Multi-branch sustainable convolutional neural network for disease classification

Pandemic and natural disasters are growing more often, imposing even more pressure on life care services and users. There are knowledge gaps regarding how to prevent disasters and pandemics. In recent years, after heart disease, corona virus disease-19 (COVID-19), brain stroke, and cancer are at their peak. Different machine learning and deep learning-based techniques are presented to detect these diseases. Existing technique uses two branches that have been used for detection and prediction of disease accurately such as brain hemorrhage. However, existing techniques have been focused on the detection of specific diseases with double-branches convolutional neural networks (CNNs). There is a need to develop a model to detect multiple diseases at the same time using computerized tomography (CT) scan images. We proposed a model that consists of 12 branches of CNN to detect the different types of diseases with their subtypes using CT scan images and classify them more accurately. We proposed multi-branch sustainable CNN model with deep learning architecture trained on the brain CT hemorrhage, COVID-19 lung CT scans and chest CT scans with subtypes of lung cancers. Feature extracted automatically from preprocessed input data and passed to classifiers for classification in the form of concatenated feature vectors. Six classifiers support vector machine (SVM), decision tree (DT), K-nearest neighbor (K-NN), artificial neural network (ANN), naïve Bayes (NB), linear regression (LR) classifiers, and three ensembles the random forest (RF), AdaBoost, gradient boosting ensembles were tested on our model for classification and prediction. Our model achieved the best results on RF on each dataset. Respectively, on brain CT hemorrhage achieved (99.79%) accuracy, on COVID-19 lung CT scans achieved (97.61%), and on chest CT scans dataset achieved (98.77%). © 2023 Wiley Periodicals LLC.

Smart Campus Framework: A Solution for New Normal Education System

The Covid-19 pandemic has affected all aspects of human life and has even forced humans to shift their life habits, including in the world of education. The learning model must shift from the traditional to modern synchronous or asynchronous models with information technology-based applications. This condition is known as the New Normal era in the education system. Y Generation and Z Generation as educational objects are now very close to technology, especially information technology, including in the teaching and learning process, so there is no need for extra effort in this regard. Therefore, it is essential to create a learning environment under the characteristics of this generation and can also support the new normal era of the education system. We offer the concept of a smart campus framework that integrates an IT-based learning system and a hybrid smart classroom system as a modern education method in an educational scenario that promises to accelerate quality education without leaving a good learning process. This article designs the concept of a smart campus framework that will accommodate a learning model that will accelerate the improvement of the quality of education through smart learning solutions and smart blended learning systems. We also offer achievements in improving service performance through smart academic services solutions and accommodating the management of existing classroom resources through smart equipment system solutions. This framework is designed to automatically solve all university-level education system problems based on multimedia and integrated with websites and information systems used on campus. © 2021 IEEE.

The attitude and behavior related to social distancing as prevention transmission of coronavirus disease 19 among adolescents living in coastal area of indonesia

BACKGROUND: The majority of adolescents living in the coastal area are Muslim who has a habit of carrying out worship and cultural activities in the congregation. They are in the school-age period and have received sufficient information about social distancing as prevention of coronavirus disease 2019 (COVID-19) transmission. AIM: This study aimed to explore the attitude and behavior related to social distancing in response to prevent COVID-19 transmission among adolescents living in the coastal area, Indonesia. METHODS: This is a cross-sectional study that invited adolescents in the coastal area, Madura, East Java, Indonesia, as participants. Data were collected conveniently through an online questionnaire. Univariate and bivariate analyses were performed for the analysis of the data. RESULTS: A total of 224 participants completed the survey. A number of participants disagreed to certain attitudes related to social distancing including praying from home (21%), wearing a mask (15%), and not organizing mass gathering events (9%). Furthermore, as many as 44% of participants refused to facilitate infected people to do self-isolation. CONCLUSION: The attitudes related to the social distancing of adolescents living in the coastal area might be influenced by culture and Islam reference. Therefore, a religious approach is considered important to be involved in the preparation of strategic actions in preventing the transmission of COVID-19 through social distancing. The refusal of participants to isolate an infected person might be caused by a limited knowledge about COVID-19 prevention. The related institutions need to conduct a major health socialization to prevent COVID-19 transmission through social distancing.

Sentiment Analysis on COVID Tweets: An Experimental Analysis on the Impact of Count Vectorizer and TF-IDF on Sentiment Predictions using Deep Learning Models

Due to the higher popularity of social media and its excessive use, COVID-19 has become the topic of the talk since 2019 and it has become a cause of stress, anxiety and depression for people around the world. In this article, we experimented with different classifiers on COVID data to train deep neural networks to enhance the accuracy rate using two popular word embedding techniques: Count Vectorizer and Term Frequency-Inverse Document Frequency. Finally, we compare accuracies and observe that TF-IDF comes out to be more efficient as compared to Count Vectorizer where datasets are of huge volume and in our case i.e., for covid19 tweets, both vectorizers have been approximately similar in performance except on Single Layer Perceptron where Count Vectorizer results in 10% more efficiency in terms of accuracy. © 2021 IEEE.

Road toward rapid-molecular point of care test to detect novel SARS-coronavirus 2019 (COVID-19): Review from updated literature.

Coronavirus disease 2019 (COVID-19) named by the WHO as a result of the global public health emergency. COVID-19 is caused by a new coronavirus named as novel coronavirus (2019-nCOV). From the first case reported in December 2019 it is now a pandemic situation and a major public health emergency. The COVID-19 transmission rate is very high, infecting two to three persons on average with contact to an already infected person. There is a need for the health system, specially in developing countries such as in Pakistan, to combat such a novel disease by rapid, accurate, and high quality diagnostic testing in order to screen suspected cases and also surveillance of the disease. A rapid, accurate and low-cost diagnostic point-of-care device is needed for timely diagnosis of COVID-19 and is essential to combat such outbreaks for compelling preventive measures against the disease spread. This review is to highlight the importance of point-of-care diagnostics device for robust and accurate diagnosis of COVID-19 in physician offices and other urgent healthcare-type settings and encourage academics and stake holders towards advancement in order to control outbreaks and develop the public health surveillance system.