Mobile users can open program in new tab for better viewing.

Open program in new tab

Day 1 04/12/2020
Room #1

Opening message by General Chair 09:00 - 09:05

Prof. Dr. Fadi Al-Turjman

Welcome message by EAI 09:00 - 09:05

Aleksandra Sledziejowska

Welcome message by EAI Community Manager 09:05 - 09:10

Michal Dudic

Session 1 09:10 - 10:30

Moderator: Bashiir Abdirahman
09:10 - 09:25
Covid-19 Detection on CT Scans using Local Binary Pattern and Deep Learning

X-ray and CT scans show lungs, and images can be used to differentiate positive and negative cases. Analyzing these scans using an artificial intelligent method might provide fast and accurate COVID-19 detection. In this paper, a local binary pattern based deep learning method is proposed for the detection of COVID-19 infection on CT Scans. The proposed technique generates local binary pattern (LBP) representations of the CT scans, and then these representations are modeled using fine-tuned models. The fine-tuned models are AlexNet, VGG, ResNet-18, ResNet-50, MobileNetV2, and DensNet-121. We show that the proposed local binary pattern based deep learning model provides higher performance than classic deep learning models for COVID-19 detection. The classification performance of the method provides $90\%$ AUC value for COVID-19 detection.
Authors: Sertan Serte (Near East University, Nicosia, Turkey), Fadi AL-TURJMAN (Near East University, Nicosia, Turkey),
Hide Authors & Abstract

Show Authors & Abstract
09:25 - 09:55
Automated Segmentation of COVID-19 Lesion from Lung CT Images using U-Net Architecture

The pneumonia caused by the novel Coronavirus Disease (COVID-19) is emerged as a global threat and considerably affected a large population globally irrespective of their age, race and gender. Due to its rapidity and the infection rate, the World Health Organization (WHO) declared this disease as the pandemic. The proposed research work aims to develop an automated COVID-19 lesion segmentation system using the Convolutional Neural Network (CNN) architec-ture called the U-Net. The traditional U-Net scheme is employed to examine the COVID-19 infection present in the lung CT images. This scheme is implemented on the benchmark COVID-19 images existing in the literature (300 images) and the segmentation performance of the U-Net is confirmed by computing the essen-tial performance measures using a relative assessment among the extracted lesion and the Ground-Truth (GT). The overall result attained with the proposed study confirms that, the U-Net scheme helps to get the better values for the performance values, such as Jaccard (>86%), Dice (>92%) and segmentation accuracy (>95%).
Authors: Seifedine Kadry (Beirut Arab University, Lebanon), Fadi Al-Turjman (Near East University, Nicosia, Turkey), V. Rajinikanth (St. Joseph’s College of Engineering, Chennai, India),
Hide Authors & Abstract

Show Authors & Abstract
09:55 - 10:30
A new Blood Pressure prediction approach using PPG sensors : subject specific evaluation over a long-term period.

In this paper, a new approach for predicting the blood pres- sure (BP) from the photoplethysmogram (PPG) signal is proposed related with a new original public dataset. The originality of the dataset is based on the fact that subjects are periodically monitored over weeks, while public datasets consider short acquisition periods. The proposed BP prediction approach uses key frequencies in the spectrum of the PPG signal isolated using the LASSO algorithm, then a predictive model is constructed. The eciency of the proposed methodology is evaluated on experimental data recorded over a long time period. Moreover, an evaluation of the various temporal markers of the PPG signal that have been proposed in the literature is conducted on the same data set. It is showed that only few of these temporal markers are useful for the prediction of the systolic and diastolic blood pressures. The results highlight that better blood pressure predictions are obtained when using the spectrum of the PPG signal rather than optimally selected temporal markers.
Authors: Franck Mouney (Angers University, Angers, France), Teodor Tiplica (Angers University, Angers, France), Jean-Baptiste Fasquel (Angers University, Angers, France), Magid Hallab (Clinique Bizet, Service de Cardiologie, Paris), Mickael Dinomais (LARIS Laboratory, Angers, France),
Hide Authors & Abstract

Show Authors & Abstract

Coffee break 10:30 - 10:40

Session 2 10:40 - 12:20

Moderator: Bashiir Abdirahman
10:40 - 11:15
5G network Slicing Technology and its Impact on COVID-19: A Comprehensive Survey

At the end of 2019, no one could have thought how the world will dramatically change. A new outbreak has emerged causing millions of people to go into lockdown for their own safety. World Health Organization (WHO) has later announced this outbreak of Coronavirus Disease 2019 (COVID-19) as pandemic, this has caused huge stress to medical staff. The need for digital connectivity between communities and nations has arisen. Digital revolutionary services like telehealth, telemedicine, eVisit, etc. play a vital role in reducing the risk and fighting the spread of the pandemic The industry and academics accept 5G as the potential network capable of serving vertical applications of next generation with these specific service needs. In order to achieve this dream, the physical network must be separated into several separate functional blocks of various sizes and systems devoted to specific kind of services depending on their needs (a full slice for large eHealth apps, healthcare servers, IoT apps, smart cities and so on). Network slicing (NS) was described as the foundation of fast-growing 5G. Although, as its standardization advances and consolidation, few literatures which address main concepts, research challenges and service enablers, in a detailed way are available. In this paper these aspects should be provided and discussed. A brief overview about this emerging technology should be given.
Authors: Bashir Hussein (Near East University), Fadi AL-TURJMAN (Research Center for AI and IoT, Near East University, Nicosia),
Hide Authors & Abstract

Show Authors & Abstract
11:15 - 11:50
An Empirical Study of Trilateration and Clustering for Indoor Localization and Trend Prediction

With the drastic increase in population and services lever- aging the Internet of Things (IoT), it has become an urgent problem on how to e ectively monitor people and things. Trilateration aims to address this issue by determining the location of moving objects using distances between the object and multiple stations. This paper presents an e ective way of tracking objects using trilateration in a closed space. We analyze the data generated from the stations which consisted of co- ordinates, timestamps, and identi ers. After running a clustering algo- rithm on the data, we infer information on the behavior of the object, frequently visited places, and predict objects's pattern. Field test results at Santa Clara University demonstrate that the model has an average accuracy of 73%.
Authors: Aarth Tandel (Santa Clara University, USA), Anvesh Chennupati (Santa Clara University, USA), Behnam Dezfouli (Santa Clara University, USA),
Hide Authors & Abstract

Show Authors & Abstract
11:50 - 12:20
IoT and AI for COVID-19 in Scalable Smart Cities

COVID-19 which is also known as the novel coronavirus started from China. Motivated by continuous advancement and employments of the Artificial Intelligence (AI) and IoT in various regions, in this study we focus on their underlining deployment in responding to the virus. In this survey, we sum up the current region of AI applications in clinical associations while battling COVID-19. We moreover survey the component, challenges, and issues identified with these technologies. A review was made in requesting AI and IoT by then recognizing their applications in engaging the COVID-19. In like manner, emphasis has been made on a region that utilizes cloud computing in combating diverse similar diseases and the COVID-19 itself. The investigated procedures set forth drives clinical information examination with an exactness of up to 95%. We further end up with a point by point discussion about how AI utilization can be in an ideal situation in battling diverse diseases. This paper gives masters and specialists new bits of information in which AI and IoT can be utilized in improving the COVID-19 situation, and drive further assessments in ending the flare-up of the infection.
Authors: Adedoyin Ahmed Hussain (Near East University, Nicosia, Turkey), Barakat Dawood (Near East University, Nicosia, Turkey), Fadi Al-Turjman (Near East University, Nicosia, Turkey),
Hide Authors & Abstract

Show Authors & Abstract

Lunch break 12:20 - 13:00

Session 3 13:00 - 14:25

Moderator: Bashiir Abdirahman
13:00 - 13:30
Security and privacy issues associated with Coronavirus diagnosis and prognosis

The urgency of the need to manage and find a cure for the COVID-19 has made it necessary to share information. However, sharing information involves potential risks that are inevitably likely to infringe individual privacy. Therefore, whether permissible under extenuation circumstances or not, sharing and handling of information for medical diagnosis and prognosis need consideration without ignoring the need to protect privacy. This makes it important to strike a balance between protecting individual privacy and collecting information to combat the virus, the responsibility for doing so rests with the state. However, circumstances in which the COVID-19 pandemic appears to be accelerating, the medical professionals and the government seem to be focusing more on collecting information that could be used to limit the extent of the outbreak and mitigate the risks. Such a strategy overrides perception of the need to protect personal privacy. This paper investigates the security and privacy challenges associated with SARS-CoV-2 diagnosis and prognosis using case studies from different countries.
Authors: Vibhushinie Bentotahewa (Cardiff Metropolitan University), Chaminda Hewage (Cardiff Metropolitan University), Jason Williams (Cardiff Metropolitan University),
Hide Authors & Abstract

Show Authors & Abstract
13:30 - 13:50
Approach for the development of a system for COVID-19 preliminary test

Nowadays, Coronavirus is the biggest challenge of medicine. This problem is divided into two sectors: health and economy. In relation to health, there has been an alarming exponential rise in deaths, those who do not belong to the risk group are precisely those who contaminate and lead to disease. The economy also bleeds globally, and companies are failing. Thus, thousands of people are out of work. This paper is focused on predicting whether an individual is possible with symptoms of COVID-19 and proposing the use of technology. In a context of ambient assisted living, it can save thousands of lives and builds the world economy. Therefore, a preliminary mobile diagnosis may provide a reduction in government costs and a potential alternative to the existing tests. In view of all that has been mentioned, sensors are the best solution to detect the symptoms of the disease. This project will try to identify different symptoms, such as high body temperature, breathing difficulties, and cough. The sensors that may be used to identify these symptoms are a thermometer, an electroencephalogram (EEG) sensor, an electromyography (EMG) sensor and an electrodermal activity (EDA) sensor.
Authors: Ticiana Capris (Polytechnic Institute of Viseu, Viseu, Portugal), Pedro Melo (Polytechnic Institute of Viseu, Viseu, Portugal), Pedro Pereira (Polytechnic Institute of Viseu, Viseu, Portugal), José Morgado (Polytechnic Institute of Viseu, Viseu, Portugal), Nuno Garcia (University of Beira Interior, Covilhã, Portugal), Ivan Pires (University of Beira Interior, Covilhã, Portugal),
Hide Authors & Abstract

Show Authors & Abstract
13:50 - 14:25
COVID-19 Patient Care: A Content-Based Collaborative Filtering Using Intelligent Recommendation Systems

COVID-19 is a more transferable illness caused by a new novel coronavirus. It is highly emerging with efficient biosensors such as sensitive and selective that afford the diagnostic tools to infer the disease at early-stage. It can maintain a personalized healthcare system to evaluate the growth of disease under proper patient care. To discover as a personalized technology, the healthcare system prefers a collaborative filtering. It can effectively deal with cold-start and sparse-data to conduct useful extensions. Due to the continuous expansion of scaling data in a medical scenario, content-based, collaborative filtering, and similarity metrics are preferred. It relies on the most similar social users or threats when the information is large. A huge number of neighbors gain importance to obtain a set of users with whom a target user is likely to match. Forming communities reveal vulnerable users and also reduce the challenges of collaborative filtering like data-sparsity and cold-start problems. Thus, this framework proposes a content-based collaborative filtering using intelligent recommendation systems (CCF-IRS) that is based on high correlation and shortest neighbor in the social community. The result is shown that the proposed CCF-IRS achieves better accuracy than the existing algorithms.
Authors: Deebak B D (School of Computer Science and Engineering, Vellore Institute of Technology, Vellore 632014, India.), Fadi AL-TURJMAN (Research Center for AI and IoT, Near East University, Nicosia),
Hide Authors & Abstract

Show Authors & Abstract

Closing remarks by Fadi Al-Turjman 14:25 - 14:30

Best paper announcement