• Journal of Physiology & Pathology in Korean Medicine
• /
• v.27 no.5
• /
• pp.683-687
• /
• 2013

Evacuation disorder(ED) is frequently observed in the elderly people. In this study, we investigated the tongue color properties in the elderly. 327 subjects were participated in this study and classified into normal group (n=95) and ED group (n=23) by two Korean Oriental Medicine doctors. The tongue images were acquired by using computerized tongue diagnosis system, and its color were linearly corrected base on CIE $L^*a^*b^*$ values of 12 color samples. The tongue region was segmented from acquired image and divided into two regions along the vertical direction. In order to estimate color properties of the tongue, a color histogram was calculated for the root region based on the CIE $L^*$ and $a^*$ values, and differences of color histogram values between normal and ED groups were computed based on the Mann-Whitney U test. As results, pixels corresponding to typical colors of the pale tongue and thin tongue coating were significantly more distributed in ED than those in normal group(p<0.05). The tongue color of the root region in ED was revealed to be different from those in healthy subjects.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.2
• /
• pp.401-406
• /
• 2008

Fall event detection is one of the most common problems for elderly people, especially those living alone because falls result in serious injuries such as joint dislocations, fractures, severe head injuries or even death. In order to prevent falls or fall-related injuries, several previous methods based on video sensor showed low fall detection rates in recent years. To improve this problem and outperform the system performance, this paper presented a novel approach for fall event detection in the elderly using a subtraction between successive difference images and temporal templates in real time environment. The proposed algorithm obtained the successful detection rate of 96.43% and the low false positive rate of 3.125% even though the low-quality video sequences are obtained by a USB PC camera sensor. The experimental results have shown very promising performance in terms of high detection rate and low false positive rate.

• Fashion & Textile Research Journal
• /
• v.14 no.5
• /
• pp.720-729
• /
• 2012

This study investigates trends and design characteristics of recent eco fashion designs on websites. For such purposes, 1185 pictures were collected from the websites of 12 eco fashion brands from 2006 to 2010 to analyze current status and design characteristics. Content analysis and statistical analysis using SPSS will be conducted for data analysis. The results of the research are as follows. First, the change difference according to the year of the eco fashion design. The focus was on, the natural image (from 2006 to 2008), the romantic image (from 2008 to 2009), and vintage, multi, and modern (from 2010). It was noticeable that the forms, colors, and materials changed simultaneously with the various images. The changing progress of eco fashion design was on the design changes according to fashion image changes. Second, after an examination of the characteristic difference of eco fashion designs according to seasons, the difference was shown as a natural and romantic image in the S/S season as well the vintage and classical image focused on the F/W season. It is figurative that S/S season shows a romantic image as well as magnifies a sportive image that is natural and active. Multi, natural and vintage images mostly appeared for the F/W season. In conclusion, eco fashion design is influenced by fashion trends, yearly changes, and seasons.

• Fashion & Textile Research Journal
• /
• v.12 no.5
• /
• pp.555-563
• /
• 2010

This research has attempted for a categorization by contemplating on concepts and characteristics of eco fashion design through analysis of precedent studies and to study the design characteristics, images, and internal values through keyword and design codes which appeared in the precedent studies. The subject of analysis was mostly focused on the theses published in international and domestic academic journals from 1990s to September 2009. The design characteristics of each eco fashion design were analyzed by classifying by form, detail, color, fabric and pattern. Method of analysis did content analysis. The results of the research can be summarized as follows. First of all, types of eco fashion design were human-ecology design, natural-ecology design, and social-ecology design. Secondly, the human-ecology design was presented a natural and comfortable form, color of the nature, and functional and new materials. The natural-ecology design was presented a natural silhouette, natural colors, and natural fiber. The social-ecology design were used a loose silhouette and over-size forms, natural colors, and recycled materials and bio fabric. Thirdly, the images per type of eco fashion design were Zen, sportive, natural, and modern image. And the internal values were presented efficiency, health-orientation, naturalness, and continuity.

• The Journal of Korea Robotics Society
• /
• v.15 no.3
• /
• pp.269-276
• /
• 2020

As we become an aging society, the number of elderly patients continues to increase. Pressure sores that can easily occur in patients with trauma cause serious socio-economic problems. In general, prevention of bedsores through predicting the patient's posture is being developed. Developed method usually use artificial intelligence techniques to estimate the patient's posture by measured pressure images in the mattress. In this method, it has a problem the reduction of estimation accuracy when posture of patient is changed. Therefore, it is necessary to use the filter of pressure images in the position transition of patient. In this paper, we propose an algorithm to predict the patient's posture, and an algorithm to reduce the ambiguity that can occur in the patient's posture transition section. By obtaining stable data through this algorithm, learning/prediction stability of the neural network can be expected, and prediction performance is improved accordingly. Through experiments, the effectiveness of the algorithm was verified.

• Journal of Biomedical Engineering Research
• /
• v.44 no.5
• /
• pp.329-335
• /
• 2023

Perceived age is defined as age estimated based on physical appearance. Perceived age is an important indicator of the overall health status of the elderly. This is because people who appear older tend to have higher rates of morbidity and mortality than people of the same chronological age. Although perceived age is an important indicator, there is a lack of objective methods to quantify perceived age. In this paper, we construct a quantified perceived age model from face images using a convolutional neural network. The face images are enlarged to super-resolution and the skin, an important feature in perceived age, is made clear. Moreover, through Tanh-polar transformation, the central area of the face occupies a relatively larger area than the boundary area, helping the neural network better recognize facial skin features. The experimental results show mean absolute error (MAE) of 6.59, showing that the proposed model is superior to existing method.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.808-811
• /
• 2009

Robovie-R2 [1], developed by ATR, is a 110cm high, 60kg weight, two wheel drive, human like robot. It has two arms with dynamic fingers. It also has a position sensitive detector sensor and two cameras as eyes on his head for recognizing his surrounding environment. Recent years, we have carried out a project to integrate new functions into Robovie-R2 so as to make it possible to be used in a dining room in healthcare center for helping serving meal for elderly. As a new function, we have developed software system for adaptive movement control of Robovie-R2 that is primary important since a robot that cannot autonomously control its movement would be a dangerous object to the people in dining room. We used the cameras on Robovie-R2's head to catch environment images, applied our original algorithm for recognizing obstacles such as furniture or people, so as to control Roboie-R2's movement. In this paper, we will focus our algorithm and its results.

• Progress in Medical Physics
• /
• v.24 no.1
• /
• pp.25-34
• /
• 2013

To investigate effects of phase mask on susceptibility-weighted images (SWI) using voxel-based analyses in normal elderly subjects. A three-dimensional (3D) gradient echo sequence ran to obtain SWIs in 20 healthy elderly subjects. SWIs with two (SWI2) and four (SWI4) phase multiplications were achieved with positive (PSWI) and negative (NSWI) phase masks to investigate phase mask effects. The voxel-based comparisons were performed using paired t-tests between PSWI and NSWI and between SWI2 and SWI4. Differences of signal intensities between magnitude images and SWI4 were larger than those between magnitude images and SWI2s. Differences of signal intensities between magnitude images and PSWIs were larger than those between magnitude images and NSWIs. Moreover, the signal intensities from NSWI2s and NSWI4s were greater than those from PSWI2s and PSWI4s, respectively. More differences of signal intensities between NSWI4 and PSWI4s were found than those between NSWI2s and PSWI2s in the whole brain images. The voxel-based analyses of SWI could be beneficial to investigate susceptibility differences on the entire brain areas. The phase masking method could be chosen to enhance brain tissue contrast rather than to enhance venous blood vessels. Therefore, it is recommended to apply voxel-based analyses of SWI to investigate clinical applications.

• Imaging Science in Dentistry
• /
• v.52 no.2
• /
• pp.197-207
• /
• 2022

Purpose: This study evaluated the associations of the dental arch form, age-sex groups, and sagittal root position (SRP) with alveolar bone thickness of the maxillary central incisors using cone-beam computed tomography (CBCT) images. Materials and Methods: CBCT images of 280 patients were categorized based on the dental arch form and age-sex groups. From these patients, 560 sagittal CBCT images of the maxillary central incisors were examined to measure the labial and palatal bone thickness at the apex level and the palatal bone at the mid-root level, according to the SRP classification. The chi-square test, Kruskal-Wallis test, and multiple linear regression were used for statistical analyses. Results: Significant differences were found in alveolar bone thickness depending on the arch form and SRP at the apex level. The square dental arch form and class I SRP showed the highest bone thickness at both levels of the palatal aspect. The taper dental arch form and class II SRP presented the highest bone thickness at the apex level of the labial aspect. No association was found between the dental arch form and SRP. Elderly women showed a significant association with thinner alveolar bone. Age-sex group, the dental arch form, and SRP had significant associations with alveolar bone thickness at the apex level. Conclusion: The patient's age-sex group, dental arch form, and SRP were associated with alveolar bone thickness around the maxillary central incisors with varying magnitudes. Therefore, clinicians should take these factors into account when planning immediate implant placement.

• Korean Journal of Cognitive Science
• /
• v.20 no.1
• /
• pp.79-107
• /
• 2009

Episodic memory, i.e. memorization of information within a spatiotemporal environment, is affected Alzheimer's disease(AD), but its impairment may also be occurred in the normal aging process. The purpose of this study is to analyze and evaluate memory in with Dementia of Alzheimer Type by examining their cognitive skills in episodic memory using the technique. This new method involves assessing the mental images the subject's own past in the mind like projected and movies. Three patients in the early stage of Dementia of Alzheimer Type, one with mild depression, and 2 healthy controls for comparison were asked to retrieve their episodic memory of the previous day, week, month, and a day testing day. The answers were then analyzed with regards to their specific features as emotional state, color, and time order. In the following day, the subjects were tasked to recall again the images they reproduced in the day's test order to observe of memory. Results showed that all 3 patients failed to arrange the retrieved images in time order and their images of the previous day were unclear in color and were stationary like photographs, even when they reproduced the mental images at much quantity as controls. patients could not remember particular events of yesterday, and only recalled the general occurrences of every day life. These results suggest that in the early stage of Dementia of Alzheimer Type, difficulties in the retrieval of recent episodic memory begin to primarily occur, and qualitative impairment happens earlier than quantitative.