• Journal of Intelligence and Information Systems
• /
• v.21 no.4
• /
• pp.1-16
• /
• 2015

Traffic accident is one of the major cause of death worldwide for the last several decades. According to the statistics of world health organization, approximately 1.24 million deaths occurred on the world's roads in 2010. In order to reduce future traffic accident, multipronged approaches have been adopted including traffic regulations, injury-reducing technologies, driving training program and so on. Records on traffic accidents are generated and maintained for this purpose. To make these records meaningful and effective, it is necessary to analyze relationship between traffic accident and related factors including vehicle design, road design, weather, driver behavior etc. Insight derived from these analysis can be used for accident prevention approaches. Traffic accident data mining is an activity to find useful knowledges about such relationship that is not well-known and user may interested in it. Many studies about mining accident data have been reported over the past two decades. Most of studies mainly focused on predict risk of accident using accident related factors. Supervised learning methods like decision tree, logistic regression, k-nearest neighbor, neural network are used for these prediction. However, derived prediction model from these algorithms are too complex to understand for human itself because the main purpose of these algorithms are prediction, not explanation of the data. Some of studies use unsupervised clustering algorithm to dividing the data into several groups, but derived group itself is still not easy to understand for human, so it is necessary to do some additional analytic works. Rule based learning methods are adequate when we want to derive comprehensive form of knowledge about the target domain. It derives a set of if-then rules that represent relationship between the target feature with other features. Rules are fairly easy for human to understand its meaning therefore it can help provide insight and comprehensible results for human. Association rule learning methods and subgroup discovery methods are representing rule based learning methods for descriptive task. These two algorithms have been used in a wide range of area from transaction analysis, accident data analysis, detection of statistically significant patient risk groups, discovering key person in social communities and so on. We use both the association rule learning method and the subgroup discovery method to discover useful patterns from a traffic accident dataset consisting of many features including profile of driver, location of accident, types of accident, information of vehicle, violation of regulation and so on. The association rule learning method, which is one of the unsupervised learning methods, searches for frequent item sets from the data and translates them into rules. In contrast, the subgroup discovery method is a kind of supervised learning method that discovers rules of user specified concepts satisfying certain degree of generality and unusualness. Depending on what aspect of the data we are focusing our attention to, we may combine different multiple relevant features of interest to make a synthetic target feature, and give it to the rule learning algorithms. After a set of rules is derived, some postprocessing steps are taken to make the ruleset more compact and easier to understand by removing some uninteresting or redundant rules. We conducted a set of experiments of mining our traffic accident data in both unsupervised mode and supervised mode for comparison of these rule based learning algorithms. Experiments with the traffic accident data reveals that the association rule learning, in its pure unsupervised mode, can discover some hidden relationship among the features. Under supervised learning setting with combinatorial target feature, however, the subgroup discovery method finds good rules much more easily than the association rule learning method that requires a lot of efforts to tune the parameters.

• Journal of Korean Medical classics
• /
• v.3
• /
• pp.218-247
• /
• 1989

As mentioned above, I got the next conclusion since I had considered the medical contents of the ancient period(上古時代) and the era of the old-Korea(古朝鮮時代) through several bibliographic records. 1. There were Pung-baeg(風伯), Uh-sa(雨師), Un-sa(雲師) that were the names of the governmental officials during the ancient period of Whan-ung(桓雄). Among them, Uh-sa specially managed the treatment for diseases. When we think of the significance of Pung(風)-which means the winds, Uh(雨)-which means the rain, Un(雲)-which means of clouds, we will find out that the human life will be affected by all kinds of phenomena of the nature. So I can infer that ancestries could prevent and treat diseases with adjusting them tn the changes in the weather. 2. There were five government officials(五事) in the ancient period of Whan-ung(桓雄上古時代). They are Uh-ga(牛加), Ma-ga(馬加), Ku-ga(狗加), Cheo-ga(猪加) and Yang-ga(羊加), and had charges of five important duties. Among them, Cheo-ga was set to a charge of treatment for diseases. So we can notice that there existed people who treated for diseases professionally. When we think of the meanings of Uh(牛)-which intends cows or bulls. Ma(馬)-which intends horses, Ku(狗)-which intends dogs, Cheo(猪)-which intends wild boars and Yang(羊)-which intends sheep, we can see that livestocks would be raised at that time, and they came to have more chances to digest meat. Since the digestion of meat became to be a burden on the stomach and the intestines, it might cause a lot of indigestive troubles. 3. When I compared Tan-gun Pal-ga(檀君八加) with the Oh-ga(五加) in the ancient period of Whan-ung(桓雄上古時代), I could tell that the community of Tan-gun's period is more advanced and specialized than one of Whan-ung's. When I think of the next sentence ; "The Prince Imperial, Bu-u(夫虞) become to be a Ro-ga(鷺加), who treat for diseases professionally.", I am sure that the treatment for diseases was more importment than any other things, because he was the third son of Tan-gun(檀君). 4. According to Tan-gun(檀君) mythology, Whan-ung(桓雄) came down from the heaven of the pure Yang(純陽) to the earth and then changed into a man who had had more Yang(陽) than Yin(陰). And a bear came up from the underground(or the cave) to the ground and then changed into a women who had had more Yin(陰) than Yang(陽). So both of them became to hold together. This story implicated that ancestors had taken a serious view of each of them, namely the ancestors didn't give the ascendance to the one side of them, and made much account of the mutual harmony. So I am sure that this fact coincided with the basic theories of oriental medical science. To refer to two proverbs of Tan-gun mythology that are "Ki-Sam-Chil-Il(忌三七日)" which means caring for twenty one days, and "Pul-Gyon-Il-Gwang-Baeg-Il(不見日光百日)" which means keeping indoors for one hundred days, I can tell you that "twenty-one-day" involves the principle of the birth of life, and "one-hundred-day" contains a preparatory period or the period of death to bear another life. 5. From the medical stuff, such as wormwood(艾), garlic(蒜), or wonder-working herbage(靈草), that had been written at the bibliographic papers of the ancient period(上古時代) and the era of the old-Korea(古朝鮮時代), I consider that many people might get a lot of women's diseases, indigestive troubles, and other diseases that were caused by the weakness, but with using various spices, such as the leaves of water pepper(蔘), they could prevent the occurrance of all kinds of diseases previously. So I regard this treatment as the medicine from food. 6. One of the sayings at Nae-gyong(內經) is that "The stone accupuncture(砭石) came from the orient." We can see both "wonder-wor-king wormwood(靈草)" and "dried wormwood(乾艾)" in the several bibliographic papers of the ancient history of the old-Korea(朝鮮上古史). From these records, I can be convinced that ancestors would utilize the acupuncture(針) and the moxa cautery(灸) to cure a patient of a disease. 7. Even though someone claimed that the book, "medical science and chemistry(醫學化學)" and "medical treatment(醫學大方)" had had been written during the ancient period of the old-Korea(上古朝鮮時代), such a fact can't have been ascertained historical evidence. But it has been handed down that there existed the original phonetic alphabet, such as the "Ka-Im-To alphabet(加臨土文字)" at that time. The terms about the diseases, which had been occurred at the community of the old-Korea(古朝鮮地域), were recorded fragmentarily at other records after that time. The origin of confucianism came from the race of the eastern barbarians, and Tae-Ho-Pok-Hi(太嗅伏義) and the king. Sun(舜) came from the eastern barbarians, too. The divination of tortoise shells at the country of Un(殷) is another from which was developed at the eastern barbarians' fortune-telling of animal bones. From these facts, I can infer that, by all means, they might record the medical knowledge which had been stored for thousands of years while contacting with china directly.

• Journal of Acupuncture Research
• /
• v.30 no.5
• /
• pp.155-167
• /
• 2013

Objectives : This research was conducted to investigate the factors that affect the level of facial nerve damage. Methods : From October 2009 to September 2013, the total number of 581 patients of Bell's palsy and Ramsay-Hunt syndrome visited Facial Palsy Center in Kyung Hee University Hospital at Gangdong for Traditional Korean and Western combined medical treatment. Of these, 453 patients of peripheral facial nerve palsy were selected for the research. After reviewing the medical records that have details of age, gender, diagnosis(Bell's palsy and Ramsay-Hunt syndrome), onset, underlying diseases(DM, HTN), and HbAlc value, the analysis on the influence factors on the level of facial nerve damage was drew out. Results : The axonal loss rate of oris branch and nasal branch were significantly higher than the axonal loss rate of frontal branch and oculi branch. In addition, the frequency of becoming a major damaged branch was also high in the oris branch nasal branch. The factors by month, weather, smoking, and alcohol did not influence EMG axonal loss rate. Male rather than female and patient with Rasmay-Hut syndrome rather than Bell's palsy had a higher axonal loss rate in all branches. Of those, front of branch of male was remarkably higher than female. Patient with DM as P/H had high axonal loss rate in all branches. Patient with HTN as P/H had high axonal loss rate in all branches except for oris branches. Patients with DM and HTN group had significantly higher value from the average of axonal loss rate than patients who are only with HTN and without DM/HTN. DM alone group had significantly higher value than patients who are without DM/HTN. However, HTN alone was not significantly high. By analysing HbAlc of the patients who were hospitalised regardless DM, axonal loss rate was high in the order of DM group, preDM group, normal group. Nevertheless, only DM group showed higher axonal rate statistically than normal group. Considering DM and HbA1c value, the patients can be divided into 4 different groups of hkDM, lkDM, hfDM and nDM. By analysing those groups, the average damaged value of the groups with diagnosis followed by treatment(lkDM, hkDM) were higher than the average rate of hfDM and statistically higher than the rate of the nDM. Conclusions : The influential factors of increasing the level of EMG damage are male(only for the frontal branch), age above sixties, HTN, DM, and HbAlc value above 6.5. Besides, the negligible factors are month, season, diagnosis, alcohol, and smoking. Further research including clinical prognosis should be conducted.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.19 no.1
• /
• pp.19-26
• /
• 2017

Surface air temperature ($T_{air}$) is a key variable for the meteorology and climatology, and is a fundamental factor of the terrestrial ecosystem functions. Satellite remote sensing from the Moderate Resolution Imaging Spectroradiometer (MODIS) provides an opportunity to monitor the $T_{air}$. However, the several problems such as frequent cloud cover and mountainous region can result in substantial retrieval error and signal loss in MODIS $T_{air}$. In this study, satellite-based $T_{air}$ was estimated under both clear and cloudy sky conditions in Gangwon Province using Aqua MODIS07 temperature profile product (MYD07_L2) and GCOM-W1 Advanced Microwave Scanning Radiometer 2 (AMSR2) brightness temperature ($T_b$) at 37 GHz frequency, and was compared with the measurements from the Automated Mountain Meteorology Stations (AMOS). The application of ambient temperature lapse rate was performed to improve the retrieval accuracy in mountainous region, which showed the improvement of estimation accuracy approximately 4% of RMSE. A simple pixel-wise regression method combining synergetic information from MYD07_L2 $T_{air}$ and AMSR2 $T_b$ was applied to estimate surface $T_{air}$ for all sky conditions. The $T_{air}$ retrievals showed favorable agreement in comparison with AMOS data (r=0.80, RMSE=7.9K), though the underestimation was appeared in winter season. Substantial $T_{air}$ retrievals were estimated 61.4% (n=2,657) for cloudy sky conditions. The results presented in this study indicate that the satellite remote sensing can produce the surface $T_{air}$ at the complex mountainous region for all sky conditions.