PUPamula Udayaraju

Pamula Udayaraju

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Pamula Udayaraju has a total of 30 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Explainable attention-based intrusion detection for encrypted 5G network traffic

    by Raghu Dhumpati, Varun Vemulapalli, Udayaraju Pamula, Kranthi Kumar Lella, N. Sandeep Chaitanya, D. Pramodh Krishna, Syed Ziaur Rahman

    The widespread adoption of end-to-end encryption in 5G networks limits the effectiveness of traditional intrusion detection systems that rely on payload inspection. This challenge is particularly critical for detecting Advanced Persistent Threats (APTs), which employ low-rate, long-duration, and stealthy communication strategies to evade conventional defenses. This study presents a privacy-preserving intrusion detection framework that operates exclusively on flow-level traffic metadata without deep packet inspection. Network packets are aggregated into bidirectional flows, from which temporal, statistical, and directional features are extracted to characterize behavioral patterns. A Transformer-based model with self-attention is employed to capture long-range dependencies across encrypted traffic sequences and identify subtle, temporally dispersed attack indicators. The framework is evaluated on a large-scale 5G-relevant dataset containing over one million flow records and compared against classical machine learning, ensemble, CNN, and LSTM models. Results demonstrate high recall and strong F1-score in distinguishing APT from benign traffic. Attention-based and feature-level explanations further reveal that prolonged communication, irregular timing gaps, and directional asymmetry significantly influence detection decisions. The findings support the practicality of explainable Transformer models for secure and scalable APT detection in encrypted 5G environments.


  • Open Access

    A spider wasp-based deep neural prediction framework for emotion recognition and sentiment analysis in big data

    by Udayaraju Pamula, G. N. V. G. Sirisha, Ravi Babu Devareddi, R. Sathish Kumar, T. Santhi Sri, Nanditha Boddu, Ramesh Vatambeti

  • Open Access

    Enhancing Non-Alcoholic Fatty Liver Disease Prediction with Machine Learning and Recursive Feature Elimination

    by Koppisetti Giridhar, Dr.J.Nafeesa Begum, Bajjuri Usha Rani, Manasa Adusumilli, M M.Padmavathi, Boddu L.V.Sivarama Krishaa, M. Sitharam, Pamula Udayarau

    Non-alcoholic disease detection is one of the leading research works in recent days. Modern life has changed the food and environmental culture, making them overweight, stressed, unhealthy conditions always and which causes various diseases due to overweight and diabetes. Commonly, an alcoholic addict can be affected by Fatty Liver Diseases (FLD), whereas identifying fatty liver diseases for a non-alcoholic person is a challenging task. It is not so easy even suspecting that a patient has FLD at the earlier stage of the symptoms since the symptoms of FLD are very similar to other diseases, and it may lead to wrong diagnosis and treatment. The severity level of 30% of FLD patients is increased suddenly and leads to heart attack, stroke, and death. Thus, based on the symptoms of weight loss, abdominal pain, and fatigue, it is essential to diagnose NAFLD, which can be identified accurately from pathological and genomic data using efficient learning methods to provide the right and better treatment immediately. This paper implements multiple machine learning algorithms for analyzing the pathological information obtained from the NAFLD and NASH DNA datasets and finding the best model concerning the performance. This paper uses 3-fold cross verification with recursive feature elimination methods to improve the original accuracy of the prediction. The performance comparison shows that the SVM model obtained 87% accuracy, which is better than the KNN and RF models. The experimental results with the performance comparison are explained in detail in the paper.

  • Open Access

    Implement A Transfer Learning Model For Analyzing, Identifying, And Predicting Plant Diseases On Plant Leaf Image Dataset

    by T.V.K.P. Prasad, Pamula Udayaraju, M. Gayathri, Katakam Ranga Narayana, Bala Prasanthi Pavuluri, N. Neelima

    The early detection of plant diseases is vital for ensuring crop health and maximizing agricultural productivity. This study presents a comprehensive evaluation of advanced transfer learning models for automatic classification of plant diseases using leaf image datasets. Five deep learning architectures—CNN, Inception V3, ResNet, VGG16, and VGG19—were implemented and compared to identify the most effective model for generalized plant disease detection. The experimental workflow involves image preprocessing, augmentation, and feature extraction to enhance model performance. Datasets comprising 87,000+ images from Kaggle’s PlantVillage were used for training and evaluation. Each model was assessed using accuracy and loss metrics under consistent hardware and software environments. Results indicate that the VGG16 model consistently outperforms others in classification accuracy and computational efficiency, making it a robust choice for large-scale and diverse agricultural applications. This research contributes a scalable and effective solution for automated disease identification, supporting precision agriculture and reducing reliance on manual inspection.

  • Open Access

    Accuracy Assessment of Convolutional Neural Networks for Plant Disease Prediction with Multi-Stage Image Preprocessing

    by A. Geetha Devi, K. Thirupal Reddy, V. Dilip Kumar, M. Venkata Subbarao, Yeswanth Kumar Alapati, J. Hymavathi, Pamula Udayaraju

    Plant disease forecasting is among the advanced research areas targeted by most agricultural institutions and government bodies to enhance yields. Forecasting diseases is a very vital topic of international agriculture since crop health directly affects human health proportionately. Various plant organs, like root, stem, leaves, fruits, or a major proportion of the crop, are diagnosed to identify diseases, while various previous work employed images of plant leaves to identify disease. Previous works employed standard practices, optimization techniques, and machine learning methods for plant disease prediction but specifically for sets of leaf images. No work adopted a generalized approach to disease detection for any plant image data because the dataset was large, colored, aligned, and resolution varied. The goal of this paper is to adopt a Preprocessing Framework with a Convolution Neural Network (PF-CNN). It works on any plant leaf image. The preprocessing framework includes alignment, rotation, resizing, cropping, color transformation, and image enhancement. Final output images are passed through CNN for disease classification. As this work is the beginning of the research work, CNN is trained using pretrained images and checked against ground truth outputs to validate the disease class. Next, CNN is tested with test images and confirmed using validation images. Experiment output is cross-checked and compared with other analogous methods to analyse the performance of PF-CNN. Keywords: Preprocessing, CNN, Plant Disease Detection, Leaf Images, Tomato Leaves, Maize Leaves.