Phaneendra Varma Chintalapati
Research Subjects
Phaneendra Varma Chintalapati has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
- Gurujukota Ramesh Babu
Shri Vishnu Engineering College for Women
11 shared publications - Kiran Sree Pokkuluri
Department of Computer Science & Engineering, Shri Vishnu Engineering College for Women, Bhimavaram, Andhra Pradesh 534202, India
9 shared publications - S. S. S. N. Usha Devi N.
Jawaharlal Nehru Technological University, Kakinada, India
7 shared publications - P. B. V. Raja Rao
Shri Vishnu Engineering College for Women(A)
6 shared publications - Maddula Prasad
Shri Vishnu Engineering College for Women(A)
4 shared publications - P. J. R. Shalem Raju
Shri Vishnu Engineering College for Women
4 shared publications
Latest Publications
- Open Access
- 22 September 2026
- Published by Elsevier in Intelligence-Based Medicine
- Vol. 16
A heterogeneity-aware federated learning framework for multimodal nanotoxicological risk assessment
- 22 September 2026
- Published by Elsevier in Intelligence-Based Medicine
- Vol. 16
Open AccessA heterogeneity-aware federated learning framework for multimodal nanotoxicological risk assessment
- Open Access
- 1 August 2026
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 15 (4) , 3120-3130
Deep learning for lung cancer diagnosis: a comparative artificial intelligence study
Early and accurate lung cancer diagnosis (LCD) is critical, yet traditional imaging methods such as X-rays and computed tomography (CT) scans are costly, invasive, and heavily reliant on expert interpretation. This study investigates artificial intelligence (AI)-driven diagnostics by comparing deep learning models (convolutional neural network (CNN), residual network (ResNet), and visual geometry group 16 (VGG16)) with traditional machine learning algorithms (logistic regression (LR) and support vector machine (SVM)), using lung image database consortium and image database resource initiative (LIDC-IDRI) and Kaggle lung CT scan datasets. Performance was evaluated across multiple metrics: accuracy, sensitivity, specificity, and area under the curve-receiver operating characteristic (AUC-ROC). Among the models, ResNet achieved the highest performance, with an accuracy of 94%, sensitivity of 95%, specificity of 93%, and AUC-ROC close to 1. CNN and VGG16 also showed superior metrics compared to LR and SVM, highlighting the robustness of deep learning techniques. These results demonstrate that deep learning models not only achieve higher diagnostic accuracy but also significantly reduce false detections compared to traditional approaches. The findings support the potential of AI to automate and enhance LCD, thereby improving accessibility, consistency, and speed in clinical settings. Future work will emphasize clinical validation, address ethical challenges, and focus on integrating AI models into real-world healthcare workflows to improve patient outcomes.
- 1 August 2026
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 15 (4) , 3120-3130
Open AccessDeep learning for lung cancer diagnosis: a comparative artificial intelligence study
Early and accurate lung cancer diagnosis (LCD) is critical, yet traditional imaging methods such as X-rays and computed tomography (CT) scans are costly, invasive, and heavily reliant on expert interpretation. This study investigates artificial intelligence (AI)-driven diagnostics by comparing deep learning models (convolutional neural network (CNN), residual network (ResNet), and visual geometry group 16 (VGG16)) with traditional machine learning algorithms (logistic regression (LR) and support vector machine (SVM)), using lung image database consortium and image database resource initiative (LIDC-IDRI) and Kaggle lung CT scan datasets. Performance was evaluated across multiple metrics: accuracy, sensitivity, specificity, and area under the curve-receiver operating characteristic (AUC-ROC). Among the models, ResNet achieved the highest performance, with an accuracy of 94%, sensitivity of 95%, specificity of 93%, and AUC-ROC close to 1. CNN and VGG16 also showed superior metrics compared to LR and SVM, highlighting the robustness of deep learning techniques. These results demonstrate that deep learning models not only achieve higher diagnostic accuracy but also significantly reduce false detections compared to traditional approaches. The findings support the potential of AI to automate and enhance LCD, thereby improving accessibility, consistency, and speed in clinical settings. Future work will emphasize clinical validation, address ethical challenges, and focus on integrating AI models into real-world healthcare workflows to improve patient outcomes.
- Open Access
- 2 December 2025
- Published by Springer Nature in Social Network Analysis and Mining
- Vol. 16 (1)
Few-shot and zero-shot Assamese hate speech detection: a comparative benchmark of large language models
- 2 December 2025
- Published by Springer Nature in Social Network Analysis and Mining
- Vol. 16 (1)
Open AccessFew-shot and zero-shot Assamese hate speech detection: a comparative benchmark of large language models
- 4 April 2025
- Published by IGI Global Scientific Publishing
- p. 169-180
Enhancing Route Planning in Mobility as a Service (MaaS) Through Deep Learning Techniques
Enhancing route planning the ability to improve route planning as applied to MaaS is paramount to improving mobility in urban areas and the experience of it. This work focuses on deep learning methods for improving route planning in context of MaaS. suggest the deep learning model employing traffic data, the user preference and real-time environmental data to develop efficient routes planning. The model uses convolutional neural network (CNN) for spatial-temporal data analysis extracting features related to graphs and exploits the recurrent neural network (RNN) for sequential data analysis such as traffic flow and time series. Thus, by using this deep learning mechanism the system is capable of updating routes whenever there is a change in the environment thus offering persons efficient and customarily satisfying routes.
- 4 April 2025
- Published by IGI Global Scientific Publishing
- p. 169-180
Enhancing Route Planning in Mobility as a Service (MaaS) Through Deep Learning Techniques
Enhancing route planning the ability to improve route planning as applied to MaaS is paramount to improving mobility in urban areas and the experience of it. This work focuses on deep learning methods for improving route planning in context of MaaS. suggest the deep learning model employing traffic data, the user preference and real-time environmental data to develop efficient routes planning. The model uses convolutional neural network (CNN) for spatial-temporal data analysis extracting features related to graphs and exploits the recurrent neural network (RNN) for sequential data analysis such as traffic flow and time series. Thus, by using this deep learning mechanism the system is capable of updating routes whenever there is a change in the environment thus offering persons efficient and customarily satisfying routes.
- 14 March 2025
- Published by IGI Global Scientific Publishing
- p. 287-300
Machine Learning Approaches for Multi-Modal Integration in Remote Learning Platforms
The integration of machine learning approaches in remote learning platforms aims to revolutionize education through advanced learning analytics. With the growing emphasis on remote experimentation and digital education, the need for adaptive and intelligent systems to support diverse learning environments has become increasingly critical. By applying multi-modal integration techniques, this study focuses on enhancing the personalization and efficiency of educational content delivery. Machine learning models are employed to analyze various data streams, including student behavior, engagement metrics, and performance indicators, to provide real-time insights and adaptive feedback.
- 14 March 2025
- Published by IGI Global Scientific Publishing
- p. 287-300
Machine Learning Approaches for Multi-Modal Integration in Remote Learning Platforms
The integration of machine learning approaches in remote learning platforms aims to revolutionize education through advanced learning analytics. With the growing emphasis on remote experimentation and digital education, the need for adaptive and intelligent systems to support diverse learning environments has become increasingly critical. By applying multi-modal integration techniques, this study focuses on enhancing the personalization and efficiency of educational content delivery. Machine learning models are employed to analyze various data streams, including student behavior, engagement metrics, and performance indicators, to provide real-time insights and adaptive feedback.
- 9 February 2025
- Published by Springer Nature
- p. 45-51
Hate Speech Detection Using Recurrent Neural Networks (RNN)
- 9 February 2025
- Published by Springer Nature
- p. 45-51
Hate Speech Detection Using Recurrent Neural Networks (RNN)
- 9 February 2025
- Published by Springer Nature
- p. 37-44
Fake News Detection Using ML Algorithms
- 9 February 2025
- Published by Springer Nature
- p. 266-273
Generative Adversarial Networks (GANs) for Drug Discovery
- 9 February 2025
- Published by Springer Nature
- p. 266-273
Generative Adversarial Networks (GANs) for Drug Discovery
- 9 February 2025
- Published by Springer Nature
- p. 78-86
Identification of Different Medicinal Plants Using Machine Learning and Image Processing
- 9 February 2025
- Published by Springer Nature
- p. 78-86
Identification of Different Medicinal Plants Using Machine Learning and Image Processing