AASTMT

Content on this page requires a newer version of Adobe Flash Player.

Get Adobe Flash player

 
 

Graduation Projects

List of graduation projects of the 2nd semester 2018/2019

HTML Table

Project Title Superviros'' Names Country
A Smart Way to Shop for Glasses Based on Deep Learning and Augmented Reality Technologies Nadartak.com Prof. Dr. Osama Badawy Germany
Centro comercial Moctezuma Francisco Chang Mexico
Ernst Handel Roland Mendel Austria
Island Trading Helen Bennett UK
Laughing Bacchus Winecellars Yoshi Tannamuri Canada
Magazzini Alimentari Riuniti Giovanni Rovelli Italy

A Smart Way to Shop for Glasses Based on Deep Learning and Augmented Reality Technologies Nadartak.com

Studies indicate that more than one billion people worldwide need eyeglasses. The statistics indicate that there are a lot of people who already wear glasses. The work is composed of an Augmented Reality service, Machine Learning Service, and a Cloud Based Backend as a Service. This work utilized state-of-art technologies to implement a system that helps users to try on glasses before they purchase, not only that but also they can upload their images and based on the input image, an output of a set of glasses is generated for the user based on the detected face shape. The work resulted in a high accuracy of face shape detection and best performance for dealing with purchasing glasses.

Course Registration System Web Application Course Code

E-learning nowadays is the most used way of learning techniques that led to more people willing to learn on an academic track. We came to the realization that e-learning can help us through our years of college in many different ways and scenarios. Our project is made specifically for our college, computer science department, to help guide students and make their education journey simpler. Course Code is a place where computer science students can find their courses and related materials in one place. Since coronavirus hit in 2020 e-learning was the only way for schools and colleges to continue providing for their students. The COVID-19 pandemic has changed education forever.

A Care App to help Alzheimer patients

Alzheimer is one of the most widely spread diseases among people and it is affecting a huge amount of the population today, specially elders starting from 60 years old, and many people ignore the first stage Alzheimer which lets the case develop faster. The aim of the project is to help Alzheimer patients and their families by making the first stage Alzheimer patient more independent as possible through features we're providing in our application such as, reminders, emergency, tracking, nearby person and cognitive mind games. All of these are to lessen the development of the first stage of Alzheimer.

Auto Maintenance

Auto Maintenance application is an application that solves the problem of customers not being able to reach many maintenance centers through the application. Through the application, you can book an appointment to repair your car or order spare parts from service centers. Furthermore, the customer can request roadside assistance from the center provided to him online or he can ask a mechanic to go to his location and fix his car. Moreover, the customer can request that his car get transported to the maintenance center’s place.

Buddy: A PSYCHOLOGIST-CHATBOT

Recently, the development of chatbots has increased. Although the first chatbot in computational history was presented as a psychotherapist, few virtual agents with this type of function have been built since then. In Our project we built a therapist chatbot embedded in an application that gives a full experience that helps any user that has any psychological problems or wanting to get into the right mindset. Our project Simulates an Experience connecting an Ai bot with a scripted bot in a hybrid system that aims to give the user a full experience using CBT and some additional features such as having a mood tracker and a gratitude journal.

GeoMarketing: Location-Based Digital Marketing

Geomarketing is a location-based system that uses the geographic information about the location in the process of planning and implementation of marketing activities. This project aims to develop a customer relationship management (CRM) system that uses the aspects of geomarketing in the promotion of products, prices, and places as geo-targeting in market segments. Available commercial and open source geomarketing applications frameworks are evaluated and their main features are identified. Requirements analysis and specifications are carried out to provide a design model. A geodatabase is designed to support the required features. The geodatabase is implemented using Django APIs. The location-based CRM is developed using Geo-Django. The developed system are tested using real customer datasets. The analysis aimed to discover the important characteristics using charts and GIS. The results of analysis showed the effectiveness of the developed system to identify customer segments, locate potential customers, and customer loyalty.

Health Care System

The rise of COVID-19 pandemic has a lasting impact in many countries worldwide since 2020. As for prevention, wearing a face mask is essential. Our project provides a face-mask detection system to avoid mask-less people from entering desired places. This has been achieved by using computer vision and deep learning technologies. Experiments have been done in real-time where the system is able to detect the people who wear or do not wear the face mask accurately even if they are moving. A second part in our project can measure the health status of a person by tracking the temperature and heartbeat using a smart watch. According to the readings, the watch can make a call-in case of emergency to help in reducing the impact of the current pandemic.

Human Computer Interaction System

The project aims to build a Human Computer Interaction system using computer vision and Artificial Intelligence Tools. The idea focuses on that the interaction between a computer and the user should resemble human-to-human. Robots are considered as machines with built-in intelligence. Our robot monitors the motion of the user's arm using a Kinect. The skeletal image of the user’s hand obtained using OpenCV. Coordinate Geometry is used to calculate the angles between the links connecting the joints. The obtained angles are sent using a serial communication port to the Arduino microcontroller, which in turn generates signals to the servo motors. The combined motion of the servos results in a complete Robotic arm movement which is a mimic of the human arm movement. The signals can be sent remotely using client/server communication so you can mentor and guide your robot wherever you are.

I’m Algorithm!

Studies indicate that more than thousands and millions of people want to learn programming, but studies have also proven that many of those who want to flee from learning for many reasons, one of these reasons is the difficult way to deliver, teach, and represent educational content. We are "I'm Algorithm!" We transform all the programming fundamentals, object-oriented programming, data structure, and algorithms into a granular task and then pose a question for the learner to test in the lesson he or she chooses, this is the part of an offline mode, and there's also an online mode that the player can create or join a room to compete with another player to solve programming problems.

Pixel Restoration in Architectural Settings

Image inpainting using deep learning was the passion for us to pick this project. There are many references and papers developing image inpainting but we decided using generative adversarial networks (GANs) and normalized flows. GAN was first developed in 2014. But if we look back to compare the output back then and now. There’s a huge difference. GANs is now involved in many applications in our normal life. In particular, we developed a prototype to predict the missing parts in an image using GAN and normalized flow. The dataset is composed of historical buildings and world heritage made out of 7000 pictures we used to train the neural network.

Octopus 3D Printer

The Aim of this project is to produce 3D printer which give a tangible material to your plan by making layers which is useful for assembling and designing that need a genuine model for testing and planning which will help in many industries. Likewise, the printer will be distantly gotten to by the application we make and for advertising the item. So, whether the customer can buy the whole 3D printer or order just the model which he can customize it him self or browse our already done models. All of this is managed by a mobile application to facilitate the process.

Accessible Text to Speech Support for Individuals with Low Vision or Blindness

The main idea of Read Me application is to implement the suitable optical character recognition (OCR) algorithm for Arabic language, then convert the recognizable Arabic text into speech. The main purpose of read me application is helping visually impaired and blind people with reading Arabic hard copy documents. Implementation of OCR: for preprocessing of the image, we used EAST model for text detection and OpenCV for enhancement, For OCR we used tesseract. Implementation of TTS: google text to speech is used. The project code is composed of three tiers, Front-end is written using Flutter framework, Server code is written using Flask web framework, and finally the database is NoSQL DB using MongoDB.