Search

Cyber security and Cloud platforms are utilized in various usage and applications in today's world. Given the wide range of applications, and the ease of usage they provide, the popularity of them are increasing dramatically. Leading many individuals and organizations to depend on them mainly. Securing data, hardware, networks and other resources from cyber-attacks represent a crucial factor for these organizations. The work in this paper proposes an approach of multiple stages to detect and predict the cyber -attacks types aiming to enforce higher security procedures to secure the organization resources in general and data in specific. The approach first stage is the data collection where Meraz dataset available on the internet is used, and then different levels of preprocessing were conducted. The third stage is to apply different classification algorithms to group the attacks into malicious or not. Then after, the data related to the classifier that yield optimum classification results is selected for next level of knowledge extraction where hierarchical clustering was applied. The clustering is built on the malware samples of test dataset only. This dataset is divided into training and testing samples. A 10% of the dataset was used to predict the malware type. Hierarchical clustering was used with various configurations. The reason for using clustering is to predict the attack type by assigning each attack for distinct cluster. The proposed approach gave 98.88% of accuracy with Random Forest classifier and a reliable result for clustering were using Hierarchical clustering by using Euclidean distance metric, and ward linkage, The prediction values were as follows {0: 10671, 1: 3603, 2: 824}. The results obtained gave a novel approach for developing Machine Learning solution for cloud systems security. With this novel solution, the limitations of the traditional solutions are solved. [ABSTRACT FROM AUTHOR]

The primary objective of the study is to explore the effectiveness of Audio classification using a Novel Artificial Neural Network (ANN) Algorithm in comparison with Random Forest to classifying different sounds into specific groups and representing them as waveforms. Material and Methods: The dataset which has been collected from Urban Sounds 8k that include a total of 8700 audios. Each Audio is composed of 40 rows and 40 columns for the classification of audio based mel frequency. Researchers compared the performance of a novel Artificial Neural Network (ANN) with a Random Forest algorithm for audio classification. A statistical analysis ensured a high probability of detecting true effects (power of 0.8) while minimizing false positives (alpha of 0.05). The ANN achieved a significantly higher mean accuracy (94.34%) compared to Random Forest (67.26%) over 10 trials (p-value = 0.004). This suggests that ANNs are a promising approach for audio classification tasks based on the findings of this study. [ABSTRACT FROM AUTHOR]

Machine learning algorithms find patterns in data that helps to make better prediction and decision. In day to day life these algorithms help to make critical decision such as medical diagnosis, stock prediction fault detection etc., Classification algorithm predict labels from trained patterns. Imbalanced data classification distribute data unevenly among classes i.e majority class has high proportion data whereas minority class takes low proportion data. Common machine learning algorithms have poor prediction accuracy for minority class leads to data imbalance problem. Besides multi class imbalanced learning has greater challenges than binary classification. To address this issue, this works designed a new classifier model that combine pipeline sampling for resample the data and Dynamic ensemble classifier selection for prediction on multiclass imbalanced dataset taken form UCI repository. Performance are evaluated through the multiclass classification metrics such as Weighted average Accuracy, weighted average Precision and weighted average F1 score, Roc_AUC Score, cohen's kappa score, Mathew correlation co-efficient. A thorough empirical comparison is conducted to analyze the performance of proposed model with existing ensemble algorithm Gradient Boosting Classifier Bagging classifier and Random forest classifier. Dynamic ensemble algorithm outperforms the existing ensemble algorithm [ABSTRACT FROM AUTHOR]

In this era, technology has revolutionized the health industry to a great extent. The proposed model aims to design a diagnostic system for various diseases based on their symptoms. The Disease Prediction System has implemented different ML prediction models for the prediction of the user's disease based on various symptoms inputted by the user. Machine learning classification algorithms analyse the inputs given by the user and then predict the disease and probability of occurrence of the disease as output. The proposed system predicts the diseases such as i) Diabetes, ii) Kidney, iii) Cancer, iv) Heart and v) Liver. Four prediction models, Naive Bayes, Decision Tree, Random Forest and Logistic Regression, has been implemented in the proposed system for various disease. The dataset "Disease Prediction Using Machine Learning," with a count of 132 symptoms, has been used in the proposed model. The main goal of the proposed model is to predict the disease; however, the user doesn't need a medical report to use this system as the prediction is based on the symptoms, which will save time and money. The system also has an easy-to-use user interface, and all the users can use it to predict genetic diseases. [ABSTRACT FROM AUTHOR]

The fundamental objective of this study is to evaluate and contrast the performance of two innovative classification algorithms, namely Random Forest and Decision Tree. Each of the random forest and choice tree exercises had 20 participants. The academic success of a student in the past might serve as an indication of the possible future achievements the student will have. The purpose of this research is to come up with strategies that can accurately forecast how well a kid will do academically. The use of decision trees and random forests as methods for forecasting student success are now both considered to be well-established methodologies. Each of the research groups had a total of 72 participants. The accuracy of predictions made using this dataset ranges from 88.2 percent when utilising the time-tested Decision tree to 91.7 percent when utilising the innovative Random forest classifier. 0.03 is the most significant part of the fraction. The Random Forest algorithm is better to the decision tree approach for this reason. The innovative decision tree known as the random forest performs far better than its predecessor, the tried-and-true decision tree. [ABSTRACT FROM AUTHOR]

This paper focuses on finding the best classification algorithm model in the case study of student performance prediction and comparing the algorithm performance before and after using the normalization method. To achieve this goal, this study uses data mining classification techniques to analyse student performance at Vocational High School in 2020-2021. The steps of the research carried out include: data collection, data pre-processing, build algorithm models without using normalization and with using normalization, and final step are comparing algorithm performance before and after using normalization. The algorithms that will be used include: Random Forest, Decision Tree, Logistic Regression, SVM, Naive Bayes, and KNN. While the normalization methods used are Standard Scaler, Min-Max Scaler, and Robust Scaler. The result of this research is that the normalization method is able to significantly increase the accuracy of the model. Based on the tests and evaluations carried out, the normalization method using the Min-Max Scaler has the biggest impact in improving the overall model performance and the algorithm with the best performance is Random Forest. This paper reviews the effect of the normalization method to improve algorithm performance in predicting student performance, where based on previous research no one has used the normalization method to gain accuracy of the model which actually has a considerable impact on gaining accuracy of the model. [ABSTRACT FROM AUTHOR]

Machine learning is increasingly being used in medical diagnosis. It can, among other things, serve to improve disease classification and detection systems and can supply information to aid medical personnel in the early identification of fatal diseases, thereby extending patient survival can be improved. To anticipate diseases, this paper uses various classification algorithms to five distinct disease databases which include heart, breast cancer, diabetes, and liver. The study's findings support the notion that machine learning might be used to predict sickness early as each of the dataset consists of adequate number of records. Each of the concerned dataset consists minimum 2000 plus records. For this work, we conducted experiments using a variety of models, including logistic regression, random forest classifier, SVM, etc. We obtained a score of 0.96 on the scale of 0 to 1, using Random Forest classifier in kidney amongst all approaches. [ABSTRACT FROM AUTHOR]

The aim of the study is to investigate the possibility of applying machine learning methods for saccades and fixation detection from eye tracking signals. There are two widely used approaches to solving this task: velocity-based saccade identification (I-VT) and dispersion-based saccade identification (I-DT). Both require setting an optimal threshold which directly influences detection quality. Another important problem comes from the necessity of noise handling if eye tracking signal has a high noise level. Using I-VT and I-DT algorithms in this case will result in misclassification. Previous researchers have obtained promising results using Random Forest algorithm for saccade and fixation detection. Our aim with the article was to compare Random Forest with other binary classification algorithms such as Logistic Regression and K-Nearest Neighbors. We've also compared mentioned algorithms with velocity-based approach. The results show that Random Forest has the best classification metrics. The findings suggest that this machine learning approach could also be useful for eye movement event detection and proves the importance of further research in this field [ABSTRACT FROM AUTHOR]

Sentiment, emotions, feelings, showing or giving judgments by face gestures, etc. can be communicated by text, speech or images. Analyzing image Polarity via images is now a burgeoning research field. An image can easily be interpreted by any human being and acts as a bridge to relate an image to the human's thoughts. The paper proposed a model for analyzing the sentiments or emotions of an image. We have used a Data-Mining Orange Tool for executing the experiment for classification and sentiment analysis of an image. The main challenge is to acquire the polarity of the unlabeled data using optimal machine learning techniques. To overcome this challenge for getting the polarity and sentiment of an unlabeled data the proposed model used various noteworthy machine learning models like Neural Network, Naïve Bayes and random forest for classifying and analyzing the image sentiment and also provide a comparison based on certain parameters like Area Under Curve, Precision, Recall, classification Accuracy, etc. The tool provides a complete package for performing image analysis using the widgets available with orange tool and a data visualization tool to get a visible representation of the output. The proposed model shows that Random Forest performance the best from the three compared algorithms with classification Accuracy of 0.747, recall & precision as 0.747 & 0.752 and the accuracy based on confusion matrix is 74.72%. [ABSTRACT FROM AUTHOR]

Discretization is a technique of changing numerical values to categorical values. Discretization plays an important role in classification. Nowadays we are dealing with huge amount of numerical continuous data. Many of the classification algorithms performs best when categorical data is fed to it. So discretization is gaining importance nowadays. This paper compares the performance of discretization on the accuracy of Random Forest classifier. The variables are discretized based on the correlation of variables with the 'outcome' and 'disorder'. The correlation is identified using heatmap. It is found that the discretization of most correlated variables improves the accuracy of Random Forest Classification. But the Random Forest Classification performs best upon the discretization of continuous numerical attributes. For performing the experiment two publicly available datasets are chosen. In both datasets there are continuous attributes. Upon discretizing those continuous attributes, the performance of Random Classifier further increased. But when discretized all the attributes together degraded the performance of Random Classifier. The Discretization method used is Equal Width Binning Discretization [6]. When all the continuous data are discretized the performance is degraded, due to over discretization [1]. The datasets chosen for the experiment are Pima Indian Diabetes Dataset and Liver Disease Prediction Dataset [21]. [ABSTRACT FROM AUTHOR]

Imbalance of dataset in the accuracy testing process can lead to biased results. It occurs due to insufficient data in the training phase where unbalanced data causes problems in Machine Learning. Classification and predicting results become difficult when there is insufficient data to study. To overcome this, it takes steps in balancing the data, one of which is the random over sampling technique. The basic principle of using this technique is to rebalance an unbalanced data set with a concrete strategy. The use of sampling technique in the case of data imbalance is proven to be able to improve the performance of the algorithm. The results of testing the KNN, Naive Bayes, SVM, J.48 and Random Forest algorithms using 10 fold cross validation on the public dataset of early stage diabetes risk prediction from the Hospital in Sylhet, Bangladesh after going through the re-sample stage proved to be able to improve measurement results with a high level of accuracy. The highest using KNN with an accuracy of 99.4231%, while the results of the J.48 algorithm test with an accuracy rate of 99.2308%, Random Forest with an accuracy rate of 98.0769%, SVM with an accuracy rate of 96.5385% and Naïve Bayes with an accuracy rate of 90.3846%. [ABSTRACT FROM AUTHOR]

To Improve performance analysis in classification with accuracy of innovative phishing websites using the innovative Random Forest algorithm by comparing with the Support Vector Machine algorithm. Random Forest algorithm (N=20) is compared with the Support Vector Machine algorithm (N=20) in order to get high accuracy. The framework depends on Machine Learning. Random forest has the highest accuracy (92.11%) in comparison to the Support Vector Machine algorithm (90.26%) and the independent T-test was carried out and shows that it is statistically insignificant (α=0.354) with a confidence value of 95%. Random Forest algorithm obtained seems to be better accuracy than the Support Vector Machine algorithm in the detection of phishing Websites. [ABSTRACT FROM AUTHOR]

Diabetes is a long-term or chronic condition characterized by high or above-normal blood glucose levels. People who combine physical exercise with a high-calorie, high-fat diet that lacks fiber are at risk of developing diabetes. Machine Learning is a type of artificial intelligence that may be used to categorize someone's diabetes. The system will learn to recognize several diabetic factors automatically using the provided medical record data set. The Random Forest, Support Vector Machine, and K-Nearest Neighbor algorithms are compared in this study. In order to prove which is superior, Random Forest is combined with several decision tree possibilities. The Support Vector Machine is used to find a dividing line so that it can distinguish between the two classes of diabetic patients who are treated optimally and those who are not. K-Nearest Neighbor is a classification algorithm that uses characteristics and training samples to categorize new objects. The test results from the comparison of three approaches for categorizing diabetes show that K-Nearest Neighbor (KNN) has the lowest level of accuracy compared to the two methods (89.6%), Support Vector Machine algorithm has 91.5 percent accuracy, and Random Forest algorithm has 93.5 percent accuracy. As a result, the Random Forest algorithm is a suitable and effective approach for assessing the level of accuracy in diabetes diagnosis. [ABSTRACT FROM AUTHOR]

The process of building new dataset and the existence of such a data followed the urgent need for the existence of datasets that are specialized in educational lectures, so this will need an accurate classification algorithm to classify it, the benefit of classify such dataset is to minimize the workload of classifying each file manually and individually. In the present paper, authors perform experimentations for conducting an empirical deep learning study, especially, convolutional neural network, for three new datasets of educational lectures which are (PDF, Word and PowerPoint datasets), The three new datasets using real data educational resources lectures collected from various document projects of different universities and institutions. The architecture has been applied to the task of the text classification in the domain of the document with documents data-sets have been obtained from a variety of projects on actual document cases. The aim of the present study is to initially test the performance of each dataset (PDF, Word, and PowerPoint dataset) through using four machine learning classification algorithms which are (Bayes Net, Random Forest, Random Committee, and OneR). Second goal is experimenting the efficiency of the approach of the deep learning in the tasks of classification and after that, comparing the efficiencies with the efficiencies of traditional machine learning classification methods. Mainly two classification techniques used to maximize the benefits of the classification process, the first one is to use the deep learning algorithm which shows an accuracy of classifying file between (95 and 96%) for three new dataset files and standard machine learning algorithms (OneR, Random forest, Bayes net, and Random Committee) these algorithm shows accuracy 91% for PDF Dataset using random forest and random committee algorithms, for Word dataset the accuracy is 46% using random committee, and for the last dataset PowerPoint the accuracy is 77% using random forest, Therefore, we will choose Deep learning algorithm because it gives higher results and accuracy than machine learning algorithms. [ABSTRACT FROM AUTHOR]

Islamophobia is explored in many different perspectives in various settings, however Internet-based or online settings Islamophobia remain under-researched. Islamophobic content on social media promotes a biased and negative sentiments towards Muslims. The aim of this paper is to develop an automatic recognition and detection of Islamophobic tweets to address bigotry and hatred towards Islam and Muslims. A unique set of lexical, syntactic and semantic features were extracted from 2200 tweets containing keywords "Islam" and "Muslims". Using Sequential Minimal Optimisation (SMO), and Logistic Regression (LR), we achieved f-measures of above 0.7, demonstrating the accuracy of the classifier and the usefulness of the features extracted. Based on the experiments conducted, Random Forest (RF) algorithm proved to be the top performing algorithm in this study showing 86.69% of f-measure in training model, with LibSVM being the second top performing algorithm. [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]

Heart disease is one of the deadliest diseases in the world. Many factors that trigger heart disease, such as age, sex, cholesterol, blood pressure, etc. Diagnosis of patients suffering from heart disease can be known from the symptoms experienced by the patient also the patient's and family's disease history. Further tests will be carried out to check for the actual disease. The length of the examination time will increase the risk borne by the patient. Therefore we need a classification algorithm that can speed up the process of diagnosing a disease. The Logistic Regression algorithm is one of the simple algorithms that have good classification capabilities as proven by previous studies. Logistic Regression develops the concept of Linear Regression with categorical dependent variables. Besides, there is also one algorithm that can be used in similar cases. Random Forest is an ensemble learning method, bagging from Decision Trees that works by randomly generating trees. This research compares the performance of the two algorithms in the classification of heart disease. This data research uses the Framingham Heart Study dataset. With define data into training and testing, the result of the classification shows that Logistic Regression is greater with an accuracy of 85.04% and 84.4% for Random Forest. [ABSTRACT FROM AUTHOR]

With the continuous development of machine learning, industry and academia have released a lot of machine learning frameworks based on distributed computing platform, and have been widely used. However, the existing framework of machine learning is limited by the limitations of machine learning algorithm itself, such as the choice of parameters and the interference of noises, the high using threshold and so on. This paper introduces the research background of machine learning framework, and combined with the commonly used random forest algorithm in machine learning classification algorithm, puts forward the research objectives and content, proposes an improved adaptive random forest algorithm (referred to as ARF), and on the basis of ARF, designs and implements the machine learning framework. [ABSTRACT FROM AUTHOR]

This paper presents an image classification algorithm based on spatial sparse coding model and random forest. Firstly, SIFT feature extraction of the image; and then use the sparse encoding theory to generate visual vocabulary based on SIFT features, and using the visual vocabulary of SIFT features into a sparse vector; through the combination of regional integration and spatial sparse vector, the sparse vector gets a fixed dimension is used to represent the image; at last random forest classifier for image sparse vectors for training and testing, using the experimental data set for standard test Caltech-101 and Scene-15. The experimental results show that the proposed algorithm can effectively represent the features of the image and improve the classification accuracy. In this paper, we propose an innovative image recognition algorithm based on image segmentation, sparse coding and multi instance learning. This algorithm introduces the concept of multi instance learning, the image as a multi instance bag, sparse feature transformation by SIFT images as instances, sparse encoding model generation visual vocabulary as the feature space is mapped to the feature space through the statistics on the number of instances in bags, and then use the 1-norm SVM to classify images and generate sample weights to select important image features. [ABSTRACT FROM AUTHOR]

We describe an investigation into how Massey University's Pollen Classifynder can accelerate the understanding of pollen and its role in nature. The Classifynder is an imaging microscopy system that can locate, image and classify slide based pollen samples. Given the laboriousness of purely manual image acquisition and identification it is vital to exploit assistive technologies like the Classifynder to enable acquisition and analysis of pollen samples. It is also vital that we understand the strengths and limitations of automated systems so that they can be used (and improved) to compliment the strengths and weaknesses of human analysts to the greatest extent possible. This article reviews some of our experiences with the Classifynder system and our exploration of alternative classifier models to enhance both accuracy and interpretability. Our experiments in the pollen analysis problem domain have been based on samples from the Australian National University's pollen reference collection (2890 grains, 15 species) and images bundled with the Classifynder system (400 grains, 4 species). These samples have been represented using the Classifynder image feature set. In addition to the Classifynder's native neural network classifier, we have evaluated linear discriminant, support vector machine, decision tree and random forest classifiers on these data with encouraging results. Our hope is that our findings will help enhance the performance of future releases of the Classifynder and other systems for accelerating the acquisition and analysis of pollen samples. [ABSTRACT FROM AUTHOR]