Daily Archives: June 18, 2026

Authors: Syed Ibrahim Hussain, Mahad Ansari, Mr.Kareem Basha

Abstract: Today, the brand new digital economy has revolutionized the way people travel and find a place to stay through platforms like Airbnb. For this purpose, this project is dedicated to delving into Airbnb data with the help of efficient data visualization methods to reveal significant patterns and insights. The study, by analyzing various factors such as pricing location types of rooms, availability, and customer reviews, is aiming at finding the answer to how different variables affect listing performance and user preferences. Through the use of visualization software, not only are complex datasets opened up in a simple and interactive visual manner like charts, graphs, and maps but it also becomes much easier to recognize the patterns and associations. Besides hosts, guests, and platform developers, the project also showcases the great potential of data visualization in enabling them to make better decisions. In short, this work illustrates the tremendous impact of visual storytelling in turning huge datasets into simpler ones and at the same time, providing useful insights in a real-life situation.

DOI: http://doi.org/10.5281/zenodo.20747004

Published by: vikaspatanker

Authors: Isse Sudi Mohamed

Abstract: This study attempts to close a research gap by examining the relationship between innovation and Somalia's commercial banks' competitiveness. The study's primary objective is to assess how innovation could increase the competitiveness of commercial banks. In particular, the study examines the relationship between financial innovation and commercial bank competitiveness, the impact of innovation strategy on commercial banks' competitive position, and the role of technical innovation on competitiveness. The study uses two primary research designs: predictive and explanatory. To shed light on the strength of the relationship between two or more variables at a particular moment in time, an explanatory correlational design was used. Structured questionnaires were used to gather primary data, and cross-sectional and correlational study methodologies were used. A sample of 86 respondents was chosen from the 110 members of the target demographic. The questionnaire's demographic part recorded the respondents' age, gender, marital status, and educational attainment. To guarantee accuracy and consistency, data analysis was carried out in tandem with data gathering. The study's conclusions offer commercial banks doing business in Somalia useful information. The study provides banks with useful advice on how to improve their capacity for innovation in order to get a competitive edge by documenting different types and methods of financial innovation. The findings show that bank competitiveness is significantly impacted by financial innovation and innovation strategy, but there is little correlation between technological innovation and competitiveness. Based on this conclusion, the report advises bank management to put in place efficient systems to improve internal innovation processes, especially by bolstering organizational and technology innovation practices.

Published by: vikaspatanker

Authors: Sonali Mohan Patil, Sayali Devidas Tarle, Latesh Jitendra Patel, Hrutvik Sanjay Rane, Assistant Professor Reshma Chhaburao Sonawane

Abstract: In this paper, we present TimeBank, which functions as a web application that enables Indian employers to establish and fill hourly employment positions. This initiative aims to address the problems associated with temporary labor. The service provides open-access structured hourly employment services which differ from Uber and Swiggy that limit their work to assigned tasks and Indian gig portals which primarily offer full-time job and long-term contract and project-based freelance work. The application uses a secure MERN stack architecture and includes features like real-time job posting and smart search and filtering and built-in time tracking and secure wallet-based payment gateways and a transparent rating and review system. The platform serves as the primary resource for student freelancers and employers who need to hire workers on an hourly basis with quickness and responsibility.

DOI: https://doi.org/10.5281/zenodo.20744200

Published by: vikaspatanker

Authors: Shreya Chavan, Mayuri Patil, Aarya Pawar, Professor Jayshri Kandekar

Abstract: Road traffic accidents continue to be an major global safety concern due to human error, delayed emergency response, and a lack of predictive monitoring systems. This paper presents an Integrated Intelligent Vehicle Safety System (IIVSS), a hybrid IoT and Artificial Intelligence-based frame-work designed for real-time accident prediction and automated emergency response. The proposed system integrates IMU and GPS sensor fusion with edge-level processing and cloud analytics to detect abnormal driving patterns and predict potential colli-sions. Unlike traditional reactive accident detection systems, the proposed architecture enables predictive safety analysis through anomaly detection algorithms and automated alert generation. The experimental evaluation demonstrates low latency response, reliable communication, and high detection accuracy. The sys-tem provides a scalable, cost-effective and intelligent solution for next-generation smart transportation and connected-vehicle ecosystems.

DOI: https://doi.org/10.5281/zenodo.20744104

Published by: vikaspatanker

Authors: Assistant Professor Sharad Nirgude, Shubham Gorade, Shraddha Sali, Diksha Dusane

Abstract: This study investigates the failure of a blanking die used to produce busbar connecting element parts on a mechanical press. During operation, the tool broke early than expected life. due to cracks. forming at the die center. This failure resulted in reduced production of the product. The analysis revealed high stress concentrations at the center of the die. These areas aim to identify the causes of the failure by studying the design closely and using finite element analysis with ANSYS software. A 3D model of the press tool was created by using NX software. The stress distribution is more where the cracks appeared in the failed tool. Poor clearance and design in the die increased these stress peaks. Recommendations are for improve press tool by adding same changes in design to reduce stress concentration, and improving material selection or heat treatment to improve toughness and fatigue resistance. That steps improve tool life, lower failure frequency, and enhance the reliability of busbar component element

DOI: https://doi.org/10.5281/zenodo.20744027

Published by: vikaspatanker

Authors: Sahil Arun Sahane, Suhani Sharma, Amay Prasad Sabnis, Suhani Singh, Assistant Professor Rahul B. Mandlik

Abstract: Efficient management of critical hospital resources such as intensive care unit (ICU) beds, oxygen supply, and medical staff has become a major challenge, particularly during large-scale healthcare emergencies. Conventional hospital management systems are largely reactive and often fail to anticipate sudden surges in patient demand, resulting in delayed responses and resource shortages. This paper presents MediCast, an AI-driven hospital resource forecasting and decision support system designed to predict ICU bed occupancy and oxygen demand in advance while supporting optimized resource allocation. The proposed framework employs Long Short-Term Memory (LSTM) networks for time-series forecasting of ICU admissions and oxygen consumption trends, and XGBoost models for learning complex patterns from structured hospital data. Based on the predicted demand, an optimization layer assists in efficient allocation of beds and staff resources to reduce overload and improve preparedness. The system also provides an interactive dashboard for real-time visualization of predictions, alerts, and analytical insights, enabling hospital administrators to take proactive decisions. By integrating predictive analytics and optimization within a unified platform, MediCast enhances operational efficiency, minimizes critical resource shortages, and supports data-driven healthcare management in high-demand scenarios.

DOI: https://doi.org/10.5281/zenodo.20743914

Published by: vikaspatanker

Authors: Assistant Professor Namrata Ghuse, Pratik Shinde, Yamini Sarnaik, Yash Bhoye, Jayesh Shewale

Abstract: Gamification is changing how online learning works. When we add points, badges, levels and progress tracking, students feel more interested and complete topics on time. In this paper, we show NextGenHire, a simple system that mixes gamified learning with job recommendation.In this system, a student first logs in and creates a profile with their skills. After that, the student watches learning content like web development or app development. When the learning part is over, the student gives tests. In the test, the gamification part starts where the student gets points and results based on quiz accuracy, time taken and activity. After tests, the system checks the student’s skill performance and compares it with job requirements. Using this method, the system recommends suitable jobs for the student. We also use basic data and simple comparison to check if gamification helps students to stay active and learn better. From this, we observed that students show better engagement after adding gamification.Overall, NextGenHire helps students learn and also suggests jobs based on their skills and performance, reducing the gap between learning and hiring.

DOI: https://doi.org/10.5281/zenodo.20743640

Published by: vikaspatanker

Authors: Mukul Rane, Om Baviskar, Devendra Nikam, Tejaswi Malode, Associate Professor Vaibhav Dabhade

Abstract: This paper proposes DocInsight, a context-aware document analysis system that integrates preprocessing, Optical Character Recognition (OCR), layout analysis, and semantic processing into a unified pipeline. The system enhances text extraction accuracy while preserving document structure, en- abling efficient understanding of unstructured documents. By leveraging layout-aware OCR and transformer-based semantic models, DocInsight supports intelligent search, context-driven retrieval, and automated report generation. The framework ensures improved accuracy, structural consistency, and reduced manual effort in document processing. The system is applicable across multiple domains such as healthcare, legal systems, educa- tion, and enterprise environments, where efficient and intelligent document understanding is essential

DOI: https://doi.org/10.5281/zenodo.20743556

Published by: vikaspatanker

Authors: Miss. Urvi Pawar, Miss. Shreya Rakibe, Miss. Vaishnavi Sandhan, Miss. Samruddhi Vispute, Assistant Professor Dr. Kirti Patil

Abstract: Communicating with Deaf or hard-of- hearing people can be difficult at times and the chal- lenges are great in multilingual countries such as India. This study describes current work on this but offers a proposal for an animated ISL (Indian Sign Language) translation system from Marathi text and/or speech – based on the fact that there are many more English- MSL (Marathi Sign Language) resources available and, therefore, a ’significant access gap’ when considering Deaf users within our target country. The majority of currently available translation systems have been based upon machine learning; however, due to insuffi- cient parallel corpora/annotated sign data resources for Marathi-MSL, this method will not work. The proposed system adopts as an alternative a ’rule based’ method- ology which will map the Marathi language & grammar structures onto ISL using linguistic ’rules’ and dictio- nary and will develop this through web application using React.jsTailwindCSSFlask for the front end of the web application, while allowing use of ’browser based’ storage thus ensuring a very lightweight deployment. Given that ISL requires ’gestures’, ’facial expressions’ and ’spatial syntax’, it is not possible to translate word for word; rather, the system will also consider some important Marathi grammatical elements, e.g. inflection; location/post position, verb forms, sentence structure and will therefore generate an ISL output that more accurately represents the original Marathi and promotes communication and accessibility for Deaf individuals.

DOI: https://doi.org/10.5281/zenodo.20743457

Published by: vikaspatanker

Authors: Manthan Gavali, Om Malode, Shreeyash Jadhav, Yash Chaudhari, Assistant Professor Vaibhav Dabhade

Abstract: This project addresses the challenge of robust audio content identification in noisy environments by developing an ML-based audio fingerprinting system.To overcome this limi-tation, our methodology leverages a deep learning approach, using a Convolutional Neural Network to automatically extract a compact, noise-invariant fingerprint from audio spectrograms. The system involves a multi-stage process: a diverse dataset of clean audio is first augmented with various types of noise which has different signal to noise ratios. The trained model then generates a unique fingerprint for each audio track in a database. Finally, these fingerprints are stored using a fast and efficient hashing mechanism, enabling quick retrieval and identification. Our evaluation will demonstrate that this ML-based system significantly outperforms Existing methods in terms of accuracy and robustness, particularly at low SNRs, thereby providing a more reliable solution for applications such as music recognition, broadcast monitoring, and copyright enforcement.It further introduces spectrogram normalization and data-driven feature learning that minimize the impact of background dis-tortions. A contrastive-learning objective enforces the noisy and clean versions of the same audio to have similar embeddings. To facilitate fast retrieval, the system uses an approximate nearest-neighbor search mechanism optimized for large-scale databases. The approach’s low cost computational for fingerprint generation and matching is also demonstrated by experimental results. In general, the proposed approach allows for a scalable, high-performance framework suitable for real-time audio identifi-cation in adverse acoustic environments.This paper proposes a machine learning-based audio fingerprinting system for accurate audio identification in noisy conditions. A Convolutional Neural Network (CNN) is employed to learn noise-robust and compact audio fingerprints from audio spectrograms. Noise is added to clean audio examples with varying signal-to-noise ratio (SNR) values to enhance robustness. Contrastive learning is employed to guarantee that embeddings of noisy and clean audio examples are similar. The produced audio fingerprints are stored through a hashing function, and an approximate nearest neighbor search is employed for efficient retrieval. Experimental results show enhanced audio identification accuracy with low computational complexity in low SNR conditions. The proposed system is appropriate for scalable and real-time audio identification tasks

DOI: https://doi.org/10.5281/zenodo.20743337

Published by: vikaspatanker