Pranshav Ritesh Gajjar

Mr. Pranshav Ritesh Gajjar

orcid

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
25 July 2025 in IEEE Transactions on Machine Learning in Communications and Networking
Verified
Journal Article
Open access
PGPranshav Ritesh Gajjar
Pranshav Ritesh Gajjar
VSVijay K. Shah
Vijay K. Shah
Despite the transformative impact of Large Language Models (LLMs) across critical domains such as healthcare, customer service, and business marketing, their integration into Open Radio Access Networks (O-RAN) remains limited. This gap is primarily due to the absence of domain-specific foundational models, with existing solutions often relying on general-purpose LLMs that fail to address the unique challenges and technical intricacies of O-RAN. To bridge this gap, we introduce ORANSight-2.0 (O-RAN Insights), a pioneering initiative to develop specialized foundational LLMs tailored for O-RAN. Built on 18 models spanning five open-source LLM frameworks—Mistral, Qwen, Llama, Phi, and Gemma—ORANSight-2.0 fine-tunes models ranging from 1B to 70B parameters, significantly reducing reliance on proprietary, closed-source models while enhancing performance in O-RAN-specific tasks. At the core of ORANSight-2.0 is RANSTRUCT, a novel Retrieval-Augmented Generation (RAG)-based instruction-tuning framework that employs two LLM agents—a Mistral-based Question Generator and a Qwen-based Answer Generator—to create high-quality instruction-tuning datasets. The generated dataset is then used to fine-tune the 18 pre-trained open-source LLMs via QLoRA. To evaluate ORANSight-2.0, we introduce srsRANBench, a novel benchmark designed for code generation and codebase understanding in the context of srsRAN, a widely used 5G O-RAN stack. Additionally, we leverage ORAN-Bench-13K, an existing benchmark for assessing O-RAN-specific knowledge. Our comprehensive evaluations demonstrate that ORANSight-2.0 models outperform general-purpose and closed-source models, such as ChatGPT-4o and Gemini, by 5.421% on ORANBench and 18.465% on srsRANBench, achieving superior performance while maintaining lower computational and energy costs. We also experiment with RAG-augmented variants of ORANSight-2.0 models and observe that RAG augmentation improves performance by an average of 6.35% across benchmarks, achieving the best overall cumulative score of 0.854, which is 12.37% better than the leading closed-source alternative. We thoroughly evaluate the energy characteristics of ORANSight-2.0, demonstrating its efficiency in training, inference, and inference with RAG augmentation, ensuring optimal performance while maintaining low computational and energy costs. Additionally, the best ORANSight-2.0 configuration is compared against the available telecom LLMs, where our proposed model outperformed them with an average improvement of 27.96%.

28 September 2023 in Information
Verified
Journal Article
Open access
PDF file
MGManav Garg
Manav Garg
PGPranshav Ritesh Gajjar
Pranshav Ritesh Gajjar
PSPooja Shah
Pooja Shah
MSMadhu Shambhu Shukla
Madhu Shambhu Shukla
BABiswaranjan Acharya
Biswaranjan Acharya
Andreas KanavosAndreas Kanavos
Andreas Kanavos
The musical key serves as a crucial element in a piece, offering vital insights into the tonal center, harmonic structure, and chord progressions while enabling tasks such as transposition and arrangement. Moreover, accurate key estimation finds practical applications in music recommendation systems and automatic music transcription, making it relevant across academic and industrial domains. This paper presents a comprehensive comparison between standard deep learning architectures and emerging vision transformers, leveraging their success in various domains. We evaluate their performance on a specific subset of the GTZAN dataset, analyzing six different deep learning models. Our results demonstrate that DenseNet, a conventional deep learning architecture, achieves remarkable accuracy of 91.64%, outperforming vision transformers. However, we delve deeper into the analysis to shed light on the temporal characteristics of each deep learning model. Notably, the vision transformer and SWIN transformer exhibit a slight decrease in overall performance (1.82% and 2.29%, respectively), yet they demonstrate superior performance in temporal metrics compared to the DenseNet architecture. The significance of our findings lies in their contribution to the field of musical key estimation, where accurate and efficient algorithms play a pivotal role. By examining the strengths and weaknesses of deep learning architectures and vision transformers, we can gain valuable insights for practical implementations, particularly in music recommendation systems and automatic music transcription. Our research provides a foundation for future advancements and encourages further exploration in this area.

26 July 2022
Verified
Book Chapter
Closed access
PDF file
PGPranshav Ritesh Gajjar
Pranshav Ritesh Gajjar
PSPooja Shah
Pooja Shah
HSHarshil Sanghvi
Harshil Sanghvi

28 October 2022 in Reports on Geodesy and Geoinformatics
Verified
Journal Article
Open access
PDF file
PGPranshav Ritesh Gajjar
Pranshav Ritesh Gajjar
MGManav Garg
Manav Garg
VSVatsal Shah
Vatsal Shah
PSPooja Shah
Pooja Shah
ADAnup Das
Anup Das
Accurate and efficient detection of ships from aerial images is an intriguing and difficult task of extreme societal importance due to their implication and association with maritime infractions, and other suspicious actions. Having an automated system with the required capabilities indicates a substantial reduction in the related man-hours of characterization and the overall underlying processes. With the advent of various image processing techniques and advancements in the field of machine learning and deep learning, specialized methodologies can be created for the said task. An intuition for the enhancement of existing methodologies would be a study on attention-based cognition and the development of improved neural architectures with the available attention modules. This paper offers a novel study and empirical analysis of the utility of various attention modules with U-Net and other subsidiary architectures as a backbone for the task of computationally efficient and accurate ship detection. The best performing models are depicted and explained thoroughly, while considering their temporal performance.


1 July 2022 in Computer Science Journal of Moldova
Verified
Journal Article
Closed access
PGPranshav Ritesh Gajjar
Pranshav Ritesh Gajjar
NMNaishadh Mehta
Naishadh Mehta
PSPooja Shah
Pooja Shah