Artificial Immune Algorithm Research Articles

A Multi-Objective Permanent Basic Farmland Delineation Model Based on Hybrid Particle Swarm Optimization

The delimitation of permanent basic farmland is essentially a multi-objective optimization problem. The traditional demarcation methods cannot simultaneously take into account the requirements of cultivated land quality and the spatial layout of permanent basic farmland, and it cannot balance the relationship between agriculture and urban development. This paper proposed a multi-objective permanent basic farmland delimitation model based on an immune particle swarm optimization algorithm. The general rules for delineating the permanent basic farmland were defined in the model, and the delineation goals and constraints have been formally expressed. The model introduced the immune system concepts to complement the existing theory. This paper describes the coding and initialization methods for the algorithm, particle position and speed update mechanism, and fitness function design. We selected Xun County, Henan Province, as the research area and set up control experiments that aligned with the different targets and compared the performance of the three models of particle swarm optimization (PSO), artificial immune algorithm (AIA), and the improved AIA-PSO in solving multi-objective problems. The experiments proved the feasibility of the model. It avoided the adverse effects of subjective factors and promoted the scientific rationality of the results of permanent basic farmland delineation.

Optimization of Microservice Composition Based on Artificial Immune Algorithm Considering Fuzziness and User Preference

Microservices is a new paradigm in cloud computing that separates traditional monolithic applications into groups of services. These individual services may correlate or cross multi-clouds. Compared to a monolithic architecture, microservices are faster to develop, easier to deploy, and maintain by leveraging modern containers or other lightweight virtualization. To satisfy the requirements of end-users and preferences, appropriate microservices must be selected to compose complicated workflows or processes from within a large space of candidate services. The microservice composition should consider several factors, such as user preference, correlation effects, and fuzziness. Due to this problem being NP-hard, an efficient metaheuristic algorithm to solve large-scale microservice compositions is essential. We describe a microservice composition problem for multi-cloud environments that considers service grouping relations and corresponding correlation effects of the service providers within intra- or inter-clouds. We use the triangular fuzzy number to describe the uncertainty of QoS attributes, the improved fuzzy analytic hierarchy process to calculate multi-attribute QoS, construct fuzzy weights related to user preferences, and transform the multi-optimal problem into a single-optimal problem. We propose a new artificial immune algorithm based on the immune memory clone and clone selection algorithms. We also introduce several optimal strategies and conduct numerical experiments to verify effects and efficiencies. Our proposed method combines the advantages of monoclone, multi-clone, and co-evolution, which are suitable for the large-scale problems addressed in this paper.

Solving forest harvesting problem with artificial intelligence approaches: An example in Taiwan

In this paper, we study the forest harvesting problem (FHP). A forest is assumed to be divided into several identical square units, and each unit has its harvesting value based on its type. Harvesting a unit will affect the growth and values of its neighboring units. In this FHP, the best harvesting plan of a unit must be identified to maximize three various objectives simultaneously. The FHP is a multiobjective mathematical and an NP-hard problem. We apply three artificial intelligence algorithms, namely, immune algorithm, genetic algorithm, and particle swarm optimization, for maximizing the weighted objective to solve the FHP. We also solve the following two sets of test problems: (i) a set of randomly generated FHP problems and (ii) a practical problem in Taiwan. Numerical results show the performance of the three algorithms for the test problems. Finally, we compare and discuss the effects of various weights for the three objectives.

Application of artificial immune system algorithm for simultaneous minimisation of multiple objectives in single row facility layout problems

Application of artificial immune system algorithm for simultaneous minimisation of multiple objectives in single row facility layout problems

Hybrid Energy Scheduling in a Renewable Micro Grid

In the present days, the society has been facing a lot of challenges in the energy scenario, as their dependency increases in that crisis that is to be given greater concern. As fossil fuels are turned out to be too expensive or it may be phased out, in spite of large investments, researchers suggest the renewable energy sources as a supplement for this issue. A microgrid which connects the generation units with the electrical power network and also the utility area results in the efficient utilization. The efficiency and flexibility of the power system can be optimized by installing microgrid. It combines the sources of heat and power (CHP) with renewable energy which includes wind and photovoltaic power that implies a reliable and controllable power supply. As power storage equipment’s and electric vehicles (EV) enhances the bidirectional power flow, the optimization of scheduling is needed for the EV and demand side management (DSM).In this work, with the CHP microgrid, an optimal scheduling model of the network is proposed with EV and DSM.The minimum operation cost is considered as an objective function and the optimization variable is the output of each source. A simulation study which improves the capability global search using hybrid Artificial Immune algorithm is put forward for higher feasibility.

WEDM of Cu/WC/SiC composites: development and machining parameters using artificial immune system

A systematic read on evaluating the machining characteristics of wire cut electrical discharge machining (WEDM) using analysis of variance (ANOVA) and multilinear regression model based multi objective optimization is provided during this analysis article. The current work explores, the surface roughness of copper metal matrix composite (MMCs) is minimized by optimizing the process parameters like spark on time, spark off time, peak current and wire feed. Taguchi’s L9 orthogonal array has been used to conduct the experiments for two samples having a different composition to measure the surface roughness. The order of significance of parameters on surface roughness (Ra) for sample 1 and 2 MMCs were found using ANOVA and a multilinear regression model (MLRM) was developed to predict the Ra value. The new contribution in the present work is that, the coefficients of MLRM were optimized using artificial immune system algorithm with the objective of minimizing the mean absolute percentage error. Finally, the optimum process parameters were obtained to minimize the surface roughness and reported that the reduced value of Ra for 2.5% and 5% WC Copper MMCs were 0.9 μm and 1.1 μm, respectively later which were established by confirmation experiments.

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.

Hybrid Artificial Immune System-firefly Algorithm Technique for Optimal DG Capacity and Operational Strategy in Distribution System

This paper presents a study on hybrid optimization technique for optimal distributed generation (DG) capacity and operational strategy in distribution system. In this study, hybrid method namely Artificial Immune System-Firefly Algorithm (AISFA) is developed to determine the optimal size of the schemes respectively in the distribution system. The Firefly Algorithm (FA) which is a type of meta-heuristic algorithm is inspired by the blinking or flashing behaviour of fireflies that is embedded into Artificial Immune System (AIS) algorithm. The aim of this study is to develop the AISFA algorithm in order to improve the voltage profile and minimize losses of distribution system between the different operational strategy and types of DG. The types of DG include DG type 1, DG type 2, and DG type 3. The proposed technique was verified on IEEE 69-bus test system and the program was developed using the MATLAB programming software. The results showed a significant loss reduction in the line losses and voltage profile improvement has been obtained for optimal DG capacity and operational strategy in distribution system. From the simulation, the results were recorded in terms of the total losses and minimum voltage for the system. The results of the optimisation process of DG are utilized for the assistance of power system operators and planners. The power system planner can adopt the suitable sizes and locations from the obtained result for the planning of utility in term of economic and geographical consideration.

Comprehensive approach for distribution system planning with uncertainties

This study presents a comprehensive approach for the distribution system expansion planning (DSEP) that considers investment, operation, carbon dioxide emission and reliability costs, as well as uncertainties over load demand and wind-based distributed generation. A restoration strategy is taken into account for obtaining the energy not supplied under the ‘N − 1’ criterion and the corresponding reliability cost over a planning horizon. The problem is modelled as mixed-integer non-linear programming by using the artificial immune system algorithm. Also, two methods to represent uncertainties are applied and compared: an interval technique through an interval power flow and a scenario-based approach. Network constraints are considered, as the limits of current, voltage and power from substations, as well as the obtaining of radial and connected topology. The novelty of the proposed interval DSEP consists of handling the uncertainties over operation in an efficient manner through a single step, instead of the several deterministic evaluations of the scenario-based approach. Numerical results are presented for well known test systems, which show the potentials of the proposed approach.

Comparisons on Intrusion Detection and Prevention Systems in Distributed Databases

With the use of distributed systems, different users can instantly access data from different locations and perform some operations on the data. However, the unauthorized access of multiple users to the system from different points at the same time can lead to dangerous results in terms of data security and confidentiality of the data. This study is based on intrusion detection and prevention systems built on distributed databases and classifies the methods used to analyze and evaluate successes comparatively. It is observed that the artificial immunity algorithm we have described in artificial intelligence techniques, which is one of the methods classified as three categories, gives more successful results compared to the other techniques mentioned in the data mining and statistical methods.

Damage diagnosis in an isotropic structure using an artificial immune system algorithm

This work proposes a recent methodology for developing structural health monitoring based on intelligent computing techniques, with the purpose of detecting structural damages in aircrafts using artificial immune systems with negative selection. To assess this methodology, an experimental setup was built with piezoelectric transducers attached to an aluminum plate (which represents a wing of an airplane), which work both as actuators and sensors, where signals were acquired in normal and damage situations. The results show robustness and accuracy for the new methodology proposed.

Joint Optimization of User Association and Resource Allocation for Millimeter-Wave Integrated Backhaul and Access Network

Since the millimeter wave integrated backhaul and access network(mm-Wave IBAN) can divide the resource ratio between the access and the backhaul link as needed, there is a huge advantage in the improvement of the utilization rate for 5G communication network. A joint optimization method of user association and resource allocation is proposed and implemented for the mm-Wave IBAN from the perspective of the maximization of the transmission traffic in the whole network. The joint optimization problem of the user association and the resource allocation is formulated as a combined non-convex optimization problem, and then the problem is decomposed into two sub-problems. The first sub-problem, which is aimed at the maximization of the whole access rate, is the problem of the user association under the condition of the match between the access rate and backhaul rate. The second sub-problem, which is aimed at the maximization of the whole traffic of the network, is the problem of the resources allocation between the access link and backhaul link. The artificial immune optimization algorithm (IOA) is used to solve the first sub-problem. After that, the optimal transmission resource ratio between the access link and backhaul link is obtained according to the differentiating of the expression for the whole traffic. The simulation results show that the proposed method has more gains in the improvement of the whole network traffic when compared with the user association mechanism based on the nearest distance.

Application of bionic and immune algorithms for the solution of ambiguous problems of transportation routing

The main objective of the study is to develop efficient methods and algorithms based on the operating principles of the immune system and evolutionary search for further search of a global optimal solution of optimization problems. It is suggested to integrate the modified evolutionary and immune algorithms to solve the set task. Transportation routing is the priority direction in the field of information technologies, industry, transport, and communication systems. Due to increasing demand of enterprises, it is impossible to ensure the efficiency of transport operations without information and software systems for analysis, planning and support of commercial solutions. Therefore, further study of artificial immune systems and algorithms and their integration with genetic algorithms aimed to solve various optimization problems and identify the class of their optimization, for which such systems and algorithms can be applied, as well as to modify the method for new applications, seems quite relevant.

The application of artificial immune algorithm to earthquake relief route planning

After an extreme earthquake attacks an urban area with many mountains, the main objective of a search and rescue operation is to minimize the number of fatalities. Therefore the task of transportation rescue resources to operational areas is of great importance to disaster managers. This paper presents a quick path planning method based on Artificial Immune Algorithm (AIA) and helicopter operation performance in order to design an optimal path for an operational area. First, a simulation of an earthquake is implemented in environment only including terrain threat. Second, a more complex model contains terrain, weather, building and communication threats simulation is executed and the resulting performance measures are evaluated by considering the survival time and total value for taken out entrapped occupants in the disaster area. Additionally, the best parameters of planning path for dual helicopters to an operational area are determined. Further work will be dedicated to adding real 3D terrain model into the current threat model.

Focusing and polarized modulation of a laser passing through a multi-core fiber

Owing to the coupling and superposition of the modes, a random speckle will be generated in case a laser beam passes through a multi-core fiber (MCF). Based on the feedback-based wavefront shaping technique, the optimized phase map can be obtained by the artificial immune algorithm. The random speckle can be transformed into a focal pattern by imposing the optimized phase map on the spatial light modulator. It is shown that the polarization state of the focal spot can be controlled and a linearly polarized focal spot can be generated. In addition, we further demonstrate the evolution of the intensity and the polarization of the focal spot along the propagation distance. The results are useful for the application of the MCF in biological and medical domains.

An artificial immune and incremental learning inspired novel framework for performance pattern identification of complex electromechanical systems

Performance pattern identification is the key basis for fault detection and condition prediction, which plays a major role in ensuring safety and reliability in complex electromechanical systems (CESs). However, there are a few problems related to the automatic and adaptive updating of an identification model. Aiming to solve the problem of identification model updating, a novel framework for performance pattern identification of the CESs based on the artificial immune systems and incremental learning is proposed in this paper to classify real-time monitoring data into different performance patterns. First, an unsupervised clustering technique is used to construct an initial identification model. Second, the artificial immune and outlier detection algorithms are applied to identify abnormal data and determine the type of immune response. Third, incremental learning is employed to trace the dynamic changes of patterns, and operations such as pattern insertion, pattern removal, and pattern revision are designed to realize automatic and adaptive updates of an identification model. The effectiveness of the proposed framework is demonstrated through experiments with the benchmark and actual pattern identification applications. As an unsupervised and self-adapting approach, the proposed framework inherits the preponderances of the conventional methods but overcomes some of their drawbacks because the retraining process is not required in perceiving the pattern changes. Therefore, this method can be flexibly and efficiently used for performance pattern identification of the CESs. Moreover, the proposed method provides a foundation for fault detection and condition prediction, and can be used in other engineering applications.

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.

Parameter Matching Analysis of Hydraulic Hybrid Bergepanzers Based on RBF-Adaptive Artificial Immune Algorithm

Due to the multiple types of support tasks and high-energy efficiency equipment, energy saving research in a Bergepanzer has attracted much attention in recent years. A hydraulic hybrid system is an effective way for these problems of Bergepanzers. The initial problem is to optimize the parameter optimization-matching for a new hydraulic hybrid Bergepanzers (NHHB), which is a relatively complex and variable time-varying nonlinear system. In this paper, an RBF-adaptive artificial immune algorithm (RBF&AAIA) is presented to solve the parameter optimization-matching problem, and the performance of algorithm is analyzed. Finally, the RBF&AAIA is successfully used for the NHHB to optimize the parameters of key components for the minimum energy consumption of system, and the optimal parameter matching group is obtained.

Dynamic risk identification safety model based on fuzzy support vector machine and immune optimization algorithm

Dynamic risk identification is used to predict future risk based on known risk information as early as possible. Risk identification technology based on the fuzzy support vector machine (FSVM) model can more comprehensively and automatically identify possible risks through a learning model, and this technology has become the main method for dynamic risk identification. To improve the efficiency and accuracy of recognition, the selection of parameters of the FSVM is very important. An artificial immune algorithm (AIA), an effective stochastic global optimization technology, has advantages of high accuracy and fast convergence speed and does not easily fall into a local optimal solution. Therefore, this paper proposes a new dynamic risk identification model based on the integration of the FSVM and immune optimization algorithm (IOA). By combining the advantages of multi-class FSVM classification and using an artificial IOA to select the FSVM parameters, experiments on the Heart-Disease data set are conducted to demonstrate the effectiveness of the model.

Research on Location and Capacity Optimization Method for Electric Vehicle Charging Stations Considering User’s Comprehensive Satisfaction

The development of electric vehicles has significant value for the sustainable utilization of energy resources. However, the unreasonable construction of charging stations causes problems such as low user satisfaction, waste of land resources, unstable power systems, and so on. Reasonable planning of the location and capacity of charging stations is of great significance to users, investors and power grids. This paper synthetically considers three indicators of user satisfaction: charging convenience, charging cost and charging time. Considering the load and charging requirements, the model of electric vehicle charging station location and volume is established, and the model based on artificial immune algorithm is used to optimize the solution. An empirical analysis was conducted based on a typical regional survey. The research results show that increasing the density of charging stations, lowering the charging price and shortening the charging time can effectively improve user satisfaction. The constructed site and capacity selection optimization solving model can scientifically guide charging station resource allocation under the constraints of the optimal user comprehensive satisfaction target, improve the capacity of scientific planning and resource allocation of regional electric vehicle charging stations, and support the large-scale promotion and application of electric vehicles.