• Journal of Intelligence and Information Systems
• /
• v.19 no.4
• /
• pp.123-132
• /
• 2013

As the smartphones are equipped with various sensors such as the accelerometer, GPS, gravity sensor, gyros, ambient light sensor, proximity sensor, and so on, there have been many research works on making use of these sensors to create valuable applications. Human activity recognition is one such application that is motivated by various welfare applications such as the support for the elderly, measurement of calorie consumption, analysis of lifestyles, analysis of exercise patterns, and so on. One of the challenges faced when using the smartphone sensors for activity recognition is that the number of sensors used should be minimized to save the battery power. When the number of sensors used are restricted, it is difficult to realize a highly accurate activity recognizer or a classifier because it is hard to distinguish between subtly different activities relying on only limited information. The difficulty gets especially severe when the number of different activity classes to be distinguished is very large. In this paper, we show that a fairly accurate classifier can be built that can distinguish ten different activities by using only a single sensor data, i.e., the smartphone accelerometer data. The approach that we take to dealing with this ten-class problem is to use the ensemble of nested dichotomy (END) method that transforms a multi-class problem into multiple two-class problems. END builds a committee of binary classifiers in a nested fashion using a binary tree. At the root of the binary tree, the set of all the classes are split into two subsets of classes by using a binary classifier. At a child node of the tree, a subset of classes is again split into two smaller subsets by using another binary classifier. Continuing in this way, we can obtain a binary tree where each leaf node contains a single class. This binary tree can be viewed as a nested dichotomy that can make multi-class predictions. Depending on how a set of classes are split into two subsets at each node, the final tree that we obtain can be different. Since there can be some classes that are correlated, a particular tree may perform better than the others. However, we can hardly identify the best tree without deep domain knowledge. The END method copes with this problem by building multiple dichotomy trees randomly during learning, and then combining the predictions made by each tree during classification. The END method is generally known to perform well even when the base learner is unable to model complex decision boundaries As the base classifier at each node of the dichotomy, we have used another ensemble classifier called the random forest. A random forest is built by repeatedly generating a decision tree each time with a different random subset of features using a bootstrap sample. By combining bagging with random feature subset selection, a random forest enjoys the advantage of having more diverse ensemble members than a simple bagging. As an overall result, our ensemble of nested dichotomy can actually be seen as a committee of committees of decision trees that can deal with a multi-class problem with high accuracy. The ten classes of activities that we distinguish in this paper are 'Sitting', 'Standing', 'Walking', 'Running', 'Walking Uphill', 'Walking Downhill', 'Running Uphill', 'Running Downhill', 'Falling', and 'Hobbling'. The features used for classifying these activities include not only the magnitude of acceleration vector at each time point but also the maximum, the minimum, and the standard deviation of vector magnitude within a time window of the last 2 seconds, etc. For experiments to compare the performance of END with those of other methods, the accelerometer data has been collected at every 0.1 second for 2 minutes for each activity from 5 volunteers. Among these 5,900 ($=5{\times}(60{\times}2-2)/0.1$) data collected for each activity (the data for the first 2 seconds are trashed because they do not have time window data), 4,700 have been used for training and the rest for testing. Although 'Walking Uphill' is often confused with some other similar activities, END has been found to classify all of the ten activities with a fairly high accuracy of 98.4%. On the other hand, the accuracies achieved by a decision tree, a k-nearest neighbor, and a one-versus-rest support vector machine have been observed as 97.6%, 96.5%, and 97.6%, respectively.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.107-122
• /
• 2017

Volatility in the stock market returns is a measure of investment risk. It plays a central role in portfolio optimization, asset pricing and risk management as well as most theoretical financial models. Engle(1982) presented a pioneering paper on the stock market volatility that explains the time-variant characteristics embedded in the stock market return volatility. His model, Autoregressive Conditional Heteroscedasticity (ARCH), was generalized by Bollerslev(1986) as GARCH models. Empirical studies have shown that GARCH models describes well the fat-tailed return distributions and volatility clustering phenomenon appearing in stock prices. The parameters of the GARCH models are generally estimated by the maximum likelihood estimation (MLE) based on the standard normal density. But, since 1987 Black Monday, the stock market prices have become very complex and shown a lot of noisy terms. Recent studies start to apply artificial intelligent approach in estimating the GARCH parameters as a substitute for the MLE. The paper presents SVR-based GARCH process and compares with MLE-based GARCH process to estimate the parameters of GARCH models which are known to well forecast stock market volatility. Kernel functions used in SVR estimation process are linear, polynomial and radial. We analyzed the suggested models with KOSPI 200 Index. This index is constituted by 200 blue chip stocks listed in the Korea Exchange. We sampled KOSPI 200 daily closing values from 2010 to 2015. Sample observations are 1487 days. We used 1187 days to train the suggested GARCH models and the remaining 300 days were used as testing data. First, symmetric and asymmetric GARCH models are estimated by MLE. We forecasted KOSPI 200 Index return volatility and the statistical metric MSE shows better results for the asymmetric GARCH models such as E-GARCH or GJR-GARCH. This is consistent with the documented non-normal return distribution characteristics with fat-tail and leptokurtosis. Compared with MLE estimation process, SVR-based GARCH models outperform the MLE methodology in KOSPI 200 Index return volatility forecasting. Polynomial kernel function shows exceptionally lower forecasting accuracy. We suggested Intelligent Volatility Trading System (IVTS) that utilizes the forecasted volatility results. IVTS entry rules are as follows. If forecasted tomorrow volatility will increase then buy volatility today. If forecasted tomorrow volatility will decrease then sell volatility today. If forecasted volatility direction does not change we hold the existing buy or sell positions. IVTS is assumed to buy and sell historical volatility values. This is somewhat unreal because we cannot trade historical volatility values themselves. But our simulation results are meaningful since the Korea Exchange introduced volatility futures contract that traders can trade since November 2014. The trading systems with SVR-based GARCH models show higher returns than MLE-based GARCH in the testing period. And trading profitable percentages of MLE-based GARCH IVTS models range from 47.5% to 50.0%, trading profitable percentages of SVR-based GARCH IVTS models range from 51.8% to 59.7%. MLE-based symmetric S-GARCH shows +150.2% return and SVR-based symmetric S-GARCH shows +526.4% return. MLE-based asymmetric E-GARCH shows -72% return and SVR-based asymmetric E-GARCH shows +245.6% return. MLE-based asymmetric GJR-GARCH shows -98.7% return and SVR-based asymmetric GJR-GARCH shows +126.3% return. Linear kernel function shows higher trading returns than radial kernel function. Best performance of SVR-based IVTS is +526.4% and that of MLE-based IVTS is +150.2%. SVR-based GARCH IVTS shows higher trading frequency. This study has some limitations. Our models are solely based on SVR. Other artificial intelligence models are needed to search for better performance. We do not consider costs incurred in the trading process including brokerage commissions and slippage costs. IVTS trading performance is unreal since we use historical volatility values as trading objects. The exact forecasting of stock market volatility is essential in the real trading as well as asset pricing models. Further studies on other machine learning-based GARCH models can give better information for the stock market investors.

• Journal of Korean Society of Forest Science
• /
• v.14 no.1
• /
• pp.1-20
• /
• 1972

The trend and achievements of forest genetics research in abroad were investigated through observation tours and reference work and following facts were found to be important aspects which should be adopted in the forest genetics research program in Korea. Because of world wide recognization on the urgency of taking a measure to reserve some areas of the representative forest type on the globe before the extingtion of such forest type as the results of continuous exploitations of the natural forests to meet the timber demand all over the world, it is urgently needed to take a measure to reserve certain areas of natural stand of Pinus koraiensis, Pinus parviflora, Pinus densiflora f. erectra, Abies koreana, Quercus sp., Populus sp., etc. as gene pool to be used for the future program of forest tree improvement. And the genetic studies of those natural forest of economic tree species are also to be performed. 1. Increase of the number of selected tree for breeding purpose. Because of the fact that the number of plus tree at present is too small to carry out selection program for tree improvement, particularly for the formation of source population for recurrent selection of parent trees of the 2nd generation seed orchard it is to be strongly emphasized to increase the number of plus tree by alleviating selection criteria in order to enlarge the population size of plus trees to make the selection program more efficient. 2. Progeny testing More stress should be placed on carrying out progeny testing of selected trees with open pollinated seeds. And particular efforts are to be made for conducting studies on adult/juvenile correlation of important traits with a view to enable to predict adult performances with some traits revealed in juvenile age thus to save time for progeny testing. 3. Genotype-environment interaction Studies on genotype and environment interaction should be conducted in order to elucidate whether the plus trees selected on the good site express their superiority on the poor site or not and how the environment affect the genotype. And the justification of present classification of seed distribution area should be examined. 4. Seed orchard of broad leaf tree species. Due to the difficulty of accurate comparison of growth rate of neighbouring trees of broad leaf tree species in natural stand, it is recommended that for the improvement of broad leaf trees a seedling seed orchard is to be made by roguing the progeny test plantation planted densely with control pollinated seedlings of selected trees. 5. Breeding for insect resistant varieties. In the light of the fact that the resistant characteristics against insect such as pine gall midge (Thiecodiplosis japonensis U. et I.) and pine bark beetle (Myelophilus pinipera L.) are highly correlated with the amount and quality of resin which are known as gene controlled characteristics, breeding for insect resistance should be carried out. 6. Breeding for timber properties. With the tree species for pulp wood in particular, emphasis should be placed upon breeding for high specific gravity of timber. 7. Introduction of Cryptomeria and Japanese Cypress In the light of the fact that the major clones of Cryptomeria are originated from Yoshino source and are being planted up to considerably north and high elevation in Japan, those species should be examined on their cold resistance in Korea by planting them in further northern part of the country.

• The korean journal of orthodontics
• /
• v.31 no.2 s.85
• /
• pp.261-270
• /
• 2001

The purpose of this study was to evaluate the clinical usefulness of plasma arc light which can reduce the curing time dramatically compared by shear bond strengths and failure patterns of the brackets bonded with visible light in direct bracket bonding. Some kinds of brackets were bonded with the Transbond$^{\circledR}$ to the human premolars which were embedded in the resin blocks according to the various conditions. After bonding, the shear bond strength was tested by Instron universal testing machine and in addition , the amount of residual adhesive remaining on the tooth after debonding was measured by the stereoscope and assessed with adhesive remnant index(ARI). The results were as follows : 1. When plasma arc light was used for bonding the brackets, the shear bond strength was clinically sufficient in both metal and ceramic brackets, but resin brackets showed significantly lower bond strength but which was clinically useful. 2. When metal brackets were bonded using visible light, there was no significant difference in shear bond strength due to the light-curing time and the bond strength was clinically sufficient. 3. When the adhesive failure patterns of brackets bonded with plasma arc light were observed by using the adhesive remnant index, the bond failure of the metal and resin bracket occurred more frequently at bracket-adhesive interface but the failure of the ceramic bracket occurred more frequently at enamel-adhesive interface. 4. There was no statistically significant difference of the shear bond strength and adhesive failure pattern between metal bracket bonded for 2 seconds by curing with plasma arc light and 10 seconds by curing with visible light. 6. When metal brackets were bonded using plasma arc light, the shear bond strength decreased as the distance from the light source increased. The above results suggest that plasma arc light can be clinically useful for bonding the brackets without fear of the decrease of the shear bond strength.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.1
• /
• pp.95-107
• /
• 2017

In this study, a preliminary study was undertaken for development of a tunnel incident automatic detection system based on a machine learning algorithm which is to detect a number of incidents taking place in tunnel in real time and also to be able to identify the type of incident. Two road sites where CCTVs are operating have been selected and a part of CCTV images are treated to produce sets of training data. The data sets are composed of position and time information of moving objects on CCTV screen which are extracted by initially detecting and tracking of incoming objects into CCTV screen by using a conventional image processing technique available in this study. And the data sets are matched with 6 categories of events such as lane change, stoping, etc which are also involved in the training data sets. The training data are learnt by a resilience neural network where two hidden layers are applied and 9 architectural models are set up for parametric studies, from which the architectural model, 300(first hidden layer)-150(second hidden layer) is found to be optimum in highest accuracy with respect to training data as well as testing data not used for training. From this study, it was shown that the highly variable and complex traffic and incident features could be well identified without any definition of feature regulation by using a concept of machine learning. In addition, detection capability and accuracy of the machine learning based system will be automatically enhanced as much as big data of CCTV images in tunnel becomes rich.

• Progress in Medical Physics
• /
• v.17 no.3
• /
• pp.131-135
• /
• 2006

A commercial ion chamber matrix was examined the characteristics and its performance for radiotherapy qualify assurance. The device was the I'mRT 2D-MatriXX (Scanditronix-Wellhofer, Schwarzenbruck, Germany). The 2D-MatriXX device consists of a 1020 vented ion chamber array, arranged in $24{\times}24cm^2$ matrix. Each ion chamber has a volume of $0.08cm^3$, spacing of 0.762 cm and minimum sampling time of 20 ms. For the investigation of the characteristics, dose linearity, output factor, short-term reproducibility and dose rate dependency were tested. In the testing of dose linearity. It has shown a good signal linearity within 1% in the range of $1{\sim}800$cGy. Dose rate dependency was found to be lower than 0.4% (Range: 100-600 Mu/min) relative to a dose rate of 300 Mu/min as a reference. Output factors matched very well within 0.5% compared with commissioned beam data using a ionization chamber (CC01, Scanditronix-Wellhofer, Schwarzenbruck, Germany) in the range of field sizes $3{\times}3{\sim}24{\times}24cm^2$. Short-term reproducibility (6 times with a interval of 15 minute) was also shown a good agreement within 0.5%, when the temperature and the pressure were corrected by each time of measurement. in addition, we compared enhanced dynamic wedge (EDW, Varian, Palo Alto, USA) profiles from calculated values in the radiation planning system with those from measurements of the MatriXX. Furthermore, anon-uniform IMRT dose fluence was tested. All the comparison studies have shown good agreements. In this study, the MatriXX was evaluated as a reliable dosimeter, and it could be used as a simplistic and convenient tool for radiotherapy qualify assurance.

• Food Science of Animal Resources
• /
• v.29 no.4
• /
• pp.445-456
• /
• 2009

Colostrum samples were collected from 36 dairy farms in Gyeonggi-do and one dairy farm in the National Institute of Animal Science (NIAS) for testing. Colostrum samples were analyzed for phisycochemicals (specific gravity, pH, titratable acidity), general components (fat, protein, lactose, total solid, solid non-fat (SNF)), fatty acids, amino acids, minerals, microflora, somatic cells, and Ig (Immunoglobulin). The first colostrum revealed the following data: fat contents were $6.16{\pm}2.39%$, proteins were $14.78{\pm}4.30%$, lactose $2.57{\pm}0.77%$, total solid $24.28{\pm}4.36%$, and SNF $18.12{\pm}4.08%$, whereas the 2nd (or $12^{th}$) colostrum revealed $5.56{\pm}1.76%$ fat, $3.46{\pm}0.41%$ proteins, $4.19{\pm}0.43%$ lactose, $13.90{\pm}1.76%$ total solid, and $8.34{\pm}0.81%$ SNF. Also, the first colostrum revealed the contents of major amino acids as 0.89% aspartic acid, 0.71% threonine, 0.86% serine, 1.75% glutamic acid, 0.64% valine, 0.95% leucine, 0.83% lysine, and 0.95% proline, and those in the 10th colostrum were 0.25% aspartic acid, 0.15% threonine, 0.19% serine, 0.59% glutamic acid, 0.19% valine, 0.35% leucine, 0.31% lysine, and 0.34% proine. Major amino acid contents rapidly decreased as milking times increased. In the first colostrum, the following mineral contents were observed: there were 2,168 ppm in Ca, 1,959 ppm in P, 914 ppm in K, 761 ppm in Na, 287 ppm in Mg, 1.7 ppm in Fe, 14.3 ppm in Zn, and 1.0 ppm in Cu; while in the 10th colostrum, the following ppm contents were 1,389 in Ca, 1,323 in P, 838 in K, 427 in Na, 131 in Mg, 1.0 in Fe, 4.7 in Zn, and 1.3 in Cu. The mineral contents in a colostrum rapidly decreased as milking times increased.

• Korean Journal of Soil Science and Fertilizer
• /
• v.45 no.5
• /
• pp.744-748
• /
• 2012

This study was carried out to investigate the incorporation effect of green manure crops (GMC) such as the hairy vetch on improvement of soil environment in reclaimed land during sorghum${\times}$sudangrass hybrid (SSH) cultivation over the past three years from 2009 to 2011. Plots consisted of conventional fertilization (CF) and incorporation of GMC were divided by rates of additional nitrogen fertilizer ($100kg\;ha^{-1}$) and decreased percentage of 30 50 70 100 fertilization in addition to non nitrogen fertilization (NNF). Soil physico-chemical properties, growth and yield potential were examined. The results were as follows. The testing soil was showed strong alkaline saline soil with low organic matter contents and less available phosphate while exchangeable sodium and magnesium were higher. Soil salinity was increased during cultivation of summer crop. However, SSH was not affected by salt content. The fresh weight of GMC at incorporation time was $18,345kg\;ha^{-1}$. Content of total nitrogen at incorporation time was 3.09% and the C/N ratio was 12.8. Fresh and dry matter yield of SSH were higher in the order of 30%, CF, N50%, N70%d, N100%, and NNF. Fresh and dry matter yield of SSH increased in the order of CF ($55,050kg\;ha^{-1}$, $16,250kg\;ha^{-1}$), N contents from 30% to 9%. Soil physical properties, such as bulk density were decrease with incoporation of GMC, while porosity was increased. Soil chemical properties, such as pH was decreased while content of exchangeable calcium, available phosphate, and organic matter were increased. Also contents of exchangeable sodium and potassium were decreased with incorporation of GMC than those before experiment. Thus, we assumed that incorporation of hairy vetch was more effective that can lead to reduce chemical nitrogen fertilizer and to improve soil environment in cultivating SSH on Saemangeum reclaimed land.

• KDI Journal of Economic Policy
• /
• v.13 no.2
• /
• pp.141-161
• /
• 1991

Resale price maintenance has long been employed in book distribution, perhaps longer than for any other product. Another unusual practice in the book trade that has proven to be quite durable in spite of its substantial cost in real resources is the returns policy. Publishers typically grant the right to return unsold books within a stipulated time for full credit against future orders. This paper investigates the functions and effects of resale price maintenance in the book trade, and argues that resale price maintenance and returns are substitute methods of providing the same economic function. Resale price maintenance can be used to compensate booksellers for initially stocking books with uncertain prospects and for providing a conduit through which manufacturers acquire information about consumer demand (market testing services). Permitting the return of unsold books for full credit places a floor under retail prices and transfers a considerable portion of the cost of introducing a new product line back to the publisher. Both reflect publishers' needs to have their books displayed. In the U.S. returns privileges were first proposed in 1913, roughly coincident with the Macy decision outlawing RPM. Publishers slowly granted return privileges, which become nearly universal by 1970. The decline in margins in recent years has been accompanied by an increase in returns as the return policy served to substitute for lost margins on successful titles as a methods of compensating full-line booksellers. In contrast, returns privileges are unusual in countries where price maintenance in books has been practiced. These observations are consistent with our analysis. In Korea, resale price maintenance of books is practiced under an exception to Korean antitrust law. The availability of effective price maintenance is likely to reduce the use of returns programs. Since consumers prefer to obtain books at outlets where they know the books are likely to be stocked rather than taking a chance on stores that carry a more limited line, it also provides a strong incentive for booksellers to expand. But the privilege of resale price maintenance should be confined to books which publishers want to be price maintained. Resale price maintenance and returns system differ in the transactions costs associated with inventory holding, and publishers' judgement on the comparative advantage of the two schemes should be honored. Publishers should also remain free to authorize sales at discount at any time not to impair the ability of booksellers to dispose of product variants that prove unpopular.

• Korean journal of applied entomology
• /
• v.20 no.4 s.49
• /
• pp.212-216
• /
• 1981

This experiment was carried out to investigate the penetration velocity and diffusion ability of methyl bromide fumigants under the condition of natural gravity, and the effect of in control of yellow corn in the vortical silo. The results were as fallows 1. The methyl bromide remainded concentration on the surface of the vertical silo was rapidly reduced from over 100mg/l to under 20mg/l, within 2 hours after supplying methyl bromide fumigant 2. Even 3m depth place from the surface of the vertical silo filled with yellolw corn was well penetrated within 30 minutes, but its remained methyl bromide gas was reduced gradually from over 100mg/l to 30mg/l after 12 hours duration. 5. In case of 13m place tile penetration ability of methyl bromide was over 100mg/l within one hour and kept the same concentration of it for 12 hours, its remainded methyl bromide preserved over 40mg/l until 48 duration time. 4. Less methyl bromide gas was detected at the bottom place than 3m and 13m depth of the vertical silo. It showed bellow 20mg/l of methyl bromide gas only through the whole duration time. 5. Comparing to the vertical penetration velocity of mehtyl bromide gas, the horizontal diffusion ability was not so good. Therefore, remained methyl bromide gas of 3m depth at the wall side of silo was about half than that of center circle where the nearer place from the methyl bromide supplying point, and the methyl bromide gas of 13m depth placed center circle was detected about 15 to 20 times than that of wall side. 6. For the purpose of examining the mortality of methyl bromide, the testing insects (Lesser Rice weevil and confused flour beetle) placed on the surface and bottom side of the silo were killed completely after 24 hrs fumigation, and the same results showed also at the 3m, 7m and 13m depth after 48 hrs fumigation.