Showing papers on "Artificial immune system published in 2017"

Applications of artificial immune systems to computer security

Abstract: For the last two decades, artificial immune systems have been studied in various fields of knowledge. They were shown to be particularly effective tools at detecting anomalous behavior in the security domain of computer systems. This article introduces the principles of artificial immune systems and surveys several works applying such systems to computer security problems. The works herein discussed are summarized and open issues are pointed out afterwards, elaborating on a novel applicability of these systems to cloud computing environments.

On the runtime analysis of the opt-IA artificial immune system

Abstract: We present a time complexity analysis of the Opt-IA artificial immune system (AIS). We first highlight the power and limitations of its distinguishing operators (i.e., hypermutations with mutation potential and ageing) by analysing them in isolation. Recent work has shown that ageing combined with local mutations can help escape local optima on a dynamic optimisation benchmark function. We generalise this result by rigorously proving that ageing leads to considerable speed-ups (compared to evolutionary algorithms (EAs)) on the standard Cliff benchmark function both when using local and global mutations. Unless the stop at first constructive mutation (FCM) mechanism is applied, we show that hypermutations require exponential expected runtime to optimise any function with a polynomial number of optima. If instead FCM is used, the expected runtime is at most a linear factor larger than the upper bound achieved for any random local search algorithm using the artificial fitness levels method. Nevertheless, we prove that algorithms using hypermutations can be considerably faster than EAs at escaping local optima. An analysis of the complete Opt-IA reveals that it is efficient on the previously considered functions and highlights problems where the use of the full algorithm is crucial.

Artificial Immune System With Local Feature Selection for Short-Term Load Forecasting

Abstract: In this paper, a new forecasting model based on artificial immune system (AIS) is proposed. The model is used for short-term electrical load forecasting as an example of forecasting time series with multiple seasonal cycles. Artificial immune system learns to recognize antigens (AGs) representing two fragments of the time series: 1) fragment preceding the forecast (input vector) and 2) forecasted fragment (output vector). Antibodies as recognition units recognize AGs by selected features of input vectors and learn output vectors. In the test procedure, new AG with only input vector is recognized by some antibodies (ABs). Its output vector is reconstructed from activated ABs. The unique feature of the proposed AIS is the embedded property of local feature selection. Each AB learns in the clonal selection process its optimal subset of features (a paratope) to improve its recognition and prediction abilities. In the simulation studies the proposed model was tested on real power system data and compared with other AIS-based forecasting models as well as neural networks, autoregressive integrated moving average, and exponential smoothing. The obtained results confirm good performance of the proposed model.

Optimizing an artificial immune system algorithm in support of flow-Based internet traffic classification

Abstract: Display Omitted In this research we expanded on previous research by implementing several optimizations on the algorithm.We give the asymptotic complexity of the optimized algorithm and draw a bound on the generalization error.We tried to improve its classification performance by applying several different distance formulas.We show how the changes do not functionally change the algorithm, while making its execution 5060% faster.We show the accuracy of the Euclidian distance is improved by the Manhattan distancegiving 12% higher accuracy. The problem of classifying traffic flows in networks has become more and more important in recent times, and much research has been dedicated to it. In recent years, there has been a lot of interest in classifying traffic flows by application, based on the statistical features of each flow. Information about the applications that are being used on a network is very useful in network design, accounting, management, and security. In our previous work we proposed a classification algorithm for Internet traffic flow classification based on Artificial Immune Systems (AIS). We also applied the algorithm on an available data set, and found that the algorithm performed as well as other algorithms, and was insensitive to input parameters, which makes it valuable for embedded systems. It is also very simple to implement, and generalizes well from small training data sets. In this research, we expanded on the previous research by introducing several optimizations in the training and classification phases of the algorithm. We improved the design of the original algorithm in order to make it more predictable. We also give the asymptotic complexity of the optimized algorithm as well as draw a bound on the generalization error of the algorithm. Lastly, we also experimented with several different distance formulas to improve the classification performance. In this paper we have shown how the changes and optimizations applied to the original algorithm do not functionally change the original algorithm, while making its execution 5060% faster. We also show that the classification accuracy of the Euclidian distance is superseded by the Manhattan distance for this application, giving 12% higher accuracy, making the accuracy of the algorithm comparable to that of a Nave Bayes classifier in previous research that uses the same data set.

Hybridized genetic-immune based strategy to obtain optimal feasible assembly sequences

Abstract: Article history: Received October 2 2016 Received in Revised Format October 28 2016 Accepted December 2 2016 Available online December 2 2016 An appropriate sequence of assembly operations increases the productivity and enhances product quality there by decrease the overall cost and manufacturing lead time. Achieving such assembly sequence is a complex combinatorial optimization problem with huge search space and multiple assembly qualifying criteria. The purpose of the current research work is to develop an intelligent strategy to obtain an optimal assembly sequence subjected to the assembly predicates. This paper presents a novel hybrid artificial intelligent technique, which executes Artificial Immune System (AIS) in combination with the Genetic Algorithm (GA) to find out an optimal feasible assembly sequence from the possible assembly sequence. Two immune models are introduced in the current research work: (1) Bone marrow model for generating possible assembly sequence and reduce the system redundancy and (2) Negative selection model for obtaining feasible assembly sequence. Later, these two models are integrated with GA in order to obtain an optimal assembly sequence. The proposed AIS-GA algorithm aims at enhancing the performance of AIS by incorporating GA as a local search strategy to achieve global optimum solution for assemblies with large number of parts. The proposed algorithm is implemented on a mechanical assembly composed of eleven parts joined by several connectors. The method is found to be successful in achieving global optimum solution with less computational time compared to traditional artificial intelligent techniques. © 2017 Growing Science Ltd. All rights reserved

Proposed Sandia frequency shift for anti-islanding detection method based on artificial immune system

Abstract: Sandia frequency shift (SFS) is one of the active anti-islanding detection methods that depend on frequency drift to detect an islanding condition for inverter-based distributed generation. The non-detection zone (NDZ) of the SFS method depends to a great extent on its parameters. Improper adjusting of these parameters may result in failure of the method. This paper presents a proposed artificial immune system (AIS)-based technique to obtain optimal parameters of SFS anti-islanding detection method. The immune system is highly distributed, highly adaptive, and self-organizing in nature, maintains a memory of past encounters, and has the ability to continually learn about new encounters. The proposed method generates less total harmonic distortion (THD) than the conventional SFS, which results in faster island detection and better non-detection zone. The performance of the proposed method is derived analytically and simulated using Matlab/Simulink. Two case studies are used to verify the proposed method. The first case includes a photovoltaic (PV) connected to grid and the second includes a wind turbine connected to grid. The deduced optimized parameter setting helps to achieve the “non-islanding inverter” as well as least potential adverse impact on power quality.

Optimal Siting of Distributed Generators in a Distribution Network using Artificial Immune System

Abstract: Distributed generation (DG) sources are being installed in distribution networks worldwide due to their numerous advantages over the conventional sources which include operational and economical benefits. Random placement of DG sources in a distribution network will result in adverse effects such as increased power loss, loss of voltage stability and reliability, increase in operational costs, power quality issues etc. This paper presents a methodology to obtain the optimal location for the placement of multiple DG sources in a distribution network from a technical perspective. Optimal location is obtained by evaluating a global multi-objective technical index (MOTI) using a weighted sum method. Clonal selection based artificial immune system (AIS) is used along with optimal power flow (OPF) technique to obtain the solution. The proposed method is executed on a standard IEEE-33 bus radial distribution system. The results justify the choice of AIS and the use of MOTI in optimal siting of DG sources which improves the distribution system efficiency to a great extent in terms of reduced real and reactive power losses, improved voltage profile and voltage stability. Solutions obtained using AIS are compared with Genetic algorithm (GA) and Particle Swarm optimization (PSO) solutions for the same objective function.

Network intrusion detection through artificial immune system

Abstract: Intrusion Detection Systems (IDS) are security technologies In this regard, Artificial Immune System (AIS) which provides distributed detection through its lymphocytes is an appealing approach for designing IDSs In this paper, an AIS based intrusion detection is proposed in which two sets of antibodies — positive and negative — are generated for normal and attack samples respectively using negative selection and positive selection theories in primary detectors' generation Standard Particle Swarm Optimization (PSO) is employed for training immature detectors to improve detection rate Moreover, antibodies' radiuses is dynamically determined through generation and training algorithms Simulation shows that the proposed algorithm achieved 991% true positive rate while the false positive rate is 19%

Detection and classification of structural changes using artificial immune systems and fuzzy clustering

Abstract: Among all the elements that are integrated into a structural health monitoring (SHM) system, methods or strategies for damage detection and classification are nowadays playing a key role in enhancing the operational reliability of critical structures in several industrial sectors. The main contribution of this paper is the application of a new methodology to detect and classify structural changes. The methodology is based on: 1) an artificial immune system (AIS) and the notion of affinity is used for the sake of damage detection; 2) a fuzzy c-means algorithm is used for damage classification. One of the advantages of the proposed methodology is the fact that to develop and validate the strategy, a model is not needed. Additionally, and in contrast to standard Lamb waves-based methods, there is no need to directly analyse the complex time-domain traces containing overlapping, multimodal and frequency dispersive wave propagation that distorts the signals and difficult the analysis. The proposed methodology is applied to data coming from two sections of an aircraft skin panel. The results indicate that the proposed methodology is able to accurately detect damage as well as classify those damages.

Artificial immune systems applied to fault detection and isolation

Abstract: Graphical abstractDisplay Omitted HighlightsWe review some approaches inspired on infectious nonself and danger models.Novel immune-inspired algorithms tend to rely more on expert knowledge.Reviewed approaches can be applied to a fault detection benchmark.Experimental results show fault detection with no false alarms.A fault isolation mechanism can be provided from class ambiguity measurements. This paper aims to document the application of a new generation of artificial immune systems (AIS) in fault detection and isolation problems. These kind of algorithms are able to explore normal and anomalous behavior evidences, however, they may often require a more explicit prior knowledge provided by experts, usually difficult to obtain in some practical cases. Thus, many immune inspired approaches applied to fault detection and isolation (FDI) in the literature are based on negative selection algorithms. Considering these points, this work presents a review on three AIS approaches. Once reviewed and contextualized, the evaluated techniques are properly adjusted considering their main parameters and ways of processing data, and then, applied to a case study of fault detection and isolation in order to provide a performance analysis of these techniques, according to their applicability to these problems.

Towards accurate intrusion detection based on improved clonal selection algorithm

Abstract: Artificial immune system constructs a dynamic and adaptive information defense system through a function similar to the biological immune system. In order to resist the external invasion of useless and harmful information and ensure the effectiveness and the harmlessness of received information. Due to the low accuracy and the high false positive rate of the existing clonal selection algorithms applied to intrusion detection, in this paper, we propose an improved clonal selection algorithm. The improved method detects the intrusion behavior by selecting the best individual overall and cloning them. Experimental results show that the improved algorithm achieves very good performance when applied to intrusion detection. And it is shown that the algorithm is better than BP neural network with its 99.5 % accuracy and 0.1 % false positive rate.

Symbiotic Organisms Search Technique for SVC Installation in Voltage Control

Abstract: Increasing demand experienced by electric utilities in many parts of the world involving developing country is a normal phenomenon. This can be due to the urbanization process of a system network, which may lead to possible voltage decay at the receiving buses if no proper offline study is conducted. Unplanned load increment can push the system to operate closes to its instability point. Various compensation schemes have been popularly invented and proposed in power system operation and planning. This would require offline studies, prior to real system implementation. This paper presents the implementation of Symbiotic Organisms Search (SOS) algorithm for solving optimal static VAr compensator (SVC) installation problem in power transmission systems. In this study, SOS was employed to perform voltage control study in a transmission system under several scenarios via the SVC installation scheme. This realizes the feasibility of SOS applications in addressing the compensating scheme for the voltage control study. Minimum and maximum bound of the voltage at all buses have been considered as the inequality constraints as one of the aspects. A validation process conducted on IEEE 26-Bus RTS realizes the feasibility of SOS in performing compensation scheme without violating system stability. Results obtained from the optimization process demonstrated that the proposed SOS optimization algorithm has successfully reduced the total voltage deviation index and improve the voltage profile in the test system. Comparative studies have been performed with respect to the established evolutionary programming (EP) and artificial immune system (AIS) algorithms, resulting in good agreement and has demonstrated its superiority. Results from this study could be beneficial to the power system community in the planning and operation departments in terms of giving offline information prior to real system implementation of the corresponding power system utility.

Robust Artificial Immune System in the Hopfield network for Maximum k-Satisfiability

Abstract: Artificial Immune System (AIS) algorithm is a novel and vibrant computational paradigm, enthused by the biological immune system. Over the last few years, the artificial immune system has been sprouting to solve numerous computational and combinatorial optimization problems. In this paper, we introduce the restricted MAX-kSAT as a constraint optimization problem that can be solved by a robust computational technique. Hence, we will implement the artificial immune system algorithm incorporated with the Hopfield neural network to solve the restricted MAX-kSAT problem. The proposed paradigm will be compared with the traditional method, Brute force search algorithm integrated with Hopfield neural network. The results demonstrate that the artificial immune system integrated with Hopfield network outperforms the conventional Hopfield network in solving restricted MAX-kSAT. All in all, the result has provided a concrete evidence of the effectiveness of our proposed paradigm to be applied in other constraint optimization problem. The work presented here has many profound implications for future studies to counter the variety of satisfiability problem.

Artificial immune system based fault diagnosis in large wireless sensor network topology

Abstract: The Fault diagnosis problem in wireless sensor network (WSN) based on Artificial Immune System (AIS) is a recent technique to diagnose the fault status of sensor nodes. In fact, this allows every sensor node to achieve diagnosis. Here, an Artificial Immune System (AIS) based fault diagnosis for WSN (WAIS) algorithm has been proposed where the performance measures average diagnosis latency, detection accuracy, false alarm rate improved by 32.79%,1.76%,0.8% with respect to the existing algorithms such as dynamic distributed self diagnosis protocol (D DSDP), adaptive distributed self diagnosis protocol (A DSDP), mobile distributed self diagnosis protocol (M DSDP).

Denial of service attack detection using dendritic cell algorithm

Abstract: Denial-of-service (DoS) and distributed denial-of-service (DDoS) is one of the most popular and easy-to-implement attacks targeting online systems and networks. This paper presents a system for detecting DoS attacks in a network using the dendritic cell algorithm (DCA). The proposed system classifies incoming network traffic into either of two classes: “normal” or “DoS attack.” This paper investigates some common DoS/DDoS attacks that target communication networks, and how these attacks can be detected using the Dendritic Cell Algorithm (DCA) which is an Artificial Immune System (AIS)-based algorithm. The proposed detection system is evaluated using the popular NSL-KDD dataset. Our results show that our system is very effective in detecting DoS/DDoS attacks with very high accuracy.

Evolutionary Algorithm-Based Radial Basis Function Neural Network Training for Industrial Personal Computer Sales Forecasting

Abstract: Forecasting is one of the crucial factors in applications because it ensures the effective allocation of capacity and proper amount of inventory. Because Box-Jenkins models using linear forecasting have their constraint to predict complexity in the real world, other nonlinear approaches are developed to conquer the challenge of nonlinear forecasting. With the same goal, we are proposing a hybrid of genetic algorithm and artificial immune system HGAI algorithm with radial basis function neural network learning for function approximation and further applying it to conduct an industrial personal computer sales forecasting exercise. In addition, five well-known benchmark problems were used to evaluate the results in the experiment, and the newly proposed HGAI algorithm has returned better results than the Box-Jenkins models and other algorithms.

Dynamic network structured immune particle swarm optimisation with small-world topology

Abstract: Particle swarm optimisation (PSO) has attracted much attention and is used to wide applications in different fields in recent years because of its simple concept, easy implementation and quick convergence. However, it suffers from premature convergence since the population's diversity loses quickly. In this paper, a novel and efficient variant of PSO named DNIPSO is proposed which help the diversity of the swarm be preserved via the Newman-Watts small world network topology and the immune learning operator. Initially the topology of the population is the regular network. Then the Newman-Watts small world topology is formed gradually and the swarm evolves simultaneously. The optimisation process contains the population structure dynamics and particle immune learning two parts which mutually promoted effectively in whole population. Furthermore, the immune operator which is based on the clonal selection theory achieves a trade-off between exploration and exploitation abilities. Numerical experiments both on continuous unconstrained and constrained benchmark functions are used to test the performance of DNIPSO. Simulation results show it is effective and robust.

An immunological approach based on the negative selection algorithm for real noise classification in speech signals

Abstract: This paper presents a new approach to detect and classify background noise in speech sentences based on the negative selection algorithm and dual-tree complex wavelet transform. The energy of the complex wavelet coefficients across five wavelet scales are used as input features. Afterward, the proposed algorithm identifies whether the speech sentence is, or is not, corrupted by noise. In the affirmative case, the system returns the type of the background noise amongst the real noise types considered. Comparisons with classical supervised learning methods are carried out. Simulation results show that the artificial immune system proposed overcomes classical classifiers in accuracy and capacity of generalization. Future applications of this tool will help in the development of new speech enhancement or automatic speech recognition systems based on noise classification.

A Survey of Diversity Oriented Optimization: Problems, Indicators, and Algorithms.

Abstract: In this chapter it is discussed, how the concept of diversity plays a crucial role in contemporary (multi-objective) optimization algorithms. It is shown that diversity maintenance can have a different purpose, such as improving global convergence reliability or finding alternative solutions to a (multi-objective) optimization problem. Moreover, different algorithms are reviewed that put special emphasis on diversity maintenance, such as multicriteria evolutionary optimization algorithms, multimodal optimization, artificial immune systems, and techniques from set oriented numerics. Diversity maintenance enters in different search operators and is used for different reasons in these algorithms. Among them we highlight evolutionary, swarm-based, artificial immune system-based, and indicator-based approaches to diversity optimization. In order to understand indicator-based approaches, we will review some of the most common diversity indices that can be used to quantitatively assess diversity. Based on the discussion, ’diversity oriented optimization’ is suggested as a term encompassing optimization techniques that adress diversity maintainance as a major ingredient of the search paradigm. To bring order into all these different approaches, an ontology on diversity oriented optimization is proposed. It provides a systematic overview of the various concepts, methods, and applications and it can be extended in future work.

Immunity-Based Accommodation of Aircraft Subsystem Failures

Abstract: Purpose This paper aims to describe the design, development and flight-simulation testing of an artificial immune-system-based approach for accommodation of different aircraft sub-system failures/damages. Design/methodology/approach The approach is based on building an artificial memory, which represents self- (nominal conditions) and non-self (abnormal conditions) within the artificial immune system paradigm. Self- and non-self are structured as a set of memory cells consisting of measurement strings, over pre-defined time windows. Each string is a set of features values at each sample time of the flight. The accommodation algorithm is based on the cell in the memory that is the most similar to the in-coming measurement. Once the best match is found, control commands corresponding to this match are extracted from the memory and used for control purposes. Findings The results demonstrate the possibility of extracting pilot compensatory commands from the self/non-self structure and capability of the artificial-immune-system-based scheme to accommodate an actuator malfunction, maintain control and complete the task. Research limitations/implications This paper concentrates on investigation of the possibility of extracting compensatory pilot commands. This is a preliminary step toward a more comprehensive solution to the aircraft abnormal condition accommodation problem. Practical implications The results demonstrate the effectiveness of the proposed approach using a motion-based flight simulator for actuator and sensor failures. Originality/value This research effort is focused on investigating the use of the artificial immune system paradigm for control purposes based on a novel methodology.

Theoretical Analysis of Stochastic Search Algorithms

Abstract: Theoretical analyses of stochastic search algorithms, albeit few, have always existed since these algorithms became popular. Starting in the nineties a systematic approach to analyse the performance of stochastic search heuristics has been put in place. This quickly increasing basis of results allows, nowadays, the analysis of sophisticated algorithms such as population-based evolutionary algorithms, ant colony optimisation and artificial immune systems. Results are available concerning problems from various domains including classical combinatorial and continuous optimisation, single and multi-objective optimisation, and noisy and dynamic optimisation. This chapter introduces the mathematical techniques that are most commonly used in the runtime analysis of stochastic search heuristics. Careful attention is given to the very popular artificial fitness levels and drift analyses techniques for which several variants are presented. To aid the reader's comprehension of the presented mathematical methods, these are applied to the analysis of simple evolutionary algorithms for artificial example functions. The chapter is concluded by providing references to more complex applications and further extensions of the techniques for the obtainment of advanced results.

An artificial immunity approach to malware detection in a mobile platform

Abstract: Inspired by the human immune system, we explore the development of a new Multiple-Detector Set Artificial Immune System (mAIS) for the detection of mobile malware based on the information flows in Android apps. mAISs differ from conventional AISs in that multiple-detector sets are evolved concurrently via negative selection. Typically, the first detector set is composed of detectors that match information flows associated with malicious apps while the second detector set is composed of detectors that match the information flows associated with benign apps. The mAIS presented in this paper incorporates feature selection along with a negative selection technique known as the split detector method (SDM). This new mAIS has been compared with a variety of conventional AISs and mAISs using a dataset of information flows captured from malicious and benign Android applications. This approach achieved a 93.33% accuracy with a true positive rate of 86.67% and a false positive rate of 0.00%.

Hybrid and Cooperative Strategies Using Harmony Search and Artificial Immune Systems for Solving the Nurse Rostering Problem

Abstract: The nurse rostering problem is an important search problem that features many constraints. In a nurse rostering problem, these constraints are defined by processes such as maintaining work regulations, assigning nurse shifts, and considering nurse preferences. A number of approaches to address these constraints, such as penalty function methods, have been investigated in the literature. We propose two types of hybrid metaheuristic approaches for solving the nurse rostering problem, which are based on combining harmony search techniques and artificial immune systems to balance local and global searches and prevent slow convergence speeds and prematurity. The proposed algorithms are evaluated against a benchmarking dataset of nurse rostering problems; the results show that they identify better or best known solutions compared to those identified in other studies for most instances. The results also show that the combination of harmony search and artificial immune systems is better suited than using single metaheuristic or other hybridization methods for finding upper-bound solutions for nurse rostering problems and discrete optimization problems.

Application of artificial immune systems for the creation of IoT intrusion detection systems

Abstract: The advances made in the field of IoT in recent years implore us to take a closer look at the security challenges it presents. Due to its ubiquitous nature and high heterogeneity of the connected devices and communication protocols a novel approach must be taken. This papers aim is to make a brief review of the work done in the areas of Negative Selection and Danger Theory and to do a comparative analysis of the available solutions. Furthermore, the most prominent characteristic an artificial immune system must attain in order to conform to the unique security requirements put forward by the IoT are identified.