Arun Solomon Appadurai

Dr. Arun Solomon Appadurai


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
2 September 2022 in Computers in Biology and Medicine
Verified
Journal Article
Closed access
ASAkila Agnes S
Akila Agnes S
AJAnitha J
Anitha J
AAArun Solomon Appadurai
Arun Solomon Appadurai

6 May 2023 in Remote Sensing Applications: Society and Environment
Verified
Journal Article
Closed access
AAArun Solomon Appadurai
Arun Solomon Appadurai
ASAkila Agnes S
Akila Agnes S

29 July 2024 in Geographies
Verified
Journal Article
Open access
PDF file
AAArun Solomon Appadurai
Arun Solomon Appadurai
ASAkila Agnes S
Akila Agnes S
Recent advancements in deep learning have significantly improved the performance of remote sensing scene classification, a critical task in remote sensing applications. This study presents a new aerial scene classification model, the Multi-Scale Swin–CNN Aerial Classifier (MSCAC), which employs the Swin Transformer, an advanced architecture that has demonstrated exceptional performance in a range of computer vision applications. The Swin Transformer leverages shifted window mechanisms to efficiently model long-range dependencies and local features in images, making it particularly suitable for the complex and varied textures in aerial imagery. The model is designed to capture intricate spatial hierarchies and diverse scene characteristics at multiple scales. A framework is developed that integrates the Swin Transformer with a multi-scale strategy, enabling the extraction of robust features from aerial images of different resolutions and contexts. This approach allows the model to effectively learn from both global structures and fine-grained details, which is crucial for accurate scene classification. The model’s performance is evaluated on several benchmark datasets, including UC-Merced, WHU-RS19, RSSCN7, and AID, where it demonstrates a superior or comparable accuracy to state-of-the-art models. The MSCAC model’s adaptability to varying amounts of training data and its ability to improve with increased data make it a promising tool for real-world remote sensing applications. This study highlights the potential of integrating advanced deep-learning architectures like the Swin Transformer into aerial scene classification, paving the way for more sophisticated and accurate remote sensing systems. The findings suggest that the proposed model has significant potential for various remote sensing applications, including land cover mapping, urban planning, and environmental monitoring.

1 January 2024 in Matéria (Rio de Janeiro)
Verified
Journal Article
Open access
PDF file
AAArun Solomon Appadurai
Arun Solomon Appadurai
ASAkila Agnes S
Akila Agnes S
ANAnand N.
Anand N.
The over-exploitation of river sand for construction has led to significant environmental concerns, prompting bans and the search for viable alternatives such as Manufactured Sand (M-Sand). This study evaluates the feasibility of M-Sand as a substitute for river sand in concrete production by comparing their physical, mechanical, and durability properties. Physical property assessments include grading and specific gravity. Mechanical properties such as compressive and split tensile strengths were evaluated to determine the structural integrity of the concrete. Durability tests, including the Rapid Chloride Penetration Test (RCPT), alkalinity test, and impact resistance test, were conducted to assess the concrete’s resilience to environmental challenges. This study investigated M20, M25, and M30 grades of concrete using river sand and M-Sand. Compressive strengths for M-Sand were slightly lower than river sand but remained within acceptable ranges: 23.80 N/mm2 (M20), 27.50 N/mm2 (M25), and 33.85 N/mm2 (M30). Split tensile strengths followed a similar trend. Durability tests, including RCPT, showed comparable resistance to chloride penetration, with all mixes rated “Very Low.” Alkalinity levels were maintained between 9 and 12, protecting steel reinforcement. Impact resistance and ductility were also comparable, with an average ductility index of 1.289. M-Sand is confirmed as a sustainable alternative to river sand.

30 October 2025 in Engineering Research Express
Verified
Journal Article
Closed access
AAArun Solomon Appadurai
Arun Solomon Appadurai
ASAkila Agnes S
Akila Agnes S
Sridhar JayaprakashSridhar Jayaprakash
Sridhar Jayaprakash
Amidst escalating concerns about global climate change, the construction industry emerges as a significant contributor to environmental degradation, primarily due to its extensive resource and energy utilization. To address this gap, this study adopts a Building Information Modeling (BIM)-enabled Life Cycle Assessment (LCA) approach to quantify the Global Warming Potential (GWP) and embodied carbon of key construction materials ready-mix concrete, steel, and bricks. Four residential building models of varying scales were developed in Autodesk Revit Architecture and analyzed using the One-Click LCA tool. The results reveal that steel exhibits the highest GWP (3.2–3.6 t.CO 2 e per tonne), followed by bricks (0.24–0.28 t.CO 2 e per tonne) and ready-mix concrete (0.11–0.15 t.CO 2 e per tonne). On average, steel accounts for 34% of the total embodied carbon in buildings, making it the most carbon-intensive material. The embodied carbon benchmarks for the case studies range from 507 to 5176 kg.CO 2 e m −2 , placing all models in the high-emission (red band) category. These findings underscore the crucial need for material optimization and sustainable design strategies at early project stages. The integration of BIM with LCA thus provides a powerful decision-support tool to understand the material impact on environment and advance carbon-conscious construction practices.

1 November 2026 in Engineering Research Express
Verified
Journal Article
Closed access
AAArun Solomon Appadurai
Arun Solomon Appadurai
SAS Akila Agnes
S Akila Agnes
This paper presents a reproducible Building Information Modelling (BIM) workflow that couples sun-path and floor-by-floor shadow analysis with whole-building energy simulation, applying one geometrically invariant residential prototype across the four climatic zones of India to give architects, builders and code authorities indicative, climate-graded shading guidance. A G + 3 reference model of 391.52 m 2 , created in Autodesk Revit 2025, was replicated without geometric change in Chennai (Warm-Humid), Jodhpur (Hot–Dry), New Delhi (Composite) and Shimla (Cold). Shadow plots were generated at nine Indian Standard Time instants per city, and annual energy performance was simulated with the Revit-integrated OpenStudio and EnergyPlus engines using Indian Society of Heating, Refrigerating and Air-Conditioning Engineers typical-year weather data. In parallel, cast ground-shadow areas were derived analytically for all 36 instants from a rectangular-prism projection, with solar positions from the NREL Solar Position Algorithm. Annual site energy-use intensity (EUI) falls from 479 to 396 kWh m −2 yr −1 with internal loads held identical, and cooling takes 74.5%–81.3% of site energy in every zone; these are ideal-load results for a fully conditioned scenario, not predictions of metered consumption. The cooling-to-heating ratio falls from infinity at Chennai to about 26–1 at Shimla but never inverts. Cast shadow area spans 30–733 m 2 , and the city-mean shadow area correlates inversely with site EUI ( r = − 0.98, 95% CI −1.00 to −0.34, p = 0.019, n = 4). An independently built EnergyPlus model verifies the workflow within +6.3% to +14.2% of site energy at the three lowland cities and shows that the cloud weather data behind the BIM runs do not resolve Shimla’s 2202 m highland climate. The indicative shading recommendations and the closed-form shadow-area model give practitioners a reproducible, early-stage design aid for setting façade-specific shading and estimating cast-shadow extent at any Indian site from latitude, orientation and date alone.