ABSTRACT
Misleading health information is a critical phenomenon in our modern life due to advance in technology. In fact, social media facilitated the dissemination of information, and as a result, misinformation spread rapidly, cheaply, and successfully. Fake health information can have a significant effect on human behavior and attitudes. This survey presents the current works developed for misleading information detection (MLID) in health fields based on machine learning and deep learning techniques and introduces a detailed discussion of the main phases of the generic adopted approach for MLID. In addition, we highlight the benchmarking datasets and the most used metrics to evaluate the performance of MLID algorithms are discussed and finally, a deep investigation of the limitations and drawbacks of the current progressing technologies in various research directions is provided to help the researchers to use the most proper methods in this emerging task of MLID.
ABSTRACT
The fast growth of technology in online communication and social media platforms alleviated numerous difficulties during the COVID-19 epidemic. However, it was utilized to propagate falsehoods and misleading information about the disease and the vaccination. In this study, we investigate the ability of deep neural networks, namely, Long Short-Term Memory (LSTM), Bi-directional LSTM, Convolutional Neural Network (CNN), and a hybrid of CNN and LSTM networks, to automatically classify and identify fake news content related to the COVID-19 pandemic posted on social media platforms. These deep neural networks have been trained and tested using the 'COVID-19 Fake News';dataset, which contains 21,379 real and fake news instances for the COVID-19 pandemic and its vaccines. The real news data were collected from independent and internationally reliable institutions on the web, such as the World Health Organization (WHO), the International Committee of the Red Cross (ICRC), the United Nations (UN), the United Nations Children's Fund (UNICEF), and their official accounts on Twitter. The fake news data were collected from different fact-checking websites (such as Snopes, PolitiFact, and FactCheck). The evaluation results showed that the CNN model outperforms the other deep neural networks with the best accuracy of 94.2%.
ABSTRACT
In this study, an effective local minima detection and definition algorithm is introduced for a mobile robot navigating through unknown static environments. Furthermore, five approaches are presented and compared with the popular approach wall-following to pull the robot out of the local minima enclosure namely;Random Virtual Target, Reflected Virtual Target, Global Path Backtracking, Half Path Backtracking, and Local Path Backtracking. The proposed approaches mainly depend on changing the target location temporarily to avoid the original target’s attraction force effect on the robot. Moreover, to avoid getting trapped in the same location, a virtual obstacle is placed to cover the local minima enclosure. To include the most common shapes of deadlock situations, the proposed approaches were evaluated in four different environments;V-shaped, double U-shaped, C-shaped, and cluttered environments. The results reveal that the robot, using any of the proposed approaches, requires fewer steps to reach the destination, ranging from 59 to 73 m on average, as opposed to the wall-following strategy, which requires an average of 732 m. On average, the robot with a constant speed and reflected virtual target approach takes 103 s, whereas the identical robot with a wall-following approach takes 907 s to complete the tasks. Using a fuzzy-speed robot, the duration for the wall-following approach is greatly reduced to 507 s, while the reflected virtual target may only need up to 20% of that time. More results and detailed comparisons are embedded in the subsequent sections.
ABSTRACT
The aim of the study was to assess the degree of aerosolisation in different chest drainage systems according to different air leak volumes, in a simulated environment. This novel simulation model was designed to produce an air leak by passing air through and agitating a fluorescent fluid. The air leak volume and amount of fluorescent fluid were tested in various combinations and aerosolisation was assessed at 10-minute intervals using the ultraviolet light. The following chest drainage systems were compared: (1) single-chamber chest drainage system, (2) 3-compartment wet-dry suction chest drainage system, (3) digital drainage and monitoring system. The impact of suction (-2 and -4 kPa) in generating aerosolised particles was tested as well. A total number of 187 of 10-minute interval measurements were performed. The single-chamber chest drainage system generated the largest number of aerosolised particles at different air leak volumes and drainage output. The 3-compartment wet-dry suction system and the digital drainage and monitoring system did not generate any identifiable aerosolised particles at any of the air leak or drain output volumes considered. Suction applied to the chest drainage systems did not have an effect on aerosolisation. Aerosol generation in the simulated air-leak model demonstrated the potential risk of SARS-CoV-2 spread in the clinical setting. Full personal protective equipment must be used in patients with an air leak. Single-chamber chest drainage system generates the highest rate of aerosolised particles and it should not be used as an open system in patients with an air leak.