Interactive Genetic Algorithm Research Articles

Customer-centered co-design modularization: the skirt design on mobile application

With the development of mobile technology, customer-centered co-design modularization (CCCM) has been studied by researchers and brand operators. In contrast, in the field of skirt design, CCCM on mobile application has been largely ignored. The purpose of this study is to develop a customer-centered co-design modularization on skirt that enables customers to co-design skirt on mobile application. On the basis of analytic hierarchy theory and interactive genetic algorithm, CCCM is consisted of two categories, such as skirt parts (design attributes) and communicating parts (behavior attributes). Skirt parts are determined by knowledge classification. Communicating parts are supported by recommending, consulting, evaluating among customers, consultant, and expert. The customer-centered co-design modularization was conducted and proved by a mathematical model. Compared to online shopping, the proposed CCCM is a good approach to involve stakeholders (customer, consultant, and expert) to design together who can communicate on mobile application.

Interactive Genetic Algorithm Oriented toward the Novel Design of Traditional Patterns

To create alternative complex patterns, a novel design method is introduced in this study based on the error back propagation (BP) neural network user cognitive surrogate model of an interactive genetic algorithm with individual fuzzy interval fitness (IGA-BPFIF). First, the quantitative rules of aesthetic evaluation and the user’s hesitation are used to construct the Gaussian blur tool to form the individual’s fuzzy interval fitness. Then, the user’s cognitive surrogate model based on the BP neural network is constructed, and a new fitness estimation strategy is presented. By measuring the mean squared error, the surrogate model is well managed during the evolution of the population. According to the users’ demands and preferences, the features are extracted for the interactive evolutionary computation. The experiments show that IGA-BPFIF can effectively design innovative patterns matching users’ preferences and can contribute to the heritage of traditional national patterns.

Application of EEG and Interactive Evolutionary Design Method in Cultural and Creative Product Design.

In order to design a cultural and creative product that matched the target image, this paper proposed to use EEG, interactive genetic algorithm (IGA), and back propagation neural network (BPNN) to analyze the users' image preferences. Firstly, the pictures of cultural elements were grouped according to the pleasantness value and emotional state by PAD emotion scale, and the brain waves induced by the pictures of cultural elements with different pleasure degree were recorded by electroencephalograph. Then, the preference of cultural elements was obtained according to the theory of frontal alpha asymmetry. Secondly, the semantic difference method was used to carry out questionnaire survey to users, and the factor analysis method was used to statistically analyze the survey results to extract the perceptual image semantics of users for cultural and creative products. Thirdly, an interactive evolutionary design system based on IGA and BPNN was constructed. According to the cultural elements preferred by users, the designer designed the initial set of morphological characteristics, and the fitness value was determined according to the degree of user preference for the image semantics. Meanwhile, in order to reduce the fatigue caused by users' interaction evaluation, BPNN was introduced to simulate artificial evaluation. Finally, the proposed method was verified by the practice of flavoring bottle design. User preference requirement could be used as feedback information to help designers understand users' design emotional need and generate design schemes that satisfied the users' perceptual image.

DPM-IEDA: Dual Probabilistic Model Assisted Interactive Estimation of Distribution Algorithm for Personalized Search

An interactive evolutionary algorithm (IEA) is powerful for solving personalized search when the user's preference can be well caught, expressed, and applied in the process of searching. Hybrid recommendation by articulating the content-based and collaborative filtering techniques is popular and effective for the personalized recommendation, but has not been developed to improve the performance of IEA for fulfilling the personalized search. Accordingly, we here propose an enhanced interactive estimation of distribution algorithm by designing dual-probabilistic models based on the hybrid recommendation for personalized search. The concept of hybrid personalized search is first defined from the viewpoint of using not only the historical search information but also the social or group preference. A dual-probabilistic model by sufficiently combining the content-based and collaborative filtering is presented and used to design the effective interactive estimation of distribution algorithm (IEDA). The probabilistic model is directly combined with the initialization of IEDA for illuminating the sparsity of the traditional IEA in encoding. The effectiveness of the proposed algorithm in fast and efficient searching with a lower computational cost is experimentally illustrated by two typical personalized searches on movies and TV series described with documents.

A user-centered side silhouette generation system for sedan cars based on shape templates

A tool for the generation of side silhouettes for sedan cars is developed in this work; this enables ordinary people to produce personalized silhouettes that they prefer. Multiple silhouettes are collected from different car brands and analyzed in an off-line step. The silhouette is partitioned into nine characteristic lines, each of which is represented by either quadratic or cubic Bezier curves. Furthermore, geometric properties, such as geometric constraints and lower/upper bounds for the characteristic line dimensions, are determined. Next, a characteristic line is sampled via a spatial simulated annealing approach, while minimizing the Audze–Eglais potential energy between the sampled characteristic lines generated. These samples are called line templates or shape templates. A car side silhouette is encoded by a sequence of parameters, such as characteristic line lengths and heights and line template indices (i.e., 21 parameters in total). Once the values for these parameters are set, the silhouette can be generated. A user interface is provided for users to develop personalized car side silhouettes. According to the user study performed in this work, the developed tool enables users to obtain more desired/preferred silhouette(s) compared to those obtained using an interactive genetic algorithm.

Product evolutionary design driven by environmental performance

This article is in terms of product environmental performance demand and proposes four structure evolutionary operation modes which include combined evolutionary method, decomposition evolutionary method, replacement evolutionary method, and material-changing evolutionary method to express the structure evolutionary process of products. Through the quotient space theory and proposed method combined with probability statistics, probability mapping from environmental performance to product structure is established and the evolutionary individuals with outstanding environmental performance are listed. Through the analysis to the specific conditions of the evolutionary individuals, the design constraints are extracted, and the objective function of environmental performance is established. This article presents an interactive genetic algorithm as evolutionary algorithm and combines it with four structure evolutionary operation modes to conduct corresponding gene manipulation and generates evolutionary product. Finally, the proposed methodology is successfully applied to engine gear chamber and the environmental impact is found to be better than before evolution.

Evolving Behaviors for an Interactive Cube-Based Artifact

In the present paper we explore the idea of combining computation power and the availability of ordinary art spectators in order to produce new interactive art works. This is investigated for a particular application, which consists of producing new behaviors for a programmable art apparatus named C3 Cubes. Given the nature of the problem and some difficult challenges to be dealt with, an Interactive Evolutionary Computation (IEC) approach was devised. Furthermore, it was necessary to adopt a surrogate function method for approximating the user's preferences and to implement a Web-based virtual simulation environment for speeding up the generation and the evaluation of C3 Cubes projects. The integration of all these elements is crucial for producing new user-guided cube projects with interesting behaviors. The main approaches experimented in this research and the proposed design solutions are useful to solving similar problems in other domain areas, for example, in the context of game design.

A computer-aided coloring method for virtual agents based on personality impression, color harmony, and designer preference

Endowing virtual agents with desired personality impression is one of the most important considerations when designers create agents. Color appearance of agents has been suggested to be able to convey personality impression but how to design the right color appearance to obtain the desired personality impression is still a challenge to unexperienced designers, since they have little information on how colors evoke personality impression; moreover, the design become more difficult when multiple design goals need to be considered simultaneously. To respond to the challenge, we propose an automated method for creating color appearance of agents using a multi-objective interactive genetic algorithm. The method can automatically generate the desired color appearance that can convey desired personality impression, has harmonious color combinations, and express designers' preference. The experimental results show that our method can lower the barrier for designers and speed up the design process.

Multiobjective and Interactive Genetic Algorithms for Weight Tuning of a Model Predictive Control-Based Motion Cueing Algorithm.

Driving simulators are effective tools for training, virtual prototyping, and safety assessment which can minimize the cost and maximize road safety. Despite the aim of a realistic motion generation for the impression of real-world driving, motion simulators are bound in a limited workspace. Motion cueing algorithms (MCAs) aim to plan an acceptable motion feeling for drivers, without infringing the simulated boundaries. Recently, model predictive control (MPC) has been widely used in MCAs; however, the tuning process for finding the best weights of the MPC optimization is still a challenge. As there are several objectives for the optimization without any standard weighting for solution evaluations, a nonbiased scalarization of solutions for the purpose of comparison is impossible. In this paper, a clear method for obtaining the best MPC weighting has been proposed. This method searches for the best tune of MPC cost function weights, reduces the user burden for weight tuning while receiving feedback from the user satisfaction. The MPC-based MCA weights are optimized using a multiobjective genetic algorithm (GA) considering objectives, such as minimization of motion inputs (linear acceleration and angular velocity), input rates, output displacements and the sensed motion errors. Any process based on trial-and-error has been omitted. The adjusted weights have to satisfy a set of predefined conditions related to maximum tolerated error and maximum displacement. The obtained Pareto-front is used for decision making via an interactive GA (IGA), aiming for maximization of the decision maker's satisfaction. A Web interface is developed to interact with the IGA and to influence the region of searching. Simulation results show the superiority of the proposed method compared with the previous empirical tuning method. The sensed motion error is minimized using the proposed method and with the same available workspace, a more realistic motion can be rendered to the driver.

Interactive multi-objective evolutionary optimization of software architectures

While working on a software specification, designers usually need to evaluate different architectural alternatives to be sure that quality criteria are met. Even when these quality aspects could be expressed in terms of multiple software metrics, other qualitative factors cannot be numerically measured, but they are extracted from the engineers know-how and prior experiences. In fact, detecting not only strong but also weak points in the different solutions seems to fit better with the way humans make their decisions. Putting the human in the loop brings new challenges to the search-based software engineering field, especially for those human-centered activities within the early analysis phase. This paper explores how the interactive evolutionary computation can serve as a basis for integrating the humans judgment into the search process. An interactive approach is proposed to discover software architectures, in which both quantitative and qualitative criteria are applied to guide a multi-objective evolutionary algorithm. The obtained feedback is incorporated into the fitness function using architectural preferences allowing the algorithm to discern between promising and poor solutions. Experimentation with real users has revealed that the proposed interaction mechanism can effectively guide the search towards those regions of the search space that are of real interest to the expert.

Development of an Automatic Crack Inspection System for Concrete Tunnel Lining Based on Computer Vision Technologies

This paper presents an automatic crack inspection system for concrete tunnel lining based on image processing technique and computer vision. The system includes a video image acquisition device, an image stitching software, and a crack detection software. Firstly, the video image acquisition device uses six video cameras and three illuminators mounted on a steel framework which is capable of sliding from side to top of the inspecting vehicle to shoot the full surface of the tunnel lining. Secondly, the image stitching software based on image matching technique was developed to create layout panorama from the tunnel lining surface images, making it easier to visualize a large and detailed section of the tunnel lining. Finally, we propose a semi-automatic crack detection software relied on a combination of image processing technique and interactive genetic algorithm (iGA) to crack detection for concrete surface images of the tunnel lining. Experimental results demonstrate the effectiveness of the proposed method.

Research progress survey on interactive evolutionary computation

We report our research progress on interactive evolutionary computation (IEC). Following description of IEC features, we present our research on IEC user modeling, acceleration of IEC search, several IEC frameworks, evolutionary multi-objective optimization with IEC, and IEC for human science. IEC research is categorized into three fields in general; major part of IEC papers is IEC application-oriented research; almost all the others are research that aims to reduce IEC user fatigue; and very little work researches the use of IEC for human science. In particular, IEC is a data analysis and processing method and tool for the discovery of human psychological and physiological knowledge. We include several of our IEC application-oriented research projects in this paper, and focus on two other research directions, i.e., IEC algorithm research to reduce user fatigue, and IEC for human science research.

An interactive genetic algorithm for portfolio optimization considering the decision maker’s preference

Generally, investor has his/her own preference toward risk and return. To develop a decision support system, it should be designed to reflect the investor’s preference structure. An Interactive Genetic Algorithm (iGA) is an advanced genetic algorithm method that reflect the decision maker’s subjective preference structure.We propose a method for supporting investor’s judgement based on portfolio optimization using iGA that present the best compromised solution set that satisfy Pareto optimality and investor’s subjective preference structures toward risk and/or return. We develop a system that present investment plan for the investors and show an example to apply the system to the real world problems.

A method for product personalized design based on prospect theory improved with interval reference

Abstract How to rapidly and accurately response to customers' demands is the key in product personalized design, which could be perfectly achieved by interactive genetic algorithm (IGA) emphasizing on collaborative interaction and user participation through human–computer interaction. However IGA widely adopted now neglects the impact of decision makers' psychological changes on decision-making behaviors. It's hard to capture customers' demands and grasp their preferences, generating slow convergence speed and heavy user fatigue. Thus an interactive genetic algorithm based on prospect theory improved with interval reference (IGA-PTIR) is proposed in the paper. In IGA-PTIR, an evolutionary individual's fitness value is represented by interval prospect value of prospect theory improved with interval reference instead of single reference in order to correct individual fitness deviation caused by ambiguity and uncertainty of user cognition. An interval number sorting strategy based on dominance degree is then adopted to rank individuals, which makes it possible to perform subsequent operations of selection, crossover and mutation. In the paper, IGA-PTIR is applied into automobile wheel hub design system and compared with traditional interactive genetic algorithms (TIGA). Experimental results indicate that the proposed algorithm can increase convergence speed, ease user fatigue, and improve search performance to a large extent.

A FIREFLY APPROACH FOR PRIORITIZING FUNCTIONAL AND NONFUNCTIONAL REQUIREMENTS

The prioritization of requirements is an important task in software development to implement requirements based on budget, time, customer expectations and practical constraints. An Interactive Genetic Algorithm (IGA) has been used to prioritize requirements by satisfying constraints. IGA sometimes provides a poor ranking due to population divergence. This is resolved in this paper by utilizing Firefly algorithm. The methods for prioritizing both functional and non functional requirements together are very less and have several drawbacks like of considering a small number of non functional requirements and applying less ranking weight. The firefly algorithm provides random prioritization initially then improves the prioritization iteratively by minimizing disagreement between priorities and constraints while maximizing agreement between priority and customer satisfaction. The sum of disagreement is considered as light intensity of firefly. The population of firefly generates an ordered list of functional and non functional requirements. The fitness value (intensity) is found for all fireflies then each firefly updates its position towards the best search of a firefly until all fireflies obtain same fitness value. The experimental result proves that the firefly based prioritization outperforms than Genetic Algorithm based prioritization.

Music Melodies Suited to Multiple Users' Feelings Composed by Asynchronous Distributed Interactive Genetic Algorithm

This article aims to compose music melody suited for multiple users' feelings by employing parallel Distributed Interactive Genetic Algorithm (DIGA). In the DIGA, each user proceeds into a general Interactive Genetic Algorithm (IGA) process by evaluating solution candidates subjectively. In some generations, individuals in IGA are exchanged between the users. With the exchange, each of the users is affected by other users' feelings. As a result, obtaining good solutions suited for all users is expected. The authors conducted listening experiments for investigating the efficiency of the DIGA for composition of a music melody. Two experimental conditions with and without the exchange were employed. Ten people participated in the experiment as subjects, and were paired for the IGA task. The experimental results showed that a higher fitness was obtained in the final generation and similar melodies were obtained with the exchange.

On distributed user-centric memetic algorithms

A user-centric memetic algorithm (UcMA) represents an instance of the so-called interactive evolutionary computation, in which the subjacent algorithm that interacts with a human consists of a memetic algorithm (MA) that manages knowledge of the problem with the aim of accelerating the solution search process. UcMAs have been proved to be effective optimization methods to tackle problems that require human intervention (in the form of evaluations/decisions). This paper proposes two generic schemas to distribute a number of (interactive/proactive) UcMAs that act as independent agents and, eventually, synchronize to interchange information. These schemas can be instantiated via a number of parameters (including the cooperation topology) to develop novel 2-dimensional spatially structured cooperative UcMAs. These algorithms can be viewed as specific instances of the so-called parallel MAs but with the particularity that they are especially suited to dealing with combinatorial problems whose solving requires subjective evaluations. An experimental study over microarray ordering problems is done including distinct instances of an NP-hard problem with strong implications in biomedicine and molecular biology, namely the gene ordering problem. It is shown that some distributed UcMAs, especially those based on proactivity, which have been instantiated from our proposals, efficiently handle these problems.

Application of multi-objective genetic algorithm to aggregate production planning in a possibilistic environment

The present study is to develop an interactive possibilistic environment-based genetic algorithm for multi-product and multi-period aggregate production planning (APP). APP is the prerequisite in order to make material requirement planning and/or capacity requirement planning accurately. The present study attempts to minimise the production cost and the rate of changing in labour level where production costs, backordering cost, labour level changing cost, demand are considered as imprecise parameters. It is noted that all these imprecise parameters are defined by the triangular possibility distribution. As the overtime production capacity is the fraction of available regular time production capacity, it is defined separately to make the result more acceptable. The proposed methodology is finally applied to demonstrate an industrial case in order to justify the feasibility. The solution obtained by the proposed methodology is compared with other solutions in context with computation efficiency and solution practicability.

Portfolio Optimization by Fuzzy Interactive Genetic Algorithm

Portfolio Optimization by Fuzzy Interactive Genetic Algorithm

Affordance based interactive genetic algorithm (ABIGA)

Designers can involve users in the design process. The challenge lies in reaching multiple users and finding the best way to use their input in the design process. Affordance based design (ABD) is a design method that focuses in part on the perceived or existing interactions between the user and the artifact. The shape and physical characteristics of the product enable the user to perceive some of its affordances. The goal of this research is to use ABD, along with an optimization tool, to evolve the shape of products toward better perceived solutions using the input from users. A web application has been developed that evolves design concepts using an interactive multi-objective genetic algorithm (IGA) relying on the user assessment of product affordances. As a proof of concept, a steering wheel is designed using the application by having users rate specific affordances of solutions presented to them. The results show that the design concepts evolve toward better perceived solutions, allowing designers to explore more solutions that reflect the preferences of end users. Relationships between affordances and product design variables are also explored, revealing that specific affordances can be targeted with changes in design parameter values and highlighting the tie between physical characteristics and affordances.