shhubhxm Goto Github PK

ai-speech-emotion-recognition-with-librosa

Speech Emotion Recognition, abbreviated as SER, is the act of attempting to recognize human emotion and affective states from speech. This is capitalizing on the fact that voice often reflects underlying emotion through tone and pitch. This is also the phenomenon that animals like dogs and horses employ to be able to understand human emotion.

batteryrulpredictor

productionalization on Django.

big-data---hadoop---yelp-dataset

The folder contains 5 problems & pdf contains description of five problems and Yelp dataset

ct_diagnostic

data-science-global-terrorism

Data Science project with data eda and model building.

data-science-salary-prediction

The data science salary prediction, cleaning, model building and eda.

dodo-price-advantage-tweet-alert

The project who rates a bot that tracks DODO price advantage and tweets about it in real-time.

fly-buy

This is a Clone of Amazon built with React, Firebase, and Stripe payment API.

gateapi-python

gatews

Gate Websocket V4 SDK

github-bot

A framework for building GitHub Apps to automate and improve workflow.

grimo-bughunter

A Bug management project for Bug Hunter. Bug Hunter easily Manage Bug & track Bug.

hack4humanity

handwritten-digit-recognition

Handwritten Digit Recognition on MNIST dataset

host

housepriceprediction-ml_model

Using UCI boston dataset created a model and looking for promising attributes, finding out correlations, plotting graphs, creating a pipeline, dealing with missing values and saving the model using joblib.

housepriceprediction_website

House Price Prediction using Django and Heroku to host. The Web App uses the UCI Boston dataset as inputs and predicts the output using RandomForestRegressor.

jp-morgan-internship

Worked on Stock Price Data, Data Visualisation, and created a Traders Dashboard during my virtual software internship at JP-Morgan.

leetcode_neetcode

Leetcode solutions

mri_classification_app

This sample application demonstrates how a Custom Vision Service exported TensorFlow model is added to a real-time image classification application.

pixel-portfolio-webite

A Nintendo inspired lightweight, No BS responsive single-page portfolio website built with HTML and CSS :space_invader:

prostate_segmentation

NCI-ISBI 2013 Challenge - Automated Segmentation of Prostate Structures

python-engineer-notebooks

resume

rulmodeltraining

Model building and predicting the Remaining Useful Life(RUL) using SVM(Support Vector Machine), XGBoost, RVM(Relevance Vector Machine).

salary-priceprediction_website

Built a client-facing API using Django with Random Forest Regressor model calculates the predicted salary of a data scientist/engineer.

scheduling_gui

This is a small college project regarding the visualization of the scheduling algorithms with GUI input and output. It is also have visualization in graph. All are welcome to do UI changes , add animation, grant chart and add more algorithms and visualization like page scheduling, disk scheduling, etc.

shhubhxm

Shubham Vyas' Github readme.

shubham.software

For this project, I registered a domain through name.com and set up a Linux Ubuntu instance on Amazon EC2 with Apache, MySQL, and PHP. The domain was pointed to EC2 VM. I created an "about me" homepage with HTML5 and a video, figure, background image, and navigation. I secured the site with HTTPS using a manual certification from Cloudflare.

skin-disease-detection-team-technophile

We are team technophiles and participated in 48hrs hackathon organized by Nirma University in collabration with Binghamton University. Our Problem Definition : To develop a solution, the first step is to understand the problem. The problem here is to develop an Application Programming Interface which can be easily integrated with Android and IOS to detect the skin disease without any physical interaction with a Dermatologist. The detected skin disease should be sent through whatsapp to a particular patient and doctor. Our college name: Pandit Deendayal Energy University Team Members: Rushabh Thakkar, Divy Patel, Denish Kalariya, Yug Thakkar, and Shubham Vyas. Project Details: We made an application which classifies the skin diseases into these given types healthy, lupus, ringworm and scalp_infections How did we make? The data given was analysed first. We came to conclusion that the data given was not enough so we searched for new datasets. We got these datasets: https://ieee-dataport.org/documents/image-dataset-various-skin-conditions-and-rashes https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/DBW86T We segregated the datasets of harvard. Combined all the datasets and trained the tensorflow image classification model multiple times. Accuracy was not satisfying. Augmented the data to unbaised the model and the dataset would be balanced. Data Augmentation was done on the data given . We generated 800 images per disease. Again we had trained the model. Accuracy was good. Exported the .tflite and label.txt file. We imported the files into android studio We have used three python codes: data_removal.py This code is used to remove data randomly from the folder if there are more number of images than required. We just need to change total_files_req variable in the code to number of files required after deletion. data_augmentation.py This code is used to augment the data randomly from the folder if there are less number of images than required. We just need to change total_files_req variable in the code to number of files required after augmentation. We change various parameters of images like clearity, rotation, brightness, etc. image_classification_code.py This is the main code in which we have trained the model and exported it to run on the app Models we tried: efficientnet-lite0(USED in our project) efficientnet-lite1 efficientnet-lite2 efficientnet-lite3 efficientnet-lite4 API: TensorFlowLite Used Android studio for App development . Used Language = java We sync all the grade files. Changed the model files and update it with the new model Working model file name is model.tflite Tflite classifier working java files are CameraActivity.java CamerConnectionFragment.java ClasssifierActivity.java LegacyCameraConnectionFreagment.java Dataset: Uploaded on Github WORKING MODEL LINK: https://drive.google.com/file/d/1BnqfFInFkJJDkYDlmdj9VB601f7PjTdj/view?usp=sharing