A Survey on Machine Learning Techniques for Multimodal Biomedical Signal Processing

In recent years, there has been a significant growth in the development of machine learning algorithms towards better experience in patient care. In this paper, a contemporary survey on the deep learning and machine learning techniques used in multimodal signal processing for biomedical applications is presented. Specifically, an overview of the preprocessing approaches and the algorithms proposed for five major biomedical applications are presented, namely detection of cardiovascular diseases, retinal disease detection, stress detection, cancer detection and COVID-19 detection. In each case, processing on each multimodal data type, such as an image or a text is discussed in detail. A list of various publicly available datasets for each of these applications is also presented. © 2023 IEEE.

A Long Short Term Memory Machine Learning Technique for Covid-19 Patient Count Prediction

The Corona-virus H19 pandemic is quickly spreading throughout the globe. Every three to four times, waves occur and have a major effect on people's lives. Other illnesses including covid disorders are misdiagnosed in this setting. There is no reliable statistics on the total number of covid patients in the nation, and no system exists to track them. This prevents the patients from receiving the necessary care and treatment. The number of patients in a given dataset may be determined with more precision using AI methods. In this article, we show how to forecast how many patients will be included in the Covid-19 database by using an adaptive method. Python spyder is used to run the simulation. . © 2023 IEEE.

A Predictive Model for Assessing Satisfaction with Online Learning for Higher Education Students During and After COVID-19 Using Data Mining and Machine Learning Techniques: A Case of Jordanian Institutions

Higher education institutions confronted an escalating unexpected pressure to rapidly transform throughout and after the COVID-19 pandemic, by replacing most of the traditional teaching practices with online-based education. Such transformation required institutions to frequently strive for qualities that meet conceptual requirements of traditional education due to its agility and flexibility. The challenge of such electronic learning styles remains in their potential of bringing out many challenges, along with the advantages it has brought to the educational systems and students alike. This research came to shed the light on several factors presented as a predictive model and proposed to contribute to the success or failure in terms of students' satisfaction with online learning. The study took the kingdom of Jordan as a case example country experiencing online education while and after the covid -19 intensive implementation. The study used a dataset collected from a sample of over "300” students using online questionnaires. The questionnaire included "25” attributes mined into the Knime analytics platform. The data was rigorously learned and evaluated by both the "Decision Tree” and "Naive Bayes” algorithms. Subsequently, results revealed that the decision tree classifier outperformed the naïve bayes in the prediction of student satisfaction, additionally, the existence of the sense of community while learning electronically among other reasons had the most contribution to the satisfaction. Copyright © 2023 by SCITEPRESS - Science and Technology Publications, Lda. Under CC license (CC BY-NC-ND 4.0)

Machine Learning Techniques on X-ray Images for Covid-19 Classification

The Public Health Commission of Hubei Province, China, at the end of 2019reported cases of severe and unknown pneumonia, marked by fever, malaise, dry cough, dyspnea, and respiratory failure, that occurred in the urban area of Wuhan, according to the World Health Organization (WHO). The lung infection, SARS-CoV-2, also known as COVID-19, was caused by a brand-new coronavirus (coronavirus disease 2019). Since then, infections have increased exponentially, and the WHO labeled the outbreak a worldwide emergency at the beginning of March 2020. Infected and asymptomatic individuals who can spread the virus are the main sources of it. The transmission occurs mainly by airthrough the air through the droplets, however indirect transmission is also possible, such as through contact with infected surfaces. It becomes essential to identify viral carriers as soon as possible in order to stop the spread of the disease and reduce morbidity and mortality. Imaging examinations, which are among the specific tests used to make the definite diagnosis, are crucial in the patient's management when COVID-19 is suspected. Numerous papers that use machine learning techniques discuss the use of X-ray chest radiographs as a component that aids in diagnosis and permits disease follow-up. The goal of this work is to supply the scientific community with information on the most widely used Machine Learning algorithms applied to chest X-ray images. © 2022 IEEE.

Fusion-Based Segmentation and Classification of Novel Coronavirus or Pneumonia from Chest X-ray Images Using Machine Learning Techniques

The deadfall widespread of coronavirus (SARS-Co V-2) disease has trembled every part of the earth and has significant disruption to health support systems in different countries. In spite of such existing difficulties and disagreements for testing the coronavirus disease, an advanced and low-cost technique is required to classify the disease. For the sense of reason, supervised machine learning (ML) along with image processing has turned out as a strong technique to detect coronavirus from human chest X-rays. In this work, the different methodologies to identify coronavirus (SARS-CoV-2) are discussed. It is essential to expand a fully automatic detection system to restrict the carrying of the virus load through contact. Various deep learning structures are present to detect the SARS-CoV-2 virus such as ResNet50, Inception-ResNet-v2, AlexNet, Vgg19, etc. A dataset of 10,040 samples has been used in which the count of SARS-CoV-2, pneumonia and normal images are 2143, 3674, and 4223 respectively. The model designed by fusion of neural network and HOG transform had an accuracy of 98.81% and a sensitivity of 98.65%. © 2022 IEEE.

Human Activity Recognition Using Machine Learning Technique

COVID has made education shift towards online mode. In online mode, instructors have a hard time keeping track of their students. Students' performance in online classes falls considerably below the level of learning due to a lack of attention. This initiative aids in the supervision of students during online classes. Artificial Intelligence (AI) models are being developed to better recognize student activities during online sessions. Many applications rely on determining an individual's mental state. When evaluating which subtask is the most challenging, a quantitative measure of human activity while executing a task can be helpful. Thus, the goal of this research is to create an algorithm that uses EEG data gathered with a Muse headset to measure the amount of cognitive intelligence of students during online classes. The data collected by the Muse headset is multidimensional, and it is pre-processed before being fed into machine learning algorithms. Using feature selection, the dataset's dimension is now reduced. The model's precision and recall were calculated, and a confusion matrix was created. The Support Vector Machine produces better outcomes in the experiment. © 2022 IEEE.

Intelligent ResNet-18 based Approach for Recognizing and Assessing Arabic Children's Handwriting

Studies tackling handwriting recognition and its applications using deep learning have been promoted by developing advanced machine learning techniques. Yet, a shortage in research that serves the Arabic language and helps develop teaching and learning processes still exists. Moreover, COVID-19 pandemic affected the education system considerably in many countries and yielded an immediate shift to distance learning and extensive use of e-learning tools. An intelligent system was proposed and used in this paper to recognize isolated Arabic handwritten characters. Particularly, pre-trained CNN models were exploited and fine-tuned to meet the requirements of the considered application. Specifically, the designed system automatically supports teaching Arabic letters and evaluating children's writing skills. The Arabic Handwritten Character Dataset (AHCD) was used to train the models built upon ResNet-18 and assess the overall system performance. Furthermore, several models were investigated using various hyper-parameter settings in order to determine the most accurate one. The best model with the highest accuracy rate of 99% was used and integrated into the proposed system to recognize the Arabic alphabets. © 2023 IEEE.

Covid-19 and Diabetes Risk Prediction for Diabetic Patient using Advance Machine Learning Techniques and Fuzzy Inference System

Diabetes has become a common and critical disease which generally occurs due to the presence of high sugar in blood for long time. A diabetic patient has to follow different rules and restrictions where he/she has to be under proper attention by measuring diabetes level frequently to avoid unexpected risk. The risk become more when patient even doesn't know that he/she is already having diabetes and doesn't follow those restrictions. To prevent this risk, everyone should check the diabetes status to be sure. With the same target different system using machine learning techniques have been introduced which can predict the diabetes status of a patient. But the challenging fact is that the performances and accuracy of those models are questionable where there may be a huge risk of patient's life. The conventional systems are not able to show that which level of diabetes a patient can have using the previous records. To solve this issue, through this paper an efficient system has been proposed with which the diabetes status can be predicted correctly. The proposed system can also show the complexity of diabetes as well as the Covid-19 risk percentage that can also be possible to measure. After comparing several machine learning techniques, the suitable model has been selected where high level of accuracy has been ensured in term of predicting the disease. © 2022 IEEE.

A Novel Real-time Automated Face Classification and Detection system using Machine Learning Technique

In recent days, Image classification and detection technique has become an important and more essential in the Image processing research field. Creating effective face detection is an essential aspect of handling the detection mechanism, Tracking mechanism and Validation mechanism. The classical methods used for face detection do not have sufficient output. This research paper presents various studies and how machine learning methods are become to solve many challenges present in the face detection system. The first phase of work has a classification model with support vector machines, decision trees and Hybrid Ensemble Transfer learning algorithm. The second phase of work is investigated with real-the world's most popular dataset from World Masked Face Image Dataset and Label Faces in the wild (RMFD). Moreover, the experiment, results show how better accuracy and fast computation which has been achieved by Hybrid Ensemble algorithm with SVM and Decision Trees machine learning techniques. This research helps to assist many social applications such as during pandemics like covid-19 and personal identity, it can be verifying the mask-worn persons. © 2023 IEEE.

A Prototype for Interpretation of Sars-Cov-2 Tests Using Artificial Vision

Covid-19 has been declared a pandemic by the World Health Organization in March 2020, so science has been trying to help mitigate its effects from its various fields of study. Machine learning methods can play an important role in identifying test results that reveal whether an individual has the disease. This degree work presents a prototype based on computer vision and machine learning techniques to automatically detect SARS-CoV-2 serology tests. The goal of the prototype is to identify and classify the serology test cassette result by Immunoglobulin G and Immunoglobulin M indicators that are flagged after a test reaction time which is approximately 15 minutes. The results in the identification performed by the prototype are promising and ease its analysis, reducing the errors in the identification of the test and the interpretation of the results. The result is a prototype that allows to perform, simplify and improve the tasks of health professionals, which they must perform daily in the triage area. © 2022 IEEE.

A Decision Support System using Machine Learning -IoT to tackle the Covid-19 pandemic in Uttarakhand

Covid-19 spread is worldwide;India is now at the second place where this epidemic is spreading with high rate. The state of Uttarakhand, a hilly state of India also has a significant impact of Covid-19. This paper suggests that machine learning techniques with IOT can equipped the doctors, and lab technicians to deal with this pandemic. Here, we also design a prediction system to help the doctors so that they can keep the records of infected patients. We used IoT, machine learning and ensemble methods for healthcare to store infected patient's data in the cloud database, and enable doctors/others to screen patient's data about their disease. We developed a decision support system to detect the diseases quickly and the treatment can be initiated immediately. © 2022 IEEE.

Machine Learning Techniques for Predicting Risks of Late Delivery

Supply chain is a cornerstone of the eCommerce industry and is a key component in its growth. Supply chain data analytics and risk management in the eCommerce space have picked up steam in recent times. With the availability of suitable & capable resources for big data and artificial intelligence, predictive analytics has become a significant area of interest to achieve organizational excellence by exploiting data available and developing data-driven support systems. The existing literature in supply chain risk management explain various methods assisting to identify & mitigate risks using big data and machine learning (ML) techniques across industries. Although ML techniques are used in various industries, not many aspects of eCommerce had utilized predictive analytics to their benefit. In the eCommerce industry, delivery is paramount for the business. During COVID-19 pandemic, needs changed. Reliable delivery services are preferred to speedy delivery. Multiple parameters involve delivering the product to a customer as per promised due date. This research will try to predict the risks of late deliveries to online shopping customers by analyzing the historical data using machine learning techniques and comparing them by multiple performance metrics. As a part of this comparative study, a new hybrid technique which is a combination of Logistic Regression, XGBoost, Light GBM, and Random Forest is built which has outperformed all the other ensemble and individual algorithms with respect to accuracy, specificity, precision, and F1-score. This study will benefit the eCommerce companies to improve their customer satisfaction by predicting late deliveries accurately and early. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

An Ingenious Method to Detect COVID in X-Ray Images Using Machine Learning Techniques

Covid-19 is a fatal disease caused by the Covid-19 virus. It is very big problem for the whole world. The World Health Organization (WHO) has declared a pandemic. In May 2020, more people throughout the world had a favorable experience. The COVID illness is rapidly growing, and we are unable to stop it. We addressed the COVID-19 data science research initiatives employing a number of approaches, including statics, machine learning (ML), modelling, simulation, data visualization, and artificial intelligence (AI). We all suffering from COVID-19. in this case higher value of case comes from negative and lower false positive rate. The global impact of the COVID-19 outbreak was enormous. To tackle the pandemic, many projects have been launched, including those in the field of deep learning. This paper proposes a deep neural network modification based on the Xception model. The model is used to detect COVID-19 using chest X-ray images. Batch normalization and two stacks of two dense layers each are used in the proposed model. The layer addition is intended to avoid overfitting the proposed model. The proposed as a result, we compare the model's loss, accuracy, and performance speed, and the results show that the quality of the machine learning model has higher prediction accuracy and loss, but it takes longer to execute than traditional machine learning languages. Machine learning algorithms in general, and convolutional neural networks (CNNs) in particular, have shown promise in medical picture analysis and categorization. The architecture of this study has been presented for the diagnosis of COVID-19. © 2022 IEEE.

Covid Analysis Using Machine Learning Technique

The recent pandemic, covid-19 has largely affected people's lives, health, and productivity. The first case of Covid-19 was recorded on December 31, 2019, in Wuhan, China. Since then, the number of cases has increased exponentially, and subsequently, numerous precautions have been taken to prevent and cure the virus. By May 26, 2021, totally, 168 million cases were reported worldwide, with 3.49 million deaths, and the pandemic is currently underway, with people continuing to get affected and fighting for their lives from this deadly virus. The World Health Organization (WHO) has also released various precautions and vaccines to combat the pandemic, but these are insufficient to reduce the number of infected cases or save people's lives. The proposed research study discusses about the utilization of artificial intelligence (AI), machine learning (ML), and data science techniques for gaining a better understanding of covid-19 virus. This technological advancement can easily make proper judgments about covid-19, as well as the predictions on confirmed & recovered cases and deaths were made by using this technology. The datasets also include previous and current information about covid-19. The proposed research study also discusses about a tool called "Prophet.” Prophet is a Facebook open-source tool, which uses the Sklearn model API. The proposed study initially creates a prophet instance and then use its fit and predict methods. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Analysis of Face Mask Detection through Machine Learning Techniques in Spread of COIVD-19

To distinguish individuals wearing face masks in observation settings like banks and ATMs, this work will give a profound learning model to face mask recognition. Hoodlums and offenders perpetrate wrongdoings by disguising their elements behind face masks, which is contrary to the standard in checking environmental factors. To recognize and secure offenders and lawbreakers, the face mask locator model set forth in this study can be joined with observation cameras in independent reconnaissance frameworks. The COVID-19 pandemic has in short order disturbed worldwide exchange and transportation, influencing our everyday lives. The act of utilizing a defensive face mask has changed. Coming soon from now on, a few public specialist co-ops will expect that clients utilize the legitimate masks while utilizing their administrations. Face mask ID is turning into a significant obligation to help the worldwide civilization. This paper frames a dense strategy for accomplishing this objective using specific essential AI instruments, including Tensor Stream, Keras, OpenCV, and Scikit-Learn. The proposed procedure effectively perceives the face in the picture and afterward decides if it is covered by a mask. © 2022 IEEE.

Visualizing COVID-19 Vaccination Rate and Vaccination Centre in Malaysia using DBSCAN Clustering model

In February 2021, the Malaysian government launched a vaccination campaign against coronavirus disease 2019 (COVID-19). However, there is a problem in identifying suitable location for vaccination centre should be allocated. At the same time, there are population that living in the rural area and has difficulty to travel to the nearest vaccination centres. Therefore, based on the data of vaccination rate collected by Ministry of Health, the proposed project aims to classify and visualise the data based on number of COVID-19 vaccination rate and centre in Malaysia for the adult and adolescent populations. This project uses machine learning technique called Density-Based Spatial Clustering of Applications with Noise (DBSCAN). The system is developed in Python language platform for back-end development, and PyCharm is utilised for front-end development in web-based platform. This project follows four phases in Waterfall model: requirement analysis, design, implementation, and testing. The system is evaluated for functionality and usability based on user satisfaction and the accuracy of the model. The results of the testing shows that all the functionality of the system have been implemented successfully in the system. The system also rated good according to SUS Questionnaire in usability testing with score of 88.5%. The model of machine learning also achieved a good accuracy score which is greater than 0.3. In conclusion, the data visualization web-based application helps the Malaysian government to identify location for additional vaccination centres in strategic locations and it helps Malaysian people to locate nearby vaccination centres in their area. © 2022 IEEE.

Continuous Monitoring for Diagnosis: A Wearable for Covid-19 Detection in Symptomatic Patients

We develop an approach for systematically designing continuous monitoring solutions for early symptom diagnosis. Effective early diagnosis requires collecting and correlating symptoms derived from a number of vitals. For designing a continuous monitoring solution, it is crucial to determine the vitals to be monitored for targeted detection, the errors that can be tolerated, various parameters that need to be tuned, etc. Furthermore, this determination must be made before the design of the monitoring solution itself. Our approach shows how to use a variety of machine learning techniques to systematically derive, tune, and optimize the vitals to be monitored before accessing the continuous monitoring data. We show the effectiveness of our approach in the design of a wearable for early detection of COVID-19 infections in symptomatic patients. © 2023 IEEE.

RBTM: Prediction of COVID-19 from Random Blood Test with Machine Learning Algorithms

Recently, the ongoing global pandemic of novel coronavirus infection had a devastating impact worldwide. We develop an efficient classification model that effectively produces the predictive values of infected patients with suspicious symptoms and epidemiological history to defeat this. The research aims to use the Traditional technique to compare clinical blood tests of positive and negative cases. The diagnostic Machine Learning model incorporates 551random blood samples with the following parameters of the patient's demographic features, Platelet, Hemoglobin, Lymphocyte, Neutrophil, Leukocyte (WBC), Turbidimetric, Troponin-I of COVID positive and negative cases. The prediction model can achieve the classification report of Accuracy, Precision, Recall, and F1 score values. In this analysis, considering seven different algorithms for the prediction and the observation's estimation, the data is 5-fold cross-validated. Finally, investigational outcomes attain accurate predictions. Logistic Regression predicted 0.83% of accuracy. The Receiver Operator Characteristic (ROC) metrics for Logistic Regression, the Precision was 0.78%, Recall was 0.85%, and F1-score was 0.82%, Specificity was 0.58%, and Sensitivity was 0.41%. © 2022 IEEE.

Feature Selection For High Dimensional Data Using Supervised Machine Learning Techniques

In recent years, feature selection has become an increasingly active field of data science and machine learning research. Most of the datasets that are being used nowadays for various machine learning tasks consist of thousands of features (columns), which make them extremely complex and difficult to work with. In this paper, we propose a feature selection methodological pipeline that can be used to reduce the complexity of high dimensional datasets through the elimination of redundant and/or non-informative features as well as to improve the performance of machine learning models which are trained on high dimensional datasets. The proposed method has been applied to high-dimensional biomedical data and compared against a classic filter-based feature selection algorithm. Specifically, the method was applied to gene expression profiles of a single-cell RNA-seq dataset from healthy and infected by covid-19 human samples. © 2022 IEEE.

Pose Estimation of Yoga Poses using ML Techniques

POSE ESTIMATION is a technique to identify joints in a human body from an image or video given as input to a computer. Pose estimation can be performed using Machine Learning (ML) techniques and Deep Learning techniques. Lately, it has been receiving lots of attention in the fields of Human Sensing and Artificial Intelligence. The main aim of pose estimation is to predict the poses of humans by locating key points like elbows, knees, wrists etc.In this work, we have proposed a model which uses Mediapipe, an ML framework, to obtain key point coordinates and ML algorithms like SVM, Gaussian Naive Bayes, Random Forest, Gradient Boost and K Neighbours classifier, which are compared and used to predict Yoga poses. Yoga is practised by people of all ages alike these days to fight issues caused both physically and mentally, thus improving the overall quality of life. Especially since the rise of the COVID-19 pandemic, the number of people practising yoga has only been increasing. In the model, human joint coordinates obtained are used as features. The model with the best accuracy and f score (MediaPipe+ SVM) is chosen for the final work.The yoga poses we used are Plank, Warrior 2, Downdog, Goddess, Tree and Cobra. On implementing the work, a real-time video feed from the webcam of the user's system is obtained, and pose estimation and classification of the yoga pose are done. Unlike in most current systems, suggestive measures to correct the yoga posture are also displayed in real-time alongside the webcam display of the person performing yoga along with some other basic pose information. © 2022 IEEE.