Artificial Immune System Method Research Articles

Security and storage improvement in distributed cloud data centers by increasing reliability based on particle swarm optimization and artificial immune system algorithms

SummaryOne of the major concerns in security and storage improvement of data centers is due to the fact that there is a possibility of access to cloud information, and the distance between data centers for data transfer causes cloud storage problems. In this article, an encryption method using artificial immune system (AIS) is leveraged to secure sensitive data in data centers and particle swarm optimization (PSO) algorithm is exploited to improve the selection of storage services in distributed cloud data centers to store and transfer particular a data set between data centers. To obtain satisfied performance considering the transmitting cost, and smallest transmitting distance, we exploited one discrete PSO algorithm and AIS method and called PSO_AIS. To evaluate the proposed PSO_AIS algorithm, we designed the experiments and simulated it in MATLAB software. In the simulation, we conducted experiments on 13 data centers located in different locations in Iran. The experimental results expose that the proposed algorithm reduces 30% the distance and cost to select a particular data center for a particular data set. Experiments have been carried‐out to demonstrate the effectiveness of the proposed encryption method, which is based on AIS. The results showed that the encoding performance of the proposed method is better than other methods.

Application of Artificial Immune Systems in Advanced Manufacturing

In recent years, the application of Advanced Manufacturing Technologies (AMT) in industrial processes represents the introduction of different Advanced Manufacturing Systems (AMS), which encourage enterprises to improve their core competitiveness and maintain sustainable development when facing the increasing demand for personalized product customization. More recently, AMT led to a new Internet revolution, mostly known as 4th Industrial Revolution. Considering the development and deployment of Artificial Intelligence to enable smart and self-behaving industrial systems, autonomic approaches allow the system to adapt itself, eliminating the need for human intervention for management. This paper presents a systematic literature review regarding Artificial Immune Systems (AIS) approaches to tackle multiple AMS problems requiring levels of autonomy. First, a systematic review of current industrial AIS applications in manufacturing environments is presented. Then, a conceptual framework is proposed to bridge the gap between research in the AIS field and the manufacturing industry while discussing key challenges and opportunities to be addressed by future research. This study aims to build a body of knowledge for researchers and manufacturers regarding AIS solutions under Advanced Manufacturing while suggesting directions for understanding the requirements for designing and managing autonomic industry applications supported by AIS. • Presentation of a systematic review of AIS methods application in AMS. • Summary of the empirical evidence of the benefits of applying AIS algorithms in AMS. • Exploration of the readiness level and autonomy of AIS applications in AMS. • Outline the key areas where future research can improve the use of AIS in AMS.

Optimisasi Multi-objektif pada Rekonfigurasi Jaringan Distribusi Tenaga Listrik dengan Integrasi Pembangkit Terdistribusi Menggunakan Metode Sistem Kekebalan Buatan

This study proposes a multi-objective optimization for power distribution network reconfiguration by integrating distributed generators using an artificial immune system (AIS) method. The most effective and inexpensive technique in reducing power losses in distribution networks is optimizing the network reconfiguration. On the other hand, small to medium scale renewable energy power plant applications are growing rapidly. These power plants are operated on-grid to a distribution network, known as distributed generation (DG). The presence of DG in this distribution network poses new challenges in distribution network operations. In this study, the distribution network optimization was carried out using the AIS method. In optimization, the goal to be achieved is not only one objective but should be multiple objectives. Multi-objective optimization aims to reduce power losses, improve the voltage profile, and maintain a maintained network load balance. The AIS method has the advantage of fast convergence and avoids local minima. To test the superiority of the AIS method, the distribution network optimization with and without DG integration was carried out for the 33-bus and 71-bus models of the IEEE standard distribution networks. The results show that the AIS method can produce better system operating conditions than before the optimization. The parameters for the success of the optimization are minimal active power losses, suitable voltage profiles, and maintained load balance. This optimization has successfully increased the efficiency of the distribution network by an average of 0.61%.

Multidomain Features-Based GA Optimized Artificial Immune System for Bearing Fault Detection

This paper proposes a novel multidomain features-based genetic algorithm (GA) optimized artificial immune system (AIS) framework for fault detection in real systems. Different from native real-valued negative selection algorithm (RNSA) that operates in original data space, this algorithm utilizes feature space transformation and diversity factor-based GA for optimized detector distribution in nonself feature space. The proposed framework comprises three stages namely; feature extraction, unsupervised feature selection, and GA optimized AIS. In the first stage, signal processing methods are applied to extract multidomain features (time-domain statistical, frequency domain statistical, and special features) of the system. In the second stage, two unsupervised methods namely, ${k}$ -NN clustering and pretraining using deep learning neural network are proposed for dominant fault-characterizing feature selection. Finally, in the third stage, the fault-characterizing feature vectors are used for system status categorization (i.e., normal, fault) using selected (fault-characterizing) features-based AIS method. The efficacy of the proposed framework is verified through experiments on motor bearing fault detection using vibration signal. The major accomplishment of the proposed combination of space transformation, feature selection and AIS (anomaly classification) techniques is the alleviation of computational burden on RNSA implementation. Moreover, GA optimized AIS fault diagnosis based on well-established features gives improved detection performance.

Application of Artificial Immune System Algorithm for Simultaneous Minimization of Multiple Objectives in Single Row Facility Layout Problems

In this paper, an artificial immune system (AIS) algorithm is proposed to solve single row facility layout problem (SRFLP) for obtaining a best layout design of machines, which simultaneously minimises the multiple objectives. The multi-product environment with multiple objectives is considered in this work and it is a non-polynomial hard problem too. Total number of machines in the layout, total flow distance of products, total length of the flow line and total material handling cost are considered as objectives. Four problems are taken from Lenin et al. (2018) and four problems are randomly generated to obtain the best layout using AIS. The reduction in objective values is good by the proposed AIS algorithm compared with Lenin et al. (2018). In addition, the computational time for all the eight problems by the proposed AIS method is less compared with Lenin et al. (2018).

The application of artificial immune system for parallel process of calculation and their comparison with existing methods

The present paper is devoted to the application of artificial immune system method for the solution of the symbolic regression problem. A mathematical model with the algorithm of its realization in sequential and parallel realization using some properties of the natural immune system is proposed. In the description of the proposed artificial immune system model and algorithm the terminology of the natural immune system is preserved. The concept of B-cells, which are responsible for producing antibodies, a special class of complex proteins on the surface of B-lymphocytes, capable of binding to certain types of molecules (antigens), is adopted and used. Accuracy of calculations is compared to that for other methods, i.e. methods of genetic programming. The program product involving the algorithms is developed. Computing experiments for each considered task are made.

The deconvolution of complex spectra by artificial immune system

An application of the artificial immune system method for decomposition of complex spectra is presented. The results of decomposition of the model contour consisting of three components, Gaussian contours, are demonstrated. The method of artificial immune system is an optimization method, which is based on the behaviour of the immune system and refers to modern methods of search for the engine optimization.

Comparison of AIS and fuzzy c-means clustering methods on the classification of breast cancer and diabetes datasets

Data reduction is an indispensable part of pattern classification processes in many cases. If the number of samples is excessive, sample reduction or data reduction algorithms can be used for an effective processing time and reliable successive results. Many methods have been used for data reduction. Fuzzy c-means is one of these methods and it is widely used in such applications as clustering algorithms. In this study, we applied a different clustering algorithm, an artificial immune system (AIS), for the data reduction process. We realized the performance evaluation experiments on the standard Chainlink and Iris datasets, while the main application was conducted using the Wisconsin Breast Cancer and Pima Indian datasets, which were taken from the University of California, Irvine Machine Learning Repository. For these datasets, the performance of the AIS in the data reduction process was compared with the fuzzy c-means clustering algorithm, in which a multilayer perceptron artificial neural network was used as a classifier after the data reduction processes. The obtained results show that the maximum classification accuracies were obtained as 73.96 % for the Pima Indian Diabetes dataset and 97.80% for the Wisconsin Breast Cancer dataset with the AIS and the compression rates were 80% and 40% for these results. For fuzzy c-means clustering, however, the aforementioned accuracies were obtained as 63% and 86.69% for the Pima Indian Diabetes and Wisconsin Breast Cancer datasets, respectively. Moreover, the compression rates for these results for fuzzy c-means were 90% and 70%. When the mean classification accuracy values over the experimented compression rates were taken into consideration, the AIS reached a mean classification accuracy of 70.07% for the Pima Indian Diabetes dataset, while 47.64% was obtained by fuzzy c-means for this dataset. For the Wisconsin Breast Cancer dataset, however, the mean classification accuracies of the AIS and fuzzy c-means methods were recorded as 94.90% and 75.43%, respectively.

Artificial immune simulation for improved forecasting of electricity consumption with random variations

This paper presents an integrated algorithm for forecasting annual electrical energy consumption based on Artificial Immune System (AIS), Genetic Algorithm (GA), Particle Swarm Optimization (PSO) and computer simulation. Computer simulation is developed to generate random variables for annual electricity consumptions in selected countries. Most recent studies are concerned with deterministic data sets which could enhance relative error. However, this study utilizes fitted random variables as input data to decrease the relative error. Mean Absolute Percentage Error (MAPE) is used for evaluating the results and selecting the best forecasting model. To show the applicability of the proposed algorithm, the annual electricity consumptions for 16 countries from 1980 to 2006 are considered and the proposed algorithm is applied to the corresponding historical data. Three considered meta-heuristics (i.e. AIS, GA, and PSO) are compared with each other in estimation of electricity consumption in the selected countries. The comparison is made based on MAPE for the test period data. For the selected countries, AIS method with the Clonal Selection Algorithm (CLONALG) shows satisfactory results when applied with simulated data and has been selected as the preferred method. This is the first study that uses an integrated AIS-simulation for improved forecasting of electricity consumption with random variations.

SHADuDT: Secure hypervisor-based anomaly detection using danger theory

Intrusion Detection based upon learning methods is an attractive approach in research community. These researches have two critical concerns: secure information gathering and accurate detection method. Here we used system calls together with their arguments as a suitable pattern for describing behavior of each process. In security applications, these patterns must be collected safely, so we proposed SHADuDT, a secure and robust hypervisor-based architecture for system call intercepting and information gathering that utilizes the second generation of Artificial Immune Systems (AIS) as intrusion detection method. Generally intrusion detection based on AISs fall into two categories. The first generation of AIS is inspired from adaptive immune reactions but the second one that is called danger theory focuses on both of these reactions to build a more biologically-realistic model of Human Immune System.Here we presented a novel Algorithm in Danger Theory field as SHADuDT detection method (SHADuDT_DM) for anomaly detection and utilized hypervisor architecture for SHADuDT secure auditor (SHADuDT_SA) to guarantee the safety of information gathering. We evaluated SHADuDT architecture through several criteria and compared its detection method with classic AIS methods for anomaly detection. These Evaluation results show considerable improvements in terms of detection performance and false alarm rates while keeping low overheads in execution time and memory by using the advantages of both hypervisor technology and Artificial Immune Systems.

Fault Localization of Analog Circuit with Small Sample Using SVM and AIS Methods

Both Support Vector Machines (SVM) and Artificial Immune Systems (AIS) are by far effective on faults localization of analogue circuits for small samples. In this paper, both a selective SVM ensemble based on clustering Algorithm and a new AIS based on real-valued NS (RNS) algorithm are applied to the fault diagnosis and their effects are evaluated. The fault diagnosis experiments on a continuous-time state-variable filter circuit show that the fault diagnosis method based the AIS can obtain high fault localization rate of 95% when only one group samples acted as the training samples and the other method can obtain fault localization rate of 85% when 400 group samples acted as the training samples. So, AIS is a more effective method to fault diagnosis with small samples.

Performance evolution of a newly developed general-use hybrid AIS-ANN system: AaA-response

In this study, we have developed a nonlinear recognition system in the artificial immune systems (AIS) field named `AaA-response (artificial neural network (ANN)-aided AIS-response)', which is different from previous AIS methods in that it uses a different modeling strategy in the formation of the memory response. Because it also uses ANNs in the determination of the correct output, it can be seen as a hybrid system that involves AIS and ANN approaches. Unlike the other AIS methods, AaA-response uses multiple system units (or antibodies) to form an output for a presented input. This property gives the proposed system the ability of producing the desired output values, other than just being a classification algorithm. That is, AaA-response can also be used as a regression method, like ANNs, by producing any output value for the given inputs. The parameter analyses of the system were conducted on an artificially generated dataset, the Chainlink dataset, and the important points in the parameter selection were emphasized. To investigate the performance of the system for real-world problems, the Iris dataset and Statlog Heart Disease dataset, taken from the University of California - Irvine machine learning repository, were used. The system, which obtained 99.33% classification accuracy on the Iris dataset, has shown an important performance superiority with regard to the classification accuracy to other methods in the literature by reaching 90.37% classification accuracy for the Statlog Heart Disease dataset.

Intelligent Motion Control for Four-Wheeled Holonomic Mobile Robots Using FPGA-Based Artificial Immune System Algorithm

This paper presents an intelligent motion controller for four-wheeled holonomic mobile robots with four driving omnidirectional wheels equally spaced at 90 degrees from one another by using field-programmable gate array (FPGA)-based artificial immune system (AIS) algorithm. Both the nature-inspired AIS computational approach and motion controller are implemented in one FPGA chip to address the optimal control problem of real-world mobile robotics application. The proposed FPGA-based AIS method takes the advantages of artificial intelligence and FPGA technology by using system-on-a-programmable chip (SoPC) methodology. Experimental results are conducted to show the effectiveness and merit of the proposed FPGA-based AIS intelligent motion controller for four-wheeled omnidirectional mobile robots. This FPGA-based AIS autotuning intelligent controller outperforms the conventional nonoptimal controllers, the genetic algorithm (GA) controller, and the particle swarm optimization (PSO) controller.

A two-stage AIS approach for grid scheduling problems

Grid workflow scheduling problem has been a research focus in grid computing in recent years. Various deterministic or meta-heuristic scheduling approaches have been proposed to solve this NP-complete problem. A perusal of published papers on the artificial immune system (AIS) reveals that most researchers use the clonal selection of B cells during the evolving processes and the affinity function of B cells to solve various optimisation problems. This research takes a different approach to the subject – firstly by applying a modified algorithm (Hu, T.C., 1961. Parallel sequencing and assembly line problem. Operations Research, 9 (6), 841–848) to sequence the job and this sequence is applied for further application. Secondly, the derived sequence is then used for machine allocations using the AIS approach. The proposed AIS apply B cells to reduce the antigens and then combining T helper cells and T suppressor cells to solve the grid scheduling problems. Our proposed methodology differs from other earlier approaches as follows: 1. A two-stage approach is applied using a fixed sequence derived from heuristic to allocate machine. 2. AIS apply B cells as bases and then T cells are employed next. T helper cells are used to help improve the solution and then T suppressor cells are generated to increase the diversity of the population. A new formula is proposed to calculate the affinity of the antibody with the antigen. The total difference of completion time of each job is applied instead of the difference of makespan of the schedule. This new AIS method can supplement the flaw of genetic algorithms (GA) using fitness as the basis and a new lifespan which will keep good diversified chromosomes within the population to extend the searching spaces. The experimental tests show that this novel AIS method is very effective when compared with other meta-heuristics such as GA, simulated annealing (SA), and ant colony optimisation (ACO).

Pickup and delivery problem using metaheuristics techniques

Dial-a-ride problem (DARP) is an optimization problem which deals with the minimization of the cost of the provided service where the customers are provided a door-to-door service based on their requests. This optimization model presented in earlier studies, is considered in this study. Due to the non-linear nature of the objective function the traditional optimization methods are plagued with the problem of converging to a local minima. To overcome this pitfall we use metaheuristics namely Simulated Annealing (SA), Particle Swarm Optimization (PSO), Genetic Algorithm (GA) and Artificial Immune System (AIS). From the results obtained, we conclude that Artificial Immune System method effectively tackles this optimization problem by providing us with optimal solutions.

Application of genetic optimized artificial immune system and neural networks in spam detection

Spam is a serious universal problem which causes problems for almost all computer users. This issue not only affects normal users of the internet, but also causes a big problem for companies and organizations since it costs a huge amount of money in lost productivity, wasting users’ time and network bandwidth. There are many studies on spam indicates that spam costs organizations billions of dollars yearly. This work presents a lot of modification on a machine learning method inspired by the human immune system called artificial immune system (AIS) which is a new emerging method that still needs more investigations and demonstrations. Core modifications were applied on the standard AIS with the aid of the Genetic Algorithm (GA). Also Artificial Neural Network (ANN) for spam detection is applied in a new manner. SpamAssassin corpus is used in all our simulations. In standard AIS several user defined parameters are used such as culling of old lymphocytes. Genetic optimized AIS is used to present culling time instead of using user defined value. Also, a new idea to check antibodies in AIS is introduced. This would make the system able to accept types of messages that were previously considered as spam. The idea is accomplished by introducing a new issue which we call “rebuild time”. Moreover, an adaptive weighting of lymphocytes is used to modify selection opportunities for different gene fragments. In this work also, core modifications on ANN neurons are applied; these modifications allow neurons to be changed over time replacing useless layers. This approach is called Continuous Learning Approach Artificial Neural Network, CLA_ANN. The final results are compared and analyzed. Results show that both systems, optimized spam detection using GA and spam detection using ANN, achieved promising scores comparable to standard AIS and other known methods.

Manufacturing cell formation using artificial immune system

The cellular manufacturing system is a well-known strategy which improves the production efficiency and cutting down the manufacturing cost. The main problem in designing cellular manufacturing system is cell formation, which is concerned with grouping parts with similar processing required into part families and associated machines into machines and minimises the exceptional elements. This paper presents the artificial immune system method to solve the manufacturing cell formation problems with the objective to minimise the exceptional elements. This method is applied to the existing datasets found in the literature and it is found to out performs other methods.

Mining fuzzy rules using an Artificial Immune System with fuzzy partition learning

The paper introduces accuracy boosting extension to a novel induction of fuzzy rules from raw data using Artificial Immune System methods. Accuracy boosting relies on fuzzy partition learning. The performance, in terms of classification accuracy, of the proposed approach was compared with traditional classifier schemes: C4.5, Naïve Bayes, K ∗, Meta END, JRip, and Hyper Pipes. The result accuracy of these methods are significantly lower than accuracy of fuzzy rules obtained by method presented in this study (paired t-test, P < 0.05).

Prediction of protein cellular localization sites using a hybrid method based on artificial immune system and fuzzy k-NN algorithm

The use of artificial intelligence methods in biological data analysis has been increased recent since performance of the classification and detection systems have improved considerably to help medical experts in diagnosing. In this paper, we investigate the performance of an artificial immune system (AIS) based fuzzy k-NN algorithm with and without cross validation in a class of imbalanced problems in bioinformatics. Furthermore, we devise an unsupervised AIS algorithm in a supervised manner which contains a training stage for data reduction and a classification stage using fuzzy k-NN algorithm. The experiments show the efficacy of the proposed method with promising results. Using the Escherichia coli and yeast database, we compare the classification accuracy of the proposed method with those of other methods which have been proposed in the literature. The proposed hybrid system produced much more accurate results than the Horton and Nakai's method [P. Horton, K. Nakai, Better prediction of protein cellular localization sites with the k-nearest neighbors classifier, in: Proceedings of Intelligent Systems in Molecular Biology, Halkidiki, Greece, 1997, pp. 368-383]. Besides the improvement on the classification accuracy, one of the important aspects of the proposed method is the complexity. As the proposed AIS method incorporates data reduction in the training stage, the training complexity is considerably low comparing with the k-NN classifier.

Accelerating improvement of fuzzy rules induction with artificial immune systems

The paper introduces an algorithmic improvement to IFRAIS, an existing Artificial Immune System method for fuzzy rule mining. The improvement presented consists of using rule buffering during the c...