2022
Vol 7, No 1 (2022): Temperature & Mask Scan Entry System
Authors:Â Sammed Amol Kupade, Karan Suresh Pujari, Sammed Suresh Murgunde, R.Adity Satish Chavare, Mhetar Kranti kumar
Abstract:Â IOT TECHNOLOGY Grounded TEMPERATURE and mask checkup entry system now numerous shops, services and institutionsarere-opening again after the Corona lockdown, numerous businesses are faced .with the need to give the stylish possible protection for their staff and guests. Face masks and body temperature checks play an important part in the protection trouble. While this is formerly done routinely and at a large scale at airfields or road stations, numerous businesses and institutions are floundering to meet the challenge. Face mask monitoring frequently requires fresh staff coffers. At the same time, body temperature checks by staff come with certain pitfalls in terms of hygiene and data sequestration. In this system, we proposed a completely automated temperature scanner and entry provider system. It's an amulet-purpose system that has a wide range of operations. The system makes use of a contactless temperature scanner and a masked examiner. The scanner is connected directly with a mortal hedge to bar entry if a high temperature or no mask is detected. Any person won't be handed entry without a temperature and mask checkup. The only Person having both conditions is incontinently allowed outside. The system uses a temperature detector and camera connected with a jeer pi system to control the entire operation. The camera is used to overlook for mask and temperature detector for forepart temperature. The jeer processes the detector inputs and decides whether the Person is to be allowed. In this case, the system operates a motor to open the hedge allowing the Person to enter the demesne. If a person is flagged by the system for high temperature or no Mask, the system glows the red light and bars the Person from entry. This total operation is controlled by jeers Pi.
Keywords: IOT Technology, Raspberry Pi, Temperature checks, Mask Scan Entry System
Vol 7, No 1 (2022): A Website on Online Real Estate
Authors:Â Saurabh Sunil Patil, Abhishek Vijaykumar Aptagiri, Ahsih Kishor Lande, Sainath Vynakat Patil, N.V.Shaha
Abstract:Â The world we live in today is a digital one and searching for a home is no different. Buyers now have apps that let them search by location and neighbourhoods. Online listings have virtual tours so viewers can look at many potential homes while narrowing down their search to a select few in the effort to save time. Online searching maximizes the ability to compare and contrast homes on the market by selected features. Most of this is done before a potential home buyer connects with a real estate agent.
Keywords: Real Estate, Property management, Agent, Client
2021
Vol 6, No 3 (2021): Synthetic Data Generation for Machine Learning
Authors: Dr. Ananya Mehra
Abstract: The rapid expansion of artificial intelligence (AI) has created a pressing demand for large, diverse, and high-quality datasets to train machine learning models. Synthetic data generation—creating artificial datasets through algorithms rather than collecting them from real-world events—has emerged as a viable solution to address data scarcity, privacy concerns, and bias in AI systems. This paper examines the principles, methodologies, and applications of synthetic data generation in machine learning, exploring how it enhances model accuracy, reduces overfitting, and addresses ethical issues. We discuss the key generation techniques, including generative adversarial networks (GANs), variational autoencoders (VAEs), and agent-based simulation methods. The paper also evaluates the challenges such as ensuring realism, avoiding overfitting to synthetic patterns, and maintaining fairness. Practical applications in autonomous driving, healthcare, finance, and cybersecurity are highlighted, supported by case studies. We conclude with recommendations for integrating synthetic data generation into business and research workflows, emphasizing transparency, validation, and responsible usage.
Vol 6, No 3 (2021): Analysis of Plant Disease by Applying Machine Learning Classification Techniques
Authors:Â Manu Hajari, Chandra Mouli Kathi
Abstract:Â In India, Agriculture plays an essential role because of the rapid growth of population and increased in demand for food. Therefore, it needs to increase in crop yield. One major effect on low crop yield is disease caused by bacteria, virus and fungus. It can be prevented by using plant diseases detection techniques. Machine learning methods can be used for diseases identification because it mainly apply on data themselves and gives priority to outcomes of certain task. This paper presents the stages of general plant diseases detection system and comparative study on machine learning classification techniques for plant disease detection. In this survey it observed that Convolutional Neural Network gives high accuracy and detects more number of diseases of multiple crops.
Keywords: Plant disease detection; Classification; Machine Learning.Â
Vol 6, No 3 (2021): Analysis of Covid-19 Epidemiological Data Using Machine learning and OLAP
Author:Â K. Sucharitha
Abstract: In the current technological era, huge amounts of big data are generated and collected from a wide variety of rich data sources. These big data can be of different levels of veracity in the sense that some of them are precise while some others are imprecise and uncertain. Embedded in these big data are useful information and valuable knowledge to bed is covered. An example of these big data is healthcare and epidemiological data such as data related to patients who suffered from epidemic diseases like the corona virus disease 2019 (COVID-19). Knowledge discovered from these epidemiological data—via data science techniques such as machine learning, data mining, and on line analytical processing(OLAP) helps researchers epidemiology is its and policy makers to get a better understanding of the disease, which may inspire them to come up ways to detect, control and combat the disease. In this paper, we present a machine learning and big data analytic tool for processing and analysing COVID-19 epidemiological data. Specifically, the tool makes good use of taxonomy and OLAP to generalize some specific attributes into some generalized attributes for effective big data analytics. Instead do fig nosing unknown or unstated values of some attributes, the tool provides users with flexibility of including or excluding these values, depending on their preference and applications. Moreover, the tool discovers frequent patterns and their related patterns, which help reveal some useful knowledge such as absolute and relative frequency of the patterns. Furthermore, the tool learns from the patterns discovered from historical data and predicts useful information such as clinical outcomes for future data. As such, the tool helps users to get a better understanding of information about the confirmed cases of COVID-19. Although this tool is designed or machine learning and analytics of big epidemiological data, it would be applicable to machine learning and analytics of big data in many other real-life applications and services.
Keywords: Big data, machine learning, on line analytical processing, OLAP, data science, data analytics, data mining, corona virus disease, COVID-19, epidemiological data
Vol 6, No 3 (2021): Obtaining MapReduce Monitoring and Implementation in Cloud Computing
Authors:Â Meenakshi, Ramachandra AC, Subhrajit Bhattacharya
Abstract:Â We live in an Internet-based world. On-demand information or data is required wherever and whenever it is wanted. Big Data is defined as a large volume of data in many formats that cannot be handled using typical methods such as a database management system. Hadoop's MapReduce is one of the computational techniques used in Big Data Analytics. MapReduce as a Service is provided by the cloud. We examine and analyse the problems and requirements of MapReduce integrity in the cloud in this work. The capabilities of some of the most major integrity assurance frameworks are also examined, as well as future research directions. Algorithms for detecting collusive and non-collusive personnel were discussed.
Keywords:Â Cloud Computing, Hadoop, MapReduce, Security, Integrity
Vol 6, No 3 (2021): A Study of Robust Cryptography to Ensure Safe Online Voting
Author:Â Surbhi Vashisht, Gayatri Pandey
Abstract:Â Few individuals vote these days because of their hectic lifestyles. There is a multitude of reasons for this, including the requirement for some to go to the polls, the need to wait in long lines, and the fact that many people are weary due to their hectic schedules. As a result, we created a voting system that is accessible over the internet. This strategy, however, has several drawbacks. Phishing attackers legally acquire client credentials and utilise the proper secret passwords to access critical websites. Consider a web-based voting system for corporate organisations, in which members vote once a year to elect a president, secretary, or key management. On election day, every voter must converge in one area to cast his or her ballot under the current system. We use a distinct approach termed visual cryptography in this strategy. In this design, we use visual data for security. In this step, we split the one-of-a-kind image into two halves, each of which is kept in a separate database. When these two are intertwined, we obtain the original picture. When we get our hands on the original image, we use it as a secret password. This method is incredibly handy and well-suited for online remote voting. Because this is an electronic application, it may be accessed via the web through any lawful personal space on the planet.
Keywords: Online Validation, Online voting, Visual Cryptography, Phishing attack, Cyber security, Privacy, encrypted password Â
Vol 6, No 2 (2021): Predictive Analytics in Business Intelligence Tools
Authors: Dr. Ananya Verma, Rajesh Malhotra
Abstract: Predictive analytics has emerged as a transformative capability within Business Intelligence (BI) tools, enabling organizations to move beyond descriptive insights toward proactive, data-driven decision-making. By leveraging historical datasets, machine learning algorithms, and statistical modeling, predictive analytics empowers enterprises to forecast trends, identify opportunities, and mitigate risks with greater precision. This paper explores the integration of predictive analytics into BI environments, its core methodologies, real-world applications, and the challenges faced in implementation. It further emphasizes the strategic value of predictive analytics in enhancing competitive advantage, operational efficiency, and customer satisfaction. Through illustrative examples and structured analysis, this work outlines how organizations can harness predictive capabilities to drive sustainable growth in an increasingly data-centric business landscape.
Vol 6, No 2 (2021): Forecasting Stock Market Tendency Using Machine Learning Algorithms
Authors:Â MD. Zaheda Parveen
Abstract:Â Stock is an unpredictable curve. Prediction in the stock market is covered with complexity and instability. The main aim for the persuasion of the topic is to predict the stability in the future market stocks. Many researchers have performed their research on the movement of future market evolution. Stock consists of fluctuating data which makes data an integral source of efficiency. Impact on the same chances the efficiency of the forecast. In the recent trend of Stock Market Prediction Technologies, machine learning has integrated itself in the picture for deployment and prediction of training sets and data models. Machine Learning employs different predictive models and algorithms to predict and automate things of requirement. The paper focuses on the use of Regression and to predict
Keywords: Stock, Machine Learning Algorithms, Marketization, Data Preprocessing
Vol 6, No 2 (2021): Blood Bank Management System Using Software Logistics
Authors: Dr. Ashmi Chakraborty, Intekhab Hussain, Lipika Mandal, Sumanta Karmakar, Ankita Mondal, Ishita Sharma
Abstract:Â The purpose of this study was to develop a Blood Bank Management system to assist in the management of blood donor records and ease/or control the distribution of blood in various parts of the country basing on the medical demands or needs. Without quick and timely access to donor records, creating market strategies for blood donation, lobbying and sensitization of blood donors becomes very difficult. The Blood Bank Management system offers functionalities to quick access to donor records collected from various parts of the country. It enables monitoring of the results and performance of the blood donation activity such that relevant and measurable objectives of the organization can be checked. It provides to management timely, confidential and secure. The reports generated by the system give answers to most of the challenges management faces as far as blood donor and patient records are concerned.
Â
The proposed of Blood Bank Management website helps the people who are in need of a blood by giving them all details of blood group availability or regarding the donors with the same blood group. They don’t need to hassle every wherein search of the blood in need. They just need to use this website then all the result will appear within the couple of second. Our life is so busy, and during a medical emergency it would very risky to waste even a minute, so we definitely won’t have time to hassling here and there, we can use this technical way to search the desired blood by using the Blood Bank Management we can find thousands of people who are donating the blood and also get the detail the of that person that in which city he belongs to and what is their Blood group of that person along with the unit of blood available. So in such time where world is already dealing with the pandemic, this website can be useful to settle down the risks of deaths due to unavailability or late arrival of blood.
Keywords:Â Blood Bank Management System, Software Logistics, Donating the blood, Blood Group
Vol 6, No 2 (2021): A Review on Mobile Ad Hoc Networks Security Using Alternate Path Routing
Author: Deepa Rathore
Abstract: Mobile ad hoc networks (MANETs) are made up of a collection of self- configuring wireless mobile nodes with no network infrastructure. The meaning of accountability is apparent: in a mobile ad hoc network, there is no clear assured border that can be combined or compared to a defined line in a traditional wired network. Invader attacks on these ad hoc networks are on the rise right now. Various algorithmic implementations are done to transport data over the network to avoid data breach to avoid the occurrence of these attacks. The design of MANETs raises a number of difficulties. We must provide maximal capability as well as security to these ad hoc networks in order to ensure secure communication. The shortest path algorithm is employed to provide these safeguards, however there are a number of other concerns that arise as a result of this algorithm's lack of security and efficiency, such as invader assault and concentrated load. We're looking for the Invader Safe path that's closer to the shortest than the shortest. These networks are very dynamic, mobile, and large-scale, yet they also provide static coercion, which is a source of power.
Vol 6, No 2 (2021): Efficient Distribution for Distributed OLTP DBMS
Authors: P.R.K.Ayyappa, P.Veena
Abstract: Distributed online transaction processing (OLTP) database management systems (DBMS) are characterized with ACID properties, that is atomicity, consistency, isolation, durability. However, these OLTP DBMSs that handle massive data schema, need to be scalable that cannot give up strong transactional and consistency requirements. The large-scale schemas are deployed on distributed server and each server's memory is limited, in that case, how this system partition is the key factor to affect its performance. In this paper, we present a partition approachˈ that applies to general schema and taking care of load balancing and distributed transaction rates. Our method achieve this by periodically update the partition plan and migration hot data among the servers. OLTP workload are modelled as a graph and using a graph partition algorithm to partition set of data into same server that are often co-accessed by one transaction. To evaluate our method, our framework Assort is integrated into a distributed, main-memory DBMS and shows that it can partition schema in OLTP DBMS and enable the system to outperformance traditional method 3-4 h throughput.
Keywords: OLTP, DBMS, partition, data migration
Vol 6, No 1 (2021): Accelerating IoT Responsiveness: Edge Computing as the Backbone of Real-Time Data Processing
Authors: Dr. Meghana V. Reddy, Rohit B. Narwane
Abstract: The rapid growth of the Internet of Things (IoT) has triggered an unprecedented surge in data generation. Traditional cloud computing models are often inadequate to process and respond to such massive data volumes with minimal latency. This paper investigates how Edge Computing bridges this gap by bringing computation closer to data sources, thus enhancing the real-time responsiveness of IoT applications. It explores architectural frameworks, benefits, real-world deployments, and critical challenges. Through comparative analysis and a tabulated review of latency improvement across use cases, the paper emphasizes how edge computing is transforming the performance and efficiency of modern IoT systems.
Vol 6, No 1 (2021): Cloud Computing in the Modern Era
Authors: Geeta Baisla, Sunidhi, Dr. Devendra Tyagi
Abstract: Seemingly a complicated term, cloud computing can be a simple yet liberating experience. It is rather an essential in modern computing. As for the sake of defining it, PCMag Encyclopedia defines it succinctly as "hardware and software services from a provider on the internet." In reality, cloud is a metaphor for the space that’s high end and invisible, the internet. To put it simply, cloud computing is the technology that enables users to save their data on the internet instead of the device or computer.
Vol 6, No 1 (2021): Improved PSO Scheduling Research Using Virtualization and Internet-Cloud Computing
Authors: Megha Saxena, Ritu Tiwari, Jagdeep Bhonsale
Abstract: Industry, health care, academic, development and manufacturing, as well as the private sector, are all experiencing scheduling issues these days. This paper provides an overview of the scheduling problems that particle swarm optimization can solve. It can be seen from a study of various author papers that particle swarm optimization provides better results in terms of time, productivity, and a balanced workload, among other things.
In recent years, cloud computing has exploded in popularity in the fields of computing, science, and business. Virtualization through the internet has opened up new possibilities for developing software and providing different services to end users. Since the user must pay for resource use based on time, task scheduling is critical in cloud computing. It helps to spread the load equally among system resources by optimising utilisation and reducing task execution time. In a cloud computing system, solving the scheduling problem for user requests is impossible. In order to reduce to polynomial complexity, this problem is normally solved using heuristic methods. The goal of this paper is to (1) reduce the system's total cost and (2) meet users' QOS (Quality of Service) requirements.
Vol 6, No 1 (2021): Air Quality Monitoring System
Authors:Â Abhishek Bhosle, Deegesh Gala, Harsh Gada, Manish Bhelande
Abstract:Â Now-moment of truth is air pollution is individual one of the most influential concern of the globe. Air pollution concedes possibility progress from anthropogenic or natural point of supply. Air pollutants of having or giving an atmosphere meaning like CO, CO2, SO2, NO2, and O3 suspended coarse matter (SPM), repairable pensile particulate matter (RSPM), and changeable organic compounds (VOCs) bear a excellent effect on people as political whole physical. Most of the major large town fashionable developing countries and most large town of the developed rural area exist suffering from it. Thus, to expand a actual time for action or event air quality and contamination listen system exist critical. We bear grown an arduino based air contamination indicator which linked a small-judge, minimum-cost sensor to an arduino microcontroller part. The advantages of the indicator bear a reliable resistance of some degree, very quick response improvement and long-life facial characteristics. It happens to be affordable, easy to use, cheap and minimum-power necessity tools which exist appropriate for mobile calculation, in addition to comprehensible information in visible form accumulation. It has a subject to series of actions to achieve result software intelligent to resolve, collected kind information in visible form with extreme accuracy. Simple instrument that can be commercially make use of.
Â
Vol 6, No 1 (2021): IOE Home Automation System
Authors:Â Jay Bhanushali, Karan Bhanushali, Shresht Choubey, Manish Bhelande
Abstract: With quickly developing innovation as the time passes by, individuals are exceptionally reliant on internet. So to keep up with this technological pace everybody is keen on computerizing their homes. The Internet of Everything (IOE) is a domain of Grand effect, development and potential with such fast developments of factors like smart components like homes, hospitality, smart urban areas and smart everything. Internet Of thing (IOT) develops a climate in which everything is coordinated, digitalized and smart. A majority of masses heavily depend on their smart phones or computers and want to carry out their day to day functionalities in an efficient way using this devices. Conventional or traditional homes comprises of various computerized machines that are controlled or seen by distant frameworks systems. Thus, it becomes extremely tedious to utilize and control such individual segments of homes. This rising technology and innovation has practically made possible all home parts accessible through computers. An expansion of IoT is Home Automation, where these IoT gadgets are utilized to give savvy usefulness to specific components in the home. The proposed framework utilizes an Arduino Uno, that shapes the premise of the home robotization framework and can detect the quantity of tenants in the room with the assistance of Passive Infrared (PIR) sensors and naturally switch the lights ON/OFF dependent on inhabitance. It utilizes an ESP8266 module permits Arduino to associate with a Wi-Fi organization and simplify TCP/IP associations utilizing Hayes orders. Further, the framework additionally sends information to the ThingSpeak cloud for information examination. Different and distinctive home automation systems with different conclusions and executions were proposed in literature.
The Objective is to present a IOE based methodology for productive home automation framework utilizing Node MCU and Thingspeak. ThingSpeak cloud stage is utilized to coordinate the home segments; dissect and measure the information. MQTT is executed in our proposed system for LAN communication. This paper will give an approach to IoT fashioners and experts to sense, digitalize and control the homes in setting of future IoT. Likewise, this work is filling in as an instance of how life will be less difficult with the help of IOT applications.
2020
Vol 5, No 3 (2020): AI-Driven Threat Detection and Response Systems: Transforming Cybersecurity for the Modern Enterprise
Author: Dr. Rohan Mehta
Abstract: Artificial Intelligence (AI) is revolutionizing cybersecurity by enabling faster, more accurate, and adaptive threat detection and response mechanisms. Traditional security systems rely heavily on predefined rules and human intervention, which limits their ability to respond to sophisticated, evolving cyber threats. AI-driven systems integrate machine learning, natural language processing, and deep analytics to detect anomalies, identify threats in real-time, and autonomously initiate countermeasures. This paper discusses the architecture, working principles, benefits, challenges, and enterprise-level applications of AI-driven threat detection and response systems. It also provides a comparative analysis of conventional versus AI-enabled security frameworks, supported by case studies and performance data.
Vol 5, No 3 (2020): Test Automation Frameworks for Large-Scale Projects
Authors: Dr. Aakash Mehra, Ms. Priyanka Sharma
Abstract: The rapid growth of software complexity in large-scale projects demands robust, maintainable, and scalable test automation frameworks to ensure product quality, reduce regression time, and enhance delivery efficiency. This paper explores the principles, architecture, and implementation considerations of test automation frameworks designed for large-scale environments, highlighting key features such as modularity, maintainability, reusability, and integration with CI/CD pipelines. The discussion includes comparisons of popular frameworks, their suitability for enterprise-scale deployments, and best practices to optimize testing workflows. Case studies and real-world scenarios demonstrate how organizations have achieved significant improvements in efficiency, reliability, and cost reduction by employing tailored automation strategies.
Vol 5, No 3 (2020): AI-Driven Transformation in Natural Language Processing and Conversational Agents
Authors: Dr. Meera Kapoor
Abstract: Artificial Intelligence (AI) has emerged as a transformative force in the field of Natural Language Processing (NLP), enabling the development of advanced conversational agents that can understand, interpret, and respond to human language with unprecedented accuracy. This paper explores the role of AI in NLP, focusing on algorithms, architectures, and real-world applications. It examines the evolution of conversational agents from rule-based systems to AI-powered chatbots and virtual assistants, the integration of deep learning and transformer models, and the importance of contextual understanding. Furthermore, it addresses the challenges of bias, explainability, and multilingual capabilities, alongside advancements that promise future improvements. The discussion highlights practical use cases in customer service, healthcare, education, and business process automation. Through this comprehensive analysis, the paper underscores the transformative potential of AI-driven NLP in enhancing human-computer interaction and enabling efficient, natural, and personalized communication.
Vol 5, No 3 (2020): AI-Powered Code Generation and Debugging Tools
Author: Dr. Kavita Sharma
Abstract: Artificial Intelligence (AI)-powered code generation and debugging tools have transformed the landscape of software development by automating routine programming tasks, improving accuracy, and accelerating project delivery timelines. These tools leverage advanced machine learning models, particularly large language models (LLMs), to generate high-quality source code, detect and fix bugs, and provide intelligent code suggestions in real-time. The adoption of AI in programming has enabled developers to focus on solving higher-order problems while minimizing time spent on repetitive coding activities. This paper explores the key technologies, applications, benefits, and challenges of AI-powered code generation and debugging tools, along with their potential to redefine the software engineering process.
Vol 5, No 3 (2020): Agile Scaling Frameworks for Large Enterprises: Strategies, Challenges, and Best Practices
Author: Dr. Rakesh Menon
Abstract: Agile scaling frameworks have emerged as essential methodologies to manage complex, large-scale software development projects in enterprise environments. While Agile methods were initially designed for small, cross-functional teams, large organizations require approaches that maintain agility while addressing the structural, governance, and communication needs of multi-team, geographically dispersed projects. This paper explores the evolution of Agile scaling frameworks, including SAFe (Scaled Agile Framework), LeSS (Large-Scale Scrum), and Disciplined Agile (DA), focusing on their principles, implementation strategies, and challenges. It also examines the cultural and organizational changes necessary to enable successful scaling. Through comparative analysis and industry case studies, the paper provides best practices for selecting and adopting the right framework in large enterprises. The aim is to present an integrated perspective on scaling Agile that balances adaptability with enterprise-level governance.
Vol 5, No 2 (2020): Hybrid and Multi-Cloud Infrastructure Management
Authors: Dr. Ananya Sharma
Abstract: Hybrid and multi-cloud infrastructure management is increasingly becoming a crucial aspect of enterprise IT strategy. This paper explores strategies, challenges, and solutions for effective management of such infrastructures, focusing on scalability, cost optimization, interoperability, and security.
Vol 5, No 2 (2020): Serverless Computing: Revolutionizing Cloud-Native Development Paradigms
Authors: Dr. Ananya Kapoor, Ritesh Malhotra
Abstract: Serverless computing has emerged as a transformative approach within the cloud-native ecosystem by abstracting away server management and infrastructure provisioning. This paradigm empowers developers to focus purely on code while dynamically allocating compute resources based on execution needs. Unlike traditional cloud services, serverless models such as Function-as-a-Service (FaaS) provide event-driven execution, automatic scaling, and cost efficiency. This paper presents an in-depth review of serverless computing, its architecture, key providers, benefits, challenges, and use cases. Further, it explores how this model influences software development lifecycles, DevOps practices, and real-world enterprise adoption. The ethical and operational implications are also discussed, offering a balanced perspective on this emerging trend in cloud-native computing.
Vol 5, No 2 (2020): Revolutionizing Privacy: Federated Learning and the Rise of Decentralized AI
Author: Dr. Kunal Verma
Abstract: Federated Learning (FL) is transforming how machine-learning models are trained, enabling decentralized data processing while preserving user privacy. Unlike traditional machine learning approaches that require centralized data aggregation, FL allows data to remain on edge devices, such as smartphones and IoT sensors, and only shares model updates with a central server. This paradigm promotes privacy, reduces latency, and facilitates compliance with data protection regulations like GDPR. This paper explores the architecture, benefits, challenges, and key applications of Federated Learning. Emphasis is placed on its relevance in industries like healthcare, finance, and smart cities, where sensitive data must remain confidential. The paper also provides a comparative analysis of FL with traditional learning models and outlines future research directions.