Affective Computing

The growing field of Affective Computing (AC) aspires to enhance human’s self-awareness of his or her affective state and to build systems that adapt and respond to this affective state. To realize such systems, there is a need to detect affective state, track its changes and to respond to this detected affect with all its constituent components: mood, emotions and cognitive state. We are establishing an affective computing lab. The proposed thesis topics aim to pave the way for the various fields needed for this lab. We will implement affective applications, utilize sensors and other means to determine the affective state of the user, set up an AR and VR platform with applications as well as look into visualizing the affective data. Link for overview slides:

  • Related Bachelor Projects:
    • Mood-dependent Applications
    • Virtual Reality
    • Augmented Reality
    • Bio Sensors
    • Indirect Lifelogging
    • Visualization
    • Sensorless Emotions

Agroweather Station

An agroweather station is a constellation of weather sensors employed in a farm to monitor weather phenomena and issue warnings in case weather conditions are sympathetic to the spread of plant diseases. The relation between weather phenomena and different plant diseases is governed by a "disease model" which is provided by acrigulture scholars.

  • Related Bachelor Projects:
    • Software Component of an Agroweather Station

Applied Data Analytics

Data analytics emerged as a response to the large volumes of data collected and stored in today’s systems. In this set of projects, you are invited to work on real life datasets. You will use analytics or machine learning algorithms to analyse these datasets and uncover its intrinsic patterns and conclusions. Throughout the process, you will use various frameworks and libraries and learn about the dataset’s application domain.

  • Related Bachelor Projects:
    • Analysis of Amazon’s copurchasing network & other datasets
    • Machine learning algorithms for mining streams of big data
    • Highly scalable recommender systems: incremental algorithms
    • Applications of deep and recurrent neural networks
    • Machine learning algorithms for financial analytics

Bio-image Informatics

Imaging has become an essential component in many fields of bio-medical research and clinical practice. Biologists study cells and generate 3D microscopy data sets, virologists generate 3D reconstructions of viruses from micrographs, radiologists identify and quantify tumors from MRI and CT scans, and neuroscientists detect regional metabolic brain activity from PET and functional MRI scans. Analysis of these diverse types of images requires sophisticated algorithms and tools. To support scientific research in the field of bio-medical we aim to develop image processing-based solutions that are accurate reliable and efficient.

  • Related Bachelor Projects:
    • Medical Image Processing
    • Microscopic imaging

CHEOPS: Cultural Heritage Enhancement over CPS

Cultural heritage in Egypt is largely an untapped resource. It is desirable to attract people from all age groups and cultures to utilize this resource. Technology can play a big role is enhancing the experience of visiting a museum or an ancient site. For example, technology can provide real-time information to visitors as they move around the sites. Technology can also provide attractive and interactive methods to enhance the experience of the visit. This is especially important for attracting younger generations. One of the main technologies that we will focus on in this cluster is augmented reality, which provides means to interact with the site without having to look away from the site itself. We will study how augmented reality can be combined with other technologies to provide an attractive overall experience in cultural heritage sites.

  • Related Bachelor Projects:
    • Localization in Cultural Heritage Sites: Using CV
    • Localization in Cultural Heritage Sites: Using Wireless Devices
    • Integrating Animations over Augmented Reality: Indoors
    • Integrating Animations over Augmented Reality: Outdoors
    • Detecting the Mood of the Visitors
    • Determining Interest using Feature Detection
    • Resurrecting the Pharaohs

DeepMind: Deep Reinforcement Learning

Reinforcement learning is one class of machine learning algorithms where an agent learns a winning strategy to complete a mission; such as avoiding obstacles to reach a goal or maximizing the score in an arcade-style game. When combined with deep neural networks, some reinforcement learning algorithms are able to achieve near-human performance on challenging tasks. AlphaGo is such algorithm that combines reinforcement and deep learning, managing to beat the European champion in the game Go in October 2015 . DeepMind was the startup behind AlphaGo and other similar algorithms, and is now part of Google.

In this group of projects, you are invited to use state of the art frameworks, such as Theano and TensorFlow , to develop deep reinforcement learning algorithms. You can test the performance of your algorithm using the recently released OpenAI Gym. OpenAI Gym provides an implementation of many games such as Go9x9 and DoomPredict within a wrapper that allows your algorithm to play the game and track its progress. You can easily port a game of your choice to the OpenAI Gym and develop the algorithm to win it.

  • Related Bachelor Projects:
    • DeepMind-like: Go 9x9
    • DeepMind-like: DoomPredict
    • DeepMind-like: a game of your choice 1
    • DeepMind-Like: a game of your choice 2

Electroencephalography (EEG)

This thesis topic focuses on the different usages of EEG (brain) recording.

  • Related Bachelor Projects:
    • EEG and IQ

Embedded Systems

An Embedded system is any electronic system that uses a computer chip, but that is not a general-purpose workstation, desktop or laptop computer. Such systems use microcontrollers (MCUs) or microprocessors (MPUs), or they may use custom-designed chips. Deployed by the billions each year in thousands applications, the embedded systems market uses the lion's share of all the electronic components in the world. Embedded systems are employed in automobiles, planes, trains, space vehicles, machine tools, cameras, consumer electronics, office appliances, network appliances, video games, cellphones, GPS navigation as well as robots and toys. Low-cost consumer products can use microcontroller chips that cost less than a dollar.

  • Related Bachelor Projects:
    • Smart Free Pen
    • An Audio card shield for Arduino
    • PC-Based Oscilloscope and Logic Analyzer
    • Sensor fusion for position tracking

Enhancing Lab Exprience

Students performing a lab experiment or design activity often have limited time to perform free exploration of the topic at hand. The aim of this research topic is to utilize augmented and tangible interaction to enhance the student learning experience.

  • Related Bachelor Projects:
    • Enhancing Physics Lab Experience
    • Enhancing Chemistry Lab Experience
    • Enhancing Electronics Lab Experience

Gamifying Physiotherapy

Children can suffer from impaired motor skills due to cerebral palsy or injuries. For these children, restoring motor skills requires lengthy and sometime painful physiotherapy sessions extending over years. Gamification of physiotherapy and rehabilitation is a research and product direction that is gaining the interest of game designers and medical researchers alike. Gamification has the potential of transforming what is now a traumatic experience of many children to an enjoyable and fruitful part of the child’s daily life. The game aspect serves multiple purposes: from providing motivation to distracting the patient from pain as he performs the required exercises.

The purpose of this set of projects is starting an open source , free for all, gamified hand and arm physiotherapy programs. In each of the projects below, you will develop a game that requires the patient to move his hand or arm to complete a series of game missions and milestones. These movements will be part of the medically-devised physiotherapy program. Your game will monitor the patient’s movement via Kinect or Android watch. Your game will aim to lead the patient through completing the physiotherapy program via providing motivation and distraction from pain when needed.

  • Related Bachelor Projects:
    • A Kinect game with a focus on patient motivation
    • A Kinect-based game with a focus on pain management
    • A multiplayer Kinect game for collaboration during physiotherapy
    • An Android-wearable and mobile game for adolescent patients
    • An Android-wearable game with focus on treatment consistency

Gesture-based Interaction

Gesture-based interaction is an area within HCI aiming to create more natural and intuitive interfaces using the hands and fingers.

  • Related Bachelor Projects:
    • Gestures for Desktop Systems
    • Gestures for Large Displays
    • Using Machine Learning in Understanding Gestures

Graphics and Visualization

While computer graphics is the field that is concerned with using utilizing input description to produce artificial digital images, visualization is the visual representations of abstract data. We will work on different graphics and visualization tools.

Human Language Technology (HLT)

The goal of Human Language Technology (HLT) field is to allow computers to perform useful tasks by processing human natural language. Human language is used in everyday communications in the forms of text and/or speech. Technologies based on that field are becoming increasingly widespread. For example, smart phones and tablets support predictive text, speech recognition and handwriting recognition; web search engines give access to information locked up in unstructured text; machine translation allows us to retrieve texts written in any source language and read them in a completely different language; text analysis enables us to detect sentiment in social media.

  • Related Bachelor Projects:
    • Author identification based on his writing style
    • Automatic Keyword tagging for English text
    • Automatic Diacritization System for Arabic Text
    • Arabic Named Entity Recognition (NER) System
    • Sentiment Analysis for Movie Reviews
    • Arabic Sentiment Analysis system
    • Arabic Dialect Classification for Social networks
    • Text category classification for Arabic articles
    • Automatic Proofreading System for Arabic
    • Automatic Text Summarization for Arabic
    • Text Predictive System for Arabic
    • Classifying Movie Scripts By Genre
    • Word-Embedding for Arabic using the word2vec toolkit
    • Text Classification based on Quality of Writing
    • Word Sense Disambiguation System
    • Part of Speech tagger for Arabic

Integrating Rule-Based Learning with Rule-Based Deduction

Typical learning systems are just that--learning systems; likewise, typical deductive system are only deductive systems with no capacity for learning. It would be interesting and instructive to have a system with a natural capacity for both learning and deduction.

  • Related Bachelor Projects:
    • Inductive SNePS

Interaction Design and Formal Evaluation

This topic aims to investigate new interaction techniques, whether it being a new menu design, a new gesture, or a completely unconventional way to interact with a cell phone or desktop interface.

  • Related Bachelor Projects:
    • Experiment: Desktop for ADHD
    • Using Kinect
    • Tangible Interaction

Java SNePS v. 2.0

SNePS is one of the oldest, yet developing, systems for knoweldge representation and reasoning in AI. Akin to a programming language, SNePS is a flexible system for building and manipulating propositional semantic networks. A propositional semantic network is a labelled directed graph were nodes represent entities (possibly propositions) and arcs represent structural relations among them. The basic SNePS system is a network managing system concerned with building and finding nodes. On top of that, there are several sub-systems for reasoning, acting, belief-revision, and natural language understanding and generation. The official version of SNePS is implemented in Common Lisp. Over the past four years, we have implemented a local Java version. We are now ready to launch version 2.0 of Java SNePS. In the course of developing Java SNePS v. 2.0, we shall take extra care of implementation efficiency and proper software engineering practices.

  • Related Bachelor Projects:
    • SNeRE
    • SNeBR
    • SNePS Networks

Massively Scalable Apps

Social web apps (e.g. facebook, twitter, etc...) have pushed the boundaries when it comes to performance requirements. The need to support hundreds of millions of registered users, millions of logged-in users, and tera bytes of media uploaded and downloaded, all led to the creation of a new breed of software: massively scalable apps. Projects in this category will focus on the architecture, design and tools used to create such apps.

  • Related Bachelor Projects:
    • Twitter Replica - front end mobile
    • Twitter Replica - backend
    • eCurrency/Bitcoin
    • Family Focus

Multimedia Analytics

Day to day vastly more media data are produced. It is became a part of everyday culture. Many people capture and edit visual and other multimedia data using simple devices. They share it through social networks, which have become the new leading tool mass communication. Multimedia data content are not yet automatically discovered. Most of tools for multimedia indexing and retrieval rely on metadata generated automatically at media production time or randomly by the users. In this seminar we aim to address this problem by studying recent contribution in content-based indexing and retrieval, automatic or interactive multimedia data annotation, large-scale image analysis, video semantic search engines, video synopsis, etc…

  • Related Bachelor Projects:
    • Video Surveillance
    • Large Scale Image/Data Processing

Nonmonotonic Reasoning

Nonmonotonic reasoning is a hallmark of human rational behavior. New models of nonmonotonic reasoning are always worth exploring and investigating.

  • Related Bachelor Projects:
    • Nonmonotonic Reasoning as Reasoning about Graded Propositions

Non-traditional Imaging

This area is concerned with emerging applications of non-traditional imaging technologies and the related challenges and limitations. These types of non-traditional imaging technologies includes multispectral, hyperspectral, Near-Infrared, Shortwave IR and Mediumwave IR Imaging.

  • Related Bachelor Projects:
    • Challenges of Focus Estimation in MWIR Images
    • Automated Visual Inspection of Electrical Systems
    • Comparative Study of Focus Measures in NIR Images
    • Denoising of MWIR Images using Wavelet Shrinkage
    • Detecting VP Panels Anomalies using Imageries
    • Monitoring Injection Molding Process using MWIR Images
    • Studying The Effect of Photon Shot Noise..

Optimization of hybrid power networks

Hybrid power networks are becoming the norm. Instead of relying on one source of energy to generate power, today’s hybrid power networks integrate green energy sources such as solar and wind energy. The variable nature of green power sources adds a new challenge to the problem of optimizing and stabilizing power networks.

Power consumption has always been variable, at times following predictable patterns; such as the increased power consumption between 6 and 7 am on school days. Power consumption also sees surges occurring at less predictable patterns; for example, power consumption increases during heat waves due to use of air conditioners. Green energy sources make power production also variable; as power production now depend on weather changes.

The problem of optimizing and stabilizing hybrid power networks is a problem faced by power engineers, however, the algorithms to solve it are classical computer science algorithms.

  • Related Bachelor Projects:
    • Simulating and optimizing the national hybrid power network