• Korean Journal of Soil Science and Fertilizer
• /
• v.10 no.3
• /
• pp.189-201
• /
• 1977

Some of basic aspects of soil potassium with special reference to soil physical properties were discussed. Data in the Official Soil Series Description(Korea) was analyzed according to soil type, land form, and soil texture to find soil potassium status which may explain different response to potassium application. Exchangeable potassium contents decreased with soil depth irrespective of soil type, land form and soil texture. Change in degree of potassium saturation within soil profile was not so clear as exchangeable potassium but the degree of potassium saturation of A horizon was highest among soil horizon. Soils of terrace and mountain foot slope showed high values both in exchangeable potassium and degree of potassium sauration and only these two soils were classified as soils having exchangeable potassium higher than 0.3 meq per 100g of soil and degree of potassium saturation higher than 5.0%. Exchangeable potassium of fine loamy and fine clayey soils is higher than 0.3 meq per 100g of soil but degree of potassium saturation is lower than 4.0%. Degree of potassium saturation of sandy soils exceeds 5.0% but exchangeable potassium is very low. Soils of rolling, hilly, unmatured and alpine land soils have lower exchangeable potassium and show lower degree of potassium saturation. The highest distribution of exchangeable potassium content irrespective of soil horizons was shown in the range of 0.1-0.2 meq per 100g of soil. The highest distribution of degree of potassium saturation was in the range of 2.0-3.0% in A horizon and 1.0-2.0% in B and C horizons. Of the soil series concerned in this analysis, 27.3% in A horizon, 11.1% in B horizon and 4.0% in C horizon had exchangeable potassium higher than 0.3 meq per 100g of soil and 18.0% in A horizon, 6.3% in B horizon, and 4.1% in C horizon showed degree of potassium saturation higher than 5.0%. The low response of potassium application only to soils in terrace and mountain foot slope may be resulted from the high exchangeable potassium content and high degree of potassium saturation. It is concluded that a great response of potassium application to soils is expected especially in dry season.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.93-112
• /
• 2015

Depending on the change in consumer's consumption pattern, existing retail shop has evolved in hypermarket or convenience store offering grocery and daily products mostly. Therefore, it is important to maintain the inventory levels and proper product configuration for effectively utilize the limited space in the retail store and increasing sales. Accordingly, this study proposed proper product configuration and inventory level strategy based on RFM(Recency, Frequency, Monetary) model and SOM(self-organizing map) for manage the retail shop effectively. RFM model is analytic model to analyze customer behaviors based on the past customer's buying activities. And it can differentiates important customers from large data by three variables. R represents recency, which refers to the last purchase of commodities. The latest consuming customer has bigger R. F represents frequency, which refers to the number of transactions in a particular period and M represents monetary, which refers to consumption money amount in a particular period. Thus, RFM method has been known to be a very effective model for customer segmentation. In this study, using a normalized value of the RFM variables, SOM cluster analysis was performed. SOM is regarded as one of the most distinguished artificial neural network models in the unsupervised learning tool space. It is a popular tool for clustering and visualization of high dimensional data in such a way that similar items are grouped spatially close to one another. In particular, it has been successfully applied in various technical fields for finding patterns. In our research, the procedure tries to find sales patterns by analyzing product sales records with Recency, Frequency and Monetary values. And to suggest a business strategy, we conduct the decision tree based on SOM results. To validate the proposed procedure in this study, we adopted the M-mart data collected between 2014.01.01~2014.12.31. Each product get the value of R, F, M, and they are clustered by 9 using SOM. And we also performed three tests using the weekday data, weekend data, whole data in order to analyze the sales pattern change. In order to propose the strategy of each cluster, we examine the criteria of product clustering. The clusters through the SOM can be explained by the characteristics of these clusters of decision trees. As a result, we can suggest the inventory management strategy of each 9 clusters through the suggested procedures of the study. The highest of all three value(R, F, M) cluster's products need to have high level of the inventory as well as to be disposed in a place where it can be increasing customer's path. In contrast, the lowest of all three value(R, F, M) cluster's products need to have low level of inventory as well as to be disposed in a place where visibility is low. The highest R value cluster's products is usually new releases products, and need to be placed on the front of the store. And, manager should decrease inventory levels gradually in the highest F value cluster's products purchased in the past. Because, we assume that cluster has lower R value and the M value than the average value of good. And it can be deduced that product are sold poorly in recent days and total sales also will be lower than the frequency. The procedure presented in this study is expected to contribute to raising the profitability of the retail store. The paper is organized as follows. The second chapter briefly reviews the literature related to this study. The third chapter suggests procedures for research proposals, and the fourth chapter applied suggested procedure using the actual product sales data. Finally, the fifth chapter described the conclusion of the study and further research.

• Radiation Oncology Journal
• /
• v.23 no.3
• /
• pp.186-193
• /
• 2005

Purpose: To improve the management of a medical linear accelerator, the records of operational failures of a Varian CL2l00C over a ten year period were retrospectively analyzed. Materials and Methods: The failures were classified according to the involved functional subunits, with each class rated Into one of three levels depending on the operational conditions. The relationships between the failure rate and working ratio and between the failure rate and outside temperature were investigated. In addition, the average life time of the main part and the operating efficiency over the last 4 years were analyzed. Results: Among the recorded failures (total 587 failures), the most frequent failure was observed in the parts related with the collimation system, including the monitor chamber, which accounted for $20\%$ of all failures. With regard to the operational conditions, 2nd level of failures, which temporally interrupted treatments, were the most frequent. Third level of failures, which interrupted treatment for more than several hours, were mostly caused by the accelerating subunit. The number of failures was increased with number of treatments and operating time. The average life-times of the Klystron and Thyratron became shorter as the working ratio increased, and were 42 and $83\%$ of the expected values, respectively. The operating efficiency was maintained at $95\%$ or higher, but this value slightly decreased. There was no significant correlation between the number of failures and the outside temperature. Conclusion: The maintenance of detailed equipment problems and failures records over a long period of time can provide good knowledge of equipment function as well as the capability of predicting future failure. Wore rigorous equipment maintenance Is required for old medical linear accelerators for the advanced avoidance of serious failure and to improve the qualify of patient treatment.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.221-241
• /
• 2018

Deep learning is getting attention recently. The deep learning technique which had been applied in competitions of the International Conference on Image Recognition Technology(ILSVR) and AlphaGo is Convolution Neural Network(CNN). CNN is characterized in that the input image is divided into small sections to recognize the partial features and combine them to recognize as a whole. Deep learning technologies are expected to bring a lot of changes in our lives, but until now, its applications have been limited to image recognition and natural language processing. The use of deep learning techniques for business problems is still an early research stage. If their performance is proved, they can be applied to traditional business problems such as future marketing response prediction, fraud transaction detection, bankruptcy prediction, and so on. So, it is a very meaningful experiment to diagnose the possibility of solving business problems using deep learning technologies based on the case of online shopping companies which have big data, are relatively easy to identify customer behavior and has high utilization values. Especially, in online shopping companies, the competition environment is rapidly changing and becoming more intense. Therefore, analysis of customer behavior for maximizing profit is becoming more and more important for online shopping companies. In this study, we propose 'CNN model of Heterogeneous Information Integration' using CNN as a way to improve the predictive power of customer behavior in online shopping enterprises. In order to propose a model that optimizes the performance, which is a model that learns from the convolution neural network of the multi-layer perceptron structure by combining structured and unstructured information, this model uses 'heterogeneous information integration', 'unstructured information vector conversion', 'multi-layer perceptron design', and evaluate the performance of each architecture, and confirm the proposed model based on the results. In addition, the target variables for predicting customer behavior are defined as six binary classification problems: re-purchaser, churn, frequent shopper, frequent refund shopper, high amount shopper, high discount shopper. In order to verify the usefulness of the proposed model, we conducted experiments using actual data of domestic specific online shopping company. This experiment uses actual transactions, customers, and VOC data of specific online shopping company in Korea. Data extraction criteria are defined for 47,947 customers who registered at least one VOC in January 2011 (1 month). The customer profiles of these customers, as well as a total of 19 months of trading data from September 2010 to March 2012, and VOCs posted for a month are used. The experiment of this study is divided into two stages. In the first step, we evaluate three architectures that affect the performance of the proposed model and select optimal parameters. We evaluate the performance with the proposed model. Experimental results show that the proposed model, which combines both structured and unstructured information, is superior compared to NBC(Naïve Bayes classification), SVM(Support vector machine), and ANN(Artificial neural network). Therefore, it is significant that the use of unstructured information contributes to predict customer behavior, and that CNN can be applied to solve business problems as well as image recognition and natural language processing problems. It can be confirmed through experiments that CNN is more effective in understanding and interpreting the meaning of context in text VOC data. And it is significant that the empirical research based on the actual data of the e-commerce company can extract very meaningful information from the VOC data written in the text format directly by the customer in the prediction of the customer behavior. Finally, through various experiments, it is possible to say that the proposed model provides useful information for the future research related to the parameter selection and its performance.

• Journal of Food Hygiene and Safety
• /
• v.13 no.2
• /
• pp.112-120
• /
• 1998

This study was performed to investigate the synergistic effect of chitosan and sorbic acid as a new food preservative. So it was performed to investigate inhibitory effect on growh of E. coli 0157:H7, gram negative pathogenic food borne disease bacteria and of S. aureus, gram positive food borne disease bacteria in chitosan, sorbic acid and combination of chitosan and sorbic acid. Minimun Inhibitory Concentration (MIC) of chitosan in E. coli 0157:H7 was 500 ppm at pH 5.0, 250 ppm at pH 5.5, 500 ppm at pH 6.0, and 2000 ppm at pH 6.5, while in Staph. aureus 31.25 ppm at pH 5.0 and 62. 5 ppm at more than pH 5.5. also, MIC of sorbic acid in E. coli 0157:H7 was 500 ppm at pH 5.0, 1500 ppm at pH 5.5, and 2000 ppm at more than pH 6.0, while in Staph. aureus 1500 ppm at pH 5.0 and more than 2000 ppm at more than pH 5.5. Due to the effect of pH in E. coli 0157:H7, MIC of combined chitosan and sorbic acid was 500 ppm of chitosan with 500 ppm of sorbic acid at pH 6.5, but 250 ppm of chitosan with 31.3 ppm of sorbic acid at pH 5.0. In Staph. aureus, there was great effect of chitosan, but neither effect of pH nor sorbic acid. When E. coli 0157:H7 were treated with 500 ppm of chitosan with 500 ppm of sorbic acid and 250 ppm of chitosan with 250 ppm of sorbic acid at pH 6.5, they were inhibited. But, they were increased at the initial concentration of bacteria at 1000 ppm of chitosan in 18 hours, at 500 ppm of chitosan in 36 hours. There was no effect of growth inhibition with sorbic acid but great effect with chitosan on Staph. aureus. The correl~tions between MICs of chitosan and sorbic acid in E. coli 0157:H7 accoding to pH were higher than those in Staph. aureus. R values in E. coli 0157:H7 were 0.95 (p<0.01), 0.99 (p<0.01), 0.97 (p<0.01), and 0.99 (p<0.01) at pH 6.5, 6.0, 5.5, and 5.0 respectively. The synergistic effect of chitosan and sorbic acid in E. coli 0157:H7 could be confirmed from the result of this experiment. Therefore, it was expected that the food preservation would increase or maintain by using sorble acid together with chitosan, natural food additive that did no harm to human body.

• 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 Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.73-92
• /
• 2014

An Adaptive Clustering-based Collaborative Filtering Technique was proposed to solve the fundamental problems of collaborative filtering, such as cold-start problems, scalability problems and data sparsity problems. Previous collaborative filtering techniques were carried out according to the recommendations based on the predicted preference of the user to a particular item using a similar item subset and a similar user subset composed based on the preference of users to items. For this reason, if the density of the user preference matrix is low, the reliability of the recommendation system will decrease rapidly. Therefore, the difficulty of creating a similar item subset and similar user subset will be increased. In addition, as the scale of service increases, the time needed to create a similar item subset and similar user subset increases geometrically, and the response time of the recommendation system is then increased. To solve these problems, this paper suggests a collaborative filtering technique that adapts a condition actively to the model and adopts the concepts of a context-based filtering technique. This technique consists of four major methodologies. First, items are made, the users are clustered according their feature vectors, and an inter-cluster preference between each item cluster and user cluster is then assumed. According to this method, the run-time for creating a similar item subset or user subset can be economized, the reliability of a recommendation system can be made higher than that using only the user preference information for creating a similar item subset or similar user subset, and the cold start problem can be partially solved. Second, recommendations are made using the prior composed item and user clusters and inter-cluster preference between each item cluster and user cluster. In this phase, a list of items is made for users by examining the item clusters in the order of the size of the inter-cluster preference of the user cluster, in which the user belongs, and selecting and ranking the items according to the predicted or recorded user preference information. Using this method, the creation of a recommendation model phase bears the highest load of the recommendation system, and it minimizes the load of the recommendation system in run-time. Therefore, the scalability problem and large scale recommendation system can be performed with collaborative filtering, which is highly reliable. Third, the missing user preference information is predicted using the item and user clusters. Using this method, the problem caused by the low density of the user preference matrix can be mitigated. Existing studies on this used an item-based prediction or user-based prediction. In this paper, Hao Ji's idea, which uses both an item-based prediction and user-based prediction, was improved. The reliability of the recommendation service can be improved by combining the predictive values of both techniques by applying the condition of the recommendation model. By predicting the user preference based on the item or user clusters, the time required to predict the user preference can be reduced, and missing user preference in run-time can be predicted. Fourth, the item and user feature vector can be made to learn the following input of the user feedback. This phase applied normalized user feedback to the item and user feature vector. This method can mitigate the problems caused by the use of the concepts of context-based filtering, such as the item and user feature vector based on the user profile and item properties. The problems with using the item and user feature vector are due to the limitation of quantifying the qualitative features of the items and users. Therefore, the elements of the user and item feature vectors are made to match one to one, and if user feedback to a particular item is obtained, it will be applied to the feature vector using the opposite one. Verification of this method was accomplished by comparing the performance with existing hybrid filtering techniques. Two methods were used for verification: MAE(Mean Absolute Error) and response time. Using MAE, this technique was confirmed to improve the reliability of the recommendation system. Using the response time, this technique was found to be suitable for a large scaled recommendation system. This paper suggested an Adaptive Clustering-based Collaborative Filtering Technique with high reliability and low time complexity, but it had some limitations. This technique focused on reducing the time complexity. Hence, an improvement in reliability was not expected. The next topic will be to improve this technique by rule-based filtering.

• Tuberculosis and Respiratory Diseases
• /
• v.49 no.6
• /
• pp.752-759
• /
• 2000

Background : Many studies have shown that pulmonary function differs widely among race, age and geographical residency. By virtue of the improvement of nutrition and environment, the elderly population in Korea is markedly increasing and so are the ages of patients complaining respiratory symptoms. However, we do not have our own data on the pulmonary functional reserve of elderly persons in Korea. We evaluate the deterioration of pulmonary functional reserve and standardize the predictive values of pulmonary function in the elderly population. Method : Pulmonary function tests were conducted in 100 men and 100 women over the age of 65. We analyzed changes of FVC and $FEV_1$ according to age and height by linear regression. We compared our new multiple linear regression equation with other equations currently used in Korea. Results : In men, the mean age was $71.5{\pm}5.2$(mean${\pm}$SD) years and the mean height was $163.6{\pm}6.2$cm. The mean FVC was $3.42{\pm}0.49{\ell}$ and the mean $FEV_1, $2.72{\pm}v$. In women, the mean age was $72.0{\pm}5.1$ years and the mean height was $149.1{\pm}5.9$cm. The mean FVC was $2.22{\pm}0.42{\ell}$ and the mean $FEV_1$ $1.83{\pm}0.34{\ell}$. Multiple linear regression equation using age and height as an independent factors was as follows : FVC(${\ell}$)=1.857-0.0356$\times$age(year)+0.02517$\times$height(cm) (p<0.01, $R^2$=0.279), $FEV_1(${\ell}$)=1.340-0.02698$\times$age(year)+0.02021$\times$height(cm) (p<0.01, $R^2$=0.255) in men, FVC(${\ell}$) =-0.09765-0.03332$\times$age(year)+0.03164$\times$height(cm) (p<0.01, $R^2$=0.435), $FEV_1(${\ell}$)=-0.l69-0.02469$\times$age(year)+0.02539$\times$height(cm) (p<0.01, $R^2$=0.41) in women. Conclusion : We established prediction regressions for pulmonary functional tests in the elderly Korean population. We also confirmed that currently adopted equations do not exactly anticipate the expected pulmonary functional reserve in the aged person over 65 years old. We suggest that our new equations from this study should be applied to interpret the pulmonary function tests in the elderly population in Korea.

• The Journal of Korean Society for Radiation Therapy
• /
• v.30 no.1_2
• /
• pp.191-199
• /
• 2018

Purpose : In this study, we evaluated the usefulness of colloid gel(slime) as a compensator for irregular patient surfaces in radiation therapy. Materials and Methods : For this study, colloid gel suitable for treatment was made and four experiments were conducted to evaluate the applicability of radiation therapy. Trilogy(Varian) and CT(SOMATOM, Siemens) were used as treatment equipment and CT equipment. First, the homogeneity according to the composition of colloid gel was measured using EBT3 Film(RIT). Second, the Hounsfield Unit(HU) value of colloid gel was measured and confirmed by CRIS phantom, Eclipse RTP(Eclipse 13.1, Varian) and CT. Third, to measure the deformation and degeneration of colloid gel during the treatment period, it was measured 3 times daily for 2 weeks using an ion chamber(PTW-30013, PTW). The fourth experiment was compared the treatment plan and measured dose distributions using bolus, rice, colloid gel and additional, dose profiles in an environment similar to actual treatment using our own acrylic phantom. Result : First experiment, density of the colloid gel cases 1, 2 and 3 was $1.02g/cm^3$, $0.99g/cm^3$ and $0.96g/cm^3$. When the homogeneity was measured at 6 MV and 9 MeV, case 1 was more homogeneous than the other cases, as 1.55 and 1.98. In the second experiment, the HU values of case 1, 2, 3 were 15 and when the treatment plan was compared with the measured doses, the difference was within 1 % at all 9, 12 MeV and a difference of -1.53 % and -1.56 % within the whole 2 % at 6 MV. In the third experiment, the dose change of colloid gel was measured to be about 1 % for 2 weeks. In the fourth experiment, the dose difference between the treatment plan and EBT3 film was similar for both colloid gel and bolus, rice at 6 MV. But colloid gel showed less dose difference than bolus and rice at 9 MeV. Also, dose profile of colloid gel showed a more uniform dose distribution than the bolus and rice. Conclusion : In this study, the density of colloid gel prepared for radiation therapy was $1.02g/cm^3$ similar to the density of water, and alteration or deformation was not observed during the radiotherapy process. Although we pay attention to the density when manufacturing colloid gel, it is sufficient in that it can deliver the dose uniformly through the compensation of the patient's body surface more than the bolus and rice, and can be manufactured at low cost. Further studies and studies for clinical applications are expected to be applicable to radiation therapy.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.