Negative Selection Algorithm Research Articles

Современные иммунологические модели и их приложения

he paper considers main models and algorithms of artificial immune systems, which are related to the evolutionary computation paradigm and used to search for potential solutions, each of which is represented by an artificial lymphocyte. Same as an individual in evolutionary computation, an artificial lymphocyte is most often encoded by a binary string or a vector of real numbers. As far as the main models of artificial immune systems are concerned, the clonal selection algorithm is close to the evolutionary strategy of evolutionary computing, though it uses more powerful mutation operators and is applied mainly to solve numerical and combinatorial optimisation problems. The negative selection algorithm is based on the "friend or foe" recognition principle found in the immune system and is most popular in applications. The paper presents two aspects of the algorithm: 1) the basic concept, that is, expanding the set of "friend" cells; 2) the goal, which is to learn to distinguish between "friend" and "foe" cells, while only "friend" cell samples are available. We consider continuous and discrete network models representing regulated networks of molecules and cells. We note the advantages and disadvantages of these models and their application in the field of computer security, robotics, fraud and malfunction detection, data mining, text analysis, image recognition, bioinformatics, games, planning, etc.

EVALUATION OF DIGITAL IMAGE WATERMARKING TECHNIQUES

The advancing world of digital multimedia communication is facing problems linked to security and authenticity of digital data. The data security term is described as protecting information or digital data against any attack that may be performed by utilizing different attacking technologies, methods and techniques. A watermark system is reported to be secure, if the hacker cannot take away the watermark without full knowledge of embedding algorithm, detector and composition of watermark. This paper has shown the survey on image watermarking and its various techniques. From the survey it has been concluded that none of the technique performs effectively in all fields. Keywords— CZT, DWT, Image Watermarking, Negative Selection Algorithm, SVD

Optimized Negative Selection Algorithm for Image Classification in Multimodal Biometric System

Optimized Negative Selection Algorithm for Image Classification in Multimodal Biometric System

A NOVEL APPROACH FOR TEST DATA GENERATION

Software testing is an essential phase in software design process, accounting for more than half of the total cost due to its rigorous and time-consuming nature. Path test data generation is the most important stage in software testing, and researchers have devised several methods to automate it. In this research, a novel approach based on ant colony optimization and negative selection algorithm (NSA) is projected to automatically create test data for path testing. The most widely used benchmark programs such as triangle classification, dayfinder, minmax and isprime, has been used to test the proposed approach. When compared to random testing, the experimental findings reveal that the proposed method is more efficient in terms of coverage, execution time and more effective in terms of test data creation.

Disease-Ligand Identification Based on Flexible Neural Tree.

In order to screen the disease-related compounds of a traditional Chinese medicine prescription in network pharmacology research accurately, a new virtual screening method based on flexible neural tree (FNT) model, hybrid evolutionary method and negative sample selection algorithm is proposed. A novel hybrid evolutionary algorithm based on the Grammar-guided genetic programming and salp swarm algorithm is proposed to infer the optimal FNT. According to hypertension, diabetes, and Corona Virus Disease 2019, disease-related compounds are collected from the up-to-date literatures. The unrelated compounds are chosen by negative sample selection algorithm. ECFP6, MACCS, Macrocycle, and RDKit are utilized to numerically characterize the chemical structure of each compound collected, respectively. The experiment results show that our proposed method performs better than classical classifiers [Support Vector Machine (SVM), random forest (RF), AdaBoost, decision tree (DT), Gradient Boosting Decision Tree (GBDT), KNN, logic regression (LR), and Naive Bayes (NB)], up-to-date classifier (gcForest), and deep learning method (forgeNet) in terms of AUC, ROC, TPR, FPR, Precision, Specificity, and F1. MACCS method is suitable for the maximum number of classifiers. All methods perform poorly with ECFP6 molecular descriptor.

Nearest fixed boundary negative selection algorithm based method for early-warning of centrifugal compressor unit without fault data

In the modern industrial process, a complete production process is achieved by requiring a variety of equipment to cooperate with each other. The abnormality in any equipment will have a large or small impact on process safety or product quality, resulting in increased risk. In recent years, many data-driven early-warning methods have been developed in academia. However, most of the methods need to be implemented on the support of normal and fault data. In order to overcome the problem, this paper establishes a new early-warning model based on negative selection algorithm (NSA) for centrifugal compressor unit without fault data. Firstly, a nearest neighbor fixed boundary negative selection algorithm (NFB-NSA) is proposed by optimizing detector generation mechanism and matching rules for test samples. Secondly, the performance of NFB-NSA is tested by Iris dataset. The experimental results among NFB-NSA, V-detector, and other anomaly detection methods for Iris dataset shows that NFB-NSA can achieve the highest detection accuracy and the lowest false alarm rate in most cases. Finally, the early-warning of centrifugal compressor unit under normal samples is carried on by NFB-NSA in this paper. Validated by field data, NFB-NSA is demonstrated to be of excellent accuracy and robustness by results of experiments. Moreover, the influence of size of training sample on performance of NFB-NSA is obtained.

Detection, Location and Quantification of Structural Faults in a Two-Story Building Using the Artificial Immunological System

Large buildings and skyscrapers are vulnerable to environmental, temporal, and anthropological stresses, generating wear and tear that can lead to this social and economic impediment's collapse. The technological improvements of the fourth industrial revolution have resulted in changes in the connection between physical space and man, known as the cyber physic model, which necessitates monitoring systems to protect the structural branch and so correct this structural vulnerability. Thus, the structural health monitoring system is the exact measure of the evolution required by the cyber physic model in construction and the protection of the monumental buildings, ensuring not only their economic development but also the safety of society. Therefore, this research work presents the innovative proposal of the cyber-physical structural health monitoring system aimed at buildings and skyscrapers, based on and differentiated by intelligent computing techniques, using the negative selection algorithm to perform the analysis and monitoring of structural integrity, overcoming the existing traditional work. The cyber-physical structural health monitoring system will be applied to experimental data obtained from the shear building model that represents these imposing skyscrapers. An artificial immune system will be developed and used in the decision-making process based on the acquisition and processing of the obtained signals to perform the identification, localization, and quantification of possible structural damage. Observing the results, this work proved to be efficient, robust, and economically feasible, having high performance and overcoming the shortcomings of traditional techniques. It represents the perfect measure of cyber physics in the monitoring of large buildings and skyscrapers.

Immune systems in computer science

A simplified description of the immune system is as follows: this is an organic system intended for protecting the host organism from the threats posed to it from pathogens and toxic substances. The architecture of the immune system is such that a series of defensive layers protect the host. Once the pathogen makes it inside the host, it must contend with the innate and adaptive immune system. These two immunological sub-systems are comprised of several types of cells and molecules produced by specialized organs and processes to address the self non-self problem. Artificial Immune Systems (AIS) are computational models, based on natural immune systems. They tend to solve specific problems in computer science by resembling the natural mechanisms. These systems are more widely applied within problem domains like clustering, pattern recognition, classification, optimization, and machine learning. Modern AIS are inspired by one of three sub-fields: clonal selection, negative selection, and immune network algorithms. In computer science, the clonal selection pattern can be used for pattern matching and optimization. The negative selection algorithm was designed for change detection, novelty detection, and intrusion detection. Immune network algorithms are inspired by the immune network theory of the acquired immune system and it is an upgrade of the clonal selection theory. The objective of the immune network process is to prepare a repertoire of discrete pattern detectors for a given problem domain, where better performing solutions suppress low affinity solutions within the same network. This is an interactive process of exposing the pattern to external information to which it responds. This article explains the biological background, the mechanisms of AIS, and presents their real-world applications. It presents an overview of those important applications of AIS for solving problems from problem domains like data analysis, anomaly detection, intrusion detection, and others.

Multiclass anomaly detection for unsupervised and semi-supervised data based on a combination of negative selection and clonal selection algorithms

A key challenge in anomaly detection is the imbalance between the amounts of normal and abnormal signal data. Specifically, the amount of abnormal signal data is considerably less than that of normal signal data. To solve this problem, techniques for detecting abnormalities using only normal signal data derived from artificial immune systems (AISs) have been investigated. A representative example is the negative selection algorithm (NSA), which classifies data and detects anomalies using only normal signals through a process that mimics the underlying principle of vertebrate immunity. However, the NSA is optimized to detect only two classes of anomalies. Therefore, in this study, we developed a multiclass anomaly detection algorithm that hybridizes the principles of NSA and the clonal selection algorithm (CSA). We improved this algorithm using unsupervised and semi-supervised learning algorithms to conveniently detect anomalies at actual industrial sites. This paper presents a process for applying an AIS algorithm to anomaly detection using the evolution of data-based anomaly-detection algorithms. In particular, we leveraged the NSA principle of classification through semi-supervised learning to enable multiple classifications of unlabeled data. The obtained detector data formed clones optimized by the CSA and had constant memory, thus improving the classification accuracy and reducing run time. The proposed algorithm was validated using an intelligent maintenance system bearing dataset and a vacuum deposition equipment dataset.

Discrete R-Contiguous bit Matching mechanism appropriateness for anomaly detection in Wireless Sensor Networks

Resource exhaustion is one of the main challenges for the security of Wireless Sensor Networks (WSNs). The challenge can be addressed by using algorithms that are light weighted. In this paper use of light-weighted R-Contiguous Bit matching for attack detection in WSNs has been evaluated. Use of R-Contiguous bit matching in Negative Selection Algorithm (NSA) has improved the performance of anomaly detection resulting in low false positive, false negative and high detection rates. The proposed model has been tested against some of the attacks. The high detection rate has proved the appropriateness of R-Contiguous bit matching mechanism for anomaly detection in WSNs.

Negative Selection Algorithm Research and Applications in the Last Decade: A Review

The negative selection algorithm (NSA) is one of the important methods in the field of immunological computation (or artificial immune systems). Over the years, some progress was made that turns this algorithm (NSA) into an efficient approach to solve problems in different domain. This review takes into account these signs of progress during the last decade and categorizes those based on different characteristics and performances. Our study shows that NSA’s evolution can be labeled in four ways highlighting the most notable NSA variations and their limitations in different application domains. We also present alternative approaches to NSA for comparison and analysis. It is evident that NSA performs better for nonlinear representation than most of the other methods, and it can outperform neural-based models in computation time. We summarize NSA’s development and highlight challenges in NSA research in comparison with other similar models.

Artificial immune systems applied to clinical diagnosis of breast cancer samples

This work employments a manufactured resistant framework connected for diagnosing breast cancer tests. Taking as premise an immunological prepare, the Negative Selection Algorithm was utilized to segregate the tests, achieving a classification for generous or harmful cases. The most application of the strategy is to help experts within the breast cancer demonstrative prepare, in this manner giving decision-making agility, efficient treatment arranging, unwavering quality and the vital mediation to spare lives. To assess this strategy, the Wisconsin Breast Cancer Determination database was utilized. This is often a real breast cancer database. The comes about gotten utilizing the strategy, when compared with the specialized writing, appear precision, strength and proficiency within the breast cancer demonstrative handle.

Guest Editorial: Hybrid Approaches to Nature-Inspired Population-Based Intelligent Optimization for Industrial Applications

These days, hybrid nature-inspired population-based intelligent optimization methods are a wide range of the algorithms, which are used very often to solve real-world (industrial) optimizationproblems. As it was shown in [item 1) in the Appendix] by Slowik and Cpalka, nature-inspired methods can be divided into several groups of algorithms. In these groups of nature-inspired algorithms, we can find physics-based algorithms (gravitational search algorithm, harmony search algorithm, big bang-big crunch algorithm, etc.) and bio-inspired methods. In bio-inspired methods, we can find evolutionary algorithms (genetic algorithms, evolution strategies, genetic programming, etc.), swarm intelligence algorithms (particle swarm optimization algorithm, ant colony optimization algorithm, bat algorithm, etc.), immune algorithms (clonal selection algorithm, negative selection algorithm, etc.), and others (flower pollination algorithm, great Salomon run, Japanese tree frogs calling, etc.). These four selected groups of nature-inspired population-based optimization algorithm are commonly used in creating hybrid methods.

Clinical diagnosis of breast cancer samples using artificial immune systems with negative selection / Diagnóstico clínico de amostras de cancro da mama utilizando sistemas imunitários artificiais com selecção negativa

This paper uses an artificial immune system applied for diagnosing breast cancer samples. Taking as basis an immunological process, the negative selection algorithm was used to discriminate the samples, attaining a classification for benign or malignant cases. The main application of the method is to assist professionals in the breast cancer diagnostic process, thereby providing decision-making agility, efficient treatment planning, reliability and the necessary intervention to save lives. To evaluate this method, the wisconsin breast cancer diagnosis database was used. This is an actual breast cancer database. The results obtained using the method, when compared with the specialized literature, show accuracy, robustness and efficiency in the breast cancer diagnostic process.

MONITORAMENTO DE FALHAS EM SISTEMAS DINÂMICOS UTILIZANDO UM MÉTODO DE ANÁLISE DE DADOS BASEADO NO ALGORITMO DE SELEÇÃO NEGATIVA

This work presents the application of a method for monitoring and diagnosing failures in mechanical structures based on the theory of vibration signals and on Artificial Immune Systems to assist in data processing. It uses the Negative Selection Algorithm as a tool to identify fault samples extracted from the laboratory simulated signals of a dynamic rotor. This methodology can help mechanical structure maintenance professionals, facilitating decision-making. The data set used in the processing of the intelligent system was generated through experiments. For normal (base-line) conditions, the signals of the rotor in free operation were used, that is, without the addition of unbalance mass, and for the fault conditions, unbalance masses were added to the system. The results are satisfactory, showing precision and robustness.

A survey of intrusion detection techniques based on negative selection algorithm

A survey of intrusion detection techniques based on negative selection algorithm

Combine labeled and unlabeled data for immune detector training with label propagation

Artificial immune detectors are the basic recognition components of immune systems. Traditionally, the candidate non-self detectors are compared with the whole self training set to eliminate self-reactive ones in negative selection algorithms (NSAs). However, the training process has low efficiency due to the exhausting comparisons. Furthermore, it can be more efficient if we straightforwardly generate self-detectors based on the available self samples to avoid the overwhelmed comparisons. In the paper, a new detector training algorithm is proposed. Firstly, the self training set is enlarged by the label propagation algorithm (LPA) using both labeled and unlabeled samples; and then the newly labeled samples is evaluated based on noisy learning theory to remove the unqualified ones. Finally self-detectors are directly generated at the locations of self samples. The theoretical analysis demonstrated that the time complexity of our algorithm is much reduced, especially that the exponential relationship between self size and time complexity in traditional NSAs is eliminated. The experimental results showed that: not only the time cost of detector training, but also the detection accuracy is improved.

Self-adaptive mobile web service discovery approach based on modified negative selection algorithm

Self-adaptive mobile web service discovery approach based on modified negative selection algorithm

A hybrid real-valued negative selection algorithm with variable-sized detectors and the k-nearest neighbors algorithm

A negative selection algorithm generates detectors to realize abnormality detection by simulating the maturation process of T cells in human immunity. Holes are areas of feature space that cannot be covered by the detector set and are the major factor in the degradation of algorithm performance. Conventional methods alleviate the hole problem by minimizing the coverage area of the holes. In this study, we approach the issue from a different angle. Holes are prone to form in the boundary area between the self and nonself regions, and when the self and the nonself cross or overlap, the hole problem becomes more serious. The k-nearest neighbors (k-NN) algorithm is more suitable than other methods for pending instance sets where the class domain crosses or overlaps more. Therefore, we propose a hybrid real-valued negative selection algorithm with variable-sized detectors (V-Detector) and the k-NN algorithm, abbreviated as V-Detector-kNN. The V-Detector-kNN hybrid algorithm first uses the V-Detector algorithm to classify, and then, for the problem that the nonself instances in the holes are misclassified as selfs, k-NN is introduced to classify those misclassified instances to improve the detection rate. Theoretical analysis proves that the V-Detector-kNN algorithm that we proposed has a higher detection rate than the V-Detector algorithm in most cases. Comparative experiments with 5 different algorithms on 9 UCI datasets show that our proposed algorithm ranks first in detection rate.

Abnormal Detection of Pumping Unit Bearing Based on Extension Theory

In order to solve the problem that is difficult to extract the fault data of bearing of pumping unit in operation, a negative selection algorithm based on extension theory is proposed to detect the abnormal of bearing. First, a negative selection algorithm detector set model is constructed by using matter element. Synthetic correlation degree function is used as the matching rule of detector generation stage and bearing fault anomaly detection stage. Genetic Particle Swarm Optimization (GPSO) is used to generate detector set. Aiming at the problem of large redundancy of the detector set, the correlation function is used to formulate merging rules to merge the detector set interval. Finally, bearing anomaly detection is carried out by using the bearing fault data of Case Western Reserve University. The results show that the activation rate of the inner ring fault detector is 98.89%, the activation rate of the outer ring fault detector is 98.61%, and the activation rate of the ball fault detector is 99.17%. © 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.