Keynote Speakers

     

 

Dr. Andreas Koop                                 

CEO, BFSTS GmbH, Baar, Switzerland

Visiting Professor of Medical Informatics, University of Derby, UK

Personal Medical Record – from limited to worldwide usage

Abstract: 

Usually, a person’s medical information is stored separately by various healthcare providers such as hospitals, resident doctors, and physical therapists, and therefore scattered in several places within a healthcare system. This situation makes it difficult for people to keep track of their examinations, diagnoses, and findings. What makes things more complicated is that people do not necessarily spend their whole life in one place or even one country anymore, but instead often have to move because of family and jobs. In addition, healthcare systems are organized quite differently from country to country. Although several approaches have been made so far to help people keep their own medical record, they are all geared to a limited user community or they lack necessary communication capabilities.

Thanks to recent advances in distributed systems (graph approaches, blockchain, etc.), the necessary prerequisites have become available for creating a fully secured personal medical record and for connecting it to the relevant stakeholders within a healthcare system. Considering that personal medical information is very valuable for research purposes (real-world data), the personal medical record needs to be accessible to research as well.

An overview of existing solutions and a new approach for creating a modern personal medical record will be presented.

..............................................................................................................................................................................................................................................

     

 

Dr. Mohd Shafry Mohd Rahim

Universiti Teknologi Malaysia.

Semantics Gap in Image Analytics 

Abstract: 

Humans have a strong ability to process millions of data and information to assist in the decision-making process. With new disruptive technology, trillion of data has been flooded into the cloud computing and require analytical process to produce valuable information. Images are one of the data collected using a variety of sensors that carry a lot of valuable information for the decision-making process. Therefore, Image Analytics is a very significant research area to be strengthened in the new era of Big Data. Extraction of useful information from the processed image is an essential task in image processing; some of such methods try to mimic human visual processes. The difference between the low-level representation of the image and its high-level human perception is known as a semantic gap. Semantic image analysis provides better and as per human perception access to image databases, and content filtering, summarization, enhance human and computer interaction. The problem of the semantic gap is crucial and as can be seen in many tasks of image analysis, as Content-Based Image Retrieval (CBIR) or Automatic Image Annotation (AIA). The result greatly depends on lower level vision techniques, such as colour, shape, feature selection, segmentation, object recognition, and spatial layout. Content-Based Image Retrieval (CBIR) is a technique of searching images according to a user’s interest by visual features extracted from the image; usually large-scale image databases are searched. The image retrieving is a challenge when expecting the results according to human perspective and expectations. The use of deep models has freed humans from manually selecting and extracting the set of features. Deep learning does this automatically, developing more abstract features at successive levels. In this keynote, the discussion will focus on experiences in Image Analytics and discussing key challenges in various applications for further research.

Keywords: Big Data, Image Analytics, Semantic Gap, Deep Learning, Image Retrieval.

..............................................................................................................................................................................................................................................

    

 

Dr. Kareem Darwish

Principal Scientist,, Qatar Computing Research Institute,

Hamad Bin Khalifa University, Qatar

Unsupervised Stance Detection

Abstract: 

I present a highly effective unsupervised method for detecting the stance of Twitter users with respect to controversial topics. In particular, the method uses dimensionality reduction to project users onto a low-dimensional space, followed by clustering, which allows us to find core users that are representative of the different stances. The method has three major advantages over current state-of-the-art methods, which are based on supervised or semi-supervised classification. First, prior labeling of users is not required. Instead, clusters of core users are identified, which are much easier to label manually afterwards, e.g., in a matter of seconds or minutes instead of hours. Second, there is no need for domain- or topic-level knowledge either to specify the relevant stances (labels) or to conduct the actual labeling. Third, the method is robust in the face of data skewness, e.g., when some users or some stances have greater representation in the data. We experiment with different combinations of user similarity features, dataset sizes, dimensionality reduction methods, and clustering algorithms to ascertain the most effective and most computationally efficient combinations across three different datasets (in English and Turkish). The best combination in terms of effectiveness and efficiency uses retweeted accounts as features, UMAP for dimensionality reduction, and Mean Shift for clustering, and yields a small number of high-quality user clusters, typically just 2–3, with more than 98% purity. Moreover, the method is robust to variations in the parameter values and also with respect to random initialization.

Bio: Kareem Darwish is a principal scientist at the Arabic Language Technologies at QCRI with interest in natural language processing (NLP), social computing, and information retrieval. He was as a researcher at the Cairo Microsoft Innovation Lab and the IBM Human Language Technologies group in Cairo. He also taught in the Electrical Engineering Department at the German University in Cairo and the Faculty of Computer and Informatics at Cairo University. He is currently developing a state-of-the-art Arabic NLP toolkit that includes POS tagging, named entity recognition, parsing, etc.  In social computing, he is working on the automated detection of propaganda accounts on social media and on stance detection.

-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

    

 Professor Amir Hussain

Visiting Professor: Anhui University                                        

Full Professor: Edinburgh Napier University, UK.

Founding Director: Cognitive Big Data & Cybersecurity (CogBiD) Lab,

Edinburgh Napier University, UK.

 Towards Cognitive Big Data Sentiment Analytics: Real-world case studies and emerging research challenges 

Abstract: 

Cognitive Big Data Sentiment Analytics is a rapidly developing discipline, bringing together neurobiology, cognitive psychology, Big Data, AI and Natural Language Processing. Ongoing pioneering work at Edinburgh Napier University is exploring development of cognitively-inspired Big Data Sentiment Analytics for engineering the secure and intelligent systems of tomorrow. Selected case studies are presented in this talk exploring future open-domain sentiment analysis of natural language text, using sentic computing: a novel multi-disciplinary paradigm, exploiting the semantic, latent and implicit meaning of natural language concepts. Ongoing extensions of this work include a cognitively-inspired emotion recognition system based on contextual multimodal input, including text, audio and facial information, leading to more natural human computer interaction, and future secure and smart e-applications. We present a brief summary of these exciting multi-disciplinary research areas, and also outline some future research directions and challenges in a number of other selected, cognitive big data informatics applications.

-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------