Projects



  1. E-LEARNING Website


    Aim:

    To Build an E-Learning platform website.

    Details:

    Used HTML, CSS and Java Script.

    Outcomes:

    Created a responsive website that provides various E-Learning courses.

    Link:

    Speech-Emotion-Recognition

  2. Dine-In


    Aim:

    To build a design for the restaurant’s website.

    Details:

    Used Figma functions like frames, plugins, rectangles to create a design

    Outcomes:

    Created a design of the restaurant home page using Figma.

    Link:

    Speech-Emotion-Recognition

  3. Portfolio website


    Aim:

    Building a website to show case accomplishments.

    Details:

    Used the tools HTML, CSS, and Java Script to build my website

    Outcomes:

    A responsive website show casing my career achievements to date.

    Link:

    Ashish Portfolio

  4. Speech Emotion Recognition


    Aim:

    Analysing the emotion of a person.

    Details:

    Used the visualization techniques like waveplot and spectrogram, used data augmentation techniques, and also extracted the features using libROSA library.

    Outcomes:

    Created a pre-trained model with an accuracy of 61 percentage.

    Link:

    Speech-Emotion-Recognition



  5. Time-series-data-analysis


    Aim:

    Analysis of the time series data using different techniques

    Details:

    Used various models like FB-Prophet, ARIMA Model, VAR Model, and SARIMAX Model.

    Outcomes:

    This project has the collection of the various time series techniques put together and helps to choose the best model for the data.

    Link:

    Time-series-data-analysis


  6. Tableau project on air travel data of the San Francisco airport


    Aim:

    Creating an interactive dashboard for analysing data.

    Details:

    Used the tableau public functions to create the dashboard.

    Outcomes:

    This dashboard helps the users to analyse the traffic at the San Francisco airport.

    Link:

    Tableau public


  7. Spam and Ham Mail detection


    Aim:

    Analysing a given mail is spam or ham.

    Details:

    Used NLP to clean the data and applied the multinomial naïve bayes theorem.

    Outcomes:

    Created a model that has scored an accuracy of 96.94 percentage accuracy on the test data.

    Link:

    Spam and Ham Mail detection