• Journal of the Korean Society for Marine Environment & Energy
• /
• v.9 no.4
• /
• pp.235-242
• /
• 2006

The precise estimation of total and organic carbon contents in sediments is fundamental to understand the benthic environment. To test the precision and accuracy of CHN analyzer and the procedure to quantify total and organic carbon contents(using in-situ acidification with sulfurous acid($H_2SO_3$)) in the sediment, the reference material s such as Acetanilide($C_8H_9NO$), Sulfanilammide($C_6H_8N_2O_2S$), and BCSS-1(standard estuary sediment) were used. The results indicate that CHN analyzer to quantify carbon and nitrogen content has high precision(percent error=3.29%) and accuracy(relative standard deviation=1.26%). Additionally, we conducted the instrumental comparison of carbon values analyzed using CHN analyzer and Coulometeric Carbon Analyzer. Total carbon contents measured from two different instruments were highly correlated($R^2=0.9993$, n=84, p<0.0001) with a linear relationship and show no significant differences(paired t-test, p=0.0003). The organic carbon contents from two instruments also showed the similar results with a significant linear relationship($R^2=0.8867$, n=84, p<0.0001) and no significant differences(paired t-test, p<0.0001). Although it is possible to overestimate organic carbon contents for some sediment types having high inorganic carbon contents(such as calcareous ooze) due to procedural and analytical errors, analysis of organic carbon contents in sediments using CHN Analyzer and current procedures seems to provide the best estimates. Therefore, we recommend that this method can be applied to measure the carbon content in normal any sediment samples and are considered to be one of the best procedure far routine analysis of total and organic carbon.

• Journal of Biomedical Engineering Research
• /
• v.25 no.1
• /
• pp.11-19
• /
• 2004

Stage 1 sleep provides important information regarding interpretation of nocturnal polysomnography, particularly sleep onset. It is a short transition period from wakeful consciousness to sleep. Lack of prominent sleep events characterizing stage 1 sleep is a major obstacle in automatic sleep stage scoring. In this study, we attempted to utilize simultaneous EEC and EOG processing and analyses to detect stage 1 sleep automatically. Relative powers of the alpha waves and the theta waves were calculated from spectral estimation. Either the relative power of alpha waves less than 50％ or the relative power of theta waves more than 23％ was regarded as stage 1 sleep. SEM (slow eye movement) was defined as the duration of both eye movement ranging from 1.5 to 4 seconds and regarded also as stage 1 sleep. If one of these three criteria was met, the epoch was regarded as stage 1 sleep. Results f ere compared to the manual rating results done by two polysomnography experts. Total of 169 epochs was analyzed. Agreement rate for stage 1 sleep between automatic detection and manual scoring was 79.3％ and Cohen's Kappa was 0.586 (p＜0.01). A significant portion (32％) of automatically detected stage 1 sleep included SEM. Generally, digitally-scored sleep s1aging shows the accuracy up to 70％. Considering potential difficulties in stage 1 sleep scoring, the accuracy of 79.3％ in this study seems to be robust enough. Simultaneous analysis of EOG provides differential value to the present study from previous oneswhich mainly depended on EEG analysis. The issue of close relationship between SEM and stage 1 sleep raised by Kinnariet at. remains to be a valid one in this study.

• Geophysics and Geophysical Exploration
• /
• v.10 no.3
• /
• pp.173-182
• /
• 2007

It is well known that manganese nodules enriched with valuable metals are abundantly distributed in the abyssal plain area in the Clarion-Clipperton (C-C) fracture zone of the northeast Pacific. Previous studies using deep-sea camera (DSC) system reported different observations about the relation of seafloor topographic change and nodule abundance, and they were sometimes contradictory. Moreover, proper foundation on the estimation of DSC underwater position, was not introduced clearly. The variability of the mining condition of manganese nodule according to seafloor topography was examined in the Korea Deep Ocean Study (KODOS) area, located in the C-C zone. In this paper, it is suggested that the utilization of deep towing system such as DSC is very useful approach to whom are interested in analysing the distributional characteristics of manganese nodule filed and in selecting promising minable area. To this purpose, nodule abundance and detailed bathymetry were acquired using deep-sea camera system and multi-beam echo sounder, respectively on the seamount free abyssal hill area of southern part ($132^{\circ}10'W$, $9^{\circ}45'N$) in KODOS regime. Some reasonable assumptions were introduced to enhance the accuracy of estimated DSC sampling position. The accuracy in the result of estimated underwater position was verified indirectly through the comparison of measured abundances on the crossing point of neighboring DSC tracks. From the recorded seafloor images, not only nodules and sediments but cracks and cliffs could be also found frequently. The positions of these probable unminable area were calculated by use of the recorded time being encountered with them from the seafloor images of DSC. The results suggest that the unminable areas are mostly distributed on the slope sides and hill tops, where nodule collector can not travel over.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.19 no.1
• /
• pp.19-26
• /
• 2017

Surface air temperature ($T_{air}$) is a key variable for the meteorology and climatology, and is a fundamental factor of the terrestrial ecosystem functions. Satellite remote sensing from the Moderate Resolution Imaging Spectroradiometer (MODIS) provides an opportunity to monitor the $T_{air}$. However, the several problems such as frequent cloud cover and mountainous region can result in substantial retrieval error and signal loss in MODIS $T_{air}$. In this study, satellite-based $T_{air}$ was estimated under both clear and cloudy sky conditions in Gangwon Province using Aqua MODIS07 temperature profile product (MYD07_L2) and GCOM-W1 Advanced Microwave Scanning Radiometer 2 (AMSR2) brightness temperature ($T_b$) at 37 GHz frequency, and was compared with the measurements from the Automated Mountain Meteorology Stations (AMOS). The application of ambient temperature lapse rate was performed to improve the retrieval accuracy in mountainous region, which showed the improvement of estimation accuracy approximately 4% of RMSE. A simple pixel-wise regression method combining synergetic information from MYD07_L2 $T_{air}$ and AMSR2 $T_b$ was applied to estimate surface $T_{air}$ for all sky conditions. The $T_{air}$ retrievals showed favorable agreement in comparison with AMOS data (r=0.80, RMSE=7.9K), though the underestimation was appeared in winter season. Substantial $T_{air}$ retrievals were estimated 61.4% (n=2,657) for cloudy sky conditions. The results presented in this study indicate that the satellite remote sensing can produce the surface $T_{air}$ at the complex mountainous region for all sky conditions.

• Journal of Intelligence and Information Systems
• /
• v.23 no.3
• /
• pp.119-138
• /
• 2017

Recently, SNS has become an important channel for marketing as well as personal communication. However, cybercrime has also evolved with the development of information and communication technology, and illegal advertising is distributed to SNS in large quantity. As a result, personal information is lost and even monetary damages occur more frequently. In this study, we propose a method to analyze which sentences and documents, which have been sent to the SNS, are related to financial fraud. First of all, as a conceptual framework, we developed a matrix of conceptual characteristics of cybercriminality on SNS and emergency management. We also suggested emergency management process which consists of Pre-Cybercriminality (e.g. risk identification) and Post-Cybercriminality steps. Among those we focused on risk identification in this paper. The main process consists of data collection, preprocessing and analysis. First, we selected two words 'daechul(loan)' and 'sachae(private loan)' as seed words and collected data with this word from SNS such as twitter. The collected data are given to the two researchers to decide whether they are related to the cybercriminality, particularly financial fraud, or not. Then we selected some of them as keywords if the vocabularies are related to the nominals and symbols. With the selected keywords, we searched and collected data from web materials such as twitter, news, blog, and more than 820,000 articles collected. The collected articles were refined through preprocessing and made into learning data. The preprocessing process is divided into performing morphological analysis step, removing stop words step, and selecting valid part-of-speech step. In the morphological analysis step, a complex sentence is transformed into some morpheme units to enable mechanical analysis. In the removing stop words step, non-lexical elements such as numbers, punctuation marks, and double spaces are removed from the text. In the step of selecting valid part-of-speech, only two kinds of nouns and symbols are considered. Since nouns could refer to things, the intent of message is expressed better than the other part-of-speech. Moreover, the more illegal the text is, the more frequently symbols are used. The selected data is given 'legal' or 'illegal'. To make the selected data as learning data through the preprocessing process, it is necessary to classify whether each data is legitimate or not. The processed data is then converted into Corpus type and Document-Term Matrix. Finally, the two types of 'legal' and 'illegal' files were mixed and randomly divided into learning data set and test data set. In this study, we set the learning data as 70% and the test data as 30%. SVM was used as the discrimination algorithm. Since SVM requires gamma and cost values as the main parameters, we set gamma as 0.5 and cost as 10, based on the optimal value function. The cost is set higher than general cases. To show the feasibility of the idea proposed in this paper, we compared the proposed method with MLE (Maximum Likelihood Estimation), Term Frequency, and Collective Intelligence method. Overall accuracy and was used as the metric. As a result, the overall accuracy of the proposed method was 92.41% of illegal loan advertisement and 77.75% of illegal visit sales, which is apparently superior to that of the Term Frequency, MLE, etc. Hence, the result suggests that the proposed method is valid and usable practically. In this paper, we propose a framework for crisis management caused by abnormalities of unstructured data sources such as SNS. We hope this study will contribute to the academia by identifying what to consider when applying the SVM-like discrimination algorithm to text analysis. Moreover, the study will also contribute to the practitioners in the field of brand management and opinion mining.

• Journal of Intelligence and Information Systems
• /
• v.16 no.3
• /
• pp.99-120
• /
• 2010

Due to the wide spread of customers' frequent access of non face-to-face services, there have been many attempts to improve customer satisfaction using huge amounts of data accumulated throughnon face-to-face channels. Usually, a call center is regarded to be one of the most representative non-faced channels. Therefore, it is important that a call center has enough agents to offer high level customer satisfaction. However, managing too many agents would increase the operational costs of a call center by increasing labor costs. Therefore, predicting and calculating the appropriate size of human resources of a call center is one of the most critical success factors of call center management. For this reason, most call centers are currently establishing a department of WFM(Work Force Management) to estimate the appropriate number of agents and to direct much effort to predict the volume of inbound calls. In real world applications, inbound call prediction is usually performed based on the intuition and experience of a domain expert. In other words, a domain expert usually predicts the volume of calls by calculating the average call of some periods and adjusting the average according tohis/her subjective estimation. However, this kind of approach has radical limitations in that the result of prediction might be strongly affected by the expert's personal experience and competence. It is often the case that a domain expert may predict inbound calls quite differently from anotherif the two experts have mutually different opinions on selecting influential variables and priorities among the variables. Moreover, it is almost impossible to logically clarify the process of expert's subjective prediction. Currently, to overcome the limitations of subjective call prediction, most call centers are adopting a WFMS(Workforce Management System) package in which expert's best practices are systemized. With WFMS, a user can predict the volume of calls by calculating the average call of each day of the week, excluding some eventful days. However, WFMS costs too much capital during the early stage of system establishment. Moreover, it is hard to reflect new information ontothe system when some factors affecting the amount of calls have been changed. In this paper, we attempt to devise a new model for predicting inbound calls that is not only based on theoretical background but also easily applicable to real world applications. Our model was mainly developed by the interactive decision tree technique, one of the most popular techniques in data mining. Therefore, we expect that our model can predict inbound calls automatically based on historical data, and it can utilize expert's domain knowledge during the process of tree construction. To analyze the accuracy of our model, we performed intensive experiments on a real case of one of the largest car insurance companies in Korea. In the case study, the prediction accuracy of the devised two models and traditional WFMS are analyzed with respect to the various error rates allowable. The experiments reveal that our data mining-based two models outperform WFMS in terms of predicting the amount of accident calls and fault calls in most experimental situations examined.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_3
• /
• pp.1457-1468
• /
• 2018

The sigma naught (${\sigma}^0$) equation is essential to calculate geo-physical properties from Synthetic Aperture Radar (SAR) images for the applications such as ground target identification,surface classification, sea wind speed calculation, and soil moisture estimation. In this paper, we are suggesting new Kompsat-5 (K5) Radar Cross Section (RCS) and ${\sigma}^0$ equations reflecting the final SAR processor update and absolute radiometric calibration in order to increase the application of K5 SAR images. Firstly, we analyzed the accuracy of the K5 RCS equation by using trihedral corner reflectors installed in the Kompsat calibration site in Mongolia. The average difference between the calculated values using RCS equation and the measured values with K5 SAR processor was about $0.2dBm^2$ for Spotlight and Stripmap imaging modes. In addition, the verification of the K5 ${\sigma}^0$ equation was carried out using the TerraSAR-X (TSX) and Sentinel-1A (S-1A) SAR images over Amazon rainforest, where the backscattering characteristics are not significantly affected by the seasonal change. The calculated ${\sigma}^0$ difference between K5 and TSX/S-1A was less than 0.6 dB. Considering the K5 absolute radiometric accuracy requirement, which is 2.0 dB ($1{\sigma}$), the average difference of $0.2dBm^2$ for RCS equation and the maximum difference of 0.6 dB for ${\sigma}^0$ equation show that the accuracies of the suggested equations are relatively high. In the future, the validity of the suggested RCS and ${\sigma}^0$ equations is expected to be verified through the application such as sea wind speed calculation, where quantitative analysis is possible.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.25 no.4
• /
• pp.337-345
• /
• 2023

Estimating the rice heading date is one of the most crucial agricultural tasks related to productivity. However, due to abnormal climates around the world, it is becoming increasingly challenging to estimate the rice heading date. Therefore, a more objective classification method for estimating the rice heading date is needed than the existing methods. This study, we aimed to classify the rice heading stage from various images using a CNN classification model. We collected top-view images taken from a drone and a phenotyping tower, as well as slanted-view images captured with a RGB camera. The collected images underwent preprocessing to prepare them as input data for the CNN model. The CNN architectures employed were ResNet50, InceptionV3, and VGG19, which are commonly used in image classification models. The accuracy of the models all showed an accuracy of 0.98 or higher regardless of each architecture and type of image. We also used Grad-CAM to visually check which features of the image the model looked at and classified. Then verified our model accurately measure the rice heading date in paddy fields. The rice heading date was estimated to be approximately one day apart on average in the four paddy fields. This method suggests that the water head can be estimated automatically and quantitatively when estimating the rice heading date from various paddy field monitoring images.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.14 no.4
• /
• pp.195-204
• /
• 2009

In order to estimate sea surface current fields in the East Sea, we examined characteristics of mean dynamic topography (MDT) fields (or mean surface current field, MSC) generated from three different methods. This preliminary investigation evaluates the accuracy of surface currents estimated from satellite-derived sea level anomaly (SLA) data and three MDT fields in the East Sea. AVISO (Archiving, Validation and Interpretation of Satellite Oceanographic data) provides a MDT field derived from satellite observation and numerical models with $0.25^{\circ}$ horizontal resolution. Steric height field relative to 500 dbar from temperature and salinity profiles in the East Sea supplies another MDT field. Trajectory data of surface drifters (ARGOS) in the East Sea for 14 years provide another MSC field. Absolute dynamic topography (ADT) field is calculated by adding SLA to each MDT. Application of geostrophic equation to three different ADT fields yields three surface geostrophic current fields. Comparisons were made between the estimated surface currents from the three different methods and in-situ current measurements from a ship-mounted ADCP (Acoustic Doppler Current Profiler) in the southwestern East Sea in 2005. For offshore areas more than 50 km away from the land, the correlation coefficients (R) between the estimated versus the measured currents range from 0.58 to 0.73, with 17.1 to $21.7\;cm\;s^{-1}$ root mean square deviation (RMSD). For coastal ocean within 50 km from the land, however, R ranges from 0.06 to 0.46 and RMSD ranges from 15.5 to $28.0\;cm\;s^{-1}$. Results from this study reveal that a new approach in producing MDT and SLA is required to improve the accuracy of surface current estimations for the shallow costal zones of the East Sea.

• 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.