Sardar Patel College of Engineering

In the biomedical domain, the technologies like 3D computer vision and Bio-CAD arriving significant attention for computerized diagnosis, analysis and treatment of head and neck fractures. The advanced medical scanning devices internally scan and assemble the fragmented geometric data of the human body. The assembled skull model frequently suffers from damages caused by the process of the skull assembly process. Such damaged skull data may lead to missing some vital data for further medical analysis. Thus it is necessary to have an automatic mechanism of skull prototyping or completion before detect damaged skull models and repair them automatically for medical investigation. Automatic skull damage detection approach proposed using computer vision and machine learning methods in this paper. The input skull model in 3D format converted into 2D followed by the pre-processing operation to denoise and enhance the image quality. Then the Region of Interest (ROI) performed a dynamic binary segmentation technique. The automatic and manual features extracted from ROI using Convolutional Neural Network (CNN) layers and hybrid methods respectively. The hybrid model includes the structural, regional, and histogram features followed by its concatenation and normalization. The hybrid feature set is feed to conventional machine learning methods for skull damage detection. Automatic damage detection in input skull image is performed by the consolidated deep learning model using CNN (For features extraction) and Long-Short Term Memory (LSTM) for categorization called CNN-LSTM. The experimental outcomes show the high classification accuracy using the deep learning model compared to other machine learning techniques.

Urban infrastructure management demands real-time, context-aware access to subsurface utility data. This paper presents SubsurfaceXR, an augmented reality (AR) field asset management system that integrates Visual Positioning System (VPS)-anchored 3D GIS overlays with a Cesium.js-rendered 2D interactive map for simultaneous visualization of multiple utility layers-pipelines, cables, water drainage networks, and manholes. Deployed as native applications on both Android and iOS platforms, the system achieves positioning accuracy below 0.5 m using Google's ARCore Geospatial API, a significant improvement over GPS-only approaches (2-5 m error). Field validation across multiple sites in Chennai, India, yielded a critical discovery: several manholes recorded in the GIS asset database were physically undetectable due to sediment and mud accumulation. AR-guided excavation confirmed their presence at the predicted locations, demonstrating that the system can direct field investigation toward invisible infrastructure. The system was recognized with the CUMTA Innovation Open Hack Challenge award. A field-validation feedback loop is proposed as a standard protocol for AR-based infrastructure surveys, enabling iterative improvement of GIS data quality.

The chills are metallic piece which is used in casting to obtain directional solidification. The effect of chills temperature on microstructure of low alloy steel (WCB) carbon during casting process was predicated using Numerical investigation and some of the numerical cases are experimentally validated. It is found that experimental work gets validate with numerical. So, we can predicate microstructure of low alloy steel numerically by using ANSYS Fluent before actual cast can produce. This investigation is very useful for casting industries because we can predicate microstructure of casting before actual cast to be produce.

Single microgrids enhance local reliability and renewable integration; however, the next paradigm is the multi-microgrid (MMG)-an interconnected framework of multiple microgrids enabling coordinated operation, power sharing, and protection. MMGs enhance systemwide flexibility, resilience, and fault tolerance, making their behavioral study essential for future grids. Detailed analysis of power flow, current magnitude and direction, and fault characteristics under various operating modes is required for effective control and protection design. To achieve this, an accurate and scalable model is developed using OpenDSS, chosen for its advanced distribution system modeling capabilities. Conventional tools such as MATLAB or ETAP are limited in representing complex MMG interactions. Load flow analysis is carried out on the developed model to demonstrate the suitability and richness of OpenDSS for comprehensive MMG studies.

The most promising technology for creating highly self-healing concrete (SHC) resistant to cracks shortly appears to be the genetically modified Bacillus subtilis known as “Bacilla-Filla,” which is a “custom-designed” bacteria that can embed itself deeply into concrete cracks. They create a mixture of unique bacterial glue and calcium carbonate that solidifies to the same strength as the nearby concrete. This project investigates the effects of adding an incorrect amount of Bacillus subtilis to regular concrete. Additionally, it compares the different characteristics of bacterial and regular concrete, including density, compressive strength, pH, slump, and setting time. The concrete cube cracks are used to make observations regarding the healing of cracks in regular concrete and self-healing concrete. The use of a cylinder to reach the water into the cubes to activate the bacteria and heal the cracks themselves is the process studied in this project. It is evident from observation and research that self-healing concrete has many benefits. When compared to regular concrete, it is found that the self-healing concrete has less slump and more setting time, density, and compressive strength.