I’m thrilled to unveil my latest project: a simple yet efficient site designed for event attendees to seamlessly input their information. Once entered, this data is stored in a database and can be immediately converted into a printable name card, providing instant and on-site utility.

The primary objective behind the creation of this platform was to expedite the process of registration at events, without compromising on accuracy or efficiency. To ensure a smooth experience, the site also incorporates a login page exclusively for administrators, granting them the ability to view all registered participants at a glance.

While the design currently serves as a temporary layout for this utility, I am committed to refining it further and introducing additional features to make it an even more invaluable on-site tool.

For those intrigued by the technicalities, this site stands on the foundation of a client-server architecture. I leveraged the power of Nextjs for the frontend, while the backend was meticulously crafted using Expressjs. Data storage was managed through Mongoose, which offers an elegant way to work with MongoDB and Node.js.

If you’re an event organizer or simply a tech enthusiast, do give EventGo a visit!

Looking forward to more opportunities to create, innovate, and enhance in the future.

Introduction

The Event Posting and Management Platform is an innovative startup project designed to revolutionize the way individuals and organizations plan and manage events. From selecting venues to hiring temporary staff, selling tickets, and coordinating with suppliers, this platform offers a comprehensive solution for all event-related needs.

Website: https://evtgo.com/

Note: UI/UX is done by contractors, but prototyping and coding are done by me.

(Above Prototype is designed by me)

(Detailed design by third party)

Features

Event Planning Tools

• Venue Selection: Browse and rent the perfect place for your event.
• Supplier Coordination: Find and collaborate with suppliers for catering, decorations, and more.
• Equipment Rental: Rent necessary equipment such as sound systems, lighting, and furniture.
• Staffing Solutions: Hire temporary staff for event support.
• Ticketing System: Manage ticket sales and distribution seamlessly.
• Collaborative Planning: Share and coordinate plans with team members or clients.

Technology Stack

Backend

• ExpressJS and REST API: Powering the server-side logic and providing a robust API for client interaction.
• Mongoose and MongoDB: Serving as the primary database for storing event details, user information, and more.
• Redis: Utilized as a caching solution for frequently requested content, enhancing performance.
• InfluxDB: Used as data logging micro service, trade off little accuracy to eliminate blocking and complex batching

User Management

• Cognito: Managing user authentication, authorization, and profile handling. (Removed in later version)
• Decoupled DB: For User Store and other regional data for best performance while maintain user data consistency

Hosting and Deployment

• EC2: Hosting the application on Amazon’s Elastic Compute Cloud (EC2) for scalable and reliable performance.
• S3: Leveraging Amazon S3 as an economical Content Delivery Network (CDN) solution.
• Docker: Implementing containerization for consistent development, testing, and deployment through CI/CD pipelines.
• Lambda: Utilizing AWS Lambda for serverless computing, enabling efficient scaling and cost optimization.

Future Expectation

The app is expected to use the user generated data to train AI and perform Interest based recommendation on events and ads, and provide events planning AI for faster planning and suitable options and solutions.

Conclusion

The Event Posting and Management Platform is a comprehensive solution that simplifies the complex process of event planning. By integrating cutting-edge technologies and providing user-friendly tools, it offers a one-stop solution for event organizers, suppliers, and attendees. Explore the platform and transform the way you plan and execute events.

Title: CNN Thunderdome Showdown: Benchmarking YOLOv7, VGG-16, and GoogleNet for Recyclables Image Classification Accuracy

Date: April 8, 2023
Authors: Tom Sun, Dexuan Ren, Deepta Adhikary
University: York University

Abstract

The study focuses on image classification for recyclable sorting and classification. Three models were tested: YOLOv7, VGG-16, and GoogleNet. GoogleNet was found to be the most effective with an accuracy rate of 94% and faster training speed. The findings can be applied to reduce costs in recycling plants and create garbage collecting mini robots.

Introduction

The project explores the challenges of image classification and how transfer learning using pre-trained models like CNNs can overcome these challenges. The study focuses on recyclables and assumes that recycling plants have techniques to isolate each piece of recyclable and capture images.

Methodology

• Models Used: YOLOv7, VGG-16, and GoogleNet.
• Dataset: Kaggle dataset for recyclables.
• Design & Training Pipeline: Pre-trained VGG-16 and GoogleNet models implemented in PyTorch. YOLOv7 used for object detection. Images processed using RoboFlow platform.
• Model Training Changes for YOLOv7: Background removal and manual relabeling.

Results

• Baseline Accuracy: 70% (average from Kaggle models), Human accuracy at 99%.
• Scores:
  • YOLOv7: 70%
  • VGG-16: 88%
  • GoogleNet: 94%
• Observations: Different models have strengths and weaknesses depending on the specific materials or objects being classified.

Discussion

• Strengths and Limitations: YOLOv7 required significant overhead, while VGG-16 and GoogleNet were easier to train. GoogleNet was concluded as the better model for this task.
• Future Directions: Further testing on various datasets and exploring other areas like facial or shape recognition.
• Peer Evaluation: Feedback received and changes made to improve the report.

Updated YOLO V8 and latest model

The project has been updated to use the latest YOLO V8, which enhances the performance and efficiency of the models. You can find more details about YOLO V8 model here.

Conclusion

The study provides a foundation for automated garbage sorting, potentially reducing costs and human effort in waste management. GoogleNet was identified as the most suitable model for this task, with potential applications in recycling industries and the creation of waste-collecting robots.

Full Report

Tech Stack

MERN
WebSocket

Participation

Software Design and Author of SRS
Implemented Web Socket Related Functions
Part of Pan Test (Static Code Analisys)
Bug fixing and security checklist
Demo Deployment (Over Web with HTTPS)

All Source Code can be found here: Github

Download SRS