To estimate the garment impression, we verified three regression models using design parameters, geometrical and texture features of images, and convolutional features of images. Adopting three-dimensional apparel simulation, we generated 375 images of a men's outdoor jacket by changing design parameters, namely the length, waist, hem circumference, and sleeve circumference. Nine participants evaluated the cool-uncool (kakkoī-kakkowarui in Japanese) impression of the garment images using a semantic differential method. We used the measured widths, angles, and G-type Fourier descriptors of the jacket images as geometrical features. For texture features, the fractal dimension and Haralick texture features (Asm, Entropy, Contrast, Correlation) of the images were used. Convolutional features were obtained from the images using a convolutional neural network. By using the design parameters and the obtained features, we estimated the image impression using three regression models: multiple linear regression, neural network, and light gradient boosting machine (LightGBM) models. As a result, the LightGBM with the design parameters had the highest mean correlation coefficient for all participants. The inclusion of design parameters was thus found to be effective in estimating the impression based on garment design parameters with LightGBM.

Psychophysical and affective experiences while watching audiovisual content can be antecedents to determine the overall evaluation of viewing experiences. However, the layered relationships among these experiences have been hardly discussed. We investigated these experiences and their semantic structure while watching hug scenes. We selected 38 adjectives describing hugs and classified them into three layers: psychophysical, affective, and overall evaluation. Participants scored each of the 24 videos containing hugging scenes using these adjectives. The structure among the three layers was computed: the four psychophysical factors affected the four affective factors, which in turn affected the two overall evaluation factors, i.e., joyful and reassuring. The model was confirmed to have statistical validity by structural equation modeling and semantic validity by experiments using dummy links. The results will lead to the determination of measures to enhance affective experiences when viewing videos, and the formulation of criteria for measuring and evaluating affective experiences.

It is useful to extract the time factor of gait from captured gait videos. However, this requires frame-by-frame counting, which is expensive in terms of manpower and time. In this study, we developed discrimination models to discriminate between the stance phase and the swing phase of a walker from a walking video. Using MediaPipe, a marker-less motion capture system that can be used with a single camera, we discriminated the stance phase and swing phases of a walker from the angular changes of the waist, knee, and ankle on each side of the walker in each frame. The results showed that the right leg and left leg were discriminated with 95.1% and 95.0% accuracy, respectively. The gait cycle was calculated from the discrimination results, and the average deviation was only 7.4% for the right leg and 4.2% for the left leg.

We have been developing a cognitive, brain-machine interface (BMI)-based, training system called the “Neurotrainer.” This system was initially designed to detect averaged event-related potentials (ERPs), which reflect momentary heightened attention, allowing these individuals to participate in cognitive training without the need for hands-on interaction. In this study, we expanded our method to decode single-trial ERPs during a racing game, with the expectation that neurofeedback would accelerate the training process. We assessed the performance of the prototype system with healthy volunteers. The decoding accuracy of the target character was approximately 54% for a single trial and 83% for five trials (chance level = 12.5%). Moreover, ERP responses were stronger in the feedback condition than in the no-feedback condition. These results suggest that the BMI could be an effective tool for cognitive training, as real-time neurofeedback influences the brain activation of the players.

We investigated the effects of stroking stimuli near the external auditory meatus on the emotions aroused by the experience of listening to sounds. Previous studies demonstrated that vibratory stimuli to the upper body manipulate emotions while watching videos or listening to sounds; however, none examined the effects of stroking stimuli near the external auditory meatus through which the vagus nerve extends. This study investigated the effects of stroking stimuli to the outer ear on emotions for each of six emotionally evocative sounds that arouse pleasant or unpleasant feelings. They comprised the sounds of rain, shampoo, insects’ buzz, and horrifying winds. When the sound stimuli were presented with stroking stimuli at the ear, participants’ emotions mostly changed to be more pleasant and sleepy, that is less arousing. These findings are expected to help in the development of haptic interfaces for more emotionally appealing content.

Face tracking is a necessary technique for facilitating nonverbal communication between avatars in the metaverse space. In this study, we investigated a dynamic measurement approach for real-time representation of open/closed eye. The conventional method of extracting open/closed eye based on the aspect ratio of the eye has been the mainstream method, but it encounters issues with false detection when the neck is tilted or when the user wears glasses during live transmission. To address these limitations, we developed detection method based on the ratio of the distance between the outer and inner eyelid, complemented by a calibration technique. The detection accuracy was verified by comparing the results with camera images. The open/close eye extraction system used a web camera and Google’s MediaPipe. The results demonstrated the accuracy of open/closed eye detection was 78.68%, even when the head was in motion, and 72.96% even when the participant was wearing eyeglasses.

In this study, we developed a system to quantitatively evaluate self-study attitudes based on biometric information, with a specific focus on the number of blinks, head swaying, and brainwaves. The experiment involved 24 students from a Kanagawa Prefectural high school, and they participated in two sets of 20-minute self-study sessions. We compared the system evaluation values derived from biometric information with evaluations provided by teachers. “Teacher Evaluation” was based on the “Proactive attitude toward learning.” As a result, 95.45% of valid data aligned with teacher evaluations, providing data that could assist teachers (with a difference of 1 or less between Teacher Evaluation and System Evaluation). The utilization of system-calculated values for assessing learning attitudes has the potential to enable teachers to conduct fair and efficient grading processes.

Taste is perceived based on chemical and physical factors. The former includes taste and smell, while the latter includes texture, appearance, and sound. Physical factors have a considerable impact on the tastiness of solid foods. In this study, a quantitative evaluation is performed by analysing the sound of chewing for the ‘crispy’ sensation when chewing food. It is confirmed that the loudness increases and that many high-frequency components are included. The sharpness calculation results reveal that the sharpness value of a sample with a high sensory level is large. The results indicate a correlation exists between the shrillness of different sounds perceived by humans.

In this paper, we used ALLSTAR big data to investigate changes in Heart rate variability(HRV) and body acceleration(BA) in younger (20s) and elderly groups (70s) during the COVID-19 pandemic. Compared to before (2019) and during (2020, 2021) the COVID-19 pandemic, significant decrease in HRV was observed in both the younger and the elderly groups (P<0.01). BA in the younger groups decreased significantly in 2020 compared to 2019, and no significant difference was observed in the elderly group. Mental stress due to the COVID-19 pandemic is thought to be one of the factors contributing to the decrease in HRV. In the elderly group, respiratory frequency was faster in 2020 than in 2019 (P<0.01) and slower in 2021 than in 2020 (P<0.01). It is thought that the respiratory frequency is changing due to the mask life.

Violins have existed for five centuries without changing the philosophy and design of traditional artisans, without being taken in by industrial advances such as alternative materials and efficiency that have accompanied many technological innovations since the Industrial Revolution. Violin has a long historical background with traditions inherited by the luthiers have attracted numerous researchers to conduct scientific research. However, it is not clear to what extent luthiers are interested in and aware of scientific research. Thus, this study was conducted to investigate the attitudes of luthiers toward scientific research. The results of the survey indicated that luthiers are highly interested in scientific research and seek ways to deepen their own understanding by connecting science their own practice through visualization of violin phenomena, and that scientific research may have a beneficial effect on luthier development as an affective support.

Erratum
International Journal of Affective Engineering Vol.23 No.3 pp.299-308 (2024)

Line 3 on page 304

Incorrect
On the other hand, because nothing works On the other hand, only 0.3% of the luthier responded Because nothing works.

Correct
On the other hand, only 0.3% of the luthier responded because nothing works.