This paper is aimed to process properties of the conventional hardness and microstructure of Al-Sic nano composites with grapheme flakes. It is planned to use various combinations with weight percentage of grapheme and Sic and to produce the Aluminum matrix composites by Compression Process. The use of AL-Blast furnace slag reinforced Composite materials is finding applications day by day in engineering fields such as aero-space, automotive, aircrafts constructions, etc. Glass fibre polymer composites are reinforced with granulated blast furnace slag (GBFS) ball milled to size of 5 nm in different weight fractions, i.e. (0%, 5%, 10% and 15%) and fabricated by using hand lay-up technique. These fabricated slabs are cut into required dimensions and the tests for mechanical properties like Tension test, Compression test, Flexural test Impact test and Hardness test were performed. Tension test, compression test and Flexural test were performed on Computerized Universal Testing Machine (UTM), Impact test was performed for Izod and Charpy specimens and Hardness test was performed on Brinell's Hardness Testing Machine. From the experimental results obtained, it was noticed that the mechanical properties were enhanced when the blast furnace slag percent was increased and also among these percentages of blast furnace slag, the specimen having 5% was possessing highest properties.

Keywords :

Author : DrDVRao, M.Sukun, G.V.Ganesh Reddy , S.K.Altaf, E.Sai kumar

Title : Modeling, Analysis and Fabrication of Piston Using Al-Si/Fly ash/Granite Dust Reinforced Composite

Volume/Issue : 2022;04(4)

Page No : 1-4

There has been a recent uptick in the installation of high-tech video surveillance equipment in public areas. One of the primary uses for gathered video features is safety monitoring, made possible by the implementation of deep learning and machine learning techniques. In this work, our primary focus is on anomaly detection in situations with a large number of people, both indoors and outdoors. In this study, we describe the VGG 16 architecture for the detection of abnormalities occurring in surveillance cameras using classifiers. The VGG 16 architecture was implemented with state-of-the-art classifiers like random forest, J48, decision tree, and SVM. Experiments revealed that the suggested model of using VGG 16 has a relatively low computational burden while still producing satisfactory results, with an accuracy of 80.86% for the random forest classifier.

Keywords :

Author : KALLEPALLI ROHIT KUMAR,2DR.NISARG GANDHEWAR

Title : ANOMALY DETECTION USING VGG 16 ARCHITECTURE

Volume/Issue : 2022;04(4)

Page No : 5-12

The increasing presence of AI, cloud-native platforms and data-driven bank services resulted in new challenges around data governance, compliance with regulations, risk management and model explainability. Hence Financial institutions have to deal with large volumes of structured & unstructured data while being capital optimal and complying with regulations like Basel III, BCBS 239, GDPR, AML, KYC, PCI-DSS. Regular data warehouses and data lakes cannot offer a wide enough environment necessary for concurrent implementation of advanced analytics, explainable AI, governance automation and regulatory reporting. In this research, we propose the Regulated Banking AI Lakehouse: a comprehensive framework unifying adoption of AI-driven governance, compliance management, risk analytics & explainable artificial intelligence in a modern lakehouse architecture. Integrating all these key components, you have a framework that meets the operational and regulatory needs of contemporary banks with scalable data storage, smart metadata management powering automated compliance monitoring, real-time risk analysis and transparent AI decision-making. The architecture allows for keeping data secure and processing it, automatic policy enforcement, model governance, fraud detection as well as credit risk assessment and being audit ready. Results from experiments show that these results yield improvements relative to traditional banking data platforms on key metrics, such as governance efficiency, compliance accuracy, fraud detection performance, and regulatory reporting automation. Conclusions The findings highlight the suitability of AI lakehouse architectures as a strategic infrastructure for reliable, scalable, and regulatory compliant financial ecosystems. The framework will advance responsible AI adoption in banking, while offering a pragmatic foundation for next-generation intelligent financial services.

Keywords : AI Lakehouse, Regulated Banking, Explainable AI, Data Governance, Regulatory Compliance, Risk Analytics, Financial Intelligence, Model Governance, Responsible AI, Banking Technology

Author : Kuladeep Sandra Data Engineering Manager & Platform Leader Independent Researcher and Technology Professional

Title : The Regulated Banking AI Lakehouse: A Unified Framework for Governance, Compliance, Risk Analytics, and Explainable AI

Volume/Issue : 2022;04(4)

Page No : 13-27