3D Scanning and Point Clouds

Clouds are formed of separate points in the 3D space. The lack of connectivity among these points introduces the problem of displaying them. As the connectivity information is missing, there are no surfaces to display; hence a full 3D model cannot be displayed. Another problem occurs based on the density of the points. In case of having too many points, rendering them all would not be efficient. In a zoom-out perspective, points can overlap or occlude each other. In a zoom-in perspective, many sections can be out of the field of view. Work in this topic is divided as follows

Affective and Character Computing

The rising trend of Adaptive and Seamless Interactive Systems requires having elaborate user profiles to be able to best adapt the application to the user’s behaviour. Instead of focusing on the current state of the user (affect) our interest is to have profiles describing the user’s general state (character). Various models for extracting human personalities and character traits exits. One such model is the Five Factor Model of Personality which represents personality using five traits namely Openness, Conscientiousness, Extraversion, Agreeableness and Neuroticism. Instead of relying on the lengthy self-assessment methods, the interdisciplinary, multimodal, emerging field of Character Computing aims at designing and training predictors and classifiers for some stable, measurable traits. It also aims at modeling certain aspects of character and personality in different ways such as through computer algorithms or game scenarios. Character Computing can then be applied in different use cases (e.g. healthcare, education and entertainment) to help individuals by adapting to their personality. This cluster aims to address these tasks from various aspects. All projects require very strong coding skills and at least initial knowledge and a strong interest Research, Machine Learning and Data Analysis.

  • Related Bachelor Projects:
    • OCEAN-VR: A VR Game for Determining the Big 5 Personality Traits
      Supervised by:
    • ACT-StRoop: Implementing the Stroop Test using ACT-R
      Supervised by:
    • VRacter: Character-based Avatar Preference in Education
      Supervised by:
    • A Ubiquitous Data Collection Game
      Supervised by:

Arabic Bixby

Bixby is Samsung's take on the pocket assistant, combining machine learning, voice assistance, visual help and more into an all-encompassing helper. Bixby is not quite the same as Google Assistant, though, as Bixby is more conversational and apologetic when it messes up. This is a voice-activated virtual assistant that truly aims to please. Bixby does not have Arabic support, which limits its usability in the Arabic region.

  • Related Bachelor Projects:
    • Arabic Bixby for the Visually Impaired
      Supervised by:

Augmented, Virtual, and Mixed Reality

Augmented, virtual, and mixed reality applications all aim to enhance a user’s current experience or reality. In this cluster, we will investigate different applications and show how and where these applications could be of benefit.

  • Related Bachelor Projects:
    • Virtual Reality for Social
      Supervised by:
    • Virtual Reality Environments for the Visually Impaired
      Supervised by:
    • Social VR: Let’s have a chat!
      Supervised by:
    • AR for Tourism
      Supervised by:
    • MR Trainer
      Supervised by:

Autonomous Cars

Autonomous vehicles have held the attention of futurists and technology enthusiasts for some time as evidenced by the continuous research and development in autonomous vehicle technologies over the past two decades. Rapid advances in robotics, artificial intelligence, computer vision, and edge computing capabilities are resulting in machines that can potentially think, see, hear, and move more deftly than humans. Autonomous vehicles in the form of self-driving cars have become the subject of both hype and intense competition among auto majors and technology companies. Self-driving car prototypes that are decked in lidars, radars, cameras, ultrasonic sensors?—?along with heavy computational capabilities under the hood to recognize and maneuver around obstacles?—?is becoming a common sight in many cities. With the emergence of sophisticated autonomous vehicle technologies, we are now on the cusp of their rapid deployment in industrial applications, and the confluence of the Internet of Things (IoT) and AV technologies are poised to re-make and re-imagine industries. Here at the GUC, we started a project to develop a self driving car platform that can drive autonomously around the GUC campus, the topics within this cluster will focus on developing and improving the current developed systems and creating new systems to achieve this goal.

  • Related Bachelor Projects:
    • Object Detection and Avoidance
      Supervised by:
    • Safety System
      Supervised by:
    • Vector Mapping and Path Planning
      Supervised by:
    • Vehicle Dashboard and Information System
      Supervised by:
    • Road Obstacles Detection and Interaction
      Supervised by:

Big Data Analytics

Big data analytics examines large amounts of data to uncover hidden patterns, correlations and other insights. With today’s technology, it’s possible to analyze your data and get answers from it almost immediately – an effort that’s slower and less efficient with more traditional business intelligence solutions. The volume is not the only dimension through which big data analytics would outperform traditional systems, but there is also the heterogeneous data sources that generate endless streaming data from a multitude of systems. Big data platforms, which mainly target distributed data processing, have to cater for ever-growing complex data analysis methods and algorithms, and have to handle large, complex, and streaming data.

  • Related Bachelor Projects:
    • Big Data Platforms for Graph Analytics
      Supervised by:
    • Improving Queries over Streaming Data
      Supervised by:
    • Context-aware Recommender Systems
      Supervised by:
    • MapReduce-based K-Means
      Supervised by:
    • Analysis of Arabic Literature Themes
      Supervised by:
    • Personalized Recommendations of Test Questions
      Supervised by:

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:
    • Mammogram-based Cancer Detection Using Multiresolution Analysis / Random Forest
      Supervised by:
    • Detection and Localization of Spinal Anatomy in CT Images Using Deep Convolutional NN / Random Fores
      Supervised by:
    • Deep Convolutional NN for Lung Nodule Detection and Annotation
      Supervised by:
    • Deep Convolutinal NN for Liver Tumor Segmentation in CT Scans
      Supervised by:
    • Microscopic Imaging: Particles Localization, Counting and Size Recognition
      Supervised by:
    • Microscopic Imaging: Particles Classification and Tracking based on Texture and Morphological Featur
      Supervised by:

Brain-Computer Interface Applications

Brain-computer interface (BCI) systems allow controlling computers and other electronic devices using brainwaves, which is relevant to be applied for users especially with reduced motor abilities. BCIs currently provide new hope for people with disabilities whose brain function is still intact. By recording brain activity, BCIs could translate recorded brain activity to actions that can interact with the external environment.

  • Related Bachelor Projects:
    • A Brain-controlled Android Web Browser
      Supervised by:
    • Emotion Recognition using Brain Activity
      Supervised by:
    • A Brain-controlled On-screen Assistive Keyboard
      Supervised by:
    • A Brain-controlled Robotic Arm
      Supervised by:
    • A Visual-evoked Potential Speller
      Supervised by:
    • A Brain-controlled Wheelchair
      Supervised by:
    • A Brain-Tablet Interface
      Supervised by:

Code-switching

Do you code-switch? In other words, do you use more than one language while talking? Mmkn teb2a betekalem 3araby and then in the middle of the sentence te2leb English? This behaviour has become a common phenomenon among multilingual societies, especially among urban youth. It has become normal for people to code-switch in everyday conversations. This has created a demand on Natural Language Processing (NLP) applications to be able to handle such mixed input. Most of the work done in the field of Arabic Natural Language Processing (NLP) has covered Modern Standard Arabic (MSA). There is still huge room for research in the NLP as well as psycholinguistics fields for code-switched Arabic-English.

  • Related Bachelor Projects:
    • Who Code-switches?
      Supervised by:
    • Building an Arabic-English multilingual ASR system
      Supervised by:
    • Named Entity Recognition on Code-Mixed Data
      Supervised by:

Computational and Data Intensive Sciences

Sciences like Physics, Chemistry, Biology, and even Economy and other sciences are no longer limited to theoretical and experimental. The vast development in complexity, uncertainty, and inability to develop a theory or run experimentation necessitated the need for HPC to practice the science computationally. The enormous flood of data from experimental and computational techniques also mandated the integration of Big Data analytics with the scientific investigations. Projects: In each of the following projects The student will be given reading material to understand the underlying science and will be given code to start the simulation process. The student will work on completing and optimizing the simulation and developing tools to learn and extract the results and conclusions.

Computer Science in healthcare

Technology today affects every single aspect of modern society. In fact, there is not an industry out there that has not been affected by the hi-tech revolution. Technological breakthroughs are revolutionizing the way healthcare is being delivered. Modern technology has changed the structure and organization of the entire medical field. From widespread adoption of electronic medical records, to advances in bio-medical engineering and technology, modern healthcare and its delivery methods are changing at an ever increasing rate. Continuous technological developments in healthcare have saved countless lives and improved the quality of life for even more. Advancements in medical technology have allowed physicians to better diagnose and treat their patients since the beginning of the professional practice of medicine. Today’s healthcare industry uses computers in a much more sophisticated way, and lab scientists are no longer required to analyze the data collected by computers in a research laboratory. These days, patients and doctors can log into Web-based information portals to coordinate treatment plans and schedule appointments. Patients are also increasingly using mobile and wearable devices for many reasons like dosage schedules and monitoring vital information such as heart rate and blood pressure. This cluster aims at developing applications for assisting the health care field in many different ways like chronic care management, medication management, diagnostics, pain management and many more.

  • Related Bachelor Projects:
    • Detecting Social Anxiety though Interactive Large Displays
      Supervised by:
    • ADDjust: Focused Reality for ADHD Students through VR
      Supervised by:
    • Interactive pain management through VR games.
      Supervised by:
    • Smart Mirror for Detection of Mental Illness
      Supervised by:

Democratizing Data Analytics

It has been projected that individuals generate 70 percent of the overall data, but enterprises store 80 percent of this data. Even though digital data created by consumers is doubling every two years, almost all of it remains unused or unanalyzed. Research indicates that 99 percent of new data is never used, analyzed or transformed. Of what use is the data if it is trapped in silos and not analyzed effectively? Democratization of data and analytics is the phenomenon of making data available to people who need it and have the skill sets to deriving meaningful insights from it. By freeing themselves from data silos and the traditional practice of data collection, storage and access, agile businesses can not only improve their dynamic decision-making, but they can also expedite enterprise data integration and decentralization. While a plethora of analytics and data visualization tools have opened up new possibilities for sharing data across a business, they have also introduced a new set of challenges for business owners and analytics teams.

  • Related Bachelor Projects:
    • Self-service Data Preparation
      Supervised by:
    • Automated Machine Learning
      Supervised by:
    • Evaluating User Interactions with Machine Learning Systems
      Supervised by:
    • Evaluating AutoML Platforms for Deep Neural Design
      Supervised by:

Drive like an Egyptian 2.0

The dream of self-driving cars roaming the neighborhood seems now closer than ever, with both industry and research active in the area. Reinforcement learning (RL) is one class of machine learning concerned with teaching a smart agent to take actions and decisions. The agent learns independently and without hardcoding any built-in behavior. RL is heavily used in building self-driving agents among other applications. Meanwhile, a software agent that can adapt to the surprises of normal roads or drive in rural areas or developing cities has not yet been realized.

In this topic, you will learn, build and use cutting edge reinforcement learning techniques. The objective is to build an agent that can drive like an Egyptian; that is to drive in the wild. An Egyptian driver adapts to surprising road conditions, pedestrians crossing the roads randomly and even overtakes other cars when possible. While we would hope self-driving agents would abide by driving etiquette, having such skills can be very useful for preventative driving or during emergency situations.

Here we build on a driving simulator developed By 34- students: Gehad Abdelhalim, Amr Khalil and Mira Ekladious. The simulator shows a car learning to navigate a dynamic set of routes in presence of obstacles and pedestrians randomly crossing the road. The simulator supports imitation learning, where you can record a player controlling (driving) the car. The RL algorithm then learns to imitate that human driver. The simulator currently supports several RL algorithms, you will improve on these implementation and support more advanced algorithms, such as convolutional network –based RL and actor critic, as well as the use of evolutionary techniques to speed up the learning. You may choose to benefit from the recent release from Unity for Machine Learning support.

  • Related Bachelor Projects:
    • Maneuvers
      Supervised by:
    • Obstacles
      Supervised by:
    • Response and learning speed
      Supervised by:

Education

Educational reform is occurring throughout the world and one of the tenets of the reform is the introduction and integration of assistive technological means in educational systems. Motivated by the prospect of greater economic, social, educational and technological gains, both developing and developed countries, are bringing about this reform, with a clear focus on technology integration in education. This cluster looks at how developing countries can adopt, adapt, and apply the knowledge gained by countries that have already embarked on the technological assistive means integration bandwagon in their own educational systems. We aim at illustrating the ways in which technology mediated learning can be offered for all students with their different profiles in order to achieve a better learning experience and knowledge gain.

  • Related Bachelor Projects:
    • A-Learning: Adaptive Educational Games Platform
      Supervised by:
    • Education Gamification with Culture Integration
      Supervised by:
    • Can you block NAO?: Teaching children programming using Block b
      Supervised by:
    • Screen less Fun: Designing AR Interactive Interfaces for Prescho
      Supervised by:
    • ARcode: Programming for Youngsters through AR
      Supervised by:
    • Rule-Based Visualization Platform for Java
      Supervised by:
    • SEA-CS: Visualizing Data Structures and Analyzing Algorithms through VR and AR
      Supervised by:
    • Automated Haskell Consultant
      Supervised by:

Evolutionary Code Generation

Evolutionary computation is a family of algorithms for global optimization inspired by biological evolution. In technical terms, they are a family of population-based trial and error problem solvers with a metaheuristic or stochastic optimization character. In evolutionary computation, an initial set of candidate solutions is generated and iteratively updated. Each new generation is produced by removing less desired solutions, and introducing small random changes. In biological terminology, a population of solutions is subjected to natural selection (or artificial selection) and mutation. As a result, the population will gradually evolve to increase in fitness according to a fitness function chosen for the algorithm.

  • Related Bachelor Projects:
    • Evolutionary Strategies for Code Generation
      Supervised by:

Game with a Purpose and Crowd Sourcing

Game with a Purpose (GWAP) make use of the contributions submitted by players of different Web gaming platforms in order to collect data. The games are designed in such a way so that while users are playing, needed data is collected. Crowdsourcing is an emerging approach that involves humans in solving problems which, so far, have no pure algorithmic solutions. Both fields are increasingly gaining importance. They aim at making use of human intelligence.

  • Related Bachelor Projects:
    • Virtual/Mixed Reality Control of a Game through Scratch (BlockRunner)
      Supervised by:
    • Virtual/Mixed Reality Game to Teach Computational Thinking (VR MiniColon)
      Supervised by:
    • Virtual/Mixed Reality Game to Teach Hardware Programming
      Supervised by:
    • Build Up Your Computer
      Supervised by:
    • A Serious Game For Social Skills Enhancement For Children With Autism Spectrum Disorder
      Supervised by:

Hierarchical Processing in Computer Vision

The adaptive pyramid is a solution for the problem of detection and delineation of objects in a scene. This is achieved by joining smaller segments of the scene based on a joining criterion. The joint segments are abstracted into nodes, and these nodes are re-joined forming bigger segments. This process is recursively repeated till no more segments are able to be joined. Multiple variations of the algorithm components can result in different definitions for scene objects resulting in variant outputs. The goal here is to consider the various components variations, alongside implementing them. The various components depend on the joining criteria (i.e., the base on which objects are joined or differentiated), segmentation scope (i.e., the region of the scene on which the algorithm is to be performed) and the type of space (whether 2D or 3D).

Human Intelligence Understanding

This topic focuses on attempting to understand human intelligence differences and the relation between brain activity and intelligence.

  • Related Bachelor Projects:
    • Investigating Relation between EEG and IQ Test Performance
      Supervised by:

Intelligence for Future Networks and Services

The future Internet encompasses a multitude of technologies that will enable ubiquitous access to the Internet by the ever-growing population of devices and users with diverse data and connectivity needs and varying QoS requirements. The aim of these technologies is therefore to address the most critical technical and usage aspects for the Internet to sustain the huge future expectations of society at large. The technology perspective primarily addresses the limitations of communication networks and cloud computing infrastructures and services when moving towards a hyper connected world with hundreds of billions of devices fueled by ambient and pervasive services. Through incorporating intelligent algorithms and data analysis methods, the future Internet technologies are poised to address the communication and cloud infrastructure limitations and provide innovative services.

  • Related Bachelor Projects:
    • Software-defined Management of Edge-as-a-Service Networks
      Supervised by:
    • Resource Allocation in Cognitive Networks
      Supervised by:
    • Cooperative Spectrum Sensing for Cognitive Networks
      Supervised by:
    • Sensor-based System for Independent Tourist Mobility
      Supervised by:
    • Data forwarding in Delay-tolerant Networks using Transient Communities
      Supervised by:

Intelligent Autonomous Robots Control

Reactive autonomous robots navigating in real-world unstructured environments (i.e. environments that have not been specifically engineered for the robot) must be able to operate under conditions of imprecision and uncertainty present in such environments. The choice of adequate methods to model and deal with such uncertainties is crucial for robots operations in unstructured environments.

  • Related Bachelor Projects:
    • Adaptive pyramid implementation using mean values in full 2D space
      Supervised by:

Intelligent IoT Systems

The Internet of Things (IoT) characterize our near and expectedly far future. However, the mere extensive connectivity of all “Things” is not the main objective of IoT. Intelligent processing of the data generated by IoT devices in connection with multimedia and media convergence is the real goal of IoT for a better life.

Intelligent Transportation Systems for a healthier community

Intelligent Transportation System –ITS- uses advanced technologies of electronics, communications, embedded computers, control actuators and detecting sensors in all kinds of transportation systems in order to improve safety, efficiency and service, traffic situation, and -most recently- pollution. this is done through capturing and transmitting real-time information. People's health is badly affected from noise and particle emissions from traditional transportation systems, notability cars. Innovative connected sensors, on-board and/or in the infrastructure, allow real-time monitoring and control of transport noise and emissions.

  • Related Bachelor Projects:
    • Real-time Detection and identification of polluting vehicles
      Supervised by:
    • Emissions/Noise V2I system
      Supervised by:
    • Automated tolling system
      Supervised by:
    • Traffic management system based on noise and emission data
      Supervised by:

Interaction Design and Formal Evaluation

Interaction design is a broad area within Human Computer Interaction (HCI) whose goal is creating fluid interfaces and natural ways of interacting with software. Whether it being a new menu, a set of new gestures to perform a basic task such as drag and drop, or a completely unconventional way to interact with a computing platform or the physical world, interaction designer and researchers are guided by theoretical findings coming mostly from psychology, physiology and few other disciplines. The thesis projects under this topic are all HCI and interaction design focused. Because HCI is offered in the 9th semester, most of you will be unaware of the basic concepts of HCI. However, if you take one of the below projects, I will be giving you a crash 1 day course in the beginning of the semester to help you start thinking like an HCIer!

  • Related Bachelor Projects:
    • Input Tasks Using Sonar Interaction
      Supervised by:
    • Interaction Techniques for Life Logging
      Supervised by:
    • Augmented Reality App for Egyptian Museum
      Supervised by:
    • Wearable Interface and Mobile Interaction
      Supervised by:
    • Interaction Techniques for Holographic Display
      Supervised by:
    • Augmented Reality Tutoring Game
      Supervised by:
    • Health Monitoring using Facial Expression & ML
      Supervised by:
    • Rapid GUI Prototype Construction using Hand Gestures
      Supervised by:
    • Mixed Reality Game for Teaching Arabic Letters
      Supervised by:
    • Augmented Reality for Teaching Mechanics Laws
      Supervised by:
    • Enhancing Drag and Drop
      Supervised by:
    • Study on Object-based Memory Recall
      Supervised by:
    • Acquisition of Moving Targets
      Supervised by:
    • Speed as an Input Channel
      Supervised by:
    • ADHD Coaching System
      Supervised by:
    • Mid-air Typing
      Supervised by:
    • Drag and Drop in 3D scene
      Supervised by:
    • Evaluation & Enhancement of in-class Tutoring Aid
      Supervised by:
    • Evaluation & Enhancement of Textbook Studying Aid
      Supervised by:
    • Augmented Reality for Anatomy Visualization
      Supervised by:
    • Bridging the Gap between VR and Reality
      Supervised by:
    • Interaction Techniques for a Foot-based Interface
      Supervised by:

Java SNePS

SNePS is one of the oldest, yet developing, systems for knowledge 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 labeled directed graph where nodes represent entities (possibly propositions) and arcs represent structural relations among them. A SNePS network is thought of as the "mind" of an artificial, intelligent agent. The basic SNePS system is a network management 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 seven years, we have implemented local Java versions. We are now ready to launch the third version Java SNePS. In the course of the development, we shall take extra care of implementation efficiency and proper software engineering practices.

  • Related Bachelor Projects:
    • Java SNePS Task 1
      Supervised by:
    • Java SNePS Task 2
      Supervised by:
    • Java SNePS Task 3
      Supervised by:
    • Java SNePS Task 4
      Supervised by:
    • Java SNePS Task 5
      Supervised by:
    • Java SNePS Task 6
      Supervised by:
    • Java SNePS Task 7
      Supervised by:
    • Java SNePS Task 8
      Supervised by:
    • Java SNePS Task 8
      Supervised by:

Machine Learning for Medical Diagnosis and Analysis

Machine learning has recently gained the attention of the medical research community for automated diagnosis of various diseases. Advances in machine learning and data analytics have enabled the analysis of patients’ data to aid physicians in their diagnosis as well as helping patients.

  • Related Bachelor Projects:
    • Predicting Epileptic Seizures from Recorded EEG
      Supervised by:
    • Automated Leukemia Detection
      Supervised by:
    • Automated Heart Arrythmia Recognition
      Supervised by:

Massively Scalable Apps

This topic focus on the architecture, design and implementation of massively scalable applications such as those of social networks. Related areas include data structures and algorithms for scalability, distributed databases, data stores, distributed caches, farms, message queues, asynchronous I/O, load balancing, scalability, architectural design patterns, cloud architecture, design, and implementation.

  • Related Bachelor Projects:
    • Twitter-replica: Backend Enhancement
      Supervised by:
    • Twitter-replica: Front-end Enhancement
      Supervised by:
    • Service Oriented RDBMS
      Supervised by:
    • Aviation Control Algorithm for within City Flights
      Supervised by:

Media and Sensing Convergence Approaches

The wide spread of media and sensing technologies on many levels from in-pocket mobile phones to satellite and remote sensing created not only tremendous challenges but also huge opportunities for the convergence of different types of arts, sciences, socioeconomics, and more

Multimedia Networking

Multimedia streaming over data networks is extremely important in entertainment industry, communication systems, business applications and social networks. The audio and video streaming protocols keep evolving trying to meet new challenges and fulfill ever growing demand. This group of projects allows students, who are interested in this area, to learn more about up-to-date technologies and practice the implementation of streaming systems for a variety of goals. Although, these goals can be achieved using yesterday’s technologies, students will be asked to use today’s technologies.

  • Related Bachelor Projects:
    • Distant Office-Hours
      Supervised by:
    • Audio-visual Lab Support
      Supervised by:
    • Small-scale PBX Alternative
      Supervised by:
    • Audio-visual Home Intercom
      Supervised by:
    • Collaboration Hub for small teams
      Supervised by:
    • Secure Assignment Submission Platform
      Supervised by:
    • Over-LAN Baby Monitoring
      Supervised by:
    • Pet Monitoring Over Internet
      Supervised by:
    • Remote Industrial Quality Check
      Supervised by:
    • On-line Medical Consultant
      Supervised by:
    • Instant Delivery of Medical Test Results
      Supervised by:
    • Comparative Study on RTP Implementations
      Supervised by:
    • Comparison between Methods of Improving Mobile EEG data
      Supervised by:

Multimedia Processing & 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:
    • Profile Phonebook.. Face Recognition using oneself phonebook and social networks.
      Supervised by:
    • Fast Image Compression based on Multiresolution Analysis
      Supervised by:
    • Verification of Images Originality in Online News
      Supervised by:
    • Toward Quran Verses Recognition in General Speeches Using Machine Learning
      Supervised by:
    • Action Modeling Using Kinect for Sport Analysis and Rehabilitation Applications
      Supervised by:
    • Dynamic Video Summarization
      Supervised by:
    • Dynamic Video Summarization
      Supervised by:
    • Command Line Interface for Digital Audio Workstation
      Supervised by:
    • Music Scripting Using DSP Techniques
      Supervised by:

Neural networks take the IQ test: Abstract reasoning

One ongoing and heated debate is whether artificial intelligence should be considered intelligence at all and accordingly whether we should be preparing for the robots’ takeover of the world. One can easily dismiss both concerns. After all, machine learning is indeed only a coating around statistical models that detect similarity in data, no real intelligence here. Or is it?

Can machine learning models go beyond simply learning similarity of images and words? Recently, a team of researchers from DeepMind thought to put this hypothesis to the test. They constructed a dataset based on human IQ tests, such as completing patterns (one example is Raven’s Progressive Matrices, such as the diagrams in the first two pages here ). Existing neural networks failed, however, simple modifications in their architecture showed good performance on some of the IQ challenges.

  • Related Bachelor Projects:
    • Neural networks take the IQ test: abstract reasoning
      Supervised by:

Online Activism

Online platforms have become an influential medium for the spread of ideas, trends and products. This project aims to understand how ideas spread (and battle!) over social media. The same problem applies for business and political ideas. Product brands as much as political parties compete over maximizing their positive mentions on social media platform. In this project, we choose to focus on the political and social ideas.

Building on Youssef Ayman’s work from last year in analyzing Twitter population around the times of the debates from the latest American elections, we now focus on the Arab community on Twitter.

In this project, you will collect and analyze Twitter data using graph analytics techniques, sentiment analysis or machine learning to show how online activist groups mirrored key political events.

  • Related Bachelor Projects:
    • Polarization in the Arabic Twitter community
      Supervised by:
    • The revolutions were tweeted
      Supervised by:

Personal Shopper: Social and Visual Marketing

How to best recommend products to users is a key issue to online businesses. Many algorithms were and are being introduced and improved, mostly trying to predict what a user may wish to buy based on what other similar users bought. In this project, we harness social information about the user himself to recommend products.

  • Related Bachelor Projects:
    • Brand recognition
      Supervised by:
    • Personalization
      Supervised by:
    • Privacy
      Supervised by:

Prosthetic Vision

Visual prostheses hold hope of vision restoration for millions with retinal degenerative diseases. The main principal of visual prosthesis is to bypass the damaged part of the human visual pathway and electrically stimulate subsequent functional parts. Such electrical stimulation is supposed to deliver electrical pulses to the visual pathway that mimic what would have been received if the damaged part was intact. There are different types of visual prostheses; some of them have already been approved to be used to restore vision to blind patients, while others are under development. The most successful type is the retinal implant in which stimulating electrodes are used to replace damaged photoreceptors; converting light into electric pulses to stimulate the undamaged parts of the retina. However, the use of retinal implants is limited as parts of the retina have to remain intact to interface with the implant. Therefore, when the retina is completely damaged, other potential targets along the visual pathway are considered. One type is cortical visual prostheses that target the primary visual cortex (V1). Another type is thalamic visual prostheses which target the Lateral Geniculate Nucleus (LGN) in the brain, which represents a mid-way target for visual prostheses. Despite the success of many of theses devices, the image perceived by blind patients who are using these devices is very primitive. Perceived images are only black and white with very limited resolution. Given that our understanding of the perceived image is mainly based on the verbal description of the implanted patients, there is currently multiple research efforts to simulate how such perceived image looks like. Such simulation studies are expected to enhance our understanding of prosthetic vision and, thus, enhance the quality of the perceived image. Suggested Readings: Fernandez, Eduardo. "Development of visual Neuroprostheses: trends and challenges." Bioelectronic Medicine 4.1 (2018): 12. Chen, S. C., et al. "Visual acuity measurement of prosthetic vision: a virtual-reality simulation study." Journal of Neural Engineering 2.1 (2005): S135.

  • Related Bachelor Projects:
    • Character Recognition using Prosthetic Vision
      Supervised by:
    • Face Recognition using Prosthetic Vision
      Supervised by:
    • Feature Extraction for Navigation using Prosthetic Vision
      Supervised by:

Qualitative Spatial Reasoning

Qualitative spatial reasoning (QSR) (Cohn and Renz, 2008) is the field of research which studies all aspects of reasoning about spatial phenomena in a qualitative, rather than quantitative, metric-based, manner. In particular, QSR is primarily concerned with the logical representation of spatial knowledge and the computational problems of reasoning with that knowledge. Qualitative spatial knowledge covers topological relations among regions of space (Randell et al, 1992), cardinal directions (Ligozat, 1998), qualitative orientation information (Freksa, 1992), positional information (Clementini et al., 1997), qualitative shape (Cohn, 1995), and qualitative size (Gerevini and Renz, 2002; Bittner, 2011).

  • Related Bachelor Projects:
    • Reasoning about Vision
      Supervised by:

Remote Sensing Images

Remote Sensing Images refer to image acquisition using satellite- or aircraft-based sensor technologies to detect and classify objects on Earth. It has many applications in many fields such as security, traffic managements, civil engineering, environmental monitoring and others.

  • Related Bachelor Projects:
    • Unmanned Aerial Vehicles Images: Car Detection and Counting
      Supervised by:
    • Desertification Monitoring using Remote Sensing Images
      Supervised by:
    • Semantic Segmentation for Land Use Classification of Multispectral Remote Sensing Images
      Supervised by:

Smart Agriculture

The surge in global population is compelling a shift toward smart agriculture practices. This coupled with the diminishing natural resources, limited availability of arable land, increase in unpredictable weather conditions makes food security a major concern for most countries. As a result, the use of Internet of Things (IoT) and data analytics (DA) are employed to enhance the operational efficiency and productivity in the agriculture sector. There is a paradigm shift from use of wireless sensor network (WSN) as a major driver of smart agriculture to the use of IoT and DA. The IoT integrates several existing technologies, such as WSN, radio frequency identification, cloud computing, middleware systems, and end-user applications. All of these systems can be leveraged to build smart agriculture systems across different functionalities.

  • Related Bachelor Projects:
    • IoT-based Intelligent Irrigation Control System
      Supervised by:
    • IoT-based Intelligent Agriculture Field Monitoring System
      Supervised by:
    • Big Data Platform for Agriculture
      Supervised by:

Smart homes for the elderly

Unprecedentedly, people around the world are growing older—and living longer. In 2015, 617 million people (8.5% of the world’s population) were age 65 and older. That number is expected to grow to 1.6 billion (17 % of the world’s population) by 2050. Smart homes can be viewed as a residence equipped with technology that anticipates and responds to its occupants’ needs, working to promote their comfort, convenience, security… Instead of having the elderly spend their golden age in institutional care, or move to a brand new smart house full of high-tech gadgets, the idea is to turn their own -already familiar- homes smarter, making life comfortable, convenient and safe.

  • Related Bachelor Projects:
    • Smart refrigerator for the elderly
      Supervised by:
    • Smart lock and motion alerts system for the elderly
      Supervised by:
    • Automated Thermostats & Lights system for the elderly
      Supervised by:
    • A smart Medical Alert system
      Supervised by:
    • A smart Pet feeder
      Supervised by:

Smart office

A “smart office” is an office space equipped with IoT devices. It can be seen as an ecosystem relying on those IoT devices that: monitor, control, and manage various operations and working conditions. Among the many benefits of a smart office: Energy savings, efficient business operations, comfortable working environment, better employee productivity, increased workplace safety…

  • Related Bachelor Projects:
    • A Smart Security system for visitor management and access control
      Supervised by:
    • A smart scheduling systems for meeting rooms
      Supervised by:
    • Smart Real-time office floor plans / Employee Location Tracker
      Supervised by:
    • Smart office chair
      Supervised by:
    • Smart sensitive planter system
      Supervised by: