Recently machine learning-based intrusion detection approaches have been subjected to extensive researches because they can detect both misuse and anomaly. In this paper, rough set classification (RSC), a modern learn...Recently machine learning-based intrusion detection approaches have been subjected to extensive researches because they can detect both misuse and anomaly. In this paper, rough set classification (RSC), a modern learning algorithm, is used to rank the features extracted for detecting intrusions and generate intrusion detection models. Feature ranking is a very critical step when building the model. RSC performs feature ranking before generating rules, and converts the feature ranking to minimal hitting set problem addressed by using genetic algorithm (GA). This is done in classical approaches using Support Vector Machine (SVM) by executing many iterations, each of which removes one useless feature. Compared with those methods, our method can avoid many iterations. In addition, a hybrid genetic algorithm is proposed to increase the convergence speed and decrease the training time of RSC. The models generated by RSC take the form of'IF-THEN' rules, which have the advantage of explication. Tests and comparison of RSC with SVM on DARPA benchmark data showed that for Probe and DoS attacks both RSC and SVM yielded highly accurate results (greater than 99% accuracy on testing set).展开更多
Based on the historical observed data and the modeling results,this paper investigated the seasonal variations in the Taiwan Warm Current Water(TWCW)using a cluster analysis method and examined the contributions of th...Based on the historical observed data and the modeling results,this paper investigated the seasonal variations in the Taiwan Warm Current Water(TWCW)using a cluster analysis method and examined the contributions of the Kuroshio onshore intrusion and the Taiwan Strait Warm Current(TSWC)to the TWCW on seasonal time scales.The TWCW has obviously seasonal variation in its horizontal distribution,T-S characteristics and volume.The volume of TWCW is maximum(13746 km^3)in winter and minimum(11397 km^3)in autumn.As to the contributions to the TWCW,the TSWC is greatest in summer and smallest in winter,while the Kuroshio onshore intrusion northeast of Taiwan Island is strongest in winter and weakest in summer.By comparison,the Kuroshio onshore intrusion make greater contributions to the Taiwan Warm Current Surface Water(TWCSW)than the TSWC for most of the year,except for in the summertime(from June to August),while the Kuroshio Subsurface Water(KSSW)dominate the Taiwan Warm Current Deep Water(TWCDW).The analysis results demonstrate that the local monsoon winds is the dominant factor controlling the seasonal variation in the TWCW volume via Ekman dynamics,while the surface heat fl ux can play a secondary role via the joint ef fect of baroclinicity and relief.展开更多
Biological invasions are an important and growing component of global environmental change （Vitousek et al., 1996）. Hundreds of billions of dollars are lost each year to invasive species damage and management （Pime...Biological invasions are an important and growing component of global environmental change （Vitousek et al., 1996）. Hundreds of billions of dollars are lost each year to invasive species damage and management （Pimentel et al., 2001）. Scientists have responded by conducting research to understand the biology of the invasive species itself, in the hope that such information will allow effective control, and examining the impact of the invader on native taxa to determine the nature and magnitude of its effect.展开更多
Intrusion detection is regarded as classification in data mining field. However instead of directly mining the classification rules, class association rules, which are then used to construct a classifier, are mined fr...Intrusion detection is regarded as classification in data mining field. However instead of directly mining the classification rules, class association rules, which are then used to construct a classifier, are mined from audit logs. Some attributes in audit logs are important for detecting intrusion but their values are distributed skewedly. A relative support concept is proposed to deal with such situation. To mine class association rules effectively, an algorithms based on FP-tree is exploited. Experiment result proves that this method has better performance.展开更多
文摘Recently machine learning-based intrusion detection approaches have been subjected to extensive researches because they can detect both misuse and anomaly. In this paper, rough set classification (RSC), a modern learning algorithm, is used to rank the features extracted for detecting intrusions and generate intrusion detection models. Feature ranking is a very critical step when building the model. RSC performs feature ranking before generating rules, and converts the feature ranking to minimal hitting set problem addressed by using genetic algorithm (GA). This is done in classical approaches using Support Vector Machine (SVM) by executing many iterations, each of which removes one useless feature. Compared with those methods, our method can avoid many iterations. In addition, a hybrid genetic algorithm is proposed to increase the convergence speed and decrease the training time of RSC. The models generated by RSC take the form of'IF-THEN' rules, which have the advantage of explication. Tests and comparison of RSC with SVM on DARPA benchmark data showed that for Probe and DoS attacks both RSC and SVM yielded highly accurate results (greater than 99% accuracy on testing set).
基金Supported by the National Natural Science Foundation of China(Nos.41506020,41476019,41528601)the CAS Strategy Pioneering Program(No.XDA110020104)+2 种基金the Foundation for Innovative Research Groups of the National Natural Science Foundation of China(No.41421005)the NSFC-Shandong Joint Fund for Marine Science Research Centers(No.U1406401)the Global Change and Air-Sea Interaction(No.GASI-03-01-01-02)
文摘Based on the historical observed data and the modeling results,this paper investigated the seasonal variations in the Taiwan Warm Current Water(TWCW)using a cluster analysis method and examined the contributions of the Kuroshio onshore intrusion and the Taiwan Strait Warm Current(TSWC)to the TWCW on seasonal time scales.The TWCW has obviously seasonal variation in its horizontal distribution,T-S characteristics and volume.The volume of TWCW is maximum(13746 km^3)in winter and minimum(11397 km^3)in autumn.As to the contributions to the TWCW,the TSWC is greatest in summer and smallest in winter,while the Kuroshio onshore intrusion northeast of Taiwan Island is strongest in winter and weakest in summer.By comparison,the Kuroshio onshore intrusion make greater contributions to the Taiwan Warm Current Surface Water(TWCSW)than the TSWC for most of the year,except for in the summertime(from June to August),while the Kuroshio Subsurface Water(KSSW)dominate the Taiwan Warm Current Deep Water(TWCDW).The analysis results demonstrate that the local monsoon winds is the dominant factor controlling the seasonal variation in the TWCW volume via Ekman dynamics,while the surface heat fl ux can play a secondary role via the joint ef fect of baroclinicity and relief.
文摘Biological invasions are an important and growing component of global environmental change （Vitousek et al., 1996）. Hundreds of billions of dollars are lost each year to invasive species damage and management （Pimentel et al., 2001）. Scientists have responded by conducting research to understand the biology of the invasive species itself, in the hope that such information will allow effective control, and examining the impact of the invader on native taxa to determine the nature and magnitude of its effect.
基金The work is supported by Chinese NSF(Project No.60073034)
文摘Intrusion detection is regarded as classification in data mining field. However instead of directly mining the classification rules, class association rules, which are then used to construct a classifier, are mined from audit logs. Some attributes in audit logs are important for detecting intrusion but their values are distributed skewedly. A relative support concept is proposed to deal with such situation. To mine class association rules effectively, an algorithms based on FP-tree is exploited. Experiment result proves that this method has better performance.
