GITAM University, Visakhpatnam India
The project involves creating offline access to college notes using a local server. By setting up a web server (e.g., Apache) on a machine and placing the notes in a designated directory, users can access them without an internet connection. The local IP address of the machine serves as the access point. It's a user-friendly solution, allowing seamless access within a closed network. Security measures, such as firewall settings, are considered, and the project is documented for easy replication. This localized approach enhances accessibility, making important educational resources available even without an internet connection.

University of Texas at Arlington
Python project utilizes Beautiful Soup for web scraping, extracting stock opening and closing prices from a CNN stock website. The script establishes a connection to the website, retrieves the relevant data, and organizes it into a CSV file. The implementation involves sending a request to the specified URL, parsing the HTML content using Beautiful Soup, and locating specific HTML elements containing stock information. The extracted data, including opening and closing prices, is then saved to a CSV file for further analysis. This project enhances accessibility to financial data by automating the extraction process, providing a convenient tool for monitoring stock performance from the CNN website.

University of Texas at Arlington
"Employing advanced forecasting techniques in the R programming language, this project delves into the intricate realm of women's empowerment using SARIMA and ARIMA models on 2019 data. Leveraging cutting-edge statistical methodologies, our analysis unveils nuanced insights into the dynamics of women's empowerment trends. The application of Seasonal Autoregressive Integrated Moving Average (SARIMA) and Autoregressive Integrated Moving Average (ARIMA) models adds precision to our predictions, unraveling complex patterns and empowering informed decision-making. This project seamlessly integrates statistical expertise, data-driven insights, and the power of R programming to provide a comprehensive understanding of women's empowerment dynamics, substantiated by robust forecasting models and technical acumen."

University of Texas at Arlington
A Python script was developed to tackle image classification using the Fashion MNIST dataset. The script efficiently processed the dataset, creating arrays of images and harnessing various machine learning algorithms. The focus was on implementing robust models capable of accurately categorizing fashion items. Following successful training on the dataset, the project went a step further by attempting predictions with custom grayscale images. This innovative approach extended the application beyond the original dataset, showcasing the adaptability of the machine learning algorithms to new inputs. The project stands as a testament to the versatility of Python in image classification, from dataset processing to real-world image predictions."

University of Texas at Arlington
This project utilizes advanced Python scripting and diverse regression models to predict drama movies from a detailed CSV movie dataset. Employing logistic regression and other technical methodologies, the script delves into data preprocessing, extracting key features that define the drama genre. From model training to insightful predictions, Python showcases its versatility in predictive analytics. The project not only forecasts movie genres but also unravels the intricacies of storytelling, revealing the technical nuances that underpin cinematic trends. Dive into the world of data-driven film prediction, where Python scripting and regression models combine to decode the essence of drama in the cinematic landscape..

University of Texas At Arlington
Dive into the cutting-edge realm of advertisement analysis with our project, where we seamlessly blend technology and innovation. Armed with the Video Intelligence API, we embarked on a journey to categorize advertisement videos. Facing challenges with logo and label detection, we pivoted towards a novel approach—transcript analysis. Leveraging NLP tools like YAKE and Summa, we extracted dominant words, crafting a dynamic Excel sheet. This unique dataset became the training ground for our industry-centric model. Behold the birth of an intelligent classifier; our machine learning model accurately predicts the industry of new videos based on their content. Step into the future of advertisement analytics, where AI decoding transforms videos into valuable insights."