Classical intrusion detection system tends to identify attacks by using a set of rules known as signatures defined before the attack, this kind of detection is known as misuse intrusion detection. But reality is not always quantifiable, and this drives us to a new intrusion detection technique known as anomaly intrusion detection, due to the difficulties of defining normal pattern for random data frames, anomaly detection suffer from false positives, where normal traffic behavior is mistaken and classified as an attack and cause a great deal of manpower to manual sort the attacks. In this paper we construct a network based anomaly intrusion detection system using naive Bayes as weak learners enhanced with AdaBoost (Adaptive Boosing machine learning algorithm), experiment using KDD ’99 cup data proved that our IDS can achieve extremely low False Positive and has acceptable detection rate.
{"title":"Using Naive Bayes with AdaBoost to Enhance Network Anomaly Intrusion Detection","authors":"Wei Li, Qingxia Li","doi":"10.1109/ICINIS.2010.133","DOIUrl":"https://doi.org/10.1109/ICINIS.2010.133","url":null,"abstract":"Classical intrusion detection system tends to identify attacks by using a set of rules known as signatures defined before the attack, this kind of detection is known as misuse intrusion detection. But reality is not always quantifiable, and this drives us to a new intrusion detection technique known as anomaly intrusion detection, due to the difficulties of defining normal pattern for random data frames, anomaly detection suffer from false positives, where normal traffic behavior is mistaken and classified as an attack and cause a great deal of manpower to manual sort the attacks. In this paper we construct a network based anomaly intrusion detection system using naive Bayes as weak learners enhanced with AdaBoost (Adaptive Boosing machine learning algorithm), experiment using KDD ’99 cup data proved that our IDS can achieve extremely low False Positive and has acceptable detection rate.","PeriodicalId":319379,"journal":{"name":"2010 Third International Conference on Intelligent Networks and Intelligent Systems","volume":"4 11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129503405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Analytical hierarchy process is widely used in the system assessment. While a large number of operations need to be carried out to determine the consistency of comparison matrix. And when the comparison matrix is inconsistent, which should also be regulated and reduces the quality and efficiency of the assessment. In this essay, fuzzy consistent matrix which is verified using experimental data is adopted instead of comparison matrix. The fuzzy consistent matrix is in better consistent. So that it is applied in practical problem such as system performance assessment.
{"title":"Research on Fuzzy Consistent Matrix Generation Method Based on Entropy","authors":"Zhiguo Liu, Deyu Zhang","doi":"10.1109/ICINIS.2010.52","DOIUrl":"https://doi.org/10.1109/ICINIS.2010.52","url":null,"abstract":"Analytical hierarchy process is widely used in the system assessment. While a large number of operations need to be carried out to determine the consistency of comparison matrix. And when the comparison matrix is inconsistent, which should also be regulated and reduces the quality and efficiency of the assessment. In this essay, fuzzy consistent matrix which is verified using experimental data is adopted instead of comparison matrix. The fuzzy consistent matrix is in better consistent. So that it is applied in practical problem such as system performance assessment.","PeriodicalId":319379,"journal":{"name":"2010 Third International Conference on Intelligent Networks and Intelligent Systems","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126202086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents the development of an algorithm based on K-Means clustering and probabilistic neural network (PNN) for classifying the industrial system faults. The proposed technique consists of a preprocessing unit based on K-Means clustering and probabilistic neural network (PNN). Given a set of data points, firstly the K-Means algorithm is used to obtain K-temporary clusters, and then PNN is used to diagnose faults. To validate the performance and effectiveness of the proposed scheme, K-Means and PNN are applied to diagnose the faults in TE Process. Simulation studies show that the proposed algorithm not only provides an accepted degree of accuracy in fault classification under different fault conditions and the result is also reliable.
{"title":"Fault Diagnosis Based on K-Means Clustering and PNN","authors":"Dongsheng Wu, Qing Yang, Feng Tian, Dongxu Zhang","doi":"10.1109/ICINIS.2010.169","DOIUrl":"https://doi.org/10.1109/ICINIS.2010.169","url":null,"abstract":"This paper presents the development of an algorithm based on K-Means clustering and probabilistic neural network (PNN) for classifying the industrial system faults. The proposed technique consists of a preprocessing unit based on K-Means clustering and probabilistic neural network (PNN). Given a set of data points, firstly the K-Means algorithm is used to obtain K-temporary clusters, and then PNN is used to diagnose faults. To validate the performance and effectiveness of the proposed scheme, K-Means and PNN are applied to diagnose the faults in TE Process. Simulation studies show that the proposed algorithm not only provides an accepted degree of accuracy in fault classification under different fault conditions and the result is also reliable.","PeriodicalId":319379,"journal":{"name":"2010 Third International Conference on Intelligent Networks and Intelligent Systems","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121488127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Neural network has self-learning and adaptive ability, and has strong fault tolerance and robustness, so it has a broad applications in the pattern recognition. In this paper, we adopt an improved BP algorithm - Flexible BP algorithm (RPROP) in the image recogntion, and we used it to simulate the image recognition in this field of pattern recognition application . The results of the expriments show that this method can better overcome the shortcoming that use the BP algorithm trained the network, which may fall into the local minimum values, and the method has better improvement in the convergence precision and identification speed.
神经网络具有自学习和自适应能力，并且具有较强的容错性和鲁棒性，因此在模式识别中有着广泛的应用。本文在图像识别中采用了一种改进的BP算法——柔性BP算法(Flexible BP algorithm, RPROP)，并用它来模拟图像识别在模式识别领域的应用。实验结果表明，该方法能较好地克服使用BP算法训练网络可能陷入局部极小值的缺点，在收敛精度和识别速度上有较好的提高。
{"title":"The Research and Application of Image Recognition Based on Improved BP Algorithm","authors":"G. Wei, Liu Piyan, Zhao Hai, Mei Zhan","doi":"10.1109/ICINIS.2010.144","DOIUrl":"https://doi.org/10.1109/ICINIS.2010.144","url":null,"abstract":"Neural network has self-learning and adaptive ability, and has strong fault tolerance and robustness, so it has a broad applications in the pattern recognition. In this paper, we adopt an improved BP algorithm - Flexible BP algorithm (RPROP) in the image recogntion, and we used it to simulate the image recognition in this field of pattern recognition application . The results of the expriments show that this method can better overcome the shortcoming that use the BP algorithm trained the network, which may fall into the local minimum values, and the method has better improvement in the convergence precision and identification speed.","PeriodicalId":319379,"journal":{"name":"2010 Third International Conference on Intelligent Networks and Intelligent Systems","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123310314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Firstly, the concept of Multi-Agent System (MAS) was described. And then introduced the whole management modeling based on MAS, which can realized the information transmission and share instantly via Order Agent (OA), Manager Agent (MA), Production Agent (PA) and Service Agent (SA). PA is also built on MAS and it includes two agents, Task Agent (TA) and Resource Agent (RA). It has been found that this modeling can improve the working flow and production efficiency and shorten the time of delivery.
{"title":"Research on Production Agent Modeling Based on MAS","authors":"Li He, Yongxian Liu, Kelong Zhang","doi":"10.1109/ICINIS.2010.80","DOIUrl":"https://doi.org/10.1109/ICINIS.2010.80","url":null,"abstract":"Firstly, the concept of Multi-Agent System (MAS) was described. And then introduced the whole management modeling based on MAS, which can realized the information transmission and share instantly via Order Agent (OA), Manager Agent (MA), Production Agent (PA) and Service Agent (SA). PA is also built on MAS and it includes two agents, Task Agent (TA) and Resource Agent (RA). It has been found that this modeling can improve the working flow and production efficiency and shorten the time of delivery.","PeriodicalId":319379,"journal":{"name":"2010 Third International Conference on Intelligent Networks and Intelligent Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131526815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hilbert-Huang Transform (HHT) is a kind of signal analysis method proposed by Huang in the late 20th century. The combination of HHT and vector signal processing is called vector HHT. To solve the problem of too much computational cost in the real-time implementation of vector HHT, this paper makes some improvement on vector HHT for real-time operation, including the improvement on sifting method, curve fitting, treatment of boundary and stop condition. Both performance and operation speed are considered in the improvement. The improved algorithm has much less computational cost, with performance basically remaining unchanged. A parallel signal processing system composed of multiple chips digital signal processor (DSP) is designed, in which vector HHT is implemented real time. The result obtained from the parallel signal processing system shows that the system met the need of data real time processing, and has good performance.
{"title":"Real-time Implementation of Vector Hilbert-Huang Transform","authors":"Zheng Zhu, Yilin Wang, Ping Cai","doi":"10.1109/ICINIS.2010.174","DOIUrl":"https://doi.org/10.1109/ICINIS.2010.174","url":null,"abstract":"Hilbert-Huang Transform (HHT) is a kind of signal analysis method proposed by Huang in the late 20th century. The combination of HHT and vector signal processing is called vector HHT. To solve the problem of too much computational cost in the real-time implementation of vector HHT, this paper makes some improvement on vector HHT for real-time operation, including the improvement on sifting method, curve fitting, treatment of boundary and stop condition. Both performance and operation speed are considered in the improvement. The improved algorithm has much less computational cost, with performance basically remaining unchanged. A parallel signal processing system composed of multiple chips digital signal processor (DSP) is designed, in which vector HHT is implemented real time. The result obtained from the parallel signal processing system shows that the system met the need of data real time processing, and has good performance.","PeriodicalId":319379,"journal":{"name":"2010 Third International Conference on Intelligent Networks and Intelligent Systems","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116927725","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, a clustering method for handwritten digit recognition is studied. The digit samples, firstly are processed and features are extracted. Based on these features, a clustering method is designed and implemented to cluster the digit samples. Experiments finally show that the clustering method is efficient in handwritten digit recognition.
{"title":"On a Clustering Method for Handwritten Digit Recognition","authors":"Ye Xu, Wei Zhang","doi":"10.1109/ICINIS.2010.130","DOIUrl":"https://doi.org/10.1109/ICINIS.2010.130","url":null,"abstract":"In this paper, a clustering method for handwritten digit recognition is studied. The digit samples, firstly are processed and features are extracted. Based on these features, a clustering method is designed and implemented to cluster the digit samples. Experiments finally show that the clustering method is efficient in handwritten digit recognition.","PeriodicalId":319379,"journal":{"name":"2010 Third International Conference on Intelligent Networks and Intelligent Systems","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115436959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pareto on-off models were widely adopted to simulate and construct network traffic with self-similar characteristic. In this paper, a new Pareto-Poisson model was proposed based on AOS multiplexing. And the new model can produce self-similarity network traffic with adjustable H parameter. In the R/S test algorithm, the new self-similar represents well the self-similar characteristic.
{"title":"Reseach on the Self-Similarity of Multi-probabilty Ditribution Based on ON-OFF Models in AOS Multiplexing","authors":"Yuntao Zhao, Chengsheng Pan, Ye Tian, Mingxue Bi","doi":"10.1109/ICINIS.2010.83","DOIUrl":"https://doi.org/10.1109/ICINIS.2010.83","url":null,"abstract":"Pareto on-off models were widely adopted to simulate and construct network traffic with self-similar characteristic. In this paper, a new Pareto-Poisson model was proposed based on AOS multiplexing. And the new model can produce self-similarity network traffic with adjustable H parameter. In the R/S test algorithm, the new self-similar represents well the self-similar characteristic.","PeriodicalId":319379,"journal":{"name":"2010 Third International Conference on Intelligent Networks and Intelligent Systems","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124862378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper addresses the problem of stabilizing discrete-time linear systems with quantized state feedback control, where sensors, controllers and plants are connected by noisy communication channels. The approach to be proposed here is to implement dynamic uniform quantizers and dynamic state feedback controllers. The case with disturbance inputs is argued. It is derived that based on the policy, the dynamic state feedback controller can stabilize the unstable plant. Simulation results show the validity of the proposed quantization policy.
{"title":"Stabilization of Quantized Feedback Control Systems with Communication Constraints","authors":"Qingquan Liu, F. Jin","doi":"10.1109/ICINIS.2010.60","DOIUrl":"https://doi.org/10.1109/ICINIS.2010.60","url":null,"abstract":"This paper addresses the problem of stabilizing discrete-time linear systems with quantized state feedback control, where sensors, controllers and plants are connected by noisy communication channels. The approach to be proposed here is to implement dynamic uniform quantizers and dynamic state feedback controllers. The case with disturbance inputs is argued. It is derived that based on the policy, the dynamic state feedback controller can stabilize the unstable plant. Simulation results show the validity of the proposed quantization policy.","PeriodicalId":319379,"journal":{"name":"2010 Third International Conference on Intelligent Networks and Intelligent Systems","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129128177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
TDDM-BOC modulation signal is realized to overlap with different signals in the same frequency and has the better anti-jamming ability, because of the unique character of split spectrum and auto-correlation multi-peak. According to the auto-correlation character of TDDM-BOC modulation signal, an algorithm is proposed for direct acquiring TDDM-BOC signal based on sub-sampling. With decreasing Signal-to-Noise, the algorithm is simulated and its performance is analyzed. The validity of the algorithm with the lower SNR is proved by simulation result under band-pass sub-sampling. The number of computing data is much less, because of the lower sampling frequency.
{"title":"The Research of Acquiring TDDM-BOC Signal Base on Sub-sampling","authors":"Bo Qian, B. Dong, Ren Li, S. Sun","doi":"10.1109/ICINIS.2010.109","DOIUrl":"https://doi.org/10.1109/ICINIS.2010.109","url":null,"abstract":"TDDM-BOC modulation signal is realized to overlap with different signals in the same frequency and has the better anti-jamming ability, because of the unique character of split spectrum and auto-correlation multi-peak. According to the auto-correlation character of TDDM-BOC modulation signal, an algorithm is proposed for direct acquiring TDDM-BOC signal based on sub-sampling. With decreasing Signal-to-Noise, the algorithm is simulated and its performance is analyzed. The validity of the algorithm with the lower SNR is proved by simulation result under band-pass sub-sampling. The number of computing data is much less, because of the lower sampling frequency.","PeriodicalId":319379,"journal":{"name":"2010 Third International Conference on Intelligent Networks and Intelligent Systems","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128816461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：