Sandhyalaxmi G. Navada

Dr. Sandhyalaxmi G. Navada


Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
16 December 2025 in Systems Science & Control Engineering
Verified
Journal Article
Open access
OPOmkar Prabhu
Omkar Prabhu
SNSandhyalaxmi G. Navada
Sandhyalaxmi G. Navada

29 October 2017
Verified
Book Chapter
Closed access
PDF file
SNSandhyalaxmi G. Navada
Sandhyalaxmi G. Navada
CAChandrashekara S. Adiga
Chandrashekara S. Adiga
SKSavitha G. Kini
Savitha G. Kini

1 January 2014
Verified
Conference Paper
Closed access
NMNitesh Mishra
Nitesh Mishra
TJTanvi Jain
Tanvi Jain
SNSandhyalaxmi G. Navada
Sandhyalaxmi G. Navada
This paper focuses on the thermal and lighting analysis of two standard office models. The first model is an office in Department of Electrical and Electronics, Manipal Institute of Technology, Manipal University. The second model is a general office taken in Manipal. Manipal is located 13.3500° N, 74.7800° E. It experiences tropical climate. Temperature ranges from 29° C to 34°C and the highest temperature is recorded in the months of March to May. For this project models are designed using Ecotect environment using its own internal drawing commands, extrusions and other modeling features. By changing the orientation of the room, angle of the blinds, material of the floor and walls, lighting and thermal analysis is done and one optimum design is created to achieve maximum energy saving.

28 November 2016 in Indian Journal of Science and Technology
Verified
Journal Article
Open access
PDF file
TATini Grace Abraham
Tini Grace Abraham
SNSandhyalaxmi G. Navada
Sandhyalaxmi G. Navada
SKSavitha G. Kini
Savitha G. Kini
NGNidhi Gupta
Nidhi Gupta
Objective: To study the effect of various energy conservation measures on building energy performance. Analysis: U.S Green Building Council’s Leadership in Energy and Environmental Design (LEED) Rating System for green building uses energy modeling as one way to demonstrate the energy use of a building and to quantify the savings to the proposed design. A whole building energy simulation tool, Visual DOE4.0 is used to estimate the energy performance of an office building in warm and humid climate. The tool is used for recommending energy saving strategies for insulation, glazing, shading devices, lighting and controls and air conditioning equipment. Performance analysis of the building with different combinations of measures is carried out to identify the best possible strategy. Findings: It is analyzed green roof, insulated AAC wall, glazing system with low Solar Factor (SF) , shading devices, energy efficient air conditioning and efficient lighting systems & control helps in reducing the annual energy consumption of building by 20.85% compared to American Standard for Heating Refrigeration and Air conditioning Engineer’s (ASHRAE) standard building. Improvement: Further investigation can be carried out with different configurations in wall, roof, shading devices, air conditioning system, using daylight sensors in the periphery and also by the use of renewable energy sources.

29 May 2026 in Scientific Reports
Verified
Journal Article
Open access
RSRachana V. Shanbhogue
Rachana V. Shanbhogue
NGNeha S. Gandhi
Neha S. Gandhi
SBShanthi P. B.
Shanthi P. B.
SNSandhyalaxmi G. Navada
Sandhyalaxmi G. Navada
Human Heparanase (HPSE), the only mammalian endo- $$\beta$$ -D-glucuronidase, plays an important role in extracellular matrix remodeling and the release of heparin-bound growth factors. Its overexpression is strongly correlated with increased tumor growth, angiogenesis, metastasis, and inflammation, highlighting HPSE as a compelling therapeutic target for oncology and inflammatory diseases. This study aimed to develop and validate a robust computational workflow for predicting the activity class of potential HPSE inhibitors using curated data from the ChEMBL database. Bioactivity data ( $$pIC_{50}$$ ) for known HPSE inhibitors were extracted and put through a meticulous data curation process, which included chemical structure standardization, molecular weight filtering, and final deduplication based on standardized isomeric SMILES to ensure structural uniqueness. Continuous $$IC_{50}$$ values (nM) were converted to $$pIC_{50}$$ and subsequently categorized into three activity classes: A ( $$pIC_{50} \ge 4$$ and $$< 5$$ ), B ( $$pIC_{50} \ge 5$$ and $$< 6$$ ), and C ( $$pIC_{50} \ge 6$$ and $$< 7$$ ) for multi-class classification. Molecular representations included two-dimensional physicochemical descriptors, Morgan fingerprints, and three-dimensional descriptors derived from optimized low-energy conformers generated using ETKDGv3 and MMFF94s. Multiple machine learning classifiers were evaluated using pipelines incorporating imputation, scaling, optional Principal Component Analysis (PCA) dimensionality reduction applied to the combined feature sets, and SMOTE (Synthetic Minority Over-sampling Technique) to address class imbalance. Models were trained and optimized using randomized search cross-validation on an 80% training split, maximizing balanced accuracy. The best-performing model pipeline (RF_B, a Random Forest with PCA on 2D+Morgan Fingerprints+3D features) achieved approximately 80% accuracy and 78.5% balanced accuracy on the held-out 20% test set. The final validated model was successfully utilized to predict the activity classes of new, unseen compounds. This comprehensive pipeline provides a validated tool for classifying HPSE inhibitors derived from ChEMBL data, potentially aiding virtual screening efforts and guiding hit prioritization in drug discovery campaigns targeting HPSE.

12 November 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
DCDeeksha Chetan
Deeksha Chetan
SBSandeep Bhat
Sandeep Bhat
SNSandhyalaxmi G. Navada
Sandhyalaxmi G. Navada
UNURVASHI S NAIK
URVASHI S NAIK
Deep transfer learning has been used to classify oral cancer in clinical photographs. Most comparisons depend on a single training run and data split, and few control for leakage or test on external data. In this study, 2,444 images from five public repositories were audited using perceptual hashing and deep-feature similarity. Duplicates and label conflicts accounted for 57.2% of files, and 1,045 images were retained. Seven ImageNet-pretrained convolutional neural networks were trained with three seeds each under a common two-stage protocol. Checkpoints and a threshold of 0.5 were fixed on validation data before the models were evaluated once on an internal test set and on an independent clinical cohort (813 images; 303 patients). Mean internal areas under the ROC curve (AUCs) were between 0.951 and 0.972, and after Holm adjustment no model differed significantly from ResNet50. On the external cohort, ResNet50 retained moderate discrimination (AUC 0.855; 95% confidence interval, 0.808–0.893), whereas its specificity declined from 0.887 to 0.320. A threshold derived from 91 external patients increased specificity on the remaining 212 patients to 0.756 (sensitivity 0.790). Evaluation design had a larger effect than the choice of architecture. Leakage auditing, locked external validation and local recalibration should precede clinical application.