Category Archives: Uncategorized

Authors: Assistant Professor Mr Pradeep, Mr. Kunal Pandey, Mr Deepanshu Tyagi

Abstract: Effective financial management is essential for individuals and businesses to track income, expenses, and overall financial health. This study presents Finlytics AI, an intelligent finance and budget management platform that leverages machine learning to enhance financial tracking, budgeting, and analysis. By integrating real-time transaction categorization, AI-powered receipt scanning, and interactive financial visualizations, the system provides users with deeper insights into their spending habits. The platform also supports multi-account tracking, recurring transaction management, and automated budget alerts to help users maintain financial discipline. With AI-driven financial reports and trend analysis, Finlytics AI empowers users to make informed financial decisions, improving both short-term budgeting and long-term financial planning. Through advanced data analytics and automation, this approach enhances the efficiency, accuracy, and accessibility of financial management, offering a scalable and intelligent solution for personal and business finance.

DOI: https://doi.org/10.5281/zenodo.16419749

Published by: vikaspatanker

Authors: Mohammed Obaid Baba, Muddam Siddartha, Pulluri Sai Vardhan, Swati Sucharita, M.A Jabbar

Abstract: The rapid evolution of machine learning (ML) technologies has significantly impacted various sectors, including education. This analysis reviews the advancements in machine learning-driven models within the educational system, highlighting their roles in enhancing teaching methods, supporting personalized learning, and predicting student performance. By employing a range of ML techniques from traditional algorithms to hybrid and deep learning approaches educators can better assess student engagement, identify at-risk learners, and tailor interventions to improve academic outcomes. The review also explores key applications such as early academic performance prediction, intelligent tutoring systems, and adaptive learning environments that respond dynamically to individual student needs. Despite the promising results, challenges such as data privacy concerns, ethical considerations, and the need for comprehensive, unbiased datasets persist. This review aims to provide a holistic view of how machine learning is reshaping the educational landscape, while discussing existing limitations and suggesting future directions to maximize the benefits of ML in education.

DOI: https://doi.org/10.5281/zenodo.16419553

Published by: vikaspatanker

Authors: Assoc. Prof. Swati Mehta, Dr. Ujjvala M. Tiwari

Abstract: For hundreds of years, creators and designers have looked to nature for inspiration. Sustainability and environmentalism have led to the widespread use of natural textures, shapes, and colours in many areas of design. More lately, graphic designers have been unable to ignore the beauty of mother nature as a source of inspiration, in contrast to paintings, sculpture, architecture, and textiles. According to a number of studies, logos that represent real-world objects—such as plants, animals, or locations—require less processing work than abstract ones because they are easier to recognize. Because they appeal to a particular target demographic and offer a personal touch, animals are a popular symbol for logos. For instance, the image of the lion, who rules the jungle, stands for power, strength, bravery, and justice. On the one hand, jewellery logos use the beauty and grace of a swan, while logos that use lions may symbolize a brand's strength or authority within its industry. Certain companies' logos use plants, trees, and flowers to symbolize life, growth, creativity, freedom, harmony, prosperity, value, and tranquillity. Unilever's emblem features 25 natural symbols: a lion and palm tree representing the RBI, a galloping horse for TVS Motor Company, a soaring swan with the Konark Chakra for Air India, and a banyan tree for Dabur India Limited. The current study focuses on how different types of nature are portrayed in logos for Indian advertising firms.

DOI: http://doi.org/10.5281/zenodo.16408435

 

 

Published by: vikaspatanker

Authors: Sudhanshu Gupta, Avinash Aganihotri, Harsh Sharma, Tanya Handa

Abstract: More people understand the use of technology and that is being used on their daily life. This will increase the chances of losing valuable data and information to the scammers who might use your data for your own detriment or have a word or a spell with you or harm you in any possible manner or way. Consequently, fraud detection Systems are employed in different fields of businesses such as banking, e-commerce, healthcare, and cybers security to identify and terminate fraud. They are essential because of the prevention of monetary losses, the protection of private information, the attainment of client confidence, and compliant with legal requirements. Some of the modern systems employ machine learning methods, while supervised learning methods are adopted to ascertain pre-defined fraud patterns and the unsupervised ones to extract anomalies. Techniques to increase precision of the identification of fraud include anomaly detection, graph based method and ensemble. Consequently, to guarantee an effective fraud detection for user it is necessary to find best fraud detection algorithm while maintaining regulatory standards and customer satisfaction , the best fraud detection algorithm must handle all aspects; efficiency, false positive disrupts, F1 score, dealing with imbalanced data and cost.

DOI: https://doi.org/10.5281/zenodo.16419380

Published by: vikaspatanker

Authors: Jeslin Hashly, Jestin K Sunil, Alby Shinoj

Abstract: This paper introduces CyberGuardian, a new LLM-based agent for autonomous penetration testing. CyberGuardian is composed of two parts: a planner and a summarizer. These parts cooperate to create and carry out commands in an iterative manner. To evaluate CyberGuardian, we introduce two new benchmark suites based on the popular Capture the Flag (CTF) systems PicoCTF and OverTheWire, comprising 200 challenges in various domains and levels of difficulty. Our experiments check CyberGuardian's most critical parameters, such as levels of creativity and token usage, on LLM. Results reaffirm the need of good security procedures and show how LLM-based agents can advance autonomous penetration monitoring.

DOI: https://doi.org/10.5281/zenodo.16419170

Published by: vikaspatanker

Authors: Sharath Chandra Kodtihyala, Riddhi kinnera, Shashikiran Sangisetti, Praveem Kumar, Prasanthrao A

Abstract: This study presents Polyglot, a deep learning-based language translation system that utilizes Transformer, LSTM, Attention, and Seq2Seq models to enhance context-aware translation. While well-known systems like Google Translate provide reliable translations, Polyglot offers improved contextual understanding through a hybrid approach that balances accuracy and efficiency. The study evaluates Polyglot’s performance using BLEU scores and user satisfaction, demonstrating its effectiveness. It includes a detailed discussion on the dataset, model architecture, training process, and evaluation criteria. The results indicate a significant improvement in translation quality compared to baseline models. Future work will focus on real-time improvements and customization to further enhance translation accuracy and user experience

DOI: https://doi.org/10.5281/zenodo.16418885

Published by: vikaspatanker

Authors: Deepti Ram Gangurde, Arun Mishra, Shantanu Singh

Abstract: This research proposes a decentralized courier tracking system using blockchain technol- ogy and smart contracts, aimed at enhancing transparency, trust, and security in logistics. The solution is implemented on the Volta blockchain and integrates MetaMask[3] to facilitate se- cure interactions between participants without relying on centralized intermediaries. The sys- tem automates shipment updates, maintains immutable tracking records, and protects sensitive data through cryptographic mechanisms. The implementation demonstrates improved trace- ability, operational efficiency, and stakeholder accountability. Performance evaluation indi- cates significant enhancements in security, cost-effectiveness, and scalability when compared to conventional courier tracking methods. The proposed system offers a robust alternative for modern supply chain management[6].

DOI: https://doi.org/10.5281/zenodo.16418691

Published by: vikaspatanker

Authors: Yassine Dahbi, Hamza Naciri, Hamza Zaouri, Ouahib Alaoui

 

Abstract: This study examines the use of GradientBoostingRegressor, StackingRegressor, and Gradient Boosting Regression with HistGradientBoosting in developing models that predict the compressive strength (fcu) and splitting tensile strength (fsp) of steel fiber-reinforced recycled aggregate concrete (SFR-RAC). The information comprises 465 compressive strength and 339 splitting tensile strength data of concrete mixes with varied ratios. Training and model testing were performed using 80/20 split with PSO for the hyperparameter optimization. The performance of the model was measured with four statistical metrics: coefficient of determination (R²), mean absolute error (MAE), root mean squared error (RMSE), and mean absolute percentage error (MAPE). Out of the models, Gradient Boosting Regression with HistGradientBoosting performed better in terms of prediction, with StackingRegressor taking the second rank. SHapley Additive exPlanations (SHAP) and feature importance were employed to determine the influence of input parameters on model predictions. From the results obtained, it was evident that the water content, cement content, and fiber ratio influence considerably the strength of SFR-RAC. The models give good insights regarding SFR-RAC mixture behavior, which is helpful in the production of environmentally friendly concrete with greater enhanced strength. Future research can enhance the data and use other predictor variables to further support these models.

DOI: https://doi.org/10.5281/zenodo.16420152

 

Published by: vikaspatanker

Authors: Saba Zaidi, Thakur Nikhil, Tripti Goyal, Veersavarkar

Abstract: To meet the need of productivity concerns, project timelines, and changing needs, this research explores the interesting realm of web service development. The overall purpose of this research is to develop an easy-to-use and effective development system based on the Django framework. This provides programmers with the facility to simply develop web services that are efficient, effective, and reliable. Utilizing the Model-View-Template (MVT) design pattern is important, as it is compatible with list management systems. The overall effectiveness and efficiency of the system are improved by web page creation being automated using HTML, CSS, and Python modules; protocols for data sharing are standardized, system users are decentralized, and user login and registration processes are accelerated are all prioritized at their best. My SQL maintains the data base efficiently, and Django manages the smooth data interaction to provide an integrated and efficient user experience. Another central area of focus in this research is the development of a web application that provides secure, real-time user interactions while encrypting data to preserve its confidentiality and integrity. Django REST framework is employed to create a stable service that integrates with the front-end seamlessly through REST APIs. This allows HTML/CSS and JavaScript to drive a dynamic and interactive user interface. The research points out the key features of Django, including its administrative capabilities, Object-Relational Mapping (ORM), comprehensive documentation, secure and rapid development features, and REST API support. A deeper understanding of this dynamic subject attempts to shed light on the development, importance, challenges, and modern solutions in web technology and web service development. Following our research, the goal is to use Django to develop are liable, effective, and secure online application. Our goal is to use all of its characteristics to streamline the development process. Django's solid frame work promises the assurance of scalability and reliability .Our aim is to utilize its benefits for an extensive, modern, and efficient web service creation, ensuring a successful outcome meeting the increasing demands for efficient web services. In today’s digital world, websites and web applications play a very important role in how we communicate, do business, and share information. To build these websites, developers use tools called web frameworks. One of the most popular frameworks is Django, which is written in the Python programming language. This research paper explains how Django helps developers create websites faster and more efficiently. Django follows a structure called MVC (Model-View-Controller), or in Django’s case, MTV (Model-Template-View). This helps keep the code organized and easy to manage. Django also comes with many built-in features like user authentication, database management, security, and admin interface, which save time and effort for developers. The paper highlights Django’s advantages like its security features, scalability, and reusability of code. It also compares Django with other popular frameworks to show where Django performs better and where it might not be the best choice. In short, Django is a powerful tool that allows both beginners and professional developers to build high-quality web applications quickly and securely. This research explores Django’s role in modern web development and why it is a preferred choice for many developers and companies .The research by Idris et al. emphasizes Django's comprehensive nature, highlighting its suitability for developers seeking a full-featured framework that handles various aspects of web development out-of-the-box. This contrasts with frameworks like Flask, which offer more flexibility but require additional setup for features that Django provides by default. Moreover, Django's emphasis on security is notable. It includes protections against common web vulnerabilities like cross-site scripting (XSS), cross-site request forgery (CSRF), and SQL injection, ensuring that applications built with Django are robust and secure.

DOI: https://doi.org/10.5281/zenodo.16418373

Published by: vikaspatanker

Authors: Himanshu Shahoo, GautamYadav, ChinmayeeTripathy, Padmaja Panda

Abstract: Flower identification is a crucial aspect of plant classification and ecological research, playing a significant role in understanding biodiversity and ecosystem dynamics. This research paper presents a new approach to flower identification using advanced deep learning techniques. The proposed system used folding networks (CNNs) to automatically extract hierarchical features from high-resolution images of flowers, allowing for more accurate and efficient classification. The procedure is implemented as a multi-stage process, beginning with data preprocessing to enhance image quality and remove noise. Using another data record, educated CNN models such as modified reset 50, VGG16, or Google are then fine-tuned with commented flower images. Furthermore, transfer learning is used to properly use knowledge from large data records and improve the ability of models to generalize different types of flowers.. In the end, our approach achieved an accuracy of 82.04% using VGG16, the highest compared to other algorithms.

DOI: http://doi.org/10.5281/zenodo.16610684

Published by: vikaspatanker