Article Per Year (5 Year)
p-Index From 2021 - 2026
1.813
P-Index
This Author published in this journals
All Journal Journal of Multidisciplinary Science: MIKAILALSYS Asian Journal of Science, Technology, Engineering, and Art Mikailalsys Journal of Advanced Engineering International Mikailalsys Journal of Mathematics and Statistics International Journal of Education, Management, and Technology African Multidisciplinary Journal of Sciences and Artificial Intelligence Open Access DRIVERset
Suresh Kumar Sahani
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Arts Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Computer Science & IT Education Electrical & Electronics Engineering Engineering Environmental Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Physics Social Sciences Other

Published : 13 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 13 Documents
Search

 1   2 
Model-Free Reinforcement Learning for Parabolic Trajectory Optimization in Robotic Arms Aadarsh Karn; Neha Shah; Dilip Kumar Sah; Suresh Kumar Sahani
African Multidisciplinary Journal of Sciences and Artificial Intelligence Vol 3 No 1 (2026): African Multidisciplinary Journal of Sciences and Artificial Intelligence
Publisher : Darul Yasin Al Sys

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58578/amjsai.v3i1.9338

Abstract

Robotic arms are widely employed in applications that require smooth motion and energy-efficient operation, particularly in tasks such as object throwing and liquid dispensing, where movement often follows a curved path toward a target point. However, conventional trajectory planning methods that rely on predefined mathematical equations may not accurately represent real-world robotic systems due to uncertainties and payload variations. This study aims to optimize the trajectory of a robotic arm moving along a parabolic path using reinforcement learning and to evaluate whether this approach can successfully learn improved trajectory patterns during motion. The research integrates initial classical physics principles for curved motion with a reinforcement learning framework to enhance trajectory following toward a desired point. The findings indicate that reinforcement learning can effectively learn optimized trajectory paths and improve the motion performance of the robotic arm. The study concludes that reinforcement learning offers a promising approach for achieving smoother robotic motion with satisfactory energy efficiency under dynamic conditions. This work contributes to the advancement of intelligent motion planning by demonstrating the potential of reinforcement learning to improve trajectory optimization in robotic systems operating under practical uncertainties.
Mathematical Analysis of the Impact of Climate Factors and Agricultural Practices on Rice Yield in Nepal: A Time Series Data Analysis Omkar Poudel; Nand Kishor Kumar; Pradeep Acharya; Deep Raj Sharma; Suresh Kumar Sahani
Journal of Multidisciplinary Science: MIKAILALSYS Vol 3 No 2 (2025): Journal of Multidisciplinary Science: MIKAILALSYS
Publisher : Darul Yasin Al Sys

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58578/mikailalsys.v3i2.5725

Abstract

Rice is a staple food and a crucial element of Nepal’s agrarian economy; however, its yield is significantly affected by climatic factors such as rainfall and temperature, as well as agricultural practices like pesticide use. Understanding these dynamics is essential for sustaining productivity in the face of climate change. This study employs an Autoregressive Distributed Lag (ARDL) model to analyze 33 years of time-series data (1990–2022), focusing on key variables including rice yield, temperature, rainfall, and pesticide use, all derived from secondary data sources. Diagnostic tests confirmed normality (????=0.06), absence of serial correlation (????=0.58), and homoscedasticity (????=0.68), with stability validated through CUSUM and CUSUMSQ tests. The results indicate that temperature has a significant positive long-term impact on rice yield (????=2181.48, ????<0.05), suggesting that moderate warming can enhance productivity. Rainfall exerts a marginal positive effect (????=5.10, ????=0.05), while pesticide use shows a strong correlation with yield (????=17.70, ????<0.01). The Granger Causality Test identifies temperature (????=7.76, ????<0.01) and pesticide use (????=11.25, ????<0.01) as critical predictors of rice yield. These findings demonstrate that while temperature and pesticide use significantly affect rice yield, the impact of rainfall is diminished due to effective irrigation systems. Nevertheless, the heavy reliance on pesticides raises sustainability concerns, underscoring the necessity for integrated pest management and environmental safeguards. This study advocates for the adoption of climate-smart agricultural practices, enhancement of irrigation infrastructure, and promotion of sustainable pesticide management, offering actionable insights for policymakers to devise adaptive strategies that bolster resilience and productivity in Nepal’s rice sector.
Physics-Informed Neural Networks for Solving Stochastic Differential Equations Rishav Jha; Kameshwar Sahani; Suresh Kumar Sahani; Ravi Kumar Raj; Dilip Kumar Sah
Journal of Multidisciplinary Science: MIKAILALSYS Vol 4 No 2 (2026): Journal of Multidisciplinary Science: MIKAILALSYS
Publisher : Darul Yasin Al Sys

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58578/mikailalsys.v4i2.10240

Abstract

Stochastic differential equations (SDEs) are fundamental tools for modeling systems with inherent randomness across finance, physics, biology, and engineering; however, traditional numerical methods, including Monte Carlo simulations and Euler–Maruyama schemes, often face substantial computational challenges, particularly in high-dimensional settings. This study aims to develop and evaluate a comprehensive Physics-Informed Neural Networks (PINNs) framework as an efficient approach for solving SDEs. The proposed methodology embeds physical laws and stochastic dynamics directly into the neural network architecture through a carefully designed loss function that incorporates PDE residuals, initial conditions, and boundary constraints. The framework was evaluated through extensive numerical experiments on benchmark problems, including geometric Brownian motion, Ornstein–Uhlenbeck processes, and multi-dimensional stochastic systems. The findings indicate that PINNs achieve accuracy comparable to traditional numerical methods while providing substantial computational advantages, especially for parametric studies and real-time applications. Across all test cases, relative L2 errors consistently remained below 2%, and computational speedups reached up to 1000 times compared with Monte Carlo methods after network training. The proposed framework also demonstrated strong scalability for higher-dimensional problems, addressing the curse of dimensionality commonly associated with conventional numerical approaches. This study concludes that PINNs offer a promising paradigm for the efficient and accurate solution of stochastic differential equations. Its contribution lies in advancing scientific machine learning for stochastic modeling and opening further opportunities for uncertainty quantification and real-time computational applications.
Co-Authors Aadarsh Karn Bardan Sah Deep Raj Sharma Dilip Kumar Sah Kameshwar Sahani Nand Kishor Kumar Neha Shah Omkar Poudel Pradeep Acharya Praveen Sah Praveen Shah Rajnandani Das Ravi Kumar Raj Rishav Jha Ritika Jayswal Satyam Thakur