The Zeus banking malware is one of the most prolific banking malware variants ever to be discovered. This paper examines and analyses the Support Vector Machine (SVM), Decision Tree and Random Forest machine learning ...
详细信息
ISBN:
(数字)9781728150611
ISBN:
(纸本)9781728150628
The Zeus banking malware is one of the most prolific banking malware variants ever to be discovered. This paper examines and analyses the Support Vector Machine (SVM), Decision Tree and Random Forest machine learning algorithms when used in conjunction with a manual feature selection process to detect Zeus network traffic. Selecting the features manually provides the researcher with more control over which features that can and should be selected. The manual feature selection process will also allow the researcher to analyze the impact of the various features and then select the features that provide the best accuracy results during the classification and detection of Zeus. The algorithms in scope for this research are the Decision Tree algorithm, Random Forest algorithm and the SVM algorithm.
In order to improve the accuracy and generalization performance of text sentiment analysis model, an integrated learning model is proposed in this paper, which includes three different classification algorithms - Logi...
详细信息
In order to improve the accuracy and generalization performance of text sentiment analysis model, an integrated learning model is proposed in this paper, which includes three different classification algorithms - Logistic regression, support vector machine and K-Neighborhood algorithm. Compared with single classification algorithm, this algorithm shows better accuracy. The experimental results show that the model has good generalization performance and robustness.
Hierarchical classification is a technique used to solve problems with hierarchical concepts, which are usually arranged into trees or directed acyclic graphs (DAGs). Research in this field is mostly done in the field...
详细信息
ISBN:
(数字)9781728123691
ISBN:
(纸本)9781728123707
Hierarchical classification is a technique used to solve problems with hierarchical concepts, which are usually arranged into trees or directed acyclic graphs (DAGs). Research in this field is mostly done in the field of bioinformatics and text classification, because both fields have hierarchical problems. Completion of hierarchy classification can be done with a local approach and a big-bang approach. From several previous studies, it was found that hierarchical classification with the big bang approach got good results, both in terms of predictive accuracy, model size and time needed to build the model. In this paper, we survey previous research on hierarchical classification algorithms using bing-bang approach.
Diabetes mellitus (DM) is a chronic disease. It has been rising more rapidly in middle- and low-income countries. World Health Organization (WHO) [1] estimates that diabetes was the seventh leading cause of death in 2...
详细信息
ISBN:
(数字)9781728130217
ISBN:
(纸本)9781728130224
Diabetes mellitus (DM) is a chronic disease. It has been rising more rapidly in middle- and low-income countries. World Health Organization (WHO) [1] estimates that diabetes was the seventh leading cause of death in 2016. In this paper a database concerning this disease where discussed and implemented by data mining techniques. Data mining techniques used to help the prediction of DM. It makes the prediction process faster, cheaper and more accurate for the benefit of both physicians and patients. In this paper, wellknown data mining algorithms explored to achieve DM prediction. The performance of these algorithms was evaluated and discussed using Orange Data Mining tool. The performance evaluation executed using two metrics: the recall and the precision; applied to each discussed classification algorithm. The studied classification algorithms are Naïve Bayes, K-Nearest Neighbours, Artificial Neural Network, Decision Tree, Random Forest, Support Vector Machine and Logistic Regression.
Data mining applications usually use datasets with large dimensions. Unfortunately, the large dimension in a dataset affects the processing time and outcome of the classification. One solution to this problem is to se...
详细信息
Data mining applications usually use datasets with large dimensions. Unfortunately, the large dimension in a dataset affects the processing time and outcome of the classification. One solution to this problem is to select relevant features for the reduce dimensions. The selection of the right features can increase the accuracy of the classification process. This study proposes a proper feature selection model for increasing the accuracy for specific classifier models by comparing several existing feature selection models and some of the classifier. The feature selection, we use information gain, gain ratio, and correlation-based feature selection (CBFS) while the classifier we employee K-Nearest Neighbor (K-NN), Support Vector Machine (SVM), Artificial Neural Network and Decision Tree. Evaluation is done using several public databases from UCI Machine Learning Repository. Evaluation results indicate that all feature selection methods are increasing the accuracy, but Decision Tree only increases in CBFS. Based on the result, feature selection does not always improve classifier accuracy but depends on the characteristics and algorithms used.
Nowadays smartphones are widely used in people daily life as they have a lot of sensors that can recognize physical conditions and people in their tasks. One of the task that a smartphone can be utilized is the driver...
详细信息
ISBN:
(纸本)9789526865386
Nowadays smartphones are widely used in people daily life as they have a lot of sensors that can recognize physical conditions and people in their tasks. One of the task that a smartphone can be utilized is the driver face analysis in vehicle cabin. Together with the information from smartphone sensors such analysis allows to provide recommendations for a driver to prevent the emergency situations. The paper contains the classification of dangerous situations that can be determined by a smartphone as soon as algorithms that can be used for this determination.
Nowadays Brain tumor detection in early stage is necessary because many people died due to unawareness of having a brain tumor. On the other side influence of machine learning becomes larger and larger in our lifes an...
详细信息
ISBN:
(纸本)9781538642559;9781538642542
Nowadays Brain tumor detection in early stage is necessary because many people died due to unawareness of having a brain tumor. On the other side influence of machine learning becomes larger and larger in our lifes and our society, artificial intelligence might also start playing an important role in medical diagnosis and support of doctors and surgeons. This paper is focused on review of those papers which include segmentation, detection and classification of brain tumors. The common procedure for an algorithm which aims to classify brain tumors on fMRI or MRI scans is: Preprocessing the image for example by removing noise, then segmenting the image, which yields the region which might be a brain tumor, and finally classifying features such as inten-sity, shape and texture of this region. Many machine learning approaches towards brain tumor detection have already been made. However, these approaches, even though yielding good results, are not used yet. Therefore this research topic remains important and still requires attention.
According to World Health Organization report the number of deaths by road traffic accident is more than 1.25 million people and every year with non-fatal accidents affecting more than 20-50 million people. Several fa...
详细信息
According to World Health Organization report the number of deaths by road traffic accident is more than 1.25 million people and every year with non-fatal accidents affecting more than 20-50 million people. Several factors are contributed on the occurrence of road traffic accident. In this study, data mining classification techniques applied to establish models (classifiers) to identify accident factors and to predict traffic accident severity using previously recorded traffic data. Using WEKA (Waikato Environment for Knowledge Analysis) data mining decision tree (J48, ID3 and CART) and Naïve Bayes classifiers are built to model the severity of injury. The classification performance of all these algorithms is compared based on their results. The experimental result shows that the accuracy of J48 classifier is higher than others.
classification is a method used to predict membership of specific instance into a group of data. It uses a supervised learning method. Various of classification algorithm are available to process data, but the issue i...
详细信息
classification is a method used to predict membership of specific instance into a group of data. It uses a supervised learning method. Various of classification algorithm are available to process data, but the issue is which one is preferred taking consideration of the different input parameters. In this paper, we choose the several major supervised algorithms: K-NN (K Nearest Neighbors), NB (Naive Bays) and DT (Decision Tree). We use Vehicle Ad Hoc Network (VANET) real time data. This paper focuses on study of effectiveness measures in terms of accuracy and runtime.
In the last decade, a large number of computer aided diagnosis (CAD) tools are developed for the identification of different algorithm. For the disease diagnosis, classification algorithms based on ML (ML) techniques ...
详细信息
ISBN:
(纸本)9781538658741
In the last decade, a large number of computer aided diagnosis (CAD) tools are developed for the identification of different algorithm. For the disease diagnosis, classification algorithms based on ML (ML) techniques are commonly used. The classification algorithm uses a supervised learning methodology to makes the system or computer program to learn from the given input data and then employ the learning knowledge to identify the upcoming observations. This paper intends to evaluate the different classification algorithms namely radial basis function (RBF), Naive Bayes (NB), J48 and Olex-GA on the identification of Lymph diseases. For the performance evaluation of different classifiers, a benchmark Lymph dataset is used interms of different performance measures. The obtained results proved that the RBF network attained better performance compared to NB, J48 and Olex-GA.
暂无评论