Object Detection using Amazon Web Services(AWS) SageMaker

This is an ongoing project for object detection using the Oxford-IIT Pet Dataset. The goal of this project is to train an object detection model using the AWS cloud. Key AWS concepts such as AWS notebook instances, AWS SageMaker and AWS S3 buckets are explored during this project. Performed Tasks: Gathered and extracted the data from XML files Extracted the annotations from the XML data Setup AWS SageMaker with Resnet-50 base network Created an S3 bucket to store the data and results Uploaded the data to the S3 bucket Trained the model using AWS SageMaker train instance ‘ml.

October 30, 2020

Semi-supervised Fault Detection using Convolutional Clustering

Performed exploration and feature engineering on Tennessee Eastman Process data Trained a convolutional autoencoder with K-Means clustering algorithm incorporated with the network criterion Extracted the encoder to train a new model in a semi-supervised manner Developed different algorithms for binary and multi-class classification Tuned the hyperparameters and visualized the results using Tensorboard

August 5, 2020

Twitter Sentiment Analysis

Explored tweets to find out the characteristics and patterns. Explored the positive and negative tweets by using Wordcloud to visualize the most frequent used words Performed data cleaning to remove repeating words and twitter user tags Performed Count Vectorization or Tokenization to convert the text data into numbers Trained a Naive-Bayes Classifier to classify positive and negative tweets GitHub Repository