Charan Teja Nagisettygari
Research Subjects
Charan Teja Nagisettygari has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Noor Ul Amin
Taylor's University, Malaysia
3 shared publications - Addy Arif Bin Mahathir
Taylor's University, Malaysia
2 shared publications - Sai Rama Mahalingam
Taylor's University, Malaysia
2 shared publications - Sivamuganathan Mohana Dass
Taylor's University, Malaysia
2 shared publications - Asfa Haikal Bin Asrul Hazli
Taylor's University, Malaysia
1 shared publication - Darrshan A/L Mahendran
Taylor's University, Malaysia
1 shared publication
Latest Publications
- Open Access
- 2 September 2025
- Published by MDPI AG in Preprints.org
Real-Time Big Data Technologies in Retail: Enhancing Personalization and Operational Efficiency
This study explores the integration of Big Data Technologies (BDT) in the retail industry, emphasizing their role in enabling real-time data processing and personalized customer experiences. The project examines how technologies such as Apache Hive, Impala, and Spark can process large-scale retail datasets to identify purchasing patterns, refine customer segmentation, and facilitate predictive analytics. The paper introduces four types of analytics—descriptive, predictive, prescriptive, and diagnostic—alongside machine learning algorithms, including supervised, unsupervised, and reinforcement learning, as well as Natural Language Processing (NLP). These tools collectively enable retailers to deliver dynamic, personalized marketing, enhance operational efficiency, and increase revenue. A practical experimentation using a Kaggle-based retail dataset evaluates the comparative performance of Hive, Impala, and Spark through SQL-like operations and MapReduce batch processing. Results show that while Impala excels in speed, Spark provides flexibility for complex data science tasks. The study concludes with an analysis of key considerations such as data storage, privacy, integration, and processing speeds necessary for effective big data deployment in retail environments.
- 2 September 2025
- Published by MDPI AG in Preprints.org
Open AccessReal-Time Big Data Technologies in Retail: Enhancing Personalization and Operational Efficiency
This study explores the integration of Big Data Technologies (BDT) in the retail industry, emphasizing their role in enabling real-time data processing and personalized customer experiences. The project examines how technologies such as Apache Hive, Impala, and Spark can process large-scale retail datasets to identify purchasing patterns, refine customer segmentation, and facilitate predictive analytics. The paper introduces four types of analytics—descriptive, predictive, prescriptive, and diagnostic—alongside machine learning algorithms, including supervised, unsupervised, and reinforcement learning, as well as Natural Language Processing (NLP). These tools collectively enable retailers to deliver dynamic, personalized marketing, enhance operational efficiency, and increase revenue. A practical experimentation using a Kaggle-based retail dataset evaluates the comparative performance of Hive, Impala, and Spark through SQL-like operations and MapReduce batch processing. Results show that while Impala excels in speed, Spark provides flexibility for complex data science tasks. The study concludes with an analysis of key considerations such as data storage, privacy, integration, and processing speeds necessary for effective big data deployment in retail environments.
- Open Access
- 2 September 2025
- Published by MDPI AG in Preprints.org
Data Mining for Insights into Accidental Drug Mortality Trends in the U.S.
This research project addresses the use of data mining techniques for studying accidental opioid-related deaths in the United States using the "Accidental_Drug_Related_Deaths" dataset. More specifically, we seek to identify the distinctions in patterns and associated factors between accidental overdose incidents and intentional overdose incidents (suicide, undetermined intent, homicide). During the time period being analyzed, we determined that there were more than 90% of overdose deaths that were classified as accidental in 2022. The main goal of this project is to utilize classification models to predict whether or not opioids are likely to be involved in an incident of overdose based on the identifying features of the demographic and situational features. This prediction will allow for more timely and targeted medical interventions with the individuals experiencing an overdose incident. The analysis considers class imbalance, using SMOTE-Tomek Links, models each of the classification in a single analysis, including, Random Forest, XGBoost, Logistic Regression, SVM, and MLP Classifier, while hyper-parameter tuning the models toward maximum recall. In addition to the classification models, we applied several algorithms for anomaly detection (OneClassSVM, Isolation Forest, Elliptic Envelope) to describe the possibility of rare drug combinations that could be potentially dangerous. Overall, we demonstrated that when handled carefully, there is a range of preprocessing, feature selection, and machine learning approaches for anomaly detection that made it possible to better identify risk factors for opioid-related overdose, which could be used to support a public health-based area of intervention, data-driven programming for states that are facing the opioid crisis.
- 2 September 2025
- Published by MDPI AG in Preprints.org
Open AccessData Mining for Insights into Accidental Drug Mortality Trends in the U.S.
This research project addresses the use of data mining techniques for studying accidental opioid-related deaths in the United States using the "Accidental_Drug_Related_Deaths" dataset. More specifically, we seek to identify the distinctions in patterns and associated factors between accidental overdose incidents and intentional overdose incidents (suicide, undetermined intent, homicide). During the time period being analyzed, we determined that there were more than 90% of overdose deaths that were classified as accidental in 2022. The main goal of this project is to utilize classification models to predict whether or not opioids are likely to be involved in an incident of overdose based on the identifying features of the demographic and situational features. This prediction will allow for more timely and targeted medical interventions with the individuals experiencing an overdose incident. The analysis considers class imbalance, using SMOTE-Tomek Links, models each of the classification in a single analysis, including, Random Forest, XGBoost, Logistic Regression, SVM, and MLP Classifier, while hyper-parameter tuning the models toward maximum recall. In addition to the classification models, we applied several algorithms for anomaly detection (OneClassSVM, Isolation Forest, Elliptic Envelope) to describe the possibility of rare drug combinations that could be potentially dangerous. Overall, we demonstrated that when handled carefully, there is a range of preprocessing, feature selection, and machine learning approaches for anomaly detection that made it possible to better identify risk factors for opioid-related overdose, which could be used to support a public health-based area of intervention, data-driven programming for states that are facing the opioid crisis.
- Open Access
- 22 April 2025
- Published by MDPI AG in Preprints.org
Integrating Cognitive Computing into Hospital Information Management Systems: A Comparative and Architectural Approach Using IBM Watson and Microsoft Azure
The integration of cognitive computing into Hospital Information Management Systems (HIMS) is a revolutionary opportunity for the healthcare industry to enhance operational efficiency, diagnosis speed, and patient outcomes. This article presents comparative strengths and limitations of IBM Watson and Microsoft Azure, two leading cognitive platforms, in healthcare settings. The paper examines existing legacy systems like Meditech and the limitations of legacy architectures leading to real-time analytics, interoperability, and scalability challenges. A new hybrid system architecture is envisioned, combining IBM Watson's strong AI-driven analytics and NLP capabilities with Microsoft Azure's secure, scalable cloud environment and compliance models. The hybrid architecture supports end-to-end integration of data, enhances decision-making through predictive analytics, and provides improved system performance. In addition, the paper outlines an implementation plan, cost advantages, and ethical considerations to ensure secure, unbiased, and transparent AI use in hospitals.
- 22 April 2025
- Published by MDPI AG in Preprints.org
Open AccessIntegrating Cognitive Computing into Hospital Information Management Systems: A Comparative and Architectural Approach Using IBM Watson and Microsoft Azure
The integration of cognitive computing into Hospital Information Management Systems (HIMS) is a revolutionary opportunity for the healthcare industry to enhance operational efficiency, diagnosis speed, and patient outcomes. This article presents comparative strengths and limitations of IBM Watson and Microsoft Azure, two leading cognitive platforms, in healthcare settings. The paper examines existing legacy systems like Meditech and the limitations of legacy architectures leading to real-time analytics, interoperability, and scalability challenges. A new hybrid system architecture is envisioned, combining IBM Watson's strong AI-driven analytics and NLP capabilities with Microsoft Azure's secure, scalable cloud environment and compliance models. The hybrid architecture supports end-to-end integration of data, enhances decision-making through predictive analytics, and provides improved system performance. In addition, the paper outlines an implementation plan, cost advantages, and ethical considerations to ensure secure, unbiased, and transparent AI use in hospitals.