Search

Students are customers of a higher education institution. Various types of services and facilities are provided by universities for students, such as academic services, student services, and infrastructure including information technology services. Student satisfaction with the quality of the university services is one of the factors that affect the academic performance of the university. This study aims to compare the level of accuracy between the Random Forest method, Support Vector Machine and Neural Network for the classification of student satisfaction with the services provided by Higher Education. The dataset consisted of 430 respondents from private universities in Vietnam taken and adapted from previous research. The training and testing dataset uses a split proportion of 80:20 of the total available datasets. Model performance measurements using matrix confusion include accuracy, sensitivity (recall), and precision. The results showed that the Random Forest method can produce the best accuracy rate of 76.47%, followed by Neural Network and Support Vector Machine algorithms with an accuracy rate of 74.12% on each. [ABSTRACT FROM AUTHOR]

Industry 4.0 is nothing but automation with digitalization, which is the need of every industry to compete globally. It was introduced to enhance manufacturing capabilities by making technological advancements to increase client satisfaction and production efficiency. To increase the profitability and efficiency of the entire operation, new services and technologies are being developed at the manufacturing level. This work aims to explore Industry 4.0 from bottom to top i.e., field devices to the cloud. In this work, a simple bottle filling process has been developed using PLC programming language - Structured Text in B&R Automation Studio, visualized in human machine interface (HMI). The data generated in B&R Automation Studio is extracted using the OPC UA communication protocol and UaExpert Client, and a log is generated later using Python. The process is remotely monitored as well as controlled from anywhere in the world using the UaExpert Test Client. Then this data is pushed and stored in real-time in a Firebase database and it is used for remote monitoring the process through the developed mobile application by accessing the data from Firebase Database. Predictive maintenance (PdM) is also done where various Machine Learning Regression models like Simple Linear Regression, Random Forest Regression are implemented for predicting the failure of the machine and its components. This completes the whole field to cloud experience of Smart Manufacturing using Industry 4.0. [ABSTRACT FROM AUTHOR]

Many people express their opinions regarding policies or rules imposed by the government through Twitter social media. This study was conducted to determine public sentiment regarding the rules for implementing the reverse-transcriptase polymerase chain reaction (RT-PCR) test as one of the requirements for using air transportation. The research was conducted using the Random Forest and K-Nearest Neighbor (KNN) algorithms and the CRISP-DM research method. Twitter data used is classified into negative, neutral and positive. The results of the sentiment analysis showed that the KNN algorithm outperformed Random Forest with an accuracy value of 75.63% and the sampling technique used was stratified sampling. The results of the sentiment analysis show that the public has a negative sentiment towards the policies issued by the government. [ABSTRACT FROM AUTHOR]

Internet of Thing (IoT) environment deals with large amounts of data from sensors and other things. The main problem with Internet of Things based applications right now, is security threats with respect to the large amount of data in transit and at rest. Theft or snooping of information or fault in IoT device can cause the data to have some anomalies. We can scan the network to get details of type of packets being transferred, type of protocols being used, source and destination, etc. These data can be analysed to get meaningful inferences and detect intrusion in a network. Most of the work done in this field is single system, single core system based application. This paper focuses on proposing a network anomaly detection mechanism using Machine Learning method, Random Forest in a distributed setup (cluster of machines) using SPARK. Such a mechanism should detect anomalies in large IoT data in an accurate and efficient manner on an IoT dataset called UNSW- NB15. [ABSTRACT FROM AUTHOR]

Vitiligo is a disorder in the cells that generate the major pigment, and melanin of skin. Vitiligo vulgaris is an autoimmune disease which is developed unpredictably. There may be the occurrence of vitiligo in any area of the body and in any shape. It sometimes even covers the whole surface of the skin. Vitiligo can be seen clearly on an individual having dark-phototype and leads to cause socio-relational issues. The ultraviolet light is utilized to eliminate the issue of visibility disparity. The vitiligo disease diagnosis consists of various processes: pre-processing, feature extraction, segmentation and classification. The technique of vitiligo disease is proposed in which K-mean, GLCM and voting ensemble are applied for segmenting, feature extracting, classifying the disorder. The voting ensemble is applied as a blend of logistic regression, random forest and GNB (Gaussian Naive Bayes) methods. The framework constructed in this project is enforced in python software, and based on some metrics the obtained outcomes are studied. [ABSTRACT FROM AUTHOR]

To explain a complicated machine-learning model, data scientists work a lot with identifying the importance of predictor features of the model. Shapley Additive Explanation (SHAP) and Permutation Feature Importance (PFI) are popular methods useful to measure the feature-importance levels. This research examines the utilization of both techniques to reveal the contribution of predictors in a model to classify the food-insecurity status of Indonesian households. Food insecurity is a condition in which a person does not have protected access to safe and nutritious food in sufficient quantities for normal growth and development and active and healthy life. Instead of identifying significant predictors for a population in general, the study is interested in identifying each sub-population: urban and rural areas in West Java Province. A random forest algorithm was implemented to generate a model using both complete data and separate data. A follow-up analysis was then conducted by applying SHAP for both types of data and PFI for separate data. In general, the two approaches using SHAP resulted in quite similar feature importance levels. Meanwhile, the results of SHAP and PFI are relatively different. [ABSTRACT FROM AUTHOR]

To anticipate the choice dependent on recorded information is conceivable through Predictive Analytics. Machine learning calculations are arranged into four classifications: supervised, unsupervised, semi-supervised, and reinforcement learning. Be that, as it may, in this paper, we will consider supervised learning. The working of supervised learning algorithms is to prepare informational collection as information, which comprises features and class names for learning. Prior to learning, descriptive analytics is applied to authentic information to comprehend the highlights and their effect on preparing. When learning is finished, the classifier is applied on informational test collection or constant informational index, which comprises just features. The classifier needs to foresee the class name, which is obscure in the informational test index. Here we examine a portion of the famous supervised learning algorithms like SMO, Naïve Bayes, J48, Random Forest, k-NN and the performance of these algorithms on different datasets based on time and accuracy. ML algorithms can be applied on different applications, such as email messages as spam or non-spam, an estimate of client purchasing conduct dependent on recorded deals information, oddity location, misrepresentation disclosure, cancer detection, diabetes prediction, etc. Our outcomes anticipated that SMO is best at exactness and IBk is best at preparing rapidly. [ABSTRACT FROM AUTHOR]

The rate of death in heart failure patients keeps increasing, but the causes of death are always uncertain. Even though heart failure is a diverse syndrome classified by ejection fraction, the relationship among both ejection fraction and death rates is significant but elusive. According to health cardiology report, Patients with heart failure and reduced ejection fraction have greater risk of dying, compared with heart failure patients and preserved ejection fraction. However, the factors influencing the death rate of heart failure patients remains a challenging task for the doctors and researchers. With this motivation, this paper attempts to analyze the important features that influences the mortality rate of the patients. The Heart Failure dataset from UCI data warehouse repository is subjected for analyzing the heart failure patients. The dataset is preprocessed with data cleaning process and missing values. The preprocessed dataset is applied to all the classifiers and the performance of the mortality grading is analyzed before and after feature scaling. The raw dataset with entire 12 features are applied to Ada Boost, Random Forest, Extra Tree and Gradient Boost classifier to extract the top six important features to increase the accuracy performance. The feature importance dataset is then applied to all the classifier and the performance is analyzed in terms of accuracy, precision, recall, FScore and Run Time. The implementation results shows that random forest classifier is showing the accuracy of 89% after feature scaling and the random forest classifier with the feature importance of Gradient Boost classifier shows the accuracy of 97%. [ABSTRACT FROM AUTHOR]

The PM10 (Particulate Matter with diameter of 10 microns or less) is a major air pollutant with a number of harmful effects on human health. As a primary pollutant, it is also an indicator of the overall level of the ecological state of the environment. This determines the need and appropriateness of research on the accumulated empirical data, especially in affected areas. This paper examines the average daily PM10 levels in a specific region of Bulgaria, near the Black Sea coast and a large refinery for oil and petroleum products. The data of PM10 and meteorological variables such as air temperature, humidity, wind speed and others for a period of more than 6 years are studied. Using the Box-Jenkins ARIMA model, an autoregressive term was identified in the PM10 time series, which was used as an additional predictor in the models. Regression analysis with the Random Forest (RF) machine learning method is used for statistical modeling of the time series. RF models were obtained describing the data by almost 94%. The models are applied for short-term forecasts of PM10 pollution with 1 to 7 days ahead. The comparison with the actual measurements showed that the proposed approach gives very good results and could be embedded in mobile software for air pollution forecasting. [ABSTRACT FROM AUTHOR]

The paper below introduces an image classification workflow concept for biomedical purposes and present the process of determination of accuracy and probabilities in the analysis of large-scale biomedical data. The workflow is based on image features extraction through deep network embedding. The distance computation in the workflow is accomplished using Cosine distance. The experiments are conducted on the base of the Logistic Regression, Random Forest and Naïve Bayes and are directed on accuracy and probability in the analysis of large-scale data. The performed analysis shows the advantage of the Logistic Regression results which are considered to be the most reliable compared to the results generated through the Random Forest and Naïve Bayes. [ABSTRACT FROM AUTHOR]

Occupational Health Hazard is prevalently on the rise as industrialization increases in the global world. In the fireworks industry, manufacturing procedures for fireworks utilize hazardous chemicals for producing light, color, and sound. Fireworks manufacturing often necessitates human handling of dangerous chemicals, for all manufacturing processes where employees come into close contact with dangerous substances that cause illness to heath. It produces health implications that could result in diseases and sicknesses. Machine learning supervised algorithms were a dominating approach in the field of data mining. Recently, predictions on the health effects associated with hazardous chemicals have proven that these strategies may be applied. Each algorithm's experimental outcomes on the dataset have been examined. The purpose of this study is to discover major trends between different types of supervised machine learning algorithms and their performance and use to prevent ailment risk based on the work process. In comparison between the Support Vector Machine with Random Forest algorithm predicts that the severity level of disease would have the highest accuracy (90.7%), Sensitivity (88.8%) and specificity (92.6%). [ABSTRACT FROM AUTHOR]

Smartphone authentication is a widely discussed topic of research in the recent time because of the wide range of security sensitive personal applications and the associated private data. Traditional authentication methods like PIN, passwords, graphical pattern can't identify the actual user , since the one who enters the credentials correctly will get access to the smartphone application and its data. Physiological biometric security mechanisms like fingerprint and face recognition can provide moderate security to sensitive applications and data but are vulnerable to impersonation, spoofing and presentation attacks. Behavioral biometrics on the other hand, where authentication is done using the behavioral pattern, are proved to be an effective authentication mechanism and can be deployed as continuous and transparent which improve the usability and effectiveness of the authentication system. The proposed work in this paper is based on behavioral biometrics and the dataset is collected from 30 subjects, keeping the smartphone in 4 different positions, performing 5 different activities with each activity contributing to 63000 samples. The data collected are applied to a random forest classifier and the results are compared with different number of folds for cross validation, varying maximum depth for the tree and the number of generated sub trees. [ABSTRACT FROM AUTHOR]

Thermal conductivity and viscosity are crucial thermophysical properties of nanofluids. They play a pivotal role in industries involved with heat transfer applications. Alumina (Al2O3) nanoparticles are known to be a good additive for thermophysical properties enhancement with favorable results in countless research. However, the measurement of thermophysical properties of nanofluids through experimental is expensive. Therefore, the random forest (RF), an advanced computational intelligence approach, is proposed to correctly predict the thermal conductivity and viscosity of alumina-based engine coolant nanofluids in this research. Experimental data from previous literature are utilized as input parameters for the development of the random forest models. The input parameters for the prediction of thermal conductivity are temperature and concentration, whereas the input parameters for the prediction of viscosity are temperature, concentration, and shear rate. Error metrics consisting of R-squared (R2), Adjusted R-squared (A-R2), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) are used to analyze and determine the performance of each random forest model. Based on the results, it is observed that all random forest models exhibit significantly high and consistent predictive accuracy with R2 of 0.9877 for thermal conductivity prediction and R2 of 0.9974 for viscosity prediction. The predictive accuracy of the random forest models can be enhanced by training it with multiple datasets which include several thermophysical properties of diversified nanofluids. [ABSTRACT FROM AUTHOR]

The work utilizes the genome-wide association data sourced from subjects diagnosed with autism spectrum disorder (ASD) - Stage I and II. This system facilitates early and definitive prediction of autism to start intervention techniques at a young age. The Decision Tree model is used to classify the incoming gene-expression. Through the model selection stage, the performance of Decision-Trees and Random Forests was evaluated. This method of diagnosis, a combination of Machine Learning and Precision Medicine, ensures direct and a more conclusive diagnosis that can be adapted at feasible costs. The results are presented on a webpage using the Flask web framework. [ABSTRACT FROM AUTHOR]

Social media is serving majorly in all ways but on the other side, it is being misused in troubling the users by harassing, stalking, and blackmailing. From all among, the most availing is online bullying. It has become vividly common, especially among teenagers, with the expansion of the digital sphere all over. Thus, in order of detecting the harassment texts in comment sections or the tweets relative to any social media, we are going to train an ML model that automatically analyzes the text and classifies it and reverting to report the account to the helpline such that these accounts can no longer bully other users on social media. In this paper, we depicted our model and compared different algorithms like Decision Tree, Logistic Regression, KNeighbors, GaussianNB, Random Forest classifiers respectively. Atlast, we created a Web-Application that runs our trained model (Random Forest classifier with 94.4% score) in the backend which will be predicting the probability of being bullied comment with the defined constraints and based on that, detects and report cyber harassment. [ABSTRACT FROM AUTHOR]

There is a tremendous increment of liver sickness patients as a result of exorbitant utilization of liquor, breathe in of hurtful gases, admission of polluted food, pickles and medications. Therefore lot of burden is put on the doctors to identify a patient whether he is having any liver disease are not.This paper helps to reduce the burden on the doctor by analyzing patients conditions using machine learning techniques[1]. We also make a comparison of few machine learning algorithms like random forest,logistic regression and SVM and compare their accuracy levels in predicting the liver disease. [ABSTRACT FROM AUTHOR]

Cricket is an outdoor game which is highly common and extremely followed in Asia. This game has a huge fan following across the globe. There are three formats of playing Cricket. The challenges posed by each format is different from other. When two equally skilled teams clash, the outcome of the cricket match becomes highly unpredictable. Each team comprises of eleven members and the collective effectiveness of a team determines its win.This work is focused towards performing a thorough review of the various approaches and techniques that are deployed across the game of cricket and how they are instrumental in predicting the outcome of the game. Also a basic prediction model that uses classifiers like Support Vector Machines (SVM), Decision Tree and Random Forest. [ABSTRACT FROM AUTHOR]

Body Mass Index (BMI) is one of the most widely used characteristics when considering an individual's fitness. BMI is a metric that is used to distinguish people and label them as overweight, underweight, or fit, which is helpful in assessing their health status. BMI is related to cholesterol and body fat, and is an important predictor of diseases that can evolve as a result of higher body fat levels. Most people are unconcerned with their health due to a lack of physical exercise and a hectic lifestyle. For a higher body fat ratio, a higher calorie diet is more normal these days. Malnutrition, on the other hand, is more serious and pervasive than we would imagine these days. BMI is a method used to assess adult dietary status of both people and populations. We suggest a cost and time effective approach for estimating Height, Weight, and BMI from a human face in the real world, where people have less time in their busy lives and most people do not own a measuring tape or a weighing machine. Kernal Ridge and Random Forest Regression Models were used. The Face recognition module in Python is used to detect a person's face from an image. The image is then forwarded to the Feature Extractor model for processing. The derived features of height, weight, and BMI will be used in the regression models we used for further processing. For the validation of our concept, we used the VIP attribute dataset. The VIP attribute dataset includes photographs of men and women's faces along with their weight, height, BMI, age, and gender. When used as a Feature Extractor, the Random Forest Regressor model worked well for the weight attribute. Kernel Ridge performed well when dealing with height, while the Random Forest regressor performed well when dealing with the BMI attribute. [ABSTRACT FROM AUTHOR]

The implementation of high-speed broadband has resulted in a huge rise in internet use, which has skyrocketed as more people use remote access. Despite the fact that this rise in use allows for more online activities, the rapid growth of the Internet provides attackers with a wealth of network knowledge, and a large number of network threats has a negative effect on the network's development. Machine learning approaches are good at detecting unknown attacks. Random Forest, Decision Tree, Support Vector Machine, Logistic Regression, Gaussian Naive Bayes, and Gradient boosting Classifier are among the Supervised Machine Learning classification algorithms evaluated against the NSL-KDD dataset in this paper. Random Forest Classifier outperforms other methods in detecting attacks, according to the results of the experiments. [ABSTRACT FROM AUTHOR]

Currently, health management is a major concern all over the world. Particularly in India, due to population, the health issues are increasing rapidly. Diabetes has become a major issue that affects people all over India. With the advancement of Machine Learning approaches, many solutions have been developed to curb this serious issue. The goal of this paper is to design a model that can detect diabetes at preliminary stages with more accuracy. Therefore, various classification algorithms namely K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), and Gradient Boosting (GB) are used to solve this problem at earliest. Various performance metrics like accuracy, sensitivity, specificity, precision and recall are used for evaluation of the model. Evaluations are performed on PIMA Indian diabetes database, which is pulled from the Machine Learning cache. Results procured manifest that Random Forest outplay with the highest precision of 85.06%. The results are appropriately authenticated through a bar graph representation. [ABSTRACT FROM AUTHOR]

Lungs are a pair of spongy, air-filled organs that are a part of the Human Respiratory System. Cancer is a disease where the cell growth in a body goes out of control. Such uncontrollable abnormal cell growth in the lungs leads to lung cancer. Lung tumors can be categorized as small cell lung cancer and non – small cell lung cancer depending on the size of the cell as perceived under a microscope. More people are affected by non-small lung cancer than small-lung cancer. Tumors, which are detected at a prior stage have more likelihood of getting treated at a faster period, however, if left undetected or undiagnosed for a long period, it could lead to various obstructions. As a fact, the traditional methods used for diagnosing are time-consuming and have more probability of chances of errors. Thus a non – invasive method of diagnosing has been studied and discussed. In the proposed study, PET-CT images have been collected from various online databases and processed using Gradient Vector Flow (GVF) Algorithm. As a result of the study, the proposed gradient vector flow algorithm provides a precise segmentation in the lung images. Statistical features like mean, kurtosis, skewness, standard deviation, have been studied and compared between the normal and abnormal images. Thus a most precise and fast programmed method has been implemented to segment the lung tumor images using a gradient vector flow algorithm. Machine learning classifiers like KNN, Naïve Bayes, multilayer perceptron and random forest were analyzed. It was observed that the accuracy value of KNN classifier is 91.8%, Naive Bayes Classifier is 91.9%, Multilayer Perceptron is 89.1% and Random Forest Classifier is 87.9%. [ABSTRACT FROM AUTHOR]

Machine Learning is widely used technology in today's market, It plays an important role in healthcare industry. It is impossible to process thousands of medical reports manually but with machine learning algorithms millions of data can processed in no time. Using machine learning algorithms, it is possible to predict a disease within hours even before their onset, which is not possible in the real time. Sepsis is one among fatal disease brought by the body's reaction to an infection which in turn causes Systematic Inflammation Response Syndrome leading to a progressive organ dysfunction. With help of Ensemble approach, sepsis is predicted with improved accuracy (97.7%) using improved random forest. Our Proposed System is helpful for doctors to diagnose the sepsis very quickly compared to traditional way. [ABSTRACT FROM AUTHOR]

Diabetic retinopathy is a possible complication of diabetes that causes severe eye problems and, in some cases, blindness in adulthood as a result of an increase in glucose levels in the physical body fluids. The diabetic retinopathy, if it is detected early will avoid the harm to retina and eye sight damage or a minimum of reducing its development. Most important objective of the current research was to produce a CAD system so as to spot diabetic retinopathy by removing red lesion both Micro aneurysm and Hemorrhage. The extracted retinal images will be validated with several image databases. Digital retinal fundus pictures got from sixty Indian subjects where forty images from Messidor information base and another forty pictures from DIARETDB1 data set. They were used for various examinations, and a hand-drawn 'ground truth' result was gathered for each image. The proposed calculation has been evaluated quantitatively using Support Vector Machine and Random Forest classifiers. The results are connected against the 'ground truth'. The highlights like mean region of the segmented area, Eccentricity and Solidity were extricated for all test dataset. The CAD framework for Diabetic Retinopathy screening will be approved with public fundus image dataset, containing the ground certainties. The images are gathered from numerous expert doctors and contrasted with privately accessible data set. The proposed Random Forest classifier gives the Sensitivity of 95%, Specificity of 90% and Accuracy of 94%. In this way, the proposed CAD framework may be helpful for Diabetic Retinopathy screening. [ABSTRACT FROM AUTHOR]

The healthcare sector consists of vast amounts of data that is often utilized less. The need for this utilization of unused data arises from the requirement of computational decisions supports in smart hospitals for the early diagnosis of different diseases. Heart illness is one of the diseases responsible for so many deaths worldwide, even more than cancer. Heart disease counting is increasing day by day. It may be reduced by early analysis and medication. Utilization of the latest technology may help in the diagnosis of heart disease timely. This work focuses on the likelihoods of occurring heart diseases in terms of percentage, thereby introducing an innovative methodology for classifying heart by various supervised machine learning techniques such as Naive Bayes, KNN, random forest, SVM, decision trees & ensemble methods to handle multivariate datasets in nature. However, only a few of those techniques will be approved for the generation of consistent, precise as well as biologically interpretable rules. Results will be then interpreted to compare the algorithms used on the basis of the accuracy level acquired by each algorithm. [ABSTRACT FROM AUTHOR]

Power generation from renewable energy sources is key to a clean energy future and solar energy is world's fastest growing energy sector. Solar energy is renewable, CO2-free and with low operational cost. There are several advantages of using solar energy; however, it does have a few drawbacks such as hefty initial cost, high-priced storage, weather dependency, sizable space requirement, etc. As such, it is critical to predict solar radiation (SR) in an accurate and efficient way to install solar plants in optimal locations. Factors like global horizontal irradiance (GHI), temperature, humidity, cloud cover, wind speed, etc. make SR highly intermittent and variable. Accurate forecasting of SR is vital to finalize installed capacity of the proposed power plant but is extremely challenging due to unpredictability of sunlight. Even the world's best organizations such as the International Energy Agency (IEA) finds it difficult to accurately predict SR. In this work, we analyze global and diffuse SR data gathered from India Meteorological Department (IMD) Pune. This data is first analyzed for features, dominant features are identified, and several machine learning algorithms are employed. Random forest method provides the best results on this data based on several quantitative measures. [ABSTRACT FROM AUTHOR]

During the purchase of mobile phones, various features like memory, display, battery, camera, etc., are considered. People fail to make correct decisions, due to the non-availability of necessary resources to cross-validate the price. To address this issue, a machine learning model is developed using the data related to the key features of the mobile phone. The developed model is then used to predict the price range of the new mobile phone. Three machine learning algorithms namely Support Vector Machine (SVM), Random Forest Classifier (RFC), Logistic Regression are used to train the model and predict the output as low, medium, high or very high. The dataset used in this study is taken from Kaggle platform. In order to improve the classification accuracy, Chi-Squared based feature selection method is used. Among 21 features available in the dataset, only top 10 features namely RAM, pixel height, battery power, pixel width, mobile weight, internal memory, screen width, talk time, front camera and screen height are selected and used to train the model. Before applying feature selection, the accuracy obtained using SVM, RFC and Logistic Regression is 95%, 83% and 76% respectively. After feature selection, the accuracy of SVM, RFC and Logistic Regression improved to 97%, 87% and 81% respectively. From the experiments conducted, it is found that SVM gave superior performance when compared to other two classifiers. [ABSTRACT FROM AUTHOR]

Machine learning (ML) prediction Algorithms have exemplified their capacity to foresee perioperative results in order to enhance prospective course of action decisions. In many application domains, the ML models have long been used which needed to recognise and prioritise adverse threats. A number of tools for statistical problems and data comprehension are also used to address decision-making. This study demonstrates the ability of ML models to predict the number of future patients affected by COVID-19 who are currently considered to be a abeyant intimidation to hominids. Three standard models, such as linear regression (LR), Decision tree regressor(DR), Random forest regressor(RFR). LR models make Three types of predictions, such as the amount of newly infected cases and the amount of recoveries, Amount of Deaths based on COVID-19 tests on each phase. The study divides into three stages(peak, transition, slowdown). DR and RFR help to understand insights of data. Results show the unlockdown causes for rapid increase in Covid infection rate, 78% deaths happen due to covid-19 in peak stage only. Andhra Pradesh's average infection rate is 16.58% near the ICMR Third Sero Sample Survey. In Andhra Pradesh, testing is a primary parameter as opposed to population density. Chittoor, Guntur, Krishna, Nellore, Visakhapatnam Are The Five Host Spot Districts For Covid-19 Spreading In Andhra Pradesh State. [ABSTRACT FROM AUTHOR]