In this paper, the authors compare the images of a town held by old residents who have lived there for many decades with that held by young students who have come there few years ago. An experiment was conducted in which participants photographed what impressed them in the town and wrote explanations why they had impressed them. Cooccurrence graphs were created based on the text data of the explanations and images of the town were extracted from the cooccurrence graphs. It was revealed that both of the old residents and the young students have two images. One of them is a visual image and the other is a conceptual image. It was also revealed that the old residents’ images contain what exist in their memories such as scenes of other seasons, episodes, and personal customs, whereas the young students obediently develop their images using what exist in front of them.
The purpose of this study is to estimate mental states quantitatively using an ECG signals for preventing depression and anxiety. Then, we focus on mood change during imagining the near future. ECG signals are measured from participants during imagining the near future and participants evaluate mood change during that. Features of heart rate variability (HRV) are extracted from this ECG signals and mental states are defined in four levels by mood change. The mental states are estimated using support vector machine (SVM) with forward stepwise as feature selection. The estimation result shows f-measure 0.48 and features contributing to mental states. That indicates the effectiveness of focusing on mood change during imagining the near future and estimating mental states using ECG signals during that.
This research aimed to investigate the effect that smartphones have on brain networks. The Subjects were 23 healthy adults (25.7 ± 5.64 years old). Five sessions with relax, pleasant, unpleasant, pleasant sentences, and unpleasant sentences, stimuli were conducted using a smartphone. The electroencephalography (EEG) was measured soon after the stimuli. The coherence analysis and the complex network analysis were conducted for EEG in the alpha2 wave band. In the stress-free group, the brain shows low network efficiency under relax or pleasant stimuli, and high network efficiency under unpleasant stimuli. In the stress group, there are no differences in network efficiency among any kinds of stimuli. In either group, the network efficiency under sentence stimuli is close to that under unpleasant stimuli. Our study using complex network analysis for the coherence value from EEG revealed that network efficiency of the brain depends on the category of emotional stimuli during smartphone operation.
In this paper, we propose an emotion estimation method for words and its application to construct a word-emotion dictionary. Since the estimation of more delicate emotions in various natural language processing tasks is a crucial issue, we aim to estimate various emotions to a word. In order to realize it, we employ the distributional hypothesis and assume that an emotional word in a sentence influences the surrounding words. First, we collect more than 2,000 words expressing emotions from an emotion expression dictionary. By using these emotional words and a neural model based on Continuous Bag-of- Words (CBOW), we propose an automatic system to estimate the emotions of many ordinary words. As a result, emotion vectors for 20,000 words could be obtained. We carried out experiments to examine the accuracy of the vectors. It is confirmed that the generated emotion vectors reflect the emotion image for words that humans have.
Improving ride comfort is important both from the viewpoint of road user satisfaction and in order to improve the effective use of existing social infrastructure. In the past, ride comfort was usually examined with multivariate analysis using road landscape elements as well as questionnaire results. This study uses rough set analysis to investigate the landscape features such as alignment, slope surface and planting of a specific road section in order to improve ride comfort. The most frequently employed concept even in rough set analysis involves the use of decision rules. In this study, a Covering Index (CI) is used to indicate what sample of the whole decision class corresponds to the decision rule. Based on the CI, road alignment, slope surface and planting can be considered factors that influence ride comfort.
Many papers and books on improving voice quality exist around the world. This suggests that some people want to change their voice. However, there is a difficult image on improving voice quality. The reason is that objectively evaluating your own voice training is difficult. In this study, to improve the voice quality based on the user’s voice, we propose a method to create ideal voice heard from other’s using software UTAU and Interactive Differential Evolution. As result of the search and evaluation experiments, the evaluation values significantly increased from the initial to the final generations. These results showed that the proposed method has the possibility of making the ideal voice of the user. Furthermore, overall convergence was observed when in the transition of individual parameters. Especially, in the transition of the parameter related to voice formant, obvious convergence was confirmed in 13 out of all 14 subjects.
In this paper, we propose an automatic consultation system by latent variable hierarchical recurrent encoder-decoder (VHRED) using transfer learning. VHRED has been developed to alleviate a large shortcoming of the sequence to sequence. They cannot consider the flow of dialog: the same output is produced for the same input. However, when we try to use VHRED, there is a small amount of Japanese corpus with long dialog-turns. The proposed system employs a method of transfer learning: the encoder layer and the decoder layer in VHRED are learned using a large corpus of dialog pairs obtained easily such as from Twitter and the other layers are learned by transfer learning using a small corpus with long dialog-turns. In the evaluation experiment, subjective evaluation experiments were carried out to compare with VHRED without transfer learning. As the results, it is shown that transfer learning of VHRED became possible by the proposed method.
“Kawaii” is a sensibility peculiar in Japan, but widely used in the world nowadays. In this report, the kawaii degree of twelve aroma oils and the concentration dependence were evaluated by sensory evaluation. Mostly, higher kawaii evaluation appeared at lower concentration, but at higher concentration in fruits fragrances. On the other hand, high correlation (R = 0.796) between kawaii and preference was observed. However, their factors were different. For high “kawaii”, the impression terms of “feminine” and “infant” were derived. In high “preference”, “favorable impression” and “friendly” were derived. Incidentally, there was no gender difference for recognition of “kawaii”. By classifying subjects with similar recognition of “kawaii”, groups mixed with male and female were formed.
‘MOKUIKU’ is an educational activity to aim to deepen the experience with wood from infancy that can lead to a richer life, a better society, and an awareness for importance of the creation of new forests. ‘MOKUIKU-Toys’ is educational toys which have effect of encourage intellectual growth for young children. In our previous research of ‘Classification of Wooden Toys and Survey Analysis of the Effects’, we were able to verify the toys that were suitable for the development of children’s intelligence and physical ability. In addition, the relation between growth stage of children and the use of educational wooden toys was clarified in this research. Using a method of classifying 154 wooden toys for children from 0 years old to 3 years old in five categories, the relation between age group and play style was clarified using multivariate analysis. After that, using text mining analysis, we extracted useful information such as frequency of appearance of words in sentences, correlation of co-occurrence, appearance tendency. Finally, we created ‘Age correspondence table of effective use for children’s growth with MOKUIKU-Toys’. Using these results, we hope to create new production guidelines for MOKUIKU-Toys for preschool children.
The objective of this study was to develop a home care support system using a smartphone to solve problems of patients with psychiatric disorders such as schizophrenia. We have created a system by which patients can input their symptoms, drug administrations, doctor’s appointments, and so on from the comfort of their homes to support their own treatment and recovery. We got healthcare professionals including nurses and psychiatric patients to evaluate the system. The results showed that the input items for the physical and mental symptoms were inevitable. In particular, it was suggested that support for prodromal symptoms, thought disorders, and lack of motivation would be effective in the system. These findings suggest that a home care support system via a smartphone could be helpful for psychiatric patients’ self-care.
Hangzhou women’s fashion is a set of women’s apparel manufacturing and distributors with the leading share in China. These entrepreneurs exist in Zhejiang District. This study was promoted to investigate store development in those brands in China. The top 31 companies and those 50 brands were extracted. 661 cities were classified into six grades according to population, GDP, income, artificial commercial accumulation (shopping center etc.), temperature, distance from Shanghai and others. The survey was covered the first-class city to the fourth-class city among them. 50 brands classified into 3 types by products characteristics. First, the aggregation was carried out for each city class. Then, the numbers of stores were sum up for each city, with three different brands as a unit. The number of shops in each city was classified using principal component analysis and other multivariable analysis. The proportion of shops belonging to young women’s brands (their daily clothing) was higher for lower class cities than for advanced cities. The 19 first-class cities are scattered all over the country, but the number of stores was similar. The number of stores belonging to the brands of young ladies (daily clothing for young people) had a higher weight than lower class cities. In this way, multiple brands of different concepts existed uniformly throughout the country according to the city characteristics. Brand characteristics (concept) spread as a uniform layer throughout China of 9.6 million square kilometers. The number of layers is comparable to the number of brands. Consequently, each uniform layer is spreading and overlapping in China’s female fashion market. Understanding of such uniformity and multi-layering is essential for the successful entry into the Chinese market. However, it is unknown whether these successes will pass in the European and US markets.
After the reform and opening up, a huge fashion market was created in China. The Zhejiang area has been a silk producing area since ancient times. In the 1990’s, it changed to the production area of women’s clothing (Hangzhou Women’s Fashion) with high competitiveness in China. This study investigated the establishment process of Hangzhou Women’s Fashion and discussed its possibility of internationalization. As the results, we emphasized the following. 1) Strong structural reforms were forced before that stage. 2) With this, the former power of the textile industry, mainly state-owned enterprises, has been wiped out. 3) Modeling was acquired by OEM production in the 1980s. 4) However, the company could not learn styling. 5) As a result, counterfeit goods were mass-produced and sold at a low price. 6) Fashion School was established in Zhejiang Sci-Tech University , Formerly Silk Graduate School. 7) Successful people who were excellent in styling from graduates came out. After that, a huge market grew rapidly. Many businesses were culled. Alliances and M & A with foreign companies will not acquire styling ability. In order to sell Hangzhou Women’s Fashion in different country regions, it is necessary to enhance the function of styling.
We examined the effects of foot massage on healthy adult females’ mental and physical functions by electroencephalography as an emotional assessment method. We randomized 20 healthy adult females into 2 groups receiving a massage by a therapist (Group A) and mechanical massage using a commercially available massager (Group B), each of which consisted of 10 subjects. After massage, the lower limb volume significantly decreased in both groups, but Group A showed more favorable results related to comfort, pain, and feeling refreshed. Electroencephalography confirmed increased beta waves, indicating enhanced neuronal activity, in the medial prefrontal cortex and anterior cingulate gyrus of Group A after massage. The results suggest that foot massage by a therapist positively influences not only physical functions, but also mental conditions.