Showing papers on "Artificial immune system published in 2018"

Computational Intelligence: An Introduction

Abstract: Computational Intelligence: An Introduction, Second Edition offers an in-depth exploration into the adaptive mechanisms that enable intelligent behaviour in complex and changing environments. The main focus of this text is centred on the computational modelling of biological and natural intelligent systems, encompassing swarm intelligence, fuzzy systems, artificial neutral networks, artificial immune systems and evolutionary computation. Engelbrecht provides readers with a wide knowledge of Computational Intelligence (CI) paradigms and algorithms; inviting readers to implement and problem solve real-world, complex problems within the CI development framework. This implementation framework will enable readers to tackle new problems without any difficulty through a single Java class as part of the CI library. Key features of this second edition include: A tutorial, hands-on based presentation of the material. State-of-the-art coverage of the most recent developments in computational intelligence with more elaborate discussions on intelligence and artificial intelligence (AI). New discussion of Darwinian evolution versus Lamarckian evolution, also including swarm robotics, hybrid systems and artificial immune systems. A section on how to perform empirical studies; topics including statistical analysis of stochastic algorithms, and an open source library of CI algorithms. Tables, illustrations, graphs, examples, assignments, Java code implementing the algorithms, and a complete CI implementation and experimental framework. Computational Intelligence: An Introduction, Second Edition is essential reading for third and fourth year undergraduate and postgraduate students studying CI. The first edition has been prescribed by a number of overseas universities and is thus a valuable teaching tool. In addition, it will also be a useful resource for researchers in Computational Intelligence and Artificial Intelligence, as well as engineers, statisticians, operational researchers, and bioinformaticians with an interest in applying AI or CI to solve problems in their domains. Check out http://www.ci.cs.up.ac.za for examples, assignments and Java code implementing the algorithms.

Fundamentals Of Natural Computing: Basic Concepts, Algorithms, And Applications

Abstract: Introduction A Small Sample of Ideas The Philosophy of Natural Computing The Three Branches: A Brief Overview When to Use Natural Computing Approaches Conceptualization General Concepts PART I - COMPUTING INSPIRED BY NATURE Evolutionary Computing Problem Solving as a Search Task Hill Climbing and Simulated Annealing Evolutionary Biology Evolutionary Computing The Other Main Evolutionary Algorithms From Evolutionary Biology to Computing Scope of Evolutionary Computing Neurocomputing The Nervous System Artificial Neural Networks Typical ANNS and Learning Algorithms From Natural to Artificial Neural Networks Scope of Neurocomputing Swarm Intelligence Ant Colonies Swarm Robotics Social Adaptation of Knowledge Immunocomputing The Immune System Artificial Immune Systems Bone Marrow Models Negative Selection Algorithms Clonal Selection and Affinity Maturation Artificial Immune Networks From Natural to Artificial Immune Systems Scope of Artificial Immune Systems PART II - SIMULATION AND EMULATION OF NATURAL PHENOMENA IN COMPUTERS Fractal Geometry of Nature The Fractal Geometry of Nature Cellular Automata L-Systems Iterated Function Systems Fractional Brownian Motion Particle Systems Evolving the Geometry of Nature From Natural to Fractal Geometry Artificial Life Concepts and Features of Artificial Life Systems Examples of Artificial Life Projects Scope of Artificial Life From Artificial Life to Life-As-We-Know-It PART III - COMPUTING WITH NATURAL MATERIALS DNA Computing Basic Concepts from Molecular Biology Filtering Models Formal Models: A Brief Description Universal DNA Computers Scope of DNA Computing From Classical to DNA Computing Quantum Computing Basic Concepts from Quantum Theory Principles from Quantum Mechanics Quantum Information Universal Quantum Computers Quantum Algorithms Physical Realizations of Quantum Computers: A Brief Description Scope of Quantum Computing From Classical to Quantum Computing Afterwords New Prospects The Growth of Natural Computing Some Lessons from Natural Computing Artificial Intelligence and Natural Computing Visions Appendix A: Glossary of Terms Appendix B: Theoretical Background Linear Algebra Statistics Theory of Computation and Complexity Other Concepts Bibliography Appendix C: A Quick Guide to the Literature Introduction Conceptualization Evolutionary Computing Neurocomputing Swarm Intelligence Immunocomputing Fractal Geometry of Nature Artificial Life DNA Computing Quantum Computing Index *All Chapters contain an Introduction, Summaries, Discussions, Exercises, and References

Adaptive artificial immune networks for mitigating DoS flooding attacks

Abstract: Denial of service attacks pose a threat in constant growth. This is mainly due to their tendency to gain in sophistication, ease of implementation, obfuscation and the recent improvements in occultation of fingerprints. On the other hand, progress towards self-organizing networks, and the different techniques involved in their development, such as software-defined networking, network-function virtualization, artificial intelligence or cloud computing, facilitates the design of new defensive strategies, more complete, consistent and able to adapt the defensive deployment to the current status of the network. In order to contribute to their development, in this paper, the use of artificial immune systems to mitigate denial of service attacks is proposed. The approach is based on building networks of distributed sensors suited to the requirements of the monitored environment. These components are capable of identifying threats and reacting according to the behavior of the biological defense mechanisms in human beings. It is accomplished by emulating the different immune reactions, the establishment of quarantine areas and the construction of immune memory. For their assessment, experiments with public domain datasets (KDD’99, CAIDA’07 and CAIDA’08) and simulations on various network configurations based on traffic samples gathered by the University Complutense of Madrid and flooding attacks generated by the tool DDoSIM were performed.

A Multi-Level Intrusion Detection System for Wireless Sensor Networks Based on Immune Theory

Abstract: The human body has been, and will continue to be, a source of inspiration for researchers across various disciplines owing to its robustness and myriad of functions. While some of these advancements include the attempt to replicate the entire body to create an artificial self, some tend to use a few characteristics and theories and build upon an artificial subsystem. In this paper, an effort is made to secure a wireless sensor network (WSN) using an immune theory technique called Danger Theory. In other words, a multi-level intrusion detection system (IDS) is designed based on the functions of various immune cells. This is realized by monitoring WSN parameters, such as energy, volume of data and frequency of data transfer and developing an output based on their weights and concentrations which is a suitable basis for IDS design in WSNs.

Survey on evolutionary computation methods for cybersecurity of mobile ad hoc networks

Abstract: In this paper, a comprehensive survey of evolutionary computation (EC) methods for cybersecurity of mobile ad hoc networks (MANETs) is presented. Typically, EC methods are named based on the natural processes inspiring them, such as swarm intelligence (e.g., ant colony optimization, artificial bee colony, and particle swarm optimization), evolutionary algorithms (e.g., genetic algorithms, genetic programming, grammatical evolution, and differential evolution), artificial immune systems, and evolutionary games analyzing strategic interactions among different population types. We introduce these methods with their typical applications, and commonly used algorithms to improve cybersecurity within the scope of MANETs. Ongoing and speedy topology changes, multi-hop communication, non-hierarchical organization, and power and computational limitations are among the intrinsic characteristics of MANETs causing cybersecurity vulnerabilities. We describe basic defense mechanisms in MANETs for vulnerability detection, attack deterrence, prevention and recovery, and risk mitigation. We classify principal applications of EC as intrusion detection, trust management, and cryptography in cybersecurity systems to counter measure adversarial activities.

Fast Artificial Immune Systems

Abstract: Various studies have shown that characteristic Artificial Immune System (AIS) operators such as hypermutations and ageing can be very efficient at escaping local optima of multimodal optimisation problems. However, this efficiency comes at the expense of considerably slower runtimes during the exploitation phase compared to standard evolutionary algorithms. We propose modifications to the traditional ‘hypermutations with mutation potential’ (HMP) that allow them to be efficient at exploitation as well as maintaining their effective explorative characteristics. Rather than deterministically evaluating fitness after each bit-flip of a hypermutation, we sample the fitness function stochastically with a ‘parabolic’ distribution which allows the ‘stop at first constructive mutation’ (FCM) variant of HMP to reduce the linear amount of wasted function evaluations when no improvement is found to a constant. By returning the best sampled solution during the hypermutation, rather than the first constructive mutation, we then turn the extremely inefficient HMP operator without FCM, into a very effective operator for the standard Opt-IA AIS using hypermutation, cloning and ageing. We rigorously prove the effectiveness of the two proposed operators by analysing them on all problems where the performance of HPM is rigorously understood in the literature.

An Artificial Immune System for Offline Isolated Handwritten Arabic Character Recognition

Abstract: Character recognition plays an important role in the modern world. In recent years, character recognition systems for different languages has gain importance. The recognition of Arabic writing is still an important challenge due to its cursive nature and great topological variability. The Artificial Immune System is a supervised learning technique that embodies the concepts of natural immunity to cope with complex classification problems. The objective of this research is to investigate the applicability of an Artificial Immune System in Offline Isolated Handwritten Arabic Characters. The developed system is composed of three main modules: preprocessing, feature extraction and recognition. The system was trained and tested with ten-fold cross-validation technique on an original realistic database that we built from the well-known IFN/ENIT benchmark. Parameter tuning was performed with a grid-search algorithm with leave-one-out cross-validation. The obtained results of the proposed system are promising with a classification rate of 93.25% and often outperform most well-known classifiers from Scikit Learn Library.

A botnet detection approach based on the clonal selection algorithm

Abstract: The paper presents a new technique for the botnets' detection in the corporate area networks. It is based on the usage of the algorithms of the artificial immune systems. Proposed approach is able to distinguish benign network traffic from malicious one using the clonal selection algorithm taking into account the features of the botnet's presence in the network. An approach present the main improvements of the BotGRABBER system. It is able to detect the IRC, HTTP, DNS and P2P botnets.

An Artificial Immune System based Method for Defense against Wormhole Attack in Mobile Adhoc Networks

Abstract: Mobile ad hoc networks (MANETs) are structure-less networks in which the mobile nodes are communicate wirelessly with each other’s. This wireless channel makes the MANETs vulnerable against different types of attacks. Wormhole is one of these attacks, according to which, two active attackers create a virtual private communication tunnel; reduce message normal stream and pretend two non-neighbored nodes as neighbors. In this way, the path between these two nodes is pretended as the shortest possible route between the source and the destination. Thus, all data packets passing through this route can be eliminated by these attacker nodes. This paper inspires from human immune system to design a defense mechanism against wormhole attack, called WAAIS (Wormhole Attack Artificial Immune System). In this proposed mapping, all unsecure routes, are considered as antigen. These unsecure routes are recognized by some rules, which are considered as antibody. The simulation results show that WAAIS outperforms WormPlanar and AODV in terms of packet delivery rate, average end-to-end delay and drop packets rate.

Weak thruster fault detection for autonomous underwater vehicle based on artificial immune and signal pre-processing

Abstract: This article investigates weak thruster fault detection problem for autonomous underwater vehicle subject to the external disturbances. A weak thruster fault detection method is developed based on ...

An Artificial Immune Based Approach for Detection and Isolation Misbehavior Attacks in Wireless Networks

Abstract: MANETs (Mobile Ad-hoc Networks) is a temporal network, which is managed by autonomous nodes, which have the ability to communicate with each other without having fixed network infrastructure or any central base station. Due to some reasons such as dynamic changes of the network topology, trusting the nodes to each other, lack of fixed substructure for the analysis of nodes behaviors and loss of specific offensive lines, this type of networks is not supportive against malicious nodes attacks. One of these attacks is black hole attack. In this attack, the malicious nodes absorb data packets and destroy them. Thus, it is essential to present an algorithm against the black hole attacks. This paper proposed a new approach, which improvement the security of DSR routing protocol to encounter the black hole attacks. This schema tries to identify malicious nodes according to nodes behaviors in a MANETs and isolate them from routing. The proposed protocol, called AIS-DSR (Artificial Immune System DSR) employ AIS (Artificial Immune System) to defend against black hole attacks. AIS-DSR is evaluated through extensive simulations in the ns-2 environment. The results show that AIS-DSR outperforms other existing solutions in terms of throughput, end-to-end delay, packets loss ratio and packets drop ratio.

Artificial Immune System-Negative Selection Classification Algorithm (NSCA) for Four Class Electroencephalogram (EEG) Signals.

Abstract: Artificial immune systems (AIS) are intelligent algorithms derived from the principles inspired by the human immune system. In this study, electroencephalography (EEG) signals for four distinct motor movements of human limbs are detected and classified using a negative selection classification algorithm (NSCA). For this study, a widely studied open source EEG signal database (BCI IV-Graz dataset 2a, comprising nine subjects) has been used. Mel frequency cepstral coefficients (MFCCs) are extracted as selected features from recorded EEG signals. Dimensionality reduction of data is carried out by applying two hidden layered stacked auto-encoder. Genetic algorithm (GA) optimized detectors (artificial lymphocytes) are trained using negative selection algorithm (NSA) for detection and classification of four motor movements. The trained detectors consist of four sets of detectors, each set is trained for detection and classification of one of the four movements from the other three movements. The optimized radius of detector is small enough not to mis-detect the sample. Euclidean distance of each detector with every training dataset sample is taken and compared with the optimized radius of the detector as a nonself detector. Our proposed approach achieved a mean classification accuracy of 86.39% for limb movements over nine subjects with a maximum individual subject classification accuracy of 97.5% for subject number eight.

Damage detection of truss structures by hybrid immune system and teaching–learning-based optimization

Abstract: One of the challenging tasks in structural optimization is locating and evaluating partial damages that have occurred in a system of finite elements. It may be assessed by an inverse problem of assuming stiffness degradation in some elements and comparing the resulting frequencies with those of true/measured values on the damaged structure. The present study formulates this problem as an optimization task and concentrates on teaching–learning-based optimization for its solution. The algorithm is further improved with some concepts of Artificial Immune System to provide better search refinement. Performance of the proposed hybrid method is then evaluated through numerical tests on a number of truss structures as literature benchmarks. The results exhibit superior damage detection capability by the proposed framework, when the vaccination and receptor editing operators are applied within the base algorithm.

Detecting RTL Trojans using Artificial Immune Systems and High Level Behavior Classification

Abstract: Security assurance in a computer system can be viewed as distinguishing between self and non-self. Artificial Immune Systems (AIS) are a class of machine learning (ML) techniques inspired by the behavior of innate biological immune systems, which have evolved to accurately classify self-behavior from non-self-behavior. This work aims to leverage AIS-based ML techniques for identifying certain behavioral traits in high level hardware descriptions, including unsafe or undesirable behaviors, whether such behavior exists due to human error during development, or due to intentional, malicious circuit modifications, known as hardware Trojans, without the need for a golden reference model. We explore the use of Negative Selection and Clonal Selection, which have historically been applied to malware detection on software binaries, to detect potentially unsafe or malicious behavior in hardware. We present a software tool which analyzes Trojan-inserted benchmarks, extracts their control and data-flow graphs (CDFGs), and uses this to train an AIS behavior model, against which new hardware descriptions may be tested. The proposed model is capable of detecting the specified (Trojan or Trojan-like) behavior with an accuracy of ~85% and an average false negative rate of 12.6% for Negative Selection and 12.8% for Clonal Selection.

Fast Artificial Immune Systems

Abstract: Various studies have shown that characteristic Artificial Immune System (AIS) operators such as hypermutations and ageing can be very efficient at escaping local optima of multimodal optimisation problems. However, this efficiency comes at the expense of considerably slower runtimes during the exploitation phase compared to standard evolutionary algorithms. We propose modifications to the traditional `hypermutations with mutation potential' (HMP) that allow them to be efficient at exploitation as well as maintaining their effective explorative characteristics. Rather than deterministically evaluating fitness after each bitflip of a hypermutation, we sample the fitness function stochastically with a `parabolic' distribution which allows the `stop at first constructive mutation' (FCM) variant of HMP to reduce the linear amount of wasted function evaluations when no improvement is found to a constant. By returning the best sampled solution during the hypermutation, rather than the first constructive mutation, we then turn the extremely inefficient HMP operator without FCM, into a very effective operator for the standard Opt-IA AIS using hypermutation, cloning and ageing. We rigorously prove the effectiveness of the two proposed operators by analysing them on all problems where the performance of HPM is rigorously understood in the literature. %

Applying Artificial Immune System for Intrusion Detection

Abstract: This paper investigates the approaches of using an analogy of the Human Immune System (HIS) to create an Artificial Immune System (AIS) based Intrusion Detection System (IDS). The two most popular AIS generating algorithms, Negative and Clonal Selection were explored and tested on the NSL-KDD dataset with different sets of features and different numbers of detectors. The experiments show that the Negative Selection Algorithm (NSA) and the Clonal Selection Algorithm (CSA) show a severe scaling issue when handling real network traffic.

Quantum-Inspired Immune Clonal Algorithm for solving large-scale capacitated arc routing problems

Abstract: In this paper, we present an approach to Large-Scale CARP called Quantum-Inspired Immune Clonal Algorithm (QICA-CARP). This algorithm combines the feature of artificial immune system and quantum computation ground on the qubit and the quantum superposition. We call an antibody of population quantum bit encoding, in QICA-CARP. For this encoding, to control the population with a high probability evolution towards a good schema we use the information on the current optimal antibody. The mutation strategy of quantum rotation gate accelerates the convergence of the original clone operator. Moreover, quantum crossover operator enhances the exchange of information and increases the diversity of the population. Furthermore, it avoids falling into local optimum. We also use the repair operator to amend the infeasible solutions to ensure the diversity of solutions. This makes QICA-CARP approximating the optimal solution. We demonstrate the effectiveness of our approach by a set of experiments and by Comparing the results of our approach with ones obtained with the RDG-MAENS and RAM using different test sets. Experimental results show that QICA-CARP outperforms other algorithms in terms of convergence rate and the quality of the obtained solutions. Especially, QICA-CARP converges to a better lower bound at a faster rate illustrating that it is suitable for solving large-scale CARP.

Towards the development of robot immune system: A combined approach involving innate immune cells and T-lymphocytes.

Abstract: Mobile robots in uncertain and unstructuredenvironments frequently encounter faults. Therefore, an effective fault detection and recovery mechanism is required. One can possibly investigate natural systems to seek inspiration to develop systems that can handle such faults. Authors, in this pursuit, have explored the possibility of designing an artificial immune system, called Robot Immune System (RIS), to maintain a robot’s internal health-equilibrium. This contrasts with existing approaches in which specific robotic tasks are performed instead of developing a self-healing robot. In this respect, a fault detection and recovery methodology based on innate and adaptive immune functions has been successfully designed and developed. The immuno-inspired methodology is applied to a simulated robot using Robot Operating System and Virtual Robot Experimentation Platform. Through extensive simulations in increasingly difficult scenarios, the RIS has proven successful in autonomously detecting the abnormal behaviors, performing the recovery actions, and maintaining the homeostasis in the robot. In addition to being multi-tiered, the developed RIS is also a non-deterministic and population-based system.

Spam Filtering in Social Networks Using Regularized Deep Neural Networks with Ensemble Learning

Abstract: Spam filtering in social networks is increasingly important owing to the rapid growth of social network user base. Sophisticated spam filters must be developed to deal with this complex problem. Traditional machine learning approaches such as neural networks, support vector machine and Naive Bayes classifiers are not effective enough to process and utilize complex features present in high-dimensional data on social network spam. To overcome this problem, here we propose a novel approach to social network spam filtering. The approach uses ensemble learning techniques with regularized deep neural networks as base learners. We demonstrate that this approach is effective for social network spam filtering on a benchmark dataset in terms of accuracy and area under ROC. In addition, solid performance is achieved in terms of false negative and false positive rates. We also show that the proposed approach outperforms other popular algorithms used in spam filtering, such as decision trees, Naive Bayes, artificial immune systems, support vector machines, etc.

Network Intrusion Detection System Using Artificial Immune System (AIS)

Abstract: The number of computer network attacks are increasing due to the global use of Internet in our daily life This has led to the increased risks of data stealing, hacking, privacy intrusion and others The research on intrusion detection system (IDS) has gained significant attention due capacity In this paper, we propose the use of Artificial Immune System (AIS) as the tool to detect the occurrence of intrusion in a computer network In a computer network connection, many features are involved such as duration, type of protocol and type of service among others The combination of different connection features can be grouped by using classification method Based on this classification, IDS can be utilized to distinguish between valid and attack connections Data from KDD Cup 99 competition were utilized in this study to determine the type of connection The results obtained indicate that the proposed method is effective in identifying attack connections with a high success rate

Artificial Immune Algorithm for Subtask Industrial Robot Scheduling in Cloud Manufacturing

Abstract: The current generation of manufacturing industry requires an intelligent scheduling model to achieve an effective utilization of distributed manufacturing resources, which motivated us to work on an Artificial Immune Algorithm for subtask robot scheduling in cloud manufacturing. This scheduling model enables a collaborative work between the industrial robots in different manufacturing centers. This paper discussed two optimizing objectives which includes minimizing the cost and load balance of industrial robots through scheduling. To solve these scheduling problems, we used the algorithm based on Artificial Immune system. The parameters are simulated with MATLAB and the results compared with the existing algorithms. The result shows better performance than existing.

Continuous Authentication on PCs using Artificial Immune System

Abstract: Most of the existing systems require the users to provide a password or biometric data to authenticate themselves. However, as long as the user is still active in the system, there are no mechanisms to check whether the user is the genuine one or not. For the most computer system, the user identity is verified using Static Authentication (SA) only during the initial login process. In this paper, we focus on Continuous Authentication (CA) to continuously check the identity of the current user, based on every user action performed. We proposed to apply Artificial Immune System (AIS) Negative Selection (NS) for CA. Our proposed system was validated with a unique biometric dataset. The dataset was collected in a completely uncontrolled environment from 24 users. In this research, a combination of mouse and keystroke user behavior has been used. Our proposed system, shows that AIS was correctly able to continuously authenticate the users with high accuracy. The best achieved accuracies for 10 NS runs, where the number of generated detectors is 100, 200, 300, and 600, are 97.74%, 99.01%, 99.275%, and 99.7% respectively.

An Extreme Learning Machine Based on Artificial Immune System

Abstract: Extreme learning machine algorithm proposed in recent years has been widely used in many fields due to its fast training speed and good generalization performance. Unlike the traditional neural network, the ELM algorithm greatly improves the training speed by randomly generating the relevant parameters of the input layer and the hidden layer. However, due to the randomly generated parameters, some generated “bad” parameters may be introduced to bring negative effect on the final generalization ability. To overcome such drawback, this paper combines the artificial immune system (AIS) with ELM, namely, AIS-ELM. With the help of AIS’s global search and good convergence, the randomly generated parameters of ELM are optimized effectively and efficiently to achieve a better generalization performance. To evaluate the performance of AIS-ELM, this paper compares it with relevant algorithms on several benchmark datasets. The experimental results reveal that our proposed algorithm can always achieve superior performance.

RBF neural network based RFID indoor localization method using artificial immune system

Abstract: Indoor location based service is more and more popular in our daily lives. Due to such advantages of low power consumption, large interrogation range and low deployment cost, the Radio Frequency IDentification (RFID) becomes a simple, cost-effective indoor localization technology in indoor location based service systems. However, some existing RFID indoor localization methods are yet not satisfactory in accuracy. This paper proposes an Artificial Immune System based Radial Basis Function Neural Network (AIS-RBF-NN) to realize RFID indoor localization, in which artificial immune system is used to optimize the center vector selection of radial basis functions. To counteract the effect of the scene noise, the differences between the Received Signal Strength Indication (RSSI) values are fed into AIS-RBF- NN as well as RSSI values themselves. Simulation results indicate that the proposed AIS-RBF-NN based RFID indoor localization method is effective and outperforms the existing method.