Volume 13 | Issue 4 |

 Abstract

The system is a research project on developing a Visual Inquiry (VI) system utilizing deep learning for visual comprehension and Natural Language Processing (NLP) for making context-based replies. VI systems are intended to understand and respond to visual content questions to deliver natural-style cognition and interaction. The system leverages Convolutional Neural Networks (CNNs) to obtain the visual features of the images to obtain salient facts like objects, scenes, and spatial relationships. They are then merged with NLP models that detect the input question in an attempt to display a compound presentation of text and image knowledge.Worthy of mention here are the use of state-of-the-art models such as attention mechanisms and Transformer models to project the image features onto the semantic features of the question. Attention layers enable the model to attend to the correct location in the image and enhance the accuracy of response generation. VI system is trained on vast amounts of data, for example, the VI v2 or Visual Genome dataset, with labeled images, questions, and answers.With the addition of vision and language processing, this VI system is able to answer appropriately to various types of questions, ranging from object recognition to more abstract reasoning questions.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Convolution Neural Networks(CNN), Vision Transaction, Image segmentation, Large Language Models(LLms), Transformer Architecture (BERT,GPT,T5), Question Answering Systems, Named Entity Recognition

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Underwater imaging often faces challenges such as reduced visibility, poor contrast, and color distortions due to light absorption and scattering in water. This project presents a novel approach to underwater image enhancement using a UNet convolutional neural network. The model was trained on a publicly available dataset of underwater images and their enhanced versions. Through its encoder-decoder structure, the U-Net model effectively improves clarity, contrast, and color fidelity. The solution includes preprocessing data, building and training the model, and developing a web application for user interaction. The application, with a Flask backend and a user-friendly frontend, allows users to upload underwater images and view enhanced outputs. By combining deep learning with accessibility, this project offers a practical tool for improving underwater image quality, catering to diverse audiences and applications.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Image Enhancement, Convolutional Neural Networks, Underwater image processing, Deep Neural Network, Machine Learning.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

As libraries embrace advanced technologies to enhance efficiency and user experience, this project presents a Library Management System integrating Radio-Frequency Identification (RFID) and Internet of Things (IoT). This system modernizes library operations by enabling seamless book borrowing and returning through RFID-enabled student identity cards and book tags. When a student places their card near an RFID reader, the system instantly verifies their identity, ensuring fast, secure, and error-free transactions. Beyond automation, the system incorporates real-time tracking of books within library racks, minimizing misplaced or lost items. Additionally, automated notifications remind students of due dates and alert them about overdue books, promoting timely returns. Designed for efficiency at minimal cost, this system optimizes library management, enhances security, and offers a more organized and user-friendly experience.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Library Management System, RFID, IoT, Real-Time Tracking, Automated Notifications, Book Borrowing and Returning, Student Identity Verification, Misplaced Book Detection, Smart Library, Low-Cost Automation.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

With the rapid pace of urbanization and industrial growth, noise pollution has become an inevitable by-product of modern development. This escalating issue is now a major concern for industrial corporations, businesses, and urban planners, affecting both productivity and quality of life. Noise mapping involves analysing and categorizing urban areas based on noise levels to assess and manage noise pollution. In this study, noise levels were surveyed at seven key locations in Nashik city using a noise level meter. The collected data was utilized to develop GIS-based noise maps, which were subsequently compared with the permissible noise levels outlined by the Central Pollution Control Board (CPCB), New Delhi. The findings revealed significant exceedances of permissible noise limits in several zones, underscoring the urgent need for targeted noise mitigation measures. These insights provide a critical foundation for local authorities to implement effective noise reduction strategies and inform urban planning initiatives aimed at minimizing the adverse impacts of noise pollution on public health and quality of life.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Road traffic noise, urban intersection, noise map, GIS

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Neuromarketing refers to the confluence of neuroscience and marketing. It is concerned with understanding how marketing strategies are designed to elicit consumer purchases. It has now extended to the financial domain, where it is crucial in determining how investment decisions are made. investors are swayed by emotions, branding, and psychological aspects more than reasoning. Interdisciplinary research demonstrates that emotions such as fear, enthusiasm, and trust have a significant influence on investment decisions in stocks, mutual funds, and other financial instruments. Financial marketers employ neuromarketing through enticing promotional and branding campaigns. Investors are unknowingly influenced by subconscious stimuli which causes them to engage in irrational, emotional, or overly cautious investing. This paper builds on past research and behavioural finance studies to discuss the role of neuromarketing in changing investor behaviour. Grasping these matters allows financial firms to better structure their marketing and enables investors to use reasoning while making investment decisions.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Neuromarketing, Investment Decisions, Investor Behaviour, Emotional Biases, Behavioural Finance, Financial Neuroscience.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Career decision-making plays a crucial role in shaping students' futures, yet many struggle due to lack of structured guidance and awareness of their strengths. This paper presents an AI-powered Career Assistance Platform, a web-based system designed to recommend personalized job roles based on students' academic performance and personality traits. The platform employs Support Vector Machine (SVM) algorithms to classify inputs and suggest relevant career paths. It is developed using PHP and Flask, with a secure backend for data management. The system was tested using real and sample input data and achieved a prediction accuracy of over 95%, validating its effectiveness in career role classification. The platform aims to bridge the gap between education and employment by offering reliable, accessible, and intelligent career guidance.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Career Prediction, Machine Learning, SVM, Web Development, Career Guidance, PHP, Flask

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The importance of Indian libraries to the country's knowledge system and their important role in its preservation shall be the main topics of this essay. With the goal of encouraging multidisciplinary research via preservation and dissemination, the 2020 education strategy has placed a strong emphasis on the Indian knowledge system. The Indian Knowledge System (IKS) is a priceless cultural legacy that offers insightful information and environmentally friendly methods. However, traditional knowledge is seriously threatened at a time of fast technological development, cultural uniformity, and globalization. With a rich history spanning thousands of years, the Indian knowledge system covers a broad range of topics, such as mathematics, astronomy, philosophy, medicine, and more. Libraries are essential for maintaining, sharing, and expanding this information. Ancient Indian libraries housed literary works, scientific papers, philosophical treatises, and holy writings. Libraries were centers for talks, debates, and intellectual interaction in addition to being locations to store books. The preservation of information, manuscripts, artifacts, and historical items is the duty of libraries that function as administrators. An extensive review of the state of the art in traditional knowledge preservation is given in this study.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Indian Knowledge System (IKS), Knowledge Preservation, National Mission for Manuscript (NMM), National Digital Library of India (NDLI), and Traditional Knowledge Digital Library (TKDL), Libraries; New Education Policy etc.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Tablets and capsules are prone to dysphagia, leading to non-compliance and inefficient therapy. To avoid difficulties associated with conventional Mouth dissolving tablets are the preferred dosage form for paediatrics, geriatrics, and traveling patients due to its hardness, consistent dose, and ease of administration. The MDTs were designed to have high hardness, integrity, and rapid disintegration without water. Fast dissolving Tablets dissolve easily in saliva, eliminating the need for water. Fast-dissolving pills dissolve quickly in saliva, taking only a few seconds. Fast-disintegrating tablets contain chemicals that speed up tablet disintegration in the oral cavity, taking up to a minute to fully dissolve. This tablet type allows for oral delivery of a substantial dose without the need for water. Tablets dissolve quickly in saliva, typically within 60 seconds.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Mouth dissolving tablet, Disintegration, Patented technologies, Marketed MDTs

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The paper reports the results of the analysis of large-scale study data of diabetes prediction by employing an array of machine learning models. The Random Forest model is found to be highly discriminatory on the training set if its Area Under the Curve (AUC) value is close to one. Overfitting or erroneous classification threshold may be one of the probable issues as it has low accuracy in properly tagging data. The research also contrasted the Gaussian Naive Bayes, XgBoost, CatBoost, Gradient Boosting, and Logistic Regression models. Consistent performance of logistic regression on datasets with mid-level accuracy and AUC revealed equally well-balanced capability in classification and ranking. XgBoost and CatBoost did well in generalization and test data accuracy, and Gaussian Naive Bayes did well on the training data but suffered a dramatic decline in performance when executed on test and unseen data, possibly due to an overfitting problem. Gradient boosting also had a very close margin of accuracy when run on unseen data but had excellent discriminative capability on all the training, test, and unseen data and excellent generalization from the training data. The research ended with an agreement that which model would be used would be based on whether the specific requirement of the application was class discrimination, label prediction, or both being more salient.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Diabetes, Blood Glucose Monitoring, Machine Learning, IoT, Classification, Prediction, Healthcare Monitoring.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Visually impaired individuals face significant challenges in navigating complex environments and accessing real-time information about their surroundings. Current assistive technologies often fall short in providing the independence and ease of use required for daily activities. This project addresses these limitations through the development of a cutting-edge smart glasses system, specifically designed to enhance mobility and accessibility for the visually impaired. The proposed smart glasses integrate a high-resolution camera, a Raspberry Pi Zero 2 W, and audio output via earphones to offer real-time auditory feedback on the user's environment. The camera captures live visual data, which is processed using advanced models like Vision language Model The Raspberry Pi Zero 2 W serves as the core processing unit, chosen for its compact size and adequate processing power, ensuring that the device remains lightweight and comfortable for prolonged use.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Raspberry Pi, Raspberry Pi Camera, Vision Language Model, Image Processing, Transformers.

  License

Creative Commons Attribution 4.0 and The Open Definition