NEW HYBRID AI-SVM ALGORITHM: COMBINATION OF SUPPORT VECTOR MACHINES AND ARTIFICIAL IMMUNE NETWORKS

Support vector machines （SVMs） are combined with the artificial immune network （aiNet）, thus forming a new hybrid ai-SVM algorithm. The algorithm is used to reduce the number of samples and the training time of SVM on large datasets, aiNet is an artificial immune system （AIS） inspired method to perform the automatic data compression, extract the relevant information and retain the topology of the original sample distribution. The output of aiNet is a set of antibodies for representing the input dataset in a simplified way. Then the SVM model is built in the compressed antibody network instead of the original input data. Experimental results show that the ai-SVM algorithm is effective to reduce the computing time and simplify the SVM model, and the accuracy is not decreased.

Intrusion detection based on rough set and artificial immune

In order to increase intrusion detection rate and decrease false positive detection rate,a novel intrusion detection algorithm based on rough set and artificial immune( RSAI-IDA) is proposed.Using artificial immune in intrusion detection,anomaly actions are detected adaptively,and with rough set,effective antibodies can be obtained. A scheme,in which antibodies are partly generated randomly and others are from the artificial immune algorithm,is applied to ensure the antibodies diversity. Finally,simulations of RSAI-IDA and comparisons with other algorithms are given. The experimental results illustrate that the novel algorithm achieves more effective performances on anomaly intrusion detection,where the algorithm's time complexity decreases,the true positive detection rate increases,and the false positive detection rate is decreased.

An optimization algorithm for locomotive secondary spring load adjustment based on artificial immune

In order to control the locomotive wheel(axle) load distribution, a shimming process to adjust the locomotive secondary spring loads was heretofore developed. An immune dominance clonal selection multi-objective algorithm based on the artificial immune system was presented to further improve the performance of the optimization algorithm for locomotive secondary spring load adjustment, especially to solve the lack of control on the output shim quantity. The algorithm was designed into a two-level optimization structure according to the preferences of the problem, and the priori knowledge of the problem was used as the immune dominance. Experiments on various types of locomotives show that owing to the novel algorithm, the shim quantity is cut down by 30% 60% and the calculation time is about 90% less while the secondary spring load distribution is controlled on the same level as before. The application of this optimization algorithm can significantly improve the availability and efficiency of the secondary spring adjustment process.

Dynamic route guidance algorithm based onartificial immune system

To improve the performance of the K-shortest paths search in intelligent traffic guidance systems, this paper proposes an optimal search algorithm based on the intelligent optimization search theory and the metaphor mechanism of vertebrate immune systems. This algorithm, applied to the urban traffic network model established by the node-expanding method, can expediently realize K-shortest paths search in the urban traffic guidance systems. Because of the immune memory and global parallel search ability from artificial immune systems, K shortest paths can be found without any repeat, which indicates evidently the superiority of the algorithm to the conventional ones. Not only does it perform a better parallelism, the algorithm also prevents premature phenomenon that often occurs in genetic algorithms. Thus, it is especially suitable for real-time requirement of the traffic guidance system and other engineering optimal applications. A case study verifies the efficiency and the practicability of the algorithm aforementioned.

A Robust Damage Detection Method Developed for Offshore Jacket Platforms Using Modified Artificial Immune System Algorithm

Steel jacket-type platforms are the common kind of the offshore structures and health monitoring is an important issue in their safety assessment. In the present study, a new damage detection method is adopted for this kind of structures and inspected experimentally by use of a laboratory model. The method is investigated for developing the robust damage detection technique which is less sensitive to both measurement and analytical model uncertainties. For this purpose, incorporation of the artificial immune system with weighted attributes （AISWA） method into finite element （FE） model updating is proposed and compared with other methods for exploring its effectiveness in damage identification. Based on mimicking immune recognition, noise simulation and attributes weighting, the method offers important advantages and has high success rates. Therefore, it is proposed as a suitable method for the detection of the failures in the large civil engineering structures with complicated structural geometry, such as the considered case study.

An Improved Artificial Immune Algorithm with a Dynamic Threshold

An improved artificial immune algorithm with a dynamic threshold is presented. The calculation for the affinity function in the real-valued coding artificial immune algorithm is modified through considering the antibody＇s fitness and setting the dynamic threshold value. Numerical experiments show that compared with the genetic algorithm and the originally real-valued coding artificial immune algorithm, the improved algorithm possesses high speed of convergence and good performance for preventing premature convergence.

Feature selection for chemical process fault diagnosis by artificial immune systems

With the Industry 4.0 era coming, modern chemical plants will be gradually transformed into smart factories, which sets higher requirements for fault detection and diagnosis(FDD) to enhance operation safety intelligence. In a typical chemical process, there are hundreds of process variables. Feature selection is a key to the efficiency and effectiveness of FDD. Even though artificial immune system has advantages in adaptation and independency on a large number of fault samples, antibody library construction used to be based on experience. It is not only time consuming, but also lack of scientific foundation in fault feature selection, which may deteriorate the FDD performance of the AIS. In this paper, a fault antibody feature selection optimization(FAFSO) algorithm is proposed based on genetic algorithm to optimize the fault antibody features and the antibody libraries' thresholds simultaneously. The performance of the proposed FAFSO algorithms is illustrated through the Tennessee Eastman benchmark problem.

A decision hyper plane heuristic based artificial immune network classification algorithm

Most of the developed immune based classifiers generate antibodies randomly, which has negative effect on the classification performance. In order to guide the antibody generation effectively, a decision hyper plane heuristic based artificial immune network classification algorithm （DHPA1NC） is proposed. DHPAINC taboos the inner regions of the class domain, thus, the antibody generation is limited near the class domain boundary. Then, the antibodies are evaluated by their recognition abilities, and the antibodies of low recognition abilities are removed to avoid over-fitting. Finally, the high quality antibodies tend to be stable in the immune network. The algorithm was applied to two simulated datasets classification, and the results show that the decision hyper planes determined by the antibodies fit the class domain boundaries well. Moreover, the algorithm was applied to UCI datasets classification and emotional speech recognition, and the results show that the algorithm has good performance, which means that DHPAINC is a promising classifier.

Distance Concentration-Based Artificial Immune Algorithm

The diversity, adaptation and memory of biological immune system attract much attention of researchers. Several optimal algorithms based on immune system have also been proposed up to now. The distance concentra- tion-based artificial immune algorithm (DCAIA) is proposed to overcome defects of the classical artificial immune al- gorithm (CAIA) in this paper. Compared with genetic algorithm (GA) and CAIA, DCAIA is good for solving the prob- lem of precocity,holding the diversity of antibody, and enhancing convergence rate.

Hybrid artificial immune system and extremal optimization algorithm for permutation flowshop scheduling problem

The permutation flowshop scheduling problem （PFSP） is one of the most well-known and well-studied production scheduling problems with strong industrial background. This paper presents a new hybrid optimization algorithm which combines the strong global search ability of artificial immune system （AIS） with a strong local search ability of extremal optimization （EO） algorithm. The proposed algorithm is applied to a set of benchmark problems with a makespan criterion. Performance of the algorithm is evaluated. Comparison results indicate that this new method is an effective and competitive approach to the PFSP.

Parameter optimization of pharmacokinetics based on artificial immune network

A new method for parameter optimization of pharmacokinetics based on an artificial immune network named PKAIN is proposed. To improve local searching ability of the artificial immune network, a partition-based concurrent simplex mutation is developed. By means of evolution of network cells in the PKAIN artificial immune network, an optimal set of parameters of a given pharmacokinetic model is obtained. The Laplace transform is applied to the pharmacokinetic differential equations of remifentanil and its major metabolite, remifentanil acid. The PKAIN method is used to optimize parameters of the derived compartment models. Experimental results show that the twocompartment model is sufficient for the pharmacokinetic study of remifentanil acid for patients with mild degree of renal impairment.

Smartphone Malware Detection Model Based on Artificial Immune System

In order to solve the problem that me traditional signature-based detection technology cannot effectively detect unknown malware, we propose in this study a smartphone malware detection model （SP-MDM） based on artificial immune system, in which static malware analysis and dynamic malware analysis techniques are combined, and antigens are generated by encoding the characteristics extracted from the malware. Based on negative selection algorithm, the mature detectors are generated. By introducing clonal selection algorithm, the detectors with higher affinity are selected to undergo a proliferation and somatic hyper-mutation process, so that more excellent detector offspring can be generated. Experimental result shows that the detection model has a higher detection rate for unknown smartphone malware, and better detection performance can be achieved by increasing the clone generation.

Improved clustering method based on artificial immune

An improved clustering method based on artificial immune is proposed. To obtain the better initial solution, the initial antibody network is introduced by self organizing map （SOM） method. In the process of the clustering iteration, a series of optimization and evolution strategies are designed, such as clustering satisfaction, the threshold design of scale compression, the learning rate, the clustering monitoring points and the clustering evaluations indexes. These strategies can make the clustering thresholds be quantified and reduce the operator’s subjective factors. Thus, the local optimal and the global optimal clustering simultaneously are proposed by the synthesized function of these strategies. Finally, the experiment and the comparisons demonstrate the proposed method effectiveness.

A new artificial immune algorithm and its application for optimization problems

A new artificial immune algorithm （AIA） simulating the biological immune network system with selfadjustment function is proposed in this paper. AIA is based on the modified immune network model in which two methods of affinity measure evaluated are used, controlling the antibody diversity and the speed of convergence separately. The model proposed focuses on a systemic view of the immune system and takes into account cell-cell interactions denoted by antibody affinity. The antibody concentration defined in the immune network model is responsible directly for its activity in the immune system. The model introduces not only a term describing the network dynamics, but also proposes an independent term to simulate the dynamics of the antigen population. The antibodies＇ evolutionary processes are controlled in the algorithms by utilizing the basic properties of the immune network. Computational amount and effect is a pair of contradictions. In terms of this problem, the AIA regulating the parameters easily attains a compromise between them. At the same time, AIA can prevent premature convergence at the cost of a heavy computational amount （the iterative times）. Simulation illustrates that AIA is adapted to solve optimization problems, emphasizing muhimodal optimization.

A fuzzy logic resource allocation and memory cell pruning based artificial immune recognition system

In order to improve the resource allocation mechanism of artificial immune recognition system(AIRS) and decrease the memory cells,a fuzzy logic resource allocation and memory cell pruning based AIRS(FPAIRS) is proposed.In FPAIRS,the fuzzy logic is determined by a parameter,thus,the optimal fuzzy logics for different problems can be located through changing the parameter value.At the same time,the memory cells of low fitness scores are pruned to improve the classifier.This classifier was compared with other classifiers on six UCI datasets classification performance.The results show that the accuracies reached by FPAIRS are higher than or comparable to the accuracies of other classifiers,and the memory cells decrease when compared with the memory cells of AIRS.The results show that the algorithm is a high-performance classifier.

ARTIFICIAL IMMUNE ALGORITHM OF MULTICELLULAR GROUP AND ITS CONVERGENCE

Objective To find out more extrema simultaneously including global optimum and multiple local optima existed in multi-modal functions. Methods Germinal center is the generator and selector of high-affinity B cells, a multicellular group's artificial immune algorithm was proposed based on the germinal center reaction mechanism of natural immune systems. Main steps of the algorithm were given, including hyper-mutation, selection, memory, similarity suppression and recruitment of B cells and the convergence of it was proved. Results The algorithm has been tested to optimize various multi-modal functions, and the simulation results show that the artificial immune algorithm proposed here can find multiple extremum of these functions with lower computational cost. Conclusion The algorithm is valid and can converge on the satisfactory solution set D with probability 1 and approach to global solution and many local optimal solutions existed.

Fault-Diagnosis Method Based on Support Vector Machine and Artificial Immune for Batch Process

A new fault-diagnosis method to be used in batch processes based on multi-phase regression is presented to overcome the difficulty arising in the processes due to non-uniform sample data in each phase.Support vector machine is first used for phase identification,and for each phase,improved artificial immune network is developed to analyze and recognize fault patterns.A new cell elimination role is proposed to enhance the incremental clustering capability of the immune network.The proposed method has been applied to glutamic acid fermentation,comparison results have indicated that the proposed approach can better classify fault samples and yield higher diagnosis precision.

Anomaly Detection with Artificial Immune Network

Inspired by the immune network theory, an adaptive anomaly detection paradigm based on artificial immune network, referred as APAI, is proposed. The implementation of the paradigm includes： initially, the first is to create the initial antibody network; then, through the learning of each training antigen, the antibody network is evolved and updated by the optimal antibodies. Finally, anomaly detection process is accomplished by majority vote of the k nearest neighbor antibodies in the network. The experiments used the famous Sonar Benchmark dataset in our study, which is taken from the UCI machine learning database. The obtained detection accuracy of APAI was 97.7%, which was very promising with regard to the other classification applications in the literature for this problem. In addition to its nonlinear classification properties, APAI possesses biological immune network properties such as clonal selection, immune network, and immune memory, which can be applied to pattern recognition, classification, and etc.

A Review of Artificial Immune System Based Security Frameworks for MANET

Mobile ad hoc networks (MANETs) are collections of wireless mobile devices that form a communication network with restricted broadcast range, limited resources and without fixed infrastructure. Routing is a critical function in multi-hop MANETs. At the same time, security in MANETs—especially routing security—presents a number of new and interesting challenges. Communication is achieved by relaying data along routes that are dynamically discovered and maintained through collaboration between the nodes. Advances in the field of artificial immune systems provide an opportunity to improve MANET security and performance. Artificial immune systems mimic the functionality of the human immune system wherein there is clear distinction between self and non self and this delineation is important in a MANET where there is no centralized management. The high level of protection provided to the human body by an evolved immune system can be applied as a security feature in MANET. The current security techniques proposed for MANET have varying degrees of success due to the dynamic nature of a MANET. This paper will review different strategies for the application of artificial immune systems to MANETs.

Combining Artificial Immune System and Clustering Analysis: A Stock Market Anomaly Detection Model

Artificial intelligence research in the stock market sector has been heavily geared towards stock price prediction rather than stock price manipulation. As online trading systems have increased the amount of high volume and re-al-time data transactions, the stock market has increased vulnerability to at-tacks. This paper aims to detect these attacks based on normal trade behavior using an Artificial Immune System (AIS) approach combined with one of four clustering algorithms. The AIS approach is inspired by its proven ability to handle time-series data and its ability to detect abnormal behavior while only being trained on regular trade behavior. These two main points are essential as the models need to adapt over time to adjust to normal trade behavior as it evolves, and due to confidentiality and data restrictions, real-world manipula-tions are not available for training. This paper discovers a competitive alterna-tive to the leading approach and investigates the effects of combining AIS with clustering algorithms;Kernel Density Estimation, Self-Organized Maps, Densi-ty-Based Spatial Clustering of Applications with Noise and Spectral clustering. The best performing solution achieves leading performance using common clustering metrics, including Area Under the Curve, False Alarm Rate, False Negative Rate, and Computation Time.