Pallavi Sagar Deshpande

Pallavi Sagar Deshpande

Auto-generated profile, based on publicly available information

Pallavi Sagar Deshpande

Bharati Vidyapeeth, India

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 February 2025
Verified
Book Chapter
Closed access
PSP. Selvakumar
P. Selvakumar
PDPallavi Sagar Deshpande
Pallavi Sagar Deshpande
VKV. Karthick
V. Karthick
KSK. Sivasubramani
K. Sivasubramani
MOMohit
Mohit
TC ManjunathTC Manjunath
TC Manjunath
Open innovation represents a paradigm shift in the way organizations approach research and development, emphasizing the value of external ideas and collaborations alongside internal efforts. This model acknowledges that valuable knowledge and expertise are often dispersed outside organizational boundaries, and leveraging these external sources can significantly enhance innovation outcomes. By engaging with customers, suppliers, academic institutions, and even competitors, organizations can tap into a broader pool of ideas, technologies, and insights, ultimately driving innovation more effectively and efficiently. This collaborative approach is particularly relevant in today's fast-paced and competitive landscape, where the rapid evolution of technology and changing consumer preferences necessitate agile and adaptive innovation strategies. Organizations must establish robust IP strategies that not only protect their innovations but also facilitate collaboration.

6 May 2022 in Security and Communication Networks
Verified
Journal Article
Open access
PDF file
PDPallavi Deshpande
Pallavi Deshpande
NSNagarajan Suganthi
Nagarajan Suganthi
GNG. Nirmala
G. Nirmala
APAnand Pandey
Anand Pandey
KPKrishna Patteti
Krishna Patteti
Evans AsensoEvans Asenso
Evans Asenso
The implementation of accurate models to improve access technologies, communication transmission, and network slicing is anticipated to play a big part in the edge computing approach, as the demands and needs of individuals are quickly evolving. Deep learning models have tended to deliver more benefits in a wide range of applications; it also assists data providers in demonstrating considerable improvements in tackling complex real-world challenges. While the integration of connected wireless networks and deep learning is still in its infancy, wireless communication networks are increasingly focused on sophisticated technologies to meet the current and future needs of end users. Based on the theoretical and practical aspect that ranges from the basic aspect to future applications of wireless communication, this study is intended in addressing the opportunities of adopting metaheuristic deep learning-driven wireless communication. The researchers intend to apply descriptive design to the study as this enables in understanding the critical aspects of the study in an elaborate manner. The authors use both a primary data sources and a secondary data sources for performing the analysis. The secondary data source is sourced to understand the application of deep learning in the wireless communication area, and primary research is used to gather the data from the respondents to test the hypothesis and provide conclusions based on the analyses. The scope of this work is to utilize a quantitative model to undertake an analysis on evaluating the key parameters in the application of deep learning in wireless communication, which will allow for critical analysis and interpretation based on the findings.

13 December 2024
Verified
Book Chapter
Closed access
JDJulia Punitha Malar Dhas
Julia Punitha Malar Dhas
MKMartin Victor K.
Martin Victor K.
PSP. Santhiya
P. Santhiya
PDPallavi Sagar Deshpande
Pallavi Sagar Deshpande
DSDillip Narayan Sahu
Dillip Narayan Sahu
Joshuva Arockia DhanrajJoshuva Arockia Dhanraj
Joshuva Arockia Dhanraj
Face spoof detection and authentication systemhas significant role in IoT application that include validation of identity for computer security atm access crime detection and social care. Even though the authentication and classification system are vulnerable to different types of attacks. Presentation attack is a clear threat for facial and biometric based security and authentication applications. The discussed issues can be solved using artificial neural networks for face proof detection in IoT platform. The deep learning approaches for feature extraction in multicolor space is useful for obtaining more information from the input face regarding chrominance and luminance data. The extracted features can be selected and combined with minimum redundancy maximum relevance algorithm for providing discriminate and efficient feature set.

4 April 2025
Verified
Book Chapter
Closed access
MRM. Rajkumar
M. Rajkumar
NMNiladri Maiti
Niladri Maiti
RCRiddhi Chawla
Riddhi Chawla
RRRipal D Ranpara
Ripal D Ranpara
RYR. Yogitha
R. Yogitha
ASAakifa Shahul
Aakifa Shahul
The development of machine learning applications in the healthcare industry depends on safe medical image sharing. Protecting patient privacy is more difficult but necessary as medical imaging data grows. This paper investigates how to integrate encryption techniques and secure data-sharing methods, like blockchain, to facilitate cross-organizational collaboration while maintaining data privacy. Sensitive patient data is kept in local systems thanks to collaborative models like federated learning, which enable institutions to train machine learning algorithms on decentralized datasets. This strategy makes use of the variety of data available across healthcare facilities while protecting the privacy of medical records. The creation of machine learning models for diagnosis and treatment planning that are more reliable and accurate is made possible by the safe interchange of medical images.

1 December 2025 in Journal of Integrated Science and Technology
Verified
Journal Article
Open access
VBVinayak Bairagi
Vinayak Bairagi
PDPallavi Sagar Deshpande
Pallavi Sagar Deshpande
MGMilind P Gajare
Milind P Gajare
This study is focused on developing a Marathi text-to-speech (TTS) system aimed at making digital content more accessible in local languages. With the growing demand for voice-enabled applications in education and assistive technologies - particularly for regional users - the system is designed using a combination of natural language processing techniques, such as text normalization, grapheme-to-phoneme conversion, and concatenative synthesis. Implemented in Python, the system places strong emphasis on phonetic accuracy and the correct pronunciation of Marathi text. Evaluation through user feedback and standard metrics, such as the Mean Opinion Score (MOS), indicates that the generated speech is clear, natural-sounding, and easy to understand. The system has potential applications in educational tools, assistive devices for the visually impaired, and Marathi-language voice assistants. A major challenge addressed in this work involves handling specific linguistic issues, including complex phonetic structures and the lack of large-scale linguistic datasets. Overall, this project contributes to ongoing efforts in regional language speech technology by providing a practical and adaptable foundation for future research and development.