Search

The direction of numerical projections has actively been developed in recent years by an intensive investigation of processed observational data to identify trends of change and generate numerical data of climatic parameters for the future. Weather forecasting offers knowledge that people and organizations may use to lessen weather-related losses and improve social benefits. This study compares different machine learning models in an effort to identify which one provides the most accurate weather prediction data. In our proposed approach, we employed the models such as GridSearch Cross Validation, Random Forest, Logistic Regression, and Gaussian Naïve Bayes. The Random Forest Tree method, which has a very high accuracy of 99%, is judged to be the best for predicting the weather after evaluation. [ABSTRACT FROM AUTHOR]

Eye defects in teenagers is becoming more prevalent these days, especially due to the pandemic situation. Digital eye strain due to excessive usage of gadgets can result in a prescription for spectacles, which is a basic test in any ophthalmology clinic, but due to the current situation of the pandemic, visiting a clinic might be risky. In this project, we propose an AI (ML) model for spectacles prediction based on a few input parameters through an app. AI machine learning models are used widely in the medical sector. Here, we applied three different machine learning models (logistic regression algorithm, decision tree algorithm and random forest algorithm) to extract maximum accuracy prediction using the dataset we collected from teenagers. We achieved highest accuracy of 97% using logistic regression model and made a website to predict spectacles. [ABSTRACT FROM AUTHOR]

Cybercrime has been on a massive increase for several years. As more individuals conduct business and live their lives online, more criminals are turning to the internet to steal. With the developments in cybersecurity, adoption of best practices, cybersecurity awareness initiatives, and increased regulations and partnerships between businesses and governments to resolve the problems, cybercriminals may be feeling the pressure. In this paper, we are going to predict operating system vulnerabilities using machine learning algorithms. And evaluate their accuracies through training them. The aim of the paper is to use Machine Learning algorithms to predict with accuracy operating systems vulnerabilities. Different ML algorithms have been analyzed, such as Logistic Regression, Support Vector Machine and Random Forest. And, out of all of these algorithms, Random Forest had the highest accuracy of 99.33%. [ABSTRACT FROM AUTHOR]

The accuracy and precision with which Logistic Regression (LR) and Random Forest can predict forest fires are compared in this study (RF). The List Consists Of The Random Forest method outperforms other machine learning techniques in fire detection speed and accuracy. To better detect forest fires, a system that compares Random Forest with Logistic Regression was developed. Using G power, we determined that 28 people were needed for each experiment. The sample size for the pilot study was calculated to be 95 percent confident. The dataset shows that the Random Forest (RF) model is 95 percent accurate in predicting forest fires, whereas the Logistic Regression (LR) model is 62 percent accurate. The p-value for Logistic Regression is 0.005, but Random Forest is a superior classifier. In terms of accuracy and precision, Random Forest is superior to Logistic Regression. [ABSTRACT FROM AUTHOR]

The study's primary objective is to compare the efficacy of the state-of-the-art SVM method for image prediction with that of KNN, Logistic Regression, Random Forest, and Decision Tree. The UCI Machine Learning Laboratory provides a total of 569 samples. Groups like SVM, KNN, Decision Tree, Random Forest, and Logistic Regression are used to the samples after they have been separated into benign and malignant cells so that their respective performances may be compared. G power calculation is used to determine how many samples are needed for this analysis. The maximum acceptable error is set at 0.5, and the minimum power of analysis is set at 0.8. Predictions made using Logistic Regression appear to have a higher accuracy(95%) than those made using SVM, KNN, Decision Tree, or Random Forest(92%,90%,85%, and 91%). This proposed system has a probability importance of 0.55. The Wisconsin dataset was used to compare Logistic Regression against SVM, KNN, Decision Tree, and Random Forest for the detection of breast cancer. [ABSTRACT FROM AUTHOR]

The goal of this study is to utilise machine learning classifiers to categorise people's income levels, namely those with and without a household income of $50,000 or more. We examine two common algorithms in this study: Random Forest and Logistic Regression Algorithm. This experimental inquiry makes use of the Adult Income dataset, which has 32516 items. An experiment with N=10 repetitions was carried out in order to discriminate between income groups of more than $500,000 and less than $40,000. For statistical reasons, the G-power test is run at 80%. The trials demonstrate that the Random Forest Algorithm has an average accuracy of 84.1840, whereas the Logistic Regression Algorithm has an average accuracy of 79.6410. Statistical analysis reveals a substantial difference in accuracy between the two techniques, with a p-value of 0.032 for the t-test on independent samples. The results reveal that the Random Forest Algorithm outperforms the Logistic Regression Algorithm. [ABSTRACT FROM AUTHOR]

Now-a-days, Health care industries are literally playing a major role in curing the diseases that are suffering the people. And this will be one kind of help to health care industries. In present days, people are facing lot of issues related to their health due to their life style and their livelihood. Due to their busy schedule in their lives, people are not at all taking care of their health. They are not having the time to consult doctors and know what they are going through and it may lead to severe risk for them. So, People should be aware of what they are going through at early stage will reduce the high risk. In our proposed system we used logistic regression, Random Forest Classifier and Decision tree classifier in prediction of the disease. Disease Prediction is a supervised model that is used for prediction of diseases from the symptoms or the information provides by the user. This proposed system will process the symptoms entered by the user and provide the predicted disease as an output. [ABSTRACT FROM AUTHOR]

Network security has emerged as an essential issue as an outcome of the Internet's broad consumption. The efficiency of anomaly-based detection systems for network intrusions (IDS) as a tool for spotting illicit traffic has risen. IDS's precision and efficiency have been enhanced with the assistance of ML methods. The performance of multiple machine learning (ML) algorithms in anomaly-based intrusion detection is compared in this paper using KDD-CUP-99 dataset. The algorithms considered include Voting, LightGBM, Decision Tree, KNN, Random Forest, AdaBoost, Naive Bayes Model, CatBoost, and Logistic Regression. The study's findings indicate that the Decision Tree, Random Forest, LightGBM, and Voting algorithms did remarkably well and exhibited high rates of accuracy, while Naive Bayes performed inadequately. This study comes to the conclusion that using ML algorithms might greatly improve the precision of knowledge-based network intrusion detection and provide a workable network security solution. [ABSTRACT FROM AUTHOR]

Coronary heart disease has been ranked as the number one leading cause of death in Malaysia. Based on the recent data published by WHO in 2018, death caused by this disease has reached 34,766 which brought up to 24.69 of the total deaths and places the Malaysian population 64th in the world. Medical researchers all around the world believe that there are multiple circumstances for this disease which include health problems, unhealthy personal habits, genetics, and family history. It is not an easy task to predict heart disease since the study needs a broad range of expertise from many disciplines. Recently, machine learning had been applied as one of the methods to predict heart disease. To test the accuracy of different machine learning methods, this study is conducted by applying the data extracted from the machine learning repository. The proposed predictive modelling in this study was developed using the ensemble method. The ensemble technique used was stacking where logistic regression was used as the meta-level classifier while Random Forest and k-nearest neighbour method were applied as the meta-level classifiers. Results obtained from this study show that the proposed method outperforms other single methods with 82.42 accuracies. Although the accuracy and RMSE of the ensemble method are similar to Random Forest, the proposed method is still the best method since it has a 0.903 value for the area under the ROC and 0.843 value for F1 score. This proposed predictive model will be applied by using smartwatch datasets for future study. [ABSTRACT FROM AUTHOR]

Breast cancer is a major concern to middle-aged women across the globe, and it is now the second leading cause of cancer mortality in women. SVM, KNN, and Random Forest, Decision Trees are the primary focus of my research. Samples from the University of California, Irvine's Machine Learning Laboratory total 569. SVM, Decision Tree, Random Forest, and KNN are used to classify the samples as either benign or malignant based on the appearance of the cells. G-power calculations are used to determine the number of samples needed for this study. The analysis's minimum power is set at 0.8, while the tolerated error level is set at 0.5. As compared to SVM, KNN, and Decision Tree, Random Forest predicts a 95 percent accuracy rate (compared to 92 percent, 90 percent, and 88 percent, respectively). This system has a significance of 0.22. Random Forest outperforms SVM, Decision Tree, and KNN in the identification of breast cancer in this innovative picture prediction. [ABSTRACT FROM AUTHOR]

The study's primary goal is to identify accuracy in auto loan eligibility utilising machine learning techniques, namely the Logistic Regression Algorithm and the Novel Random Forest Algorithm. The Logistic Regression and Random Forest algorithms were iterated 180 times with a sample size of N=90 to determine the accuracy of automobile loan eligibility. The novel Random Forest method outperforms the Random Forest algorithm in terms of accuracy (87.02%). The loan prediction independent samples T-test has a high significance (p<0.05). When the results were compared, the Random Forest algorithm outperformed the Logistic Regression approach in terms of discovering accuracy in automobile loan eligibility. [ABSTRACT FROM AUTHOR]

Heart Disease is one of the diseases that cause deaths in large numbers, so predicting these diseases is one of the most necessary tasks in the field of heart to reduce the number of deaths by providing health care to patients, so the process of forecasting these diseases aids in reducing disease-related risks and alerting patients to them. In this paper, Machine Learning (ML) algorithms were applied to a set of medical data to help diagnose these diseases and predict the chances of infection by using different data mining techniques like Decision Tree (DT), Naive Bayes (NB), Random Forest (RF), and Logistic Regression (LR). The dataset used 615 samples of medical data from the Kaggle Repository. After a comparison between these algorithms, the RF algorithm had the highest accuracy of 97.40% then LR with 90.24%, NB at 87.1545 %, and finally, DT with the low accuracy of 72.3577 %. It also used other evaluation matrices such as precision, recall, and f-measure for each algorithm, then compare accuracy founding with another paper using the same dataset and algorithm. [ABSTRACT FROM AUTHOR]

Software is becoming more complex, and lengthier in size, and needs to be updated on a time basis. But the constant change in codes has a high chance of arising faults that adversely affect the system performance. To avoid this interruption, and to improve the overall performance of software, a fault prediction system is required. The nature of the fault depends upon various parameters, but it is also important to identify the role of parameters in fault generation. In this paper, four feature selection techniques (Correlation Coefficient, Fisher Score, LASSO, Recursive Feature Selection) are applied on three machine learning methods individually (Random Forest, Logistic Regression, SVM) using Python 3.8 to compare the result for highest performance. The result clearly shows that Random Forest gives the highest accuracy of 95% when combined with the Fisher Score feature selection technique. The outcome shows that rather than using all features of any data set, a selected feature should be used for better fault-free software performance. [ABSTRACT FROM AUTHOR]

Distributed Denial of Service (DDoS) attack is a massive menace to web based systems. It immediately overwhelms the web-based system in a short time and interrupts their services. Numerous traditional techniques have been available to detect different kind of DDoS attacks. However, there are several issues encountered with these traditional techniques, such as they require more time for analyzing incoming traffic, failing to identify attacks in real-time, thus itself becoming the victim of DDoS attacks. Therefore, to resolve these issues, we need to implement the DDoS detection system in distributed framework and our proposed approach relies on the distributed Spark Framework. In our DDoS detection approach we worked with different machine learning algorithms, such as Multiclass Logistic Regression, Naive Byes, Decision Trees, and Random Forest. We evaluated our approach using the CIC-DDoS2019 dataset. The reporting results highlights that Decision Tree and Random forest gives us almost equal accuracy and produces best results in detecting DDoS attack in comparison to other machine learning algorithms. [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]

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]

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]