-
Pepper Disease Classification - Using Convolutional Neural Networks for the bacterial disease classification in bell pepper images with 100% accuracy on test dataset.
Skills demonstrated: Python, Tensorflow, Jupyter Notebook, CNN, Deep Learning -
Rice Image Classification - Using Convolutional Neural Network for the classification of rice images into five categories with 98% accuracy on test dataset.
Skills demonstrated: Python, Tensorflow, Jupyter Notebook, Data Visualization, Deep Learning -
House Price Prediction using Deep Neural Network - Using Deep Neural Network for the prediction of house prices. The predicted values are so close to the actual values that a client can totally rely on them.
Skills demonstrated: Python, Tensorflow, Keras, Deep Neural Networks, Jupyter Notebook, Data Visualization -
Missing Values Imputation using Deep Neural Network - Using Deep Neural Network for the prediction of missing values in dataset provided by Jeff Heaton (Instructor of Applications of Deep Neural Networks at Washington University).
Skills demonstrated: Python, Data Preprocessing, Tensorflow, Keras, Deep Neural Networks, Jupyter Notebook
- Driver Alertness Detection - Using multiple classification algorithms to identify the best one and predict driver alertness using the best model. Random Forest Classifier yields the best accuracy of 99% on validation data.
Skills demonstrated: Python, Pandas, Scikit-learn, Jupyter Notebook, Data Preprocessing, Machine Learning, Model Validation and Testing
- World Happiness Report 2022 - EDA of World Happiness Report 2022 identifying factors that make people in a country happy.
Skills demonstrated: Python, Matplotlib, Seaborn, Jupyter Notebook, Storytelling