The world has entered a new nuclear age where the threat of catastrophic nuclear war has subsided, but the proliferation of weapons and the materials, combined with strengthening of non-state actors, have made the threat of “dirty bomb” to substantially increase. This unprecedented danger threatens the security and the safety of the countries around the region and the world.
One of the main challenges in this domain is the detection and mitigation of nuclear threats, especially in big cities. Today, nuclear sources are not just restricted to the already well-controlled power plants or military facilities, but can be widely found in hospitals via medical equipment, medicine, and medical waste, or in research laboratories through research materials, or many other such sources. These sources when obtained distributedly or taken from a single source can easily be engineered to produce a radiological dispersal device or the “dirty bomb.” Moreover, these sources may be mobile, i.e., carried by individuals, and can be moved around through logistical chains, which poses a real threat to the population at large.
To address these challenges, we propose for the first time a multi-faceted approach to develop a well-rounded dynamic participatory system, using Internet of Things (IoT) and Mobile Crowdsensing (MCS), which can provide continuous high-precision and real-time detection, tracking, and localization of small mobile and immobile radiation sources and unexpected radioactive materials, within a noisy radioactive environment in an urban setting. The proposed solution also has the potential to cross the boundary of nuclear detection, as other sensing nodes and networks may be developed, on similar principles, for applications in environmental, industrial, or military monitoring.
Prostate cancer (CaP) is the most frequently diagnosed malignancy after skin cancer and the second leading cause of cancer-related to male deaths after lung cancer. In the UAE, a recent study by the Health Authority of Abu Dhabi revealed that CaP is the third most common cancer in the UAE, affecting around 313 males out of every 100,000 of the population, making it the fourth most prevalent form of disease in among men in the UAE. Early and accurate detection will allow clinicians to initiate early intervention and appropriate treatment at earlier stages. Thus, it can potentially decrease the mortality rate of CaP. In addition, it is estimated that early detection of CaP using invasive MRI-based systems will reduce the diagnostic costs by 90%, benefiting patients, payers, and, in a bundled payment system, providers as well. This research will also bring more awareness about the importance of early prostate cancer screening.
Most of the MRI-based computer-aided diagnosis systems proposed so far, indicate the presence of CaP either on whole MRI scan or in a sectional part of it without providing any information about the location of the CaP lesion in the MRI scan image. In this project, we propose to fill this gap by designing an advanced machine learning system capable of accurately locating the related lesions in the MRI scans. This information will provide pertinent guidance for the physician when performing the biopsy, thus reducing the risk of misdiagnosis.
Artificial intelligence technologies are increasingly taking more essential roles in modern society. They are used in web-searches, social and e-commerce websites, cars, and cell phones, etc. More recently, deep-learning methods made important advances in solving a wide range of problems in artificial intelligence. It achieved remarkable results outperforming other machine learning algorithms in fields like image recognition, speech recognition, and natural language understanding. These results sparked a wave of commercial activities and startups.
Deep learning methods are a class of neural networks that allows a machine to be fed with raw data and to automatically discover the necessary formulas needed for classification. After training, the performance of the system is tested on new data sets. Deep neural networks are composed of a multi-layer stack of simple neural networks. Each module in this stack transforms the input using non-linear or linear mathematical operations. Despite the progress enabled by deep-learning methods, limitations of the technology remain to be explored and addressed in order for it to reach its full potential and range of application areas. In this project, we will design and develop novel systems that extends the capabilities of current technology.
Electric vehicles (EVs) are known for their low pollution, high efficiency, and smooth control. It is expected that in the near future the number of electric vehicles will increase. Research in the area of EVs is important to the UAE as it fits in to the UAE Green Agenda 2015-2030. The electric vehicle technology is still in the early stages and there is lot of scope for research and improvement in the electric vehicle technology. High-density battery packs, efficient power conversion and power management, and efficient and cheaper drive train are some of the major challenges that need to be addressed for the success of EV technology.
Majority of the EVs use permanent magnet motors as prime movers in the drive train of the EVs. Permanent magnets are compact in size and efficient but expensive. Permanent magnets are made up of rare earth materials and these are available in limited quantity and as the number of vehicles increase the cost of these magnets will rise exponentially. Therefore, there is a need to develop an alternate drive technology based on other motors like induction motors or switched reluctance motors.
This research proposal aims at developing a cost-effective drive train based on induction motors. Proper estimation of rotor and stator resistance and flux estimation, developing compact and efficient power converters, distributed drive train using in wheel type drive, better utilization of the battery voltage using dual fed drive and increased drive range with efficient regenerative breaking are some of the objectives of the proposed research proposal.
A challenge in using induction motor is the high DC bus voltage requirement, therefore a suitable high gain DC to DC converter to interface the low voltage battery bank to the high voltage DC bus of the inverter will be developed. This DC-DC converter need to be bidirectional for regenerative breaking. A mathematical model of the drive technology will be developed and verified through computer simulation. A scaled down model of the EV drive train will be designed to verify the proposed improvement experimentally.
The power electronics research laboratory at Khalifa University has the necessary infrastructure and facility to execute the above project. The research team has the necessary background and expertise, and is confident on the successful completion of the project in the scheduled time frame. The research team will consist of graduate and undergraduate student researchers (with preference to UAE nationals) and will be led by a team of three experienced faculty members, two of which are UAE nationals. The successful completion of this project will prove the feasibility of using induction motor as the prime mover in the drive train of EVs.
Recent advancements in technology, along with the rise of the “sharing economy,” has popularized crowd sensing, which is the act of requesting data or services from individuals in the public who perform the task and are then appropriately compensated. An important limitation of crowd sensing is to motivate the workers to perform the tasks at reasonable costs, which ensures a better service for the task requesters, as well as provides fair compensation to the individual participants. These frameworks of crowd sensing also raise an important issue of trustworthiness of the workers and the collected data, which in turn can affect the service provided to the task requester. In this proposal, we present a background in the areas of incentivization and trustworthiness in crowd sensing, along with limitations of existing work in both areas. Additionally, we outline our objectives and suggested research plan to develop an incentive mechanism and game theoretical model for crowd sensing platforms along with the impact of our work. Finally, the required resources and the budget are discussed.
Standard optimization algorithms, such as those arising in machine learning, assume precise knowledge of their inputs, and optimize their performance based on this assumption. However, in real-life applications, the data collected (either training data or problem parameters) includes some sort of noise, which can be used to model the uncertainty in the data. For example, in classification algorithms, the training data points may be known up to a limited precision with errors introduced possibly due to inaccuracy in measurements, and distortions by privacy-preserving data perturbation. Clearly, an algorithm designed based on such distorted data to optimize a certain objective function would not yield reliable results, if no special consideration of such uncertainty is taken. Several previous works have considered the incorporation of such noise into the machine learning and other optimization algorithms. A general approach, within the framework of robust optimization, is to characterize the noise by some generic assumptions, e.g., it lies in a (small) bounded convex region around a nominal value, and optimize the objective function for the worst-case possibility within this region.
In many cases, it turns out that the obtained convex robust optimization problem can be cast as a second-order cone program (SOCP), or more generally, as a semidefinite program (SDP). Most (if not all) previous work essentially provides reductions from the underlying machine learning problems under uncertainty to robust convex optimization, but stop at this point since one can then rely on available general convex programming (CP) solvers to tackle the problem. However, it is observed that the computational efficiency of available general CP solvers is not practical for very large data sets. On the other hand, most of the problems arising in machine learning have a special structure that can be exploited to provide faster algorithms. This motivates the exploration of specialized CP methods, such as first-order methods. Such techniques have been extensively explored for the non-robust optimization versions of machine learning algorithms, but we are not aware of any extensions to the robust versions.
The first part of this project aims at delivering practical algorithms for such robust versions of common machine learning optimization algorithms, as well as theoretical and empirical analyses of their performance on real-world data. The situation becomes even more challenging when the solution space is discrete, e.g., in the case of clustering problems, in which case the problem is computationally hard. In the non-robust case, a standard approach is to formulate and solve a linear programming (LP) or SDP-relaxation of the problem, then use careful rounding techniques to map the obtained continuous solution into the discrete solution space without losing much in the objective value. Extending these techniques to the robust version makes the second main part of this project. Based on the obtained results, a software tool will be built to provide efficient algorithms for robust versions of a wide range of machine learning algorithms.
To date, there is no unified way to mathematically represent a soft robot; instead, several complementary and disjoined modeling approaches have been proposed so far. For this reason, as opposed to traditional rigid robotics, there are no standard computational tools for the mechanical and control design of this new class of robots, and this has prevented the soft robotics field to reach its full potential.
In this project, we will take a cue from the authors’ most recent works to build and demonstrate a unified modeling framework capable of modeling soft and rigid robots within the same formulation, creating a standard for the modeling and control of soft robots. A complete and systematic generalization of the main concepts of robotics will be proposed. This unprecedented attempt will be based on a new modeling approach called Piecewise Constant Strain, which is a generalization of the geometric theory of robotics developed since Brockett’s original work on the subject. The result of this unification and generalization will be transferred into existing robotics simulation platforms in the form of toolbox and software packages. In particular, a MATLAB toolbox and SOFA packages will be developed for mechanical design and low-level control and high-level control, respectively.
Machine learning algorithms often deal with large volumes of data focusing on data analytics, inference, and decision‐making. These algorithms require frequent memory/storage access and highly parallel largescale computations. Real‐time response (performance) and energy consumption of such algorithms are mostly determined by memory accesses or data transfer. Conventional computing systems (von Neumann architecture) are designed such that computation and data are inherently separated. Such systems often suffer from large latency and data transfer costs. Even though CMOS technology scaling provide exponential growth of speeds and storage densities over time (Moore’s law), data transfer rates between the processor and memory have been lagging behind. Thus, the processing capabilities of today’s systems are limited by data transfer rates, which is known as the von Neumann bottleneck or memory wall. In addition, the impact of data transfer for typical data intense computation is a big percentage of system energy. Recent studies of machine learning algorithm and Neural network showed that greater than 65% of energy is consumed by memory access. Hence, techniques that radically reduce these costs for such applications are needed.
Most of traditional architecture solutions of negative impact of memory access on performance and energy are focusing on employing multi‐level memory system and architecture. The ideal solution is to decrease the distance between the system memory and processing to zero. Memristor technology is an emerging Resistive Random Access Memory (RRAM) technology that holds great potential to play a role in achieving close to ideal solution by enabling In‐Memory‐ Computing (IMC) for both digital and analog type operations. In addition to reducing the memory bottleneck, IMC makes it possible for IoT type of systems to do local processing and decision making that enables autonomous application. The objective of the proposed research is to explore memristor-based architectures to perform machine learning for pattern recognition applications in IoT devices.
The technology developments for autonomous operation and wireless charging in different disciplines are encouraging and promising. However, the focus on the system wide implementation with respect to challenges, impacts and potential solutions is limited both in literature, practice and policy. This project aims to solve some of the challenges in system wide deployment of electric vehicle wireless charging (WC). The project focuses on the implementation of wireless EV charging system in the UAE.
This research project is infrastructure based on cooperative autonomous driving technology development. In this project, we use infrastructure in the road to compensate for the limitation of ongoing development of autonomous vehicle. The specific technologies to be developed are:
The final delivery of this project will be the autonomous vehicle driving in an established infrastructure testbed.
The emergence of the Cyber-Physical Systems (CPS), digital eco-systems where humans live and work side by side with billions of intelligent objects, is not just a technological innovation, like others that have occurred in past, but a singularity that has radically and forever changed the way human beings live and work. Today, CPS support a wide range of applications, such as intelligent manufacturing, transportation, finance, healthcare, and entertainment. Developing research in this field and drawing up its technological development are crucial parts of the UAE strategy and of the Abu Dhabi Economic Vision 2030. The KU Research Centre on Cyber-Physical Systems (C2PS) will investigate transformative ICT technologies supporting change like micro-devices, cloud/edge computing architectures, cyber-security, and mobile communications, as well as with emergent disruptive innovations that bring on change, such as Artificial Intelligence, Internet-of-Everything, and Blockchain.
The C2PS mission is threefold:
C2PS activity revolves around four Themes that converge to support and enable CPSs: Computation architectures, Networks and Communication technology, Hardware and Micro-Device technology, Big Data analytics and Artificial Intelligence, Security, trust, dependability and privacy. C2PS four research Themes converge to a common goal: building today’s digital applications whose dimensionality, variability and volume defy traditional approaches.
Robotics is a powerful technology poised to have a disruptive societal impact. Potential robotic applications are ubiquitous and robotics technology has huge economic potential. This is reflected in the unprecedented interest and investments in robotics research and development worldwide, including the UAE. Khalifa University (KU) created a Robotics Institute (KURI) in 2012. Since then, KURI has developed into one of the top robotics labs in the region and is fast gaining a strong international reputation. KURI has state of the art research labs with over 25 dedicated faculty, staff, and graduate students, and has established strong collaborations with local industry. KURI played the leading role in designing and launching the very successful MBZIRC in 2017. Building on this track record and momentum, the proposed Khalifa University Center for Autonomous Robotic Systems (KUCARS), will integrate robotics and computer vision related research activities in the three campuses of KU, bringing together 24 faculty, to address some of the cutting edge R&D challenges in robotics. Based on existing strengths and UAE-based stakeholder interests, KUCARS will focus on three frontier robotics application themes: infrastructure inspection, extreme environments, and industrial applications. KUCARS has the vision to be amongst the top robotics labs in the world within the next five years.
The core mission of KUCARS will include, carrying out world class research and development in robotics as evidenced by high-quality research outputs, focusing on robotics based innovation leading to entrepreneurial activities, engaging with local and international industry to tackle high-impact societal problems, and developing human capacity in the UAE to support this vital economic sector.
Nuclear and hydro power generation techniques have an important role to play in the UAE’s 2030 energy vision of low carbon sources to meet future energy demand. The UAE is currently investing in the installation of a number of conventional hydro power plants and its first nuclear power plant, Barakah, costing around 25 billion USD. For these plants to operate at high efficiencies and to satisfy stringent safety requirements, a step-change is consequently needed in modeling and simulation capabilities to accurately describe the multi-physics (coupled thermal hydraulics and solid mechanics) processes.
The current proposed project not only targets the wider thermal-hydraulics modeling/design planned activities of the UAE’s 2030 energy vision but also directly supports the ‘UAE Strategy for Artificial Intelligence (AI),’ which emphasizes strongly on the automation of renewable energy and space sectors.
The main objectives of the current project are to:
The project is divided into multiple work packages (WP) with an aim to enhance the applicability and reliability of current modeling capabilities targeting the multi-physics problems encountered in nuclear and renewable energy sectors.
Underwater soft robotics is receiving growing popularity within the scientific community, thanks to its prospective capability of tackling challenges that are hardly dealt with by traditional rigid technologies, especially while interacting with unstructured environment. Incorporating the benefits of the two approaches, we propose a multi-functional, multi-module underwater robotic system with deformable appendages for grasping and propulsion inspired by bacteria morphology. Exploiting natural compliance, several modules resembling bacterial flagella provide propulsion and manipulation skills, while representing also dynamically flow-responsive and highly deformable appendages for distributed sensing and energy harvesting capabilities. The proposed design, combined with onboard autonomous operation capability, has the potential to unveil an effective solution for a broad range of tasks currently unsolved, such as the non-invasive monitoring of water quality and marine habitats, easing the mapping of the species and their distribution. It also allows to perform safe, robust, and gentle manipulation and intervention in underwater human-made structures.
A significant barrier to deploying autonomous vehicles (AVs) on a massive scale is safety assurance. Several technical challenges arise from the uncertain environment in which AVs operate, such as road and weather conditions, the uncertain behavior of pedestrians and agent vehicles, as well as model inaccuracy. In this project work, we will develop an algorithm pipeline along with a technical stack for trajectory optimization for AVs with bounded risk of collision. We consider three major contributions. First, an intention recognition system that predicts the driving-style and the intention of agent vehicles and pedestrians. Second, a planning system that takes into account the uncertainty in the environment and propagates all the way to control policies that explicitly bound the risk of collision. Third, a high-level planning system that extends to multi-vehicle on-the-spot collaboration, under diverse game-theoretic situations that arise due to competing local objectives among AVs.
The number of passengers traveling by air is continuously on the rise. According to the World Bank, ~3.7 billion passengers travel by air globally (with ~7% increase every year). The UAE is witnessing an extraordinary growth in both land and air passenger traffic. In Abu Dhabi’s airport for instance, the passenger traffic is growing at a rate of 19% annually. Such an expansion, together with the cosmopolitan population in the UAE, safety and security concerns in today’s world and middle eastern conjuncture, in particular, require fast and foolproof security measures. To ensure safety, the security staff at ports manually inspect incoming and outgoing passenger luggage, packages, and containers with x-ray scanners. The screening process is resource intensive and requires constant attention of human experts during monitoring. This introduces an additional risk of human error caused by fatigued work-schedule, difficulty in catching contraband items, requirement of quick decision making, or simply due to a less experienced worker. In the case of passenger luggage, research shows that threat detection performance of human experts is only about 80–90%. Furthermore, human inspectors can only inspect a fraction of the whole incoming international mail. An intelligent, automated system for the detection of contraband items in X-ray images would bring significant contribution in mitigating the aforementioned issues. To that end, there are several challenges to overcome:
Based on the above, a practical contraband detection system for security and regulation applications that is accurate and reliable is therefore far from realization and is an open research problem. This project aims to find novel solutions to address the crucial limitations of the existing systems.