EBTIC and BT Team Win International Awards Based on Innovation, Relevance and Evidence of Success, for their SPL Solution and Trial ��

The SPL team led by Salwa Alzahmi, a senior researcher at KU’s Emirates ICT Innovation Center (EBTIC), has won two awards in two categories at the prestigious 2021 Artificial Intelligence (AI) and Machine Learning Awards in the UK.��

EBTIC is a research and innovation center focused on driving research and innovation in intelligent systems and applications founded by Khalifa University, Etisalat and BT (British Telecom), and supported by the Telecommunication and Digital Government Authority’s (TDRA) ICT Fund. It is based at the Khalifa University campus in Abu Dhabi.��

The Computing magazine’s AI and Machine Learning Awards recognise the best companies, individuals, and projects in artificial intelligence. The judging process covers several industry segments such as security, ethics, data analysis, and innovation, while showcasing the movers and shakers including the technology heroes and projects that deserve industry-wide praise.��

The awards won by EBTIC’s SPL were in the categories of Best Cloud Automation Tool and Best Use of Automation. An elite panel of 12 judges selected the SPL entries as winners based on the evidence of three factors – innovation, relevance, and achieved success. More specifically, the Best Cloud Automation Tool award was given to EBTIC and BT for the tool’s innovative and fully featured automation solution that is designed to ease the burden of application migration to the Cloud. In their citation, the judges mentioned that the SPL Tool ‘has the opportunity to hugely reduce code complexity, thus improving security and reducing the cost of cloud migration’.��

In the Best Use of Automation award category, the SPL tool was highly recommended for the automation of migrating legacy software systems to cloud-native architecture using artificial intelligence, hence, addressing the challenges of complexity and high associated costs. The judges’ citation mentioned that the SPL team is highly recommended for this category for its ‘SPL project that has a strong topical story and told it well’.��

Dr. Nawaf I. Almoosa, Acting Director, Head of Smart Infrastructure Research, EBTIC, and Associate Professor, Electrical Engineering and Computer Science, Khalifa University, said: “Achieving this success in the 2021 Artificial Intelligence and Machine Learning Awards across two categories strongly indicates the extent of cutting-edge technological innovation being produced by the EBTIC’s SPL team productive partnership with BT to accurately target the future requirements of the industry in these areas. Our team members have demonstrated their talent in another prestigious international competition, and we hope to continue exploring innovation through working on new projects in AI and ML-related areas.”

SPL is a platform developed at EBTIC and uses intelligent methods to simplify and streamline software governance, development, and migration to the Cloud. The technology is currently undergoing commercialisation as a start-up in collaboration with Khalifa Innovation Center (KIC). Salwa Alzahmi, an Emirati researcher and tech entrepreneur, is leading the SPL platform development and commercialization, and has been instrumental in driving the technology, its commercialisation and the collaboration with BT Applied Research to evaluate the tool’s business value. As part of the drive for commercialisation, Alzahmi has set up a UAE-based tech start-up in the Khalifa Innovation Center – KIC khalifainnovation.ac.ae that is registered at Abu Dhabi Global Market. The EBTIC-SPL research team also includes Ahmed Suliman, Corrado Mio and Sid Shakya.

At the Computing AI and Machine Learning Awards 2021 in London, one of the UK’s leading business technology information resource, EBTICs SPL won awards for “Best Cloud or Networking Automation Tool” and was highly commended in the category of “Best Use of Automation”

The judges commented that SPL, in winning the “Best Cloud or Networking Automation Tool” category “has the opportunity to hugely reduce code complexity, thus improving security and reducing the cost of cloud migration.”

Alzahmi, Senior Research at EBTIC who leads the SPL team, said “I’m so proud of my team to be recognised in such a fantastic way. It is testament to all the hard work that has been put in to make the SPL tool such a compelling solution.”

Dr. Nawaf Almoosa, Acting Director of EBTIC, said: “EBTIC has a history of innovating practical AI solutions and have been a leader in intellectual property generation in UAE for the past 10 years. These awards are a further testament to EBTIC’s expertise of applying AI techniques to the operations of its partner organizations, and to their effort to promote Intelligent Systems research in the UAE and the region. We are immensely proud for the SPL team to be winning such prestigious awards, and we have high hopes for the future of SPL. I’d like to thank the SPL Team: Salwa Alzahmi, Corrado Mio, Ahmad Suliman, and Sid Shakya for this great achievement.”

Computing’s AI & Machine Learning Awards recognise the best companies, individuals, and projects in the AI space today. The judging process covers every corner of the industry: security, ethics, data analysis, innovation and more, as well as showcasing the movers and shakers: the technology heroes and projects that deserve industry-wide praise. With judges from prestigious organisations, such as Expedia Group, Network Rail, MET Office, London Stock Exchange and Computing itself, the winning of these awards proves that SPL demonstrates an outstanding, innovative approach in the field of AI.

EBTIC spun-out SPL.Co Ltd as a start-up in its own right, incorporated in 2019 and registered at Abu Dhabi Global Market. It came about following the success of SPL as a research project in 2015. SPL.Co provides corporations with an intelligent software modernization solution to accelerate and reduce the high costs associated with upgrading software systems into a cloud infrastructure.

EBTIC has a very successful history with Computing awards. In 2019, EBTIC’s spares optimization project Inuitu, won two awards for ‘Outstanding AI/Machine Learning Project’ and ‘Most Innovative use of AI/Machine Learning’.

EBTIC has produced more than 500 scientific publications, developed more than 75 inventions, resulting in 60 granted patents, with more pending, and has trained more than 350 students,�� and 250 professionals. It has also organized 10 international technical workshops and developed numerous technologies and worked on many projects in collaboration with its partners and stakeholders.

Clarence Michael
English Editor Specialist
10 August 2021

The post EBTIC’s SPL Team Wins Two Artificial Intelligence and Machine Learning Awards in UK appeared first on Khalifa University.

Saruq Al-Hadid Archaeological Site in Dubai Selected for First Study by ENGEOS Researchers to Apply Newly Developed Novel Method

Khalifa University has announced that researchers at its Environmental and Geophysical Sciences (ENGEOS) Lab have used satellite remote sensing observations to detect buried objects in already known archaeological sites and to identify potentially unexplored archaeological sites in the UAE by applying machine learning techniques to satellite data.

The novel method, which combines satellite data and machine learning, was developed at Khalifa University and can be applied to similar desert environments in the UAE and elsewhere. With this technology, the researchers were able to find a new potential area, unexplored yet by classic methods. This area is buried under the ground and is located on the opposite side of the current excavations.

Currently, the ENGEOS Lab at Khalifa University is investigating another archaeological site near Al Ain in the UAE.

Results from the ENGEOS research project led by Dr. Diana Francis, head of ENGEOS Lab, show that radar imaging allows direct detection and characterization of known as well as potentially novel buried archaeological sites. Researchers use satellite-borne Synthetic Aperture Radar (SAR) at very high resolution that can detect features of the size of one meter that might be buried in the subsurface (less than two meters) under optimum conditions, that is, dry and bare soils such as the soil at Saruq Al Hadid site. Moreover, remotely sensed data are well-suited for supporting regional archaeology, as well as tracking of environmental factors that influence archaeology.

Based on the machine learning techniques and deep learning analyses conducted during this work, the ENGEOS Lab was able to find potential areas for further on-site investigation. The unsupervised artificial intelligence developed during this project was partially validated as it was able to find the areas already under excavation on the site. As a next step, the method developed during this first phase of the project will need to be validated through a field survey, which will help improve the accuracy of the results.��

This technology will not only help reduce the cost of archaeological exploration but will also effectively help archaeologists identify potential locations. At the same, it will create a model that will be more accurate with time, because it has the ability to learn and use this knowledge.

Dr. Arif Sultan Al Hammadi, Executive Vice-President, Khalifa University of Science and Technology, said: “Khalifa University researchers focus their efforts not only on science, engineering, technology and healthcare areas, but also are able to apply remote sensing to archaeology to explore UAE’s cultural and heritage sites. The ENGEOS Lab leads remote sensing at Khalifa University and has developed an archaeology application with the potential to be applied to similar desert environments, anywhere in the world.”

The Saruq Al-Hadid archaeological site was selected for the first study by the ENGEOS researchers. This site had earlier been investigated by a team of researchers from Dubai Municipality and the Mohammed bin Rashid Space Center (MBRSC) Lab, indicating the presence of buried settlements in the site used by ancient indigenous workers.��

Discovered in 2002, Saruq Al Hadid sits deep in the desert of the southern reaches of Dubai emirate and is believed to have been an iron-age metal ‘factory’ in operation around 1,300-800 BC. Even though relics from the Stone Age (10,000 BC) have also been discovered, the peak period of the site is believed to have been around 3,000 BC. Based on up to 12,000 artefacts found on the site, archaeologists believe it is one of the main centers of copper tool manufacturing in the region since the beginning of the Iron Age (1,000 BC).��

Dr. Francis said: “Remote sensing has been able to assist archaeological research in several ways in recent years, including detection of subsurface remains, monitoring of archaeological sites and monuments, and archeo-landscapes studies. Now, artificial intelligence and machine learning applied to remote sensing can provide additional support and invaluable guidance for on-site archaeological work.”

Clarence Michael
English Editor Specialist
27 July 2021

The post Researchers at Khalifa University’s ENGEOS Lab Use Remote Sensing and Machine Learning to Find Potential Unexplored Archeological Sites in UAE appeared first on Khalifa University.

The features of a cell nucleus can reveal much about the health of a cell, but finding the nucleus among the background noise of a tissue sample can be laborious and time-consuming when done manually. Khalifa University researchers are exploring how AI can be leveraged to speed up the process of detecting a cell’s nucleus.

Known as the cell’s ‘command center’, the nucleus is a large organelle that stores the cell’s DNA. The nucleus controls all of the cell’s activities, such as growth and metabolism, using the DNA’s genetic information.

Pathologists use features of the cell nucleus to distinguish benign from malignant cells. They examine tissue samples for cells with increased nuclear size and irregularities in the nuclear membrane or abnormal distribution of chromatin, a substance within the chromosomes in the nucleus.

Artificial intelligence techniques are being investigated to streamline the process of nuclei detection. However, these techniques struggle when the tissue samples are noisy or when nuclei appear crowded.

Dr. Naoufel Werghi, Associate Professor, has collaborated with Dr. Sajid Javed, Assistant Professor, and Dr. Jorge Dias, Professor, to develop a machine learning solution that can sift through the background noise and more easily identify individual nuclei. Their results were published in.

In an ideal world, a sample of tissue would contain only that tissue, but most samples contain a rich mix of several other types. Most normal epithelial cells have nuclei which are round to oval-shaped, most lymphoid cells have round nuclei, while stromal cells have ovoid to spindle-shaped nuclei. Any machine learning algorithm would need to be trained on the specific nucleus shape for the nucleus it is tasked to detect, adding a further layer of training required if the algorithm were to be used in other applications.

“Nucleus detection is a challenging task because of the nuclear clutter and diverse shapes and sizes,” said Dr. Werghi. “Additionally, computation challenges arise because the images analyzed are multi-gigapixel images, and could contain billions of pixels and tens of thousands of cell nuclei.”

A number of potential methods have been reported for automatic detection of cell nuclei, including deep learning methods to train a convolutional neural network (CNN) to generate probability maps of where the cell nuclei are present.

Existing approaches are promising, but they require a significant amount of training data and expensive platforms to cater to the high computational requirements. The model proposed by the research team can be trained using much smaller training datasets that can be executed on a typical desktop computer.

“Our solution uses correlation filters to sort through the data and identify nuclei,” explained Dr. Werghi. “Compared to end-to-end deep learning in previous methods, correlation filters are computationally effective and require significantly less training data. The correlation filters are also flexible and can detect complex and irregular-shaped nuclei without requiring handcrafted features.”

These correlation filters help the algorithm to better discriminate different nuclear components from the non-nuclear regions and also to discern each nucleus from the remaining nuclei where they are clustered.

Constraints are placed on the spatial structure of the nucleus and its local contextual information in the correlation filter framework to handle varying nuclei shapes, texture, and clutter. The first considers the spatial structure of the nucleus, while the second discriminates between the nucleus and the non-nucleus region. Both of these help to reduce the noise in any given sample.

The team plans to explore the strength of correlation filters in analysis classifying cell nuclei and tissue phenotyping problems, such as cancer detection.

This research was funded by Khalifa University Center for Autonomous Robotic Systems (KUCARS).

Jade Sterling
Science Writer
5 July 2021

The post Sifting Through the Noise to Find the Nucleus with Artificial Intelligence appeared first on Khalifa University.

Khalifa University researchers find a way to use convolutional neural networks to identify cancer in tissue samples, which could speed up diagnosis and improve outcomes in patients with colorectal cancer.

Colorectal cancer is the third most common cancer among men and women worldwide, and the second most common cause of cancer-related mortality. Most colorectal cancers are due to old age and lifestyle factors, with only a small number of cases due to underlying genetic disorders. It typically starts as a benign tumor, such as a polyp, which over time becomes cancerous. Like all forms of cancer, early diagnosis and differentiation of the tumor are crucial for a patient’s survival and wellbeing.

Colorectal cancer may be diagnosed by obtaining a sample of the colon and using histopathology – the study of changes in tissues caused by diseases – to determine the characteristics of the tumour tissue at the microscopic level.

Histology is the study of the microanatomy of cells, tissues and organs as seen through a microscope. The structure of each tissue in the body is directly related to its function and diseases affect tissues in distinctive ways. Studying the histology of a tissue can be very useful in making a diagnosis and determining the severity and progress of a condition.

Because of the great variety of tests that are available, and the high level of skill needed to carry out and interpret them, researchers are beginning to turn to computational pathology and artificial intelligence techniques to identify in tissue samples diseases like cancer.

Dr. Sajid Javed, Assistant Professor, and Dr. Naoufel Werghi, Associate Professor of Electrical Engineering and Computer Science, have collaborated with researchers from around the world to develop algorithms to identify samples of colorectal cancer tissue. A paper based on this research has been published in.

“Computational pathology is a fast-growing research area in cancer diagnosis and can play an instrumental role in helping medical professionals detect and classify tumors,” said Dr. Javed.

Cancer histology reveals underlying molecular processes and disease progression and contains rich phenotypic information that is predictive of patient outcomes.

The phenotype is the set of observable characteristics or traits of an organism or a tissue. Image-based phenotyping aims to develop the computer vision techniques and tools needed to recover quantitative data from a wide range of images. But phenotyping presents challenging problems, particularly in images from colorectal cancer tissues.

Aided by advances in slide scanning microscopes and computing, convolutional neural networks (CNNs) have emerged as an important image analysis tool. CNNs use a network of interconnected layers of filters that highlight important patterns in the images and can continue to learn from previous results.

“Manual examination of tissue samples is time-consuming, highly subjective, and often affected by the observer,” explained Dr. Javed. “Meanwhile, algorithms analyzing digitized Whole Slide Images (WSIs) can examine hundreds of thousands of cells and billions of pixels to differentiate seven distinct tissue phenotypes.”

Deep learning methods require large amounts of annotated histology data for training, which may be tedious to obtain. Additionally, while these methods may be effective in determining tumor tissue, the tissues in colorectal cancer also contain a rich mix of several other types of tissue, including smooth muscle, inflammatory, necrotic, and benign tissue. Any algorithm must be taught to distinguish between these tissue types to be effective.

Texture analysis is a commonly used approach for tissue phenotyping, where texture features are computed to train classifiers, which are then used to predict distinct tissue types.

“Texture analysis may be attractive due to its simplicity but it does not fully capture the biological diversity of tissue components,” explained Dr. Javed.

“Recent methods have proposed integrating cellular connectivity features, which are used as a proxy to cellular interaction features. The notion of cellular connectivity features is based on the fact that spatially adjacent cells have a higher probability of receiving inter-cellular signals from each other than from cells that are farther away. It has also been shown that inter-cellular signals between various types of cells can influence the progression of cancer. However, a dynamic network of tumor growth cannot be adequately modelled by a single type of interaction. Our technique uses a multiplex network model to represent the intricate relationships between cell populations. We propose four different types of cellular networks integrating a variety of features representing tissue characteristics at different levels.”

In the researchers’ model, cells from a WSI are detected and classified into five distinct categories using a deep neural network. Then, four different types of cellular interaction features are computed and used to construct a four-layer multiplex graph. Since each slide contains thousands of cells, the slides are segmented into tiles or patches, which helps the algorithm determine the distribution of different types of tissues across the cells.

“There are many directions in which this work can be further extended,” added Dr. Javed. “Further cellular types such as blood cells could improve performance and also reveal more micro-level tissue communities. Additionally, our framework could be adapted to WSIs of different types of cancer. Of course, in clinical practice, our work can help medical practitioners understand the contents of the WSI and make more accurate and timely diagnoses.”

This work was funded by the Khalifa University of Science and Technology and the UK Medical Research Council. The collaborators were also supported by the PathLAKE digital pathology consortium, which is funded from the Data to Early Diagnosis and Precision Medicine strand of the UK government’s Industrial Strategy Challenge Fund, managed and delivered by UK Research and Innovation.��

Jade Sterling
Science Writer
5 July 2021

The post Leveraging AI to Detect Colorectal Cancer appeared first on Khalifa University.

The original computers were designed around a human brain model. Since then, developments in artificial intelligence and computer science continue to take inspiration from the brain.

Read Arabic story .

The human brain has always been under study for inspiration of computing systems. Although there’s a very long way to go until we can achieve a computing system that matches the efficiency of the human brain for cognitive tasks, several brain-inspired computing paradigms are being researched. Convolutional neural networks are a widely used machine learning approach for AI-related applications due to their significant performance relative to rules-based or symbolic approaches. Nonetheless, for many tasks machine learning requires vast amounts of data and training to converge to an acceptable level of performance.

A PhD student from Khalifa University, Eman Hasan, is investigating another AI computation methodology called ‘hyperdimensional computing’, which can possibly take AI systems a step closer toward human-like cognition. The work is supervised by Dr. Baker Mohammad, Associate Professor and Director of the System-on-Chip Lab (SOCL), and Dr. Yasmin Halawani, Postdoctoral Fellow.

Hasan’s work, which was published recently in the journal, analyses different models of hyperdimensional computing and ��ݮ��Ƶ the advantages of this computing paradigm. Hyperdimensional computing, or HDC, is a relatively new paradigm for computing using large vectors (like 10000 bits each) and is inspired by patterns of neural activity in the human brain. The means by which can allow AI-based computing systems to retain memory can reduce their computing and power demands.

HDC vectors, by nature, are also extremely robust against noise, much like the human’s central nervous system. Intelligence requires detecting, storing, binding and unbinding noisy patterns, and HDC is well-suited to handling noisy patterns. Inspired by an abstract representation of neuronal circuits in the human brain, developing an HDC architecture involves encoding, training, and comparison stages.

The human brain is excellent at recognizing patterns and using those patterns to infer information about other things. For example, humans generally understand that just because a chair is missing a leg, that doesn’t mean it’s no longer a chair. An AI system may look at this three-legged chair and decide it is a completely new object that needs a new classification. HDC vectors, however, offer some margin for error. With HDC, recognizing certain features will generate a vector that is similar enough to a chair that the computer can infer the object is a chair from its memory of what a chair looks like. Hence, the three-legged chair will remain a chair in hyperdimensional computing while in traditional object recognition this is a difficult task.

“In a HD vector, we can represent data holistically, meaning that the value of an object is distributed among many data points,” explained Hasan. “Therefore, we can reconstruct the vector’s meaning as long as we have 60% of its content.”��

The structure of the vectors leads to one of the strongest advantages of the HDC approach, which is that it can tolerate errors and therefore is a great option for approximate computing applications. This arises from the representation of the hyper vectors, where a bit value is independent of its location in the bit sequence.

HDC is also powerful in that it is memory-centric, which makes it capable of performing complex calculations while requiring less computing power. This type of computing is particularly useful for ‘edge’ computing, which refers to computing that’s done at or near the source of data. In a growing number of devices, including in autonomous vehicles, computations must be carried out immediately and at the point of the data collection, instead of relying on computing done in the cloud at a data center.

��

“Hyperdimensional computing is a promising model for edge devices as it does not include the computationally demanding training step found in the widely used convolutional neural network,” explained Hasan. “However, hyperdimensional computing comes with its own challenges as encoding alone takes about 80 percent of the execution time of its training and some encoding algorithms result in the encoded data growing to twenty times its original size.”

Hasan studied the HDC paradigm and its main algorithms in one-dimensional and two-dimensional applications. Research has shown that HDC outperforms digital neural networks in one dimensional data set applications, such as speech recognition, but the complexity increases once it is expanded to 2D applications.

“HDC has shown promising results for one dimensional applications, using less power, and with lower latency than state-of-the-art simple deep neural networks,” explained Hasan. “But in 2D applications, convolutional neural networks still achieve higher classification accuracy, but at the expense of more computations.”

Hasan concluded that HDC is still considered a new paradigm and faces challenges requiring further analysis.��

Jade Sterling
Science Writer
29 April 2021

The post A Step Closer to Brain Like AI with Hyperdimensional Computing appeared first on Khalifa University.