Makoto Fukumoto

User's favorite scent design using paired comparison-based Interactive Differential Evolution

This study proposes a method that creates a scent suited with a users favor using paired comparison-based Interactive Differential Evolution. In the proposed method, the user smells two scents and selects the preferred one by simple comparison. Based on the repetitive comparisons, Differential Evolution (DE) optimizes the scent suited with the user. Each scent is composed of several source scents, and strength of each source scent is described as values in DEs vector. To investigate the efficacy of the proposed method fundamentally, smelling experiments composed of comparing experiment and evaluating experiment are performed. In the comparing experiment, the subjects compare presented pair scents and select the preferred one through ten generations, and DE evolves scent to users favor based on the comparisons. In the evaluating experiment, the subjects evaluate four representative scents picked from 0-, 3-, 6-, 9-th generations, respectively. The results of the experiments showed a tendency of the increase of fitness value in accordance with evolution.

Extended Interactive Evolutionary Computation using heart rate variability as fitness value for composing music chord progression

Interactive Evolutionary Computation (IEC) is known as an effective method to create media contents suited to each user. To reduce the users fatigue, which remains as a serious problem in IEC, an extended IEC that utilizes physiological information as fitness value have been proposed. As a new extended IEC, this study proposed an extended IEC using heart rate variability (HRV), which reflects autonomic nervous activity. High frequency component of HRV was used as a fitness value. Through two listening experiments, the efficacy of the proposed method was investigated. In the experiment 1, with a concrete system of the proposed method creating music chord progression, change in the fitness value was observed. In the experiment 2, representative created music chord progressions were evaluated subjectively. The change in the fitness value did not show gradual increase, however, lowest fitness value was observed in the initial generation in subjective evaluation. These results of subjective evaluation showed a possibility of the proposed method.

Interactive Tabu Search with Paired Comparison for Optimizing Fragrance

Interactive evolutionary computation (IEC) is known as an effective method to optimize media contents to users subjective feelings. Previous IEC studies employed various evolutionary algorithms, and one of them applied Tabu Search (TS) algorithm. This method was named Interactive Tabu Search (ITS). In the ITS, users have to select the best individual from population. The authors applied ITS for creating fragrance in our previous study, and blended fragrances composed of several aroma sources are corresponded to individuals in ITS. Strength of each aroma source was target of optimization. However, it seemed difficult for the users to decide the best fragrance from several fragrances with sequential presentation. This study focuses on proposing a new ITS method using paired comparison. The successive paired comparisons are used for deciding the best individual from population like tournament selection. Furthermore, this study investigated the efficiency of the proposed ITS method through smelling experiments.

A proposal for optimization of sign sound using interactive differential evolution

Interactive Evolutionary Computation (IEC) is known as an effective method to create media contents suited to users preference and objectives to use. The present study proposed an IEC method that creates sign sounds with interactive differential evolution. In the users evaluation, paired comparison was employed: the user selects better one from two presented media contents instead of scoring many solution candidates in a same time. To fundamentally investigate the efficacy of the proposed method, two listening experiments were performed; experiment 1 as comparing experiment and experiment 2 as re-evaluating experiment. Target of the creation with the proposed method was warning sign sounds. Eight males participated as subjects in both experiment. In the result of the experiment 1, gradual decrease of total Euclidean distance between eight DEs vectors in each generation was observed. In the result of the experiment 2, gradual increase of the subjective fitness value was observed. These results were not significant, however, shrink of searching space and increase of fitness value suggested a possibility of the proposed method to create sign sounds suited to the user.

A Proposal for Intervention by User in Interactive Genetic Algorithm for Creation of Music Melody

In the area of Interactive Evolutionary Computation (IEC), some previous studies have already proposed a method for creating music melody. However, in these methods, users concrete intention or Kansei seems not to be reflected to the created melodies. This study focuses on this point: reflection of users concrete intention and Kansei in IEC. While most of conventional IEC approaches accepted only users evaluation by scoring or comparing solution candidates, the proposed method accepts users operation for solution candidates as users intervention. To investigate the proposed method for creation of music melody, listening experiments were conducted. In the experiment, the subjects listened to music melody created from the IEC system based on the proposed method. With the system, the subjects can control key of music note in melody by themselves when they wanted to change the melody. As result of experiment, the mean fitness value gradually increased in accordance with progress of generation, and significant differences between the first generation and other generations were observed. The experiment also investigated the efficacy of the users intervention.

A Proposal for Optimization Method of Vibration Pattern of Mobile Device with Interactive Genetic Algorithm

The vibration patterns are often used in mobile devices such as cellular phone, tablet computer and smartphone, etc. However, these vibration patterns are ready-made patterns. Most of the users do NOT use vibration pattern suited to each user’s preference and objectives to use. Interactive Evolutionary Computation (IEC) was known as effective method to create contents suited to each user, and IEC was applied for creating various media contents. This study proposes an Interactive Genetic Algorithm (IGA) creating vibration pattern. Although some previous IEC studies have tried to optimize media content related to sense of touch, an IEC method optimizing vibration pattern of mobile device have not been proposed. The proposed method will dedicate to use of the vibration pattern by improving its ability of notice and/or by enhancing its suitableness in preference.

Temporal Development of Heartbeat Intervals in Transition of Sound Stimuli Inducing Different Relaxation Feelings

This paper aims to investigate the temporal development of heartbeat intervals in a transition of different sound stimuli. In the listening experiment, two minutes relaxing musical piece and white noise were employed as the different sound stimuli, and the sound stimuli were played twice alternately after five minutes rest. After the exposure of the sound stimuli, a questionnaire asked the subjects relaxation feeling for rest, noise and music sections, respectively. Psychological result showed that music section induced the highest relaxation feeling and noise section induced the lowest relaxation feelings. Average of heartbeat intervals in music section was larger than that in noise section significantly (P≪0.05). Furthermore, after the transition of sound stimuli, it took about 30-s to change heartbeat interval from previous section. These results support the previous findings that investigated the effects of sound stimuli on heartbeat and will contribute to develop musical system reflecting a users KANSEI information automatically.

Interactive differential evolution using time information required for user's selection: In a case of optimizing fragrance composition

Interactive Evolutionary Computation (IEC) spreads its area of applications. As an example of the applications, we have already proposed an IEC that optimizes fragrance composition suited to each users feelings by using Interactive Differential Evolution (IDE). To create the fragrance, six aroma sources were mixed, and the intensity of them were target of optimization. Paired comparison was employed as subjective evaluation method. To enhance searching ability of the IDE method, this study proposes a new IDE utilizing both of evolution level of DEs vector (solution candidate) and time information required in users selection in the paired comparison. In other words, shorter time duration required in the selection is considered as there is larger difference of fitness level between two vectors. Winner vector tended to have chance to evolve itself. These schemes in the proposed method are expected to accelerate searching better solutions. In this study, we constructed an IDE system optimizing fragrances based on the proposed method. Furthermore, with the IDE system, we conducted smelling experiments for investigating the fundamental efficiency of the proposed method. Target of creation was relaxing fragrance. The experimental results showed that obtained fragrances in the last generation was evaluated better than fragrances in initial generation significantly (P<;0.01).

A Creation of Music-Like Melody by Interactive Genetic Algorithm with User’s Intervention

We have recently proposed Interactive Genetic Algorithm (IGA) creating music piece with user’s intervention. IGA is one of interactive evolutionary computation and is known as effective method to optimize certain pattern suited to each user’s feelings. The user’s intervention is expected to accelerate the optimization. In the intervention method, the user operates the music melody by changing keys of some music notes in each of music melodies. In general IGA, solution candidates are presented to the users, then the users subjectively evaluate them. In the IGA with user’s Intervention, after the presentation, the users can operate the individual when the users want to. After finishing the operation, the user input the fitness value of the presented solution candidate to the IGA system. This study focuses on improving the proposed IGA to create more music like melody. With the improvements, pattern of music melody is lengthened and is attached music chord.

An Efficiency of Optimization Method of Sign Sound Using Interactive Differential Evolution

Interactive Evolutionary Computation is well known as an effective method to create media contents suited to users preference and objectives to use. As one of the methods, we have already presented a method that creates sign sounds with Interactive Differential Evolution (IDE). In the users evaluation process, the user selects better one from two presented media contents. In this study, to fundamentally investigate the efficacy of the IDE method, three listening experiments were performed, experiment 1 as comparing experiment, experiment 2 as re-evaluation for subjects themselves, and experiment 3 as re-evaluation for other subjects. Target of the creation with the IDE method was warning sign sounds. Ten males participated as subjects in the experiments. In the result of the experiment 2, gradual increase of the subjective fitness value was observed. In the result of the experiment 3, increase of the subjective fitness value was not observed. These results suggested that the IDE method has a possibility to create sign sounds suited to users preference.