The number of dementia patients is growing and has become a social issue. Early detection and treatment of dementia can slow the progression of symptoms and restore health. As a result, early detection is critical for dementia treatment. However, many dementia patients are hesitant to visit hospitals. In our lab, we are working on a dementia screening tool that will use the P300-based Spelling-brain-computer interface (Spelling-BCI) to aid in early dementia diagnosis. We believe that an easy cognitive function test with Spelling-BCI can be realized by estimating the results of neuropsychological examinations that must be performed by a specialist with BCI. We focused on the asymmetry of EEG frequency components in the parietal-posterior-temporal region of the EEG data in this study and compared the analysis results for each cognitive function decline level as determined by Mini-Mental State Examination (MMSE) scores. The outcomes were compared. As a result, there was a significant difference between the dementia and non-dementia groups in the asymmetry of α₁ wave (8-10 Hz) and θ wave (4-8 Hz) components in the parietal-posterior-temporal region. As a result, it was proposed that asymmetry of the α₁ and θ wave components is a reliable indicator of cognitive function decline.

Our final goal is to promote brain health by developing a brain-machine interface (BMI)-based cognitive training device. We have been developing a cognitive level assessment device called the "Neurotrainer," which uses event-related potential (ERP) analysis. This device was operated by decoding single-trial ERPs using pattern recognition. Here, we extended our method to decoding single-trial ERPs during a racing game with 8 choices of characters. The decoding accuracy of the target character was about 54% for a single trial and 83% for a cumulative total of five trials (chance level = 12.5%). Also, the ERP responses were stronger in the feedback condition than in the no-feedback condition. These results suggest that the BMI might be an effective tool for cognitive training, in which real-time neurofeedback affects the activation of the brain of the players.

In recent years, there has been growing interest in speech recognition technology in Japan. Against this background, several objects make use of speech recognition. However, some problems are associated with their use. For example, there is a noise problem, wherein loud ambient noise prevents accurate speech recognition. In addition, some problems depend on the user, such as the inability of people with speech impediments to use the system. Currently, there is a method for recognizing speech without speaking by attaching a myopotential sensor to the face surface. However, this method can only be recognized in a stationary state, and is difficult to recognize while walking, which involves body movements. Therefore, in this study, we focus on the recognition of silent speech while walking, which is considered difficult using conventional methods, and propose a method to improve the accuracy while minimizing the difference in classification accuracy between the case of measurement in the stationary state and the case of measurement in the walking state. In the proposed method, the variational mode decomposition algorithm, which can adaptively decompose signals, is used to finely decompose the measured signals and extract only those signals less affected by the body motion. Subsequently, based on these signals, we evaluated the proposed method using a 1-Dimensional Convolutional Neural Network (1DCNN) model that was pretrained with the measured data only at rest. Using the proposed method, we succeeded in improving the recognition accuracy of walking by approximately 10% compared to the case without it.

The transparent communication board (TCB) is a communication tool that is commonly employed by individuals with amyotrophic lateral sclerosis (ALS). Both the 50-letters and flick type TCB are prevalent in Japan. The purpose of this case study was to compare and investigate the speed of letter transmission and the subjective user impression associated with the use of the 50-letters and flick type TCB in ALS patients. The study included four ALS patients and four caregivers, who acted as communication partners. Participants used the 50-letters and flick type TCB at intervals ranging from one week to 90 days. They received video instructions on how to use each type of TCB and tried to transmit a total of 18 Japanese letters. We measured the time taken to transmit each word and the number of errors. Additionally, the participants were asked to complete a questionnaire assessing their subjective impressions of the TCB. Compared with the 50-letters type, the ALS patients and their partners tended to make fewer errors and preferred the flick type of TCB. However, the 50-letters type was easier to use to communicate if the patient and partner were not familiar with the flick type sequence. Our data suggest that the age of the patient and their partner, as well as the amount of experience using a smartphone, should be considered when choosing a TCB.

As a very creative research direction in the field of deep learning, style transfer research has been attracted a lot of attention in the past two years, which can transform ordinary photos into artistic paintings and generate interesting pictures. Existing methods can be divided in two categories: arbitrary style transfer and single style transfer. The representative method of single style transfer and method LapStyle synthesizes stylized image in a progressive procedure by using AdaIN, an arbitrary style transfer method. Inspired by it, this paper proposes a novel arbitrary style transfer framework named LapAttN to optimize the single style transfer, which combines the advantages of LapStyle and AdaAttN. The experimental results on the COCO dataset show that the image quality of proposed method is superior to other SOTA algorithms.

This paper describes the technique to create a printing plate (Hanga-ban) with an FDM 3D printer. As a material for printing plates, PLA resin mixed with 30% of xylem fibers and elastomer filament were used. Three kinds of inks: water-based pigment-based ink, oil-based paint-based ink, and Versacraft ink: were used. From the experiments, it was cleared that the former two kinds of ink do not produce good quality of prints because the inks are repelled on the printing plate, but good prints are possible with versacraft ink. Both printing plates made of PLA resin mixed with of xylem fibers and elastomer filaments produce enough quality of image, however elastomer filament produced better one. The images engraved on the printing plate were generated from a full-color image by adaptive binarization processing. The image quality of the printed image depends on the threshold and block size in the adaptive binarization, and those of optimal ones were determined by experiments. From the experiments, it was clarified that good quality prints can be printed with an FDM 3D printer by choosing appropriate binarizing parameters and creating a printing plate with an elastomer filament.

This study proposes an automatic playlist generation method that broadens interest in music and puts listeners in a positive mood. Our previous approach put listeners in a positive mood by listening to a playlist that gradually changes the song’s impression from “Low” to “High.” This study adds a new function to our previous study and broadens listener’s interest in the specific song in a playlist by emphasizing it. Specifically, the proposed method created two points in the playlist to arouse the notice of the specific song and shift listeners into positive moods in the playlist. The rapid song impression-changing point engages a listener’s interest in the song, and the gradual song impression-changing one puts listeners in a positive mood. This study conducted a subjective evaluation of the previous and proposed playlists. There were no significant differences between both methods in shifting listeners into positive moods. However, there were significant differences in attention to the emphasized and other songs. These results indicate that the proposed method may potentially expand interest in music and put listeners in a positive mood.

The purpose of this research is to develop an English learning system that makes effective use of chat. To learn a foreign language, it is essential to expose a child to it for a long period of time and to maintain motivation for learning. Focusing on the fact that Japanese people spend much more time using chat than the average of OECD member countries, we decided to use a chat app as an English learning system. This system has an English writing function and a conversation promotion function. If a user is having trouble creating an English sentence when sending a chat, the English writing function can easily create the sentence using its translation and template functions. The conversation promotion function provides topics to two users and proposes a simple reply to a user who is having trouble finding an answer during a conversation. The results of our evaluation show that conversation can be promoted by easily creating English sentences using the topic provision and template functions.

We investigated whether stroking stimuli near the external auditory meatus while listening to sounds enhances pleasant feelings. Previous studies have demonstrated that vibratory stimuli manipulate emotions evoked by watching videos or listening to sounds; however, none have investigated the effects of stroking stimuli near the external auditory meatus through which vagus nerves extend. Participants were exposed to three types of sounds with and without the stroking stimuli to their ears, and selected one stimulus condition that induced intense feelings. When the sound stimuli were presented with the stroking stimuli to the ear, joyful and pleasant feelings were intensified, whereas depressing feelings weakened. Stroking stimulation of the outer ears in combination with sound stimulation was suggested to induce positive feelings.

Fraser-Wilcox illusion is attractive for art and design. Understanding how the parameters (e.g., color, form, and size) affect the illusion is crucial to its applications. However, the effects of the parameters on the illusion have yet to reveal sufficiently for systematically understanding them. The reason for the difficulty of systematically revealing the parameters’ effects is the instability and weakness of the illusion. Some previous studies report that the oscillation of the illusion figure enhances the illusion although the details are no clear. In this study, we evaluate whether we can systematically examine the illusion by enhancing it with the illusion figure’s oscillation. For this evaluation, we conduct the experiment where the observers subjectively evaluate the illusion’s magnitude of the oscillating illusion figure. In the experiment, the oscillating vertical gratings based on the color-dependent Fraser-Wilcox illusion are generated with a mobile workstation. There are the conditions of the oscillation’s direction, amplitude, and frequency. A 4-point scale is used for the subjective evaluation of the illusion. Three observers participate in the experiment. The results obtained from the experiment indicate that the oscillation enhances the illusion. They also indicate the oscillation’s effect depends on the oscillation’s direction, amplitude and frequency, and depends on the grating’s direction. These findings support the possibility of systematically examining the illusion by enhancing it with the illusion figure’s oscillation.

There are known to be two major visual processing pathways from the occipital lobe to the temporal and parietal lobes: the ventral visual processing system, which is involved in conscious object identification, and the dorsal visual processing system, which is involved in spatial, attentional, and behavioral processing, both conscious and unconscious. However, little is known about how these pathways are employed in reaching and grasping movements. In the present study, we attempted to tease apart contributions of the two pathways by manipulating two aspects of visual stimuli, i.e. object identity, which is expected to engage the ventral pathway, and object orientation, which is relevant for grasping actions and is thus expected to engage the dorsal pathway. In the experiment we conducted, healthy subjects performed reaching and grasping movements after being briefly exposed to a visual stimulus, and we measured the priming effects that the visual stimulus had for the reaching and grasping movements. In doing so, we distinguished four conditions, depending on (i) whether the preceding visual stimulus consisted of the same type of image as the image that the subject was subsequently shown and was to try to grasp and (ii) whether the orientation of the preceding visual stimulus was such that it was likely to elicit movement of the hand that the subject was to move in the grasping action subsequently. The results showed significant priming effects of both types with no interaction between them, suggesting that both visual pathways are independently involved in reaching and grasping movements.

Art appreciation in a laboratory setting has often been used as a methodology in research on aesthetic experiences but has limitations in terms of ecological validity. This study measured behavior using body tracking during free appreciation with a higher ecological validity under laboratory conditions and examined the relationship between canvas size and viewing distance. The results indicated that the viewing distance was positively correlated with the canvas size, especially the height, which suggested vertical viewing, required a bigger viewing distance than horizontal for the same area. We discuss characteristics of art viewing as an aesthetic experience based on data obtained from eye-tracking as well.

One goal of gait analyses in gait rehabilitation is to determine treatment effects. However, gait analysis, which is mainly based on observation, is limited in determining treatment effects because it is only a qualitative evaluation. Besides, quantitative gait analysis requires special facilities and equipment, including the knowledge and skills to handle them. Therefore, this study constructed a quantitative and simple gait analysis system using MediaPipe, which can automatically analyze gait cycles from gait videos captured by smartphones and other devices. Then, I created a classification model using neural networks to discriminate gait states based on the changes in knee and ankle angles estimated from the gait videos. Investigations revealed that although the model could discriminate 94.2% of the gait state changes in the right leg and 93.5% in the left leg, 68.1% of misclassifications occurred near the change in the gait state. This alteration is hypothesized to be because of ambiguities in the teacher data used to train the classification model. Hence, future work should further improve the discrimination rate and verify the limping and shuffling gait in nonhealthy subjects.

In Japan, the aging demographic is in an increasing need of support with their gait improvement and independence to prevent falling and injuries resulting in hospitalization. However, existing mixed reality methods are limited because that they cannot be implemented with a headset. Moreover, they use large-sized avatar computer graphics (CG) that easily obstructs the field of view. This study developed a gait improvement system based on footprint CG for only-headset application that does not readily block the view. The user was instructed to walk while stepping on the 3DCG footprints superimposed on the surrounding images by the system. Using motion capture, we verified whether the system influenced the user's gait (stride length, toe angle, and knee height) under 11 display conditions with varying stride lengths, angles, and heights of the footprints. The analysis results revealed that the user's stride length by up to 8.80%, toe angle by up to 2.44°, and knee height by up to 3.76 cm varied with the footprint stride length, angle, and height, respectively. Overall, the results suggested that the proposed can control the user's gait. Further refinement of the conditions and a large amount of subject data are needed to more accurately clarify the footprint presentation conditions in which the user's gait will improve subconsciously while using the system.

In recent years, many studies have been conducted on using deep learning to predict facial attractiveness. These studies are expected to have various applications such as face editing and beautification. Therefore, it is crucial to improve the prediction accuracy. In this study, I constructed a model for predicting facial attractiveness using the Vision Transformer, which has attracted much attention in the field of image recognition in recent years. The results show that the model improves the accuracy of facial attractiveness prediction compared to a simple convolutional neural network (CNN). By confirming the prediction factors in detail, this study is expected to contribute to our understanding of human perceptual characteristics and engineering applications.

In recent years, the use of VR and AR has become common in various situations. Most of these controllers are still hand-held. Hand-held controllers have a problem of reducing the sense of immersion. Therefore, in this study, we focus on wrist-type controllerswhich is not hand-held controllers. Although the recognition accuracy of gestures is lower with the wrist type than with the conventional method, it is superior in terms of immersiveness and cost for gesture recognition, we propose a method to estimate the degree of finger bending by using a photo reflector to measure the wrist shape caused by finger bending, and by using the linearity obtained by comparing the finger bending with the sensor values. By using the proposed method, the finger bending can be estimated.

Temporal dominance of sensations (TDS) is a sensory evaluation method that measures changes in several types of sensations over time during food sample tasting. Previous analytical methods for TDS do not classify different foods using the dynamicsensory information of the TDS method results. We developed a new approach to classify products by principal component analysis computation of the time-series information of sensory responses. This method could classify five different hams in a two-dimensionalprincipal component space. The time-series information possessed by each dimension was interpretable, which suggests that thedeveloped method is helpful for analyzing the temporal properties captured by TDS methods.

The overall evaluation of audio-visual content pertains to viewers’ affective experiences while watching them. We investigated these experiences and their mutual relationships by using scenes from movies with hug scenes. We selected 36 adjectives to describe the impressions of the videos and classified them into three layers: psychophysical, affective, and evaluative, based on a user study involving seven participants. They scored each of the 24 videos containing hug scenes according to these adjectives. The connections between the three layers were computed based on the scores of the adjectives. The four psychophysical factors influenced the four affective factors, which determined two overall evaluation factors: joyful and reassuring. The results will help develop strategies to enhance viewers’ emotional experiences while watching emotional video scenes and the criteria for evaluating emotional intensities.

Human body temperature consists of skin temperature, which is easily affected by the external environment, and core body temperature, which is maintained constant to protect the functions of the body's center. Core body temperature is less susceptible to the external environment and is maintained constant in order to protect the functions of the internal organs. The deeper the sleep, the greater the decrease in body temperature. Upon entering sleep, the body temperature threshold is lowered and heat dissipation through the skin becomes more active. When sleep is deep slow-wave sleep, heat dissipation becomes very active, accompanied by sweating and a large drop in body temperature. Recently, it has become possible to continuously measure human core body temperature using infrared sensors. Therefore, we attempted to actually measure the phenomenon in which core body temperature reaches a minimum value around 4:00 a.m. using continuous measurement of human core body temperature.

In recent years, animal therapy has been adopted in various fields such as medicine and welfare because it is expected to improve symptoms of dementia and depression as well as relieve stress. However, repeated exposure to a certain stimulus may cause a gradual loss of response to that stimulus (habituation), and previous studies have shown that habituation tends to occur with neutral stimuli that are neither rewarding nor harmful. In this study, 5 animal caretakers (2 female) and 5 healthy subjects (4 female) who were exposed to nature on a regular basis were fitted with wristwatch-type wearable sensors, and their biological parameters were compared during pony riding. The results showed that the caretakers did not show significant biometric changes in response to animal and were considered to be accustomed to it.

The need for technology to predict subjective experiences based on physiological signals has increased. Our study investigated the relationship between the comicalness of comedian videos and skin conductance responses recorded while watching videos. Through a user study involving eleven participants, subjective scores of a video's funniness were predicted by multiple linear regression analysis using five types of feature values computed from skin conductance responses. We found that the most influential feature is the number of local peaks in the skin conductance response per unit of time. The correlation coefficient between the observed and predicted funniness scores is 0.53. These findings are useful for the objective evaluation of entertainment experiences.

This study proposes a system that uses virtual reality to create the illusion of decreased training load through cross-modal effects, which are when two senses, such as sight and hearing, interact and influence one another. The system utilizes a head-mounted display and headphones for auditory and visual sensory presentation while participants engage in squatting exercises. We use a chair that adjusts seat elevation to prevent user from losing balance during exercise and a non-transmissive head-mounted display to project a 3D scene that changes based on user's movement. Then, we conducted an experimental evaluation to explore the relationship between immersive tendency characteristics and subjective fatigue level. The results indicated that the system's assistance primarily reduced subjective fatigue, with minimal impact on heart rate. Additionally, it was found that the subjects' inclination towards immersion may have contributed to an increase in subjective fatigue, as the discrepancy between the avatar's movements and the subjects' own movements became more pronounced.

The popularity of smartphones as a multi-purpose communication device has led to the development of a robust mobile game industry. The development of mobile games has become much easier than years ago, and developers can create mobile games through existing game engines, which also allows players to choose from a wide range of mobile games. In order to make the mobile games developed by themselves the choice of players among many games, a good gaming experience will be one of the most influential elements. There are few studies on User Interface (UI) and User Experience (UX) from the subject of mobile games, and UI and UX play an important role in the game experience. In 2022 the Material Design (MD) design specification for smartphone applications UI and UX provides guidelines for mobile application developers to follow in UI and UX design. As a smartphone application for entertainment purposes, mobile games still have shortcomings in UI and UX design following the MD specification.This study will focus on the application of MD to cell phone game UI and UX, aiming to provide mobile game developers with a reference UI and UX optimization design guide.

The global outbreak of COVID-19 that started in 2019 made face-to-face communication challenging. As one alternative, attention was shifted to the metaverse, virtual reality (VR) space on the Internet. Particularly, avatar communication using avatars garnered attention. Avatar communication aids diverse nonverbal information to be given to avatars and is presumed to be applied in different fields including education. Nevertheless, many existing metaverse systems have considerable environmental constraints to function. Additionally, the complex environment required to include nonverbal information makes it challenging for many people to use. The final objective of this study is to construct a metaverse system that can easily add nonverbal information. As an intermediate step, we executed the extraction of open/closed eyes by applying MediaPipe. The outcomes demonstrated a 86.70% increment in the percentage of correct responses in the case of wearing glasses compared to the prior investigation. Additionally, the avatar was able to move following the extracted data. Still, because of the small number of experimental situations, it is necessary to confirm whether the system is general-purpose or not. It is also necessary to integrate the system into a metaverse system to validate the actual operation.

A quantitative evaluation was performed by analysing the sound of mastication for the sensation of "crispy" when chewing food. It was confirmed that the loudness value increased and that many high-frequency components were included. On calculating the sharpness, it was found that the sharpness value of a sample with a large sensory level was large. It was suggested that there is a correlation between the shrillness of the different sounds perceived by humans.

English skills are becoming necessary for students who would like to give a presentation at international conferences. However, it is very difficult for non-native English speakers to speak in English because of the differences between English and their native languages. There are some ways to practice speaking English such as Shadowing, and if the audio is similar to the learner’s voices inside their heads, it should be more comfortable for the learners to listen to it and repeat after the audio. We propose a method to make English voices similar to the user’s voice by using Interactive Differential Evolution. Experiments were conducted with the concrete system of IDE. 9 examinees participated in the experiments through 10 generations with 6 vectors in each generation and kept choosing the better option. After the experiment, we randomly chose 2 voices from the initial and final generation and asked the examinees to evaluate them. As a result, significantly higher evaluations were obtained in the voices from the final generation.

Streaming services repetitively provide similar kinds of music, and listeners might get tired of them quickly. This is one of the serious problems for streaming services today. Boredom is developed with repetition, and it depends on personal preference. Therefore, boredom development depends on the time spans of the repetition and personal preferences when people listen to the same music over days. This study conducts an experiment that the participants repetitively listen to one music piece 294 times for seven days in a row to observe boredom development. We measured the boredom level as the reactional factor of the failure to keep the concentration and motivation of listening. As a result, the concentration decreased in the short-term, whereas the motivation decreased in the long-term. Therefore, we could distinguish the state of boredom by the length of the time span. In addition, compared to repetitive listening with a day as the short-term, repetitive listening every day in a week as the long-term had an equal or slightly higher power to generate boredom, but there is a weak correlation between boredom and preference for a music piece. In conclusion, the results showed that the amount of repetition had a stronger effect than personal preference for music, and people may get bored even with their favorite music when they listen too many times. Moreover, the behavior of the low-frequency alpha wave in the brain had only a weak relationship to the amount of listening within a day, not in the week.

Remote work has spread rapidly since the pandemic of COVID-19, making it more convenient to work from home for a large number of people. However, excessive work concentration can lead to serious health damage such as mental stress if not monitored. In this paper, we propose a deep learning-based scheme aimed at identifying the different stress levels caused by concentration while working on a PC. We perform a set of experimental tests designed to provoke different levels of stress, namely low, medium, high, and no stress. Dedicated wearable devices are used to collect Heart Rate Variability (HRV), Galvanic Skin Reaction (GSR), and Breath Chest Force (BCF) to train and test a CNN-based stress classifier. The result shows the ability of the proposed CNN model to correctly classify stress levels achieving an accuracy of 99.08%.

NeuroFeedback (NF) is a method of altering the brain information of users, and it has been widely applied in the fields of medical and welfare. Recently, the research which aimed at improving cognitive function in healthy subjects has attracted a lot of attention. Many studies used EEG frequency bands and behavioral indices to improve and evaluate cognitive function. However, the evaluation of cognitive function using brain information indices mainly on the discussion of EEG frequency band. In addition, the frequency band has been mainly treated as a fixed band (alpha band et al.). In this study, we trained Upper Alpha (UA) based on individual alpha frequency using a proposed NF method, and not only confirm the changes in UA, but also examines the changes of P300. We found that training UA significantly reduced the latency of P300. In the future, we will use a control group to investigate whether the reduction of P300 latency is caused by NF and how the number of NF affects the latency of P300.

In recent years, wearable sensors have been used to non-invasively obtain a variety of biometric information such as heart rate, pulse wave, acceleration, etc. What is the degree of personal identifiability of biometric information obtained from such wearable sensors? In Japan, the revised Personal Information Protection Law, which was fully enforced in 2017, clarified that personal identification codes such as DNA, facial features, and iris are included in personal information. And in recent years, consideration of human rights and privacy for technologies that monitor and track people has been called for. In this study, 14 parameters were extracted from wearable sensor data of 8 subjects over a 4-day period, and their personal identifiability was verified using machine learning. The results suggest that subjects whose biometric values are close to each other may be misidentified, and that subjects with large intra-individual variation in biometric information are significantly less discriminable.

Our lives have changed dramatically since the spring of 2020 due to the new coronavirus infection COVID-19. And in an environment where we are required to coexist with the virus for the foreseeable future, teleworking to work remotely and social distancing to maintain intervals between people are required. Thorough infection prevention measures" and "ensuring the availability of healthcare delivery systems" remain critical. Recent studies have shown that patients with moderate or severe coronary infections have reduced pulmonary diffusion function as a sequela. Thus, changes in the environment, in the human organism itself, naturally affect heart rate variability indices. To investigate the changes in heart rate variability and body acceleration between the young and the elderly groups, we collected data from the Allostatic State Mapping by Ambulatory ECG Repository (ALLSTAR) database on 1342 cases (mean age 22 ± 1 year) in the young group and 12,000 cases (mean age 22 ± 1 year) in the elderly group from 2019 to 2021.) and 12,994 cases (mean age 72 ± 1 years) in the older group from 2019 to 2021 were extracted from the ALLSTAR database and analyzed. Results showed that the younger group showed a decreasing trend in activity due to the spread of coronavirus (P<0.01). The elderly group showed no significant difference in activity in 2020, but the proportion of time spent in the supine position tended to increase (P<0.01).

Temporal dominance of sensation (TDS) is used to obtain the time-series of multiple types of sensory responses during food consumption. Results of existing analysis methods for TDS are the averages of all panels. Individual differences and their time-series similarity have seldom been studied. We defined a dissimilarity index to compare individual TDS trials and performed hierarchical clustering on TDS data of strawberries using the index. Fifty-one trials were classified into four clusters with different characteristics. The method will be useful for individual analyses of time-series sensory evaluation data.

This research tries to survey the estimates of the importance of information displayed to consumers before purchasing a product, using expected results from an eye-tracking device as a behavioral insight method. This study combines measurement by eye tracker and an individual interview survey; the participant is equipped with an eye-tracking device, and the control group (participants without time constraints) and the intervention group (participants with time constraints) are set. Then, the degree of importance placed on the displayed information when a product is bought is estimated using biometrics data. Firstly, the consumer’s gaze fixation on the area of interest in the indicated product information, including the participant is presented with two graphic labels, and the Carbon Dioxide Emissions and the Organic Cultivation are measured, for comparison and evaluation. Judgment is made by demonstrating the cognitive process and attention to a specific element. Then, looking at the consumption information that was paid attention to by the presence or absence of time constraints. No statistically significant differences were found in most of the displayed information, however, the Nutrition Value was displayed with a significant trend (10%). The time looking at the label was 0.93 secs without time constraints, but only 1/3 (0.30 secs) with them. In purchase status, no statistically significant difference was detected with them at Carbon Dioxide Emissions, however, the Organic Cultivation in the amount of gaze information and the number of gazes by purchasers.

Perceived quality in industrial design constitutes CMF (color, material, and finish). Previous studies have explored the impact of car color and materials used on consumer behavior; however, there are only few studies on the impact of the type of surface finish, which this study focuses on. In the automobile industry, matte finish is provided mainly for luxury products. It is also known that the exterior design of automobiles improves the perceived quality by reflecting light. In other words, matte finish and light reflection are positioned as opposite design features. In this study, the following hypothesis was derived based on the literature on glossy finish: a matte finish of a car’s exterior has a negative impact on product attractiveness. For verification, two designs with the same SUV styling but different surface finishes (matte finish and light reflection) were studied. This hypothesis was supported and assessed using paired comparisons in an online survey. The same result was obtained regardless of conditions, such as gender, age, and ownership. This study addresses the gaps in knowledge on the effects of finish on product attractiveness and suggests that practitioners should not blindly believe the conventional perceptions of the industry.

Elementary school students carry heavy backpacks and there are some reports that the heavy backpack induces fatigue and back pain. This study proposed a backpack structure to reduce a load and analyzed the effect of the backpack structure through an experiment. The key features of the backpack structure were a three-dimensional padded back panel and a curved board. In the experiment, five pressure sensors measured the pressures between the backpack and the participant's body parts. Both the three-dimensional padded back panel and the curved board increased the contact area between the back and the backpack. Two acceleration sensors also measured the three-dimensional acceleration of the backpack and the participant. The backpack structure decreased the load of the backpack in running with a significant difference. Comparison between results using the backpack and conventional backpack revealed the effectiveness of the proposed backpack structure.

To estimate garment impressions, we verified three regression models using design parameters. Using three-dimensional apparel simulation, we generated 375 images of a men's outdoor jacket by changing design parameters: length, waist, hem circumference, and sleeve circumference. Nine people evaluated cool-uncool (kakkoī-kakkowarui in Japanese) impressions of the garment images using a semantic differential method. With the design parameters, we obtained the estimated image impression using three regression models: multiple linear regression (MLR), neural network (NN), and light gradient boosting machine (LightGBM). We used correlation coefficient(𝑐𝑜𝑟𝑟) and adjusted coefficient of determination between evaluated and estimated impression values to evaluate estimation performance. As a result, the LightGBM with the design parameters showed the highest mean 𝑐𝑜𝑟𝑟 for all participants. It was thus found that the design parameters are effective in estimating the garment impression with LightGBM.

This study analyses the luthier's philosophy on traditional violin making through a literature review and online survey to investigate the sources of the affective value produced by the violin. Violins have existed for more than five centuries without changing their traditional artisan philosophy and design, without being taken in by industrial advances such as alternative materials and greater efficiency that have accompanied many technological innovations since the industrial revolution. The luthier's philosophy of artisanship, which has been passed down is considered key to these violins, known for their acoustic performance and appearance over time due to the use of natural materials and traditional techniques by skilled artisans. The results of this study suggest that these traditional violins have a traditional philosophy that affirms the individual character of the musical instrument and is conscious of its growth after it is worked.

The evaluation areas of learning in Japanese high schools include “Knowledge and Skills,” “Thinking, Judgment, and Expression,” and “Proactive Attitude to Learning.” Aiming to solve the problem of teachers’ subjectivity in evaluating “Proactive Attitude to Learning,” we propose a system for evaluating “Proactive Attitude to Learning” based on the number of blinks, a physiological index, and the perceived difficulty of learning, a psychological index. The evaluation by this study system is 86% accurate with a ±1 margin of error. To indicate that the grade processing of a teacher can be substituted.