Search

Attacks like Distributed Denial of Service (DDoS) pose a major threat to the network's security. Many different firms' servers have fallen prey to such unusual types of attacks. These attacks from the many bots under the direction of the botmaster (cracker) can possibly result in the victim's computational and communication capabilities being severely impaired. To create an effective NIDS, the researchers used datasets that were made accessible to the public. Existing studies' datasets, however, are insufficient since they exclude the most commonly used protocols, such as DHCP, which is essential to network architecture. In a network, IP addresses and other crucial network setup settings are dynamically assigned via the Dynamic Host Configuration Protocol (DHCP). Two research inquiries serve as the foundation for this work: 1) what algorithm will get the best results for identifying Distributed Denial of Service attacks? 2) How accurate would these algorithms be if they were trained on real-world data? We exceeded 96% accuracy with the Random Forest Classifier, and we confirmed our findings using two measures. The results were also compared to other works to ensure that they were adequate. We also provide a thorough study to back up our conclusions. [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]

Cricket is the more popular game with uncertainty like a single ball can change the results. Players must concentrate more on t20 and One-Day matches without diverting their presence of mind. The sponsors invest more money in the game and players for their brand advertising. The match depended on various parameters such as player performance, pitch, team binding, etc. So, selecting a player and forming a team is essential for sponsors. Predicting player performance based on previous records will take a lot of work, so many researchers have taken forward steps to analyze the data. Machine learning algorithms, such as Linear Regression, SVM, Random forest, etc., have been implemented in various research studies. In our study, we have implemented the Artificial Neural Networks model to predict the player batting performance based on the koggle.com dataset. According to our model, ANN has provided 86.21% accuracy in predicting a player. [ABSTRACT FROM AUTHOR]

The cardiac attack is considered to have high mortality due to lifestyle habits and dietary regimes. Prediction of heart disease based on medical history of patients is critical. As privacy of sensitive data is also of concern, digital fingerprint collected from vast amount of data generated by the healthcare sector is made easier with the help of Machine Learning (ML). With advances in technology application of internet of things (IoT) in healthcare is also gaining popularity. Application of algorithms to predict heart attack is also evident. In the current work, we propose to predict cardiac arrest using medical history for the patients data and select the features best suitable for based on a comparative analysis among the ML models. Different feature selection metrics and classification models are used for prediction. ML algorithms like Regression, Decision tree, Random Forest, Support vector machine, Naive Bayes, and K-nearest neighbor have been used. Our results show the importance of medical history in prediction of cardiac disease and diagnosis. [ABSTRACT FROM AUTHOR]

Mineralogy plays an important role in the early stages of earth resource exploration. In the past decades, geologists started to use hyperspectral in various scales of mineral identification, from hand specimen samples to airborne geological mapping surveys. Performing conventional mineral classification with hyperspectral methods is time-consuming and requires significant human intervention, from the endmember selection for each mineral to validating the classes manually in laboratory analysis. In this study, we introduced supervised machine learning algorithms to stimulate the mineral mapping process of a large dataset of core data. Three hyperspectral imageries of milled pebbled samples were used where one of the samples was pre-identified and used for training machine learning models to identify the mineralogy of the other two samples. The samples contain four minerals; namely Muscovite, Tourmaline, Illite and High-Crystallinity Illite, that will be auto-identified by the machine learning algorithms. In this study, Random Forest and Convolutional Neural Network were the selected algorithms to perform the mineral identification. Both algorithms produce high-accuracy mineral maps compared to the existing mineral maps from the previous study. The Convolutional Neural Network struggled to identify High-Crystallinity Illite, whilst Random Forest succeeded in separating High-Crystallinity Illite from other minerals. Thus, the Random Forest algorithm produces higher accuracy results. The proposed workflow provides a time-efficient alternative methodology for further mineral mapping process on a larger scale dataset. [ABSTRACT FROM AUTHOR]

The rate of penetration (ROP) prediction is carried out using a recorded drilling dataset from 02-Well. The prediction approaches use machine learning random forest regressor model and artificial neural network, especially the MLP regressor. The aim is to make the best machine learning model accurately predict the ROP parameter at 02-Well. The method used is designing the architecture of the machine learning model, which is divided into five stages: exploratory data analysis, data pre-processing, prediction and modeling using the selected algorithm, hyper-parameter tuning, and model evaluation. The 02-Well dataset would be divided into a 70% training set and a 30% test set as the base case. The model evaluation results show that modeling using a random forest regressor has a mean absolute percentage error (MAPE) score of 19.81%, which belongs to the "Good Forecasting" criteria. Meanwhile, modeling using MLP regressors has a MAPE score of 22.84% with the "Reasonable Forecasting" criteria. [ABSTRACT FROM AUTHOR]

Fake news is a type of essential problem on social media. The rapid circulate of fake news has an ability for disastrous influences on human beings and the society. Thus, it becomes more useful to detect fake news on social sites or internet. Recently, many models have been developed to detect the fake news from the publicly available datasets. In this paper discussed the various machine learning algorithms and their performance analysis on two different news data. The proposed framework contains two step process. In the first step, clean the data and extracted features by TF-IDF and Hashing Vectorizer. In the second step, machine learning algorithms (Logistic regression, Decision Tree, Random Forest, Multinomial Naive Bayes, and Passive Aggressive classifier) have been applied in an effective and efficient manner. Comparative analysis revealed that the optimal performance is achieved by the Logistic regression and Passive aggressive classifier, 95.45% and 97.35% respectively for two public datasets. [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 purpose of this study was to assess the accuracy of cybercrime predictions provided using Novel Random Forest and Support Vector Machine. Material and Procedure: Cybercrime predictions were made using the new random forest (N=10) and the support vector machine (N=10), which were then analysed. Random forest trumps SVM in terms of precision (by a margin of 84 percent to 85 percent). 81 percent is the percentage. The advanced random forest classifier performed better than the conventional SVM classifier. There is a significant difference in accuracy between the two approaches (p>0.005). The development of the new cybercrime prediction system used machine learning. This novel random forest technique outperformed SVM. [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 prediction rate of social vulnerability in a web application based on a comparison of the F1-Measure of novel Reinforcement learning and the Random forest method. Components and Techniques: Outcome F1-measure and the Random Forest Algorithm with a New Reinforcement Learning Algorithm (83.85 percent). There are a total of 55,336 samples to be analysed, split evenly between two groups. Discussion and Results With an F1-measure score of 83.85 percent, the novel Reinforcement learning algorithm outperforms the more traditional Random forest approach for detecting social vulnerability (74.58 percent). In this study's final analysis, the Novel Reinforcement Learning algorithm was shown to be more accurate in predicting social vulnerability than the Random Forest technique. [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 purpose of this study is to apply machine learning methods to the problem of classifying musical genres. Here, signal processing is used to extract the rhythm pattern feature, which is then used in conjunction with machine learning algorithms to provide a multiclass categorization of musical genres. A preexisting internet music collection is used to generate two distinct datasets, one with undersampling and the other with oversampling to achieve class balance. Two types of models were compared for their efficacy in this research. The first model is an enhanced support vector machine that is fully trained to identify the musical genre of an input signal from its spectrogram. The Random Forest Classifier is the second model. G power for this research is 80%; there are two groups in total, and each has a sample size of 20. Experiments performed on the audio dataset show that an assembler classifier that takes use of both techniques achieves an AUC of 0.894. According to the findings, the support vector machine method provides a higher accuracy (69.24%) than the Random Forest Classifier (64.26%). Independent sample T-test significance level of P=0 (P 0.05, 2-tailed). The findings showed that the accuracy of the music genre classification using the enhanced support vector machine with an unique Rhythm pattern feature method was higher than using the Random Forest Classifier. [ABSTRACT FROM AUTHOR]

The purpose of this research is to compare and contrast how well the random forest algorithm and the decision tree method perform in classifying fire and smoke photographs. With a g power of 0.8 and an alpha of 0.05, we find that out of a total of 4000 photos, 2000 depict fire and the remaining 2000 depict smoke. In this case, we split the dataset into a training set (n=3200, or 80%) and a validation set (n=800, or 20%). Classification tasks are executed with the help of the Sklearn machine learning package in Python. Precision, recall, f score, and accuracy numbers are some of the metrics used to measure an algorithm's effectiveness. When compared to the Decision Tree algorithm's 90.54, 90.00, 90.9, and 89.70 percent accuracy, F-score, recall, and precision, Random Forest achieved 97.42, 97.28, 97.43, and 97.15 percent values, respectively (p0.001(2-tailed)). The results of this research show that the random forest method outperforms the decision tree algorithm by a wide margin. [ABSTRACT FROM AUTHOR]

In this study, we compare Naive Bayes (NB) and Novel Tree Specific Random Forest for their ability to forecast the downstream impacts of air pollution (RF). Naive Bayes has a greater recognition rate than other machine learning algorithms and is thus more effective in detecting air pollution. Naive Bayes over Novel Tree Specific Random Forest is presented and developed as a framework for identifying air pollution to mitigate its aftereffects. Using G power, we determined that we needed 96 participants in each group. The sample size, consisting of 48 individuals per group, was determined using a pretest power of 95%. The goal of this study is to enhance the performance of the algorithm throughout the harvesting process. Average detection accuracy is within one standard deviation, suggesting that the suggested model is both effective and quicker than the current approach. The level of significance is 0.006 (p0.05). Findings highlight Naive Bayes' superior accuracy and precision compared to Random Forest. [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]

The goal of this research is to catalogue all of the undesirable materials available on rival and popular social media platforms. Tools and methods: The dataset for training and testing the proposed prediction models was constructed using the messages from a number of popular social media messaging platforms, with a minimum of 5 attributes and 150 messages. Random Forest, a machine learning algorithm, was used to design the framework, and it was compared favourably to the Support Vector Machine algorithm. Discussion and Remarks: Accuracy in retrieval is 90.30 percent for the Random forest algorithm and 94.36 percent for the Support vector machine learning algorithm (countvectorizer). The significance level between the two algorithms is high at p=0.02 (p0.05). This study confirms that the SVM (countvectorizer) Machine Learning algorithm has a higher accuracy rate than the Random Forest algorithm and creates a novel framework to identify spam words. [ABSTRACT FROM AUTHOR]

Improved prediction of SQL injection vulnerabilities using a comparison of F1-Measure in a Random Forest model and Novel Reinforcement learning. Accuracy in Outcomes and Random Forest's Reinforcement Learning Innovations (83.8580 percent). There are a total of 55,336 samples to be analysed, split evenly between two groups. With an accuracy of 83.8580 percent, the reinforcement learning algorithm outperforms the support Random Forest algorithm's 74.5890 percent accuracy by a statistically significant amount (P0.004). The results of this research show that when it comes to predicting SQL injection vulnerabilities, the Novel Reinforcement learning Algorithm performs significantly better than the Random Forest algorithm. [ABSTRACT FROM AUTHOR]

The increasing population, accompanied by the development of technological advances, especially in the world of transportation, has led to the creation of vehicles of various types and the increase in CO2 gas emissions resulting from the combustion of vehicle fuels. The need for estimation efforts to determine the estimated CO2 gas emissions produced by vehicles with different engine sizes, cylinders, and fuel consumption. Machine learning-based estimation using a regression model. There are seven regression models, including Linear Regression, Support Vector Regression – Linear, Support Vector Regression – RBF, Decision Tree Regression, Random Forest Regressor, Gradient Boosting Regression, and NLP Regressors were compared in this study. We will look for the best model with the best accuracy value. The Gradient Boosting Regression model has a better accuracy increase in 4 accuracy tests with training and test data ratios of 90:10, 80:20,70:30 and 60:40. As a result, the Gradient Boosting Regression method has an accuracy rate of 98% with an RMSE of 5.89426278 at a data test ratio of 90:10 and 96% at a data test ratio of 70:30 with an RMSE of 11.29584732. [ABSTRACT FROM AUTHOR]

Multilevel inverter technology is the best preferred choice of high and medium power industrial control applications and its reliability is often lowered by the solid state switches such as IGBT/MOSFET. Timely monitoring and accurate identification of faulty switches is always a challenging area. Numerous measures using current measurement have been recommended to identify and localize any fault in switching devices of inverters. In view of the complications of load current addressed fault finding practices, this work focuses on voltage features of inverter which is independent of load variations. Random forest algorithm is a dominant machine learning process useful in the alignment of large data base and it is considered in this work for identification of faulty switches of multi-level inverter. Results show that random forest algorithm can be used for finding the faulty switches of multi-level inverter in an effective manner. [ABSTRACT FROM AUTHOR]

Face recognition has increasingly favored over other biometric modalities such as fingerprint, iris, that have historically been seen to be more reliable. This is because face recognition has become more accurate over time. Face recognition has certain distinct advantages over other biometric modalities one of which is that it is less intrusive. Modern facial recognition systems just need users to be in the camera's field of view. It can be used in many environments, recognition is greater where the system does not expect people to cooperate, such as in security measures. Face recognition without occluded parts can no longer meet the needs of modern society. The face recognition in complex environment needs to be addressed w.r.t the real-world situation. Thus, we have proposed face recognition system for detecting the masked and unmasked images efficiently. The dataset used for the experiment consist of 50 individuals with 50 images with masked and 50 unmasked images. The collected images were in different orientation, illumination and poses. For the purpose of face recognition, only the area the face had to be cropped and saved. So, only the face from the image was cropped using Haar-Cascade model to identify the face from the image. For masked images, a dlib script MaskTheFace is used to mask the unmasked faces and prepare a synthetic dataset of masked faces. Further, feature extraction is done using different techniques such as Histograms of Oriented Gradients (HOG) and Local Binary Pattern (LBP). Finally, we have analyzed the performance of Machine Learning algorithms like Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF) for face recognition using face as a trait for masked and unmasked persons. [ABSTRACT FROM AUTHOR]

Assessing type of soil and its required nutrients is an important domain in modern agriculture. So moving towards the same vision, this research work addresses this issue of forecasting suitable crops on the basis of environmental factors and its yield based on previous data sets available on the net. The study not only discusses yield and crops, but also stresses on the amounts and types of nutrients present in the soil beforehand by using supervised machine learning algorithms. Among different models used, random forest generates the best performance. Further in the paper we will see how random forest provides us an accuracy of 93% and the least error rate of only 0.3% among all other algorithms using rainfall as a parameter to predict our desired crops. [ABSTRACT FROM AUTHOR]

Within the banking industry, requests for credit cards are growing tremendously, and manually reviewing each application is frequently a tiresome task that is also prone to human error. In this situation, banks and other big financial institutions can use a machine learning model to forecast whether or not to grant the customer a credit card. Banks utilize machine learning techniques to process their financial data, extract knowledge from it, and use it for risk management and decision-making. This study has created, trained, and evaluated three classification models utilizing authentic Kaggle datasets. The main research goal is to assess and contrast the models based on how accurately they project the composition of the typical class. In this work, we examine the accuracy, F1 Score, Precision, and confusion matrix of different supervised machine learning models to estimate the probability that a credit card request would be approved. After testing three classifiers, it is discovered that Random Forest outperformed Decision Tree and Logistic Regression. Random Forest's accuracy is 94.67%, precision is 0.85, recall is 0.980, and F1 Score is 2.940. [ABSTRACT FROM AUTHOR]

Selling and purchasing products online is made possible by e-commerce. For both service providers and clients, organizing and looking for items is a tedious procedure. The items must be organized and labeled, which takes up a lot of time. Product categorization is the process of automatically predicting a product's catalog route based on a predetermined catalog hierarchy in which all categories are formulated. Knowing how to add your goods to the most relevant category on any marketplace, including Flipkart, and Amazon is crucial to its selling. Categorization is a lengthy process that takes extensive study on the platform which has been improved with different methodologies used in this work. Machine Learning (ML) and Deep Learning (DL) models are used to sort items into recognized categories. Using information such as the item's title and summary, this model can properly classify it in each classification. Random Forest (RF) outperformed the other ML models, such as SVM, KNN, and Naive Bayes (NB), with an f1-score of 97 percent and a macro average of 94 percent. BERT model fared the best among the DL models (LSTM, CNN, BERT, and Hybrid CNN - LSTM model) with an f1-score of 97 percent and a macro average of 88 percent. [ABSTRACT FROM AUTHOR]

In today's world, being the easy availability of the internet, almost everyone is connected. Every individual for their daily news relies on online resources, which greatly impacts their quality of life. The development of social media platforms has grown tremendously. However, many of these platforms are spreading fake news that pauses serious concern. It leads to a decrease in income for individuals or companies. Some people often create fake news for gaining fame, for election purposes, and for creating hatred towards other companies to reduce their revenue. All these can have negative consequences on society. Just by the use of a single click, many people forward appealing headlines, photos, etc. to gain the attention of an individual, without even checking whether it is fake or not. It is hard-core truth that many false websites give false news and checking their authenticity is really a challenge. This paper presents a comparative analysis of methods for the user to check the news whether that's real or fake by providing accuracy and recall using machine learning. The models used are naïve Bayes (NB), decision tree classifier (DT), random forest (RF), and logistic regression (LR) for analysis to detect fake news. The result shows that the DT classifier achieved 99.56% accuracy as compared to RF (99.35%), LR (98.91%), and NB (94.89%). The recall also shows better results for DT and RF than LR and NB. Lastly, it discusses some of the security threats and challenges faced while detecting fake news. [ABSTRACT FROM AUTHOR]

The detection of chest diseases from X-ray images is a crucial aspect of medical diagnostics, playing a vital role in the early identification and treatment of respiratory conditions. This review paper gives a general overview of how machine learning algorithms are used to identify chest diseases from X-ray pictures. It emphasizes the importance of accurate and timely diagnosis of chest diseases, while acknowledging the challenges faced by conventional diagnostic methods. The review highlights the potential of machine learning as a promising approach to enhance diagnostic accuracy and efficiency in this field. It explores the utilization of both handcrafted features and deep learning-based approaches for extracting informative features from chest X-rays. Furthermore, it discusses the adoption of various machine learning algorithms, including support vector machines, random forests, and convolutional neural networks, for effective detection of chest diseases. The review paper also recognizes the significance of training and validation strategies in ensuring the robust development of models. Additionally, it addresses the potential impact of the proposed methodology on chest disease detection and patient outcomes. The review paper discusses challenges and limitations associated with this approach, such as data availability, interpretability, and ethical considerations. In summary, this extensive analysis strives to make a valuable contribution to the field by offering insights into cutting-edge machine learning techniques, recognizing existing challenges, and proposing potential avenues for future research. [ABSTRACT FROM AUTHOR]

Brain cancer is a highly lethal form of cancer with low survival rates and expensive treatment costs. Detecting tumors at an early stage is essential for improving patient outcomes, and the utilization of machine learning (ML) algorithms has demonstrated potential in augmenting the accuracy of brain tumor detection. This research aims to develop an ML model that predicts the likelihood of brain cancer by combining various factors. Four popular ML algorithms, namely Random Forest, Support Vector Machines (SVM), Gradient Boosting, and Decision Tree, are compared for their performance in this task. The dataset used in this study is obtained from Kaggle, a platform for data science competitions and projects. Among the four ML algorithms evaluated, Gradient Boosting achieved the highest accuracy of 83.9%, followed by Random Forest with 81%, SVM with 80.2%, and Decision Tree with 74.1%. To gain further insights, the research conducted feature importance analysis to identify the factors that contribute most significantly to the prediction of brain cancer likelihood. Additionally, addressing class imbalance using the Synthetic Minority Over-sampling Technique (SMOTE) was applied to improve the model's performance. [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]

Predictive analytics is a new frontier sector of higher education in today's world of data science, similar to other businesses such as marketing, financial, fraud detection, and demographic trends. Predictive analytics can provide beneficial information to educators and potentially assist them in enhancing students' performance by analyzing historical data using a variety of approaches from data mining and machine learning. The e-learning practiced in today's education system are unfortunately cause the dropout rates among students. Dropouts may cause the big and negative issues for university system and the stakeholders as well. Based on the literature review, studies on machine learning and predictive analytics to improve student performance are still scarce in Malaysian higher education. Therefore, the objective of this quantitative research is to develop the best predictive model for predicting students' performance at Pahang Islamic University College using machine learning techniques such as Decision Tree, Random Forest, AdaBoost, and Gradient Boosting. Students who have taken the Business Statistics course from the years 2013 to 2021 will be the subjects of the study. Data retrieved through a Learning Management System were used. From the analysis that has been done, Random Forest is the best method to be used in the predictive model for students' final grades. [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]

Malware is the term for harmful software that hackers use to infiltrate specific machines or an entire network of an organization. It takes advantage of flaws in legitimate software (such as a browser or plug in for an online application) that can be hijacked. According to a recent survey, 80% of smartphones were still vulnerable to malware attacks that might jeopardize personal information, identity, and business or financial information. Android mobile malware is the biggest threat to data security. To examine the efforts surrounding malware risks on Android mobile devices, a range of machine learning algorithms, including Naive Bayes, Support Vector Machine, K Nearest Neighbor, and Random Forest, are employed in this research. Each algorithm is evaluated according to various performance criteria to determine which algorithms are better suited to detecting malicious software. According to experimental findings, Support Vector Machine and Random Forest deliver the best results, making them the most efficient methods for malware detection. [ABSTRACT FROM AUTHOR]

A malicious website, often known as a malicious URL, is a platform considering hosting unwanted content including spam, harmful advertisements, and dangerous websites. It is crucial towards quickly identify dangerous URLs. Blacklisting, regular expression, & signature matching techniques have all been employed in earlier investigations. These methods are utterly useless considering identifying new URLs, malicious URL variants, or URLs that have never been seen before. Machine learning-based solution that has been suggested can help towards solve this problem. Considering this kind about solution, in-depth study about feature engineering & feature representation about security artifact types, such as URLs, is necessary. Additionally, resources considering feature engineering & feature representation must be continuously improved towards support variations about current URLs or completely new URLs. Deep learning, machine learning, & artificial intelligence (AI) systems have recently been used towards achieve human-level performance in a number about areas & even surpass human eyesight in a number about computer vision applications. They can automatically extract best feature representation from raw inputs. We propose various algorithms, including SVM, Random forest, XgBoost, & AdaBoost, towards capitalise on & turn performance increase about them into cyber security area. [ABSTRACT FROM AUTHOR]

Premature birth (PTB) is the most common public health issue in gynecology and obstetrics. It has a variety of consequences, ranging from increased infant mortality to chronic disease and disability throughout one's life. Many PTB prediction studies have been published in recent years to improve the accuracy of PTB prediction. However, no single study has addressed the issue of premature birth using a data set from the Iraqi community. There are many research from different countries that have been collected regarding premature birth, where the pregnant woman differs from one region to another in terms of lifestyle as well as the diagnostic methods used, where in Iraq only manual methods are adopted in the diagnosis. The aim of this paper is to provide and improve the prediction accuracy of premature births using real data from Iraqi hospitals. Additionally, provide a validation of the results in terms of reliability and accuracy. The novel approach is used to identify the best maternal characteristics (those associated with PTB) from an obstetric dataset. The following classifiers (Decision Tree, Random Forest, Logistic Regression, K-Neighbor Nearest, Naive Bayes Classifier, Neural Networks, Support Vector Machine) were used in this study to classify all birth cases into term normal birth and preterm birth. As a result, the Random Forest classifier outperformed all other classifiers with a 98% percent accuracy. Its worth noting that the classifiers' performance is quantified in terms of accuracy, sensitivity, Specificity, Precision, Recall and F1 score. [ABSTRACT FROM AUTHOR]

One of the most common and practical tools for predicting and diagnosing cardiac problems is the electrocardiogram (ECG) signal. It is an advanced medical device fundamental that monitors track of cardiac excitability, transmission, and recovery. It Provides essential information on the functional features of the heart and cardiovascular system. In this work, a technique for classifying an ECG image of a patient case into four classes is proposed. This class includes (MI, Arrhythmia, History MI, and Normal case). There are three steps to the proposed system: The procedure includes "image pre-processing, feature extraction, and classification". In order to prepare and enhance the input images, certain image preprocessing techniques are utilized in the early step. Color images are converted to binary images. Utilizing local binary pattern modulation, features are extracted from the images in the second step (LBP). The extracted features are sent into a 1D ML algorithm as input in the third step. Three ML algorithms are utilized. For ECG classification, these algorithms are "K-Nearest Neighbors (KNN), Random Forest (RF), and Logistic Regression (LR)." Algorithms achieved successful results during the ECG classification process, The findings show that the suggested technique is excellent in RF the range of this classification precision is 93.66 percent, and very good in K-NN the range of this classification precision is 80.53 percent, and good degree in LR the range of this classification precision is 70.87 percent. As evidenced by the low number of fault alarms and high accuracy rate, the suggested system performs exceptionally well in classifying ECG images. [ABSTRACT FROM AUTHOR]

After a deep questioner among students, faculty members and higher education experts. The demand for qualified engineers in the specific field as understandably gone down. The situation is grimmer for tier-2 and tier-3 colleges in India. The purpose of opting engineering course is not to get expertise in the particular course, instead to get a job in government sector with valid degree. The problem identified in the field of engineering education towards improving the quality in education is addressed with the help of exploratory data analysis. The dataset used in our experiment is collect from UCI machine Learning Repository having 33 variables and 1044 observations. The contribution made in the paper is to identify the vital attributes using single and multi-variant regression techniques. To perform prediction using Decision Tree, Random Forest, Support vector Machine and compare their performance in terms of classification accuracy and F-Score. In addition to that a convolution Neural Network (CNN) model is established in which, the vital attributes identified using regression techniques are provided as inputs and weights at each stage is estimated using Gradient Decent algorithm with step size 0.5. The classification accuracy from 63% is improved to 97% with the help of CNN model in 26664 iterations. The finding of the present research states that student having backlogs are less frequently opting for higher studies. [ABSTRACT FROM AUTHOR]

Health and medicine has gained a lot of importance in today's digital world, where evolving technology is being used to fight against almost all the known diseases thoroughly. But, according to reports, more than two lakh people in China and one lakh in United States of America are dead every year due to the mistakes made while prescribing errors. This paper aims to propose a system which takes as input the symptoms from the patient to predict the disease, which is followed by recommending the correct medicine. This system consists of database system module where disease dataset contains attributes like "DiseaseID", "Disease", "Symptoms" and "count of occurrences" and drug dataset has additional attributes such as "drug" and "drug_rating". In the data preparation module, a new data frame is created where each disease with its associated symptom is given "1" and "0" if it is not the symptom related. After all these steps of preprocessing are performed on the raw dataset, the dataset is now ready to be acted upon by a machine learning algorithm. Models like Decision Tree, Random Forest and Naive Bayes were applied on the training-dataset. Entire knowledge database was fitted in models and it was seen if not much dataset is used Random Forest And Naïve Bayes classifiers showed 84% accuracy whereas Decision Tree gives 92%. But Random Forest also gives accuracy similar to Decision Tree for large dataset. Hence for disease prediction we use Decision Tree. The recommendation is done on the basis of the rating of the drug. After this, only the drug with the highest rating is included in a newly formed dataset and the rest of the drugs are ignored. The system is implemented for user access by making use of Tkinter a python GUI Library for constructing the desktop end user interface. This paper deals with the design and implementation of a system which performs the function of prediction of diseases and the recommendation of medicines, which adds to the capabilities of the present systems in health infrastructure. [ABSTRACT FROM AUTHOR]

Customer churn referred as customer who ceases his relationship with service provider. Customer churn analysis is performed to retain existing customers from churning. Churn prediction is gaining importance in telecom sector now a days because of its importance to analyze behaviors of different customers to predict who are in verge in leaving the subscription from service provider. Retaining existing clients is cheaper than gaining a newer one. This paper focuses on various machine learning and neural network methods to predict customer churn and identify the customers who are closer to leave their service from the respective service provider. Machine learning algorithms that are used to predict the customer churn such as Logistic Regression, Support Vector Machine, Random Forest, Adaboost and Artificial Neural Network. Data is collected from AT&T website and learning models are evaluated based on two criteria's i.e., Accuracy and Area under curve giving special weightage on Accuracy. Algorithm that proves to be the most accurate in all the test cases is compared and performance is measured. [ABSTRACT FROM AUTHOR]

Human activity recognition (HAR) is one of the common classification problems that has a lot of interest. In HAR, different techniques are explored to identity the physical activity of humans, given data coming from various sensors. This paper explored the use of different supervised learning techniques and algorithms such as Gaussian Bayes Theory, Logistics Regression, SVM Classifier, Quadratic Discriminant Analysis, k-Nearest Neighbor and random Forest Classifier. Accuracy measurement of how each algorithm successfully predict the correct classification is done with the Random Forest Classifier giving the highest user accuracy of 87% without cross validation and 84.9% with 5-fold cross validation. For class accuracy, Random Forest Classifier gives an accuracy of 90.5% without cross validation while k-nearest neighbor gives an accuracy of 89.2% with k=3 and 5-fold cross validation. [ABSTRACT FROM AUTHOR]

There are a lot of students in the modern educational system who need to pursue further education after taking an undergraduate certification course. Advanced education in the sense that some groups having an undergraduate degree in Engineering must complete their Masters degree through either GATE or CAT or any other entrance examination conducted by the individual institutes either in national level or in the international level to get the admission. In educational institutions, the question of understudy confidentiality is crucial. In order to foresee the probability that a undergraduate would be conceded to a Master's program, we are working with AI models. This will enable students to plan ahead and determine if they will have the chance to be recognised. There are three significant Machine learning models particularly Linear regression, Decision tree regression and Random Forest regression. In this paper we will predict the admissions using Random Forest algorithm, a well-known supervising learning model. [ABSTRACT FROM AUTHOR]

Class imbalance is one of the major challenges faced by the machine learning research community. The imbalance in the data degrades the performance of the model. The widely used resampling methods can miss important instances during undersampling. On the other hand, oversampling can cause bias in the data that lead to overfitting of the model. To avoid this problem an alternate solution of estimating the threshold for an imbalanced dataset was adapted. In general, the default threshold is fixed to 0.5, which is not suitable for imbalanced datasets. The optimal threshold is estimated by maximizing the f1-score and Geometric mean (G-mean), the two widely used metrics for imbalanced learning. The proposed approach preserves the original data without any alteration. To compare the performance six ensemble classifiers such as Adaptive Boosting (AdaBoost), Light Gradient Boosting Machine (LGBM), eXtreme Gradient Boosting (XGBoost), Gradient Boosting Machine (GBM), Random Forest (RF) and Classic Gradient Boosting (CatBoost) are selected. The IEEE-CIS fraud detection dataset from Kaggle having an imbalance ratio of 27.58 was used for this study. Experimental results show that the precision, recall and f1-score are improved by shifting the threshold values for binary classification. We observed that the performance of XGBoost (0.7325) and LGBM (0.7123) was comparably high in terms of f1-score. Hence, the selection of optimal threshold helps to provide betterfindings. [ABSTRACT FROM AUTHOR]

In today's world of COVID infection, heart monitoring should be done to Quarantine patients at home from time to time on daily basis either by an attendee or a nurse. It is becoming increasingly tedious for people to be at home to take care of their loved ones, as their jobs don't permit them to do so and also due to the infection spread. To tackle this issue, we present the concept of a heart monitoring device with line follower robot navigation. This setup is used to check elderly and bed-ridden patients automatically at a pre-defined time with the help of an Arduino controller. Also in this work, we bring forth a novel method to improve the accurateness in predicting the heart condition using machine learning procedures. The prediction model is built using a variety of feature combinations and classification approaches. The datasets are processed using Python programming and two core Machine Learning Algorithms, namely the Random Forest Algorithm and the Gradient Boosting Tree Algorithm, which reveals that the Random Forest Algorithm is the best algorithm among these two in terms of heart disease exactness. [ABSTRACT FROM AUTHOR]

Heart Disease, Diabetes and lung cancer are complex diseases and globally many people are suffering from these diseases. On time and efficient identification of these diseases, play a vital role in health care monitoring systems. In this article, we proposed an effective and precise framework to determine these and the framework depends on Machine Learning algorithms. The system is developed based on classification algorithms and includes Support vector machine, Logistic regression, K-nearest neighbor, Decision tree, Random Forest and XGBoost Classifiers. Firstly, Kaggle dataset is considered for testing the data. Later pre-processing of data is done. Then the greatest piece of any data analysis project is ensuring that the information is effectively organized and fixing it when it isn't. The initial segment of this interaction is managing Missing Data. After dealing with the missing data, we are ready to start formatting the data set for making classification tree. Formatting data is splitting data into dependent and independent variables. Finally, after formatting the data for classification tree, the data is split into training and testing sets. The experiments results show that the classifier Random Forest tree achieved high accuracy as compared to other classifiers. Additionally, the proposed system can be easily implemented in healthcare for identifying heart disease, diabetes and lung cancer. [ABSTRACT FROM AUTHOR]

Occupancy detection is critical during building operations, particularly in energy efficiency, space utility, heating, ventilation control, and air conditioning (HVAC) to optimize user comfort. However, applying occupancy sensors to detect occupants can violate a person's privacy, and the resulting data could be more precise. Therefore, this study aims to detect occupancy through environmental sensors by utilizing the accuracy of machine learning-based classification results. The ultimate goal of this study is to detect whether there are people in a room based on the benchmarks studied. Benchmarks for classifying whether people are in a room include CO2, humidity, lighting, temperature, and occupancy. This paper presents a method for comparing and evaluating a set of different machine learning techniques based on a given performance measure (for example, precision, accuracy, f1 score, and algorithm recall) and then using the algorithm with the best performance. This study uses five machine learning classification algorithms: K-Nearest Neighbors, Support Vector Machine, Decision Tree, Naive Bayes and Random Forest, and the method used to evaluate the results is cross-validation. Experiments were conducted using occupancy detection datasets from the UCI Machine Learning Repository. After performing the experiment, the predictive results of the five algorithms are high. That is, each has an accuracy value of more than 90%. Support Vector Machine has the highest accuracy value compared to other algorithms, namely 98.5%, and Decision Tree has the lowest accuracy value, namely 91.9%. The results show that selecting the right features and the suitable classification model can significantly impact prediction accuracy. [ABSTRACT FROM AUTHOR]

The IOT, in general, refers to devices being connected to a network. As a result, in order to protect network devices from security breaches, data must be secured. Because of the potential severity of the consequences of an IOT (IoT) failure, further investigation into IoT security vulnerabilities is warranted. The primary goal of IoT security is to protect user-privacy and confidentiality, as well as the architecture, communications, and technology that makes up an IoT ecosystem, as well as to ensure that the ecosphere services become inevitable. Since simulators, designers, and computation and analytic tools have become more widely available, research in IoT security has lately gained a lot of traction. An overview of the present level of IoT-security research, the essential tools, and IoT model and simulators are the core contribution of this study. Machine learning technologies will be used to identify attack threats in IoT security. Decision tree, Support Vector Machine (SVM), Bayes Algorithm, K-Nearest Neighbor (KNN), and Random Forest (RF) are the five most commonly used methods in IOT. [ABSTRACT FROM AUTHOR]

In the present time, the demand of energy is increasing rapidly. The heavy demand of energy is in the smart cities domain as there are number of sub domains like Smart Homes, Smart Transportation, Smart Healthcare, etc. So, as the result the domain is opening the new research direction for the industrialist, researchers, and scientists. They are attracting towards the domain of smart city for different kinds of research projects. The primary concern of this paper is to focus on the energy consumption of smart homes. In this paper different Machine Learning (ML) and Deep Learning (DL) models are being implemented and the results are analyzed to check the performance of the different models on the dataset of smart home energy consumption. This study found that the Random Forest is predicting the energy consumption with lowest error with 0.6616, 0.4377, 0.3171 RMSE, MSE, and MAE respectively. The performance of the models is being evaluated in the terms of Root Mean Square Error (RMSE), Mean Square Error (MSE), and Mean Absolute Error (MAE). This study found that the most suited model for energy consumption data in smart city is Random Forest. [ABSTRACT FROM AUTHOR]

The liver cleans the body's blood which converts nutrients and drugs into active molecules. Liver removes poisons and chemical waste from the blood for elimination. Untreated liver failure may kill. Machine learning predicts early sickness in contemporary healthcare. A machine learning model is constructed utilizing liver failure data. Univariate and multivariate analyses, along with any other required preprocessing procedures are put into place. Univariate analysis is useful for making changes to file names, adding new data, removing old data, and defining data types. Pairplot, heatmap, bar chart, and histogram are only some of the visualizations made possible by bivariate and multivariate data analysis for exploratory purposes. The data is presented so that the characteristics can be understood better, and a model is constructed using the random forest technique with oversampling to get the highest accuracy possible in predicting liver failure. Metrics like as accuracy, F1 score, recall, etc., are used to compare algorithms efficacy. Using the Flask web framework, the results of liver failure are obtained. [ABSTRACT FROM AUTHOR]

The state of confusion while learning can reduce the performance of students in their studies. Monitoring the engagement of students in online courses is a tedious job. This paper aims to detect the state of confusion state among students watching MOOC videos based on EEG signals. EEG (Electroencephalography) signals are the brain's electrical signals that can be used to detect activities like engagement, happiness, stress and many other emotions. Machine learning is an easy and efficient method to deal with complex EEG data and analyze it. The dataset used is a combination of two datasets from Kaggle. The first one is EEG data recorded from 10 students and the other consists of demographic information of the students. Various machine learning algorithms such as gradient boosting, decision tree, random forest, KNN and Naïve Bayes are used to classify the data as confused or not confused. Random forest classifiers proved to be the best algorithms for classification from the comparative analysis of all the implemented algorithms with an accuracy of 96%. [ABSTRACT FROM AUTHOR]

Anemia is the most common blood disorder where the blood lacks a sufficient amount of red blood cells which results in an insufficient amount of oxygen being supplied to the body tissues. The condition is most commonly seen to occur in women during their pregnancy and children in the age group of 9 to 18 months and is not easily detected at the early stages. This survey paper depicts different machine learning (ML) approaches used for the analysis of anemia. Further, it also highlights the use of the ML approach for determining the prevalence of anemia, categorizing the level/type of anemia among patients, young children, and women of reproductive age (including pregnant women). It is observed that amongst the ML approaches used by the researcher's random forest (RF) and decision tree (DT) algorithms had outperformed the other algorithms for the analysis of anemia. [ABSTRACT FROM AUTHOR]

Heart diseases are very dangerous for humans, as these are very serious and can even lead to the death of the patient. In today's world, Machine Learning has a vital role in bioscience as well. This paper presents a comparative analysis to detect cardiovascular disease using average Ensemble Learning, Random Forest and extreme Gradient Boosting Algorithms. The Normalization method is used to preprocess the used dataset and then all the techniques mentioned above are used to train the model. By using all three techniques/ methods accuracy, recall, precision, ROC, and F-measure, are evaluated. Boosting ensemble learning method performed best among all with an exactness/accuracy score of 91.2%. [ABSTRACT FROM AUTHOR]