Ravi Gupta

Mr. Ravi Gupta

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
31 August 2021 in Applied System Innovation
Verified
Journal Article
Open access
PDF file
VSVinamra Bhushan Sharma
Vinamra Bhushan Sharma
KSKartik Singh
Kartik Singh
RGRavi Gupta
Ravi Gupta
AJAyush Joshi
Ayush Joshi
RDRakesh Dubey
Rakesh Dubey
SBSusham Biswas
Susham Biswas
There has been enormous growth in the energy sector in the new millennium, and it has enhanced energy demand, creating an exponential rise in the capital investment in the energy industry in the last few years. Regular monitoring of the health of industrial equipment is necessary, and thus, the concept of structural health monitoring (SHM) comes into play. In this paper, the purpose is to highlight the importance of SHM systems and various techniques primarily used in pipelining industries. There have been several advancements in SHM systems over the years such as Point OFS (optical fiber sensor) for Corrosion, Distributed OFS for physical and chemical sensing, etc. However, these advanced SHM technologies are at their nascent stages of development, and thus, there are several challenges that exist in the industries. The techniques based on acoustic, UAVs (Unmanned Aerial Vehicles), etc. bring in various challenges, as it becomes daunting to monitor the deformations from both sides by employing only one technique. In order to determine the damages well in advance, it is necessary that the sensor is positioned inside the pipes and gives the operators enough time to carry out the troubleshooting. However, the mentioned technologies have been unable to indicate the errors, and thus, there is the requirement for a newer technology to be developed. The purpose of this review manuscript is to enlighten the readers about the importance of structural health monitoring in pipeline and wind turbine industries.

13 March 2023 in arXiv
Verified
Preprint
Open access
PDF file
RGRavi Gupta
Ravi Gupta
SNShivani Nandgaonkar
Shivani Nandgaonkar
NKNikhil Cherian Kurian
Nikhil Cherian Kurian
SRSwapnil Rane
Swapnil Rane
ASAmit Sethi
Amit Sethi
The standard diagnostic procedures for targeted therapies in lung cancer treatment involve histological subtyping and subsequent detection of key driver mutations, such as EGFR. Even though molecular profiling can uncover the driver mutation, the process is often expensive and time-consuming. Deep learning-oriented image analysis offers a more economical alternative for discovering driver mutations directly from whole slide images (WSIs). In this work, we used customized deep learning pipelines with weak supervision to identify the morphological correlates of EGFR mutation from hematoxylin and eosin-stained WSIs, in addition to detecting tumor and histologically subtyping it. We demonstrate the effectiveness of our pipeline by conducting rigorous experiments and ablation studies on two lung cancer datasets - TCGA and a private dataset from India. With our pipeline, we achieved an average area under the curve (AUC) of 0.964 for tumor detection, and 0.942 for histological subtyping between adenocarcinoma and squamous cell carcinoma on the TCGA dataset. For EGFR detection, we achieved an average AUC of 0.864 on the TCGA dataset and 0.783 on the dataset from India. Our key learning points include the following. Firstly, there is no particular advantage of using a feature extractor layers trained on histology, if one is going to fine-tune the feature extractor on the target dataset. Secondly, selecting patches with high cellularity, presumably capturing tumor regions, is not always helpful, as the sign of a disease class may be present in the tumor-adjacent stroma.