Artificial Immune Network Research Articles

Thyroid Extraction Based on Artificial Immune Network with Firefly Algorithm in Single Photon Emission Computed Tomography Image

Thyroid extraction from single photon emission computed tomography (SPECT) image is an important primary work for medical image analysis and computer aided diagnosis. However, SPECT image of thyroid does not have a clear margin boundary compared with ultrasound or CT images. A thyroid extraction method for SPECT Image based on artificial immune network that is optimized with firefly algorithm is developed. Artificial immune network is employed for discovering the correlation between spatial distance and pixel value by samples selection, and firefly algorithm with adaptive step is used for optimization the samples selection. The experimental results demonstrate that the proposed method is efficient with less extraction error which is superior to other extraction methods. The average error of the proposed method is 21.9% and 14.4% less than that of sampling method and global sampling method, respectively. And the proposed method is also robust for initial regions with varies radius. The experiments reveal that the proposed method is more efficient than other sampling methods with different trimaps.

Hyper-Parameter Optimization of Classifiers, Using an Artificial Immune Network and Its Application to Software Bug Prediction

Software testing is an important task in software development activities, and it requires most of the resources, namely, time, cost and effort. To minimize this fatigue, software bug prediction (SBP) models are applied to improve the software quality assurance (SQA) processes by predicting buggy components. The bug prediction models use machine learning classifiers so that bugs can be predicted in software components in some software metrics. These classifiers are characterized by some configurable parameters, called hyper-parameters that need to be optimized to ensure better performance. Many methods have been proposed by researchers to predict the defective components but these classifiers sometimes not perform well when default settings are used for machine learning classifiers. In this paper, software bug prediction model is proposed which uses machine learning classifiers in conjunction with the Artificial Immune Network (AIN) to improve bug prediction accuracy through its hyper-parameter optimization. For this purpose, seven machine learning classifiers, such as support vector machine Radial base function (SVM-RBF), K-nearest neighbor (KNN) (Minkowski metric), KNN (Euclidean metric), Naive Bayes (NB), Decision Tree (DT), Linear discriminate analysis (LDA), Random forest (RF) and adaptive boosting (AdaBoost), were used. The experiment was carried out on bug prediction dataset. The results showed that hyper-parameter optimization of machine learning classifiers, using AIN and its applications for software bug prediction, performed better than when classifiers with their default hyper-parameters were used.

An inception module CNN classifiers fusion method on pulmonary nodule diagnosis by signs

A “sign” on a lung CT image refers to a radiologic finding that suggests a pathological progression of some specific disease. Analysis of CT signs is helpful to understand the pathological origin of the lesion. In-depth study of lung nodules classification with different CT signs will help to distinguish benign and malignant nodules more clearly and accurately. To this end, we propose an Inception module-based ensemble classification method for pulmonary nodule diagnosis with different nodule signs. We first construct a Convolutional Neural Network (CNN) classifier adopting Inception modules and pre-train it on ImageNet. We then fine-tune this pre-trained classifier on 10 different lung nodule sign sample sets, and fuse these 10 classifiers with an artificial immune ensemble algorithm. The overall sensitivity, specificity, and accuracy of our proposed Artificial Immune Algorithm-based Inception Networks Fusion (AIA-INF) algorithm are 82.22%, 93.17%, and 88.67%, respectively, which are significantly higher than those of the alternative Bagging and Boosting methods. The experimental results show that our Inception-based ensemble classifier offers promising performance, and compared with other CADx systems, this scheme can offer a more detailed reference for diagnosis, and can be valuable for junior radiologist training.

Bidirectional reflection distribution function modeling (BRDF) for terahertz diffuse scattering analysis of dielectric rough targets

This paper presents an optical method to determine the scattering characteristics of dielectric rough targets in the terahertz band. Based on the complex permittivity of alloy Al (Aluminum) and painted Al obtained from the reflectance spectra, the analytical bidirectional reflection distribution function (BRDF) spectra of rough surfaces are simulated using physical optics. The effects of surface roughness, complex permittivity, incident angle, and wavelength are analyzed. With the optimization of artificial immune network genetic algorithms, it is demonstrated that the optimized five-parameter BRDF empirical model fits the analytical BRDF spectra over a wide range of incidence angles. Then, the radar cross section (RCS) of electrically large targets can be simulated by the relationship between the differential scattering coefficient and BRDF. The obtained RCS of the rough sphere from optimized BRDF model is in good agreement with the numerical analysis that was obtained. The proposed method is suitable for obtaining the scattering properties of large dielectric targets with different surfaces compared with traditional high-frequency electromagnetic (EM) techniques. The backscattered and bistatic terahertz RCS of a cylinder, cone and NASA almond are simulated. The proposed method shows the potential for the application of BRDF in the areas of scattering analysis and remote sensing.

Artificial Immune System-Based Learning Style Stereotypes

This paper addresses the problem of extracting fundamental learning style stereotypes through the exploitation of the biologically-inspired pattern recognition paradigm of Artificial Immune Systems (AIS). We present an unsupervised computational mechanism which exhibits the ability to reveal the inherent group structure of learning patterns that pervade a given set of educational profiles. We rely on the construction of an Artificial Immune Network (AIN) of learning style exemplars by proposing a correlation-based distance metric. This choice is actually imposed by the categoric nature of the underlying data. Our work utilizes an original dataset which was derived during the conduction of an extended empirical study involving students of the Hellenic Open University. The educational profiles of the students were built by collecting their answers on a thoroughly designed questionnaire taking into account a wide range of personal characteristics and skills. The efficiency of the proposed approach was assessed in terms of cluster compactness. Specifically, we measured the average correlation deviation of the students’ education profiles from the corresponding artificial memory antibodies that represent the acquired learning style stereotypes. Finally, the unsupervised learning procedure adopted in this paper was tested against a correlation-based version of the k-means algorithm indicating a significant improvement in performance for the AIS-based clustering approach.

A Hybrid Algorithm Between the Artificial Immunological Network and the ANFIS Technique with Application

In this research, we have taken one of the artificial immune intelligence algorithms, namely the Artificial Immune Network, was developed using the Adaptive Neuro Fuzzy Inference System (ANFIS) by using the Immune Memory, The immunological network as an input to ANFIS technology to increase the chance of training a model based on the pattern of simulation of data patterns, as the immune memory resulting from the immunological network makes copies of data with characteristics similar to the original data. The proposed algorithm proved to have better and more efficient results rack on the patterns compared with the usual artificial immune system.

Application of Artificial Intelligence-based Technology in Cancer Management: A Commentary on the Deployment of Artificial Neural Networks.

Artificial intelligence was recognised many years ago as a potential and powerful tool to predict disease outcome in many clinical situations. The conventional approaches using statistical methods have provided much information, but are subject to limitations imposed by the complexity of medical data. The structures of the important variants of the machine learning system artificial neural networks (ANN) are discussed and emphasis is given to the powerful analytical support that could be provided by ANN for the prediction of cancer progression and prognosis. The predictive ability of the cellular markers, DNA ploidy and cell-cycle profiles, and molecular markers, such as tumour promoter and suppressor gene, and growth factor and steroid hormone receptors in breast cancer management were also analysed. ANN systems have been successfully deployed to evaluate microRNA profiles of tumours which saliently sway cancer progression and prognosis of the disease, thus counteracting the negative implications of their numerical abundance. Finally, in this setting, the prospective technical improvements in artificial neural networks, as hybrid systems in combination with fuzzy logic and artificial immune networks were also addressed.

Early-season crop mapping using improved artificial immune network (IAIN) and Sentinel data.

Substantial efforts have been made to identify crop types by region, but few studies have been able to classify crops in early season, particularly in regions with heterogeneous cropping patterns. This is because image time series with both high spatial and temporal resolution contain a number of irregular time series, which cannot be identified by most existing classifiers. In this study, we firstly proposed an improved artificial immune network (IAIN), and tried to identify major crops in Hengshui, China at early season using IAIN classifier and short image time series. A time series of 15-day composited images was generated from 10 m spatial resolution Sentinel-1 and Sentinel-2 data. Near-infrared (NIR) band and normalized difference vegetation index (NDVI) were selected as optimal bands by pair-wise Jeffries–Matusita distances and Gini importance scores calculated from the random forest algorithm. When using IAIN to identify irregular time series, overall accuracy of winter wheat and summer crops were 99% and 98.55%, respectively. We then used the IAIN classifier and NIR and NDVI time series to identify major crops in the study region. Results showed that winter wheat could be identified 20 days before harvest, as both the producer’s accuracy (PA) and user’s accuracy (UA) values were higher than 95% when an April 1–May 15 time series was used. The PA and UA of cotton and spring maize were higher than 95% with image time series longer than April 1–August 15. As spring maize and cotton mature in late August and September–October, respectively, these two crops can be accurately mapped 4–6 weeks before harvest. In addition, summer maize could be accurately identified after August 15, more than one month before harvest. This study shows the potential of IAIN classifier for dealing with irregular time series and Sentinel-1 and Sentinel-2 image time series at early-season crop type mapping, which is useful for crop management.

An artificial immune system algorithm applied to the solution of an inverse problem in unsteady inward solidification

The numerical simulation and optimization in solidification involving geometries beyond one dimension normally requires expensive computational approaches in memory and data processing, generating consequently high cost associated with runtime execution. When boundary conditions are unknown, such as how heat is extracted from the casting surface, which is a typical inverse heat transfer problem (IHTP), the search for such conditions by trial-and-error makes the whole process less feasible. In this sense, this work introduces the application of an artificial immune system (AIS) algorithm as a possible meta-heuristic alternative, with a view to returning acceptable objective values to converge on a set of acceptable solutions. In the present work, the search process of the heat transfer coefficient (hg) at the casting surface during two-dimensional inward solidification of Al-1.5 wt.%Fe alloy castings of Cartesian and Cylindrical geometries in chilled molds is optimized. Two water-cooled solidification apparatuses were designed to in situ melt the alloy by a set of electrical resistances, in which heat is extracted only through the chilled faces of the molds. The thermal history during solidification was obtained via thermocouples placed at different positions in the castings. A Finite Difference heat transfer model integrated to an optimized version of the artificial immune network algorithm, which uses the experimental thermal profiles as inputs, has been applied to solve the IHTP through the search for acceptable values of heat transfer coefficient. It is shown that fast convergence of the developed algorithm can be achieved for a relatively small number of iterations. The mean relative errors associated with differences between simulated and experimental temperatures are shown to be 1% and 0.07% for Cartesian and Cylindrical geometries, respectively and expressions relating hg to time have been determined for both geometries.

An Artificial Immune Network for Distributed Demand-Side Management in Smart Grids

In this work we present a Distributed Demand-Side Management system based on the Artificial Immune Network algorithm. It implements an intelligent, distributed and autonomous control of the customer’s Air Conditioning devices in order to meet the desired demand. The system is particularly adapted to tackle the Peak Load problem that appears in Tropical and Subtropical climates due to the use of thousands of these devices at the same time. The design follows the guidelines set by the Smart Grid paradigm, in the sense that it is fault tolerant, distributed and self-controlled. It requires minimal communication infrastructure when compared to a centralized system.The algorithm was evaluated using synthetic and real data. We define Maximal and Average Tolerance as performance metrics, and show that the system keeps the consumption within 1% of the given load limit in all 5 cases.

An artificial immune network to control interrupted flow at a signalized intersection

To monitor and control interrupted flow at signalized intersections, several Traffic Signal Control Systems (TSCSs) were developed based on optimization and artificial intelligence techniques. Although learning can provide intelligent ways to deal with disturbances, existing approaches still lack concepts and mechanisms that enable direct representation of knowledge and explicit learning, particularly to capture and reuse previous experiences with disturbances. This article addresses this gap by designing a new TSCS based on innovative concepts and mechanisms borrowed from biological immunity. Immune memory enables the design of a Case-Based Reasoning (CBR) System in which cases provide a direct representation of knowledge about disturbances. Immune network theory enables the design of a Reinforcement Learning (RL) mechanism to interconnect cases, capture explicit knowledge about the outcomes (success and failure) of control decisions and enable decision-making by taking advantage of previous outcomes in reaction to new occurrences of disturbances. We provide a detailed description of new learning algorithms, both to create the case-base and to interconnect cases using RL. The performance of the suggested TSCS is assessed by benchmarking it against two standard control strategies from the literature, namely fixed-time and adaptive control using the Longest Queue First – Maximal Weight Matching (LQF-MWM) algorithm. The suggested TSCS is applied on an intersection simulated using VISSIM, a state-of-the-art traffic simulation software. The results show that the suggested TSCS is able to handle different traffic scenarios with competitive performance, and that it is recommended for extreme situations involving blocked approaches and high traffic flow.

Multi-agent immune networks to control interrupted flow at signalized intersections

Urban traffic is subject to disturbances that cause long queues and extended waiting times at signalized intersections. Although Multi-Agent Systems (MAS) were considered to control traffic at signalized intersections in a distributed way, their generic conceptual framework and lack of built-in adaptation mechanisms prevent them from achieving specific disturbance management capabilities. The traffic signal control problem is still a challenging open-ended problem for which learning and adaptation mechanisms need to be developed to deal with disturbances in an intelligent way. In this article, we rely on concepts and mechanisms inspired by biological immunity to design a distributed, intelligent and adaptive traffic signal control system. We suggest a heterarchical multi-agent architecture, where each agent represents a traffic signal controller assigned to a signalized intersection. Each agent communicates and coordinates with neighboring agents, and achieves learning and adaptation to disturbances based on an artificial immune network. The suggested Immune Network Algorithm based Multi-Agent System (INAMAS) provides intelligent mechanisms that capture disturbance-related knowledge explicitly and take advantage of previous successes and failures in dealing with disturbances through an adaptation of the reinforcement principle. To demonstrate the efficiency of the suggested control architecture, we assess its performance against two control strategies from literature, namely fixed-time control and a distributed adaptation of the Longest Queue First – Maximal Weight Matching (LQF-MWM) algorithm. Agents are developed using SPADE platform and used to control a network of signalized intersections simulated with VISSIM, a state-of-the-art traffic simulation software. The results show that INAMAS is able to handle different traffic scenarios with competitive performance (in terms of vehicle queue lengths and waiting times), and that it is particularly more successful than the other controllers in dealing with extreme situations involving blocked approaches and high traffic volumes.

Adaptive artificial immune networks for mitigating DoS flooding attacks

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.

An artificial immune network based novel approach to predict short term load forecasting

Recent trends of Short-Term Load Forecasting (STLF) is a key issue to regulate power in the electricity market. Many researchers have performed research in this area but it still needs an accurate and robust load forecast method. In this paper, we propose a novel Artificial Immune Network (AIN) based approach to predict forecast load depending on last three days’ mean actual load. The approach creates an immune memory using time series to forecast one day ahead hourly loads. The method takes hourly loads separately as an individual daily time series and considers it as an antigen, an affinity is calculated between an antigen and antibody in Immune Networks (INs). A cross reactivity threshold is used to find the appropriate cluster for an antigen in an immune network. The historical dataset of Poland is trained and tested by this method which predicts more accurately compare with most recent existing STLF methods, such as simple nearest neighbor (NN), Multilayer Perceptron (MLP), Fuzzy Estimators (FE) and Artificial Immune System (AIS).

Artificial Immune Classifier Based on ELLipsoidal Regions (AICELL) †

Pattern classification is a central problem in machine learning, with a wide array of applications, and rule-based classifiers are one of the most prominent approaches. Among these classifiers, Incremental Rule Learning algorithms combine the advantages of classic Pittsburg and Michigan approaches, while, on the other hand, classifiers using fuzzy membership functions often result in systems with fewer rules and better generalization ability. To discover an optimal set of rules, learning classifier systems have always relied on bio-inspired models, mainly genetic algorithms. In this paper we propose a classification algorithm based on an efficient bio-inspired approach, Artificial Immune Networks. The proposed algorithm encodes the patterns as antigens, and evolves a set of antibodies, representing fuzzy classification rules of ellipsoidal surface, to cover the problem space. The innate immune mechanisms of affinity maturation and diversity preservation are modified and adapted to the classification context, resulting in a classifier that combines the advantages of both incremental rule learning and fuzzy classifier systems. The algorithm is compared to a number of state-of-the-art rule-based classifiers, as well as Support Vector Machines (SVM), producing very satisfying results, particularly in problems with large number of attributes and classes.

Cloud Model-Based Artificial Immune Network for Complex Optimization Problem.

This paper proposes an artificial immune network based on cloud model (AINet-CM) for complex function optimization problems. Three key immune operators—cloning, mutation, and suppression—are redesigned with the help of the cloud model. To be specific, an increasing half cloud-based cloning operator is used to adjust the dynamic clone multipliers of antibodies, an asymmetrical cloud-based mutation operator is used to control the adaptive evolution of antibodies, and a normal similarity cloud-based suppressor is used to keep the diversity of the antibody population. To quicken the searching convergence, a dynamic searching step length strategy is adopted. For comparative study, a series of numerical simulations are arranged between AINet-CM and the other three artificial immune systems, that is, opt-aiNet, IA-AIS, and AAIS-2S. Furthermore, two industrial applications—finite impulse response (FIR) filter design and proportional-integral-differential (PID) controller tuning—are investigated and the results demonstrate the potential searching capability and practical value of the proposed AINet-CM algorithm.

THE METHODS OF ARTIFICIAL INTELLIGENCE FOR MALICIOUS APPLICATIONS DETECTION IN ANDROID OS

This paper presents and discusses a method for Android’s applications classification with the purpose of malware detection. Based on the application of an Artificial Immune System and Artificial Neural Networks we propose the “antivirus” system especially for Android system that can detect and block undesirable and malicious applications. This system can be characterized by self-adaption and self-evolution and can detect even unknown and previously unseen malicious applications. The proposed system is the part of our team’s big project named “Intelligent Cyber Defense System” that includes malware detection and classification module, intrusions detection and classification module, cloud security module and personal cryptography module. This paper contains the extended research that was presented during the IEEE 8th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS’2015) [1].

A Combination of Artificial Neural Network and Artificial Immune System for Virus Detection

In this paper, we propose an Artificial Neural Immune Network (ANIN) for virus detection. ANIN is a combination of Artificial Neural Network (ANN) and Artificial Immune Network (AiNet). In ANIN, each ANN is considered as a detector. A pool of initial detectors then undergoes a mature process, called AiNet, to improve its recognizing ability. Thus, more than one ANN objects can cooperate to detect malicious code. The experimental results show that ANIN can achieve a detection rate of 87.98% on average with an acceptable false positive rate.

Alpha matting with image pixel correlation

Alpha matting aims at estimating the foreground opacity matte in an image. It is critical to find the best known samples for foreground and background color of unknown pixels in color sampling-based matting approaches. Most matting approaches can only select color sample for each pixel each time, which prevent them from maintaining the same correlation in image pixels. In particular, they may fail to collect appropriate samples from complex images and thus lead to artifacts. In order to solve the problem, we present a correlation-based sampling method in which the image pixel correlation is employed in color sampling and optimal sample selection for the alpha matte estimation of the image. First, the foreground and background colors of sample set can completely cover the color of unknown pixels to avoid missing the true samples. This is accomplished by artificial immune network adaptively learning the image correlation in unknown pixels. Besides, we propose the sample selection process as a global optimization problem with image correlation. All unknown pixels are treated as a high-dimensional input variable, particle swarm optimization algorithms is employed to solve the global optimization problem selecting the best sample pairs for all unknown pixels. The experimental study on images dataset shows that image pixels correlation is effective to improve matting, and that our matting results are comparable to some recent approaches.

Artificial immune algorithm applied to distribution system reconfiguration with variable demand

This paper presents a new methodology to solve the reconfiguration problem of electrical distribution systems (EDSs) with variable demand, using the artificial immune algorithm Copt-aiNet (Artificial Immune Network for Combinatorial Optimization). This algorithm is an optimization technique inspired by immune network theory (aiNet). The reconfiguration problem with variable demand is a complex problem of a combinatorial nature. The goal is to identify the best radial topology for an EDS in order to minimize the cost of energy losses in a given operation period. A specialized sweep load flow for radial systems was used to evaluate the feasibility of the topology with respect to the operational constraints of the EDS and to calculate the active power losses for each demand level. The algorithm was implemented in C++ and was evaluated using test systems with 33, 84, and 136 nodes, as well as a real system with 417 nodes. The obtained results were compared with those in the literature in order to validate and prove the efficiency of the proposed algorithm.