With the rapid growth of the Internet, to make sure of the computer security has been a crucial problem, therefore, many techniques for Intrusion detection have been proposed in order to detect network attacks efficie...
详细信息
ISBN:
(纸本)9781424481262
With the rapid growth of the Internet, to make sure of the computer security has been a crucial problem, therefore, many techniques for Intrusion detection have been proposed in order to detect network attacks efficiently. On the other hand, data mining algorithms based on genetic network programming (GNP) have been proposed recently. GNP is a graph-based evolutionary algorithm and can extract many important class association rules by making use of the distinguished representation ability of the graph structures. In this paper, a probabilistic classification is proposed and combined with the class association rule mining of GNP, and applied to network intrusion detection for the performance evaluation. The proposed method creates a joint probability density function of normal and intrusion accesses and use it to efficiently classify new access data into normal, known intrusion or unknown intrusion. It is clarified from the experimental results that the proposed method shows high classification accuracy compared to the method without probabilistic classification.
In traditional financial studies, existing approaches are unable to address increasingly complex problems. In this paper, an artificial financial market is proposed, in accordance with the adaptation market hypothesis...
详细信息
In traditional financial studies, existing approaches are unable to address increasingly complex problems. In this paper, an artificial financial market is proposed, in accordance with the adaptation market hypothesis, using artificial intelligence algorithms. This market includes three types of agents with different investments and risk preferences, representing the heterogeneity of traders. genetic network programming is combined with a state-action-reward-state-action (SARSA)(lambda) algorithm for designing the market to reflect the adaptation of technical agents. A pricing mechanism is taken into consideration, based on the auction mechanism of the Chinese securities market. The characteristics of price time series are analyzed to determine whether excessive volatility exists in four different markets. Explanations are provided for the corresponding financial phenomena considering the hypotheses under the proposed novel artificial financial market.
Traditional PCA-based face recognition algorithms usually have low performance in the complicated illumination database. There are two reasons. One is that the number of classes is large compared with other classifica...
详细信息
ISBN:
(纸本)9781457706530
Traditional PCA-based face recognition algorithms usually have low performance in the complicated illumination database. There are two reasons. One is that the number of classes is large compared with other classification problems. The other is that the data in the PCA domain distributes in a narrow space and overlaps frequently. This paper presents a novel supervised learning framework for PCA-based face recognition using genetic network programming (GNP) fuzzy data mining (GNP-FDM). In the proposed framework, a face recognition oriented genetic-based clustering algorithm (GCA) is used to reduce the number of classes and overlaps in the recognition. And, a fuzzy class association rules (FCARs) based classifier is applied to mine the inherent relationships between eigen-vectors and to improve the recognition accuracy. Experimental results on the extended Yale-B database indicate that the proposed supervised learning framework has higher accuracy compared with the traditional PCA-based methods.
This research proposes a decision support system of database cluster optimization using genetic network programming (GNP) with on-line rule based clustering. GNP optimizes cluster quality by reanalyzing weak points of...
详细信息
This research proposes a decision support system of database cluster optimization using genetic network programming (GNP) with on-line rule based clustering. GNP optimizes cluster quality by reanalyzing weak points of each cluster and maintaining rules stored in each cluster. The maintenance of rules includes: 1) adding new relevant rules;2) moving rules between clusters;and 3) removing irrelevant rules. The simulations focus on optimizing cluster quality response against several unbalanced data growth to the data-set that is working with storage rules. The simulation results of the proposed method show its priority comparing to GNP rule based clustering without on-line optimization.
In this paper, we discuss a method for automatic programming of inspection image processing. In the industrial field, automatic program generators or expert systems are expected to shorten a period required for develo...
详细信息
ISBN:
(数字)9781510611221
ISBN:
(纸本)9781510611214;9781510611221
In this paper, we discuss a method for automatic programming of inspection image processing. In the industrial field, automatic program generators or expert systems are expected to shorten a period required for developing a new appearance inspection system. So-called "image processing expert system" have been studied for over the nearly 30 years. We are convinced of the need to adopt a new idea. Recently, a novel type of evolutionary algorithms, called genetic network programming (GNP), has been proposed. In this study, we use GNP as a method to create an inspection image processing logic. GNP develops many directed graph structures, and shows excellent ability of formulating complex problems. We have converted this network program model to Image Processing networkprogramming (IPNP). IPNP selects an appropriate image processing command based on some characteristics of input image data and processing log, and generates a visual inspection software with series of image processing commands. It is verified from experiments that the proposed method is able to create some inspection image processing programs. In the basic experiment with 200 test images, the success rate of detection of target region was 93.5%.
With the increasing popularity of the Internet, network security has become a serious problem recently. How to detect intrusions effectively becomes an important component in network security. Therefore, a variety of ...
详细信息
With the increasing popularity of the Internet, network security has become a serious problem recently. How to detect intrusions effectively becomes an important component in network security. Therefore, a variety of algorithms have been devoted to this challenge. genetic network programming is a newly developed evolutionary algorithm with directed graph gene structures, and it has been applied to data mining for intrusion detection systems providing good performances in intrusion detection. In this paper, an integrated rule mining algorithm based on fuzzy GNP and probabilistic classification is proposed. The integrated rule mining uses fuzzy class association rule mining algorithm to extract rules with different classes. Actually, it can deal with both discrete and continuous attributes in network connection data. Then, the classification is done probabilistically using different class rules. The integrated method showed excellent results by simulation experiments.
This paper proposes a database clustering algorithm using genetic network programming (GNP) with the advantages of fuzzy object oriented database modeling. GNP creates clusters based on pattern classification, where a...
详细信息
ISBN:
(纸本)9781479999590
This paper proposes a database clustering algorithm using genetic network programming (GNP) with the advantages of fuzzy object oriented database modeling. GNP creates clusters based on pattern classification, where a cluster label is assigned to each object represented by a set of fuzzy features. GNP is one of the evolutionary algorithms and the main object of its evolution in this paper is to discover fuzzy rules from a fuzzy object oriented database. The optimization of the clusters is executed so that the objects with high similarity are put into the same cluster. The results of clustering simulations show that the proposed method can create better clusters comparing to the conventional clustering methods.
This paper proposes a new strategy on pruning generalized multi-order rules accumulated by genetic network programming with Rule Accumulation (GNP-RA). In the pruning method, the usage of each rule (flagged by variabl...
详细信息
ISBN:
(纸本)9781457707148
This paper proposes a new strategy on pruning generalized multi-order rules accumulated by genetic network programming with Rule Accumulation (GNP-RA). In the pruning method, the usage of each rule (flagged by variable U) and the number of the days having important information in each rule (flagged by variable N) can be evolved by GA. As a result, the pruned rules with better combinations of variable U and variable N are obtained by the crossover and mutation of these variables. The proposed method is verified through experimental studies in stock markets. The effectiveness and efficiency of the proposed method are proved by simulation results.
Previously, a principal component analysis (PCA) based face recognition framework using genetic network programming (GNP) and Fuzzy Data Mining (GNP-PCA) was proposed to improve both the accuracy and robustness of the...
详细信息
ISBN:
(纸本)9784907764388
Previously, a principal component analysis (PCA) based face recognition framework using genetic network programming (GNP) and Fuzzy Data Mining (GNP-PCA) was proposed to improve both the accuracy and robustness of the conventional PCA-based face recognition algorithm in the complicated illumination database. However, it is still not robust enough in the noisy testing environments. Therefore, a GNP-based multi-agent system is constructed by GNP-PCA and multi-resolution analysis in this paper. In the proposed approach, the different scales of images in the training set are regarded as different environments and each GNP-PCA is performed as an agent in each environment. Recognition is eventually realized by evaluating the prediction scores for different classes. According to the experimental results, the proposed method has almost no accuracy loss in the Gaussian noisy testing environments compared with GNP-PCA.
暂无评论