Naga Swaroopa Chitveli

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Engineering

Scopus Publications

AI-Based Cascaded AutoEncoder-Convolutional Neural Network Model for Accurate Crop Yield Prediction Using Remote Sensing and Climate Data
Vivek Parashar, C. Naga Swaroopa, Shambhu Sharan Srivastava, P. A. Spoorthi, B. Swapna, Lakshmana Phaneendra Maguluri
Artificial Intelligence and Sustainable Networks Innovations Beyond 5g, 2026
The challenge of achieving sustainable agriculture in the face of climate variability has increased the demand for accurate and timely crop yield predictions. Crop yield-forecasting plays a critical role in food security (FS), enabling better planning, efficient resource allocation, and early intervention for climate-related risks. This study explores the application of remote sensing and geographic information systems (GISs) in the Cascaded AutoEncoder-Convolutional Neural Network (CNN) model for accurate crop yield prediction using remote sensing and climate data. The AutoEncoder reduces data dimensionality by extracting key features from multi-temporal satellite imagery and climate inputs, while the CNN captures spatial patterns associated with crop health and productivity. Data preprocessing included cloud masking, temporal aggregation, normalization, and spatial resampling, ensuring high-quality inputs for model training. Evaluated across multiple crop types and regions, the model achieved a root mean squared error (RMSE) in the range of 300–360 kg/ha and an R-squared value between 0.86 and 0.93. Accuracy was highest for corn and maize, with an average test accuracy of 89%, indicating the model’s robustness in capturing diverse crop and climatic conditions. Seasonal performance analysis revealed consistent accuracy, with slightly improved performance during autumn (R-squared: 0.91). Moreover, sensitivity analysis showed that soil moisture, temperature, and drought indices were highly influential, achieving an 87% reduction in error for drought-prone regions. These results demonstrate the effectiveness of the Cascaded AutoEncoder-CNN in providing accurate, reliable predictions across varying agricultural landscapes. This model has promising implications for crop management, yield forecasting, and FS, particularly in regions affected by climate variability.
AI and XR Applications over Energy-Efficient Networks
S. Rama Krishna, B. Arunsundar, C. Naga Swaroopa, C. Tamizhselvan, M. Rajakani, Muzeeb Khan Patan
Artificial Intelligence and Sustainable Networks Innovations Beyond 5g, 2026
Integrating artificial intelligence (AI) with extended reality (XR) is changing education by delivering personalized education that feels more lively and intelligent. Although adaptive learning environments, predictive analytics, and intelligent tutoring systems are supported by AI, XR—especially augmented reality (AR), virtual reality (VR), and mixed reality (MR)—provides involving and three-dimensional spaces for enhanced thinking activities. Conventional education systems commonly use the same method for every learner and do not help students remain involved. Conversely, when AI and XR are combined, students are given unique experiences with the content adjusting accordingly while being part of virtual settings that look like real life. This chapter provides information on how AI and XR tools are implemented and applied in learning systems, both structured and informal. We explore how AI matches learners’ behavior, offers them feedback in real time, and helps optimize teaching strategies. At the same time, XR gives students a chance to take part in interactive simulations such as virtual science labs, historical scenes, or language classes, which boosts their learning. Besides, the chapter touches on issues related to security, ethics, and sustainability when employing AI-XR in education on a large scale. Various examples from universities and businesses are given to highlight how machine learning is actually being used.
An intelligent system for cyberbullying detection in social networks using machine learning
C. Naga Swaroopa, P. Sivanjali, M. Prathyusha, K. Prasanthiram, P. Santhosh
Synergies in Smart and Virtual Systems Using Computational Intelligence, 2025
Cyberbullying is now a major issue in the modern digital age, where offensive social media posts can have severe emotional and social consequences. Previous attempts at identifying cyberbullying were based on different machine learning algorithms, including “k-nearest neighbors (KNN), Support Vector Machines (SVM)”, and deep learning (DL), which had accuracy levels of “90%, 92%, and 96%”, respectively. But these models usually have difficulty interpreting correctly the informal and casual words uttered on social media, which often come with slang and sarcasm. In our project, we present an improved method of using a “RandomForestClassifier”, whose accuracy has been enhanced to 98%. Our system reads social media postings by initially cleaning the texts to remove unnecessary items, such as links and special characters. Once cleaned, we transform the text into numerical representations through “Word2Vec”. This makes it easier for the model to understand the meaning and context of the words, which is fundamental to correct detection. To remedy the problem of class imbalance— where examples of abusive content are fewer in number—we use a method known as “RandomOverSampler”. It balances the dataset, increasing the model’s ability to detect abusive content correctly. Our approach is a blend of state-of-the-art machine learning with strong text processing, representing a major step forward in combating online abuse. In addition to employing the RandomForestClassifier, our project utilizes complex data cleaning and embedding techniques to provide better accuracy. We utilize “natural language processing (NLP)” techniques such as tokenization and sentiment analysis to normalize the text data prior to feeding it into the model. By using Word2Vec for word embedding, the system is able to get the context relationships among words more accurately, so that it can get the context of tweets and identify abusive language better. Moreover, with methods such as “RandomOverSampler”, the model is able to learn from less frequently occurring cases of cyberbullying, so that the system becomes better at performing in real-world application. These all contribute to our system being a stable tool for correctly identifying cyberbullying.
SmartShield: Harnessing Code Extraction and ML for Next-Gen Malware Detection
Gotte Ranjith Kumar, Anita Soni, C. Naga Swaroopa, R Ramesh, Shrikant Upadhyay, Nellore Manoj Kumar
2025 International Conference on Data Science Agents and Artificial Intelligence Icdsaai 2025, 2025
The rapid proliferation of Android applications has led to an increased prevalence of malware, posing significant security risks to users and devices. This research presents a novel Hybrid Model for Android malware detection, integrating multiple machine learning algorithms to enhance accuracy and robustness. The methodology involves the systematic collection of a comprehensive dataset, extraction of critical features using the Code Extraction Principle (CEP), and the evaluation of various models including SVM, Random Forest, Gradient Boosting, XGBoost, and others. The proposed Hybrid Model significantly outperforms these models, achieving an accuracy of 97.81%, with precision and recall rates of 96.72% and 95.89%, respectively. This model’s superior performance is attributed to the effective combination of different algorithms, optimizing feature extraction, and the robust handling of both benign and malicious applications. The model’s robustness against evasion techniques further underscores its potential as a reliable tool in Android malware detection. The results indicate that the proposed Hybrid Model is highly effective in minimizing both false positives and false negatives, offering a promising solution for enhancing mobile security. The findings of this research contribute to the development of more secure and efficient malware detection systems, addressing the evolving challenges in mobile cybersecurity.
Breast Cancer Classification: In-depth Exploration of Different Paradigms and Ensemble Technique
Abdulahi Mahammed Adem, Ravi Kant, Sonia, Sudesh Kumari, C. Naga Swaroopa, Gaurav Gupta
Proceedings of the 18th Indiacom 2024 11th International Conference on Computing for Sustainable Global Development Indiacom 2024, 2024
Many lives are lost to breast cancer every year. Prognosis and timely identification of cancer types are vital components of cancer research, as early diagnosis is critical to effective treatment. This study presents a comprehensive investigation into breast cancer classification, employing an extensive suite of datasets from Wisconsin Breast Cancer for machine learning models. Rigorous preprocessing techniques were applied to refine the dataset, segmented into groups of testing and training. The ensemble of models, comprising Logistic Regression, Decision Tree, Random Forest, XGBoost, Support Vector Machine (SVM), Gaussian Naive Bayes, K-Nearest Neighbors (KNN), AdaBoost, together with Deep Neural Network (DNN), underwent meticulous evaluation. For a more in-depth analysis, performance metrics like ROC-AUC scores, F1 Score, accuracy, precision, and recall were used. The ROC curve, or receiver operating characteristic provided visual insights, highlighting the trade-offs involving specificity and sensitivity. The ensemble model emerged as a promising approach, showcasing collaborative strengths across diverse algorithms, and achieves an accuracy of 98.2%. Confusion matrices and running time comparisons further elucidated model intricacies and computational efficiencies. This study will contribute valuable insights into breast cancer diagnostics, emphasizing the importance of tailored model selection and collaboration in clinical decision-making.
A machine learning based decision support system for improvement of smart watering equipment in agricultural fields
International Journal of Recent Technology and Engineering, 2019

RECENT SCHOLAR PUBLICATIONS

OPTIMIZING ALGORITHMS FOR MACHINE LEARNING-DRIVEN PREDICTIVE MAINTENANCE IN INDUSTRIAL IOT SYSTEMS
CN Swaroopa, V Bhaskar
Journal of Data Acquisition and Processing 40 (1), 33-43 , 2025
2025.0
ChatGPT as a scaffolding tool in English language teaching
BN Prasad, N Swaroopa
Lit. Vibes 14 (1), 1-10 , 2025
2025.0
Citations: 1
Breast Cancer Classification: In-depth Exploration of Different Paradigms and Ensemble Technique
AM Adem, R Kant, S Kumari, CN Swaroopa, G Gupta
2024 11th International Conference on Computing for Sustainable Global … , 2024
2024.0
Citations: 2
A Machine Learning Based Decision Support System for Improvement of Smart Watering Equipment in Agricultural Fields
V Neerugatti, S Vasu, CN Swaroopa
A Machine Learning Based Decision Support System for Improvement of Smart … , 2019
2019.0
A Machine Learning Based Decision Support System for Improvement of Smart Watering Equipment in Agricultural Fields
S Vasu, V Neerugatti, CN Swaroopa
Predictive Maintenance in Industrial IoT Using Machine Learning Approach
CN SWAROOPA
Optimizing Algorithms to integrate Advanced Machine Learning Methods for Predictive Maintenance in Industrial IoT
CN SWAROOPA

MOST CITED SCHOLAR PUBLICATIONS

Breast Cancer Classification: In-depth Exploration of Different Paradigms and Ensemble Technique
AM Adem, R Kant, S Kumari, CN Swaroopa, G Gupta
2024 11th International Conference on Computing for Sustainable Global … , 2024
2024.0
Citations: 2
ChatGPT as a scaffolding tool in English language teaching
BN Prasad, N Swaroopa
Lit. Vibes 14 (1), 1-10 , 2025
2025.0
Citations: 1
OPTIMIZING ALGORITHMS FOR MACHINE LEARNING-DRIVEN PREDICTIVE MAINTENANCE IN INDUSTRIAL IOT SYSTEMS
CN Swaroopa, V Bhaskar
Journal of Data Acquisition and Processing 40 (1), 33-43 , 2025
2025.0
A Machine Learning Based Decision Support System for Improvement of Smart Watering Equipment in Agricultural Fields
V Neerugatti, S Vasu, CN Swaroopa
A Machine Learning Based Decision Support System for Improvement of Smart … , 2019
2019.0
A Machine Learning Based Decision Support System for Improvement of Smart Watering Equipment in Agricultural Fields
S Vasu, V Neerugatti, CN Swaroopa
Predictive Maintenance in Industrial IoT Using Machine Learning Approach
CN SWAROOPA
Optimizing Algorithms to integrate Advanced Machine Learning Methods for Predictive Maintenance in Industrial IoT
CN SWAROOPA