Several data mining techniques such as Hidden Markov Model (HMM), artificial neural network, statistical techniques and expert systems are used to model network packets in the field of intrusion detection. In this pap...Several data mining techniques such as Hidden Markov Model (HMM), artificial neural network, statistical techniques and expert systems are used to model network packets in the field of intrusion detection. In this paper a novel intrusion detection mode based on understandable Neural Network Tree (NNTree) is pre-sented. NNTree is a modular neural network with the overall structure being a Decision Tree (DT), and each non-terminal node being an Expert Neural Network (ENN). One crucial advantage of using NNTrees is that they keep the non-symbolic model ENN’s capability of learning in changing environments. Another potential advantage of using NNTrees is that they are actually “gray boxes” as they can be interpreted easily if the num-ber of inputs for each ENN is limited. We showed through experiments that the trained NNTree achieved a simple ENN at each non-terminal node as well as a satisfying recognition rate of the network packets dataset. We also compared the performance with that of a three-layer backpropagation neural network. Experimental results indicated that the NNTree based intrusion detection model achieved better performance than the neural network based intrusion detection model.展开更多
Finding the optimum solution for dispatching in concrete delivery is computationally intractable because it is a NP-hard （non-deterministic polynomial-time hard） problem. Heuristic methods are required to obtain sat...Finding the optimum solution for dispatching in concrete delivery is computationally intractable because it is a NP-hard （non-deterministic polynomial-time hard） problem. Heuristic methods are required to obtain satisfactory solutions. Inefficiencies in mathematical modeling still make concrete dispatching difficult to solve. In reality, complex dispatching systems are mostly handled by human experts, who are able to manage the assigned tasks well. However, the high dependency on human expertise is a considerable challenge for RMC （ready mixed concrete） companies. In this paper, a logical reconstruction of an expert＇s decision making is achieved by two machine learning techniques： decision tree and rule induction. This paper focuses on the expert dispatcher＇s prioritization of customer orders. The proposed method has been tested on a simulation model consisting of a batch plant and three customers per day. The scenarios generated by the simulation model were given to a dispatch manager who was asked to prioritize the customers in each day. The scenarios and the decisions were then input to the machine learning programs, which created generalizations of the expert＇s decisions. Both decision trees and rules approach 80% accuracy in reproducing the human performance.展开更多
基金Supported in part by the National Natural Science Foundation of China (No.60272046, No.60102011), Na-tional High Technology Project of China (No.2002AA143010), Natural Science Foundation of Jiangsu Province (No.BK2001042), and the Foundation for Excellent Doctoral Dissertation of Southeast Univer-sity (No.YBJJ0412).
文摘Several data mining techniques such as Hidden Markov Model (HMM), artificial neural network, statistical techniques and expert systems are used to model network packets in the field of intrusion detection. In this paper a novel intrusion detection mode based on understandable Neural Network Tree (NNTree) is pre-sented. NNTree is a modular neural network with the overall structure being a Decision Tree (DT), and each non-terminal node being an Expert Neural Network (ENN). One crucial advantage of using NNTrees is that they keep the non-symbolic model ENN’s capability of learning in changing environments. Another potential advantage of using NNTrees is that they are actually “gray boxes” as they can be interpreted easily if the num-ber of inputs for each ENN is limited. We showed through experiments that the trained NNTree achieved a simple ENN at each non-terminal node as well as a satisfying recognition rate of the network packets dataset. We also compared the performance with that of a three-layer backpropagation neural network. Experimental results indicated that the NNTree based intrusion detection model achieved better performance than the neural network based intrusion detection model.
文摘Finding the optimum solution for dispatching in concrete delivery is computationally intractable because it is a NP-hard （non-deterministic polynomial-time hard） problem. Heuristic methods are required to obtain satisfactory solutions. Inefficiencies in mathematical modeling still make concrete dispatching difficult to solve. In reality, complex dispatching systems are mostly handled by human experts, who are able to manage the assigned tasks well. However, the high dependency on human expertise is a considerable challenge for RMC （ready mixed concrete） companies. In this paper, a logical reconstruction of an expert＇s decision making is achieved by two machine learning techniques： decision tree and rule induction. This paper focuses on the expert dispatcher＇s prioritization of customer orders. The proposed method has been tested on a simulation model consisting of a batch plant and three customers per day. The scenarios generated by the simulation model were given to a dispatch manager who was asked to prioritize the customers in each day. The scenarios and the decisions were then input to the machine learning programs, which created generalizations of the expert＇s decisions. Both decision trees and rules approach 80% accuracy in reproducing the human performance.
