Artificial Intelligence based prediction system for General Medicine

COVID-19 is highly infectious and has been extensively spread worldwide, with approximately 651 million definite cases crosswise the globe including Pakistan. At that era of pandemic where patients are not able to approach a doctor for even the routine checkups, in such curial situation even normal disease checkups are ignored by many families due to pandemic situations, those diseases may lead to be a perilous disease are results of it. Human disorders portray scenarios that even disturb or permanently cutoff the essential functions of a body parts. Consequently, the aim is to transform raw health data potential into actionable insights to applying the promising outcomes of Body Sensor Network (BSN) and State-of-Art Artificial Intelligence (AI) techniques to get proper medicine allocation to the particular health state of patient. In this paper the different techniques of Deep Learning and Machine Learning introduced to predict the actual medicine for the specific health state of patient according to data from the BSN. Experiments have been conducted on large dataset which shepherd it into 16 states of patient's health which will allotted to AI model to predict the medicine accordingly to the health state of patient. Experimental results show the 87.46% by Random Forest, 92.74% by K-Nearest Neighbors, 74.57% by Naive Bayes, 94.41% by Extreme Gradient Boost, 84.88% by Multi-Layer Perceptron in terms of precision of model training in event of classification. © 2023 IEEE.

Outdoor Localization for a Mobile Robot under Different Weather Conditions Using a Deep Learning Algorithm

A fundamental issue in robotics is the precise localization of mobile robots in uncertain environments. Due to changing environmental patterns and lighting, localization under difficult perceptual conditions remains problematic. This paper presents an approach for locating an outdoor mobile robot using deep learning algorithms merge with 3D Light Detection and Ranging LiDAR data and RGB-D image. This approach is divided into three levels. The first is the training level, which involves scanning the localization area with a 3D LiDAR sensor and then converting the data into a 2.5D image based on the Principal Component Analysis. The testing is the second level in the Intensity Hue Saturation process. Then, the RGB and Depth images are combined to create a 2.5D fusion image. These datasets are trained and tested using Convolution Neural Networks. The K-Nearest Neighbor algorithm is used in the third level is the classification. The results show that the proposed approach is better in terms of accuracy of 97.46% and the Mean error distance is 0.6 meters.

Predictive Six Sigma for Turkish manufacturers: utilization of machine learning tools in DMAIC

PurposeThis study aims to emphasize utilization of Predictive Six Sigma to achieve process improvements based on machine learning (ML) techniques embedded in define, measure, analyze, improve, control (DMAIC). With this aim, this study presents selection and utilization of ML techniques, including multiple linear regression (MLR), artificial neural network (ANN), random forests (RF), gradient boosting machines (GBM) and k-nearest neighbors (k-NN) in the analyze and improve phases of Six Sigma DMAIC.Design/methodology/approachA data set containing 320 observations with nine input and one output variables is used. To achieve the objective which was to decrease the number of fabric defects, five ML techniques were compared in terms of prediction performance and best tools were selected. Next, most important causes of defects were determined via these tools. Finally, parameter optimization was conducted for minimum number of defects.FindingsAmong five ML tools, ANN, GBM and RF are found to be the best predictors. Out of nine potential causes, "machine speed” and "fabric width” are determined as the most important variables by using these tools. Then, optimum values for "machine speed” and "fabric width” for fabric defect minimization are determined both via regression response optimizer and ANN surface optimization. Ultimately, average defect number was decreased from 13/roll to 3/roll, which is a considerable decrease attained through utilization of ML techniques in Six Sigma.Originality/valueAddressing an important gap in Six Sigma literature, in this study, certain ML techniques (i.e. MLR, ANN, RF, GBM and k-NN) are compared and the ones possessing best performances are used in the analyze and improve phases of Six Sigma DMAIC.

Investigating the performance of machine learning algorithms in predicting the survival of COVID-19 patients: A cross section study of Iran.

Background and Aims: Like early diagnosis, predicting the survival of patients with Coronavirus Disease 2019 (COVID-19) is of great importance. Survival prediction models help doctors be more cautious to treat the patients who are at high risk of dying because of medical conditions. This study aims to predict the survival of hospitalized patients with COVID-19 by comparing the accuracy of machine learning (ML) models. Methods: It is a cross-sectional study which was performed in 2022 in Fasa city in Iran country. The research data set was extracted from the period February 18, 2020 to February 10, 2021, and contains 2442 hospitalized patients' records with 84 features. A comparison was made between the efficiency of five ML algorithms to predict survival, includes Naive Bayes (NB), K-nearest neighbors (KNN), random forest (RF), decision tree (DT), and multilayer perceptron (MLP). Modeling steps were done with Python language in the Anaconda Navigator 3 environment. Results: Our findings show that NB algorithm had better performance than others with accuracy, precision, recall, F-score, and area under receiver operating characteristic curve of 97%, 96%, 96%, 96%, and 97%, respectively. Based on the analysis of factors affecting survival, heart disease, pulmonary diseases and blood related disease were the most important disease related to death. Conclusion: The development of software systems based on NB will be effective to predict the survival of COVID-19 patients.

Predicting and Comparing Students' Online and Offline Academic Performance Using Machine Learning Algorithms.

Due to COVID-19, the researching of educational data and the improvement of related systems have become increasingly important in recent years. Educational institutions seek more information about their students to find ways to utilize their talents and address their weaknesses. With the emergence of e-learning, researchers and programmers aim to find ways to maintain students' attention and improve their chances of achieving a higher grade point average (GPA) to gain admission to their desired colleges. In this paper, we predict, test, and provide reasons for declining student performance using various machine learning algorithms, including support vector machine with different kernels, decision tree, random forest, and k-nearest neighbors algorithms. Additionally, we compare two databases, one with data related to online learning and another with data on relevant offline learning properties, to compare predicted weaknesses with metrics such as F1 score and accuracy. However, before applying the algorithms, the databases need normalization to meet the prediction format. Ultimately, we find that success in school is related to habits such as sleep, study time, and screen time. More details regarding the results are provided in this paper.

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.

Personalized predictions of adverse side effects of the COVID-19 vaccines.

Background: Misconceptions about adverse side effects are thought to influence public acceptance of the Coronavirus disease 2019 (COVID-19) vaccines negatively. To address such perceived disadvantages of vaccines, a novel machine learning (ML) approach was designed to generate personalized predictions of the most common adverse side effects following injection of six different COVID-19 vaccines based on personal and health-related characteristics. Methods: Prospective data of adverse side effects following COVID-19 vaccination in 19943 participants from Iran and Switzerland was utilized. Six vaccines were studied: The AZD1222, Sputnik V, BBIBP-CorV, COVAXIN, BNT162b2, and the mRNA-1273 vaccine. The eight side effects were considered as the model output: fever, fatigue, headache, nausea, chills, joint pain, muscle pain, and injection site reactions. The total input parameters for the first and second dose predictions were 46 and 54 features, respectively, including age, gender, lifestyle variables, and medical history. The performances of multiple ML models were compared using Area Under the Receiver Operating Characteristic Curve (ROC-AUC). Results: The total number of people receiving the first dose of the AZD1222, Sputnik V, BBIBP-CorV, COVAXIN, BNT162b2, and mRNA-1273 were 6022, 7290, 5279, 802, 277, and 273, respectively. For the second dose, the numbers were 2851, 5587, 3841, 599, 242 and 228. The Logistic Regression model for predicting different side effects of the first dose achieved ROC-AUCs of 0.620-0.686, 0.685-0.716, 0.632-0.727, 0.527-0.598, 0.548-0.655, 0.545-0.712 for the AZD1222, Sputnik V, BBIBP-CorV, COVAXIN, BNT162b2 and mRNA-1273 vaccines, respectively. The second dose models yielded ROC-AUCs of 0.777-0.867, 0.795-0.848, 0.857-0.906, 0.788-0.875, 0.683-0.850, and 0.486-0.680, respectively. Conclusions: Using a large cohort of recipients vaccinated with COVID-19 vaccines, a novel and personalized strategy was established to predict the occurrence of the most common adverse side effects with high accuracy. This technique can serve as a tool to inform COVID-19 vaccine selection and generate personalized factsheets to curb concerns about adverse side effects.

Human Body Temperature and Face Mask Audit System for COVID Protocol

The world has suffered enough in the aspect of COVID-19. From the year 2019, all we have in our hearts is a constant fear and terror of becoming prey to this deadly virus that has almost taken five lakh and twenty-five thousand lives to date within India, as the statistics show. The way to ensure that you maintain proper public hygiene is by ensuring that you wear masks in public places. There have been many algorithms that provide quicker results. We have tested our model in K-Nearest Neighbors (KNN), Support Vector Machine (SVM) algorithms and using deep learning technique Convolution Neural Networks (CNN). Comparing others, CNN provides more accuracy and has a shorter latency. Thus, we have implemented human face mask detector using CNN. The body temperature of the individual entering a room is monitored by the support of myDAQ, NI Instruments. If the body temperature is higher than 99F, then the person entering the space is not permitted inside. We have designed a device that monitors the temperature of the person entering the room along with the monitoring of face masks using the webcam. © 2022 IEEE.

Sentiment Analysis of Tweets During the COVID-19 Pandemic Using Multinomial Logistic Regression

Recently, the research on sentimental analysis has been growing rapidly. The tweets of social media are extracted to analyze the user sentiments. Many of the studies prefer to apply machine learning algorithms for performing sentiment analysis. In the current pandemic, there is an utmost importance to analyze the sentiments or behavior of a person to make the decisions as the whole world is facing lockdowns in multiple phases. The lockdown is psychologically affecting the human behavior. This study performs a sentimental analysis of Twitter tweets during lockdown using multinomial logistic regression algorithm. The proposed system framework follows the pre-processing, polarity and scoring, and feature extracting before applying the machine learning model. For validating the performance of proposed framework, other three majorly used machine learning based models--namely decision tree, naive Bayes, and K-nearest neighbors-- are implemented. Experimental results prove that the proposed framework provides improved accuracy over other models.

Sentiment Analysis of Tweets During the COVID-19 Pandemic Using Multinomial Logistic Regression

Recently, the research on sentimental analysis has been growing rapidly. The tweets of social media are extracted to analyze the user sentiments. Many of the studies prefer to apply machine learning algorithms for performing sentiment analysis. In the current pandemic, there is an utmost importance to analyze the sentiments or behavior of a person to make the decisions as the whole world is facing lockdowns in multiple phases. The lockdown is psychologically affecting the human behavior. This study performs a sentimental analysis of Twitter tweets during lockdown using multinomial logistic regression algorithm. The proposed system framework follows the pre-processing, polarity and scoring, and feature extracting before applying the machine learning model. For validating the performance of proposed framework, other three majorly used machine learning based models- namely decision tree, naïve Bayes, and K-nearest neighbors- are implemented. Experimental results prove that the proposed framework provides improved accuracy over other models. © 2022 Taru Publications. All rights reserved.

Ensemble Learning for Sentiment Analysis on Twitter Data Related to Covid-19 Preventions

The World Health Organization (WHO) declared the 2019 Coronavirus disease outbreak (Covid-19) as a pandemic and made it a trending topic on social media platforms, such as Facebook and Twitter. Unfortunately, news and opinions shared on social media affect people's mentality and create panic situations in society, but in the other hand, these opinions can be analyzed using sentiment analysis approach to generate knowledge and insight for the local government to monitor people reaction to the policies that have been issued to prevent the outbreak of Covid-19 virus. Therefore, this work aimed to propose an ensemble learning model that can classify the sentiment inside the people's opinions from Twitter. The ensemble model used Naïve Bayes Classifier, C4.5, and k-Nearest Neighbors as base learners with voting mechanism to generate the final decision. For learning, the ensemble model used a dataset containing 3884 clean data that was successfully downloaded using Twitter API related to Covid-19 outbreak prevention and processed using TF-IDF method. The dataset has two classes, i.e., 'positive' and 'negative' to represent the sentiment of the opinion in each data. The proposed model got 80.61% of accuracy, 79.49% of recall, and 81.20% of precision, after being evaluated using 10-fold Cross Validation. It also performed better when compared to several learning models using only single Machine Learning algorithm. © 2022 IEEE.

HOG and Haralick Feature Extractions with Machine Learning Methods for Covid-19 X-Ray Image Classification

- Distinguish COVID-19 from other respiratory diseases remains a demand mainly in machine learning solutions. The overlapping symptoms can confuse identifying the type of disease and lead to misdiagnosis. This paper evaluates feature extraction methods in conjunction with machine learning to determine a positive COVID-19 class. Pre-processing operations on a benchmark COVID-19 x-ray images dataset include under-sampling, resizing, converting into grayscale images, and noise removal. These operations are carried out to reduce the data produced by the dataset. A hybrid approach was used to conduct the evaluation, with Histogram of Oriented Gradient and Haralick as feature extractor methods and Support Vector Machine and K-Nearest Neighbors as classifiers. Several different parameters help measure the classifiers' performance. Compared to other hybrid methods, the Support Vector Machine with a Histogram of Oriented Gradient feature extraction performed the best. It has the highest accuracy score possible, coming in at 93.31%. The feature extraction method contributes to higher performance in the x-ray image classifier. In the future, additional feature extraction strategies, such as deep learning, may be potential competitors to this work. © 2022 Seventh Sense Research Group®

A Comparison of Machine Learning Methods for best Accuracy COVID-19 Diagnosis Using Chest X-Ray Images

Coronavirus (COVID-19) changed the view of people towards life in all the countries of the world in December 2019. The virus has made chaos that cannot be predicted. This problem requires using a variety of technologies to aid in the identification of COVID-19 patients and to control the disease spread. For suspected instances of COVID-19 disease, chest X-ray (CXR) imaging is a standard with fewer costs, but it does not need a COVID-19 examination approach without using technology to help for a suitable diagnosis. In response to this issue, a big dataset of CXR images was divided into four classes found on the website Kaggle. Dealing with large data of the images needs dataset reprocessing through choosing the optimal method for getting speed and best accuracy. Dataset reprocessing converts into gray level then adjust image intensity, resize and extract the best features then apply Machine Learning ML models. The use of different prediction models, ML algorithms, and their performances are calculated with evaluation on the dataset after reprocessing. Decision Tree (DT), Random Forest (RF), Stochastic Gradient Descent (SGD), Logistic Regression (LR), Gaussian Naive Bayes (GNB), and K-Nearest Neighbors (KNN) are models used to foretell the specialized who would be diagnosed with COVID-19 quickly by using CXR images classification. The KNN has revealed the best accuracy compared with the others such as GNB, DT, SGD, LR, and RF. Also, KNN has the best-weighted average for all parameters, which are precision, sensitivity, and F1-score compared with the other models. © 2022 IEEE.

A study and identification of COVID-19 viruses using N-grams with Naïve Bayes, K-Nearest Neighbors, Artificial Neural Networks, Decision tree and Support Vector Machine

Coronavirus disease 2019 or COVID-19 is a global health crisis caused by a virus officially named as severe acute respiratory syndrome coronavirus 2 and well known with the acronym (SARS-CoV-2). This very contagious illness has severely impacted people and business all over the world and scientists are trying so far to discover all useful information about it, including its potential origin(s) and inter-host(s). This study is a part of this scientific inquiry and it aims to identify precisely the origin(s) of a large set of genomes of SARS-COV-2 collected from different geographic locations in all over the world. This research is performed through the combination of five powerful techniques of machine learning (Naïve Bayes, K-Nearest Neighbors, Artificial Neural Networks, Decision tree and Support Vector Machine) and a widely known tool of language modeling (N-grams). The experimental results have shown that the majority of the aforementioned techniques gave the same global results concerning the origin(s) and inter-host(s) of SARS-COV-2. These results demonstrated that this virus has one zoonotic source which is Pangolin. © 2022 IEEE.

Machine Learning-Based Classification of Chest X-Ray MRI Images into Covid-19 Graphic User Interface

To predict the best performance metrics for the diagnostic pathology of Covid-19 based on MRI image feature extractions, primarily studies analysis are required to determine the optimal setting parameters such as the knn nearest-neighbors, the test size, and the random state. In this investigation, the performance metrics that tell us how much better a model is making prediction are presented. The system is implemented and simulated in Anaconda, and its performance is tested on a real dataset that contains six (06) features and two (02) classes. Each class, an abnormal class (a patient having Covid-19), and a normal class (a patient without Covid-19) consists of 343 instances (images), and 234 instances (images), respectively. At constant random state 66, the performance of test measurements obtained from the simulations results under various test sizes [10%~50%] is carried out when the nearest neighbor knn changes from 1 to 20. For quality analysis to examine and validate the proposed technique, based on the performance metrics, the simulation results achieved an average of train accuracy, test accuracy, precision score, sensitivity, F1-score, and specificity in the interval of (100.0±0.0~74.3±0.9)%, (82.9±3.4~71.6±2)%, (82.5±3.5~66.2±2.8)%, (82.0±6.4~60.1±4.1)%, (80.6±2.3~66.3±3.4)%, and (90.0± 2.3~71.8±3.4)%,respectively. The KNN classifier combined with the optimal setting parameters show better performance, predicting the normal and abnormal class labels accurately. Based on these results, we can further improve the accuracy performance in the range of k = [2~7] and the test size in the range of [10%~35%]. With these primarily studies analysis, we have developed a graphic user interface application to perform the diagnostic of pathology on Covid-19 disease that generates the optimal performance metrics. © 2022 IEEE.

Diagnosis of COVID-19 via acoustic analysis and artificial intelligence by monitoring breath sounds on smartphones.

Scientific evidence shows that acoustic analysis could be an indicator for diagnosing COVID-19. From analyzing recorded breath sounds on smartphones, it is discovered that patients with COVID-19 have different patterns in both the time domain and frequency domain. These patterns are used in this paper to diagnose the infection of COVID-19. Statistics of the sound signals, analysis in the frequency domain, and Mel-Frequency Cepstral Coefficients (MFCCs) are then calculated and applied in two classifiers, k-Nearest Neighbors (kNN) and Convolutional Neural Network (CNN), to diagnose whether a user is contracted with COVID-19 or not. Test results show that, amazingly, an accuracy of over 97% could be achieved with a CNN classifier and more than 85% on kNN with optimized features. Optimization methods for selecting the best features and using various metrics to evaluate the performance are also demonstrated in this paper. Owing to the high accuracy of the CNN model, the CNN model was implemented in an Android app to diagnose COVID-19 with a probability to indicate the confidence level. The initial medical test shows a similar test result between the method proposed in this paper and the lateral flow method, which indicates that the proposed method is feasible and effective. Because of the use of breath sound and tested on the smartphone, this method could be used by everybody regardless of the availability of other medical resources, which could be a powerful tool for society to diagnose COVID-19.

Predicting Covid-19 Test Report Using Data Mining Techniques Based on The Second Wave in Bangladesh

Coronavirus (Covid-19) is a disease that spreads from one person to another very quickly. The whole world is facing this Covid-19 pandemic now and Bangladesh is also not out of it. After the first wave, now the second wave is going on in Bangladesh. As the second wave is spreading faster than the first wave and the test process of Covid-19 is very time-consuming. As a result, before getting the test report, a person infected with Covid-19 and spreads this virus to other people as he doesn't know whether he is infected with Coronavirus or not. To create a dataset, we have asked some patients from our nearby people who live in Faridpur, Joypurhat, and Cumilla district and collected their data who have tested for Covid-19 during the second wave. We have collected some of their symptoms that appeared before their Covid-19 test. With this dataset, we have used some data mining approach to predict whether a patient is tested positive or negative. We have applied two algorithms here. Among them, Naive Bayes gives the highest accuracy which is 80%. © 2021 IEEE.

REMOTE DISEASE DIAGNOSIS SYSTEM

In times of pandemic, human-less interaction has become a new normal where diagnostic process has transformed from hospital-centric to home-centric procedure. While hospitals are hard-pressed to treat COVID-19 patients, diagnosis and treatment of other diseases should be carried out in a remote way. Hence, an integrated approach is essential for constant monitoring of a person's health. We propose a system where parameters like height, weight, temperature, pulse rate and moisture of scalp are measured using respective sensors interfaced with Arduino. The measured values are then uploaded to the cloud using a Wi-Fi module. The data uploaded to the cloud are trained using Support Vector Machine (SVM) and K-Nearest Neighbours (KNN) algorithms to predict the prevailing health condition of an individual. By comparing SVM and KNN algorithms, SVM is proved to be more accurate than the KNN algorithm. © 2021 IEEE.

Enhanced Vaccine Recommender System to prevent COVID-19 based on Clustering and Classification

Due to the fact that countries are presently dealing with the third wave of COVID-19 pandemic and in present time, the data of vaccines for preventing COVID-19 has triggered massive information, it is vital to create a system that can assist decision-makers and health care practitioners in combating COVID-19 and to combat the problem of vaccine information overload is to provide patients with personalized vaccine recommendations. Because of the ability of recommender systems (RSs) that use Collaborative Filtering (CF) to interpret decision-maker expectations, methodologies, it widely used and direct them towards linked tools that are acceptable to recommend the suitable vaccine for the persons. In this paper, we adopted an Enhanced Vaccine RSs for preventing COVID-19, which is called EVRSs-19. EVRSs-19 face some problems such as sparsity and diversity of vaccines data. To overcome these problems, we adopted two proposals. First, use clustering of K-Means to cluster the persons in several groups according to vaccine types to cope with sparsity of vaccines data. Second, use the K-Nearest Neighbors classifier-depend model of CF to discover neighbors in each vaccine cluster to increase diversity. Evaluating the EVRSs-19 system implemented on vaccines data in two testing using some metrics and the findings of these metrics after running the clustering and classification show that the system of EVRSs-19 has a perfect structure. Such as recall (0.92), precision (0.89), diversity score (9). As the vaccines recommendation list progressed, NDCG and DCG for persons are decreased. © 2021 IEEE.

Estimating changes in air pollutant levels due to COVID-19 lockdown measures based on a business-as-usual prediction scenario using data mining models: A case-study for urban traffic sites in Spain.

In response to the COVID-19 pandemic, governments declared severe restrictions throughout 2020, presenting an unprecedented scenario of reduced anthropogenic emissions of air pollutants derived mainly from traffic sources. To analyze the effect of these restrictions derived from COVID-19 pandemic on air quality levels, relative changes in NO, NO2, O3, PM10 and PM2.5 concentrations were calculated at urban traffic sites in the most populated Spanish cities over different periods with distinct restrictions in 2020. In addition to the changes calculated with respect to the observed air pollutant levels of previous years (2013-2019), relative changes were also calculated using predicted pollutant levels for the different periods over 2020 on a business-as-usual scenario using Multiple Linear Regression (MLR) models with meteorological and seasonal predictors. MLR models were selected among different data mining techniques (MLR, Random Forest (RF), K-Nearest Neighbors (KNN)), based on their higher performance and accuracy obtained from a leave-one-year-out cross-validation scheme using 2013-2019 data. A q-q mapping post-correction was also applied in all cases in order to improve the reliability of the predictions to reproduce the observed distributions and extreme events. This approach allows us to estimate the relative changes in the studied air pollutants only due to COVID-19 restrictions. The results obtained from this approach show a decreasing pattern for NOx, with the largest reduction in the lockdown period above -50%, whereas the increase observed for O3 contrasts with the NOx patterns with a maximum increase of 23.9%. The slight reduction in PM10 (-4.1%) and PM2.5 levels (-2.3%) during lockdown indicates a lower relationship with traffic sources. The developed methodology represents a simple but robust framework for exploratory analysis and intervention detection in air quality studies.