Publications

Here are some of my published research articles in Machine Learning, and Data Science. You can explore more of my work, including technical implementations and projects, on my GitHub account.

December 9, 2023

International Journal of Applied Engineering & Technology

Title: Supply Chain Management Through Data Science And Artificial Intelligence: A Data-Driven Approach

This research investigates the optimization of supply chain processes through advanced data analytics and machine learning methodologies. We focus on enhancing supply chain efficiency and resilience by employing predictive analytics to analyze large-scale datasets, identify operational bottlenecks, and forecast demand variability. A comprehensive framework is developed that integrates statistical process control, machine learning algorithms, and real-time data processing techniques, utilizing tools such as Python, R, and SQL for data manipulation and analysis. The study employs a hybrid approach combining descriptive and prescriptive analytics to evaluate supply chain performance metrics, including lead time, inventory turnover, and order fulfillment rates. Case studies from diverse sectors, such as manufacturing and logistics, are utilized to demonstrate the efficacy of data-driven decision-making. Our findings underscore the critical importance of data integration, machine learning models, and simulation techniques in achieving supply chain agility and responsiveness. This research paves the way for the implementation of advanced analytics in optimizing supply chain networks and enhancing overall operational efficiency.

ISSN: 2633-4828
Keywords: Suppply Chain Management, Predictive Analytics, Inventory Management, Artificial Intelligence
Publisher: International Journal of Advanced Engineering and Technology (IJAET)
Published (Month, Year): December, 2023

This paper has been published in the International Journal of Advanced Engineering and Technology (IJAET Vol.5 No. 4, December 2023 Edition) and is available online. (Refer to the link below for the full paper)

September 20, 2024

IEEE Digital Xplore Library

Title: Predictive Maintenence in Automotive using Machine Learning

This research focuses on applying advanced Machine Learning (ML) techniques for predictive maintenance in automotive systems to minimize unplanned downtime. High-frequency time-series sensor data from critical components like engines and brakes are analyzed using supervised learning models such as Random Forest, Support Vector Machines (SVM), and Long Short-Term Memory (LSTM) networks. Data preprocessing, including noise reduction and feature engineering, enhances model accuracy, while Grid Search and Cross-Validation optimize hyperparameters. Feature importance is further assessed using SHAP to ensure model interpretability. The study uses Python libraries like Scikit-learn, TensorFlow, and PySpark for model training and leverages distributed computing on Apache Hadoop and Spark for large-scale data handling. Models are deployed on cloud platforms like AWS Lambda for real-time failure prediction, demonstrating how predictive maintenance can significantly reduce failure risks, improve vehicle reliability, and lower maintenance costs. This paper has been accepted for publication and will appear in the IEEE Journal in February 2025.

ISSN: 2169-3536
Manuscript ID: Access-2024-36520
Keywords: Predictive Maintenance, Automotive Systems, Machine Learning, Supervised Learning, Random Forest, LSTM, Data Engineering, Feature Importance
Publisher: IEEE Journal
Accepted (Month, Year): September, 2024

(Refer to the link below for the IEEE portal )

IEEE Portal