Digital Solutions Engineer @ SwissRe | Automating data mining at scale

github

projects

youtube

Prateek Ralhan  • Peerlist

The project mainly deals with analysing and testing different datasets and algorithms like Gradient Descent, Linear Regression, Logistic Regression etc. and use these "tools" and find a model that gives us the best generalization. From this

Predicting Boston Housing Prices using ML Techniques

In this project,I build a model to identify dog breeds in an image.

We will use the Kaggle's Dog Breed Dataset dataset for training. With 120 breeds of dogs and a limited number training images per class, you might find the problem more, e

Dog breed Classification using Tensorflow

Multiple object tracking mechanism achieved using centroid tracking algorithm and openCV4.0.
An ideal object tracking algorithm will only require the object detection phase once (i.e., when the object is initially detected),will be extremel

Multiple Object Tracking using Centroid Tracking Algorithm and openCV4.0

In this project, I analyzed a dataset on No Show Appointments By Kaggle for May 2016, and then communicated my findings about it. I used the Python libraries NumPy, pandas, and Matplotlib to make the analysis easier. I have successfully run

Investigation of Datasets using Inferential statistics

This is an implementation of the famous game Flappy bird using Reinforcement Learning using tensorflow and Pytorch.

This sample is published as part of the corresponding blog article at https://www.toptal.com/deep-learning/pytorch-reinforc

Implementation of Flappy-Bird using Reinforcement Learning

This project deals with using dlib for extracting facial landmarks from live webcam feed of the user, and using opencv to detect distance between the lips and classify it as a yawn and inform as an alert when the subject is yawning.

Refer 

Yawn Detector using facial landmark extraction using dlib and openCV

It mainly deals with the analysis and import of US bike share data and answer interesting questions about it by computing descriptive statistics. We explore data related to bike share systems for three major cities in the United States—Chic

US BIke sharing Data Analysis using Descriptive Statistics

This project named as the COMIC STRIP LIVE RESERVATION SYSTEM mainly aims at creating online booking for shows, concerts and evenings happening in the city, managing the bookings, ticket cancellation, seat allocation etc. as well as allowin

Comic Strip Live Reservation system

his project would focus on mapping high dimensional data to a lower dimensional space, a necessary step for projects that utilize data compression or data visualizations. As the ethical discussions surrounding AI continue to grow, scientist

Data compression and Visualization using principle Component Analysis (PCA) in Python

Measuring the size of objects in an image using Pixel per Metric ratio and openCV4.0 with imutils.

Measuring the size of objects in an image is similar to computing the distance from our camera to an object — in both cases, we need to defi

Object Size measurement in an image using openCV4.0 and imutils

This project mainly deals with using K-means algorithm for image classification using Scikit-learn.Here, we first preprocess the images for clustering and deploy the k-means clustering algorithm. Then we use common metrics to evaluate the c

K-Means Clustering for Image classification

The Project basically in volves a hybrid model design that can be used as a survillence bot as well as a self sriving autonomous vehicle, powered by a convolutional neural network, doing explicit image processing and the car's hardware comp

Self Driving Autonomous Vehicle with survillence support system

This python script deals woth creating and working with an image classifier between Nike and Adidas Shoes. It has been made using PIL i.e. Python imaging library instead of openCV and also using the Tensorflow deep learning library, i.e. tf

Image Classification between Nike and Adidas Shoes using PIL and tflearn

Language identification is one of the most common feature of every Social Network or Web application, this is commonly paired with Machine Translation to improve the user experience and content accesibility(a must have in the 2.0 society). 

Language Identification using tensorflow and keras

A document scanner made using openCV4.0 and imutils in python 3.5.1


Document-scanner using openCV 4.0

This python script mainly deals with generating Eminem lyrics, which is achieved using an LSTM (Long Short Term Memory) network, a fairly simple extension of neural networks brought out to overcome the drawbacks of the recurrent neural netw

Generating Eminem Lyrics using an LSTM Network

This project mainly deals with the analysis of the ALL-Covnets that were designed in 2015, that is mainly for achieving state-of-the-Art performance for object recognition. Here, I have done some manipulations and validations on the network

Analysis of ALL-Covnets for Object Recognition using CIFAR10 Dataset

A Digit recognizer made using OpenCV4.0 and imutils with Four-Point Perspective Transform

Digit Recognizer using openCV4.0 and imutils with Four point Transform

This mainly talks about an android app made using android Studio, that basically predicts the handwritten-digits, taken from the very popular MNIST Dataset.The Model has been made and trained using Tensorflow in Python and mainly comprises 

Developing an Android App with Image Detection Support using Complex MNIST

Sentiment analysis is one of the most common NLP problems. The goal is to analyze a text and predict whether the underlying sentiment is positive, negative or neutral. In thisproject, we will build a Convolutional Neural Network (CNN) class