EthiovitalEase is a machine learning project that aims to detect pneumonia from chest X-ray images using deep learning techniques. Developed as a graduation project by a team of three led by me, the project integrates React for the frontend, Flask for the backend, and TailwindCSS for styling. Its primary goal is to assist healthcare professionals in early and accurate diagnosis of pneumonia, ultimately enhancing patient outcomes. Through this project, I gained hands-on experience in deep learning and strengthened my commitment to leveraging AI in the healthcare sector.

Sebil Ai Predictor is a machine learning project that aims to help farmers choose the most suitable crops to cultivate based on environmental factors. It analyzes data such as soil type, nutrient content, humidity, pH, and temperature to generate personalized crop recommendations. By leveraging historical agricultural data and machine learning algorithms, the system empowers farmers to make data-driven decisions that can improve yield and sustainability.

House Price Predictor is a machine learning project designed to estimate property prices using linear regression enhanced with polynomial features. Trained on a dataset containing various housing attributes, the model analyzes patterns to make accurate predictions of house values. This project demonstrates the practical use of regression techniques in real estate and highlights the importance of feature engineering in improving model performance.

Customer Segmentation with K-Means is a machine learning project that groups customers based on purchasing behavior and demographic data. By applying the K-Means clustering algorithm, the model identifies distinct customer segments, enabling businesses to tailor their marketing strategies, enhance customer engagement, and increase overall sales. This project showcases the value of unsupervised learning in driving data-informed business decisions.

Cat vs. Dog Classifier is a machine learning project that uses a Support Vector Machine (SVM) model to distinguish between images of cats and dogs. The model is trained on a subset of the Kaggle Dogs vs. Cats dataset and integrated with a simple Gradio-based GUI, allowing users to easily test and visualize predictions. This project highlights the use of traditional ML algorithms in image classification and the power of user-friendly interfaces for model interaction.

Hand Gesture Recognition is a machine learning project that employs a Convolutional Neural Network (CNN) to accurately identify and classify hand gestures from image data. The goal is to enable intuitive human-computer interaction through gesture-based control systems. This project demonstrates the effectiveness of deep learning in visual recognition tasks and explores its potential in enhancing accessibility and interactive applications.