Optimization Task

The ability to infer a person’s thoughts and intentions using purely physiological methods is not only one of the holy grails of modern neuroscience but at the heart of the rapidly developing field of neuro-marketing, which seeks to understand a consumer’s cognitions without reliance on self-report. The eyes and their movements are frequently described as a window to the mind, a view supported by the preferential looking paradigm which is most frequently used when self-report measures are infeasible, such as with infants or participants with learning difficulties. Evolutionary Computation is a field of computer science which applies the central concepts of Darwinian evolution, whereby an individual’s ability to survive and pass on it’s characteristics (through genetic information) to the next generation is determined by its fitness for purpose, in the form of an iterative, optimisation algorithm which can be used to search vast sets of possible solutions for the optimum. Visual Experimental Aesthetics, which attempts to understand the features of an image which directly influence a viewer’s preference for that stimulus, has always lacked an objective, external measure which can be used to explore complex, high-dimensional sets of images for such subjective preferences. By integrating the behavioural information from a preferential looking paradigm, which is used to evaluate fitness, with a real-time method for generating stimuli using a genetic representation which can be evolved over a number of generations, this thesis describes the development of a novel paradigm for use in subjective visual psychophysics and experimental aesthetics. The thesis establishes the method over a number of experiments using uni-dimensional and abstract multi-dimensional stimuli and concludes with an example of the paradigm applied to a commercial design question, using complex, high-dimensional photo-realistic stimuli. The potential for further development of this methodology in a variety of academic and real-world applications are discussed.

Arxiv preprint arXiv:0803.3186, 2008

Abstract: In this paper, we firstly present what is Interactive Evolutionary Computation (IEC) and rapidly how we have combined this artificial intelligence technique with an eye-tracker for visual optimization. Next, in order to correctly parameterize our application, we present results from applying data mining techniques on gaze information coming from experiments conducted on about 80 human individuals.

Proceedings of the 10th annual conference on Genetic and evolutionary computation - GECCO '08, 2008

Interactive Evolutionary Computation (IEC) has been applied to art and design problems where the fitness of an individual is at least partially subjective. Applications usually present a population from which the preferred individuals are selected before the usual evolutionary operations are performed to produce the next generation. Large population sizes and numbers of generations impose significant demands on the user. This paper proposes that selecting by means of eye movements could reduce user fatigue without sacrificing quality of fitness assessment. In the first experiment, an eye-tracker is used to capture fixations and confirm the reliability of such a measure of attention as a fitness driver for subjective evaluation such as aesthetic preference. In a second experiment, the robustness and efficiency of this technique is investigated for varying population sizes, presentation durations and levels of fitness sampling. The results and their consequences for future IEC applications are discussed.

IEEE International Conference on Fuzzy Systems, 2006

We describe two approaches to reducing human fatigue in Interactive Evolutionary Computation (IEC). A predictor function is used to estimate the human user's score, thus reducing the amount of effort required by the human user during the evolution process. The fuzzy system and four machine learning classifier algorithms are presented. Their performance in a real-world application, the IEC-based design of a micromachine resonating mass, is evaluated. The fuzzy system was composed of four simple rules, but was able to accurately predict the user's score 77% of the time on average. This is equivalent to a 51% reduction of human effort compared to using IEC without the predictor. The four machine learning approaches tested were k-nearest neighbors, decision tree, AdaBoosted decision tree, and support vector machines. These approaches achieved good accuracy on validation tests, but because of the great diversity in user scoring behavior, were unable to achieve equivalent results on the user test data.

Proceedings of the ISCIE International Symposium on Stochastic Systems Theory and its Applications, 2017

Interactive Evolutionary Computation (IEC) is known as an efficient method which reflects user's subjective preference on media contents. However, user's fatigue caused by repetitive evaluation tasks remains as a severe problem in IEC. The purpose of this study is to propose a new framework of IEC, continuous evaluation-based IEC (CEIEC) that continues user's evaluation tasks in many days. CEIEC allows the user's subjective evaluation day by day to have many evaluation times without severe fatigue, while conventional IECs performed user's task in one time in one day. This study also performed a listening experiment for investigating efficiencies of CEIEC. The target of search with CEIEC was to design a bright sign sound. Sixteen subjects participated in the listening experiment which is composed of tasks of three days: in the 1st and the 2nd days, the subjects performed a selection task throughout fifteen generations. Successive update of the solution was observed during these two days. In the 3rd day, the subjects evaluated three sign sounds with 7-point scale. These three sounds were picked up from the 0th, 14th, and 29th generations, respectively. The sound with the highest score was found in the 29th generation. These results show the efficiencies of CEIEC.

Gastroenterology, 2005

This paper has proposed a new interactive genetic algorithm (IGA) framework incorporating relevant feedback (RF), in which human evaluation is regarded as not only the fitness function of GA, but also the relevant score to instruct interactive machine learning. Thus, on the one hand, user's fatigue, the key issue of IGA, can be alleviated, since some individuals with higher preference weight are added in each generation through relevance feedback technology. On the other hand, the two mapping functions between the low-level parameter space and the high-level users' psychological space can be built during interactions. An instance of this frame, which uses support vector machine (SVM) as the machine learning method in RF, is also provided. The effectiveness of our approach is first evaluated through simulation tests using two benchmark functions. The experimental results show that the convergence speed of the proposal is much faster than that of normal IGA. Then, the approach is applied to retrieve images with emotion semantics queries. The subject experiments also demonstrate that the proposal algorithm can alleviate user fatigue. Furthermore, SVM constructs an individual emotion user model though learning.

Lecture Notes in Computer Science, 2012

This paper explores the value of eye-tracking data to assess user learning with interactive simulations (IS). Our long-term goal is to use this data in user models that can generate adaptive support for students who do not learn well with these types of unstructured learning environments. We collected gaze data from users interacting with the CSP applet, an IS for constraint satisfaction problems. Two classifiers built upon this data achieved good accuracy in discriminating between students who learn well from the CSP applet and students who do not, providing evidence that gaze data can be a valuable source of information for building user modes for IS.

2017

Multiple criteria decision making (MCDM) is a fundamental part of our daily lives. To support solving the problem with conflicting multiple criteria, several analysis methods for MCDM are hitherto proposed. Here, the choice of evaluation criteria is a key to successful decision-making support, including interactive assistance systems. With appropriate evaluation criteria, decision-support systems can help users find an importance weight on each of the criteria and organize their selection interests. This process of preference structuring is helpful for users who want to select a target from alternatives, particularly when they have uncertain preferences and have not yet detailed their needs enough to search targets using appropriate keywords. Here, the questions are how to prepare evaluation criteria beforehand and how to estimate user preferences by using these evaluation criteria. This thesis introduces aspects that represent “why the users look at items,” which provide possible v...

Journal of Electronic Imaging, 2013

We present an evolutionary adaptive eye-tracking framework aiming for low-cost human computer interaction. The main focus is to guarantee eye-tracking performance without using high-cost devices and strongly controlled situations. The performance optimization of eye tracking is formulated into the dynamic control problem of deciding on an eye tracking algorithm structure and associated thresholds/parameters, where the dynamic control space is denoted by genotype and phenotype spaces. The evolutionary algorithm is responsible for exploring the genotype control space, and the reinforcement learning algorithm organizes the evolved genotype into a reactive phenotype. The evolutionary algorithm encodes an eye-tracking scheme as a genetic code based on image variation analysis. Then, the reinforcement learning algorithm defines internal states in a phenotype control space limited by the perceived genetic code and carries out interactive adaptations. The proposed method can achieve optimal performance by compromising the difficulty in the real-time performance of the evolutionary algorithm and the drawback of the huge search space of the reinforcement learning algorithm. Extensive experiments were carried out using webcam image sequences and yielded very encouraging results. The framework can be readily applied to other low-cost vision-based human computer interactions in solving their intrinsic brittleness in unstable operational environments.