• Geophysics and Geophysical Exploration
• /
• v.19 no.1
• /
• pp.1-10
• /
• 2016

The hypocenter distribution of microseismic events generated by hydraulic fracturing for shale gas development provides essential information for understanding characteristics of fracture network. In this study, we evaluate how inaccurate velocity models influence the inversion results of two widely used location programs, hypoellipse and hypoDD, which are developed based on an iterative linear inversion. We assume that 98 stations are densely located inside the circle with a radius of 4 km and 5 artificial hypocenter sets (S0 ~ S4) are located from the center of the network to the south with 1 km interval. Each hypocenter set contains 25 events placed on the plane. To quantify accuracies of the inversion results, we defined 6 parameters: difference between average hypocenters of assumed and inverted locations, $d_1$; ratio of assumed and inverted areas estimated by hypocenters, r; difference between dip of the reference plane and the best fitting plane for determined hypocenters, ${\theta}$; difference between strike of the reference plane and the best fitting plane for determined hypocenters, ${\phi}$; root-mean-square distance between hypocenters and the best fitting plane, $d_2$; root-mean-square error in horizontal direction on the best fitting plane, $d_3$. Synthetic travel times are calculated for the reference model having 1D layered structure and the inaccurate velocity model for the inversion is constructed by using normal distribution with standard deviations of 0.1, 0.2, and 0.3 km/s, respectively, with respect to the reference model. The parameters $d_1$, r, ${\theta}$, and $d_2$ show positive correlation with the level of velocity perturbations, but the others are not sensitive to the perturbations except S4, which is located at the outer boundary of the network. In cases of S0, S1, S2, and S3, hypoellipse and hypoDD provide similar results for $d_1$. However, for other parameters, hypoDD shows much better results and errors of locations can be reduced by about several meters regardless of the level of perturbations. In light of the purpose to understand the characteristics of hydraulic fracturing, $1{\sigma}$ error of velocity structure should be under 0.2 km/s in hypoellipse and 0.3 km/s in hypoDD.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.37 no.3
• /
• pp.54-60
• /
• 2009

The purpose of this study is to analyze the impacts of three-dimensional land cover on changing urban air temperatures and to explore some strategies of urban landscaping towards mitigation of heat build-up. This study located study spaces within a diameter of 300m around 24 Automatic Weather Stations(AWS) in Seoul, and collected data of diverse variables which could affect summer energy budgets and air temperatures. The study also selected reflecting study objectives 6 smaller-scale spaces with a diameter of 30m in Chuncheon, and measured summer air temperatures and three-dimensional land cover to compare their relationships with results from Seoul's AWS. Linear regression models derived from data of Seoul's AWS revealed that vegetation volume, greenspace area, building volume, building area, population density, and pavement area contributed to a statistically significant change in summer air temperatures. Of these variables, vegetation and building volume indicated the highest accountability for total variability of changes in the air temperatures. Multiple regression models derived from combinations of the significant variables also showed that both vegetation and building volume generated a model with the best fitness. Based on this multiple regression model, a 10% increase of vegetation volume decreased the air temperatures by approximately 0.14%, while a 10% increase of building volume raised them by 0.26%. Relationships between Chuncheon's summer air temperatures and land cover distribution for the smaller-scale spaces also disclosed that the air temperatures were negatively correlated to vegetation volume and greenspace area, while they were positively correlated to hardscape area. Similarly to the case of Seoul's AWS, the air temperatures for the smaller-scale spaces decreased by 0.32% ($0.08^{\circ}C$) as vegetation volume increased by 10%, based on the most appropriate linear model. Thus, urban landscaping for the reduction of summer air temperatures requires strategies to improve vegetation volume and simultaneously to decrease building volume. For Seoul's AWS, the impact of building volume on changing the air temperatures was about 2 times greater than that of vegetation volume. Wall and rooftop greening for shading and evapotranspiration is suggested to control atmospheric heating by three-dimensional building surfaces, enlarging vegetation volume through multilayered plantings on soil surfaces.

• Journal of Animal Science and Technology
• /
• v.45 no.5
• /
• pp.711-724
• /
• 2003

Some growth curve models were used to fit individual growth of 1,083 Hanwoo cows born from 1970 to 2001 in Daekwanryeong branch, National Livestock Research Institute(NLRI). The effects of year-season of birth and age of dam were analyzed. In analysis of variance for growth curve parameters, the effects of birth year-season were significant for mature weight(A), growth ratio(b) and maturing rate(k)(P〈.01). The effects of age of dam were significant for growth ratio(b) but not significant for mature weight(A) and maturing rate(k). The linear term of the covariate of age at the final weights was significant for the A(P〈.01) and k(P〈.01) of Gompertz model, von Bertalanffy model and Logistic model. For the growth curve parameters fitted on individual data using Gompertz model, von Bertalanffy model and Logistic model, resulting the linear contrasts(fall-spring), Least square means of A in three nonlinear models were higher cows born at fall and A of Logistic model was significant(P〈.05) between the seasons. According to the results of the least square means of growth curve parameters by age of dam, least square means of mature weight(A) in Gompertz model was largest in 6 year and smallest estimating for 3 and 8 years of age of dam. The growth ratio(b) was largest in 2 year of age of dam and smallest estimating in 8 year. The A and k were not different by age of dam(p〉.05), On the other hand, the b was different by age of dam(p〈.01). The estimate of A in von Bertalanffy model was largest in 6 year and smallest in 8 and 9 years of age of dam. The b was largest in 2 year and tend to decline as age of dam increased. The A and k were not different by age of dam(p〉.05), On the other hand, the b was highly significant by age of dam(p〈.01).

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.10
• /
• pp.303-308
• /
• 2020

The ReLU(Rectified Linear Unit) function has been dominantly used as a standard activation function in most deep artificial neural network models since it was proposed. Later, Leaky ReLU, Swish, and Mish activation functions were presented to replace ReLU, which showed improved performance over existing ReLU function in image classification task. Therefore, we recognized the need to experiment with whether performance improvements could be achieved by replacing the RELU with other activation functions in the super resolution task. In this paper, the performance was compared by changing the activation functions in EDSR model, which showed stable performance in the super resolution task. As a result, in experiments conducted with changing the activation function of EDSR, when the resolution was converted to double, the existing activation function, ReLU, showed similar or higher performance than the other activation functions used in the experiment. When the resolution was converted to four times, Leaky ReLU and Swish function showed slightly improved performance over ReLU. PSNR and SSIM, which can quantitatively evaluate the quality of images, were able to identify average performance improvements of 0.06%, 0.05% when using Leaky ReLU, and average performance improvements of 0.06% and 0.03% when using Swish. When the resolution is converted to eight times, the Mish function shows a slight average performance improvement over the ReLU. Using Mish, PSNR and SSIM were able to identify an average of 0.06% and 0.02% performance improvement over the RELU. In conclusion, Leaky ReLU and Swish showed improved performance compared to ReLU for super resolution that converts resolution four times and Mish showed improved performance compared to ReLU for super resolution that converts resolution eight times. In future study, we should conduct comparative experiments to replace activation functions with Leaky ReLU, Swish and Mish to improve performance in other super resolution models.

• Journal of Intelligence and Information Systems
• /
• v.22 no.4
• /
• pp.69-85
• /
• 2016

Successful relationship with loving partners is one of the most important factors in life. In psychology, there have been some previous researches studying the factors influencing romantic relationships. However, most of these researches were performed based on statistical analysis; thus they have limitations in analyzing complex non-linear relationships or rules based reasoning. This research analyzes commitment and persistence in heterosexual involvement according to styles of loving using a datamining technique as well as statistical methods. In this research, we consider six different styles of loving - 'eros', 'ludus', 'stroge', 'pragma', 'mania' and 'agape' which influence romantic relationships between lovers, besides the factors suggested by the previous researches. These six types of love are defined by Lee (1977) as follows: 'eros' is romantic, passionate love; 'ludus' is a game-playing or uncommitted love; 'storge' is a slow developing, friendship-based love; 'pragma' is a pragmatic, practical, mutually beneficial relationship; 'mania' is an obsessive or possessive love and, lastly, 'agape' is a gentle, caring, giving type of love, brotherly love, not concerned with the self. In order to do this research, data from 105 heterosexual couples were collected. Using the data, a linear regression method was first performed to find out the important factors associated with a commitment to partners. The result shows that 'satisfaction', 'eros' and 'agape' are significant factors associated with the commitment level for both male and female. Interestingly, in male cases, 'agape' has a greater effect on commitment than 'eros'. On the other hand, in female cases, 'eros' is a more significant factor than 'agape' to commitment. In addition to that, 'investment' of the male is also crucial factor for male commitment. Next, decision tree analysis was performed to find out the characteristics of high commitment couples and low commitment couples. In order to build decision tree models in this experiment, 'decision tree' operator in the datamining tool, Rapid Miner was used. The experimental result shows that males having a high satisfaction level in relationship show a high commitment level. However, even though a male may not have a high satisfaction level, if he has made a lot of financial or mental investment in relationship, and his partner shows him a certain amount of 'agape', then he also shows a high commitment level to the female. In the case of female, a women having a high 'eros' and 'satisfaction' level shows a high commitment level. Otherwise, even though a female may not have a high satisfaction level, if her partner shows a certain amount of 'mania' then the female also shows a high commitment level. Finally, this research built a prediction model to establish whether the relationship will persist or break up using a decision tree. The result shows that the most important factor influencing to the break up is a 'narcissistic tendency' of the male. In addition to that, 'satisfaction', 'investment' and 'mania' of both male and female also affect a break up. Interestingly, while the 'mania' level of a male works positively to maintain the relationship, that of a female has a negative influence. The contribution of this research is adopting a new technique of analysis using a datamining method for psychology. In addition, the results of this research can provide useful advice to couples for building a harmonious relationship with each other. This research has several limitations. First, the experimental data was sampled based on oversampling technique to balance the size of each classes. Thus, it has a limitation of evaluating performances of the predictive models objectively. Second, the result data, whether the relationship persists of not, was collected relatively in short periods - 6 months after the initial data collection. Lastly, most of the respondents of the survey is in their 20's. In order to get more general results, we would like to extend this research to general populations.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.127-146
• /
• 2022

Recently, as word embedding has shown excellent performance in various tasks of deep learning-based natural language processing, researches on the advancement and application of word, sentence, and document embedding are being actively conducted. Among them, cross-language transfer, which enables semantic exchange between different languages, is growing simultaneously with the development of embedding models. Academia's interests in vector alignment are growing with the expectation that it can be applied to various embedding-based analysis. In particular, vector alignment is expected to be applied to mapping between specialized domains and generalized domains. In other words, it is expected that it will be possible to map the vocabulary of specialized fields such as R&D, medicine, and law into the space of the pre-trained language model learned with huge volume of general-purpose documents, or provide a clue for mapping vocabulary between mutually different specialized fields. However, since linear-based vector alignment which has been mainly studied in academia basically assumes statistical linearity, it tends to simplify the vector space. This essentially assumes that different types of vector spaces are geometrically similar, which yields a limitation that it causes inevitable distortion in the alignment process. To overcome this limitation, we propose a deep learning-based vector alignment methodology that effectively learns the nonlinearity of data. The proposed methodology consists of sequential learning of a skip-connected autoencoder and a regression model to align the specialized word embedding expressed in each space to the general embedding space. Finally, through the inference of the two trained models, the specialized vocabulary can be aligned in the general space. To verify the performance of the proposed methodology, an experiment was performed on a total of 77,578 documents in the field of 'health care' among national R&D tasks performed from 2011 to 2020. As a result, it was confirmed that the proposed methodology showed superior performance in terms of cosine similarity compared to the existing linear vector alignment.

• 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 Agricultural and Forest Meteorology
• /
• v.23 no.4
• /
• pp.329-339
• /
• 2021

Soybeans (Glycine max), one of major upland crops, require precise management of environmental conditions, such as temperature, water, and soil, during cultivation since they are sensitive to environmental changes. Application of spectral technologies that measure the physiological state of crops remotely has great potential for improving quality and productivity of the soybean by estimating yields, physiological stresses, and diseases. In this study, we developed and validated a soybean growth prediction model using multispectral imagery. We conducted a linear regression analysis between vegetation indices and soybean growth data (fresh weight and LAI) obtained at Miryang fields. The linear regression model was validated at Goesan fields. It was found that the model based on green ratio vegetation index (GRVI) had the greatest performance in prediction of fresh weight at the calibration stage (R²=0.74, RMSE=246 g/m², RE=34.2%). In the validation stage, RMSE and RE of the model were 392 g/m² and 32%, respectively. The errors of the model differed by cropping system, For example, RMSE and RE of model in single crop fields were 315 g/m² and 26%, respectively. On the other hand, the model had greater values of RMSE (381 g/m²) and RE (31%) in double crop fields. As a result of developing models for predicting a fresh weight into two years (2018+2020) with similar accumulated temperature (AT) in three years and a single year (2019) that was different from that AT, the prediction performance of a single year model was better than a two years model. Consequently, compared with those models divided by AT and a three years model, RMSE of a single crop fields were improved by about 29.1%. However, those of double crop fields decreased by about 19.6%. When environmental factors are used along with, spectral data, the reliability of soybean growth prediction can be achieved various environmental conditions.

• Asian-Australasian Journal of Animal Sciences
• /
• v.33 no.10
• /
• pp.1544-1557
• /
• 2020

Objective: Genomic selection (GS) is becoming popular in animals' genetic development. We, therefore, investigated the single-step genomic best linear unbiased prediction (ssGBLUP) as tool for GS, and compared its efficacy with the traditional pedigree BLUP (pedBLUP) method. Methods: A total of 9,952 males born between 1997 and 2018 under Hanwoo proven-bull selection program was studied. We analyzed body weight at 12 months and carcass weight (kg), backfat thickness, eye muscle area, and marbling score traits. About 7,387 bulls were genotyped using Illumina 50K BeadChip Arrays. Multiple-trait animal model analyses were performed using BLUPF90 software programs. Breeding value accuracy was calculated using two methods: i) Pearson's correlation of genomic estimated breeding value (GEBV) with EBV of all animals (r_M1) and ii) correlation using inverse of coefficient matrix from the mixed-model equations (r_M2). Then, we compared these accuracies by overall population, info-type (PHEN, phenotyped-only; GEN, genotyped-only; and PH+GEN, phenotyped and genotyped), and bull-types (YBULL, young male calves; CBULL, young candidate bulls; and PBULL, proven bulls). Results: The r_M1 estimates in the study were between 0.90 and 0.96 among five traits. The r_M1 estimates varied slightly by population and info-type, but noticeably by bull-type for traits. Generally average r_M2 estimates were much smaller than r_M1 (pedBLUP, 0.40 to0.44; ssGBLUP, 0.41 to 0.45) at population level. However, r_M2 from both BLUP models varied noticeably across info-types and bull-types. The ssGBLUP estimates of r_M2 in PHEN, GEN, and PH+ GEN ranged between 0.51 and 0.63, 0.66 and 0.70, and 0.68 and 0.73, respectively. In YBULL, CBULL, and PBULL, the r_M2 estimates ranged between 0.54 and 0.57, 0.55 and 0.62, and 0.70 and 0.74, respectively. The pedBLUP based r_M2 estimates were also relatively lower than ssGBLUP estimates. At the population level, we found an increase in accuracy by 2.0% to 4.5% among traits. Traits in PHEN were least influenced by ssGBLUP (0% to 2.0%), whereas the highest positive changes were in GEN (8.1% to 10.7%). PH+GEN also showed 6.5% to 8.5% increase in accuracy by ssGBLUP. However, the highest improvements were found in bull-types (YBULL, 21% to 35.7%; CBULL, 3.3% to 9.3%; PBULL, 2.8% to 6.1%). Conclusion: A noticeable improvement by ssGBLUP was observed in this study. Findings of differential responses to ssGBLUP by various bulls could assist in better selection decision making as well. We, therefore, suggest that ssGBLUP could be used for GS in Hanwoo proven-bull evaluation program.

• Asian-Australasian Journal of Animal Sciences
• /
• v.28 no.12
• /
• pp.1696-1702
• /
• 2015

The objective of this study was to compare the effects of body weight growth adjustment methods on genetic parameters of body growth and tissue among three pig breeds. Data collected on 101,820 Landrace, 281,411 Yorkshire, and 78,068 Duroc pigs, born in Korean swine breeder farms since 2000, were analyzed. Records included body weights on test day and amplitude (A)-mode ultrasound carcass measures of backfat thickness (BF), eye muscle area (EMA), and retail cut percentage (RCP). Days to 90 kg body weight (DAYS90), through an adjustment of the age based on the body weight at the test day, were obtained. Ultrasound measures were also pre-adjusted (ABF, EMA, AEMA, ARCP) based on their test day measures. The (co)variance components were obtained with 3 multi-trait animal models using the REMLF90 software package. Model I included DAYS90 and ultrasound traits, whereas model II and III accounted DAYS90 and pre-adjusted ultrasound traits. Fixed factors were sex (sex) and contemporary groups (herd-year-month of birth) for all traits among the models. Additionally, model I and II considered a linear covariate of final weight on the ultrasound measure traits. Heritability ($h^2$) estimates for DAYS90, BF, EMA, and RCP ranged from 0.36 to 0.42, 0.34 to 0.43, 0.20 to 0.22, and 0.39 to 0.45, respectively, among the models. The $h^2$ estimates of DAYS90 from model II and III were also somewhat similar. The $h^2$ for ABF, AEMA, and ARCP were 0.35 to 0.44, 0.20 to 0.25, and 0.41 to 0.46, respectively. Our heritability estimates varied mostly among the breeds. The genetic correlations ($r_G$) were moderately negative between DAYS90 and BF (-0.29 to -0.38), and between DAYS90 and EMA (-0.16 to -0.26). BF had strong $r_G$ with RCP (-0.87 to -0.93). Moderately positive $r_G$ existed between DAYS90 and RCP (0.20 to 0.28) and between EMA and RCP (0.35 to 0.44) among the breeds. For DAYS90, model II and III, its correlations with ABF, AEMA, and ARCP were mostly low or negligible except the $r_G$ between DAYS90 and AEMA from model III (0.27 to 0.30). The $r_G$ between AEMA and ABF and between AEMA and ARCP were moderate but with negative and positive signs, respectively; also reflected influence of pre-adjustments. However, the $r_G$ between BF and RCP remained non-influential to trait pre-adjustments or covariable fits. Therefore, we conclude that ultrasound measures taken at a body weight of about 90 kg as the test final should be adjusted for body weight growth. Our adjustment formulas, particularly those for BF and EMA, should be revised further to accommodate the added variation due to different performance testing endpoints with regard to differential growth in body composition.