• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.8
• /
• pp.2068-2082
• /
• 2023

With the rapid development of deep learning, Depth Map Super-Resolution (DMSR) method has achieved more advanced performances. However, when the upsampling rate is very large, it is difficult to capture the structural consistency between color features and depth features by these DMSR methods. Therefore, we propose a color-image guided DMSR method based on iterative depth feature enhancement. Considering the feature difference between high-quality color features and low-quality depth features, we propose to decompose the depth features into High-Frequency (HF) and Low-Frequency (LF) components. Due to structural homogeneity of depth HF components and HF color features, only HF color features are used to enhance the depth HF features without using the LF color features. Before the HF and LF depth feature decomposition, the LF component of the previous depth decomposition and the updated HF component are combined together. After decomposing and reorganizing recursively-updated features, we combine all the depth LF features with the final updated depth HF features to obtain the enhanced-depth features. Next, the enhanced-depth features are input into the multistage depth map fusion reconstruction block, in which the cross enhancement module is introduced into the reconstruction block to fully mine the spatial correlation of depth map by interleaving various features between different convolution groups. Experimental results can show that the two objective assessments of root mean square error and mean absolute deviation of the proposed method are superior to those of many latest DMSR methods.

• Animal Bioscience
• /
• v.37 no.5
• /
• pp.817-825
• /
• 2024

Objective: The aim of this study was to identify suitable polynomial regression for modeling the average growth trajectory and to estimate the relative development of the rib eye area, scrotal circumference, and morphometric measurements of Guzerat young bulls. Methods: A total of 45 recently weaned males, aged 325.8±28.0 days and weighing 219.9±38.05 kg, were evaluated. The animals were kept on Brachiaria brizantha pastures, received multiple supplementations, and were managed under uniform conditions for 294 days, with evaluations conducted every 56 days. The average growth trajectory was adjusted using ordinary polynomials, Legendre polynomials, and quadratic B-splines. The coefficient of determination, mean absolute deviation, mean square error, the value of the restricted likelihood function, Akaike information criteria, and consistent Akaike information criteria were applied to assess the quality of the fits. For the study of allometric growth, the power model was applied. Results: Ordinary polynomial and Legendre polynomial models of the fifth order provided the best fits. B-splines yielded the best fits in comparing models with the same number of parameters. Based on the restricted likelihood function, Akaike's information criterion, and consistent Akaike's information criterion, the B-splines model with six intervals described the growth trajectory of evaluated animals more smoothly and consistently. In the study of allometric growth, the evaluated traits exhibited negative heterogeneity (b<1) relative to the animals' weight (p<0.01), indicating the precocity of Guzerat cattle for weight gain on pasture. Conclusion: Complementary studies of growth trajectory and allometry can help identify when an animal's weight changes and thus assist in decision-making regarding management practices, nutritional requirements, and genetic selection strategies to optimize growth and animal performance.

• Journal of dental hygiene science
• /
• v.24 no.1
• /
• pp.22-28
• /
• 2024

Background: Particulate matter (PM) has been extensively observed due to its negative association with human health. Previous research revealed the possible negative effect of air pollutant exposure on oral health. However, the predictive model between air pollutant exposure and the prevalence of periodontitis has not been observed yet. Therefore, this study aims to propose a predictive model for the number of patients with periodontitis exposed to PM and atmospheric factors in South Korea using deep learning. Methods: This study is a retrospective cohort study utilizing secondary data from the Korean Statistical Information Service and the Health Insurance Review and Assessment database for air pollution and the number of patients with periodontitis, respectively. Data from 2015 to 2022 were collected and consolidated every month, organized by region. Following data matching and management, the deep neural networks (DNN) model was applied, and the mean absolute percentage error (MAPE) value was calculated to ensure the accuracy of the model. Results: As we evaluated the DNN model with MAPE, the multivariate model of air pollution including exposure to PM_2.5, PM₁₀, and other atmospheric factors predict approximately 85% of the number of patients with periodontitis. The MAPE value ranged from 12.85 to 17.10 (mean±standard deviation=14.12±1.30), indicating a commendable level of accuracy. Conclusion: In this study, the predictive model for the number of patients with periodontitis is developed based on air pollution, including exposure to PM_2.5, PM₁₀, and other atmospheric factors. Additionally, various relevant factors are incorporated into the developed predictive model to elucidate specific causal relationships. It is anticipated that future research will lead to the development of a more accurate model for predicting the number of patients with periodontitis.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.2
• /
• pp.123-129
• /
• 2017

This paper proposes a new nonnegative matrix factorization (NMF) based direction-of-arrival (DOA) estimation method for multiple sound sources using a dual microphone array. First of all, sound signals coming from the dual microphone array are segmented into consecutive analysis frames, and a steered-response power phase transform (SRP-PHAT) beamformer is applied to each frame so that stereo signals of each frame are represented in a time-direction domain. The time-direction outputs of SRP-PHAT are stored for a pre-defined number of frames, which is referred to as a time-direction block. Next, In order to estimate DOAs robust to noise, each time-direction block is normalized along the time by using a block subtraction technique. After that, an unsupervised NMF method is applied to the normalized time-direction block in order to cluster the directions of each sound source in a multiple sound source environments. In particular, the activation and basis matrices are used to estimate the number of sound sources and their DOAs, respectively. The DOA estimation performance of the proposed method is evaluated by measuring a mean absolute error (MAE) and the standard deviation of errors between the oracle and estimated DOAs under a three source condition, where the sources are located in [$-35{\circ}$, 5m], [$12{\circ}$, 4m], and [$38{\circ}$, 4.m] from the dual microphone array. It is shown from the experiment that the proposed method could relatively reduce MAE by 56.83%, compared to a conventional SRP-PHAT based DOA estimation method.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.5
• /
• pp.338-346
• /
• 2023

During isometric elbow flexion, forearm length should be an important factor to determine not only joint torque but also maximum endurance time (MET), when the forearm is perpendicular to the direction of the force. The purpose of this paper is to examine the effect of forearm length as an additional factor on empirical models of MET such as an exponential model and a power model during isometric elbow flexion. Thirty volunteers participated in our experiment to measure factor variables such as circumferences and lengths of their upper and lower arms. Their METs were measured according to the percent of maximum voluntary contraction intensity (%MVC). For the multiple linear regression model of ln(MET) using these measurements, significant variables could be observed in %MVC and forearm lengths (P<0.05). The empirical models were assessed by these models using forearm length as the additional factor. Mean absolute deviations (MAD) between the measured METs amd the two empirical models were about 19.4 [s], but MAD using models applied forearm lengths were reduced to about 16.2 [s]. The correlation coefficients and intraclass correlation coefficients were about 0.87, but those applied forearm lengths were increased to about 0.91. These results demonstrated that forearm length was a significant additional factor to the empirical model.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.1009-1029
• /
• 2023

Urban trees play a vital role in urban ecosystems,significantly reducing impervious surfaces and impacting carbon cycling within the city. Although previous research has demonstrated the efficacy of employing artificial intelligence in conjunction with airborne light detection and ranging (LiDAR) data to generate urban tree information, the availability and cost constraints associated with LiDAR data pose limitations. Consequently, this study employed freely accessible, high-resolution multispectral satellite imagery (i.e., Sentinel-2 data) to estimate fractional tree canopy cover (FTC) within the urban confines of Suwon, South Korea, employing machine learning techniques. This study leveraged a median composite image derived from a time series of Sentinel-2 images. In order to account for the diverse land cover found in urban areas, the model incorporated three types of input variables: average (mean) and standard deviation (std) values within a 30-meter grid from 10 m resolution of optical indices from Sentinel-2, and fractional coverage for distinct land cover classes within 30 m grids from the existing level 3 land cover map. Four schemes with different combinations of input variables were compared. Notably, when all three factors (i.e., mean, std, and fractional cover) were used to consider the variation of landcover in urban areas(Scheme 4, S4), the machine learning model exhibited improved performance compared to using only the mean of optical indices (Scheme 1). Of the various models proposed, the random forest (RF) model with S4 demonstrated the most remarkable performance, achieving R² of 0.8196, and mean absolute error (MAE) of 0.0749, and a root mean squared error (RMSE) of 0.1022. The std variable exhibited the highest impact on model outputs within the heterogeneous land covers based on the variable importance analysis. This trained RF model with S4 was then applied to the entire Suwon region, consistently delivering robust results with an R² of 0.8702, MAE of 0.0873, and RMSE of 0.1335. The FTC estimation method developed in this study is expected to offer advantages for application in various regions, providing fundamental data for a better understanding of carbon dynamics in urban ecosystems in the future.

• Journal of Distribution Science
• /
• v.10 no.4
• /
• pp.29-36
• /
• 2012

Research on subjective well-being (SWB) has flourished in recent years. As SWB determines cognitive and motivational processes, including social comparison and cognitive dissonance, it determines how consumers make decisions, including the comparison and evaluation of alternatives. Considering that the comparison and evaluation of alternatives is related to social comparison and cognitive dissonance, the influence of SWB on the comparison and evaluation of alternatives needs to be investigated. This research aims to examine the effect of SWB on the comparison and evaluation of alternatives, especially when people acquire additional information about their chosen or non-chosen alternatives, leading to a change of absolute/relative value of alternatives. The reasonable price of an alternative as evaluated by individuals is used as a measure reflecting the perceived value of an alternative. Putting all of this together, the current study intended to investigate the influence of absolute and relative value on the reasonable price of an alternative depending on SWB. Participants were randomly assigned to one of two experiment groups (deterioration of non-chosen alternative vs. improvement of non-chosen alternative). After reading consumer report ratings of alternatives shown on monitor screens, participants chose one of the alternatives, followed by the change of the consumer report ratings (deterioration of non-chosen alternative vs. improvement of non-chosen alternative). Participants evaluated the reasonable price of their chosen alternative based on the provided price of the non-chosen alternative. Two weeks after the experiment, they were asked to answer survey questionnaire on SWB measures. A regression was performed on the reasonable price with experiment groups, mean-centered SWB, and their interaction. There was a significant simple effect of groups and SWB. More importantly, these effects were qualified by the predicted interaction of groups and SWB. To interpret this interaction further, simple slope tests were performed on the price when SWB was centered at one standard deviation above (i.e., happy people) and below (i.e., unhappy people) the mean. As predicted, happy people rated the reasonable price of the chosen alternative higher in the improvement of non-chosen alternative group than in the deterioration of non-chosen alternative group. Conversely, unhappy people showed no price difference between groups. These results show that happy people pay attention to the absolute value of the alternative, whereas unhappy people give more weight to the relative value as well as to the absolute value of a chosen alternative, indicating that unhappy people are more sensitive to the negative information of a non-chosen alternative compared to happy people. The present research expanded the existing research stream on SWB by showing the influence of SWB on the consumers' evaluation of alternatives. Furthermore, this study adds to previous research on SWB and social comparison by suggesting that unhappy people tend to be more sensitive to negative social comparison information of alternatives even when a target of social comparison is not explicitly present. Moreover, these results yield some managerial implications on how to provide product information based on SWB in order to make products more attractive among the alternatives available to consumers.

• Women's Health Nursing
• /
• v.2 no.1
• /
• pp.88-105
• /
• 1996

The purpose of this study was to find out physical and emotional status, and nursing needs of the pregnant women who were hospitalized by premature labor. The research respondents were 96 from four university hospitals located in Seoul, from June 30, 1996 to September 15, 1995. The research instrument was consisted of 14 items of physical status(discomforts) (Cronbach's=0.86), 17 items of emotional status (Cronbach's=0.89), 33 items of nursing needs (Cronbach's=0.94), and they were measured by 5 level of Likert Scale. The data were analyzed by frequency, percentage, mean standard deviation, ANOVA, Pearson correlation coefficient as the statistical techniques in the program of SPSS/$PC^+$. The findings were as follows : 1. The perception of physical status was mainly about physicl discomforts during the hospital stay. It included four categories about 'absolute bed rest' 3.48, 'hospital foods' 3.38, 'health care teams' 2.93, 'hospital environment' 2.83 in order of mean of discomforts. The most discomfortable one was "malodor by not doing personal hygiene." The next one was "urination and defecation on the bed using bedpan." 2. The perception of the emotional status was about negative mood related to 'fetus', 'hospitalization' perse, 'personal situation.' The highest score of negative mood was "I am afraid that the baby's condition will be bad if I deliver it before full term." The next one was "I am anxious about whether my baby will be in incubator if I deliver it before full term." 3. The highest mean score among items of nursing needs was "Nurses observe whether the labor come or not with concerns." The next one was "Nurses observe the fetal movement and check up the fetal heart sound." The lowest one was "Nurses help me when I need bedpan." 4. Nursing needs were consisted of four categories : professional, educational, emotional, and physical. The mean score of them was high in professional, educational, emotional, and physical need in order. 5. The physical status was related to "Experience of treatment for maintenance of pregnancy" and "Experience of hospitalization by premature labor". The emotional status was related to "Type of delivery" and "Type of habitation." 6. In the correlation of physical and emotional status, it showed positive correlation between them. The higher score of physical discomfort, the higher score of negative mood(r=0.5113, p=0.0001).

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.14 no.4
• /
• pp.195-204
• /
• 2009

In order to estimate sea surface current fields in the East Sea, we examined characteristics of mean dynamic topography (MDT) fields (or mean surface current field, MSC) generated from three different methods. This preliminary investigation evaluates the accuracy of surface currents estimated from satellite-derived sea level anomaly (SLA) data and three MDT fields in the East Sea. AVISO (Archiving, Validation and Interpretation of Satellite Oceanographic data) provides a MDT field derived from satellite observation and numerical models with $0.25^{\circ}$ horizontal resolution. Steric height field relative to 500 dbar from temperature and salinity profiles in the East Sea supplies another MDT field. Trajectory data of surface drifters (ARGOS) in the East Sea for 14 years provide another MSC field. Absolute dynamic topography (ADT) field is calculated by adding SLA to each MDT. Application of geostrophic equation to three different ADT fields yields three surface geostrophic current fields. Comparisons were made between the estimated surface currents from the three different methods and in-situ current measurements from a ship-mounted ADCP (Acoustic Doppler Current Profiler) in the southwestern East Sea in 2005. For offshore areas more than 50 km away from the land, the correlation coefficients (R) between the estimated versus the measured currents range from 0.58 to 0.73, with 17.1 to $21.7\;cm\;s^{-1}$ root mean square deviation (RMSD). For coastal ocean within 50 km from the land, however, R ranges from 0.06 to 0.46 and RMSD ranges from 15.5 to $28.0\;cm\;s^{-1}$. Results from this study reveal that a new approach in producing MDT and SLA is required to improve the accuracy of surface current estimations for the shallow costal zones of the East Sea.

• Journal of Biomedical Engineering Research
• /
• v.28 no.3
• /
• pp.410-416
• /
• 2007

This paper presents quantitative analysis of a training system based on an unstable platform and a visual interactive system for improving sense of equilibrium. The training system consists of an unstable platform, a force plate, a safety harness, a monitoring device, and a personal-computer. To confirm the effects of the training system, fifteen young volunteers and five elderly volunteers went through a series of balance training using the system. During the training, we measured relevant parameters such as the time a subject maintain his or her center of pressure on a target, the time a subject moves his or her center of pressure to the target, and the mean absolute deviation of the trace before and after training with this system and training programs to evaluate the effects of the training. The results showed that the training system can successfully assess the gradual improvement of the postural control capability of the subject in the system and showed a possibility of improving balance of the subject. Moreover, the significant improvement in the postural capability of the elderly subject suggests that elderly subjects can benefit more from the training using the system for the improvement of sense of equilibrium.