ChiragSoni's repositories
Autograder
:trophy: Automatically grade english essays using NLP techniques (This is not a ML model).
FuzzyJess
Loan Application Expert system is a rule based expert system designed using FUZZY JESS wherein information of a loan applicant is asserted by the user of the Bank, and finally concludes whether applicant is eligible to apply for a loan or not. System also provides suggestions to the user of the system to help him/her to make a decision in a very convenient manner. The expert system checks for all the boolean and Fuzzy parameters asserted by the user and finally claims the decision depending upon its interpretation and a few important rules set in the bank’s policy.
ChiragSoni95.github.io
A website to display my work, interests and my web development skills. My Link: https://ChiragSoni95.github.io
CodingInterviews
This repository contains coding interviews that I have encountered in company interviews
Nouveau_Scrum
Project management scrum tool for developers and managers following agile programming methodology
SMARket-SmartMarket
:trophy: System for recognizing and tracking patterns within data so as to not only react but also anticipate the customer needs in advance.
StaticCodeAnalyzer
Determine the common bugs after analyzing pattern of patches for various issue/bug reports
StockEvaluator
Monte Carlo simulator on a Octa Pi cluster using Spark and Kubernetes
Stores_REST_API
A REST API to access items, stores, user authentication.
Deep_Learning
added all materials
ExtremeCluster_ParallelProcessing
Parallel Programming lab assignments and projects using High Performing Clusters called Extreme provided by UIC ACCC powered by Acer Labs.
GeeksforGeeks-python
GeeksforGeeks Algorithms and Questions implemented in Python
IML-Mini-Project-5
You are working for a non-profit that is recruiting student volunteers to help with Alzheimer’s patients. You have been tasked with predicting how suitable a person is for this task by predicting how empathetic he or she is. Using the Young People Survey dataset (https://www.kaggle.com/miroslavsabo/young-people-survey/), predict a person’s “empathy” on a scale from 1 to 5. You can use any of the other attributes in the dataset to make this prediction.
Kitti-road-semantic-segmentation
Implementation of semantic segmentation of FCN structure using kitti road dataset. I used a tensorflow and implemented a segmentation algorithm with a mean-iou score of 0.944.
LOAN-application-expert-system-in-JESS
Loan Application Expert system is a rule based expert system designed using JESS wherein information of a loan applicant is asserted by the user of the Bank, and finally concludes whether applicant is eligible to apply for a loan or not. System also provides suggestions to the user of the system to help him/her to make a decision in a very convenient manner. The expert system checks for all the parameters asserted by the user and finally claims the decision depending upon its interpretation and a few important rules set in the bank’s policy.
Netica-J_Applied_AI
Bayesian Network designed using NETICA wherein information of different type of loan applicants and types of loan is asserted by the user of the Bank, and finally concludes whether applicant will be to repay loan or not.
Netica_Bayesian_Influence
Loan Repayment Decision system is a combination of Bayesian Network and influence Diagram designed using NETICA wherein information of different type of loan applicants and types of loan is asserted by the user of the Bank, and finally concludes whether applicant will be to repay loan or not.Accurately predicting whether a loan will be repaid (credit" scoring) is an important task for any bank.Furthermore, the decision regarding the deadline if it needs to be extended or not is made using the utility and decision node in influence diagram. High accuracy benefits both the banks and the loan applicants.
NeuralNetwork_Keras
First neural network model using the powerful Keras Python library for deep learning.
OfflineVoting-Android-Application
Offline Voting Application
OnlineLearning_Application
Android Online Learning Application
random-java-program-generator
Graduate course project which provides experience in creating a generator that creates a syntactically correct but semantically meaningless Java Program
RSSNewsFeed-Android-Application
RSSNewsFeed Android Application
SIGNS-Digit-Classification
Deep learning neural network model to recognize numbers from 0 to 5 in sign language with a pretty impressive accuracy of 95% on training data and 72% on the test data
Twitter_Sentiment_Analysis
Given a collection of tweets, classify them into four classes namely: positive, negative, neutral and mixed. The tweets used here are pertaining to two US presidential candidates namely: Barack Obama and Mitt Romney. By classifying the tweets into the mentioned classes we would be capable of predicting the opinion of the public and get a sense of the outcome of the election.
Zillow_Kaggle_Competiton-AI-
Implementation of Light Gradient Boosting Method (GBM) with parameter tuning using GridSearchCV