Bayu Adhi Tama

A Combination of PSO-Based Feature Selection and Tree-Based Classifiers Ensemble for Intrusion Detection Systems

Due to the numerous attacks over the Internet, several early detection systems have been developed to prevent the network from huge losses. Data mining, soft computing, and machine learning are employed to classify historical network traffic whether anomaly or normal. This paper presents the experimental result of network anomaly detection using particle swarm optimization (PSO) for attribute selection and the ensemble of tree-based classifiers (C4.5, Random Forest, and CART) for classification task. Proposed detection model shows the promising result with detection accuracy and lower positive rate compared to existing ensemble techniques.

Learning to Prevent Inactive Student of Indonesia Open University

The inactive student rate is becoming a major problem in most open universities worldwide. In Indonesia, roughly 36% of students were found to be inactive, in 2005. Data mining had been successfully employed to solve problems in many domains, such as for educational purposes. We are proposing a method for preventing inactive students by mining knowledge from student record systems with several state of the art ensemble methods, such as Bagging, AdaBoost, Random Subspace, Random Forest, and Rotation Forest. The most influential attributes, as well as demographic attributes (marital status and employment), were successfully obtained which were affecting student of being inactive. The complexity and accuracy of classification techniques were also compared and the experimental results show that Rotation Forest, with decision tree as the base-classifier, denotes the best performance compared to other classifiers.

Performance Analysis of Multiple Classifier System in DoS Attack Detection

DoS attacks become a serious attack so as resource protection against this kind of attack is a compulsory task. The major challenge on designing detection scheme using machine learning technique is how to maximize detection rate with lower false alarm. In this paper, we employ and analyze the performance of multiple classifier system MCS to detect DoS attack. Several renowned base classifiers such as C4.5, SVM, and k-NN are combined using combination voting scheme and we compare the results with existing ensemble learning algorithms such as Bagging, Adaboost, and Rotation Forest. Based on the experiment using NSL-KDD dataset, MCS scheme has promising performance comparing to existing ensemble learner and single classifier.

A critical review of blockchain and its current applications

Blockchain technology has been known as a digital currency platform since the emergence of Bitcoin, the first and the largest of the cryptocurrencies. Hitherto, it is used for the decentralization of markets more generally, not exclusively for the decentralization of money and payments. The decentralized transaction ledger of blockchain could be employed to register, confirm, and send all kinds of contracts to other parties in the network. In this paper, we thoroughly review state-of-the-art blockchain-related applications emerged in the literature. A number of published works were carefully included based on their contributions to the blockchains body of knowledge. Several remarks are explored and discussed in the last section of the paper.

A Framework for Blockchain Based Secure Smart Green House Farming

The emerging greenhouse technology in agriculture based on Internet of Things (IoT) used for remote monitoring and automation has been rapidly developed. But it still has major concern about security and privacy, due to the large scale of disseminating nature of its network. To overcome these security challenges, we use blockchain which allows the creation of a distributed digital ledger of transactions that is shared among the nodes on IoT network. The main aim of this paper is to provide lightweight blockchain based architecture for smart greenhouse farms to provide security and privacy. Here, IoT devices in greenhouses which act as a blockchain managed centrally to optimize energy consumption have the benefit of private immutable ledgers. In addition, we present a security framework that blends the blockchain technology with IoT devices to provide a secure communication platform in Smart Greenhouse farming.

Tree-based classifier ensembles for early detection method of diabetes: an exploratory study

Diabetes is a lifestyle-driven disease which has become a critical health issue worldwide. In this paper, we conduct an exploratory study about early detection method of diabetes mellitus using various ensemble learning techniques. Eight tree-based machine learning algorithms, i.e. classification and regression tree, decision tree (C4.5), reduced error pruning tree, random tree, naive Bayes tree, functional tree, best-first decision tree and logistic model tree are employed as a base classifier in five different ensembles, i.e. bagging, boosting, random subspace, DECORATE, and rotation forest. The performance of ensembles and base classifiers are thoroughly benchmarked on three real-world datasets in term of area under receiver operating characteristic curve metric. Finally, we assess the performance differences among the classifiers using several statistical significant tests. We contribute to the existing literature regarding an extensive benchmark of tree-based classifier ensembles for early detection method of diabetes disease.

Classifier Ensemble Design with Rotation Forest to Enhance Attack Detection of IDS in Wireless Network

This paper is devoted to discover the appropriate base classifier algorithms while employing Rotation Forest as an ensemble learning method for intrusion detection system (IDS) in wireless network. Twenty different classification algorithms are involved in the experiment and their detection performances are assessed using the value of area under receiver operating characteristic curve (AUC) performance metric. The performance result of an ensemble learner are evaluated, including its significant improvement while using diverse machine leaning algorithms as base classifiers. From the experimental result and classifier significant test, it can be revealed that the performance of Rotation Forest has brought significant improvement over the base classifiers.

Detecting major disease in public hospital using ensemble techniques

Hepatitis is chronic disease that becomes major problem in developing countries. Health experts estimate that more than 185 billion people have chronic hepatitis worldwide. This paper attempts to detect major disease such as hepatitis in public hospital using ensemble methods. Several ensemble techniques were applied to acquire knowledge from patient medical records. Afterwards, rule extraction from decision tree and neural network are summarized in order to assist experts in detecting hepatitis. Accuracy of those algorithms is also performed and from the experimental result shows that Bagging, with decision tree as base-classifier, denotes best performance among other classifiers.

A Detailed Analysis of Classifier Ensembles for Intrusion Detection in Wireless Network

Intrusion detection systems (IDSs) are crucial in this overwhelming increase of attacks on the computing infrastructure. It intelligently detects malicious and predicts future attack patterns based on the classification analysis using machine learning and data mining techniques. This paper is devoted to thoroughly evaluate classifier ensembles for IDSs in IEEE 802.11 wireless network. Two ensemble techniques, i.e. voting and stacking are employed to combine the three base classifiers, i.e. decision tree (DT), random forest (RF), and support vector machine (SVM). We use area under ROC curve (AUC) value as a performance metric. Finally, we conduct two statistical significance tests to evaluate the performance differences among classifiers.

Performance evaluation of intrusion detection system using classifier ensembles

An intrusion detection system (IDS) plays a critical role in computer protection systems. Numerous approaches such as machine learning, data mining, and statistical techniques have been examined for IDS task. Recent studies reveal that combining multiple classifiers, i.e., classifiers ensemble, may possess better performance compared to single classifier. In this paper, we conduct a comparative study of the performance of five renowned ensemble techniques, i.e., bagging, stacking, boosting, rotation forest, and voting, based on three base classifiers, i.e., decision tree (C4.5), convolutional neural network (CNN), and support vector machine (SVM). Based on the experimental results, boosting and stacking perform better than bagging, rotation forest, and voting scheme. In particular, boosting-C4.5 and stacking possess the best performance in terms of performance metrics such as accuracy, precision, recall, and AUC value.