Explainable AI for Event and Anomaly Detection and Classification in Healthcare Monitoring Systems
Authors:-J.Sree Varenya, D.Sahithi, S.Sri Divya, A.Chakri, S.Asritha, Mrs.L.Yamuna

Abstract-Artificial intelligence (AI) is transforming healthcare by automating the detection and classification of events and anomalies, enhancing patient monitoring and intervention. In this context, events refer to abnormalities caused by medical conditions such as seizures or falls, while anomalies are erroneous data resulting from sensor faults or malicious attacks. AI-based event and anomaly detection (EAD) enables early identification of critical issues, reducing false alarms and improving patient outcomes. The advancement of Medical Internet of Things (MIoT) devices has further facilitated real-time data collection, AI-driven processing, and transmission, enabling remote monitoring and personalized healthcare. However, ensuring the transparency and explainability of AI systems is crucial in medical applications to foster trust and understanding among healthcare professionals. This work presents an online EAD approach utilizing a lightweight autoencoder (AE) on MIoT devices to detect abnormalities in real time. The detected abnormalities are then explained using Kernel SHAP, a technique from explainable AI (XAI), and subsequently classified as either events or anomalies using an artificial neural network (ANN). Extensive simulations conducted on the Medical Information Mart for Intensive Care (MIMIC) dataset demonstrate the robustness of the proposed approach in accurately detecting and classifying events, regardless of the proportion of anomalies present.

DOI: 10.61137/ijsret.vol.11.issue2.327

Published by: Kajal Tripathi

Enhancing The Discretization Method by Implementing The DOE Method to Optimize The Discretization Value Using Workbench and Ansys
Authors:-Mr. M. Vinil, Meddisetti Ramesh, Polisetti Chaitanya Anil, Bharthala Subrhamanyaswamy, Kantareddy Siva Sai

Abstract-Discretization, commonly known as meshing, plays a pivotal role in finite element analysis (FEA) as it divides a component into smaller elements for numerical simulations. The quality and size of the mesh significantly influence the accuracy, convergence, and computational cost of the simulation. This project focuses on enhancing the discretization process by implementing the Design of Experiments (DOE) method to optimize the mesh size for achieving an optimal balance between computational efficiency and result accuracy. ANSYS was utilized to perform FEA simulations on a selected component with varying mesh sizes to observe their influence on key output parameters such as stress, strain, deformation, and factor of safety. Coarser meshes lead to faster computation but may compromise accuracy, while finer meshes provide more precise results but at a higher computational expense. The DOE method was applied using Minitab software to design a set of systematic experiments, enabling the identification of the most influential factors and their interactions affecting the output.

DOI: 10.61137/ijsret.vol.11.issue2.325

Published by: Kajal Tripathi

Orientation Optimization for Reducing The Support Material Wastage in Material Extrusion Process
Authors:-Mr. M. Rambabu, Akula Hemanth Raja, Bobboli Vijay Durga Rao, Namu Karthik, Bandi Ajay Shankar

Abstract-Additive Manufacturing (AM) using material extrusion processes, such as Fused Deposition Modeling (FDM), often requires support structures to ensure the stability of overhanging or complex geometries during fabrication. However, the use of support material increases material consumption, printing time, and post-processing effort, ultimately raising production costs. This project focuses on optimizing the orientation of parts during the manufacturing process to minimize the use of support material while maintaining the structural integrity and quality of the final product .Fusion 360 was used to simulate the manufacturing process by evaluating various part orientations. By analyzing the overhang angles, build directions, and contact areas requiring supports, optimal orientations were identified. The optimization process considered parameters such as material usage, print time, and surface finish quality. Additionally, simulations were conducted to evaluate the impact of orientation changes on part strength and dimensional accuracy. The study revealed that strategic orientation adjustments could significantly reduce support material wastage by minimizing the number and size of overhangs. For instance, aligning the part’s geometry with the build platform or leveraging self-supporting angles helped achieve material efficiency. The outcomes demonstrated that reducing support material by optimizing orientation not only improves material utilization but also enhances sustainability in AM processes. This research highlights the importance of orientation optimization in material extrusion processes and showcases the potential of simulation tools like Fusion 360 to refine the manufacturing process, enabling cost-effective and resource-efficient production.

DOI: 10.61137/ijsret.vol.11.issue2.324

Published by: Kajal Tripathi

Optimization of Support Patterns to Reduce Material Wastage Using Doe Method
Authors:-Mr. K. Simon Rupas1, Dondapati Vijaya Sukruthi, Chevvakula Sai Vamsi, Appana Mahesh Aditya, Bondapalli Abhiram

Abstract-In Fused Deposition Modeling (FDM), support structures are essential for printing overhanging and complex geometries. However, excessive support material increases printing costs, material wastage, and post-processing time. This study focuses on optimizing support patterns and part orientation using Design of Experiments (DOE) methods to minimize material usage while maintaining structural stability during printing. The study evaluates two commonly used support structures: normal (grid-based) and tree-like supports, along with different part orientations to determine their impact on material consumption and overhang stability. The Taguchi DOE method is implemented to systematically analyze the influence of orientation and support type on key parameters such as printing time, support volume, and ease of removal.

DOI: 10.61137/ijsret.vol.11.issue2.323

Published by: Kajal Tripathi

Design and Fluent Simulation of Draft Tube to Increase Exist Pressure
Authors:-Mr. Ch. Sai Mohan Reddy, Punnam Yesu, Yedla Tejaswi, Adabala Srirama Surya Prakash, Mangam Ajay Kumar

Abstract-The draft tube is a critical component of hydropower plants, especially for reaction and mixed-flow turbines, as it plays a vital role in ensuring efficient energy conversion and system stability. Its design significantly impacts the overall performance of the turbine by reducing velocity at the outlet, converting kinetic energy into pressure energy, and minimizing energy losses. However, the design of an efficient draft tube comes with numerous challenges, including addressing problems such as cavitation, backflow, surging, swirl flow, and erosion of metal components due to high-velocity water flow. A well-designed draft tube should effectively mitigate these issues while maintaining optimal performance. The primary objective of this project was to design a draft tube and analyze its performance under real working conditions using advanced computational tools. The draft tube design was created using a CAD software tool, providing an accurate and detailed 3D model for further analysis. Simulation of the design was then performed using ANSYS software, with Computational Fluid Dynamics (CFD) analysis carried out in ANSYS Fluent. The CFD analysis included defining key parameters such as inlet velocity, flow patterns, outlet pressure, velocity distribution, and turbulence behaviour to replicate realistic operating conditions.

DOI: 10.61137/ijsret.vol.11.issue2.322

Published by: Kajal Tripathi

Multi Objective Optimization of Print Settings For Nominal Print Time Using Frontier Analyse Method
Authors:-Mrs. S. Hemani, Vasamsetti Mallika, Ayithireddy Bhavani Raja, Annamdevula Naga Venkata Ramana, Pujari Rupesh

Abstract-In Fused Deposition Modeling (FDM), optimizing print settings is crucial to balance print time, material consumption, and part quality. Achieving an optimal combination of parameters ensures efficient production without compromising mechanical integrity. This study employs the Frontier Analysis Method for multi-objective optimization of infill pattern, wall count, and print speed to achieve a nominal print time while minimizing material consumption and maintaining print quality .The study investigates how different infill patterns (grid, gyroid, honeycomb, and line), wall counts (single, double, and multiple), and print speeds affect the total print time, material usage, and surface finish. The Frontier Analysis Method, a data-driven optimization approach, is implemented to determine the most efficient print settings that provide the best trade-off among speed, strength, and material efficiency. The results indicate that higher print speeds reduce print time but may lead to defects such as layer misalignment and poor adhesion. Increasing wall count improves strength but leads to higher material consumption and longer print times. Similarly, infill pattern selection significantly impacts part strength and material usage, with honeycomb and gyroid infills showing better strength-to-material ratios compared to grid-based structures. Through multi-objective optimization, the study identifies optimal print settings that reduce excess material use and printing time while maintaining dimensional accuracy and mechanical properties. The findings help improve FDM printing efficiency, providing a systematic approach for selecting ideal print parameters based on specific manufacturing needs.

DOI: 10.61137/ijsret.vol.11.issue2.321

Published by: Kajal Tripathi

Optimization of Print Speed for FDM Process Using Minitab
Authors:-Mrs. B. Siva Naga Ramya, Kommukuri Praveen, Bandarlanka Satya Sai, Peddapati Sai Naredra, Boddapati Madhusudhan

Abstract-The Fused Deposition Modeling (FDM) process is widely used in additive manufacturing due to its cost-effectiveness and design flexibility. However, optimizing the print speed without compromising material consumption and surface quality remains a critical challenge. This study focuses on optimizing print speed, infill pattern, and wall count using the Design of Experiments (DOE) methodology in Minitab to achieve an optimal balance between printing time, material usage, and surface finish. The research evaluates the impact of these parameters on printing efficiency through a structured Taguchi experimental design approach, allowing for the identification of parameter settings that minimize print time while ensuring adequate part strength and surface smoothness. Various infill patterns (rectilinear, honeycomb, gyroid, and concentric), wall counts (single, double, and multiple shells), and print speeds were tested to determine their influence on material deposition rate, layer bonding, and overall print quality.

DOI: 10.61137/ijsret.vol.11.issue2.320

Published by: Kajal Tripathi

Prep Gate: Advanced GATE Exam Preparation Platform using android studio & Java
Authors:-Aman Patre, Abhishek Bawankar, Mohit Selokar, Pallavi Pandey, Professor Saroj A. Shambharkar

Abstract-Prep Gate is a comprehensive mobile application designed to aid students in preparing for the Graduate Aptitude Test in Engineering (GATE), an essential examination for aspiring engineers in India. This Android-based platform offers a wide array of tools and resources that cater to the diverse needs of GATE aspirants, providing them with easy access to study materials, practice tests, progress tracking, and more, all in a user-friendly environment. Developed using Android Studio, Prep Gate incorporates interactive features such as quizzes, mock tests, and time-based assessments, allowing users to simulate real-time exam scenarios and evaluate their performance. The app also provides essential study resources, including subject-wise notes, video tutorials, and reference materials, which can be accessed at any time, facilitating flexible learning. To enhance user engagement, Prep Gate leverages Firebase Authentication for secure user login and personalized experience, allowing users to track their progress over time, set study goals, and receive timely reminders and notifications. The platform also includes a leaderboard feature, fostering a sense of competition and motivation among users.

DOI: 10.61137/ijsret.vol.11.issue2.319

Published by: Kajal Tripathi

A Comprehensive Review of Large Language Models for Code Generation: Challenges and Future Directions
Authors:-Madhav Vyas, Dhruvi Dave, Khushaliba Gohil, Professor Mansi Gosai

Abstract-Large Language Models (LLMs) have significantly transformed the field of code generation by automating programming tasks, improving developer productivity, and enabling rapid prototyping. This review explores recent advancements in LLM-based code generation, examining both proprietary (closed-source) and open-source models. Proprietary models, such as GitHub Copilot, OpenAI Codex, and Amazon CodeWhisperer, offer high accuracy and seamless integration with development environments but limit user control. In contrast, open-source models like Code Llama, StarCoder, and PolyCoder provide transparency, customization, and self-hosting capabilities. Despite their progress, LLM-generated code faces challenges, including incorrect outputs, inefficiency, security risks, and difficulty in real-world software development. Benchmark datasets like HumanEval, MBPP, APPS, and CodeXGLUE have been developed to evaluate model performance based on correctness, efficiency, and robustness. Recent studies propose new methodologies, such as reinforcement learning and self-checking systems, to enhance accuracy and usability. Future research should focus on improving evaluation methods, contextual understanding, and security measures to ensure reliable and efficient LLM-generated code.

DOI: 10.61137/ijsret.vol.11.issue2.318

Published by: Kajal Tripathi

A Comprehensive Review of Large Language Models for Code Generation: Challenges and Future Directions
Authors:-Madhav Vyas, Dhruvi Dave, Khushaliba Gohil, Professor Mansi Gosai

Abstract-Large Language Models (LLMs) have significantly transformed the field of code generation by automating programming tasks, improving developer productivity, and enabling rapid prototyping. This review explores recent advancements in LLM-based code generation, examining both proprietary (closed-source) and open-source models. Proprietary models, such as GitHub Copilot, OpenAI Codex, and Amazon CodeWhisperer, offer high accuracy and seamless integration with development environments but limit user control. In contrast, open-source models like Code Llama, StarCoder, and PolyCoder provide transparency, customization, and self-hosting capabilities. Despite their progress, LLM-generated code faces challenges, including incorrect outputs, inefficiency, security risks, and difficulty in real-world software development. Benchmark datasets like HumanEval, MBPP, APPS, and CodeXGLUE have been developed to evaluate model performance based on correctness, efficiency, and robustness. Recent studies propose new methodologies, such as reinforcement learning and self-checking systems, to enhance accuracy and usability. Future research should focus on improving evaluation methods, contextual understanding, and security measures to ensure reliable and efficient LLM-generated code.

DOI: 10.61137/ijsret.vol.11.issue2.317

Published by: Kajal Tripathi