Journal of Science Engineering Technology and Management Science

The author presents a novel approach for creating an antenna system for radio frequency identification (RFID) transponder devices. RFID antenna designers use silicon technologies to integrate slot-ring antennas with coplanar waveguide excitations for their infrastructure. The RFID frequency operates on the worldwide available 50-GHz band. The structure simulation occurs with Computer Simulation Technology (CST). The suggested antenna achieves a gain boost of 3.82 dB which could lead to extended reading capabilities.

Keywords : RFID, split-ring resonator, millimeter wave identification, frequency identification, and coplanar waveguide (CPW)

Author : M.Henry and Ch. Lin

Title : Compact CSRR TAG Antennas for Use at 50 GHz

Volume/Issue : 2025;02(06)

Page No : 01-05

The nature and properties of the antenna are the main topic of this article. The collective electrical signals obtained from RFID antennas necessitate sophisticated feeding, gain, and radiation pattern approaches. Following an overview of RFID technology (including its principles and the features of various RFID tags), the article provides several instances of how this technology is used in industry or daily life. The investigation of antenna properties stands essential for implementing radio frequency identification (RFID) systems and their wireless communications in various applications including road tolling systems and Bluetooth systems and wireless local area networks (WLAN) and military and personal communication systems and mobile phones and PDAs and animal traceability systems. The research proposes creating a new radio frequency identification printed antenna. The antenna achieves a bandwidth level much higher than standard printed antennas maintain in their planar configuration. The antenna shape for a printed dipole antenna displays significant reduction when operated in the same frequency band.

Keywords : Miniaturization, RFID, Bandwidth, RFID tags

Author : K. Mohan Kumar

Title : New UHF RFID Tag Antennas: Architecture and Compactness

Volume/Issue : 2025;02(06)

Page No : 06-09

The author proposes an enhanced robust model predictive controller (RMPC) which is founded on a model reference adaptive system (MRAS). The MRAS technique allows building a RMPC controller using combinational methods for three-degree-of-freedom satellites that handles external disturbances and moment of inertia uncertainty to preserve the stability and performance of the closed-loop system. The derivation of the state feedback control rule requires solving a convex optimization problem subject to multiple linear matrix inequalities (LMIs). An Input constraint functions as an LMI within the mentioned optimization framework to protect actuator saturation. Through the MRAS method all disturbances present in the system input become obsolete. By implementing this algorithm operators gain several advantages because it maintains stability under uncertain model conditions while collecting exact system information. The proposed method delivers system simulation results which demonstrate improvements compared to those obtained from generalized Incremental Model Predictive Control (GIPC). The suggestive controller achieves superior robustness when compared to the GIPC approach according to the experimental results.

Keywords : Inequality of linear matrices, Reference adaptive system model, Satellite attitude control system, Robust model predictive control

Author : Flourence and Kin Chie

Title : Sturdy Model Predictive Control for Satellite Attitude Control System Using MRAS

Volume/Issue : 2025;02(06)

Page No : 10-15

The advanced field of cryptography makes extensive use of bioinformatics together with other domains as one of its applications. The presented cypher operates by converting messages of all types—including texts and audio files and images—into sequences consisting of single-stranded DNA. A matrix of randomly generated 8x8 codon squares derived from the security key serves to encrypt series of triple codon sequences. The DNA encoding process creates such a significant difficulty that attackers cannot perform frequency analysis despite preserving the original encryption/decryption rules of traditional 5x5 Playfair. An interweaving operation should be added as a step to encrypt the sequence because it enhances unpredictability. Workers who used this approach gained multiple benefits against Playfair cypher modifications because their system encrypted all digital content types without text processing and integrated well for DNA steganography purposes. The proposed technique shows resistant behavior against cypher attacks because the original message and cipher-data bear minimal correlation between them.

Keywords : DNA Encryption, Cryptanalysis, Brute Force, Cypher, Codon, Interweaving, Playfair

Author : P. Vijay and K. Srinivasa Rao

Title : An Innovative Use of Interweaving in an Extended Playfair Cypher on DNA-Encoded Data

Volume/Issue : 2025;02(06)

Page No : 16-20

One significant biometric is the human face. contains a wealth of helpful data, including identity, gender, age, and race. Classifying people by gender is extremely easy for humans, but it can be difficult for computers. Gender classification from facial photos has garnered a lot of attention lately. When it comes to human-computer interface, gender detection can be helpful for things like individual designation. Our suggested approach is based on Gabor filters and Local Binary Patterns (LBP), which extract face features that are robust against interference. A number of algorithms have been developed for this aim, and the proportion of each of these problems has been resolved. We employed self-organizing neural networks to obtain a suitable categorization; these networks extract weights for each gender with minimal error. The outcomes are contrasted with pre-existing data sets in order to demonstrate the superiority of the suggested approach.

Keywords : Geometric features, self-organizing networks, gender classification, Gabor filters picture

Author : Armeen

Title : Application of Binary Features and Gabor Filters for Gender Recognition

Volume/Issue : 2025;02(06)

Page No : 21-24

: The research looks into the role of AI in matching large datasets to make decisions, reduce risks, and improve efficiency in these two sectors. Large datasets allow early detection of diseases, the development of personalized treatments, fraud avoidance, and improved forecasting in finance because of AI. There are challenges, including low quality of data, different systems not being able to share, ethical aspects, and rules. By using secondary data and carrying out thematic analysis, the study identified that using advanced AI, such as ensemble and federated learning, can make predictive systems flexible, secure, and transparent.

Keywords : healthcare, finance, predictive analytics, AI, flexibility, data security, ‘financial risk management’, companies, challenges, Accuracy

Author : Brody Stevens

Title : AI-Driven Predictive Analytics in Healthcare and Finance

Volume/Issue : 2025;02(06)

Page No : 25-29

The growing need for sustainable construction materials has led to increased research on the use of domestic waste in recycled concrete. This review paper examines the potential of incorporating household waste such as glass, plastics, ceramics, and organic residues into concrete production. Using these materials helps reduce landfill waste and supports a circular economy in the construction industry. Studies show that recycled aggregates from domestic waste can enhance concrete properties, including durability, strength, and workability, depending on processing methods and mixing proportions. However, challenges such as variations in waste composition, mechanical performance, and long-term durability must be addressed. This paper also explores advancements in treatment techniques, innovative concrete mix designs, and their compliance with construction standards. The findings suggest that integrating domestic waste into concrete is a viable approach for sustainable construction, reducing dependence on natural resources while maintaining structural integrity

Keywords : Domestic Waste, Recycled Concrete, Sustainability, Waste Management, Circular Economy

Author : Govind1 , Vineet Kumar2

Title : UTILISATION OF DOMESTIC WASTE MATERIAL IN RECYCLED CONCRETE : A SYSTEMATIC REVIEW

Volume/Issue : 2025;02(06)

Page No : 30-37

Concrete, as an integral construction material, plays a vital role in infrastructure construction across the globe. Over decades, Traditional Concrete (TC) has remained the preferred option for most of the structural application due to its proven characteristics and cost-effectiveness. With rising demands for better quality, faster construction, and more environmental sustainability, Self-Compacting Concrete (SCC) has become an updated alternative that helps to bridge many of the limitations connected with TC. This paper provides a detailed comparative appraisal of SCC and TC based on their performance in the fresh and hardened condition, sustainability under harsh exposure, lifecycle cost, and environmental impact. The work relies on extensive experimental testing, material characteristics, and field histories of real structures. Key conclusions indicate that SCC contains higher mechanical strength, increased resistance to permeability and chloride ingress, and far greater predicted service life compared with TC. While it is more expensive initially as a material, SCC yields more long-term economic benefit in the form of reduced labor demands, reduced construction cycles, and reduced maintenance requirements. Moreover, sustainability analysis shows that SCC, if produced using upplementary cementitious materials (SCMs), is of lower carbon footprint and promotes resource efficiency. Such benefits render SCC an able and forward-looking alternative in pursuing resilient and sustainable infrastructure. The results of the current study offer sound guidance for engineers, project managers, and policymakers to be in a position to make informed decisions on concrete choice and sustainable construction approaches.

Keywords :

Author : Lakshay Malik, Dr Deepak Kumar

Title : Comparative Analysis of Self-Compacting Concrete and Traditional Concrete for Sustainable Construction

Volume/Issue : 2025;02(06)

Page No : 38-42

The evolving global climate conditions imposed dangerous challenges on the stability and operational capabilities of construction materials. This research investigates in detail how global temperature increases, precipitation changes, heightened severe weather occurrences and increasing sea levels affect structural materials like concrete, steel and timber. This research demonstrates systematic identification of climate changeinduced material deterioration through literary review of previous studies together with performance dataset analysis and case study assessments. This research evaluates modern material solutions which aim to strengthen structural defenses. Construction regulations need adoption to combine advanced materials development for securing future safety and economic stability of infrastructure installations. This research brings civil engineering toward modern climate adaptation

Keywords : Construction Materials, Material Deterioration, Climate Adaptation, Material development

Author : Nitish Balwada, Deepak Kumar

Title : Investigation on the Effect of Climate Change on Structural Materials

Volume/Issue : 2025;02(06)

Page No : 43-47

The construction industry is facing increasing pressure to reduce its environmental impact, and concrete production is a significant contributor to global carbon emissions. As such, there is a growing interest in the development of sustainable concrete technologies. This paper examines the use of industrial by-products, agricultural waste, fibers, and recycled materials in concrete production, focusing on their potential to improve both the mechanical properties and environmental sustainability of concrete. Additionally, the integration of machine learning techniques to optimize concrete mix designs and predict concrete properties is explored. Case studies on the use of sustainable materials in extreme environments, including Martian soil for extraterrestrial construction, are also discussed. The findings suggest that while significant progress has been made, there are still challenges to overcome in terms of long-term durability, scalability, and the standardization of alternative materials.

Keywords :

Author : Sahil Rathi , Vineet Kumar

Title : Advancements in Sustainable Concrete Technology: Incorporating Waste Materials and Innovative Additives

Volume/Issue : 2025;02(06)

Page No : 48-54

In the years to come, 3-D printing, a disruptive technology, might have significant societal and economic effects. With the use of concrete and other cementitious and binder materials, the technology, which first emerged in the 1980s and was restricted to the production of tiny goods, is now being used in large-scale construction applications. Reducing or eliminating the energy and environmental footprints as well as the socioeconomic impact is recommended. The study comes to the conclusion that 3DP technology seems to be a promising substitute for traditional building methods and the usage of concrete, based on reported global warming potential (GWP) values. The sustainability potential, evaluations,and difficulties of 3DP concrete for built environment applications are all systematically reviewed in this paper. To determine the current trends and research gaps, a thorough and comparative evaluation of linked literature is conducted.

Keywords : 3D-printing, Reinforced cement concrete, Keys challenges, Future research direction, Application.

Author : Gourav1, Dr Vineet Kumar

Title : TRADITIONAL VS 3D CONCRETE PRINTING - APPLICATION AND CHALLENGES: A SYSTEMATIC REVIEW

Volume/Issue : 2025;02(06)

Page No : 55-61

The depletion of natural sand and the increasing accumulation of industrial waste, such as glass, necessitate sustainable alternatives in concrete production. This study investigates the effect of using waste crushed glass as a partial replacement for fine aggregate in M45 grade concrete. The impact of different waste glass replacement levels (10%, 20%, 30%, and 40%) was evaluated through comprehensive testing of compressive strength, flexural strength, water absorption, density, and workability. Compressive strength tests at 7, 14, and 28 days revealed that up to 20% waste glass replacement maintains structural integrity, while higher levels reduce strength due to the inert nature of glass particles. Flexural strength showed similar trends, with reduced tensile resistance at higher replacement percentages. Water absorption increased with waste glass content, suggesting higher porosity, while density measurements confirmed a decrease in mass, beneficial for lightweight applications. Workability tests indicated reduced slump and compacting factor, requiring admixtures to maintain fluidity. The study concludes that waste glass can be safely incorporated up to 20%, offering environmental and structural benefits, promoting sustainable construction practices.

Keywords : Waste Glass, High-Strength Bricks, Compressive Strength, Durability, Sustainable Construction

Author : Tushar Malik , Vineet Kumar

Title : Utilization of Waste Crushed Glass as a Partial Replacement for Fine Aggregate in M45 Grade Concrete

Volume/Issue : 2025;02(06)

Page No : 62-72

The introduction of artificial intelligence (AI) has altered the digital landscape of consumer engagement, with chatbots emerging as key tools for improving customer experiences. This paper explores the transformative influence of chatbots in rethinking consumer engagement at different points of the customer journey. It investigates how AI-powered chatbots affect consumer behavior, improve communication efficiency, and develop personalized interactions. The study, which draws on both primary and secondary data sources, gives insights into chatbot effectiveness and its implications for customer relationship management. The findings imply that chatbots play a vital role in establishing customer loyalty and satisfaction, in addition to optimizing operational efficiency.

Keywords : Artificial Intelligence, Chatbot, Customer Engagement

Author : Sonakshi Garg, Dr. Mukesh Kumar Sharma

Title : Redefining Engagement: Chatbots as Catalysts in the AI-Powered Customer Journey

Volume/Issue : 2025;02(06)

Page No : 73-78

The increasing demand for sustainable construction materials has catalyzed intensive research into environmentally responsible alternatives to traditional concrete. This literature review explores innovative strategies for incorporating industrial and construction waste materials including fly ash (FA), recycled aggregates (RA), bottom ash, polymer fibers, and various geopolymeric binders into concrete to enhance both mechanical performance and ecological sustainability. Across diverse methodologies, researchers have evaluated the effects of materials such as treated wastewater (TWW), recycled concrete aggregates (RCA), coal bottom ash (CBA), and supplementary cementitious materials (SCMs) like ground granulated blast furnace slag (GGBS) and silica fume (SF) on concrete's fresh and hardened properties, durability, and resistance to environmental degradation. Notably, the integration of fly ash across multiple studies has consistently demonstrated improvements in durability, strength development over extended curing periods, and reductions in environmental footprint particularly when combined with fiber reinforcement or alkaline activation for geopolymer applications. Collectively, these findings underscore the feasibility of transitioning toward a circular construction economy by utilizing sustainable concrete technologies without compromising structural integrity, offering a roadmap for future eco friendly building practices

Keywords : Sustainable concrete, recycled aggregates, fly ash, geopolymer concrete, supplementary cementitious materials

Author : Hitesh Kumar , Dr Deepak Verma

Title : THE ROLE OF RECYCLED MATERIALS AND SUPPLEMENTARY BINDERS IN SUSTAINABLE CONCRETE

Volume/Issue : 2025;02(06)

Page No : 79-86

Accurately predicting home prices is vital for buyers, sellers, and real estate professionals, enabling informed decisions, property valuation, and market analysis. Machine learning has become popular for this task due to its ability to analyze complex data patterns and generate predictive models. Traditional real estate pricing relies on agents’ expertise, appraisers, market trends, and comparable sales data. However, this approach can be subjective, prone to errors, and may not fully account for all factors influencing prices or scale well for large datasets. Machine learning offers a data-driven solution to improve prediction accuracy and provide deeper insights into the housing market. The challenge is to use regression analysis to predict home prices accurately. The goal is to develop machine learning models that outperform traditional methods, offering reliable predictions and actionable insights for real estate stakeholders. The proposed system uses the Boston Housing Dataset, a widely used dataset in machine learning, to train and evaluate regression models. Features like crime rate, zoning, and proximity to employment centers are used to predict home prices. Regression algorithms such as Random Forest Regression and XG Boost Regression will be employed to build these models. By leveraging these advanced techniques, the system aims to enhance prediction accuracy, improve decision-making, and provide valuable insights into market trends, addressing the limitations of traditional methods and meeting the growing demand for datadriven approaches in the real estate industry.

Keywords : Regression Analysis, Machine Learning, Boston Housing, Home prices, Model Building, Random Forest, XG Boost

Author : S. Puneeth, Md. Ammaar Quadri , M. Sahithi, Mohd. Arbas , P.S. Jyothi

Title : PREDICTING HOME PRICES: A BEGINNER’S JOURNEY WITH REGRESSION ANALYSIS USING THE BOSTON HOUSING DATASET

Volume/Issue : 2025;02(06)

Page No : 87-94

Connecting farmers directly with customers involves managing product listings, tracking inventory, processing orders, and maintaining customer records. Traditionally, these tasks have been handled through intermediaries or basic digital tools, leading to inefficiencies, increased costs, and limited direct interaction. Early systems were simplistic and lacked integration, real-time capabilities, and user-friendly interfaces. Additionally, they struggle with scalability, making it challenging to manage a large number of products and customers effectively. Limitations include delayed processing times, increased likelihood of errors, data loss, and an inability to provide real-time updates or remote access. Thus, this work develops a Django framework that offers a real-time data entry, automated inventory management, order processing, remote access, and multi-user functionality. Integrating an SQL database ensures reliable data storage, management, and retrieval, supporting efficient operations and better decision-making. The significance of designing a website with SQL integration lies in its ability to provide a robust, scalable, and efficient solution for connecting farmers with customers. An SQL backend ensures reliable and secure data storage, while a web interface allows for accessible, real-time interaction with the system. This integration enhances data accuracy and accessibility, supports efficient product and customer management, and improves overall operational efficiency. By transitioning to a modern, integrated web-based system, farmers can benefit from streamlined operations, reduced administrative workload, enhanced market reach, and improved scalability, ultimately leading to better customer satisfaction and increased profits for farmers.

Keywords : SQL Integration, DJANGO Framework, Connecting Farmers, MVT Architecture, Website

Author : A. Mamatha, A. Srikanth , K. Shoba , S. Mahendar Varma , Amgoth shiva

Title : DJANGO FRAMEWORK FOR CONNECTING FARMERS WITH CUSTOMERS USING SQL INTEGRATION

Volume/Issue : 2025;02(06)

Page No : 95-104

Medical imaging is vital for diagnosing diseases and guiding treatment across specialties like radiology, oncology, cardiology, and neurology. Advances in machine learning (ML) and artificial intelligence offer opportunities to enhance diagnosis prediction from imaging data (e.g., X-rays, MRIs, CT scans, ultrasounds). This project focuses on a comparative analysis of ML classifiers for accurate diagnosis prediction, aiming to improve efficiency, consistency, and patient outcomes in healthcare. Traditional diagnosis relies on radiologists’ expertise, which, while effective, can be timeconsuming, subjective, and limited in leveraging all image information. This project addresses challenges like noise, variable image quality, class imbalance, and robust feature extraction by developing and evaluating ML classifiers, such as Logistic Regression and Extra Trees. Feature engineering will extract relevant image data, while model optimization and ensemble methods will enhance performance. The comparative analysis will use metrics like accuracy, sensitivity, and specificity to identify the most effective classifier. The motivation is to augment medical professionals’ capabilities with quantitative, ML-driven insights, enabling faster and more accurate diagnoses. This can optimize resource allocation and improve patient outcomes. By systematically evaluating classifiers and addressing imaging challenges, this project aims to advance diagnostic tools, making them more reliable and scalable across medical specialties. The findings could transform healthcare by integrating AI into routine diagnostic workflows, ultimately supporting clinicians in delivering precise, timely, and data-driven care.

Keywords :

Author : Dr. SK. Mahaboob Basha, Nidanousheen, K. Anusha , E Sathwika Reddy

Title : DIAGNOSIS PREDICTION IN MEDICAL IMAGING: A COMPARATIVE ANALYSIS OF CLASSIFIERS

Volume/Issue : 2025;02(06)

Page No : 105-113

There are an increasing number of Internet of Things (IoT) devices connected to the network these days, and due to the advancement in technology, the security threads and cyberattacks, such as botnets, are emerging and evolving rapidly with high-risk attacks. IoT-based botnet attack is one of the most popular, spreads faster and create more impact than other attacks. In recent years, several works have been conducted to detect and avoid this kind of attacks by using novel approaches. Hence, a plethora of relevant of relevant models, methods, and etc. have been introduced over the past few years, with quite a reasonable number of studies reported in the research domain. Many studies are trying to protect against these botnet attacks on the IoT environment. However, there are many gaps still existing to develop an effective detection mechanism. These attacks disrupt IoT transition by disrupting networks and services for IoT devices. Many recent studies have proposed ML and DL techniques for detecting and classifying botnet attacks in the IoT environment. This work proposes machine learning methods for classifying binary classes i.e., Benign, or TCP attack. A complete machine learning pipeline is proposed, including exploratory data analysis, which provides detailed insights into the data, followed by preprocessing. During this process, the data passes through several fundamental steps. A random forest, k-nearest neighbour, support vector machines, and a logistic regression model are proposed, trained, tested, and evaluated on the dataset. In addition to model accuracy, F1-score, recall, and precision are also considered.

Keywords : Security Threat Detection, Behavioural Analysis, Binary Classification, Cyber Threats, Intrusion Detection System (IDS)

Author : Dr. S. Venkata Achuta Rao, G.Rahul , S.Purushotham , R.Rohith , A.Akhil

Title : Behavioural Analysis for Security Threat Detection: Machine Learning Classifier Comparison

Volume/Issue : 2025;02(06)

Page No : 114-124

The concept of a freelancer marketplace has evolved significantly with the advent of online platforms. Traditionally, freelancers relied on word-of-mouth, classified ads, and personal networks to find clients. Clients, on the other hand, sought freelancers through local directories, recommendations, or by visiting trade associations and events. Before online platforms, traditional systems involved manual processes such as posting classified ads in newspapers, distributing business cards, attending networking events, and relying on local employment agencies. These methods were time-consuming, lacked a broad reach, and made it difficult to verify the credentials and reliability of freelancers. The problem statements for traditional systems include Limited reach and visibility for both freelancers and clients, Time-consuming process of finding and vetting potential clients or service providers, Lack of a centralized system to manage job listings, transactions, and reviews, Difficulty in establishing trust and credibility without a structured review system. Research motivation for developing an online Freelancer Marketplace stem from the need to streamline and enhance the process of connecting freelancers with clients. By leveraging digital platforms, it's possible to create a more efficient, transparent, and accessible marketplace that benefits both parties. The motivation includes improving the reach, ease of use, reliability, and overall experience for users. The proposed system involves developing a website where freelancers can list their services, clients can hire them, and both parties can manage transactions seamlessly. Real-time examples include platforms like Upwork, Fiverr, and Freelancer, which have revolutionized the gig economy by providing a centralized hub for job listings, secure payment systems, and a review mechanism to build trust. These websites offer features like profile creation, service listing, job posting, secure payments, and feedback systems, ensuring a streamlined and trustworthy environment for freelancing

Keywords : Freelancer Marketplace, Online Service Marketplace, SQL Database, Review and Rating System, Real-time Data Access.

Author : Dr. G.N.V Vibhav Reddy, B.Shanmukha Sai Kumar , P.Anand , P.Shiva , Tejaswini

Title : Building A Platform For Freelancers To Offer Services With Sql Integration

Volume/Issue : 2025;02(06)

Page No : 125-138

Mental health issues, such as anxiety, depression, and other psychological disturbances, have become a significant public health concern globally. Identifying individuals at risk of these conditions early on can lead to timely interventions and improved outcomes. With the rise of technology and the increasing use of smartphones and wearable devices, there is an opportunity to develop an innovative system that can monitor emotional health in real-time, helping to detect potential psychological disturbances before they escalate. Traditionally, mental health assessments relied on self-reporting and periodic check-ins with mental health professionals. These approaches often had limitations, as individuals may not always accurately report their emotional state, and there could be significant delays between assessments. Additionally, access to mental health services was not always readily available, leading to potential delays in diagnosis and treatment. Therefore, the need for an innovative system for monitoring emotional health arises from the desire to overcome the limitations of traditional approaches. By leveraging technology, such as machine learning, natural language processing, we can create a continuous and unobtrusive monitoring system. Such a system could gather real-time data on an individual's emotional state, behavior, and physiological responses. Early detection of emotional disturbances can lead to timely intervention and support, improving the overall mental well-being of individuals and reducing the burden on mental health services. This innovative monitoring system has the potential to significantly improve mental health outcomes on a broader scale. It offers a proactive approach to emotional well-being, empowering individuals to take control of their mental health and providing an invaluable tool for mental health professionals in identifying and supporting those at risk of psychological disturbances.

Keywords : Chatbot Development, Natural Language Processing (NLP), NLTK (Natural Language Toolkit), Real-Time Monitoring, Text Classification.

Author : Mr. S Sundeep Kumar, G. Kusuma kumari, M.Shashidhar Reddy, S.Nikhil, T.V.V.S Prasad

Title : Building Your Own Chatbot: Exploring Natural Language Processing Techniques With Nltk And Nerual Networks

Volume/Issue : 2025;02(06)

Page No : 139-147

Handwritten digit classification is a fundamental problem in the field of machine learning and computer vision. It involves recognizing handwritten digits (0-9) from images. The MNIST dataset, consisting of 28x28 pixel grayscale images of handwritten digits, is a widely used benchmark for this task. In this we embark on the MNIST Handwritten Digit Classification Challenge, aiming to delve into image data analysis and explore different machine learning algorithms for accurate classification. Traditionally, handwritten digit classification was done manually by human experts. With the advent of computer vision and machine learning, automated systems have been developed to tackle this task. However, traditional systems often relied heavily on handcrafted features and simplistic algorithms, which limited their accuracy and scalability. Moreover, these systems struggled with variations in handwriting styles, noise in images, and computational inefficiency. The problem we address is to build an accurate and efficient system for classifying handwritten digits using machine learning techniques. Accurate handwritten digit classification has numerous real-world applications, including postal automation, bank check processing, and digit recognition in forms. By developing robust classification models, we can enhance the efficiency and reliability of such applications, leading to improved productivity and cost savings. The proposed system employs modern machine learning techniques, including Generalized Learning Vector Quantization (GLVQ) and Support Vector Machine (SVM), to classify handwritten digits effectively. These algorithms offer advantages such as automatic feature extraction, robustness to variations, and scalability to large datasets. Additionally, we leverage data visualization and performance evaluation techniques to gain insights into the classification process and ensure model reliability. Overall, our system aims to provide an accessible and insightful journey into image data analysis for beginners in the field.

Keywords : Handwritten Digit Classification, Machine Learning, MNIST Dataset, Image Recognition, Computer Vision, GLVQ, Support Vector Machine, Feature Extraction, Classification Accuracy, Digit Recognition.

Author : Dr SK Mahboob Basha, Sri Harsha Dixit, SV.Swathi, N.Shashank, K.Prashanth,

Title : EMBARKING ON THE MNIST HANDWRITTEN DIGIT CLASSIFICATION CHALLENGE: A BEGINNER'S JOURNEY INTO IMAGE DATA ANALYSIS

Volume/Issue : 2025;02(06)

Page No : 148-163

Managing car rentals traditionally involves manual or basic software-driven processes such as booking, tracking vehicle availability, maintaining customer records, and handling payments. These early systems often lacked integration, real-time capabilities, and user-friendly interfaces, resulting in inefficiencies like delayed processing, increased errors, data loss, and limited remote access. To address these issues, this project proposes the development of an online car rental management system featuring real-time data handling, automated booking and payment processing, remote accessibility, and multi-user support. A robust SQL backend is integrated to ensure secure, reliable, and efficient data storage and retrieval. The system's design aims to optimize operations, reduce administrative tasks, and enhance the overall customer experience. A web-based interface facilitates real-time interaction, streamlines fleet and customer management, and ensures data accuracy and accessibility. The transition to a modern, scalable solution not only supports better operational efficiency but also positions car rental businesses for future growth and improved service delivery.

Keywords : Car Rental, Real-time System, SQL Backend, Online Booking, Operational Efficiency

Author : S. Puneeth, A. Aravind Goud, M. Sreeram, K. Thirumalesh, K.Venkatesh

Title : BUILDING AN ONLINE CAR RENTAL MANAGEMENT SYSTEM WITH SQL INTEGRATION

Volume/Issue : 2025;02(06)

Page No : 164-176

The integration of machine learning-based energy consumption forecasting into smart grids offers significant benefits across various domains. In the utility sector, accurate forecasts enable optimized energy generation, load balancing, and infrastructure planning, resulting in improved operational efficiency and cost reductions. For renewable energy sources, such forecasting enhances the integration of intermittent resources like solar and wind, supporting grid stability and sustainability. In smart buildings and homes, energy forecasts empower users to manage consumption proactively, improve comfort, and reduce electricity bills. Traditional forecasting methods, such as statistical models and time series analysis, often fall short in handling the complexity of smart grid data. These methods typically depend on manual feature selection and struggle to incorporate contextual factors like weather, holidays, and user behavior, leading to reduced forecast accuracy and scalability limitations. To address these challenges, the proposed system employs machine learning algorithms that learn from diverse features—temporal data, environmental conditions, and grid characteristics— to provide more accurate and dynamic forecasts. Regression models are used to uncover complex patterns, while ensemble learning and optimization techniques further boost performance. This approach offers a robust, scalable solution for modern energy management needs.

Keywords : Smart Grids, Energy Forecasting, Machine Learning, Load Balancing, Renewable Integration

Author : K. Swayam Prabha, K. Murali Krishna, G. Ranjith Kumar, I. Laxman, D. Arun kumar

Title : MACHINE LEARNING-BASED ENERGY CONSUMPTION FORECASTING IN SMART GRIDS

Volume/Issue : 2025;02(06)

Page No : 177-186

Street lighting is essential for urban safety and security during nighttime, but traditional maintenance methods are often reactive and inefficient. Typically, maintenance relies on scheduled inspections and manual fixes, leading to delays in addressing faults, higher operational costs, and increased safety risks due to unexpected outages. These challenges highlight the need for a proactive, data-driven approach to managing street light operations. Predictive analytics, powered by data collected through sensors and IoT devices, offers a promising solution. By continuously monitoring street lights and analyzing environmental factors, predictive models can anticipate potential failures before they occur. This approach optimizes maintenance schedules, reduces energy consumption, and prevents service disruptions, resulting in significant cost savings and improved reliability. The absence of such predictive systems causes inefficient use of resources, greater energy waste, safety hazards, and operational interruptions. Integrating machine learning algorithms into street light management enables fault detection and diagnosis in real-time, supporting faster and more accurate decisionmaking. The proposed system focuses on building a comprehensive predictive analysis framework that includes data acquisition, processing, machine learning-based prediction, fault diagnosis, and decision support. Continuous evaluation ensures system accuracy and adaptability. Implementing this predictive maintenance system can transform urban lighting infrastructure by enhancing operational efficiency, reducing maintenance costs, and promoting sustainability. Ultimately, it improves public safety and the quality of urban life by ensuring well-maintained, energy-efficient street lighting, contributing to safer and more vibrant cities

Keywords :

Author : K. Madhavi, S. Rajesh, R. Maliklal Naik, B. Naveen, T. Raviteja

Title : PREDICTIVE ANALYSIS OF STREET LIGHT OPERATIONS: EXPLORING ENVIRONMENTAL FACTORS AND FAULT DETECTION IN URBAN LIGHTING INFRASTRUCTURE

Volume/Issue : 2025;02(06)

Page No : 187-194

Climate change, a lack of soil nutrients, a decrease in pollinators, plant diseases, and water waste from conventional irrigation techniques that cause water clogging on top soil are all contributing factors to our nation’s food issue. The issues are resolved by the suggested model, which contributes to a rise in agricultural irrigation efficiency. Microcontroller VEGA AS1061 is used in this system. The purpose of the spack fun soil moisture sensor is to periodically measure the soil’s moisture content and nutrients in order to develop a workable and reasonably priced model. DHT11 is used to measure temperature and humidity. And PH of soil is measured by PH sensor. With the help of sim 900 GSM module the status of soil moisture, PH level, soil nutrients and temperature is sent to the farmers’ phone. Farmers are provided with information using machine learning object recognition and picture classification, which may identify pests, animals, and birds.

Keywords :

Author : MR.R.SURESH BABU,MR.S PRAVEEN KUMAR,V. POOJITHA,P. SAIRAM GOUD,V. SIKINDER

Title : AUTONOMOUS AGRICULTURAL ROBOT BASED ON IOT

Volume/Issue : 2025;02(06)

Page No : 195-198