To reveal the actual situation of luxury fashion products in the online market, this study sheds light on dynamic pricing observed from the difference between regular and selling prices. Regular price distributions indicated the prestige of luxury fashion brands, with traditional French and Italian brands appearing in a higher rank. Two emerging luxury brands also had a higher social status. This result suggests that the mobility of creative talents allows emerging brands to inherit the brand equity of traditional and prestigious brands. This paper also analyzed dynamic pricing strategy in luxury fashion products by category. The results revealed 67.4% of dresses were discounted with the large markdown ratio even for online luxury fashion stores, however, 69.1% of bags were sold at regular price. A time fluctuation model of product value to interpret the dynamic pricing difference between dresses and bags are also discussed.
Non-Linguistic Utterances (NLUs) present a potentially useful additional communication channel between humans and machines. NLUs may be appropriate in situations such as assisting tourists with various language backgrounds and needs. An experiment was done to model NLU interpretation as dialogue parts. 1000 sounds were generated and evaluated for dialogue relevance to reduce the number to 53, used in the NLU evaluation experiment. 31 Subjects listened to the sounds and rated the following communicative acts for each on a 5-point scale: Greeting, Reject, Question, Thanking, Accept, Apology, Non-Understanding, and Exclamation. Factor analysis yielded three factors: 1) Interrogative vs Apologetic, 2) Appreciative vs Negative, and 3) Positive vs Non-Understanding. Prosodic features such as average pitch, pitch contour, timbre, and duration influenced the interpretation of the sounds. Future work will apply spectral-based speech and emotion recognition techniques along with prosodic features to allow machines to augment dialogue with effective NLUs.
In order to eliminate mismatches between the intentions of questioners and respondents of Question and Answer (Q&A) sites, nine factors of impressions for statements have experimentally been obtained. Factor scores have been then estimated by using the feature values of statements. So far the possibility of detecting respondents who can appropriately answer a newly posted question has been established for several categories e.g. Auction, PC, etc. It has been shown that the distance and the number of appearance could lead to selecting users who are able to appropriately answer a question. In order to inspect these tendencies, this paper tries to find the possibility of detecting appropriate respondents by adding respective eight question statements for each of the nine categories. As a result of analysis, the tendencies that particular several users are apt to appear in each category has been verified. Meanwhile, several different outstanding tendencies have been also observed.
This paper proposes a method of interpreting a transformation matrix of the factor loading matrixes obtained through factor analysis often used in affective engineering. A transformation matrix transforms a factor loading matrix of a data set to another one of another data set, and vice versa. It represents the relationship between two sets of factors. A transformation matrix is decomposed into a rotation matrix and a mapping one. It is shown that these two matrixes could be decided by specifying a non-corresponding factor in the factors of two data sets. This enables us to easily interpret the meaning of the transformation matrix.
With the ever-growing “electronic book” (e-book) market, more people are reading e-books. Along with that, social reading, for its social sharing of e-books, has gained more attention; readers may read an e-book while viewing comments on the contents of the e-book. We evaluated the impression of social reading using an experimental system to clarify its effect. Furthermore, we performed factor and customer satisfaction analyses to evaluate the impression. The results indicated that reading while viewing comments is valuable as it gives a sense of excitement and new discoveries. Moreover, we realized that there is a need to improve the method of giving readers satisfaction to “comment writing and enjoyment”.
Digital fonts are widely used in various fields such as documents, webpages, movie subtitles, etc., thus, how to select the best font for the content is an important issue. For the same font, the similarity calculated using different metrics is different. In this paper, we propose a font comparison system that considers different similarities by sorting the similarity of each font. For measuring similarity, we use MSE, PSNR, SSIM, and HaarPSI for image quality assessment, as well as Euclidean distance and cosine similarity in t-SNE to reduce the number of dimensions. We evaluate how the correlation to the font order of each comparison method changes depending on the resolution of the image, the character type, and the comparison method.
The procedure of orthopaedic surgery is quite complicated, and many kinds of equipment have been used. Operating room nurses who deliver surgical instruments to surgeon are supposed to be forced to incur a heavy burden. This study aims to offer a computer-aided orthopaedic surgery (CAOS)-AI navigation system, which assists operating room nurses by suggesting the current progress of the procedure and expected surgical instruments. This paper proposes a method for recognizing the current phase of orthopaedic procedures from surgeon-wearable video camera images. The method plays the fundamental role of CAOS-AI navigation system. The proposed method is based on a convolutional-long short-term memory (LSTM) network. We also investigate the efficient CNN model in some competitive models such as VGG16, DenseNet, and ResNet to improve the recognition accuracy. Experimental results in unicomapartmenatal knee arthroplasty (UKA) surgeries showed that the proposed method achieved a phase recognition accuracy with 48.2%, 41.2%, and 53.6% using VGG16, DenseNet, and ResNet, respectively.
This paper proposes an impression-based music playlist generation method with musical diversity and serendipity to positively impact the mood of a listener. The method designs two types of playlists with smooth transitions for audio track impressions: mood-boosting (uplifting) and mood-stabilizing (relaxing). Both these impressions have four patterns with different structures that alter the listener’s mood. To create a playlist, the proposed method calculates the probability of impressions for all audio tracks using a multinomial mixture model adopting a Bayesian approach and chooses audio tracks based on these probabilities. This study uses two psychometric evaluations to evaluate sample playlists for all four patterns of both playlists, i.e., whether they can positively influence a Japanese listener’s mood. The results indicate that the proposed method can achieve both these objectives concerning the audio tracks.
Usefulness of subjective sleep quality assessment by a questionnaire (OSA-MA sleep inventory) was examined in ten track drivers (age, 42 ± 12 y, range, 23-62 y) in reference to the objective measure of sleep apnea by cyclic variation of heart rate (CVHR) in electrocardiogram (ECG) during sleep. Total CVHR suggesting moderate-to-severe sleep apnea (average over total time in bed > 15 cycles/h) was observed only in one subject and the transient occurrence of frequent CVHR (≥ 50 cycle/h) was detected in the same subject and two other subjects. The questionnaire provided the standardized scores of five features of subjective sleep quality, including less sleepiness on rising, good initiation and maintenance of sleep, less frequency of dreaming, refreshing feeling, and subjective sleep length as factors 1-5, respectively. The subject with high average CVHR showed factor scores < -1 SD for factors 1, 2, and 3 and reported subjective sleepiness during driving. In the two subjects with transient frequent CVHR, one showed factor score < -1 SD for factors 3 and 5, while the other did not show score < -1 SD for any of the factors. Although this is preliminary study in a small sample size, it suggests the possible associations between the subjective assessment of sleep quality and the objective measure of CVHR.