A Smart Capacity Enhancement and Estimation Model for Hybrid Buildings by using Light Weight Deep Learning Model

Senthil, Kumar and Nageswara Rao, Atyam and Khadar Nawas, K and Shashank, Awasthi, and Kotteeswaran, M and Thirunavukkarasu, K S (2023) A Smart Capacity Enhancement and Estimation Model for Hybrid Buildings by using Light Weight Deep Learning Model. In: 2023 International Conference on Disruptive Technologies (ICDT).

[thumbnail of IEEE-A_Smart_Capacity_Enhancement_and_Estimation_Model_for_Hybrid_Buildings_by_using_Light_Weight_Deep_Learning_Model.pdf] Text
IEEE-A_Smart_Capacity_Enhancement_and_Estimation_Model_for_Hybrid_Buildings_by_using_Light_Weight_Deep_Learning_Model.pdf

Download (5MB)

Abstract

Abstract—Generally, for the buildings constructed in our areas, the conventional foundation known as 'shallow', i.e. from the ground level downwards, is set up in three dimensions such as length, width and depth. Foundations are not the same for all types of structures. The size and structure of the foundation varies depending on the nature of the prevailing soil, ground water level of the plot, type of building, and total load of the structure. In this paper an innovation estimation model was proposed based on light weigth deep learning technique. The proposed model introduces capacity estimation and energy efficiency plans and designs. These are all relating to commercial buildings, craft facilities and mass housing projects to enable design, construction. It also maintains the buildings under minimum energy consumption without stressing the operation of buildings. The health and comfort of the occupants are establishing compliance standards and ensure the maximum standards for energy efficiency in the plans or designs of commercial buildings. The proposed model also focuses the capacity estimation and energy efficiency programs beyond maximum standards.
Keywords—Shallow, Foundation

Item Type: Conference or Workshop Item (Paper)
Subjects: Computer Science Engineering > Deep Learning
Domains: Computer Science
Depositing User: Mr IR Admin
Date Deposited: 08 May 2026 06:03
Last Modified: 11 May 2026 13:37
URI: https://ir.vistas.ac.in/id/eprint/14112

Actions (login required)

View Item
View Item