SAMSON ANOSH BABU P

Dr. SAMSON ANOSH BABU P

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
23 March 2021 in Applied Intelligence
Verified
Journal Article
Open access
PDF file
SPSAMSON ANOSH BABU P
SAMSON ANOSH BABU P
CAChandrasekhara Rao Annavarapu
Chandrasekhara Rao Annavarapu
COVID-19 has proven to be a deadly virus, and unfortunately, it triggered a worldwide pandemic. Its detection for further treatment poses a severe threat to researchers, scientists, health professionals, and administrators worldwide. One of the daunting tasks during the pandemic for doctors in radiology is the use of chest X-ray or CT images for COVID-19 diagnosis. Time is required to inspect each report manually. While a CT scan is the better standard, an X-ray is still useful because it is cheaper, faster, and more widely used. To diagnose COVID-19, this paper proposes to use a deep learning-based improved Snapshot Ensemble technique for efficient COVID-19 chest X-ray classification. In addition, the proposed method takes advantage of the transfer learning technique using the ResNet-50 model, which is a pre-trained model. The proposed model uses the publicly accessible COVID-19 chest X-ray dataset consisting of 2905 images, which include COVID-19, viral pneumonia, and normal chest X-ray images. For performance evaluation, the model applied the metrics such as AU-ROC, AU-PR, and Jaccard Index. Furthermore, it also obtained a multi-class micro-average of 97% specificity, 95% f1-score, and 95% classification accuracy. The obtained results demonstrate that the performance of the proposed method outperformed those of several existing methods. This method appears to be a suitable and efficient approach for COVID-19 chest X-ray classification.

13 April 2023 in Diagnostics
Verified
Journal Article
Open access
PDF file
CAChandrasekhara Rao Annavarapu
Chandrasekhara Rao Annavarapu
SPSAMSON ANOSH BABU P
SAMSON ANOSH BABU P
NKNikhil Keetha
Nikhil Keetha
Praveen Kumar DontaPraveen Kumar Donta
Praveen Kumar Donta
GRGurindapalli Rajita
Gurindapalli Rajita
Early detection and analysis of lung cancer involve a precise and efficient lung nodule segmentation in computed tomography (CT) images. However, the anonymous shapes, visual features, and surroundings of the nodules as observed in the CT images pose a challenging and critical problem to the robust segmentation of lung nodules. This article proposes a resource-efficient model architecture: an end-to-end deep learning approach for lung nodule segmentation. It incorporates a Bi-FPN (bidirectional feature network) between an encoder and a decoder architecture. Furthermore, it uses the Mish activation function and class weights of masks with the aim of enhancing the efficiency of the segmentation. The proposed model was extensively trained and evaluated on the publicly available LUNA-16 dataset consisting of 1186 lung nodules. To increase the probability of the suitable class of each voxel in the mask, a weighted binary cross-entropy loss of each sample of training was utilized as network training parameter. Moreover, on the account of further evaluation of robustness, the proposed model was evaluated on the QIN Lung CT dataset. The results of the evaluation show that the proposed architecture outperforms existing deep learning models such as U-Net with a Dice Similarity Coefficient of 82.82% and 81.66% on both datasets.

1 June 2021 in Chemometrics and Intelligent Laboratory Systems
Verified
Journal Article
Closed access
SPSAMSON ANOSH BABU P
SAMSON ANOSH BABU P
CAChandra Sekhara Rao Annavarapu
Chandra Sekhara Rao Annavarapu
SDSuresh Dara
Suresh Dara

1 February 2019
Verified
Conference Paper
Closed access
SPSAMSON ANOSH BABU P
SAMSON ANOSH BABU P
CAChandra Sekhar Rao Annavarapu
Chandra Sekhar Rao Annavarapu
AMAbhilash Mohapatra
Abhilash Mohapatra
The generation of substantial quantities of low-cost, high-quality next-generation sequences (NGS) has empowered mainstream researchers to address various biological and medical research problems. The vast information delivered by NGS technologies presents a big challenge for data processing, analysis, data mining, and text mining. This paper proposes a novel topic modeling technique for NGS data analysis using Probabilistic Latent Semantic Analysis (PLSA). The proposed method has four tasks: NGS dataset construction, preprocessing of data, topic modeling, and text mining using PLSA topic outputs. The NGS data of Salmonella enterica strains were used as the dataset in this procedure. The topic modeling performance is measured using standard clustering comparison measures such as Adjusted Rand Index, Normalized Mutual Information, Normalized Information Distance, and Normalized Variation of Information. The performance of PLSA topic modeling on NGS data was compared with Non-negative Matrix Factorization (NNMF) algorithm and existing Latent Dirichlet Allocation (LDA) algorithm. The Evaluations have shown that PLSA outperforms compare with NNMF and LDA topic models.

4 May 2025 in SN Computer Science
Verified
Journal Article
Closed access
PDF file
SPSAMSON ANOSH BABU P
SAMSON ANOSH BABU P
NNNitya Narla
Nitya Narla
AJAarthi Juryala
Aarthi Juryala
SRSiddhu Ramavath
Siddhu Ramavath

30 January 2024
Verified
Book Chapter
Closed access
PDF file
SPSAMSON ANOSH BABU P
SAMSON ANOSH BABU P
MDMastan Mohammed Meera Durga
Mastan Mohammed Meera Durga
VRVallela Kaushik Shashank Reddy
Vallela Kaushik Shashank Reddy
BCBoyapati Kalyan Chakravarthi
Boyapati Kalyan Chakravarthi
PSP. Vasanth Sena
P. Vasanth Sena