• Journal of Korean Society of Forest Science
• /
• v.2 no.1
• /
• pp.19-28
• /
• 1962

Total area of bamboo groves in Korea which is limited to $37^{\circ}$ north latitude, i.e., to southern part of Chungchung-nam-do Province and Kangwon-do Province, is 3,235ha., but this country must import about 3,000 metric ton's bamboo culms from Japan every year. It may be true that the country is not so fit for economical cultivation of bamboo groves from the view point of climatic condition, but the author believes that self-sufficiency in bamboo is not impossible if some scientific method for improving bamboo groves is introduced to our primitive groves. Keeping this point in his mind the auther tried to study on the bamboo groves in the country, and as the first step set about to investigate the actual state of twenty good bamboo groves located in Cholla-nam-do Province from March, 1961 to January, 1962. This is a report on some characters of bamboo culms and growing stock with samples collected in the present investigation. 1) Numbers of bamboo culm per 0.1ha. are 1,183 in average, 1,840 in maximum and 87.5 in minimum before harvesting. 2) According to owners' saying, 1960 was such an off-year that they could hardly see any yearling bamboos in groves, but in 1961 very many new bamboos are produced as follows: the proportion of the number of yearling bamboos produced this year to that of mature bamboos (over 2 years old) is 58.7% in average; the highest 110.5% and the lowest 16.8%. 3) the average diameter of culms at eye height is 6.5cm, but the biggest diameter comes to 11.2 cm, and the average diameters of yearling and mature bamboos are 6.5cm and 6.6cm respectively. 4) Internode length records 29.4 cm in average, the shortest 21.3 cm and the longest 38.4 cm. Average internode lengths of new culms and mature culms are 27.6 cm and 29.4 cm respectively. This shows that the internode length of new culms is in the decrease to that of maturer's. 5) Through this investigation, it was found that internode length is in the influence of the exposure and density of bamboo groves, i. e., the more the dencity of bamboo groves is and the more the exposure nears the north-east, the longer the internode length becomes (see Table 7 and 8). 6) In the growing stock of bamboo groves, bundles per 0.1ha. amount to 271 sok (unit of bundle) in total average, 445 sok in maximum and 126 sok in minimum. 7) Among twenty typical bamboo groves, chosen in each County in Cholla-nam-do Province, only one passes perfectly by Veda's standard rule* prescribing the good bamboo grove, but the eight groves shown in Table 9 could be recommended as good ones in Cholla-nam-do Province, because the auther believes that those groves may be improved better, if we pay more attention to the management of them. 8) Considering that they have managed their groves carelessly and primitively, and that unfortunately their groves must have faced almost on clear felling over the entire area at the time of the Korean War, we can surely expect much more increments in bamboo groves, if we introduce some scientific methods in managing their groves.

• Asia pacific journal of information systems
• /
• v.18 no.4
• /
• pp.27-55
• /
• 2008

Due to the increasing and intensifying competition in the Internet shopping market, it has been recognized as very important to develop an effective policy and strategy for acquiring loyal customers. For this reason, web site designers need to know if a new Internet shopping mall(ISM) will be accepted. Researchers have been working on identifying factors for explaining and predicting user acceptance of an ISM. Some studies, however, revealed inconsistent findings on the antecedents of user acceptance of a website. Lack of consideration for individual differences in user ability is believed to be one of the key reasons for the mixed findings. The elaboration likelihood model (ELM) and several studies have suggested that individual differences in ability plays an moderating role on the relationship between the antecedents and user acceptance. Despite the critical role of user ability, little research has examined the role of user ability in the Internet shopping mall context. The purpose of this study is to develop a user acceptance model that consider the moderating role of user ability in the context of Internet shopping. This study was initiated to see the ability of the technology acceptance model(TAM) to explain the acceptance of a specific ISM. According to TAM. which is one of the most influential models for explaining user acceptance of IT, an intention to use IT is determined by usefulness and ease of use. Given that interaction between user and website takes place through web interface, the decisions to accept and continue using an ISM depend on these beliefs. However, TAM neglects to consider the fact that many users would not stick to an ISM until they trust it although they may think it useful and easy to use. The importance of trust for user acceptance of ISM has been raised by the relational views. The relational view emphasizes the trust-building process between the user and ISM, and user's trust on the website is a major determinant of user acceptance. The proposed model extends and integrates the TAM and relational views on user acceptance of ISM by incorporating usefulness, ease of use, and trust. User acceptance is defined as a user's intention to reuse a specific ISM. And user ability is introduced into the model as moderating variable. Here, the user ability is defined as a degree of experiences, knowledge and skills regarding Internet shopping sites. The research model proposes that the ease of use, usefulness and trust of ISM are key determinants of user acceptance. In addition, this paper hypothesizes that the effects of the antecedents(i.e., ease of use, usefulness, and trust) on user acceptance may differ among users. In particular, this paper proposes a moderating effect of a user's ability on the relationship between antecedents with user's intention to reuse. The research model with eleven hypotheses was derived and tested through a survey that involved 470 university students. For each research variable, this paper used measurement items recognized for reliability and widely used in previous research. We slightly modified some items proper to the research context. The reliability and validity of the research variables were tested using the Crobnach's alpha and internal consistency reliability (ICR) values, standard factor loadings of the confirmative factor analysis, and average variance extracted (AVE) values. A LISREL method was used to test the suitability of the research model and its relating six hypotheses. Key findings of the results are summarized in the following. First, TAM's two constructs, ease of use and usefulness directly affect user acceptance. In addition, ease of use indirectly influences user acceptance by affecting trust. This implies that users tend to trust a shopping site and visit repeatedly when they perceive a specific ISM easy to use. Accordingly, designing a shopping site that allows users to navigate with heuristic and minimal clicks for finding information and products within the site is important for improving the site's trust and acceptance. Usefulness, however, was not found to influence trust. Second, among the three belief constructs(ease of use, usefulness, and trust), trust was empirically supported as the most important determinants of user acceptance. This implies that users require trustworthiness from an Internet shopping site to be repeat visitors of an ISM. Providing a sense of safety and eliminating the anxiety of online shoppers in relation to privacy, security, delivery, and product returns are critically important conditions for acquiring repeat visitors. Hence, in addition to usefulness and ease of use as in TAM, trust should be a fundamental determinants of user acceptance in the context of internet shopping. Third, the user's ability on using an Internet shopping site played a moderating role. For users with low ability, ease of use was found to be a more important factors in deciding to reuse the shopping mall, whereas usefulness and trust had more effects on users with high ability. Applying the EML theory to these findings, we can suggest that experienced and knowledgeable ISM users tend to elaborate on such usefulness aspects as efficient and effective shopping performance and trust factors as ability, benevolence, integrity, and predictability of a shopping site before they become repeat visitors of the site. In contrast, novice users tend to rely on the low elaborating features, such as the perceived ease of use. The existence of moderating effects suggests the fact that different individuals evaluate an ISM from different perspectives. The expert users are more interested in the outcome of the visit(usefulness) and trustworthiness(trust) than those novice visitors. The latter evaluate the ISM in a more superficial manner focusing on the novelty of the site and on other instrumental beliefs(ease of use). This is consistent with the insights proposed by the Heuristic-Systematic model. According to the Heuristic-Systematic model. a users act on the principle of minimum effort. Thus, the user considers an ISM heuristically, focusing on those aspects that are easy to process and evaluate(ease of use). When the user has sufficient experience and skills, the user will change to systematic processing, where they will evaluate more complex aspects of the site(its usefulness and trustworthiness). This implies that an ISM has to provide a minimum level of ease of use to make it possible for a user to evaluate its usefulness and trustworthiness. Ease of use is a necessary but not sufficient condition for the acceptance and use of an ISM. Overall, the empirical results generally support the proposed model and identify the moderating effect of the effects of user ability. More detailed interpretations and implications of the findings are discussed. The limitations of this study are also discussed to provide directions for future research.

• Korean Journal of Ecology and Environment
• /
• v.37 no.2 s.107
• /
• pp.180-192
• /
• 2004

This study was carried out to assess the seasonal variation of water quality and the effect of pollutant loading from watershed in a shallow eutrophic reservoir (Shingu reservoir) from November 2002 to February 2004, Stable thermocline which was greater than $1^{\circ}C$ per meter of the water depth formed in May, and low DO concentration (< 2 mg $O_2\;L^{-1}$) was observed in the hypolimnion from May to September, 2003. The ratio of euphotic depth to mixing depth ($Z_{eu}/Z_{m}$) ranged 0.2 ${\sim}$ 1.1, and the depth of the mixed layer exceeded that of the photic layer during study period, except for May when $Z_{eu}$ and $Z_{m}$ were 4 and 4.3 m, respectively. Most of total nitrogen, ranged 1.1 ${\sim}$ 4.5 ${\mu}g\;N\;L^{-1}$, accounted for inorganic nitrogen (Avg, 58.7%), and sharp increase of $NH_3$-N Hand $NO_3$-N was evident during the spring season. TP concentration in the water column ranged 43.9 ${\sim}$ 126.5 ${\mu}g\;P\;L^{-1}$, and the most of TP in the water column accounted for POP (Avg. 80%). During the study period, DIP concentration in the water column was &;lt 10 ${\mu}g\;P\;L^{-1}$ except for July and August when DIP concentration in the hypolimnion was 22.3 and 56.7 ${\mu}g\;P\;L^{-1}$, respectively. Increase of Chl. a concentration observed in July (99 ${\mu}g\;L^{-1}$) and November 2003 (109 ${\mu}g\;L^{-1}$) when P loading through two inflows was high, and showed close relationship with TP concentration (r = 0.55, P< 0.008, n = 22). Mean Chl. a concentration ranged from 13.5 to 84.5 mg $L^{-1}$ in the water column, and the lowest and highest concentration was observed in February 2004 (13.5 ${\pm}$ 1.0 ${\mu}g\;L^{-1}$) and November 2003 (84.5 ${\pm}$29.0 ${\mu}g\;L^{-1}$), respectively. TP concentration in inflow water increased with discharge (r = 0.69, P< 0.001), 40.5% of annual total P loading introduced in 25 July when there was heavy rainfall. Annual total P loading from watershed was 159.0 kg P $yr^{-1}$, and that of DIP loading was 126.3 kg P $yr^{-1}$ (77.7% of TP loading. The loading of TN (5.0ton yr-1) was 30 times higher than that of TP loading (159.0 kg P yr-1), and the 78% of TN was in the form of non-organic nitrogen, 3.9 ton $yr^{-1}$ in mass. P loading in Shingu reservoir was 1.6 g ${\cdot}$ $m^{-2}$ ${\cdot}$ $yr^{-1}$, which passed the excessive critical loading of Vollenweider-OECD critical loading model. The results of this study indicated that P loading from watershed was the major factor to cause eutrophication and temporal variation of water quality in Shingu reservoir Decrease by 71% in TP loading (159 kg $yr^{-1}$) is necessary for the improvement of mesotrophic level. The management of sediment where tine anaerobic condition was evident in summer, thus, the possibility of P release that can be utilized by existing algae, may also be considered.

• Tuberculosis and Respiratory Diseases
• /
• v.47 no.3
• /
• pp.321-330
• /
• 1999

Background : Early diagnosis and proper antibiotic treatment are very important in the management of ventilator-associated pneumonia (VAP) because of its high mortality. Bronchoscopy with a protected specimen brush (PSB) has been considered the standard method to isolate the causative organisms of VAP. However, this method burdens consumer economically to purchase a PSB. Another useful method for the diagnosis of VAP is quantitative cultures of aspirated specimens through bronchoscopic bronchoalveolar lavage (BAL), for which the infusion of more than 120 m1 of saline has been recommended for adequate sampling of a pulmonary segment. However, occasionally it leads to deterioration of the patient's condition. We studied the diagnostic efficacy of minibronchoalveolar lavage (miniBAL), which retrieves only 25 ml of BAL fluid, in the isolation of causative organisms of VAP. Methods: We included 38 consecutive patients (41 cases) suspected of having VAP on the basis of clinical evidence, who had received antibiotics before the bronchoscopy. The two diagnostic techniques of PSB and miniBAL, which were performed one after another at the same pulmonary segment, 'were compared prospectively. The cut-off values for quantitative cultures to define causative bacteria of VAP were more than $10^3$ colony-forming units (cfu)/ml for PSB and more than $10^4$ cfu/ml for BAL. Results: The amount of instilled normal saline required to retrieve 25 ml of BAL fluid was $93{\pm}32 ml$ (mean${\pm}$SD). The detection rate of causative agents was 46.3% (19/41) with PSB and 43.9% (18/41) with miniBAL. The concordance rate of PSB and miniBAL in the bacterial culture was 85.4% (35/41). Although arterial blood oxygen saturation dropped significantly (p<0.05) during ($92{\pm}10%$) and 10 min after ($95{\pm}3%$) miniBAL compared with the baseline ($97{\pm}3%$), all except 3 cases were within normal ranges. The significantly elevated heart rate during ($l25{\pm}24$/min, p<0.05) miniBAL compared with the baseline ($1l1{\pm}22$/min) recovered again in 10 min after ($111{\pm}26$/min) miniBAL. Transient hypotension was developed during the procedure in two cases. The procedure was stopped in one case due to atrial flutter. Conclusion: MiniBAL is a safe and effective technique to detect the causative organisms of VAP.

• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.185-202
• /
• 2012

.Since the value of information has been realized in the information society, the usage and collection of information has become important. A facial expression that contains thousands of information as an artistic painting can be described in thousands of words. Followed by the idea, there has recently been a number of attempts to provide customers and companies with an intelligent service, which enables the perception of human emotions through one's facial expressions. For example, MIT Media Lab, the leading organization in this research area, has developed the human emotion prediction model, and has applied their studies to the commercial business. In the academic area, a number of the conventional methods such as Multiple Regression Analysis (MRA) or Artificial Neural Networks (ANN) have been applied to predict human emotion in prior studies. However, MRA is generally criticized because of its low prediction accuracy. This is inevitable since MRA can only explain the linear relationship between the dependent variables and the independent variable. To mitigate the limitations of MRA, some studies like Jung and Kim (2012) have used ANN as the alternative, and they reported that ANN generated more accurate prediction than the statistical methods like MRA. However, it has also been criticized due to over fitting and the difficulty of the network design (e.g. setting the number of the layers and the number of the nodes in the hidden layers). Under this background, we propose a novel model using Support Vector Regression (SVR) in order to increase the prediction accuracy. SVR is an extensive version of Support Vector Machine (SVM) designated to solve the regression problems. The model produced by SVR only depends on a subset of the training data, because the cost function for building the model ignores any training data that is close (within a threshold ${\varepsilon}$) to the model prediction. Using SVR, we tried to build a model that can measure the level of arousal and valence from the facial features. To validate the usefulness of the proposed model, we collected the data of facial reactions when providing appropriate visual stimulating contents, and extracted the features from the data. Next, the steps of the preprocessing were taken to choose statistically significant variables. In total, 297 cases were used for the experiment. As the comparative models, we also applied MRA and ANN to the same data set. For SVR, we adopted '${\varepsilon}$-insensitive loss function', and 'grid search' technique to find the optimal values of the parameters like C, d, ${\sigma}^2$, and ${\varepsilon}$. In the case of ANN, we adopted a standard three-layer backpropagation network, which has a single hidden layer. The learning rate and momentum rate of ANN were set to 10%, and we used sigmoid function as the transfer function of hidden and output nodes. We performed the experiments repeatedly by varying the number of nodes in the hidden layer to n/2, n, 3n/2, and 2n, where n is the number of the input variables. The stopping condition for ANN was set to 50,000 learning events. And, we used MAE (Mean Absolute Error) as the measure for performance comparison. From the experiment, we found that SVR achieved the highest prediction accuracy for the hold-out data set compared to MRA and ANN. Regardless of the target variables (the level of arousal, or the level of positive / negative valence), SVR showed the best performance for the hold-out data set. ANN also outperformed MRA, however, it showed the considerably lower prediction accuracy than SVR for both target variables. The findings of our research are expected to be useful to the researchers or practitioners who are willing to build the models for recognizing human emotions.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.10 no.2
• /
• pp.145-157
• /
• 1999

This study was performed by the children and adolescents who were abused or neglected physically, emotionally that were selected in child & adolescents psychiatric ward. We investigated the number of these case in admitted children & adolescents, and also observed characteristics of symptoms, developmental history, characteristics of abuse style, characteristics of abusers, family dynamics and psychopathology. We hypothesized that all kinds of abuse will influnced to emotional, behavioral problems, developmental courses on victims, interactive effects on family dynamics and psychopathology. That subjects were 22 persons of victims who be determined by clinical observation and clinical note. The results of the study were as follows：1) Demographic characteristics of victims：ratio of sex was 1：6.3(male：female), mean age was $11.1{\pm}2.5$. According to birth order, lst was 12(54.5%), 2nd was 5(23%), 3rd was 2(9%) and only child was 3(13.5%). 2) Characteristics of family：According to socioeconomic status, middle to high class was 3(13.5%), middle one was 9(41.% ), middle to low one was 9(41%), low one was 1(0.5%). according to number of family, under the 3 person was 3(13.5%), 4-5 was 17(77.5%), 6-7 was 2(9%). according to marital status of parents, divorce or seperation were 5(23%), remarriage 2(9%), severe marital discord was 19(86.5%). In father, antisocial behavior was 7(32%), alcohol dependence was 10(45.5%). In mother, alcohol abuse was 5(23%), depression was 17(77.3%), history of psychiatric management was 6(27%). 3) Characteristics of abuse：Physical abuse was 18(81.8%), physical and emotional abuse and neglect were 4(18.2%). according to onset of abuse, before 3 years was 15(54.5%), 3-6 years was 5(27.5%), schooler was 1(15%). Only father offender was 2(19%), only mother offender was 8(35.4%), both offender was 8(35.4%), accompaning with spouse abuse was 7(27%), and accompaning with other sibling abuse was 4(18.2%). 4) General characteristics and developmental history of victims：Unwanted baby was 12(54.5%), developmental delay before abuse was9(41%), comorbid developmental disorder was 15(68%). there were 6(27.5%) who didn‘t show definite sign of developmental delay before abuse. 5) Main diagnosis and comorbid diagnosis：According to main diagnosis, conduct disorder 6(27.3%), borderline child 5(23%), depression4(18%), attention deficit hyperactivity disorder(ADHD) 4(18%), pervasive developmental disorder not otherwise specified 2(9%), selective mutism 1(5%). According to comorbid diagnosis, ADHD, borderline intelligence, mental retardation, learning disorder, developmental language disorder, oppositional defiant disorder, chronic tic disorder, functional enuresis and encoporesis, anxiety disorder, dissociative disorder, personality disorder due to medical condition. 5) Course of treatment：A mean duration of admission was $2.4{\pm}1.5$ months. 11(15%) showed improvement of symtoms, however 11(50%) was not changed of symtoms.

• Journal of Genetic Medicine
• /
• v.8 no.2
• /
• pp.89-99
• /
• 2011

Over the years Korean health care system has improved in delivery of quality care to the general population for many areas of the health problems. The system is now being recognized in the world as the most cost effective one. It is covered by the uniform national health insurance policy for which most people in Korea are mandatory policy holders. Genetic counseling service, however, which is well recognized as an integral part of clinical genetics service deals with diagnosis and management of genetic condition as well as genetic information presentation and family support, is yet to be delivered in comprehensive way for the patients and families in need. Two major obstacles in providing genetic counseling service in korean health care system are identified; One is the lack of recognition for the need for genetic counseling service as necessary service by the national health insurance. Genetic counseling consumes a significant time in delivery and the current very low-fee schedule for physician service makes it very difficult to provide meaningful service. Second is the critical shortage of qualified professionals in the field of medical genetics and genetic counseling who can provide the service of genetic counseling in clinical setting. However, recognition and understanding of the fact that the scope and role of genetic counseling is expanding in post genomic era of personalized medicine for delivery of quality health care, will lead to the efforts to overcome obstacles in providing genetic counseling service in korean health care system. Only concerted efforts from health care policy makers of government on clinical genetics service and genetic counseling for establishing adequate reimbursement coverage and professional communities for developing educational program and certification process for professional genetic counselors, are necessary for the delivery of much needed clinical genetic counseling service in Korea.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.179-196
• /
• 2019

Recently, the "Smart Consumer" has been emerging. He or she is increasingly inclined to search for and purchase products by taking into account personal judgment or expert reviews rather than by relying on information delivered through manufacturers' advertising. This is especially true when purchasing cosmetics. Because cosmetics act directly on the skin, consumers respond seriously to dangerous chemical elements they contain or to skin problems they may cause. Above all, cosmetics should fit well with the purchaser's skin type. In addition, changes in global cosmetics consumer trends make it necessary to study this field. The desire to find one's own individualized cosmetics is being revealed to consumers around the world and is known as "Finding the Holy Grail." Many consumers show a deep interest in customized cosmetics with the cultural boom known as "K-Beauty" (an aspect of "Han-Ryu"), the growth of personal grooming, and the emergence of "self-culture" that includes "self-beauty" and "self-interior." These trends have led to the explosive popularity of cosmetics made in Korea in the Chinese and Southeast Asian markets. In order to meet the customized cosmetics needs of consumers, cosmetics manufacturers and related companies are responding by concentrating on delivering premium services through the convergence of ICT(Information, Communication and Technology). Despite the evolution of companies' responses regarding market trends toward customized cosmetics, there is no "Intelligent Data Platform" that deals holistically with consumers' skin condition experience and thus attaches emotions to products and services. To find the Holy Grail of customized cosmetics, it is important to acquire and analyze consumer data on what they want in order to address their experiences and emotions. The emotions consumers are addressing when purchasing cosmetics varies by their age, sex, skin type, and specific skin issues and influences what price is considered reasonable. Therefore, it is necessary to classify emotions regarding cosmetics by individual consumer. Because of its importance, consumer emotion analysis has been used for both services and products. Given the trends identified above, we judge that consumer emotion analysis can be used in our study. Therefore, we collected and indexed data on consumers' emotions regarding their cosmetics experiences focusing on consumers' language. We crawled the cosmetics emotion data from SNS (blog and Twitter) according to sales ranking ($1^{st}$ to $99^{th}$), focusing on the ample/serum category. A total of 357 emotional adjectives were collected, and we combined and abstracted similar or duplicate emotional adjectives. We conducted a "Consumer Sentiment Journey" workshop to build a "Consumer Sentiment Dictionary," and this resulted in a total of 76 emotional adjectives regarding cosmetics consumer experience. Using these 76 emotional adjectives, we performed clustering with the Self-Organizing Map (SOM) method. As a result of the analysis, we derived eight final clusters of cosmetics consumer sentiments. Using the vector values of each node for each cluster, the characteristics of each cluster were derived based on the top ten most frequently appearing consumer sentiments. Different characteristics were found in consumer sentiments in each cluster. We also developed a cosmetics experience pattern map. The study results confirmed that recommendation and classification systems that consider consumer emotions and sentiments are needed because each consumer differs in what he or she pursues and prefers. Furthermore, this study reaffirms that the application of emotion and sentiment analysis can be extended to various fields other than cosmetics, and it implies that consumer insights can be derived using these methods. They can be used not only to build a specialized sentiment dictionary using scientific processes and "Design Thinking Methodology," but we also expect that these methods can help us to understand consumers' psychological reactions and cognitive behaviors. If this study is further developed, we believe that it will be able to provide solutions based on consumer experience, and therefore that it can be developed as an aspect of marketing intelligence.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.57-73
• /
• 2021

Maintenance and prevention of failure through anomaly detection of ICT infrastructure is becoming important. System monitoring data is multidimensional time series data. When we deal with multidimensional time series data, we have difficulty in considering both characteristics of multidimensional data and characteristics of time series data. When dealing with multidimensional data, correlation between variables should be considered. Existing methods such as probability and linear base, distance base, etc. are degraded due to limitations called the curse of dimensions. In addition, time series data is preprocessed by applying sliding window technique and time series decomposition for self-correlation analysis. These techniques are the cause of increasing the dimension of data, so it is necessary to supplement them. The anomaly detection field is an old research field, and statistical methods and regression analysis were used in the early days. Currently, there are active studies to apply machine learning and artificial neural network technology to this field. Statistically based methods are difficult to apply when data is non-homogeneous, and do not detect local outliers well. The regression analysis method compares the predictive value and the actual value after learning the regression formula based on the parametric statistics and it detects abnormality. Anomaly detection using regression analysis has the disadvantage that the performance is lowered when the model is not solid and the noise or outliers of the data are included. There is a restriction that learning data with noise or outliers should be used. The autoencoder using artificial neural networks is learned to output as similar as possible to input data. It has many advantages compared to existing probability and linear model, cluster analysis, and map learning. It can be applied to data that does not satisfy probability distribution or linear assumption. In addition, it is possible to learn non-mapping without label data for teaching. However, there is a limitation of local outlier identification of multidimensional data in anomaly detection, and there is a problem that the dimension of data is greatly increased due to the characteristics of time series data. In this study, we propose a CMAE (Conditional Multimodal Autoencoder) that enhances the performance of anomaly detection by considering local outliers and time series characteristics. First, we applied Multimodal Autoencoder (MAE) to improve the limitations of local outlier identification of multidimensional data. Multimodals are commonly used to learn different types of inputs, such as voice and image. The different modal shares the bottleneck effect of Autoencoder and it learns correlation. In addition, CAE (Conditional Autoencoder) was used to learn the characteristics of time series data effectively without increasing the dimension of data. In general, conditional input mainly uses category variables, but in this study, time was used as a condition to learn periodicity. The CMAE model proposed in this paper was verified by comparing with the Unimodal Autoencoder (UAE) and Multi-modal Autoencoder (MAE). The restoration performance of Autoencoder for 41 variables was confirmed in the proposed model and the comparison model. The restoration performance is different by variables, and the restoration is normally well operated because the loss value is small for Memory, Disk, and Network modals in all three Autoencoder models. The process modal did not show a significant difference in all three models, and the CPU modal showed excellent performance in CMAE. ROC curve was prepared for the evaluation of anomaly detection performance in the proposed model and the comparison model, and AUC, accuracy, precision, recall, and F1-score were compared. In all indicators, the performance was shown in the order of CMAE, MAE, and AE. Especially, the reproduction rate was 0.9828 for CMAE, which can be confirmed to detect almost most of the abnormalities. The accuracy of the model was also improved and 87.12%, and the F1-score was 0.8883, which is considered to be suitable for anomaly detection. In practical aspect, the proposed model has an additional advantage in addition to performance improvement. The use of techniques such as time series decomposition and sliding windows has the disadvantage of managing unnecessary procedures; and their dimensional increase can cause a decrease in the computational speed in inference.The proposed model has characteristics that are easy to apply to practical tasks such as inference speed and model management.

• Korean Journal of Soil Science and Fertilizer
• /
• v.45 no.3
• /
• pp.344-352
• /
• 2012

Soil physical properties determine soil quality in aspect of root growth, infiltration, water and nutrient holding capacity. Although the monitoring of soil physical properties is important for sustainable agricultural production, there were few studies. This study was conducted to investigate the condition of soil physical properties of arable land according to land use across the country. The work was investigated on plastic film house soils, upland soils, orchard soils, and paddy soils from 2008 to 2011, including depth of topsoil, bulk density, hardness, soil texture, and organic matter. The average physical properties were following; In plastic film house soils, the depth of topsoil was 16.2 cm. For the topsoils, hardness was 9.0 mm, bulk density was 1.09 Mg $m^{-3}$, and organic matter content was 29.0 g $kg^{-1}$. For the subsoils, hardness was 19.8 mm, bulk density was 1.32 Mg $m^{-3}$, and organic matter content was 29.5 g $kg^{-1}$; In upland soils, depth of topsoil was 13.3 cm. For the topsoils, hardness was 11.3 mm, bulk density was 1.33 Mg $m^{-3}$, and organic matter content was 20.6 g $kg^{-1}$. For the subsoils, hardness was 18.8 mm, bulk density was 1.52 Mg $m^{-3}$, and organic matter content was 13.0 g $kg^{-1}$. Classified by the types of crop, soil physical properties were high value in a group of deep-rooted vegetables and a group of short-rooted vegetables soil, but low value in a group of leafy vegetables soil; In orchard soils, the depth of topsoil was 15.4 cm. For the topsoils, hardness was 16.1 mm, bulk density was 1.25 Mg $m^{-3}$, and organic matter content was 28.5 g $kg^{-1}$. For the subsoils, hardness was 19.8 mm, bulk density was 1.41 Mg $m^{-3}$, and organic matter content was 15.9 g $kg^{-1}$; In paddy soils, the depth of topsoil was 17.5 cm. For the topsoils, hardness was 15.3 mm, bulk density was 1.22 Mg $m^{-3}$, and organic matter content was 23.5 g $kg^{-1}$. For the subsoils, hardness was 20.3 mm, bulk density was 1.47 Mg $m^{-3}$, and organic matter content was 17.5 g $kg^{-1}$. The average of bulk density was plastic film house soils < paddy soils < orchard soils < upland soils in order, according to land use. The bulk density value of topsoils is mainly distributed in 1.0~1.25 Mg $m^{-3}$. The bulk density value of subsoils is mostly distributed in more than 1.50, 1.35~1.50, and 1.0~1.50 Mg $m^{-3}$ for upland and paddy soils, orchard soils, and plastic film house soils, respectively. Classified by soil textural family, there was lower bulk density in clayey soil, and higher bulk density in fine silty and sandy soil. Soil physical properties and distribution of topography were different classified by the types of land use and growing crops. Therefore, we need to consider the types of land use and crop for appropriate soil management.