic risk scores (PRS) to produce tailored treatment recommendations. To improve model performance and ensure interpretability, the approach employs advanced methods including polynomial feature generation, hyperparameter tuning, and SHAP-based explainability analysis. In addition, the system offers both medication-based and lifestyle-focused intervention suggestions, enabling transparent, data-driven clinical decision support. Overall, this framework shows strong promise in assisting healthcare providers with delivering patient-specific care, enhancing clinical outcomes, and improving the quality of life for individuals living with Alzheimer's disease.
- Top Cited PapersOpen Access
- 14 January 2026
- Published by International Consortium of Academic Professionals for Scientific Research in International Journal for Global Academic & Scientific Research
- Vol. 4 (4) , 135-158
Enhancing Product Availability Perception in Small-Scale E-Commerce Through Consumer Behavior-Informed AI Predictions
The present study is trying to conduct a study on the impact of AI-based product availability systems on customer trust and loyalty on seasonal retail microenterprises. Based on the common attributes, the study uses structural equation modelling (SEM) on the data gathered on 300-400 customers who used AI to shop in seasonal retail chains and identify six latent variables that forecasting, communication, preparedness, stability, trust and loyalty. The analysis shows that the positive effect of AI-driven predictive analytics and open communication on the customer trust is high, and the readiness and site stability are the mediating variables that contribute to this effect. The factor of trust comes out as one of the predictors of consumer loyalty, affirming to the fact that reliability in the technological aspect of the availability management is a precursor to long-term dedication. Based on the literature on the service quality and use of AI as means of operational aid and impression-forming elements, the given work suggests that the retailers should combine predictive AI with customer-centered open communication channels to become more loyal and competitive in the seasonal markets.
- 14 January 2026
- Published by International Consortium of Academic Professionals for Scientific Research in International Journal for Global Academic & Scientific Research
- Vol. 4 (4) , 135-158
Top Cited PapersOpen AccessEnhancing Product Availability Perception in Small-Scale E-Commerce Through Consumer Behavior-Informed AI Predictions
The present study is trying to conduct a study on the impact of AI-based product availability systems on customer trust and loyalty on seasonal retail microenterprises. Based on the common attributes, the study uses structural equation modelling (SEM) on the data gathered on 300-400 customers who used AI to shop in seasonal retail chains and identify six latent variables that forecasting, communication, preparedness, stability, trust and loyalty. The analysis shows that the positive effect of AI-driven predictive analytics and open communication on the customer trust is high, and the readiness and site stability are the mediating variables that contribute to this effect. The factor of trust comes out as one of the predictors of consumer loyalty, affirming to the fact that reliability in the technological aspect of the availability management is a precursor to long-term dedication. Based on the literature on the service quality and use of AI as means of operational aid and impression-forming elements, the given work suggests that the retailers should combine predictive AI with customer-centered open communication channels to become more loyal and competitive in the seasonal markets.
- Open Access
- 14 January 2026
- Published by International Consortium of Academic Professionals for Scientific Research in International Journal for Global Academic & Scientific Research
- Vol. 4 (4) , 112-134
Human-Centric AI Forecasting Models for Enhancing Product Availability Perception in Seasonal Retail Microenterprises
Problem Statement: This study indicates towards the questions like How do awareness of AI and trust in the predictions of components of AI affect consumer perceptions regarding product availability in small-scale sessional e-commerce retail store? And how perceived product availability mediates the relationship between AI trust and customer loyalty Methodology: Using Structural Equation Modelling (SEM) to test the proposed framework, this study looks at how usefulness, efficiency, service responsiveness, and loyalty are related to each other when people shop online. Findings: The final model shows that service responsiveness has a strong positive effect on loyalty (β = 0.864, p < 0.001), while efficiency (β = 0.748, p < 0.001) and usefulness (β = 0.200, p = 0.01) have a strong negative effect on service responsiveness. Also, usefulness is a strong predictor of efficiency (β = 0.816, p < 0.001), which means that perceived usefulness leads to higher efficiency, which leads to higher service responsiveness, which leads to higher customer loyalty. These results are in line with earlier studies on the Technology Acceptance Model ([14]; [56]) and service quality frameworks ([48]). They show how important functional and experiential features are for building long-term customer relationships. Implications: The model gives e-commerce managers useful information, showing that spending money to make things run more smoothly and provide better service can lead to big increases in customer loyalty, no matter what demographic group they belong to.
- 14 January 2026
- Published by International Consortium of Academic Professionals for Scientific Research in International Journal for Global Academic & Scientific Research
- Vol. 4 (4) , 112-134
Open AccessHuman-Centric AI Forecasting Models for Enhancing Product Availability Perception in Seasonal Retail Microenterprises
Problem Statement: This study indicates towards the questions like How do awareness of AI and trust in the predictions of components of AI affect consumer perceptions regarding product availability in small-scale sessional e-commerce retail store? And how perceived product availability mediates the relationship between AI trust and customer loyalty Methodology: Using Structural Equation Modelling (SEM) to test the proposed framework, this study looks at how usefulness, efficiency, service responsiveness, and loyalty are related to each other when people shop online. Findings: The final model shows that service responsiveness has a strong positive effect on loyalty (β = 0.864, p < 0.001), while efficiency (β = 0.748, p < 0.001) and usefulness (β = 0.200, p = 0.01) have a strong negative effect on service responsiveness. Also, usefulness is a strong predictor of efficiency (β = 0.816, p < 0.001), which means that perceived usefulness leads to higher efficiency, which leads to higher service responsiveness, which leads to higher customer loyalty. These results are in line with earlier studies on the Technology Acceptance Model ([14]; [56]) and service quality frameworks ([48]). They show how important functional and experiential features are for building long-term customer relationships. Implications: The model gives e-commerce managers useful information, showing that spending money to make things run more smoothly and provide better service can lead to big increases in customer loyalty, no matter what demographic group they belong to.
- 14 January 2026
- Published by Springer Nature
- p. 329-354
Future Prospects and Advancing Research in Environmental Education and Sustainable Development
- 14 January 2026
- Published by Springer Nature
- p. 329-354
Future Prospects and Advancing Research in Environmental Education and Sustainable Development