This project aims to develop a cloud-based computing framework that will systematically monitor, collect and integrate disaster and crisis-related data streams from diverse social network channels, and turn them into actionable intelligence in a knowledge-base for intelligent inferencing, crisis handling, and decision making. The key components of the proposed framework are three: First, the collection of multilingual and multimodal data (text, audios, videos, images, and location information or other sensor-data) and their conversion into a unified machine-understandable dynamic knowledge-base. Second, the application of Natural Language Processing (NLP), Data Mining, Machine Learning, and Artificial Intelligence techniques for automatic identification, prediction, and detection of any type of crisis or disaster using the unified knowledge-base from the previous stage. 3) Third, the development of an interactive dashboard visualization to facilitate crisis monitoring and management.
During the last few decades, the frequency of the occurrence of natural disasters has increased. These disasters include floods, earthquakes, sandstorms, disease epidemics, along with man-made disasters such as industrial accidents and terrorist incidents. Saudi Arabia is prone to three major natural disasters including floods, epidemics, and sandstorms besides industrial hazards and accidents. The Kingdom has recorded 14 natural disasters, affecting nearly 30,000 people and resulting in an economic loss of approximately $450 million over the past three decades. The Presidency of Meteorology and Environment along with the Civil Defense Directorate has taken the step to advance the Disaster Risk Management (DRM). They identified three priorities for hazard prevention and mitigation: 1) Performing risk assessments and updating preparedness strategies; 2) Strengthening urban resilience and planning; and, 3) Ensuring effective operation of early warning systems. However, the country has yet to develop a comprehensive DRM framework for automatically predicting natural hazards, early warning, and risk assessment systems. Recently, the ubiquitous connectivity and proliferation of social networks opened up new opportunities for crisis management through crowdsourcing. However, extracting meaningful information from such a large, diverse, dynamic, but potentially useful data source is a bigger challenge that is just beginning to be addressed by the research community. In this project, we will integrate new computing infrastructure and technologies (namely, AI, Big Data, Cloud computing, and social media technologies) to bring in the next generation of Disaster Management solution by using data-driven insights and knowledge from user-generated contents. Such contents will help in emergency service providers to quickly get to public needs and provide emergency services.
In this project, we investigate a cloud computing-based big data framework that will enable us to utilize heterogeneous data sources and sophisticated machine learning techniques, in order to gather and process information intelligently and provide emergency workers useful insights for making informed decisions, as well as, guide the general public on how to stay safe during emergency situations (especially disease epidemic). Such a comprehensive framework will help the kingdom to develop comprehensive Disaster Risk Management capability for automatically predicting hazards, early warning, risk assessment, and risk mitigation including coordination of emergency activities and evacuation. The main thrust is to develop an information system product by dynamically extracting data from diverse social media channels, and storing, managing, analyzing, and interpreting these data in a real-time fashion. Additionally, to disseminate resultants information to decision-makers in a format appropriate for carrying out their tasks. We will also focus on key challenges of integrating social media analytics with existing sensors-based systems, since, existing systems augmented with analytics from social media will produce more meaningful insights from data by keeping the public in the loop. In specific, the proposed solution will perform the following tasks: First, it will dynamically capture multilingual (Arabic, English, and other languages) multimodal (text, audio, video, and images) data from various social media channels in real-time. Second, it will apply language-specific models to translate multilingual and multimodal contents into a unified ontology (knowledge-base). Third, it will apply machine learning and artificial intelligence techniques for intelligent inference from the knowledge-base. Last, it will interpret results and present information on interactive dashboard and disseminate information to relevant stakeholders
The duration of the project is three years starting from Nov 2019 and is funded by the ministry of education, Saudi Arabia. Currently, distinguished researchers from King Faisal University with multidisciplinary expertise in Artificial Intelligence (AI), machine learning, natural language processing, security, and risk management are undertaking this project. The project has many components e.g. topic modeling, named entity recognition, location identification from social media posts, etc. We need young researchers to help us in developing a few modules, each module is a complete solution itself. For example, one module is identifying COVID-19 related classes that can be mapped to a humanitarian organization such as people's needs, location hotspot, so that the emergency response organization can identified which location people are in need and what kind of services they required. This kind of task certainly, keep the respondent organization aware of the public situation and mitigate their problem timely, before the situation become worse which might create a human and economic loss.
Department of Information System, College of Computer Science and Information Technology, King Faisal University (KFU), Kingdom of Saudi Arabia (KSA)
AIDE Research team
Dr. Shaheen Khatoon, Department of Information System, College of Computer Science and Information Technology, King Faisal University (KFU), Kingdom of Saudi Arabia (KSA) Dr. Md Maruf Hasan, Department of Information System, College of Computer Science and Information Technology, King Faisal University (KFU), Kingdom of Saudi Arabia (KSA) Dr. Iram Fatima, Department of Computer Science, College of Computer Science and Information Technology, King Faisal University (KFU), Kingdom of Saudi Arabia (KSA) Dr. Amna Asif, Department of Information System, College of Computer Science and Information Technology, King Faisal University (KFU), Kingdom of Saudi Arabia (KSA)