Frank Jiang

A Real-Time NetFlow-based Intrusion Detection System with Improved BBNN and High-Frequency Field Programmable Gate Arrays

Future large-scale complex computing environments present challenges to the real-time intrusion detection systems (IDSs). In this paper, we design a prototype with hybrid software-enabled detection engine on the basis of our improved block-based neural network (BBNN), and integrate it with a high-frequency FPGA board to form a real-time intrusion detection system. The established prototype can seamlessly feed the large-scale NetFlow data obtained from Cisco routers directly into the improved BBNN based IDS. The corresponding BBNN structure and parameter settings have been improved and experimentally tested. Experimental performance comparisons have been conducted against four major schemes of Support Vector Machine (SVM) and Naive Bayes algorithm. The results show that the improved BBNN outperforms other algorithms with respect to the classification and detection performances. The false alarm rate is successfully reduced as low as 5.14% while the genuine detection rate 99.92% is still maintained.

Quality and robustness improvement for real world industrial systems using a fuzzy particle swarm optimization

This paper presents a novel fuzzy particle swarm optimization with cross-mutated (FPSOCM) operation, where a fuzzy logic system developed based on the knowledge of swarm intelligence is proposed to determine the inertia weight for the swarm movement of particle swarm optimization (PSO) and the control parameter of a newly introduced cross-mutated operation. Hence, the inertia weight of the PSO can be adaptive with respect to the search progress. The new cross-mutated operation intends to drive the solution to escape from local optima. A suite of benchmark test functions are employed to evaluate the performance of the proposed FPSOCM. Experimental results show empirically that the FPSOCM performs better than the existing hybrid PSO methods in terms of solution quality, robustness, and convergence rate. The proposed FPSOCM is evaluated by improving the quality and robustness of two real world industrial systems namely economic load dispatch system and self-provisioning systems for communication network services. These two systems are employed to evaluate the effectiveness of the proposed FPSOCM as they are multi-optima and non-convex problems. The performance of FPSOCM is found to be significantly better than that of the existing hybrid PSO methods in a statistical sense. These results demonstrate that the proposed FPSOCM is a good candidate for solving product or service engineering problems which have multi-optima or non-convex natures.

HYBRID FUZZY LOGIC-BASED PARTICLE SWARM OPTIMIZATION FOR FLOW SHOP SCHEDULING PROBLEM

This paper, proposes a hybrid fuzzy logic-based particle swarm optimization (PSO) with cross-mutated operation method for the minimization of makespan in permutation flow shop scheduling problem. This problem is a typical non-deterministic polynomial-time (NP) hard combinatorial optimization problem. In the proposed hybrid PSO, fuzzy inference system is applied to determine the inertia weight of PSO and the control parameter of the proposed cross-mutated operation by using human knowledge. By introducing the fuzzy system, the inertia weight becomes adaptive. The cross-mutated operation effectively forces the solution to escape the local optimum. To make PSO suitable for solving flow shop scheduling problem, a sequence-order system based on the roulette wheel mechanism is proposed to convert the continuous position values of particles to job permutations. Meanwhile, a new local search technique namely swap-based local search for scheduling problem is designed and incorporated into the hybrid PSO. Finally, a suite of flow shop benchmark functions are employed to evaluate the performance of the proposed PSO for flow shop scheduling problems. Experimental results show empirically that the proposed method outperforms the existing hybrid PSO methods significantly.

Threshold-Based Image Segmentation through an Improved Particle Swarm Optimisation

Image segmentation plays a critical role in the process of object recognition in digital image processing. Multilevel threshold-based segmentation is one of the most popular image segmentation techniques. This paper proposes a new multilevel threshold-based image segmentation approach on the basis of the new particle swarm optimisation with wavelet mutation. Unlike the conventional particle swarm optimisation (PSO), our new algorithm distinguishes itself by having the following advantages: 1) Faster convergence rate; 2) Multi-dimensional data processing. The basic idea in this paper is to optimise the multilevel thresholds for the images and therefore to reach the goal of the total entropy of the image being maximized. The new algorithm leads to better optimised thresholds and produces more accurate segmentation results for images with multiple attributes. The trade-off between good search stability and cheaper computational cost is well balanced. By comparing with the Genetic Algorithm(GA) and an existing PSO-based image scheme called HCOCLPSO, the experimental results demonstrate the proposed scheme outperforms and very promising in terms of faster convergence rate, better exploration and exploitation capacities in the segmentation process with the reduced computational time.

Constrained NMF-based semi-supervised learning for social media spammer detection

Within the past few years, social media platforms such as Facebook, Twitter, and Sina Weibo, have gradually become important channels for information dissemination and communication. However, in the meantime, these platforms are prone to be potentially attacked by spammers, who usually propagate disgusted information such as phishing URLs, false news, and even pornography to other users. Despite rapid increase of social media spammers, the traditional spammer detection methods become less effective. In this paper, we present a novel semi-supervised social media spammer detection approach, making full use of the message content and user behavior as well as the social relation information. First, we adapt the original constrained NMF-based semi-supervised learning (CNMF) algorithm, nonnegative matrix factorization (NMF) by imposing a label information constrain and sparseness constrain. Second, we present a novel CNMF-based integral framework for social media spammer detection by implementing the collaborative factorization on the message content matrix and the user behavior and social relation information matrix. Moreover, we explore the iterative update rule (IUR) and optimization algorithm for the spammer detection model. In addition, its corresponding convergence is also proven. Extensive experiments are conducted on the real-world dataset from Sina Weibo, the experiment results demonstrate that our proposed model performs significantly better than the conventionally applied supervised classifiers for the spammer detection.

Intelligent fuzzy particle swarm optimization with cross-mutated operation

This paper presents a novel fuzzy particle swarm optimization with cross-mutated operation (FPSOCM), where a fuzzy logic is applied to determine the inertia weight of PSO and the control parameter of the proposed cross-mutated operation based on human knowledge. By introducing the fuzzy system, the value of the inertia weight of PSO becomes adaptive. The new cross-mutated operation effectively drives the solution to escape from local optima. To illustrate the performance of the FPSOCM, a suite of benchmark test functions are employed. Experimental results show the proposed FPSOCM method performs better than some existing hybrid PSO methods in terms of solution quality and solution reliability (standard deviation upon many trials). Moreover, an industrial application of economic load dispatch is given to show that the FPSOCM method performs statistically more significant than the existing hybrid PSO methods.

A new binary hybrid particle swarm optimization with wavelet mutation

Particle swarm optimization (PSO) is an evolutionary algorithm in which individuals, called particles, move around a multi-dimensional problem space at different directions (trajectories) and speeds (velocities) to find the best solution. A particle movement is based on its previous best result and the previous best result of the entire population. In one of PSO variants – the HPSOWM [4], a mutation process based on wavelet theory was added to the original PSO to prevent premature conclusion of the best solution. This hybrid PSO has improved solution stability and quality over the original algorithm as well as many other hybrid PSO algorithms. However, it is limited to work on a continuous problem space. In this paper, we propose Binary Hybrid Particle Swarm Optimization with Wavelet Mutation (BHPSPWM) – a reworked version of such algorithm which operates on binary-based problem space. The movement mechanisms of particles as well as the mutation process have been transformed. The new algorithm was applied in training block-based neural network (BBNN) as well as finding solutions for several mathematical functions. The results showed significant improvement over genetic algorithms.

Evolving Block-Based Neural Network and Field Programmable Gate Arrays for Host-Based Intrusion Detection System

In this paper, we design a prototype with hybrid software-enabled detection engine on the basis of an evolving block-based neural network (BBNN), and integrate it with a Field Programmable Gate Arrays (FPGA) board to enable a real-time host-based intrusion detection system (IDS). The established prototype can feed sequence of system calls obtained from a server directly into the BBNN based IDS. The structure and weights of BBNN are evolved by Genetic Algorithms. Experimental performance comparisons have been conducted against four major Support Vector Machines (SVMs) by carrying out leave-one-out cross validation. The results show that the improved BBNN outperforms other algorithms with respect to the classification and detection performances. The false alarm rate is successfully reduced as low as 2.22% while the detection rate 100% is still maintained. The running times of the proposed hardware based IDS versus other software based systems are also discussed.

Cooperative multi-target tracking in passive sensor-based networks

Multiple targets tracking is a popular application with huge potentials in many practical areas, such as military air combat and civilian surveillance. Recent years, sensor networks, comprising of a large number of cheap, portable and tiny sensors, have attracted a lot of research interests in many disciplines. Alternative forms of sensors such as camera, can provide rich and vivid observation information. They have been widely applied into the environment monitoring or object surveillance. However, these devices are usually very expensive, especially, it becomes impractical to fulfill tasks cooperatively done within a group of such high cost devices. Recent work shows that despite the low information volume provided by the passive binary-detection based sensor, a group of such sensors can work together to achieve good target tracking performance. In this paper, we investigate a passive proximity binary sensor-based multiple target tracking system which can autonomically achieve the self-organized tracking capabilities without the intervention of human operators. The localization and tracking algorithm is achieve false alarm rates, robust under low detection probabilities and sensor ambiguity localization errors. Experimental results show promising performance in adopting this application in practice.

LOARP: A Low Overhead Routing Protocol for Underwater Acoustic Sensor Networks

Underwater wireless communications among underwater sensor nodes enable a large number of scientific, environmental and military applications. For example, autonomous underwater vehicles will enable exploration of deep sea resources and gathering of scientific data for collaborative missions. In order to make underwater applications possible, real-time communication protocols among underwater devices must be enabled. Because of the high attenuation and scattering effect of radio and optical waves, respectively, these underwater devices are based on acoustic wireless technology. The unique characteristics of underwater acoustic channel - such as distance-dependent limited bandwidth and high propagation delays, require new, efficient and reliable communication protocols over multiple hops to network multiple devices which may be either static or mobile. This paper proposes a new low overhead ad hoc routing protocol designed for underwater acoustic sensor network. The protocol performs route discovery when needed in an on-demand manner. It also characterises a route maintenance phase which tries to recover a failed route. Detection of route failure can generate a lot of routing traffic. The proposed protocol tries to minimize this routing traffic by detecting failure in a more intelligent way either by monitoring network data traffic (if present) or generating lazy acknowledgements (if necessary). Reducing routing traffic minimizes the chance of packet collisions which in turn increases data packet delivery ratio. The performance of the proposed protocol is measured in terms of network throughput, packet delivery ratio, average endto-end delay and control overhead. The results are compared to those obtained using similar on-demand routing protocols. Simulation results show that the reduction of routing traffic can improve the performance of the network.