Modeling spread of epidemics: A Generalized Mechanistic Model for Assessing and Forecasting the COVID-19 Pandemic Spread
In addition to the high fatality rates, the rapid spread of COVID-19 has engendered tremendous social and economic implications all over the world. The global economy has also been impacted since the usage of human distancing, as an easiest solution to limit the spread of the disease. Thus, non-essential services have been shut-down, and hence, hundreds and even thousands of people lost their jobs. Furthermore, since most of the world nations have closed their borders, the international trade has collapsed. Additionally, the impact of the COVID-19 pandemic has reached the telecommunication industry. Accordingly, Internet Providers (IPs) have recently reported a massive and huge traffic due to the lock-down and stay-home orders applied by several states in the USA and other regions and countries. Over just few months, COVID-19 has changed the world and specifically our habits and daily lives and the situation does not seem to return to its normal soon in many countries. Therefore, it is very important to understand the behavior and expected trend of this disease and predict its spread. Forecasting the future evolution of this pandemic will also help assess its future consequences on different social and economic sectors. In this project, we investigate the evolution of COVID-19 in different countries using extended mechanistic models. The objective is to provide quantitative frameworks that allow scientists to assess and build hypotheses on the potential underlying mechanisms explaining patterns of the pandemic spread using real observed data at both spatial and temporal scales. Moreover, the developed frameworks allow to forecast the evolution of the virus and predict future statistics such as number of new cases and number of deaths as well as the number of quarantined and hospitalized cases. Ordinary Differential Equation (ODE) systems are employed to model the interconnection between the different states characterizing the possible behavior of the crowd and their impacts on the pandemic spread. Fitting optimization problems are then formulated and solved to estimate the values of the coefficients of the models and hence, forecast the future evolution of the pandemic given the current observation. Then, uncertainty regions are provided to visualize the expected upper and lower limits of the future evolution of the number of cases and deaths. In figure, an example illustrating the interconnections between eight intermediate and final states: protected, susceptible, exposed, infectious, recovered, hospitalized, quarantined, and deceased. We test the model on the COVID-19 data from four highly affected countries. The fitting algorithm has been validated graphically and through numerical metrics, and results show significantly accurate results for most of the countries. Once the model parameters are estimated, forecasting results are derived and uncertainty regions of the expected scenarios are provided.
A Social IoT-driven Pedestrian Routing Approach during Epidemic Time
The current smartphones and wearable devices’ as well as the omnipresent infrastructure of communication systems can boost the development of IoT-based solutions in a quick and large-scale manner to combat pandemics and prevent their spread. Precautionary practices such as hand cleaning, mask-wearing, social distancing, and close contact avoidance are highly recommended, however, they may not be sufficient to limit the exposure to the virus. Since the beginning of the pandemic, multiple IoT-based techniques have been tested and implemented to help mitigate the spread of COVID-19. One of the most promising approaches is to exploit IoT in e-monitoring such as spread tracking, contact tracing, and crowded areas monitoring. A fundamental solution to reduce the transmission of infectious diseases in general and particularly the COVID-19 is maintaining social distancing. IoT can perform a vital function in helping with social distancing practices thanks to their built-in sensors such as GPS, thermometer, and other features. For instance, in construction or industrial zones, wearables can be employed to maintain a safe distance between workers by generating alerts if social distancing is violated. It also helps track the spread of the virus in case that an infected person was present in the working area and hence, avoid the complete shutdown of the institution. The emergence of social IoT (SIoT) can be a valuable tool to leverage the traditional IoT systems and enable a better understanding of the ubiquitous IoT network. SIoT model the devices and users in the system with different social relations interconnecting the IoT devices. These relationships can be established between machine-to-machine, human-to-machine, and human-to-human connections and transform the IoT network into a socially connected network of devices that can be effectively analyzed using graph analytics tools such as community detection and machine learning. By assessing the SIoT, providing new applications to fight the virus spread can emerge and contribute to minimizing the pandemic’s negative impacts. In this project, we propose a smart navigation framework intending to give pedestrians safe routing to bypass areas where the risk of COVID-19 transmission is high. In other words, the framework recommends a pedestrian walking route along which a social distancing is guaranteed and close contact with other people is avoided. As shown in the figure, the proposed approach includes four steps: First, the framework identifies the IoT devices located in the area of interest and then establishes social graphs interconnecting these devices using different social IoT relations. Then, a community detection algorithm is applied to the SIoT relationship graphs to determine different communities of IoT devices. The third step is to compute different scores representing each street’s safety level or segment of a street in the area of interest according to the nearby detected social communities. Finally, in the last step, the city map is transformed into a weighted undirected graph to which we apply the Dijkstra algorithm in order to determine a route characterized by a certain level of safety. The framework will then deliver the trajectories to the user, e.g., via a mobile application for the best route to follow to reach a destination. The proposed routing approach takes into account the mobility of IoT devices and may update the recommended route regularly by repeating the aforementioned process. Simulation results applied on a real-world IoT data set have shown the ability of the proposed approach in achieving trade-offs between both safest and shortest paths according to the pedestrian preference.
Topic Modeling and Progression of American Digital News Media During the Onset of the COVID-19 Pandemic
Currently, the world is in the midst of a severe global pandemic, which has affected all aspects of people’s lives. As a result, there is a deluge of COVID-related digital media articles published in the United States, due to the disparate effects of the pandemic. One of the main debates that persists in the United States is the tradeoff between the economic and health costs of the measures taken to control the spread of the virus. This debate has intensified as the pandemic has progressed and a large volume of information has been generated by many media outlets having diverse perspectives. The fast-growing distrust of the media and expert opinion as well as the effects of fake and misleading information on the web make the audience struggle to consume the media products in a reasonable time. In this project, we propose a generic NLP pipeline that collects, filters, and summarizes articles from various media sources with the aim of modelling the evolution of their discussion about recent COVID-19 pandemic over time by leveraging topic modeling on the summarized articles. The aim of this model is to provide an automated tool for readers to quickly consume the essence of the stories covered by a large multiplicity of articles, while also highlighting the biases that are prominent in each institution’s reporting. The developed NLP-based framework is composed essentially of three main steps as shown in the figure. After aggregating the news sources by events, we employ text summarization algorithms to distill the articles to their essential information. Afterwards, we cluster the summaries of the articles and regroup them into groups containing articles discussing similar topics. Finally, we employ a topic modelling method with the aim of discovering the main “topic” of discussion occurring in the collection of documents of each cluster. The aim is to gain insight about the interest of various media outlets during the onset of the COVID-19 Pandemic. We utilize the developed automated pipeline to analyze the coverage of six outlets (New York Times, New York Post, CNN, Washington Post, CNBC, and ABC) and its evolution over time. We notice that domestic issues dominate the coverage, with the combination of domestic health, economics, and politics comprising at least two-thirds of all articles from each source, starting from the third month of the pandemic. Initially, the focus was essentially about international health issues as the virus started spreading in Europe.