A CNN Transfer Learning -Electrocardiogram (ECG) Signal Approach to Predict COVID-19

Deep learning is increasingly gaining traction in cutting-edge medical sciences such as image classification, and genomics due to the high computational performance and accuracy in evaluating medical data. In this study, we investigate the cardiac properties of ECG Images and predict COVID-19 in a binary classification of patients who tested positive for COVID-19 and Normal Persons who tested negative. We analyzed the electrocardiogram (ECG) images by preprocessing the ECG data and building an ECG- Deep Learning- COVID-19 (ECG-DL-COVID) classifier to predict disease. The deep learning models in our experiments constituted CNN, Multi-Layer Perceptron (MLP), and Transfer Learning. Performance evaluation was done to compare the effectiveness of the proposed methodologies with other COVID-19 deep learning-related works. In the three experiments, we achieved an 87% prediction accuracy for MLP, a 90% prediction for CNN and a 93.8% prediction for Transfer Learning. Experimental results and performance evaluation show that the proposed models outperformed previous deep-learning models in the prediction of COVID-19 by a considerable margin. © 2023 IEEE.

Precision Diagnosis to Discriminate Covid-19 and Pneumonia using Mixed-data Model based on Custom Neural Networks

Classifying Covid-19 and Pneumonia is one of the most important and challenging tasks in the field of the medical sector since manual classification with human assistance can lead to incorrect prediction and diagnosis. Additionally, it is a difficult operation when there is a lot of data that need to be analyzed thoroughly. Due to the similarity in symptoms as well as in chest X-ray images of Covid-19 and Pneumonia diseases, it is difficult to distinguish those. The study presents a technological solution to build a mixed-data model using customized neural networks to discriminate between Covid-19 and Pneumonia. The proposed method is applied to the chest X-ray images and symptoms of patients of Covid-19 and Pneumonia. This helps to perform immediate prediction of Covid-19 and Pneumonia providing fast and specialized treatment to the patients appropriately. This prediction also helps the radiologist or doctors in making quick decisions. In this work, imaging data (such as Chest X-ray images) and text data (such as disease symptoms like cough, body pain, short breathing, fever, etc.) are taken for detecting Covid-19, Pneumonia and Normal patients. Data Synthesis is carried out due to the unavailability of mixed data and it has created dataset of 450 entries of Covid-19, Normal and Pneumonia cases. The goal is to design a system that accurately classifies Covid19, Pneumonia, and Normal patients by utilizing convolutional neural networks (CNN) and multi-layer perceptron (MLP) algorithms. An accuracy of 93.33% is obtained for the mixed-data model using a deep neural network, that is designed by combining custom CNN and MLP architectures. © 2022 IEEE.

Aspect-Based Sentiment Analysis with Semi-Supervised Approach on Taiwan Social Distancing App User Reviews

Sentiment analysis has a critical role to reveal an opinion in a text-based form. Therefore, we exploit this analysis to discover the sentiment polarity of Taiwan Social Distancing mobile application. This paper proposes a semi-supervised scheme for annotating this mobile application's reviews. The semi-supervised scheme utilized a combination of numeric rating and lexicon-based sentiment. In addition, we also perform the sentiment analysis on an aspect-based level. Based on the experiment, we decide to select three aspects to be analyzed. This paper also evaluates the proposed scheme by implementing bidirectional encoder representations from transformers (BERT) and multilayer perceptron (MLP) as the classification model using the sentiment label of the proposed scheme. The result shows that the annotation of the proposed scheme outperforms the data annotation using counterpart models. © 2023 IEEE.

Hyperparameter Search for CT-Scan Classification Using Hyperparameter Tuning in Pre-Trained Model CNN With MLP

The common approach to find best hyperparameter in CNN training is grid search, by observing one set to another of hyperparameter for obtaining the best result. However, this approach is considered inefficient, time-consuming, and ineffectively computational. In this study, we are observing 2 hyperparameter tuning algorithms (bayesian optimization and random search) in search of the best hyperparameter for CT-Scan classification case. The used dataset is COVID-19 and non-COVID-19 lung CT-Scans. Several CNN architectures are also used such as: InceptionV4, MobileNetV3, and EfficientnetV2 with additional multi-layer perceptron on top layers. Based on the experiments, model EfficientnetV2-L architecture using hyperparameter from bayesian-optimization can outperform other models, with batch size of 32, learning rate of 0.01, dropout 0.5, Adam optimizer and SoftMax activation, resulting in the accuracy rate of 0.94% and a model training time of 50 minutes 40 seconds. © 2022 IEEE.

Diagnosis of COVID-19 from CT Images and Respiratory Sound Signals Using Deep Learning Strategies

COVID-19 has been a major issue among various countries, and it has already affected millions of people across the world and caused nearly 4 million deaths. Various precautionary measures should be taken to bring the cases under control, and the easiest way for diagnosing the diseases should also be identified. An accurate analysis of CT has to be done for the treatment of COVID-19 infection, and this process is complex and it needs much attention from the specialist. It is also proved that the covid infection can be identified with the breathing sounds of the patient. A new framework was proposed for diagnosing COVID-19 using CT images and breathing sounds. The entire network is designed to predict the class as normal, COVID-19, bacterial pneumonia, and viral pneumonia using the multiclass classification network MLP. The proposed framework has two modules: (i) respiratory sound analysis framework and (ii) CT image analysis framework. These modules exhibit the workflow for data gathering, data preprocessing, and the development of the deep learning model (deep CNN + MLP). In respiratory sound analysis framework, the gathered audio signals are converted to spectrogram video using FFT analyzer. Features like MFCCs, ZCR, log energies, and Kurtosis are needed to be extracted for identifying dry/wet coughs, variability present in the signal, prevalence of higher amplitudes, and for increasing the performance in audio classification. All these features are extracted with the deep CNN architecture with the series of convolution, pooling, and ReLU (rectified linear unit) layers. Finally, the classification is done with a multilayer perceptron (MLP) classifier. In parallel to this, the diagnosis of the disease is improved by analyzing the CT images. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

Multilayer Perceptron Neural Network Approach to Classifying Learning Modalities Under the New Normal

Because of community quarantines and lockdowns during COVID–19 times, the Philippine’s Department of Education (DepEd) implemented blended learning (BL) both online and offline distance learning modalities (LM) among basic educational institutions in the hope of continuing learners’learning experiences amidst the pandemic. Learners’LM are classified through the use of an Algorithm for Learning Delivery Modality as recommended by DepEd. Based on initial investigation, mismatches in learners’LM were, however, observed, resulting in learners’massive shifting from one LM to another in the middle of the school year. In this study, we introduced an approach to classifying learner’s LM using machine learning (ML) techniques. We compared the effectiveness of five ML classifiers, namely the random forest (RF), multilayer perceptron neural network (MLP NN), K-nearest neighbor (KNN), support vector machine (SVM), and Naïve Bayes (NB). Learner’s enrolment and survey form (LESF) data from the repository of a local private high school in the Philippines is used in model formulation. We also compared three existing feature selection (FS) algorithms (recursive feature elimination (RFE), Boruta algorithm (BA), and ReliefF)–integrated into the five ML classifiers as data feature reduction techniques. Results show that the combination of MLP NN and BA yielded a considerably high performance among the rest of the formulated models. Sensitivity analysis revealed that asynchronous LM is most sensitive to “existing health condition”feature, modified asynchronously, is highly characterized by low educational attainment and unstable employment status of parents or guardians, while synchronous learners have high socio–economic status as compared to other LM. IEEE

Analyzing Sensitive Factors Affecting Online Academic Performance in the New Normal: A Machine Learning Perspective

Online distance learning (ODL) is one extension of the distance learning approach introduced by the Department of Education (DepEd) as part of its learning continuity in the new normal (COVID - 19 times). Despite the advantages brought by online learning in continuing learners' learning experiences and improving learners' academic performance during the pandemic, it is still of vital importance to examine what factors are sensitive to changes in learner's online academic performance. In this study, sensitive factors affecting online academic performance are examined through the lens of machine learning (ML) methods: Boruta algorithm (BA) for feature selection;multilayer perceptron neural network (MLP NN) for model formulation;and partial derivatives method (PDM) for sensitivity analysis. Data used in the analysis are responses in the survey participated by N = 978 senior high and junior school students of a private high school institution in the Philippines. Out of eighteen factors considered in the analysis, BA revealed only six relevant factors that contributes greater information to changes in student's online academic performance. Formulated MLP NN model achieved a high testing accuracy of 0.932 with a kappa coefficient of 0.891 and an f - measure of 0.924, that aided the sensitivity analysis using PDM to have better results. Sensitivity analysis showed that motivation and mental well- being are the most sensitive factors affecting both below average and above average online academic performance. © 2022 IEEE.

Face Completion with Multi-Output Estimators

Since the beginning of the COVID-19 pandemic, images of faces with obscured bottom halves have become more common due to masking. Now more than ever, end-users are looking toward machine learning and data science to create high-quality replacements for missing facial data. For face completion, we evaluate multiple machine learning algorithms, including Decision Trees, K-Nearest Neighbors, and Support Vector Machines. Since most of the existing work in this field uses deep learning, we explore the impact of using multiple deep learning techniques and use them as a point of comparison. Our study indicates that despite the conventional norm that deep learning algorithms outperform their machine learning counterparts, the non-deep learning techniques perform better for this application.11Code is available at https://github.com/nickfons/fcwmoe. © 2022 IEEE.

Improving Radiology Report Generation via Object Dropout Strategy and MLP-based Captioner

Recently, automatically generating radiology reports has been addressed since it can not only relieve the pressure on doctors but also avoid misdiagnosis. Radiology report generation is a fundamental and critical step of auxiliary diagnosis. Due to the COVID-19 pandemic, a more accurate and robust structure for radiology report generation is urgently needed. Although radiology report generation is achieving remarkable progress, existing methods still face two main shortcomings. On the one hand, the strong noise in medical images usually interferes with the diagnosis process. On the other hand, these methods usually require complex structure while ignoring that efficiency is also an important metric for this task. To solve the two aforementioned problems, we introduce a novel method for medical report generation, the termed attention-guided object dropout MLP(ODM) model. In brief, ODM first incorporates a tailored pre-trained model to pre-align medical regions and corresponding language reports to capture text-related image features. Then, a fine-grained dropout strategy based on the attention matrix is proposed to relieve training pressure by dropping content-irrelevant information. Finally, inspired by the lightweight structure of Multilayer Perceptron(MLP), ODM adopts an MLP-based structure as an encoder to simplify the entire framework. Extensive experiments demonstrate the effectiveness of our ODM. More remarkably, ODM achieves state-of-the-art performance on IU X-Ray, MIMIC-CXR, and ROCO datasets, with the CIDEr-D score being increased from 26.8% to 41.4%, 21.1% to 30.2%, and 9.1% to 19.3%, respectively. © 2022 IEEE.

Predicting the upshot of covid-19 on crude-oil prices in nigeria using mlparima model

Researchers and investors have been paying close attention to the application of Artificial Intelligence models to the economics, agriculture and other fields in recent years. This study uses a Multilayer Perceptron Artificial Neural Network to anticipate the effect of covid-19 on crude-oil prices, continuing the deep learning trend and also applied the use of time series model known as Autoregressive Integrated Moving Average (ARIMA) to validate the result gotten from MLP-ANN. The results produced accurately predicted crude oil prices, and covid-19 data was also analyzed, as well as the association between crude-oil prices and covid-19. Because of the substantial causative association between the coronavirus (number of confirmed cases), crude oil prices, this study is intriguing. Ten years forecast was done using both MLP-ANN and ARIMA and from result gotten, MLP-ANN has accuracy of 96% while ARIMA has 39% accuracy. © 2022 IEEE.

Analysis for Data Mobility and Covid-19 Positive Rate with Multilayer Perceptron

COVID-19 has been affecting human mobility to avoid the risk of infection. Movement restriction was one of the government policies to reduce the rate of infection. However, the mobility was still occurred to be recorded during the policy. This action has led to the problem of the number of beds on hospital have to be prepared for the peak of infection. This study developed a model using Multilayer perceptron as a useful theorem in regression analysis to see the fitness approximation over this problem. Five layers neural networks combination have been used to see the performance of the model to reach the best fit of the model. The process of the study includes data acquisition of the influence of community mobility over the positive number of COVID-19, managed hyperparameters, and calculate the results of prediction in the form of the length of time the patient would be infected with COVID-19 from 2020 to 2021. This study found that the infection was happening mostly after 12 days of human mobility activity in public area such as ATM, market, park, and any public area recorded by Google mobility data. It was also showed the number of infections after 12 days in order to prepare the number of beds on hospital. Furthermore, this study found the best model with smallest loss value on 0.01452617616472448 with the gap number of infection from public area as much as 77 persons. © 2022 IEEE.

Detecting COVID-19 from Lung Computed Tomography Images: A Swarm Optimised Artificial Neural Network Approach

COVID-19 has affected many people across the globe. Though vaccines are available now, early detection of the disease plays a vital role in the better management of COVID-19 patients. An Artificial Neural Network (ANN) powered Computer Aided Diagnosis (CAD) system can automate the detection pipeline accounting for accurate diagnosis, overcoming the limitations of manual methods. This work proposes a CAD system for COVID-19 that detects and classifies abnormalities in lung CT images using Artificial Bee Colony (ABC) optimised ANN (ABCNN). The proposed ABCNN approach works by segmenting the suspicious regions from the CT images of non-COVID and COVID patients using an ABC optimised region growing process and extracting the texture and intensity features from those suspicious regions. Further, an optimised ANN model whose input features, initial weights and hidden nodes are optimised using ABC optimisation classifies those abnormal regions into COVID and non-COVID classes. The proposed ABCNN approach is evaluated using the lung CT images collected from the public datasets. In comparison to other available techniques, the proposed ABCNN approach achieved a high classification accuracy of 92.37% when evaluated using a set of 470 lung CT images. Author

Sentiment Analysis Twitter Based Lexicon and Multilayer Perceptron Algorithm

As the COVID-19 pandemic begins, the perception of online lectures according to students needs to be researched, to find out whether students have positive or negative sentiments regarding online lectures so far. Therefore, it is necessary to conduct research on sentiment analysis about online lectures taken according to student comments via tweets on the Twitter platform. The extracted tweets data will then be analyzed using machine learning to predict student sentiment about online lectures. The multilayer perceptron algorithm is used in research because it can solve non-linear problems well and is easy to implement without complicated parameter settings. However, multilayer perceptron is a supervised learning algorithm so it requires data that has been labeled/classified. So that to label the data of online lecture tweets, lexicon-based sentiment analysis is used. A total of 2,391 Indonesian-language tweets were successfully extracted. The results of the study using lexicon-based showed that as many as 63.9% gave negative sentiments towards online lectures, and 29% gave positive sentiments while the remaining 7.1% gave neutral sentiments. Meanwhile, the prediction ability of the multilayer perceptron algorithm for tweets data in this online lecture produces an accuracy of 71%. © 2022 IEEE.

A Deep learning based Safe Travel Advisory Tool for Covid-19

Looking at the massive spread of SARS CoV2(COVID-19), it not only requires medical solutions at this point but different alternatives must also be examined to prevent its contagious nature getting its hands on a large number of individuals. Getting some prior information before its actual cause can help us to prepare ourselves to fight this pandemic better. It can assist authorities and administration to make better decisions in relatively less time to figure out the most suitable solutions. Since it is difficult to devise a permanent solution to this kind of pandemic, such data analysis can be used to strategize ourselves to cope with it. This study focuses on the forecasting of the number of active cases using deep neural networks. The models used in this approach are Multilayer Perceptron(MLP), Convolution Neural Networks(CNN) and Long Short Term Memory(LSTM). The performance of all three models is analyzed and although all of them are reasonably well, the MLP model outperforms the other two. These models can be used to predict the number of cases on a given day and a potential future outbreak. © 2022 IEEE.

Artificial Neural Networks for COVID-19 Forecasting in Mexico: An Empirical Study

Artificial Neural Networks (ANN) have encountered interesting applications in forecasting several phenomena, and they have recently been applied in understanding the evolution of the novel coronavirus COVID-19 epidemic. Alone or together with other mathematical, dynamical, and statistical methods, ANN help to predict or model the transmission behavior at a global or regional level, thus providing valuable information for decision-makers. In this research, four typical ANN have been used to analyze the historical evolution of COVID-19 infections in Mexico: Multilayer Perceptron (MLP), Convolutional Neural Networks (CNN), Long Short-Term Memory (LTSM) neural networks, and the hybrid approach LTSM-CNN. From the open-source data of the Resource Center at the John Hopkins University of Medicine, a comparison of the overall qualitative fitting behavior and the analysis of quantitative metrics were performed. Our investigation shows that LSTM-CNN achieves the best qualitative performance;however, the CNN model reports the best quantitative metrics achieving better results in terms of the Mean Squared Error and Mean Absolute Error. The latter indicates that the long-term learning of the hybrid LSTM-CNN method is not necessarily a critical aspect to forecast COVID-19 cases as the relevant information obtained from the features of data by the classical MLP or CNN. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

On The Pursuit of Fake News: Graph Neural Network meets NLP

This paper presents the methods proposed by FakeINA team to participate The FakeNews: Corona Virus and Conspiracies Multimedia Analysis tasks. We concentrate our work on text-based misinformation and conspiracy detection. We proposed a multimodal neural network that combines a graph neural network (GNN) where a document is represented as graph and a multi-layer perceptron model where textual statistics are used as features. Experimental results show that however GNNs are able to classify the data, a multimodal performs better. Copyright 2021 for this paper by its authors.

A Machine Learning approach for shared bicycle demand forecasting

More than 9 million bicycles are shared worldwide through more than 3.000 Bicycle Shared Systems (BSS). Investigating possible behaviours related to the demand for these services will optimize their success. The purpose of this research is to identify the impact of weather conditions, covid and pollution on the usage of BSS. Different machine learning algorithms are studied and used to analyze the different variables. Results were consistent with the literature and theory. In what concerns the algorithms, random forest and multi-layer perceptron regressor performed better, showing a better prediction power. © 2022 IEEE Computer Society. All rights reserved.

Prediction of COVID-19 tweeting: classification based on graph neural networks

This paper presents the application of graph neural networks (GNNs) to the task of node classification. GNNs have been shown to be useful in various classification tasks where data and the relationships between them can be represented using graphs. This research aims to develop a classifier that can identify two possible classes of Twitter nodes: COVID and nonCOVID. COVID nodes refer to Twitter users (nodes) that post tweets related to COVID-19 and nonCOVID are users (nodes) that do not post tweets about COVID-19. For that purpose, in the first step, we implement a pipeline that enables the automatic, continuous collection of data from Twitter and network construction. In the second step, we prepare the data and train a graph convolutional networks(GCN) classifier. We compare GCN and multilayer perceptron (MLP) in terms of standard measures: precision, recall, F1 and accuracy. The results show that GCN performs better than MLP in the task of node classification. © 2022 Croatian Society MIPRO.

An Improved Technique for Preliminary Diagnosis of COVID-19 via Cough Audio Analysis

Humanity has suffered catastrophically due to the COVID-19 pandemic. One of the most reliable diagnoses of COVID-19 is RT-PCR (Reverse-Transcription Polymer Chain Reaction) testing. This method, however, has its limitations. It is time-consuming and requires scalability. This research work carries out a preliminary prognosis of COVID-19, which is scalable and less time-consuming. The research carried out a competitive analysis of four machine learning models namely, Multilayer Perceptron, Convolutional Neural Networks, Recurrent Neural Networks with Long Short-Term Memory, and VGG-19 with Support Vector Machines. Out of these models, Multilayer Perceptron outperformed with higher specificity of 94.5% and accuracy of 96.8%. The results show that Multilayer Perceptron was able to distinguish between positive and negative COVID-19 coughs by a robust feature embedding technique. © 2022, Springer Nature Switzerland AG.

Twitter Sentiment Analysis towards COVID-19 Vaccines: A Case Study in New York City

According to the World Health Organization report in 2019, the COVID-19 vaccine hesitancy was one of the major threats to global health. Therefore, the study of vaccine-related conversations on social media could help governments or vaccine providers around the world perceive the current public's outlook and emotion, which heavily contributes to their confidence in the vaccination process. In this paper, we collected the vaccine-related tweets from New York City using the longitude and latitude configuration. The pre-processing technique was applied in order to categorise them into three sentiment types: positive, negative, and neutral. After that, the training and testing dataset were proportionally generated. Different machine learning techniques, which included Logistic Regression (LR), Naive Bayes, Support Vector Machine (SVM), Decision Trees, Random Forest and Multi-Layer Perceptron (MLP), were then utilised on our dataset to obtained the results. The comparison showed that the highest accuracy of 93.63 percent was achieved using MLP, while Naive Bayes produced the lowest accuracy of 82.13 percent. In conclusion, the promising finding of this study suggests that the application of Sentiment Analysis on social media platform can be used to determine the public's general opinion regarding the COVID-19 vaccines. © 2021 IEEE.