Vrushank Dhande's repositories
Ayurvedic-plant-Recognition-using-Yolov3
This undertaking revolves around ayurvedic plants with medicinal applications. Given the abundant variety of plants in our environment, it's often challenging to discern their specific use cases. Consequently, I've developed an image recognition Machine Learning model that can accurately identify and categorize these plants.
Face-Recognition-Using-CNN
In summary, I successfully completed a face recognition project using a high-accuracy CNN algorithm. The project involved recording videos, converting them to images, extracting faces, and storing them on Google Drive. To handle limited GPU access, I optimized the data and achieved an impressive accuracy of 0.9154.
Movie-Recommendation-System-Using-Machine-Learning
This project employs machine learning techniques, focusing on the Vectorizer method. It extracts and preprocesses data like actors, genres, movie names, ratings, and IDs, resulting in a refined movie.csv file. Hosted on Heroku, the project employs .git files. Converging machine learning, web development, and data management, this project details.
Bank-Behaviour-Scorecard-Master
Provided Project Description: The bank has provided user's financial data and is requesting the creation of a predictive model. The goal is to develop a model capable of forecasting customers likely to default on their EMI payments. The project aims to assess the risk associated with transactions involving the transfer of credit amounts from bank
Classification-of-the-position-of-object-using-Convolutional-Neural-Networks
This project utilizes Google Colaboratory as the online source IDE to develop a Convolutional Neural Network (CNN) for image classification. The dataset contains 7500 images of an object taken from different angles. Preprocessing, including image size reduction, was performed to ease GPU processing.
Exploratory-Data-Analysis-on-Dataset-of-Sample-Superstore
By importing necessary libraries and loading the data, we explore its structure and check for missing values and duplicates. Visualizations help us understand data patterns, such as sales by region and correlations between variables. EDA provides valuable insights for data-driven decision-making to improve the store's operations and profitability.
Exploratory-Data-Analysis-on-Indian-Premier-League
Exploratory Data Analysis (EDA) on the Indian Premier League (IPL) involves using visualizations and statistics to understand key Untitled patterns, trends, and characteristics within the dataset. EDA includes steps such as importing necessary libraries, loading the dataset, basic exploration, data cleaning, visual analysis, correlation assessment.
Hand-Detection
This project utilizes the "hand" model for hand detection, without needing GPU support. OpenCV2 is used for the entire detection process, identifying 20 hand joints. Images from 0 to 6 are displayed on the screen with Python. Through OpenCV2 and a simple prediction code, the project makes predictions between hand numbers and image numbers, display
Iris-dataset-predict-the-optimum-number-of-clusters-and-represent
To predict the optimum number of clusters for the Iris dataset and visualize it, we use the K-means clustering algorithm. The steps involve loading and preprocessing the data, determining the best 'k' using methods like the Elbow Method or Silhouette Score, applying K-means clustering, and finally, visualizing the clusters with different colors .
Predict-the-percentage-of-an-student-based-on-the-no.-of-study-hours.
This project creates a regression model to predict students' percentage based on their study hours. It includes data collection, preprocessing, and visualization. The dataset is divided into training and testing sets. A linear regression model is chosen, trained, and evaluated using MSE or R-squared. The trained model is used for predictions
Sentimental_Analysis
The process of sentiment analysis utilizes natural language processing and machine learning methods to determine the emotional tone in a piece of text. This analysis categorizes sentiment as positive, negative, or neutral and is widely applied to comprehend people's opinions and emotions toward various subjects, products, services, or general text.
Website-Creating-Using-Streamlit-and-Deploymenting-on-the-web
Streamlit is a Python library for effortlessly creating interactive web applications, especially for data science and machine learning projects. It simplifies the process of building data-driven dashboards and visualizations.