Browsing by Author "Gizaw, Solomon"

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Modeling Network Intrusion Detection System Based on Anomaly Approach Using Machine Learning Techniques
    (Addis Ababa University, 2020-03-05) Hidru, Tigist; Gizaw, Solomon
    With the rapid growth use of information technology today, hacking and other unauthorized activities have dynamically increased than ever before. With the development of hardware and software, attacks are growing exponentially in type and number. Nowadays, network traffic classification has essential significance, due to the high growth of Internet users. A lot of threats are created every day by individuals and organizations to attack computer networks to steal private information and data. To protect these attacks, many organizations put into practice a broad defense such as configuring a strong firewall, authentication systems, encryption, antivirus, latest hardware and so on. Intrusion detection is another mechanism that is used to mitigate network intrusions. Many Intrusion Detection Systems have been developed for monitoring and detecting network or systems against any suspicious activity. In most of them, low detection rate, high training time, and a relatively high false alarm rate are obtained. To overcome the problems, we proposed an approach that integrates the concepts of machine learning, big data and anomaly detection for obtaining better results with improved processing speed. The proposed system has training, validation and testing main components. In the training component, the collected training data is preprocessed and fed to the classification model. Four classification models: Random Forest, Neural Network, Logistic Regression, and Decision Tree are used and compared. In the validation component, hyperparameter tuning is done using 5-fold cross-validation with a grid search technique for each of the machine learning algorithms to find the optimal value for each hyperparameter to improve the detection rate of the models. Then, the classification models are trained using the best parameters to build the final model. Finally, the final trained model is used to classify the test data into normal or attack. All of the classification models are implemented on Apache Spark big data framework. The experimental work is carried out using the NSL-KDD dataset which contains normal and attacks data. We split the dataset into 68% for training, 17% for validation and 15% for testing. The results show that almost all the algorithms give high prediction results. Among the algorithms, Neural Network has acquired the best result which is 99.9% accuracy, 99.8% precision, 99.7% recall, and 99.7% f1-score
  • No Thumbnail Available
    Item
    Modeling Network Intrusion Detection System Based on Anomaly Approach Using Machine Learning Techniques
    (Addis Ababa University, 3/5/2020) Hidru, Tigist; Gizaw, Solomon
    With the rapid growth use of information technology today, hacking and other unauthorized activities have dynamically increased than ever before. With the development of hardware and software, attacks are growing exponentially in type and number. Nowadays, network traffic classification has essential significance, due to the high growth of Internet users. A lot of threats are created every day by individuals and organizations to attack computer networks to steal private information and data. To protect these attacks, many organizations put into practice a broad defense such as configuring a strong firewall, authentication systems, encryption, antivirus, latest hardware and so on. Intrusion detection is another mechanism that is used to mitigate network intrusions. Many Intrusion Detection Systems have been developed for monitoring and detecting network or systems against any suspicious activity. In most of them, low detection rate, high training time, and a relatively high false alarm rate are obtained. To overcome the problems, we proposed an approach that integrates the concepts of machine learning, big data and anomaly detection for obtaining better results with improved processing speed. The proposed system has training, validation and testing main components. In the training component, the collected training data is preprocessed and fed to the classification model. Four classification models: Random Forest, Neural Network, Logistic Regression, and Decision Tree are used and compared. In the validation component, hyperparameter tuning is done using 5-fold cross-validation with a grid search technique for each of the machine learning algorithms to find the optimal value for each hyperparameter to improve the detection rate of the models. Then, the classification models are trained using the best parameters to build the final model. Finally, the final trained model is used to classify the test data into normal or attack. All of the classification models are implemented on Apache Spark big data framework. The experimental work is carried out using the NSL-KDD dataset which contains normal and attacks data. We split the dataset into 68% for training, 17% for validation and 15% for testing. The results show that almost all the algorithms give high prediction results. Among the algorithms, Neural Network has acquired the best result which is 99.9% accuracy, 99.8% precision, 99.7% recall, and 99.7% f1-score
  • No Thumbnail Available
    Item
    Willingness to Pay for Amenity Values of Urban Forest: The Case of Addis Ababa
    (A.A.U, 2007-06) Gizaw, Solomon; Mohammed, Mahmud (Dr)
    The forest resource in Addis Ababa, particularly the mountainous areas to the north and western directions of the city was once covered with dense natural forests of diverse species. But now a day only few patches of natural forests are left in this area mainly due to development activities, agricultural expansions, over exploitations associated with rapid population growth and too little natural management of forest land. These events have resulted in serious environmental degradation. In view of these problems, a botanic garden is introduced in this area so as to give answer for the urgent need to conserve and sustain-ably utilize the remaining natural forest and restore degraded forest areas through expansion of forest plantations. Therefore, economic analysis is required for proper management of urban forests. Such analysis would help to make decisions on varieties of urban land use options and investments. Hence, this paper has examined the application of Contingent Valuation Method in measuring the households' willingness to pay (WTP) for Improved amenity service of urban forests and tries to identify the factors that may affect their WTP. The total WTP amount for improved amenity service of urban forests through executing the botanical garden is estimated to be Birr 4,265,211 per month. The mean WTP for the open-ended and dichotomous choice formats are Birr 6.07 and 9.30 per month per household respectively. In addition to this, above 87% of the respondents have the demand for further improvements. Here, the main values are related to non use values while use values are achieved distinctively low priority. Households income, above grade 6 level of education and respondents trust for the reliability of the project implementation are found to be the major determinant factors for households WTP. This study also indicated that households' welfare gains in changing from the current situation (poor environmental condition with no payment) to the improved service by subscribing some reasonable price can be huge. It also suggests that Contingent Valuation survey can measure amenity values of urban forests with theoretically consistent and sufficiently reliable results.