Dr Pavithra G
@dsce.edu.in
Associate Professor
Dayananda Sagar College of Engineering, Bangalore
Dr. Pavithra G. was born in Bangalore, Karnataka, India & received the B.E. Degree (Bachelor of Engg.) in Electronics & Communication Engineering stream (ECE) from VTU, Belgaum, M.Tech. Degree in ECE branch with specialization in RF Communications from the Jain University in First Rank (FCD) & gold medal and obtained her doctorate - Ph.D. in Engineering from the prestigious Visvesvaraya Technological University (VTU Belgaum) respectively. She has got a teaching (academic), research experience of more than 15+ years in various engineering colleges in the Karnataka state. She has worked in the levels of Lecturer-Asst. Prof. (15+) in the colleges where she was a faculty in the Dept. of Electronics & Communication Engg. apart from having a very good industrial experience gained during her UG/PG project, internships & work tenures. Currently, she is working as an Associate Professor in the Dept. of ECE of the Dayananda Sagar College of Engg., Bangalore.
EDUCATION
B.E. (Acharya Institute of Technology, Bangalore)
Electronics & Communication Engg.
Affiliated to VTU, Belgaum, Karnataka,
Year of passing – 2006 (2002-2006)
M.Tech. (Jain College of
RF Communications
Affiliated to Jain University, Bangalore, Karnataka
Year of passing – 2012, 1st Rank, Gold Medalist (2010-12)
Ph.D. (VTU) Registered in Dec. 2015 (
Image Processing
Completed Ph.D. in VTU – RRC, Belgaum, Karnataka
Feb. 2020 (4 years)
RESEARCH, TEACHING, or OTHER INTERESTS
Electrical and Electronic Engineering, Communication, Cancer Research, Artificial Intelligence
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
V. Pushpalatha, H. N. Mahendra, A. M. Prasad, N. Sharmila, D. Mahesh Kumar, N. M. Basavaraju, G. S. Pavithra, and S. Mallikarjunaswamy
Technoscience Publications
This research paper presents a comprehensive assessment of the built-up area in Mysuru City over the decade spanning from 2010 to 2020, employing advanced geospatial techniques. The study aims to analyze the spatiotemporal patterns of urban expansion, land-use dynamics, and associated factors influencing the city’s built environment. Remote sensing imagery, Geographic Information System (GIS) tools, and machine learning algorithms are leveraged to process and interpret satellite data for accurate land-cover classification. The methodology involves the acquisition and preprocessing of multi-temporal satellite imagery to delineate and map the built-up areas at different time intervals. Land-use change detection techniques are employed to identify and quantify alterations in urban morphology over the specified period. Additionally, socio-economic and environmental variables are integrated into the analysis to discern the drivers of urban growth. The outcomes of this research contribute valuable insights into urbanization dynamics and land-use planning strategies, facilitating informed decision-making for sustainable urban development.
Rupal Vyasa, Pragnesh Brahmbhatt, Chandrakant Sonawane, Nageswara R. Lakkimsetty, and G. Pavithra
Engineering, Technology & Applied Science Research
To meet the requirements of modern Computerized Numerical Control (CNC) turning processes, it is necessary to improve efficiency, precision and surface quality while reducing negative effects such as vibration and cutting force. In an attempt to minimize vibration, surface roughness, and cutting force at the same time, this study optimizes machining settings in CNC turning of EN8. Manufacturers can find the optimal parameters by using a multi-objective optimization strategy. According to the conducted experimental validation, by reducing vibration, improving surface roughness, and minimizing cutting forces, the adjusted parameters can significantly increase productivity and quality in CNC turning operations. This research contributes to the ongoing effort to improve machining processes to meet various performance goals, for industries that rely on CNC turning.
K. Nanda Kiran, V. M. Kumari Ayushi Kishore, Vinod Kumar Malkapure, G. Pavithra, and T. C. Manjunath
AIP Publishing
B. S. Hari, Bhaskar Roy, M. Elangovan, S. Kaliappan, G. Pavithra, and T. C. Manjunath
AIP Publishing
C. Madan Kumar, Y. Mohan, G. Manvanth, B. R. Nagesh, G. Pavithra, and T. C. Manjunath
AIP Publishing
D. Anupriya, Ananth Agarwal, Akshat Kumar, Afira Ansari, G. Pavithra, and T. C. Manjunath
AIP Publishing
Sampada Viraj Dravid, Nazeer Shaik, Gurumeet C. Wadhawa, S. Kaliappan, G. Pavithra, and T. C. Manjunath
AIP Publishing
K. Madhushree, M. Keerthana, J. Poornima, R. Kavya, M. Padmavathi, G. Pavithra, and T. C. Manjunath
AIP Publishing
Vaishanavi Patil, V. K. Vaibhav, B. G. Thyagaraj, G. Suprith Gowda, G. Pavithra, and T. C. Manjunath
AIP Publishing
Sagaragouda, Sahana G. Malagali, C. H. Srujana, G. Pavithra, and T. C. Manjunath
AIP Publishing
Praveen Rathod, D. N. Kavya, Atul Gupta, S. Kaliappan, G. Pavithra, and T. C. Manjunath
AIP Publishing
J. Kamalakumari, A. Archudha, R. Kiruthikaa, N. Saranya, S. Kaliappan, G. Pavithra, and T. C. Manjunath
AIP Publishing
Pankaj Dumka, Rishika Chauhan, Dhananjay R. Mishra, Feroz Shaik, Pavithra Govindaraj, Abhinav Kumar, Chandrakant Sonawane, and Vladimir Ivanovich Velkin
Institute of Advanced Engineering and Science
<p>Chemical reaction balancing is a fundamental aspect of chemistry, ensuring the conservation of mass and atoms in reactions. This article introduces a specialized Python functions designed for automating the balancing of chemical reactions. Leveraging the versatility and simplicity of Python, the module employs advanced algorithms to provide an efficient and user-friendly solution for scientists, educators, and industry professionals. This article delves into the design, implementation, features, applications, and future developments of the Python functions for automated chemical reaction balancing. The functions thus developed were tested on some typical chemical reactions and the results are the same as that in the literature.</p>
Pavithra Goravi Sukumar, Modugu Krishnaiah, Rekha Velluri, Pooja Satish, Sharmila Nagaraju, Nandini Gowda Puttaswamy, and Mallikarjunaswamy Srikantaswamy
Institute of Advanced Engineering and Science
The deadlock-free and live lock-free routing at the same time is minimized in the network on chip (NoC) using the proposed adoptive reconfigurable routing protocol (ARRP). Congestion condition emergencies are avoided using the proposed algorithm. The input packet distribution process is improved among all its shortest paths of output points. The performance analysis has been initiated by considering different configuration (N*N) mesh networks, by sending various ranges of data packets to the network on chip. The average and maximum power dissipation of XY, odd-even, Dy-XY algorithm, and proposed algorithm are determined. In this paper, an analysis of gate utilization during data packet transfer in various mesh configurations is carried out. The number of cycles required for each message injection in different mesh configurations is analyzed. The proposed routing algorithm is implemented and compared with conventional algorithms. The simulation has been carried out using reconfigurable two-dimensional mesh for the NoC. The proposed algorithm has been implemented considering array size, the routing operating frequency, link width length, value of probability, and traffic types. The proposed ARRP algorithm reduces the average latency, avoids routing congestion, and is more feasible for NoC compared to conventional methods.
Pavithra G., Swapnil S. Ninawe, Sandeep K.V., Iffath Fawad, and Manjunath T.C.
IEEE
In this research paper, the development of hybrid algorithms for the detection of Pneumonia Disease from the human X-Ray’s images of the Chest Structure is presented along with the simulated & experimental results. A potentially fatal lung infection caused by many viral infections called pneumonia. Due to its similarities to other lung disorders, pneumonia can be challenging to diagnose and treat on chest’s X-Ray’s pictures. Chest X-ray pictures is essential to their early diagnoses of pneumonia because they allow for prompt intervention, prevention of complications, and shorter hospital stays. This work proposes a novel approach to pneumonia detection using CNN, VGG16, ResNet152V2 and Gradient Descent optimization deep learning techniques. The system automatically extracts feature using the chest’s X-ray’s image using CNNs, then uses Gradient Descent optimization to enhance its ability to discriminate between pneumonia patients and healthy cases. Pre-trained models ResNet152V2 and VGG16 are used, hence improving overall system performance. To summarize, our study demonstrates the potential of deep learning for more precise and effective diagnosis in clinical settings and advances automated pneumonia detection through the integration of state-of-the-art architectures.The accurate and timely detection of pneumonia from chest’s X-ray’s image is crucial for effective patient care and treatment. In this paper, we propose the development of hybrid algorithms for the detection of pneumonia disease from human chest’s X-ray’s image. The hybrid algorithms combine the strengths of both machine learning and deep learning techniques to improve the accuracy and efficiency of pneumonia detection. Our approach involves preprocessing the X-ray’s image to enhance features, followed by feature extraction using both traditional machine learning algorithms and deep learning models. The extracted features are then used to train a classifier to differentiate between normal and pneumonia-infected chest’s X-ray’s image. Experimental results demonstrate that the proposed hybrid algorithms outperform traditional machine learning and deep learning approaches, achieving high accuracy in pneumonia detection. These results highlight the potential of hybrid algorithms for improving the diagnosis of pneumonia from chest’s X-ray’s images, thereby aiding in early and effective medical intervention.