• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.

• Science of Emotion and Sensibility
• /
• v.13 no.3
• /
• pp.541-550
• /
• 2010

The present study examined whether the physical similarity of test stimuli affects P300 amplitude and detection accuracy for the P300-based concealed information test (P300 CIT). As the participant pretended suffering from memory impairment by an accident, own name was used as a concealed information to be probed by the P300 CIT in which the participant discriminated between a target and other (probe, irrelevant) stimuli. One group of participants was tested in the easy task condition with low physical similarity among stimuli, the other group was tested in the difficult task condition with high physical similarity among stimuli. Using the base-to-peak P300 amplitude, the interaction effect of task difficulty and stimulus type was significant at $\alpha$=.1 level (p=.052). In the easy task condition the difference of P300 amplitude between the probe and the irrelevant stimuli was significant, while in the difficult task condition the difference was not significant. Using peak-to-peak P300 amplitude, on the other hand, the interaction effect of task difficulty and stimulus type was not significant with significant differences of P300 amplitude between the probe and the irrelevant stimuli in both task difficulty conditions. The difference of detection accuracy between task conditions was not significant with both measures of P300 amplitude although the difference was much smaller when peak-to-peak P300 amplitude was used. The results suggest that the efficiency of P300 CIT would not decrease even when the perceptual similarity among test stimuli is high.

• Trans-
• /
• v.1
• /
• pp.21-44
• /
• 2016

Advertisement is composed with symbol and sign with messages trying to express. Especially, ad with dancer introduces goods or meaning of contents with the motion of dance. In this, contents of dance or motion of dancer contains symbol and sign, understanding how ad and dance are expressed meanings with which symbol and the symbolic meaning of dance or dancer on ad. To that end, this study is for analyzing expressed symbol with dance corresponds with the aim of ad and finding the way or attitude of how normal people accept dance by reevaluating symbolic meaning of dance itself. In this study, advertisement producer and director's related data is secured for understanding direction and intention of producer, and previous study related with the study purpose, image, and effect are analyzed for understanding image of dance as a physical sign on TV advertisement. With data from www.TVCF.co.kr. TV advertisement analysis is conducted only with four ads in 2008(Nam Kwang Eng. & Const Co., Lotte Dept. Store(premium sale/gift card), Hyundai Motor Company Santa Fe -Pilobolus) and one ad in 2011(PNS The zone Sash Italy Arena di Verona when dance was used for advertisement with the highest frequency per year. Also, based on considered important factors from repeatedly watching each advertisement, scenes where movement or motion of dancer and screen word is greatly changed are analyzed as a priority. Image analysis of dance is conducted with structure studies based on physical image(line, costume, expression) and dan image(type motion, qualitative feature, mood of dance). As a result, the symbolic dance image appeared in TV advertisement can be discussed as follows. First, symbol and sign of dance on advertisement corresponds with material objects of advertisement. For instance, on the TV advertisement where Lee Youngwoo appeared, his motion as a signifer means challenge for the future of Nam Kwang Eng. & Const Co., with fast turn, jump, assemble turning jump, and sliding. Second, physical image of dancer depending on intention of sender corresponds in general, but there are somewhat differences in image of dance. This makes people to unconsciously recognize symbolic image of dance on TV ad while they watch it at the same time. Especially, when it comes to advertisement, it exposes frequently with broadcasting of organized programs from a broadcaster, living long-time memory. It can be differ based on idea and character of each of receiver. Advertisement is a medium making people naturally adopt cultural art for ordinary people in their lives. Broadcasting public art from TV advertisement widely exposes pure art to people, which was only avaliable for minority, sublimating it as an art of public culture.

• Spatial Information Research
• /
• v.20 no.5
• /
• pp.99-109
• /
• 2012

Recently, due to the growth of social media and spread of smart-phone, the amount of data has considerably increased by full use of SNS (Social Network Service). According to it, the Big Data concept is come up and many researchers are seeking solutions to make the best use of big data. To maximize the creative value of the big data held by many companies, it is required to combine them with existing data. The physical and theoretical storage structures of data sources are so different that a system which can integrate and manage them is needed. In order to process big data, MapReduce is developed as a system which has advantages over processing data fast by distributed processing. However, it is difficult to construct and store a system for all key words. Due to the process of storage and search, it is to some extent difficult to do real-time processing. And it makes extra expenses to process complex event without structure of processing different data. In order to solve this problem, the existing Complex Event Processing System is supposed to be used. When it comes to complex event processing system, it gets data from different sources and combines them with each other to make it possible to do complex event processing that is useful for real-time processing specially in stream data. Nevertheless, unstructured data based on text of SNS and internet articles is managed as text type and there is a need to compare strings every time the query processing should be done. And it results in poor performance. Therefore, we try to make it possible to manage unstructured data and do query process fast in complex event processing system. And we extend the data complex function for giving theoretical schema of string. It is completed by changing the string key word into integer type with filtering which uses keyword set. In addition, by using the Complex Event Processing System and processing stream data at real-time of in-memory, we try to reduce the time of reading the query processing after it is stored in the disk.

• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1095-1105
• /
• 2021

The advancement of dam operation is further required due to the upcoming rainy season, typhoons, or torrential rains. Besides, physical models based on specific rules may sometimes have limitations in controlling the release discharge of dam due to inherent uncertainty and complex factors. This study aims to forecast the water level of the nearest station to the dam multi-timestep-ahead and evaluate the availability when it makes a decision for a release discharge of dam based on LSTM (Long Short-Term Memory) of deep learning. The LSTM model was trained and tested on eight data sets with a 1-hour temporal resolution, including primary data used in the dam operation and downstream water level station data about 13 years (2009~2021). The trained model forecasted the water level time series divided by the six lead times: 1, 3, 6, 9, 12, 18-hours, and compared and analyzed with the observed data. As a result, the prediction results of the 1-hour ahead exhibited the best performance for all cases with an average accuracy of MAE of 0.01m, RMSE of 0.015 m, and NSE of 0.99, respectively. In addition, as the lead time increases, the predictive performance of the model tends to decrease slightly. The model may similarly estimate and reliably predicts the temporal pattern of the observed water level. Thus, it is judged that the LSTM model could produce predictive data by extracting the characteristics of complex hydrological non-linear data and can be used to determine the amount of release discharge from the dam when simulating the operation of the dam.

• Journal of the Korean Magnetics Society
• /
• v.14 no.2
• /
• pp.83-88
• /
• 2004

Magnetism of molecular nanomagnet, which attracted a lot of academic attention after the discovery of the macroscopic quantum tunneling of magnetism, is reviewed. Molecular nanomagnet is metal-organic material in which magnetic ions are regularly located in the organic skeleton. Also, the interaction between the molecules is very small and those molecules form macroscopic molecular crystal in which molecules are residing at the element points in the crystal. Molecular nanomagnets show a lot of interesting features, especially, equivalence of macroscopic magnetic properties and molecular magnetic properties. In this paper, research results on molecular nanomagnet with microscopic tool like NMR are reviewed mainly. The new method to observe the quantum tunneling of magnetization discovered in Mnl2-ac with NMR is shown and the research results on the microscopic aspects of the macroscopic quantum tunneling of magnetization using the new method are shown. Also, the physical aspect of the level crossing effect which has been reported originally with NMR in molecular nanomagnet is reviewed with experiment results. The research results on the molecular nanomagnets will reveal the important information about the limit of the miniaturization of magnetic memory units and give us the basic scientific knowledge which is needed for the application for the quantum computation. Moreover, academically, many quantum mechanical theories which have not been checked the validity can be checked with experiments.

• Journal of Korean Academy of Nursing
• /
• v.31 no.1
• /
• pp.94-106
• /
• 2001

The purpose of this study was to verify the use of Seo's Elderly Stress Scale (SESS), which was developed in 1996. Through the modified tool, it is possible to examine the stress of Korean elders and to contribute to the welfare of them. The subjects were 350 elders over 65 years old who live in Seoul, Kwang-Ju, Yang-Ju Gun Kyung-ki Do, Ui-Jong Bu, and Young-Am Kun, Jeun-Ra Nam Do. the data of 331 elders (94%) were analyzed. Data were collected between January and March in 1996 and analyzed using the SPSS Win 8.0. The result are as follows: 1. Items with low correlation with the total items were removed. So 27 items were removed and 37 items remained. This 37 items were death in the family and/or close friends, family member's behavior not meeting expectations, marriage of daughter, marriage of son, friction with daughter- in-law, argument among children, children refuse to live with parent, children leaving home, sex injury or accident, in frequest visits from children and grandchildren, providing care for your daughter or daughter-in-law post-partum, decrease in decision making and authority in home, Lunar new year and the harvest featival, house sitting, working in the house, performing a sacrificial rite, missed birthday, not living with the eldest son, decreased eyesight, decreased strength, decreased memory, sleep pattern changes, thoughts about death, loneliness, decreased hearing, change of dental condition, change in your diet or eating style, difficulty in self care, moving because of disease or aging, argument with friend or neighbour, travel, dealing with the procedure of heritage, loss of money or property, not enough pocket money, hearing on elderly neglect in television or radio, hope of going home and ignorant from others. 2. Overlapped items were discussed by colleagues and were modified. 'marriage of daughter' and 'marriage of son' were modified in 'marriage of children'. 'self injury or accidents' and 'family accidents' were modified in to self or family accidents. 3. Factor analysis was done in order to identify validity and three factors were obtained from the result. The first factor familial relation area, included 17 items. The second factor, physical area, included 9 items. The third factor, psycho-socio-economic area, included 9 items. Cronbach coefficient alpha for the 35 items was .923. 4. Pearson's correlation was .704 between SESS and SOS (Symptoms of Stress) in order to confirm construct validity. Based on the result, the following is suggested; 1. The modified SESS needs to be reverified with elder. 2. Korean elder's health promotion can be made by development of stress intervention which was accurately measured with SESS.

• The Korean Journal of Physiology and Pharmacology
• /
• v.21 no.4
• /
• pp.361-370
• /
• 2017

Previous reports have suggested that physical and psychological stresses may trigger fibromyalgia (FM). Stress is an important risk factor in the development of depression and memory impairments. Antidepressants have been used to prevent stress-induced abnormal pain sensation. Among various antidepressants, tianeptine has been reported to be able to prevent neurodegeneration due to chronic stress and reverse decreases in hippocampal volume. To assess the possible effect of tianeptine on FM symptoms, we constructed a FM animal model induced by restraint stress with intermittent cold stress. All mice underwent nociceptive assays using electronic von Frey anesthesiometer and Hargreaves equipment. To assess the relationship between tianeptine and expression levels of brain-derived neurotrophic factor (BDNF), cAMP response element-binding protein (CREB), and phosphorylated cAMP response element-binding protein (p-CREB), western blotting and immunohistochemistry analyses were performed. In behavioral analysis, nociception tests showed that pain threshold was significantly decreased in the FM group compared to that in the control group. Western blot and immunohistochemical analyses of medial prefrontal cortex (mPFC) and hippocampus showed downregulation of BDNF and p-CREB proteins in the FM group compared to the control group. However, tianeptine recovered these changes in behavioral tests and protein level. Therefore, this FM animal model might be useful for investigating mechanisms linking BDNF-CREB pathway and pain. Our results suggest that tianeptine might potentially have therapeutic efficacy for FM.

• Journal of Korean Academy of Nursing
• /
• v.10 no.2
• /
• pp.95-115
• /
• 1980

Current statistics reveal remarkable prolongation of the average longevity in this country for the past decade. Welfare of the aged is no longer sole concern of the person or/and family. but has aroused social concern on the community and national level. This study was designed to assess social, economic and emotional needs of the aged. and to identify problems they are confronting. Data were gathered through questioning 273 subjects living in Seoul from July 25, to August 31. 19 80. Frequencies and percentile scores were analysed to describe the fact. and the significance of int or-variable differences was tested by Chi-square method. Results are : 1. Majority of the subjects (male : 65.38%). (female : 62.13%)“talk about past experiences”to re-collect their past days, the difference between male and female respondents was not significant. 2. Except few who earn their pocket money (4.21%). majority were doing household errands (34.52% ) and looking after their garnd children (29.26 ％）. Main sources of their pocket money revealed to be their children (84.02%) and their own savings (24.64% ). Except few (15％）engaged with social activities directly or indirectly. leisure hours are spent in chatting with aged neighbors (44.81%). Highest in the rank order on the joyous moments for the aged revealed to be when the members of family living apart paying a visit (male : 37.5%, female : 63.72%)difference of male and female was significant ( P<0.05). Among female respondents. significant difference between age group was revealed (p<0.05). 3. Majority prefered sin91e houses (84.30% ). as residential environment. the suburban (36.26% ) area was the filet in the rank order : difference between age group and the educational status were not significant. Majority of respondents revealed to have their own room in the house. The first preference was given to live with their children (68.86%). Memory of the past (37.36% )revealed to be the highest in the rank order among the reasons why they dislike moving the house. 4. Majority favored current welfare benefts provided for the old age. however. the ideal way to live at their old age they responded was to live on their own savings (50.54%). 5. Majority revealed to be daunted occasionally (62.27%) by not being less active (34.16%) socially and by poor physical health(29.75%). Male and female differ in the causes of loneliness significantly (P <0.001) : retirement (37.89%) in ale and helpessness (43.05%) in female revealed the highest in the rank order. Majority talk over their feelings with aged neighbors to overcome the loneliness. 6 Majority were in favor of planting and looking after pet animal in the house. however. male and female differ in the kind significantly (p <0.001), 7. Majority think about death and dying occasionally or more (84.11% ). Many of the respondents believes in the life after life (53.49%) : female revealed to be significantly higher (p <0.01). and subjects with christian belief were significantly higher than non-christians (P<0.001). Attitude towards death and dying differs significantly between male and female (P <0. 001) and between christians ans and nonchristians (p <0.001). Highest preference was given to simple funeral (69.85%). Precious heritage that they would pass on to their descendants was onoscience and ethical value(57. 51%) : christian response as the first value was christian belief (52.38%).

• Research in Community and Public Health Nursing
• /
• v.13 no.4
• /
• pp.648-667
• /
• 2002

This was a descriptive study designed to identify the level of coping method and its influencing factors on the family caregivers of demented patients, and resolve the family caregivers' level of stress. The data were collected from September 10 to October 10, 2001. Subjects for this study were recruited from four clinics, which were chosen from 15 clinics located in Chunbuk-Do as the study sites because of their cooperation for the study. They were similar in terms of size, the characteristics of the local community. and the population and registration status of the demented patients. The instruments used for the study were as follows: 1. Problematic behaviors of demented patients are measured by the Memory and Behavior Problem Checklist (Zarit, 1980), and the Linguistic Communication Symptoms Questionnaire (Bayles and Tomoeda, 1991) 2. The ability to carry out daily activities was measured using the Barthel Index (1965) and Katz Index (1963), which as well-known ADL assessment methods. 3. Burden was measured using Cost of Care Index by the Kosberg and Cairl (1986). 4. Coping strategy was measured Bell's 18 methods (1977). The data were analyzed using SPSS/PC. The study results were as follows: 1. The total stress score was 2.90 out of a maximum score of 5. The highest score reported was 3.09 on the dimension of restriction of individual and social activities, and the lowest region reported was 2.58 on the dimension of mental and physical health. 2. The total score of the coping method was 2.65 out of a maximum score of 5. The highest score reported was 4.01 on the dimension of thinking that includes an ideation such that it is better than any possible worst case, and the lowest score reported was 1.45 on the dimension of the self-image as a scapegoat. 3. There were significant differences in coping method among the subjects by age (F=2.752 p=0.04), caregiver (F=4.33 p=0.003), care-giving period (F=2.68 p=0.049), and dementia stage (F=2.87 p=0.034). 4. There were highly negative correlations ($\gamma$=-0.301 p=0.000) between problematic behaviors of demented patients and the coping method of their family caregivers. The highest correlation coefficient ($\gamma$=-0.339 p=0.000) was found between aggressive behaviors of the demented patients and the coping method of their family caregivers. 5. There was a low negative correlation ($\gamma$=-0.201 p=0.019) between the ADL of the demented patients and the coping method of their family caregivers. 6. There were highly negative correlations ($\gamma$=-0.213 p=0.005) between stress and the coping method of the family caregivers. The highest correlation was found between financial burden ($\gamma$=-.327 P=.000) and the coping method of the family caregivers. There was no significant correlation among unpleasant aspects of the demented patients, willingness to the demented patients, and the coping method of the family caregivers.