• Journal of Intelligence and Information Systems
• /
• v.26 no.3
• /
• pp.71-90
• /
• 2020

Recently, the global insurance industry is rapidly developing digital transformation through the use of artificial intelligence technologies such as machine learning, natural language processing, and deep learning. As a result, more and more foreign insurers have achieved the success of artificial intelligence technology-based InsurTech and platform business, and Ping An Insurance Group Ltd., China's largest private company, is leading China's global fourth industrial revolution with remarkable achievements in InsurTech and Digital Platform as a result of its constant innovation, using 'finance and technology' and 'finance and ecosystem' as keywords for companies. In response, this study analyzed the InsurTech and platform business activities of Ping An Insurance Group Ltd. through the ser-M analysis model to provide strategic implications for revitalizing AI technology-based businesses of domestic insurers. The ser-M analysis model has been studied so that the vision and leadership of the CEO, the historical environment of the enterprise, the utilization of various resources, and the unique mechanism relationships can be interpreted in an integrated manner as a frame that can be interpreted in terms of the subject, environment, resource and mechanism. As a result of the case analysis, Ping An Insurance Group Ltd. has achieved cost reduction and customer service development by digitally innovating its entire business area such as sales, underwriting, claims, and loan service by utilizing core artificial intelligence technologies such as facial, voice, and facial expression recognition. In addition, "online data in China" and "the vast offline data and insights accumulated by the company" were combined with new technologies such as artificial intelligence and big data analysis to build a digital platform that integrates financial services and digital service businesses. Ping An Insurance Group Ltd. challenged constant innovation, and as of 2019, sales reached $155 billion, ranking seventh among all companies in the Global 2000 rankings selected by Forbes Magazine. Analyzing the background of the success of Ping An Insurance Group Ltd. from the perspective of ser-M, founder Mammingz quickly captured the development of digital technology, market competition and changes in population structure in the era of the fourth industrial revolution, and established a new vision and displayed an agile leadership of digital technology-focused. Based on the strong leadership led by the founder in response to environmental changes, the company has successfully led InsurTech and Platform Business through innovation of internal resources such as investment in artificial intelligence technology, securing excellent professionals, and strengthening big data capabilities, combining external absorption capabilities, and strategic alliances among various industries. Through this success story analysis of Ping An Insurance Group Ltd., the following implications can be given to domestic insurance companies that are preparing for digital transformation. First, CEOs of domestic companies also need to recognize the paradigm shift in industry due to the change in digital technology and quickly arm themselves with digital technology-oriented leadership to spearhead the digital transformation of enterprises. Second, the Korean government should urgently overhaul related laws and systems to further promote the use of data between different industries and provide drastic support such as deregulation, tax benefits and platform provision to help the domestic insurance industry secure global competitiveness. Third, Korean companies also need to make bolder investments in the development of artificial intelligence technology so that systematic securing of internal and external data, training of technical personnel, and patent applications can be expanded, and digital platforms should be quickly established so that diverse customer experiences can be integrated through learned artificial intelligence technology. Finally, since there may be limitations to generalization through a single case of an overseas insurance company, I hope that in the future, more extensive research will be conducted on various management strategies related to artificial intelligence technology by analyzing cases of multiple industries or multiple companies or conducting empirical research.

• The Korean Journal of Quaternary Research
• /
• v.14 no.1
• /
• pp.7-31
• /
• 2000

Quaternary Geological and geophysical investigation was performed at the Eurimji reservoir of Jaechon City in order to interprete depositional environment and genesis of lake sediments. For this purpose, echo sounding, bottom sampling and columnar sampling by drilling on board and GPR survey were employed for a proper field investigation. Laboratory tests cover grain size population analysis, pollen analysis and $^{14}C$ datings for the lake sediments. The some parts of lake bottom sediments anthropogenically tubated and filled several times to date, indicating several mounds on the bottom surface which is difficult to explain by bottom current. Majority of natural sediments were accumulated both as rolling and suspended loads during seasonal flooding regime, when flash flow and current flow are relatively strong not only at bridge area of the western part of Eurimji, connected to stream valley, but at the several conduit or sewage system surrounding the lake. Most of uniform suspend sediments are accumulated at the lake center and lower bank area. Some parts of bottom sediments indicate the existence of turbid flow and mudflow probably due to piezometric overflowing from the lake bottom, the existence of which are proved by CM patterns of the lake bottom sediments. The columnar samples of the lake sediments in ER-1 and ER-3-1 boreholes indicate good condition without any human tubation. The grain size character of borehole samples shows poorly sorted population, predominantly composed of fine sand and muds, varying skewness and kurtosis, which indicate multi-processed lake deposits, very similar to lake bottom sediments. Borehole columnar section, echo sounding and GPR survey profilings, as well as processed data, indicate that organic mud layers of Eurimji lake deposits are deeper and thicker towards lower bank area, especially west of profile line-9. In addition the columnar sediments indicate plant coverage of the Eurimji area were divided into two pollen zones. Arboreal pollen ( AP) is predominant in the lower pollen zone, whreas non-aboreal pollen(NAP) is rich in the upper pollen zone. Both of the pollen zones are related to the vegetation coverage frequently found in coniferous and deciduous broad-leaved trees(mixed forest) surrounded by mountains and hilly areas and prevailing by aquatic or aquatic margin under the wet temperate climate. The $^{14}C$ age of the dark gray organic muds, ER1-12 sample, is 950$\pm$40 years B.P. As the sediments are anthropogenetically undisturbed, it is assumed that the reliability of age is high. Three $^{14}C$ ages of the dark gray organic muds, including ER3-1-8, ER3-1-10, ER3-1-11 samples, are 600$\pm$30 years B.P., 650$\pm$30 years B.P., 800$\pm$40 years B.P. in the descending order of stratigraphic columnar section. Based on the interpretation of depositional environments and formation ages, it is proved that Eurimji reservoir were constructed at least 950$\pm$40 years B.P., the calibrated ages of which ranges from 827 years, B.P. to 866 years B.P. Ancient people utilize the natural environment of the stream valley to meet the need of water irrigation for agriculture in the local valley center and old alluvium fan area.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.135-149
• /
• 2020

Artificial intelligences are changing world. Financial market is also not an exception. Robo-Advisor is actively being developed, making up the weakness of traditional asset allocation methods and replacing the parts that are difficult for the traditional methods. It makes automated investment decisions with artificial intelligence algorithms and is used with various asset allocation models such as mean-variance model, Black-Litterman model and risk parity model. Risk parity model is a typical risk-based asset allocation model which is focused on the volatility of assets. It avoids investment risk structurally. So it has stability in the management of large size fund and it has been widely used in financial field. XGBoost model is a parallel tree-boosting method. It is an optimized gradient boosting model designed to be highly efficient and flexible. It not only makes billions of examples in limited memory environments but is also very fast to learn compared to traditional boosting methods. It is frequently used in various fields of data analysis and has a lot of advantages. So in this study, we propose a new asset allocation model that combines risk parity model and XGBoost machine learning model. This model uses XGBoost to predict the risk of assets and applies the predictive risk to the process of covariance estimation. There are estimated errors between the estimation period and the actual investment period because the optimized asset allocation model estimates the proportion of investments based on historical data. these estimated errors adversely affect the optimized portfolio performance. This study aims to improve the stability and portfolio performance of the model by predicting the volatility of the next investment period and reducing estimated errors of optimized asset allocation model. As a result, it narrows the gap between theory and practice and proposes a more advanced asset allocation model. In this study, we used the Korean stock market price data for a total of 17 years from 2003 to 2019 for the empirical test of the suggested model. The data sets are specifically composed of energy, finance, IT, industrial, material, telecommunication, utility, consumer, health care and staple sectors. We accumulated the value of prediction using moving-window method by 1,000 in-sample and 20 out-of-sample, so we produced a total of 154 rebalancing back-testing results. We analyzed portfolio performance in terms of cumulative rate of return and got a lot of sample data because of long period results. Comparing with traditional risk parity model, this experiment recorded improvements in both cumulative yield and reduction of estimated errors. The total cumulative return is 45.748%, about 5% higher than that of risk parity model and also the estimated errors are reduced in 9 out of 10 industry sectors. The reduction of estimated errors increases stability of the model and makes it easy to apply in practical investment. The results of the experiment showed improvement of portfolio performance by reducing the estimated errors of the optimized asset allocation model. Many financial models and asset allocation models are limited in practical investment because of the most fundamental question of whether the past characteristics of assets will continue into the future in the changing financial market. However, this study not only takes advantage of traditional asset allocation models, but also supplements the limitations of traditional methods and increases stability by predicting the risks of assets with the latest algorithm. There are various studies on parametric estimation methods to reduce the estimated errors in the portfolio optimization. We also suggested a new method to reduce estimated errors in optimized asset allocation model using machine learning. So this study is meaningful in that it proposes an advanced artificial intelligence asset allocation model for the fast-developing financial markets.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.16 no.4
• /
• pp.316-326
• /
• 2014

Determination of the late marginal heading date (LMHD), which would allow estimation of the late marginal seeding date and the late marginal transplanting date, would help identification of potential double cropping areas and, as a result, establishment of cropping systems. The objective of this study was to determine the LMHD at 51 sites in Korea. For these sites, weather data were obtained from 1971 to 2000 and from 1981 to 2010, which represent past and current normal climate conditions, respectively. To examine crop productivity on the LMHD, climatic yield potential (CYP) was determined to represent the potential yield under a given climate condition. The LMHD was calculated using accumulated temperature for 40 days with threshold values of $760^{\circ}C$, $800^{\circ}C$, $840^{\circ}C$ and $880^{\circ}C$. The value of CYP on a given LMHD was determined using mean temperature and sunshine duration for 40 days from the LMHD. The value of CYP on the LMHD was divided by the maximum value of CYP (CYPmax) in a season to represent the relative yield on the LMHD compared with the potential yield in the season. Our results indicated that the LMHD was delayed at most sites under current normal conditions compared with past conditions. Spatial variation of the LMHD differed by the threshold temperature. Overall, the minimum value of CYP/CYPmax was 81.8% under all of given conditions. In most cases, the value of CYP/CYPmax was >90%, which suggested that yield could be comparable to the potential yield even though heading would have occurred on the LMHD. When the LMHD could be scheduled later without considerable reduction in yield, the late marginal transplanting date could also be delayed accordingly, which would facilitate doublecropping in many areas in Korea. Yield could be affected by sudden change of temperature during a grain filling period. Yet, CYP was calculated using mean temperature and sunshine duration for 40 days after heading. Thus, the value of CYP/CYPmax may not represent actual yield potential due to change of the LMHD, which suggested that further study would be merited to take into account the effect of weather events during grain filling periods on yield using crop growth model and field experiments.

• The Journal of the Korea Contents Association
• /
• v.20 no.8
• /
• pp.583-597
• /
• 2020

This study analyzed how elderly people's perception of social welfare affects social welfare service and social welfare policy satisfaction by paying attention to the use of social welfare services and satisfaction with social welfare policies. In order to achieve this research goal, 465 people aged 60 or older who completed responses to the additional survey were collected and analyzed as research targets based on data from the Korea Welfare Panel, which is accumulated by the Korea Institute for Health and Social Affairs and Seoul National University's Social Welfare Research Institute. The results of this study are as follows. First, "Awareness of welfare for the elderly (recognition of welfare expenditure, recognition of welfare targets, recognition of welfare tax increases)" was found to have a negative impact on "use of social services." Second, "Awareness of welfare for the elderly (recognition of welfare expenditure, recognition of welfare targets, recognition of welfare tax increases)" was found to have a negative impact on "satisfaction with social welfare policies." Third, the impact of the recognition of welfare for the elderly on the use of social services was found to be different according to the demographic characteristics (education level, income level, educational background, gender). Fourth, according to the "population statistical characteristics (education level, income level, educational background, gender)" the impact of the recognition of welfare for the elderly on the satisfaction of social welfare policy was shown to be different. The implications of this study are that we looked at multi-dimensional welfare awareness and social service use experience together as factors affecting social welfare policy satisfaction. In other words, it is meaningful that the government focused on welfare awareness based on individual values and subjective perceptions as an influence on social welfare policy satisfaction, and sought practical alternatives to welfare policies and welfare sites by examining whether the experience of using social services in relation to welfare awareness and social welfare policy satisfaction among the elderly.

• Journal of the Korean earth science society
• /
• v.39 no.3
• /
• pp.228-240
• /
• 2018

Solar energy is calculated using meteorological (14 station), ceilometer (2 station) and microwave radiometer (MWR, 7 station)) data observed from the Weather Information Service Engine (WISE) on the Seoul metropolitan area. The cloud optical thickness and the cloud fraction are calculated using the back-scattering coefficient (BSC) of the ceilometer and liquid water path of the MWR. The solar energy on the surface is calculated using solar radiation model with cloud fraction from the ceilometer and the MWR. The estimated solar energy is underestimated compared to observations both at Jungnang and Gwanghwamun stations. In linear regression analysis, the slope is less than 0.8 and the bias is negative which is less than $-20W/m^2$. The estimated solar energy using MWR is more improved (i.e., deterministic coefficient (average $R^2=0.8$) and Root Mean Square Error (average $RMSE=110W/m^2$)) than when using ceilometer. The monthly cloud fraction and solar energy calculated by ceilometer is greater than 0.09 and lower than $50W/m^2$ compared to MWR. While there is a difference depending on the locations, RMSE of estimated solar radiation is large over $50W/m^2$ in July and September compared to other months. As a result, the estimation of a daily accumulated solar radiation shows the highest correlation at Gwanghwamun ($R^2=0.80$, RMSE=2.87 MJ/day) station and the lowest correlation at Gooro ($R^2=0.63$, RMSE=4.77 MJ/day) station.

• Tuberculosis and Respiratory Diseases
• /
• v.42 no.1
• /
• pp.84-92
• /
• 1995

Background: Nasal applied continuous positive airway pressure(CPAP) is a highly effective method of treatment for obstructive sleep apnea syndrome. More than a decade of accumulated experience with this treatment modality confirmed that it is unquestionably the medical treatment of choice for patients with obstructive sleep apnea syndrome. However it takes long time to reach optimal CPAP pressure. To save the time to reach optimal pressure, it is necessary to clarify the time to reach optimal pressure for treatment of obstructive sleep apnea syndrome. Method: CPAP pressure is titrated during an overnight study according to a standardized protocol. Just before the presleep bio-calibration procedures, the technician applies the nasal mask and switches on the clinical CPAP unit. Initial positive for pressure is typically 3.0 centimeters of water pressure. After sleep onset, the technician gradually increases the pressure until sleep-disordered breathing events disappear or become minimal. The pressure must maintain maximal airway patency during both NREM and REM sleep to be considered effective. Before recommending a final pressure setting, sleep recording and oximetry data are reviewed by an American Board of Sleep Medicine certified Sleep Specialist and a Registrered Polysomnographic Technologist. Results: We examined the time required to reach optimal pressure during routine CPAP titration in 127 consecutively evaluated individuals diagnosed with sleep-disordered breathing. Results indicate that 33% of patients required more than four hours to attain satisfactory titration. This indicates that a four-hour session is marginally enough time, at best, to determine a proper CPAP pressure setting. Moreover, 60 of 127 patients required further adjustment after optimal pressure was reached. These additional pressure trials were needed to confirm that higher pressures were not superior for eliminating sleep-disordered breathing events. Conclusions: The data presented underscore the logistical difficulty of titrating CPAP during split-night studies without modifying the titration procedure. Futhermore, the time needed to reach optimal pressure makes it improbable that proper CPAP titration can be performed during a 2-3 hour nap study.

• Korean journal of applied entomology
• /
• v.42 no.1
• /
• pp.43-51
• /
• 2003

This study was carried out to develop the forecasting model of Pseudococcus comtocki Kuwana for timing spray. Field phonology and temperature-dependent development of p. comstocki were studied, and its stage transition models were developed. p comstocki occurred three generations a year in Suwon. The 1 st adults occurred during mid to late June, and the 2nd adults were abundant during mid to late August. The 3rd adults were observed after late October. The development times of each instar of p. comstocki decreased with increasing temperature up to 25$^{\circ}C$, and thereafter the development times increased. The estimated low-threshold temperatures were 14.5, 8.4, 10.2, 11.8, and 10.1$^{\circ}C$ for eggs, 1st+2nd nymphs, 3rd nymphs, preoviposition, and 1st nymphs to preoviposition, respectively. The degree-days (thermal constants) for completion of each instar development were 105 DD for egg,315 DD for 1st+2nd nymph, 143 DD for 3rd nymph, 143 DD for preoviposition, and 599 DD for 1 st nymph to preoviposition. The stage transition models of p. comstocki, which simulate the proportion of individuals shifted from a stage to the next stage, were constructed using the modified Sharpe and DeMichele model and the Weibull function. In field validation, degree-day models using mean-minus-base, sine wave, and rectangle method showed 2-3d, 1-7d, and 0-6 d deviation with actual data in predicting the peak oviposition time of the 1st and 2nd generation adults, respectively. The rate summation model, in which daily development rates estimated by biophysical model of Sharpe and DeMichele were accumulated, showed 1-2 d deviation with actual data at the same phonology predictions.

• Asian Oncology Nursing
• /
• v.3 no.2
• /
• pp.145-154
• /
• 2003

Purpose: The study was to furnish basic raw materials that evaluate the efficacy of meatal care according to the form and the relative importance of symptom distress which most of cancer sufferers have been experienced. For that, an investigation of five diverse major cancer symptom distress made a comparison between symptom distress and degree of suffering. Method: Study subjects were 138 inpatients with stomach cancer, lung cancer, hepatocellular carcinoma(HCC), large intestine cancer and breast cancer, except those in the terminal-stage, in 'H' university hospital in Seoul and 'K' center in Ilsan gathered from November 20, 2002 to February 20, 2003. To measure the correlation between feeling of discomfort and agony caused by cancer, 5 point scale (from zero to four), stood on the basis of Symptom Distress Scale (SDS, Rodes & Watson, 1987), was used for this study and the Cronbach's coefficient alpha was 0.95. Accumulated data was analyzed with SPSS 10.0 for window, also used by ANOVA and Duncan's Multiple Range Test. Pearson's Correlation Analysis. Results: 1. Symptom distress of cancer patients was noted and defined in their severity-fatigue, anorexia, pain, depression, dyspepsia, changing appearance and nausea. The degree of symptom distress was fatigue, dyspepsia, depression, anorexia, pain, changing appearance and the degree of suffering was nausea, pain, anorexia, dyspepsia, vomiting, breathing difficulty, changing appearance and fatigue. 2. Examining the difference of degree of symptom distress in each cancer cases, it takes the precedence of them. First, in case of stomach cancer, depression, pain, vomiting and nausea were shown in sequence. In case of lung cancer depression, pain, sleeping problem, anxiety, changing appearance, inattentiveness and vomiting were showed in sequence, depression, changing appearance, sleeping problem, pain in case of HCC, depression, pain in case of large intestine cancer and lastly in case of breast cancer changing appearance, depression, pain and anxiety were shown in sequence. The category of the degree of symptom distress that has a signifiant difference was anorexia, activity discomfort, fatigue, constipation or diarrhea, breathing difficulty, dyspepsia, caughing, fever or chillness, scotoma and urinary disorder. Verifying the highest degree of symptom distress in each cancer cases, anorexia was 1.94(F=4.00, p<.01) in stomach cancer, activity discomfort was 0.97(F=3.08, p<.01) in lung cancer and HCC, fatigue was 2.32(F=4.64, p<.01) in HCC, constipation or diarrhea was 1.83(F=22.31, p<.001) in large intestine cancer, breathing difficulty was 1.83(F=4.00, p<.01) in lung cancer, dyspepsia was 2.69(F=9.98, p<.001) in stomach cancer, coughing was 1.53(F=20.49, p<.001) in lung cancer, fever or chillness was 1.23(F=6.88, p<.001) in lung cancer, scotoma was 1.20(F=3.02, p<.05) in lung cancer and urinary disorder was 1.54(F=11.56, p<.001) in HCC. 3. Examining the difference degree of suffering on cancer cases, the result was as follows; depression of lung cancer was 1.17(F=3.76, p<.01), anorexia of stomach cancer was 1.61(F=3.89, p<.01), constipation or diarrhea of large intestine cancer was 1.42(F=10.43, p<.001), changing appearance of breast cancer was 1.65(F=5.43, p<.001), breathing difficulty of lung cancer was 2.27(F=18.57, p<.001), dyspepsia of stomach cancer was 1.97(F=13.56, p<.001), coughing of lung cancer was 1.70(F=22.07, p<.001), fever or chillness of lung cancer was 1.13(F=4.41, p<.01), scotoma of lung cancer was 0.87(F=3.34, p<.05), anxiety of lung cancer was 0.87(F=4.50, p<.001) and urinary disorder of HCC was 1.43(F=16.71, p<.001). 4. In consequence, comparing between symptom distress and degree of suffering on cancer patients undergoing chemotherapy, lung cancer patients showed the highest feeling of discomfort following stomach cancer, HCC, breast cancer and large intestine cancer(F=2.88, p<.05). On those undergoing radiotherapy, lung cancer, HCC, breast cancer, large intestine cancer was in sequence(F=3.78, p<.05) and those resisting radiotherapy, lung cancer, HCC, stomach cancer, large intestine cancer and breast cancer was in sequence(F=2.72, p<.05). 5. Correlation between symptom distress and degree of suffering on cancer patients was generally significant. Conclusion: this study not only defines a significant correlation between symptom distress and degree of suffering but also proffers basic data to evaluate the efficient meatal care depending upon diverse spectrums of symptom distress and degree of suffering.

• Korean Journal of Ecology and Environment
• /
• v.48 no.4
• /
• pp.229-237
• /
• 2015

This study aims to offer basic data to effectively preserve and manage pine forests using more precise pine forests' distribution status. In this regard, this study predicts the geographical distribution change of pine forests growing in South Korea, due to climate change, and evaluates the spatial distribution characteristics of pine forests by age. To this end, this study predicts the potential distribution change of pine forests by applying the MaxEnt model useful for species distribution change to the present and future climate change scenarios, and analyzes the effects of bioclimatic variables on the distribution area and change by age. Concerning the potential distribution regions of pine forests, the pine forests, aged 10 to 30 years in South Korea, relatively decreased more. As the area of the region suitable for pine forest by age was bigger, the decreased regions tend to become bigger, and the expanded regions tend to become smaller. Such phenomena is conjectured to be derived from changing of the interaction of pine forests by age from mutual promotional relations to competitive relations in the similar climate environment, while the regions suitable for pine forests' growth are mostly overlap regions. This study has found that precipitation affects more on the distribution of pine forests, compared to temperature change, and that pine trees' geographical distribution change is more affected by climate's extremities including precipitation of driest season and temperature of the coldest season than average climate characteristics. Especially, the effects of precipitation during the driest season on the distribution change of pine forests are irrelevant of pine forest's age class. Such results are expected to result in a reduction of the pine forest as the regions with the increase of moisture deficiency, where climate environment influencing growth and physiological responses related with drought is shaped, gradually increase according to future temperature rise. The findings in this study can be applied as a useful method for the prediction of geographical change according to climate change by using various biological resources information already accumulated. In addition, those findings are expected to be utilized as basic data for the establishment of climate change adaptation policies related to forest vegetation preservation in the natural ecosystem field.