This study aimed to construct a cognitive model of facial mildness in young men. Previous studies have shown that mildness is one of the most required attributes for Japanese men today. Since young men tend to be highly interested in cosmetics, the cognitive model would help them enhance facial mildness through cosmetics. Ten trained participants rated 34 impressions in 32 facial images of men aged from 20 to 34. Factor analysis and multiple regression analysis were performed on the rating data. As a result, mildness was predicted positively by cleanliness and liveliness, with cleanliness being the main predictor. Further, dullness around the mouth was the main negative predictor of cleanliness, and the strong appearance of the eyes was the main positive predictor of liveliness. These results showed a cognitive model representing that facial mildness is judged mainly by cleanliness, and cleanliness is mainly judged by dullness around the mouth.

Within the context of urban planning in the 21st century, it is important to evaluate landscape design impressions, which can be stakeholders’ important criteria for selecting urban green space proposals in public offering processes. In this study, we aimed to establish a questionnaire for rating impressions of urban green spaces in public offering processes. First, we conducted a qualitative pilot survey collecting 127 items for expressing impressions of urban green spaces selected from recent cases of public offerings in Tokyo. Then, based on the results of two online questionnaires (N = 300 and 100, respectively) and exploratory factor analyses, we identified 22 items classified into 3 factors, such as beautiful sight, unsatisfactory maintenance, and accessibility. General structure of these 3 factors was reproduced by a confirmatory factor analysis, indicating that factors found in this study can be useful for rating impressions of urban green spaces in public offering processes.

This paper proposes a system to estimate the emotions of Japanese words by considering the context in which they are used. It is expected to be used for realizing a dialog system that can understand and empathize with users. The proposed system uses word embeddings from a pre-trained language model: BERT to create a 10-dimensional emotion vector that expresses 10 different emotions. A 3-layer neural network with an intermediate layer with 400 nodes is used for training. Text data for learning does not need to be labeled for emotions. The proposed system automatically extracts emotional words to give its surrounding words information about the emotional words. The vocabulary of the proposed system is much larger than existing dictionary-like methods. We carried out extensive evaluation experiments and the results show that the proposed system can estimate context-sensitive word emotion.

In order to find clues to save as many lives as possible in the event of a natural disaster, this study investigated how the Big Five traits (conscientiousness, agreeableness, neuroticism, openness to experience, extroversion) and cognitive biases (myopia bias, forgetting bias, optimism bias, inertia bias, simplification bias, majority bias) affect natural disaster prevention awareness and natural disaster prevention behavior during normal times and natural disasters. Correlation analysis showed significant negative correlations between agreeableness and forgetfulness, conscientiousness and optimism, and openness and simplification. On the other hand, as a result of multiple regression analysis, conscientiousness was the only Big Five characteristic that affected natural disaster prevention awareness during normal times and natural disasters. In addition, it was clarified that forgetfulness, optimism, and simplification tended to negatively affect natural disaster preparedness awareness both during normal times and during natural disasters, and inertia only during natural disasters.

There exist some Computer Vision Models (CVMs) such as CNN, Vision Transformer (ViT), and CLIP, which were pre-trained on a huge amount of training data. The image cognition power of these CVMs is very high. In our environmental cognition research using photos, we manually measured the inter-photo visual similarity. Our previous study found that CVM-based photo similarity and visual similarity were quite similar, when compared by photo MDS. However, it was also suggested that the difference in image cognition between humans and CVM was related to representation of humans. We investigated here numerically in detail the difference between CVM-based photo similarity and visual similarity, using six types of photo sets. The influence of representation could be evaluated by cluster size on MDS. It was shown that representation influences the cognition of shrines and temples, foods, insects, buildings, greens, garden styles, perspective views, night views, the symbol tree, and so on.

A recent trend is for companies to innovate by focusing on the meaning of product. Meaning is the emotional and symbolic reason that people understand a product. This study is an examination of requirements for innovation of meaning and focuses on the interaction of first-order and second-order meanings through product appearance. This study analyzed successful cases of innovation meaning. The implications of this study are as follows. Meaning, which is the emotional and symbolic aspect of product, and the uniqueness of product appearance create fixed idea among people. When this fixed idea is destroyed which positive emotion by the transformation of product appearance, and a new relationship of uniqueness is created, innovation of meaning is established. The discovery of the original conditions and transformative elements of product appearance that make innovation of meaning show the effectiveness of companies in actively utilizing the symbolic aspect of product appearance.

In plastic surgery for facial reconstruction and gender conformity, the aspect of appearance of a natural-looking male/ female face is an important factor in the perfection of the surgery. However, there is a problem that the perfection of the postoperative facial shapes after surgery is greatly influenced by the skill of each plastic surgeon. Therefore, it is useful to verify the male/female areas of each patient’s face in order to create an appropriate shape for each patient. In this study, we generated 100 cross-sectional images per person from 3D models of male and female faces, and trained a convolutional neural network (CNN) using gender and race as the classification criteria The trained CNN was then used to visualize the acquired facial features using Grad-CAM and analyze the feature curves. The results revealed that the characteristics of the curves in specific facial regions represent the gender and racial traits.

Sound is generated by Kansei information processing performed by an instrumentalist playing a musical score. To construct datasets for Kansei information processing of musical scores, we have performed subjects’ experiments using melodies extracted from some sets of music scores. All Japan Band Contests have a lot of pieces of music, and they are all selected as the required pieces, so we extracted the melodies from them and made a set of music scores for the subject experiment. The results of five subjects’ experiments show that the subjects’ estimated tempo differs. Furthermore, the tempo estimated by the subject from the score was defined as a 2-class classification problem of fast or slow tempo and simulated by a deep neural network. The recognition rate of the training data was more than 99.8% for all subjects’ datasets, but the recognition rate of the evaluation data varied from 90.3% to 77.4%.

In this study, wearable devices and web systems that can be worn on the abdomen (underneath clothing) during sleep were developed and applied for menstrual cycle management through the continuous measurement and collection of body surface temperatures. The average body temperature was calculated using data collected from 7,543 normal menstrual cycles with a duration of 25-38 days, over a period of approximately 200,000 days. In all cases, the average value of body surface temperature was lower than the average value of oral temperature; however, the differences between the body surface and oral temperatures of the two menstrual cycle phases were 0.40°C and 0.32°C, respectively. As a result, all age groups showed similar duration of the high-temperature phase, that was 12-13 days. Thus, this study demonstrated that menstrual cycles could be monitored via measurements using a wearable device attached to the abdomen.