Ju Jiang

Intrusion detection using hierarchical neural networks

Most intrusion detection system (IDS) with a single-level structure can only detect either misuse or anomaly attacks. Some IDSs with multi-level structure or multi-classifier are proposed to detect both attacks, but they are limited in adaptively learning. In this paper, two hierarchical IDS frameworks using Radial Basis Functions (RBF) are proposed. A serial hierarchical IDS (SHIDS) is proposed to identify misuse attack accurately and anomaly attacks adaptively. A parallel hierarchical IDS (PHIDS) is proposed to enhance the SHIDSs functionalities and performance. The experiments show that the two proposed IDSs can detect network intrusions in real-time, train new classifiers for novel intrusions automatically, and modify their structures adaptively after new classifiers are trained.

RBF-based real-time hierarchical intrusion detection systems

An intrusion detection system (IDS) is an art to detect network intrusions by monitoring the network traffic patterns. Generally, an IDS uses only a single-layer detection structure; therefore it cannot adjust its structure adaptively and automatically. In this paper, two hierarchical IDSs, the serial hierarchical and parallel hierarchical IDSs, are proposed. Both of them are based on radial basis function (RBF) neural networks. Because of the short training time and high accuracy of the RBF neural networks, two hierarchical IDSs can monitor network traffic in real-time, train new classifiers for novel intrusions automatically, and modify their structures adaptively after new classifiers are trained.

Comparison of BPL and RBF network in intrusion detection system

In this paper, we present the performance comparison results of the backpropagation learning (BPL) algorithm in a multilayer perceptron (MLP) neural network and the radial basis functions (RBF) network for intrusion detection. The results show that RBF network improves the performance of intrusion detection systems (IDSs) in anomaly detection with a high detection rate and a low false positive rate. RBF network requires less training time and can be optimized to balance the detection and the false positive rates.

Adaptive mode switching of hypersonic morphing aircraft based on type-2 TSK fuzzy sliding mode control

This paper presents a novel adaptive mode switching scheme for hypersonic morphing aircraftwith retracted winglets based on type-2 Takagi-Sugeno-Kang (TSK) fuzzy sliding mode control. For each ofretracting and stretching modes, a specific sliding mode controller has been adopted. Drawing upon input/outputlinearization to globally linearize the nonlinear model of the hypersonic aircraft at first, a type-2 TSK fuzzylogic system is devised for robust mode switching between these sliding mode controllers. For rapid stabilizationof the system, the adaptive law for mode switching is designed using a direct constructive Lyapunov analysis.Simulation results demonstrate the stability and smooth transition using the proposed switched control scheme.创新点本文提出一种新的基于二型TSK模糊滑模控制的可变翼高超声速飞行器自适应模态切换方法。对于小翼收回和伸出两个模态, 采用滑模控制使其稳定。对于小翼伸缩的切换过程, 首先利用输入输出反馈线性化使飞行器的非线性模型精确线性化, 然后设计二型TSK模糊逻辑系统使小翼收回和伸出两个模态的滑模控制器实现平滑切换。为了使系统能够快速稳定, 利用李雅普诺夫稳定性理论设计模态切换的自适应律。仿真结果表明本文所提出的切换控制方法能够实现模态切换的稳定性和平滑性。

Reinforcement learning and aggregation

Reinforcement learning (RL) is a learning technique that provides a means for learning an optimal control policy when the dynamics of the environment under consideration is unavailable [L.P. Kaelbling et al., 1996, R.S. Sutton and A.G. Barto, 1998]. While RL has been successfully applied in many single or multiple agents systems [S. Arai et al., 2000, H.R. Berenji and D.A. Vengerov, 2000, M. Tan, 1993, Y. Nagayuki et al., 2000], the learning quality is greatly influenced by learning algorithms and their parameters. Setting of the parameters of RL algorithms is something of a black art, and small differences in these parameters can lead to large differences in learning qualities. Determining the best algorithm and the optimal parameters can be costly in terms of time and computation. Even if the cost is acceptable, the robustness of learning is still a question. In order to address the difficulty, an aggregated multiagent reinforcement learning system (AMRLS) is proposed to deal with the RL environment as a multiagent environment. A maze world environment is used to validate the AMRLS. Experimental results illustrate that compared with normal Q(/spl lambda/)-learning and SARSA(/spl lambda/) algorithms, the AMRLS increases both the learning speed and the rate of reaching the shortest path.

A Modular System for the Classification of Time Series Data

While the field of classification is witnessing excellent achievement in recent years, not much attention is given to methods that deal with the time series data. In this paper, we propose a modular system for the classification of time series data. The proposed approach explores the diversity through various input representation techniques, each of which focuses on a certain aspect of the temporal patterns. The temporal patterns are identified by aggregation of the decisions of multiple classifiers trained through different representations of the input data. Several time series data sets are employed to examine the validity of the proposed approach. The results obtained from our experiments show that the performance of the proposed approach is effective as well as robust.

Type-2 fuzzy adaptive sliding mode control of hypersonic flight

This paper proposes a type-2 fuzzy adaptive sliding mode control scheme for tracking control of hypersonic aircraft with uncertainties. This method uses full-state feedback to linearize the nonlinear model of hypersonic aircraft. Combining the interval type-2 fuzzy approach and adaptive sliding mode control keeps the system stable in the existence of uncertain parameters. For rapid stabilization of the system, the adaptive laws are designed using a direct constructive Lyapunov analysis together with a well-established type-2 fuzzy logic control. Simulation test results indicate that the proposed control scheme provides enhancement of robustness to parametric uncertainty and improvement in tracking performance of the hypersonic aircraft.