Home

EasyWay! - Pace University Capstone Project

Project Description

View Project Description as PDF | Download Project Description as Word Document

Project Overview

The "EasyWay" web application is a comprehensive platform designed to aggregate various utility services, including beauty, electrical maintenance, home cleaning, pest control, and more. The primary objective of the application is to provide a convenient and hassle-free experience to the end-user, enabling them to book services, pay for them, and give feedback, all in one place.

Key Features

The key features of the EasyWay web application include:

Easy service selection: The end-user can select their preferred service from a list of available options. Convenient appointment booking: The application facilitates easy calendar and time slot booking, allowing the user to schedule services at a convenient time.
Seamless payment process: The end-user can pay for their services securely and conveniently.
Feedback mechanism: The application enables the end-user to give feedback on the services they have availed, thus ensuring quality control.
One-stop-shop: The application serves as a one-stop-shop, catering to all the utility needs of the end-user.

Team Members

Kshitij Sharma Machine Learning Engineer & Software Developer kshitij.sharma@pace.edu	Aditya Kadarla Scrum Master/Project Manager ak42336n@pace.edu	Vidisha Vijay Sawant Software Developer & Cloud Engineer vs10015n@pace.edu
Femina Maheshbhai Baldha Frontend Developer/Designer fb59536n@pace.edu	Shubham Pravin Sawant Machine Learning Engineer & Software Developer ss97349n@pace.edu	Ravi Kumar Dabbada Database Administrator rd83159n@pace.edu

Project Design

Architecture Overview

The EasyWay web application is built using a client-server architecture, with the front-end implemented in Angular JS, the backend in Node JS, and the server in GOLang. The database system used is MySQL.

Front-End Design

The front-end of the EasyWay web application is designed using Angular JS, a popular framework for building single-page applications. The front-end design includes the following components:

- Front-End Continuous Integration

User Interface: The user interface is designed to be intuitive and user-friendly, with clear and concise layouts and color schemes.
Navigation: The navigation system is designed to provide easy access to all the features of the application, with clearly labeled menus and icons.
Forms and Input Fields: The forms and input fields are designed to be easy to use, with clear instructions and error messages. Interactive Elements: The interactive elements, such as buttons and links, are designed to provide a responsive and smooth user experience.

Back-End Design

The back-end of the EasyWay web application is designed using GoLang, a popular framework for building scalable and performant applications. The back-end design includes the following components:

- Back-End Continuous Integration

RESTful API: The back-end provides a RESTful API for the front-end to communicate with the server.
Database Access: The back-end interacts with the MySQL database system to store and retrieve data.
Server: The server component of the back-end is implemented in GOLang, a high-performance programming language designed for building scalable and efficient applications.

Object Detection using Deep Learning

The EasyWay web application has the ability to detect objects in images submitted by users using a state-of-the-art deep learning algorithm for object detection.

- Algo Continuous Integration

How Object Detection using Deep Learning Works

Object detection using deep learning typically involves a convolutional neural network (CNN) trained on a large labeled dataset. During training, the network learns to identify object features such as edges and corners.

Once trained, the network can be used to detect objects in new images by predicting bounding boxes and class probabilities for each object. Anchor boxes can be used to increase efficiency by defining boxes of different sizes and shapes.

Implementation in EasyWay

EasyWay uses a neural network framework optimized for GPU computing to implement object detection using deep learning. The model is trained on a custom dataset of images relevant to the application's utility services and fine-tuned using transfer learning on a large-scale dataset of common objects.

Benefits of Object Detection using Deep Learning

Object detection using deep learning offers several benefits for the EasyWay web application, including:

Real-time performance: The algorithm is designed for real-time object detection, making it well-suited for the real-time nature of the EasyWay application.
High accuracy: Object detection using deep learning is one of the most accurate object detection algorithms available, with state-of-the-art performance on common object detection benchmarks.
Easy to use: The algorithm is easy to use and integrate into the EasyWay application, thanks to its well-documented implementation in the neural network framework.
Customizability: The algorithm can be easily fine-tuned on custom datasets to improve its accuracy on specific types of objects.

Deployment

The EasyWay web application is deployed on a cloud platform named Amazon Web Services (AWS). The front-end and back-end components can be deployed separately to ensure scalability and reliability.

Deployment Status - Front-End Continuous Deployment

Languages and Tools

AWS Atom Angular Cucumber Cypress Electron Figma FileZilla Flask GitHub git Jira Jupyter Linux Matlab MySQL NodeJS NumPy OpenCV PyCharm Postman Python Slack Tensorflow TypeScript VSCode Yarn