One of the important Kansei values of automobiles is engine sound. Engine sound determines the character of a car and is an important element for branding. However, since popular cars sold around the world have diverse preferences for customers in each region, they will inevitably be developed to reflect the demand for improvement of mass production cars while compare with the level of competing cars. It is same for engine sounds, and when providing engine sounds with new Kansei values, a different approach is required. Therefore, in this research, we used Kansei engineering, devised a new process to realize engine sound of a new concept, and verified its usefulness. Specifically, we introduce an example of engine sound design based on the concept of “Woody sound”.

There are many examples of consumer behavior research focusing on media and content. It has been posited that word of mouth through the media and emotional value of content are important factors influencing purchase intentions. However, although both have been verified separately in conventional research, there are few verification examples which include the presence or absence of mutual interaction. Therefore, in this study, media and content contributing to purchase intention were evaluated by a factorial randomized controlled trial for the automobile industry. Using the multiple comparison method, the results showed that the influence of content was larger than that of media, and the superiority of design and user experience was also indicated. However, the influence of functional values, such as driving performance and advanced technology, was low. The results also confirmed that no mutual interaction occurred. These would be useful as suggestions for promotion strategies.

A market where the cooking is enjoyed as experiential consumption is being roared. Enjoyment eventually improves quality of life (QOL) via elevated positive feeling. Analogously, it is meaningful to elucidate the cooking-related factors that uplift feeling to enrich the eating habits. In this research, we tried to establish a questionnaire that measures the factors to represent uplifted feelings associated with cooking. First, a qualitative pilot survey was conducted. 104 items related to the uplifted feeling by cooking were collected. Then, 600 participants answered online-questionnaire to quantitatively evaluate the degree of uplifted feelings for each item. Exploratory factor analyses revealed that the items were classified into seven factors: special feeling, cooking characteristics, physical wellness, crowding, amount and stability, rationality, and appearance. Internal consistency for each factor was satisfactory. High convergent validity was indicated based on correlational analyses. These together indicated the factors are adequate to measure uplifted feeling regrading cooking.

In recent years, while data mining has attracted attention, formal concept analysis has the disadvantage that although it can understand the inclusion relation between attributes, it doesn’t know what kind of meaning or inclusion relation the attributes have. Therefore, in this study, the inclusion of the attributes and the visualization of the correlation are realized by combining the Hasse diagram by formal concept analysis and the layout diagram of the attribute of quantification theory type III for visualizing the meaning between the attributes. Moreover, in order to confirm usefulness of the proposed method, we developed a simultaneous visualization system of inclusion and correlation combining formal concept analysis and quantification theory type III, and evaluated the proposed method using verification data. As a result, it was confirmed that useful information that can’t be obtained only by formal concept analysis or quantification theory type III can be extracted.

In this paper, we investigated how readers perceive the emotions of writers based on the emoticons in their tweets, and clarified the influence of emoticons on emotions. Initially, we conducted a questionnaire and the emotions associated with tweets (with and without emoticons) and the emotions associated with the emoticons were quantified. Multiple regression analysis was then applied to three types of emotion data, and relationships among them were established in the form of regression equations. Finally, the accuracy of the regression equations was estimated for learned and unlearned data, and their effectiveness and robustness were evaluated. The following 10 types of basic emotions were utilized as targets: “Sadness,” “Dislike,” “Relief,” “Fear,” “Excitement,” “Liking,” “Joy,” “Surprise,” “Anger,” and “Shame.”

Brain-computer interface (BCI) is a new technology that enables communication for patients in totally locked-in state using brain activities. In this research, we examined optimal mental task for near-infrared spectroscopy-based BCI from among six mental tasks. SVM was used for learning, and the classification accuracy for each tasks through 8-fold cross validation was calculated. As a result, it was suggested that the music imagery had high discrimination accuracy and was a practical task.

This paper describes the trends in the phonemes used in naming by using the attributes of objects. The study used the names of characters in video games and automobiles as the targets of analysis. Through categorizing the objects based on their attributes, the study sought to verify if there existed a difference in the used phonemes between the categories. Resultantly, the study has clarified the phonemes used to illustrate the smallness, lightness, and weakness in addition to the phonemes used to depict the largeness, heaviness, and strength between two objects. In addition, the study had also employed evaluation experiments to verify the trends in the phonemes used in naming, which was derived from the analyses of the objects’ attributes, and to verify whether the phonemes used in the naming process matched with the people’s impressions. Throughout this process, the study has found the objects’ specific naming trends and the characteristics of the phonemes. By conducting the same analysis process for many objects, the study hopes to propose a supporting method for the naming process of specific objects.

This study aimed to construct a cognitive model of facial youthfulness. First, we investigated which higher-order impressions (e.g. lively, clean, etc.) compose youthfulness on the hypothesis that youthfulness is a complex impression. Then, we investigated which lower-order impressions (e.g. wrinkles, translucency, etc.) account for the constituent impressions of youthfulness. Eight trained participants rated 27 impressions of 32 women’s facial images in their 50s. Factorial analysis and multiple regression analysis were conducted on the rating data. Our investigation revealed that youthfulness consisted of lively impression and clean impression in addition to estimated age, while lively impression was the main constituent of youthfulness. Further analyses showed that those three impressions respectively related to strong appearance of eyes, perceived translucency, and wrinkled appearance. Based on these results, we proposed a cognitive model representing that youthfulness is a complex impression composed of three higher-order impressions, which are affected by particular facial features.

In this study, we tried to reveal the effect of steering wheel torque on steering feeling using physiological measurement and Kansei evaluation. Electroencephalogram (EEG) and electrocardiogram (ECG) were measured during driving with three types of steering wheel torque. In addition, steering feelings were evaluated after driving. We analyzed physiological indices and Kansei evaluation values. As a result, a correlation was found between the physiological indices and some emotions in the participants who had a negative impression on the steering wheel torque of hydraulic power steering. Therefore, we could find out the possibility of estimating some emotions from EEG and ECG indices.

Based on the results of the evaluation experiment consisting of multiple items using the Curve Drawing Method (CDM), the hierarchy between higher-level comprehensive evaluation and lower-level individual evaluation was examined. CDM has been devised as a continuous time-series Kansei evaluation method to replace physiological functions. A 77-minute lecture was used as the stimulus. Evaluation curve patterns were obtained for 5 items from the participants (N = 49): degree of comprehension, sense of belonging, sense of security, elation, and sense of fun. Based on the results, we examined the degree of agreement (correlation) between the composite curve obtained by averaging the value of “sense of belonging, sense of security, and elation” with the pattern of each curve for the “degree of comprehension” and the “sense of fun”. The results indicated that lower individual evaluations contributing to comprehensive evaluations could be specified, which cannot be achieved by using physiological indices.

We have been developing an EEG-based communication aid “Neurocommunicator” (NC) for people with severe motor disabilities. The NC utilizes an event-related potential (ERP), the cognitive component of the EEG. Here, we studied the feasibility of the NC for the cognitive assessment to detect subtle symptoms of mild cognitive impairment. We recorded the EEG data from 40 normal adult subjects, as the control group, during the target only task, the oddball target task, and the target selection task. We supposed that the task became more difficult in this order. While we observed the ERP to the targets in all tasks, the differential response between the target and the nontargets systematically changed by the task difficulty. These results suggest that the combination of these three tasks could have potential to reveal the cognitive processes such as bottom-up and top-down attention, which should be important to evaluate the cognitive impairment.

In this paper, we describe a method for estimating psychological impressions (e.g., “Pretty”, “Elegant”, “Romantic”, “Cool”, “Formal”, etc) from color images. Essentially, the Earth Mover’s Distance (EMD) is employed to map a given image onto the color image scale, a two-dimensional emotion space comprised of a WARM-COOL axis and a SOFT-HARD axis, on which many color combinations and Kansei words are located. To validate our proposed method, we collected real images from the Web and compared our EMD-based results with human evaluation results. The comparison demonstrated that EMD-based Kansei mapping is a promising method for extracting psychological impressions from color images.

While robotic assistants capable of automating many a task are becoming more ubiquitous, the complexity and unfamiliarity of such machines may discourage users from interacting and personalizing their robots. For that reason, the goal of this research is to study how a robot that expresses emotion-like feedback using movement affects the training interaction experience of non-expert users. To that end, a single-eyed spherical robot was developed using a Kansei design approach. A within-subjects experiment, between the robot expressing feedback and a control version that did not, was conducted with participants who had little to no experience interacting with robots. The results showed an increase in arousal when the robot expressed feedback and the overall interaction was considered engaging. Also, a positive correlation between bonding scores and relevance of the task was found. The contributions of this research are toward the development of human-trainable robots with transparent learning behavior.

The objective of our studies is the inquiry into data set of the silhouette styling by machine learning for the luxury brands. The computer vision meets the visual fashion for the long years. Recently, computer vision techniques has been employed in algorithm of fashion recognition. But the aim of the computer vision is that the computer vision meets fashion but not that fashion meets computer visions. The luxury fashion consumer expects the favorite own beautiful silhouette styling, not simply the computer pictures. Therefore, silhouette learning of clothing by Neural Network Console needs to meet the personal professional styling knowledge.