Hi there 👋

I am Kishore S, pursuing MTech in Data Science and Machine Learning.

• 👯 I’m looking for internships
• 💬 Ask me about Python, Machine Learning, Deep Learning
• 📫 How to reach me: kishoresshankar@gmail.com

These are some of the projects I've completed for academic purposes, self-learning, and my interest in data science.

Contents

• Open Source Projects

  • Fast Report: Fast Report is my first contribution to an open source project. With the help of this package, the performance of various algorithms such as Random Forest, Xgboost, Logistic Regression, and others on any data can be obtained with a single line of code. The Sklearn library is used extensively in the development of the package. The package can be downloaded from here

• Machine Learning Projects

  • Mobile Price Range Prediction: Based on configuration of mobile, the price of the mobile varies. To understand how certain features impact mobile price has been analyzed and the popular machine learning algorithms have been built to predict the price of mobile given certain features.
  • Anime Recommendation System: A study on unsupervised learning techniques, market basket analysis and recommendation systems on 'Anime Database'
  • Seoul Bike Rental prediction using linear regression: Model to precict the number of bikes required for rental.
  • Customer Segmentation: Customers are divided into groups based on their annual income and spending habits.
  • Prediction of Liver Disease: Diagnosis of liver disease using a variety of test samples

• Deep Learning Projects

  • Cars classification using Transfer learning with Deployment: The images belonging to 18 different models of car was collected. Different architecture were used for classification. Transfer learning model(MobileNet) gave the highest accuracy so it has been considered for deployment. Deployment of model has been done using the gradio library.
  • Breast Cancer Classification using ANN:This analysis aims to observe which features are most helpful in predicting malignant or benign cancer and to see general trends that may aid us in model selection and hyper parameter selection. The goal is to classify whether the breast cancer is benign or malignant. To achieve this i have used deep learning methods to fit a function that can predict the discrete class of new input.
  • Malaria Cell Image Detection using CNN: In this case study, we will learn how to detect Malaria using cell images and CNN architectures. With the advancement in Deep Learning architectures, this is fairly easy. Our objective for this case study would be to develop a system which can detect this deadly disease without having to rely entirely on medical tests.
  • Segmentation using UNET on Electron Microscopy Dataset: Semantic segmentation using UNET and the resnet34 architecture, using a model trained with images and their corresponding masks.
  • Object_localization_on_Pet Dataset: Pet face location prediction using the MobileNet transfer learning architecture
  • Object detection using RCNN: Object detection with RCNN using MobileNet architecture trained on imagenet dataset
  • Object Detection using YOLO: Object detection in images using YOLO v3 trained on the COCO dataset
  • Time Series forecasting using RNN: Deep learning techniques are used to forecast retail sales of clothing and accessories.