IJCSIS Papers by Alebachew Chiche Zewdu
With the wide use of Internet and network connectivity, it is important to prevent unauthorized a... more With the wide use of Internet and network connectivity, it is important to prevent unauthorized access to system resources and data. In this study, we present a new Network Intrusion Detection System by integrating data mining and knowledge based system to detect a network attacks. Hybrid data mining process model is followed for data mining tasks to extract hidden knowledge from KDDCup'99 intrusion dataset. J48 decision tree, JRip rule induction, Naïve Bayes and Multilayer Perceptron (MLP) Neural Network are adopted to construct a predictive model on total datasets of 63, 661 instances. This study supports network administrators to fill the knowledge gap they have to detect network attacks efficiently and effectively. Experimental result shows that, the proposed system performs 91.43 percent and 83 percent accuracy and user acceptance, respectively. Further work is required to acquire and integrate prevention knowledge automatically with the predictive model.
With the wide use of Internet and network connectivity, it is important to prevent unauthorized a... more With the wide use of Internet and network connectivity, it is important to prevent unauthorized access to system resources and data. In this study, we present a new Network Intrusion Detection System by integrating data mining and knowledge based system to detect a network attacks. Hybrid data mining process model is followed for data mining tasks to extract hidden knowledge from KDDCup'99 intrusion dataset. J48 decision tree, JRip rule induction, Naïve Bayes and Multilayer Perceptron (MLP) Neural Network are adopted to construct a predictive model on total datasets of 63, 661 instances. This study supports network administrators to fill the knowledge gap they have to detect network attacks efficiently and effectively. Experimental result shows that, the proposed system performs 91.43 percent and 83 percent accuracy and user acceptance, respectively. Further work is required to acquire and integrate prevention knowledge automatically with the predictive model.
Papers by Alebachew Chiche Zewdu
An Ensemble Method for Supervised Learning for Intrusion Detection and Network Forensics
IntechOpen eBooks, Jun 10, 2024
Action Reseach on reflctive teaching in the Plasma context: the case of Menelik II Preparatory School
In this study, an intelligent network intrusion detection and prevention system is presented for ... more In this study, an intelligent network intrusion detection and prevention system is presented for detecting network attacks that incorporates a knowledge based system and data mining techniques. To extract hidden knowledge from KDDCup’99 dataset, hybrid data mining process is used. The intrusion dataset for the study is collected from MIT Lincon lab. A predictive model is constructed on total datasets of 63, 661 instances using JRip rule induction, Naïve Bayes,J48 decision tree and Multilayer Perceptron (MLP) Neural Network. During training 99.91% prediction accuracy is achieved by J48 decision tree. So, the J48 model is integrated with knowledge based system automatically for designing intelligent network intrusion detection and prevention system. In addition, knowledge is acquired, represented and organized in the knowledge based so as to suggest possible prevention for detected attacks. Evaluation results show that the proposed system registers 91.43% accuracy in network intrusion...
Hybrid Decision Support System Framework for Crop Yield Prediction and Recommendation
International Journal of Computing, 2019
In this paper, a hybrid decision support system is presented which uses both quantitative and qua... more In this paper, a hybrid decision support system is presented which uses both quantitative and qualitative data to provide effective and efficient decision making for crop yield prediction and suggestion. Our framework integrates KD-DSS and DD-DSS for solving complex problems by complementing the existing gap of individual decision support system in agriculture domain. For analyzing collected quantitative data of agriculture research center, our framework uses artificial neural network as a data mining technique. So, we use ANN for uncovering hidden knowledge in stored dataset. And this knowledge is further integrated with the knowledge base developed by acquiring qualitative data from expertise and represented using an IF-THEN production rule. The integration of knowledge collected from both qualitative and quantitative source of data provides a potential advantage for solving complex problems for decision makers. Finally, we will have the opportunity to enhance the framework coupli...
Journal of Computer Networks and Communications
This paper introduces a new integrated learning approach towards developing a new network intrusi... more This paper introduces a new integrated learning approach towards developing a new network intrusion detection model that is scalable and adaptive nature of learning. The approach can improve the existing trends and difficulties in intrusion detection. An integrated approach of machine learning with knowledge-based system is proposed for intrusion detection. While machine learning algorithm is used to construct a classifier model, knowledge-based system makes the model scalable and adaptive. It is empirically tested with NSL-KDD dataset of 40,558 total instances, by using ten-fold cross validation. Experimental result shows that 99.91% performance is registered after connection. Interestingly, significant knowledge rich learning for intrusion detection differs as a fundamental feature of intrusion detection and prevention techniques. Therefore, security experts are recommended to integrate intrusion detection in their network and computer systems, not only for well-being of their com...
https://doi.org/10.1155/2021/8845540 Alebachew Chiche, Million Meshesha, "Towards a Scalable and Adaptive Learning Approach for Network Intrusion Detection", Journal of Computer Networks and Communications, vol. 2021, Article ID 8845540, 9 pages, 2021., 2021
is paper introduces a new integrated learning approach towards developing a new network intrusion... more is paper introduces a new integrated learning approach towards developing a new network intrusion detection model that is scalable and adaptive nature of learning. e approach can improve the existing trends and difficulties in intrusion detection. An integrated approach of machine learning with knowledge-based system is proposed for intrusion detection. While machine learning algorithm is used to construct a classifier model, knowledge-based system makes the model scalable and adaptive. It is empirically tested with NSL-KDD dataset of 40,558 total instances, by using tenfold cross validation. Experimental result shows that 99.91% performance is registered after connection. Interestingly, significant knowledge rich learning for intrusion detection differs as a fundamental feature of intrusion detection and prevention techniques. erefore, security experts are recommended to integrate intrusion detection in their network and computer systems, not only for well-being of their computer systems but also for the sake of improving their working process.
ournal of Theoretical and Applied Information Technology, 2017
In this study, an intelligent network intrusion detection and prevention system is presented for ... more In this study, an intelligent network intrusion detection and prevention system is presented for detecting network attacks that incorporates a knowledge based system and data mining techniques. To extract hidden knowledge from KDDCup'99 dataset, hybrid data mining process is used. The intrusion dataset for the study is collected from MIT Lincon lab. A predictive model is constructed on total datasets of 63, 661 instances using JRip rule induction, Naïve Bayes,J48 decision tree and Multilayer Perceptron (MLP) Neural Network. During training 99.91% prediction accuracy is achieved by J48 decision tree. So, the J48 model is integrated with knowledge based system automatically for designing intelligent network intrusion detection and prevention system. In addition, knowledge is acquired, represented and organized in the knowledge based so as to suggest possible prevention for detected attacks. Evaluation results show that the proposed system registers 91.43% accuracy in network intrusion detection and 85% in user acceptance testing. This indicates that the performance of the proposed system is promising to design an intelligent network intrusion detection system that can effectively predict and provide a prevention mechanism. The system cannot update the knowledge of prevention techniques automatically which need further researches.
JASC: Journal of Applied Science and Computations, 2019
The rapid growth in digital world, use of surveillance system, communication, ecommerce, informat... more The rapid growth in digital world, use of surveillance system, communication, ecommerce, information technology, concept of national security is becoming more and more of an issue, where person identification is very important. In this Face Feature Extraction Technique Using Polynomial Neural Network (PNN) and Genetic Algorithm (GA) for Person Identification (PI) System is the process of establishing the identity of individual (whose identity is often not known) from there stored facial attributes\features. In this approach it performs better than the PNN (Polynomial Neural Network) and other approaches of PNN such as PNN with Gradient Descent. The performances such as time and classification accuracy of the classifiers are illustrated on well known datasets from various repositories. The relevant feature subsets are selected by using GA. Feature selections are done by Polynomial Neural Networks. BioId Dataset is used for the experiment. PI system Recognition based on face inflection is widely use and acceptable approach for the identification and verification of the person.
International Journal of Computing , 2019
In this paper, a hybrid decision support system is presented which
uses both quantitative and qua... more In this paper, a hybrid decision support system is presented which
uses both quantitative and qualitative data to provide effective and efficient decision making for crop yield prediction and suggestion. Our framework integrates KD-DSS and DD-DSS for solving complex problems by complementing the existing gap of individual decision support system in agriculture domain. For analyzing collected quantitative data of agriculture research center, our framework uses artificial neural network as a data mining technique. So, we use ANN for uncovering hidden knowledge in stored dataset. And this knowledge is further integrated with the knowledge base developed by acquiring qualitative data from expertise and represented using an IF-THEN production rule. The integration of knowledge collected from both qualitative and quantitative source of data provides a potential advantage for solving complex problems for decision makers. Finally, we will have the opportunity to enhance the framework coupling the features which can provide a group knowledge sharing among decision makers. So, this feature can present the opportunities to fill the disparity of decisions made by different decision makers.
In this study, an intelligent network intrusion detection and prevention system is presented for ... more In this study, an intelligent network intrusion detection and prevention system is presented for detecting network attacks that incorporates a knowledge based system and data mining techniques. To extract hidden knowledge from KDDCup'99 dataset, hybrid data mining process is used. The intrusion dataset for the study is collected from MIT Lincon lab. A predictive model is constructed on total datasets of 63, 661 instances using JRip rule induction, Naïve Bayes,J48 decision tree and Multilayer Perceptron (MLP) Neural Network. During training 99.91% prediction accuracy is achieved by J48 decision tree. So, the J48 model is integrated with knowledge based system automatically for designing intelligent network intrusion detection and prevention system. In addition, knowledge is acquired, represented and organized in the knowledge based so as to suggest possible prevention for detected attacks. Evaluation results show that the proposed system registers 91.43% accuracy in network intrusion detection and 85% in user acceptance testing. This indicates that the performance of the proposed system is promising to design an intelligent network intrusion detection system that can effectively predict and provide a prevention mechanism. The system cannot update the knowledge of prevention techniques automatically which need further researches.
Uploads
IJCSIS Papers by Alebachew Chiche Zewdu
Papers by Alebachew Chiche Zewdu
uses both quantitative and qualitative data to provide effective and efficient decision making for crop yield prediction and suggestion. Our framework integrates KD-DSS and DD-DSS for solving complex problems by complementing the existing gap of individual decision support system in agriculture domain. For analyzing collected quantitative data of agriculture research center, our framework uses artificial neural network as a data mining technique. So, we use ANN for uncovering hidden knowledge in stored dataset. And this knowledge is further integrated with the knowledge base developed by acquiring qualitative data from expertise and represented using an IF-THEN production rule. The integration of knowledge collected from both qualitative and quantitative source of data provides a potential advantage for solving complex problems for decision makers. Finally, we will have the opportunity to enhance the framework coupling the features which can provide a group knowledge sharing among decision makers. So, this feature can present the opportunities to fill the disparity of decisions made by different decision makers.