• Composites Research
• /
• v.35 no.4
• /
• pp.248-254
• /
• 2022

In this study, TiB₂-steel composite with high-fractional TiB₂ reinforcement was fabricated by gas pressure infiltration process and the microstructure analysis and compressive strength and hardness were evaluated. To elucidate the correlation between microstructure and mechanical properties for fabricated composite, after the compression test of TiB₂-steel composite, the fracture surface was analyzed and the fracture behavior on compression test was predicted. As a result of the compression fracture surface analysis, interfacial failure trace between the steel matrix and the reinforcement was observed, and the interface between the steel matrix and the reinforcement was analyzed using TEM. From the result of microstructure analysis on the fabricated composite, it was confirmed that, in addition to TiB₂ reinforcement and steel matrix, TiC phase and coarse (Fe,M)₂B (M=Cr,Mn) phase were formed. Throughout the thermodynamic calculation, it was confirmed that TiC and (Fe,M)₂B can be formed as a stable phase under the process condition. The fabricated TiB₂-steel composite had a significantly increased hardness, and the compressive strength and Young's modulus were improved by 3.07 times and 1.95 times, respectively, compared to steel matrix. It seems that the coarse (Fe,M)₂B (M=Cr,Mn) phase formed throughout the composite causes the deterioration of mechanical properties, and by controlling the formation of the (Fe,M)₂B (M=Cr,Mn) phase, it is judged that the mechanical properties of the TiB₂-steel composite can be further improved.

• Journal of Korea Water Resources Association
• /
• v.56 no.4
• /
• pp.235-243
• /
• 2023

Due to the revision of the River Act and the enactment of the Act on the Investigation, Planning, and Management of Water Resources, a regular bed change survey has become mandatory and a system is being prepared such that local governments can manage water resources in a planned manner. Since the topography of a bed cannot be measured directly, it is indirectly measured via contact-type depth measurements such as level survey or using an echo sounder, which features a low spatial resolution and does not allow continuous surveying owing to constraints in data acquisition. Therefore, a depth measurement method using remote sensing-LiDAR or hyperspectral imaging-has recently been developed, which allows a wider area survey than the contact-type method as it acquires hyperspectral images from a lightweight hyperspectral sensor mounted on a frequently operating drone and by applying the optimal bandwidth ratio search algorithm to estimate the depth. In the existing hyperspectral remote sensing technique, specific physical quantities are analyzed after matching the hyperspectral image acquired by the drone's path to the image of a surface unit. Previous studies focus primarily on the application of this technology to measure the bathymetry of sandy rivers, whereas bed materials are rarely evaluated. In this study, the existing hyperspectral image-based water depth estimation technique is applied to rivers with vegetation, whereas spatio-temporal hyperspectral imaging and cross-sectional hyperspectral imaging are performed for two cases in the same area before and after vegetation is removed. The result shows that the water depth estimation in the absence of vegetation is more accurate, and in the presence of vegetation, the water depth is estimated by recognizing the height of vegetation as the bottom. In addition, highly accurate water depth estimation is achieved not only in conventional cross-sectional hyperspectral imaging, but also in spatio-temporal hyperspectral imaging. As such, the possibility of monitoring bed fluctuations (water depth fluctuation) using spatio-temporal hyperspectral imaging is confirmed.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.7
• /
• pp.902-909
• /
• 2023

This study evaluated the performance test of a small-sized LTE-Maritime(LTE-M) transceiver that was developed and promoted to expand the use of intelligent maritime traf ic information services led by the Ministry of Oceans and Fisheries with the aim of supporting the prevention of maritime accidents. Accoriding to statistics, approximately 30% of all marine accidents in Korean water occur with ships weighing less than 3 tons. Therefore, the blind spots of maritime safety must be supplemented through the development of small-sized transceivers. The small transceiver may be used in fishing boats that are active near coastal waters and in water leisure equipment near the coastline. Therefore, verifying whether sufficient performance and stable communication quality are provided is necessary, considering the environment of their real usage. In this study, we reviewed the communication quality goals of the LTE-M network and the performance requirements of small-sized transceivers suggested by the Ministry of Oceans and Fisheries, and proposed a test plan to appropriately evaluate the performance of small-sized transceivers. The validity of the proposed test method was verified for six real-sea areas with a high frequency of marine accidents. Consequently, the downlink and uplink transmission speeds of the small-sized LTE-M transceiver showed performances of 9 Mbps or more and 3 Mbps or more, respectively. In addition, using the coverage analysis system, coverage of more than 95% and 100% were confirmed in the intensive management zone (0-30 km) and interesting zone (30-50 km), respectively. The performance evaluation method and test results proposed in this paper are expected to be used as reference materials for verifying the performance of transceivers, contributing to the spread of government-promoted e-navigation services and small-sized transceivers.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_4
• /
• pp.1135-1144
• /
• 2023

Many agricultural reservoirs in South Korea, constructed before 1970, have become aging facilities. The majority of small-scale reservoirs lack measurement systems to ascertain basic specifications and water levels, classifying them as unmeasured reservoirs. Furthermore, continuous sedimentation within the reservoirs and industrial development-induced water quality deterioration lead to reduced water supply capacity and changes in reservoir morphology. This study utilized Light Detection And Ranging (LiDAR) sensors, which provide elevation information and allow for the characterization of surface features, to construct high-resolution Digital Surface Model (DSM) and Digital Elevation Model (DEM) data of reservoir facilities. Additionally, bathymetric measurements based on multibeam echosounders were conducted to propose an updated approach for determining reservoir capacity. Drone-based LiDAR was employed to generate DSM and DEM data with a spatial resolution of 50 cm, enabling the display of elevations of hydraulic structures, such as embankments, spillways, and intake channels. Furthermore, using drone-based hyperspectral imagery, Normalized Difference Vegetation Index (NDVI) and Normalized Difference Water Index (NDWI) were calculated to detect water bodies and verify differences from existing reservoir boundaries. The constructed high-resolution DEM data were integrated with bathymetric measurements to create underwater contour maps, which were used to generate a Triangulated Irregular Network (TIN). The TIN was utilized to calculate the inundation area and volume of the reservoir, yielding results highly consistent with basic specifications. Considering areas that were not surveyed due to underwater vegetation, it is anticipated that this data will be valuable for future updates of reservoir capacity information.

• Journal of the Korea Organic Resources Recycling Association
• /
• v.31 no.4
• /
• pp.29-39
• /
• 2023

In this study, an analysis of medical waste generation characteristics was conducted, differentiating between ordinary situation and the outbreaks of massive infectious diseases. During ordinary situation, prediction models for medical waste quantities by type, general medical waste(G-MW), hazardous medical waste(H-MW), infectious medical waste(I-MW), were established through regression analysis, with all significance values (p) being <0.0001, indicating statistical significance. The determination coefficient(R2) values for prediction models of each category were analyzed as follows : I-MW(R2=0.9943) > G-MW(R2=0.9817) > H-MW(R2=0.9310). Additionally, factors such as GDP(G-MW), the number of medical institutions (H-MW), and the elderly population ratio(I-MW), utilized as influencing factors and consistent with previous literature, showed high correlations. The total MW generation, evaluated by combining each model, had an MAE of 2,615 and RMSE of 3,353. This indicated accuracy levels similar to the medical waste models of H-MW(2,491, 2,890) and I-MW(2,291, 3,267). Due to limitations in accurately estimating the quantity of medical waste during the rapid and outbreaks of massive infectious diseases, the generation unit of I-MW was derived to analyze its characteristics. During the early unstable stage of infectious disease outbreaks, the generation unit was 8.74 kg/capita·day, 2.69 kg/capita·day during the stable stage, and an average of 0.08 kg/capita·day during the reduction stage. Correlation analysis between generation unit of I-MW and lethality rates showed +0.99 in the unstable stage, +0.52 in the stable stage, and +0.96 in the reduction period, demonstrating a very high positive correlation of +0.95 or higher throughout the entire outbreaks of massive infectious diseases. The results derived from this study are expected to play a useful role in establishing an effective medical waste management system in the field of health care.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.2
• /
• pp.129-152
• /
• 2024

In the application of deep learning object detection via CCTV in tunnels, a large number of false positive detections occur due to the poor environmental conditions of tunnels, such as low illumination and severe perspective effect. This problem directly impacts the reliability of the tunnel CCTV-based accident detection system reliant on object detection performance. Hence, it is necessary to reduce the number of false positive detections while also enhancing the number of true positive detections. Based on a deep learning object detection model, this paper proposes a false positive data training method that not only reduces false positives but also improves true positive detection performance through retraining of false positive data. This paper's false positive data training method is based on the following steps: initial training of a training dataset - inference of a validation dataset - correction of false positive data and dataset composition - addition to the training dataset and retraining. In this paper, experiments were conducted to verify the performance of this method. First, the optimal hyperparameters of the deep learning object detection model to be applied in this experiment were determined through previous experiments. Then, in this experiment, training image format was determined, and experiments were conducted sequentially to check the long-term performance improvement through retraining of repeated false detection datasets. As a result, in the first experiment, it was found that the inclusion of the background in the inferred image was more advantageous for object detection performance than the removal of the background excluding the object. In the second experiment, it was found that retraining by accumulating false positives from each level of retraining was more advantageous than retraining independently for each level of retraining in terms of continuous improvement of object detection performance. After retraining the false positive data with the method determined in the two experiments, the car object class showed excellent inference performance with an AP value of 0.95 or higher after the first retraining, and by the fifth retraining, the inference performance was improved by about 1.06 times compared to the initial inference. And the person object class continued to improve its inference performance as retraining progressed, and by the 18th retraining, it showed that it could self-improve its inference performance by more than 2.3 times compared to the initial inference.

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

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

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.123-139
• /
• 2019

The Korean NPL market was formed by the government and foreign capital shortly after the 1997 IMF crisis. However, this market is short-lived, as the bad debt has started to increase after the global financial crisis in 2009 due to the real economic recession. NPL has become a major investment in the market in recent years when the domestic capital market's investment capital began to enter the NPL market in earnest. Although the domestic NPL market has received considerable attention due to the overheating of the NPL market in recent years, research on the NPL market has been abrupt since the history of capital market investment in the domestic NPL market is short. In addition, decision-making through more scientific and systematic analysis is required due to the decline in profitability and the price fluctuation due to the fluctuation of the real estate business. In this study, we propose a prediction model that can determine the achievement of the benchmark yield by using the NPL market related data in accordance with the market demand. In order to build the model, we used Korean NPL data from December 2013 to December 2017 for about 4 years. The total number of things data was 2291. As independent variables, only the variables related to the dependent variable were selected for the 11 variables that indicate the characteristics of the real estate. In order to select the variables, one to one t-test and logistic regression stepwise and decision tree were performed. Seven independent variables (purchase year, SPC (Special Purpose Company), municipality, appraisal value, purchase cost, OPB (Outstanding Principle Balance), HP (Holding Period)). The dependent variable is a bivariate variable that indicates whether the benchmark rate is reached. This is because the accuracy of the model predicting the binomial variables is higher than the model predicting the continuous variables, and the accuracy of these models is directly related to the effectiveness of the model. In addition, in the case of a special purpose company, whether or not to purchase the property is the main concern. Therefore, whether or not to achieve a certain level of return is enough to make a decision. For the dependent variable, we constructed and compared the predictive model by calculating the dependent variable by adjusting the numerical value to ascertain whether 12%, which is the standard rate of return used in the industry, is a meaningful reference value. As a result, it was found that the hit ratio average of the predictive model constructed using the dependent variable calculated by the 12% standard rate of return was the best at 64.60%. In order to propose an optimal prediction model based on the determined dependent variables and 7 independent variables, we construct a prediction model by applying the five methodologies of discriminant analysis, logistic regression analysis, decision tree, artificial neural network, and genetic algorithm linear model we tried to compare them. To do this, 10 sets of training data and testing data were extracted using 10 fold validation method. After building the model using this data, the hit ratio of each set was averaged and the performance was compared. As a result, the hit ratio average of prediction models constructed by using discriminant analysis, logistic regression model, decision tree, artificial neural network, and genetic algorithm linear model were 64.40%, 65.12%, 63.54%, 67.40%, and 60.51%, respectively. It was confirmed that the model using the artificial neural network is the best. Through this study, it is proved that it is effective to utilize 7 independent variables and artificial neural network prediction model in the future NPL market. The proposed model predicts that the 12% return of new things will be achieved beforehand, which will help the special purpose companies make investment decisions. Furthermore, we anticipate that the NPL market will be liquidated as the transaction proceeds at an appropriate price.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.25-38
• /
• 2019

Selecting high-quality information that meets the interests and needs of users among the overflowing contents is becoming more important as the generation continues. In the flood of information, efforts to reflect the intention of the user in the search result better are being tried, rather than recognizing the information request as a simple string. Also, large IT companies such as Google and Microsoft focus on developing knowledge-based technologies including search engines which provide users with satisfaction and convenience. Especially, the finance is one of the fields expected to have the usefulness and potential of text data analysis because it's constantly generating new information, and the earlier the information is, the more valuable it is. Automatic knowledge extraction can be effective in areas where information flow is vast, such as financial sector, and new information continues to emerge. However, there are several practical difficulties faced by automatic knowledge extraction. First, there are difficulties in making corpus from different fields with same algorithm, and it is difficult to extract good quality triple. Second, it becomes more difficult to produce labeled text data by people if the extent and scope of knowledge increases and patterns are constantly updated. Third, performance evaluation is difficult due to the characteristics of unsupervised learning. Finally, problem definition for automatic knowledge extraction is not easy because of ambiguous conceptual characteristics of knowledge. So, in order to overcome limits described above and improve the semantic performance of stock-related information searching, this study attempts to extract the knowledge entity by using neural tensor network and evaluate the performance of them. Different from other references, the purpose of this study is to extract knowledge entity which is related to individual stock items. Various but relatively simple data processing methods are applied in the presented model to solve the problems of previous researches and to enhance the effectiveness of the model. From these processes, this study has the following three significances. First, A practical and simple automatic knowledge extraction method that can be applied. Second, the possibility of performance evaluation is presented through simple problem definition. Finally, the expressiveness of the knowledge increased by generating input data on a sentence basis without complex morphological analysis. The results of the empirical analysis and objective performance evaluation method are also presented. The empirical study to confirm the usefulness of the presented model, experts' reports about individual 30 stocks which are top 30 items based on frequency of publication from May 30, 2017 to May 21, 2018 are used. the total number of reports are 5,600, and 3,074 reports, which accounts about 55% of the total, is designated as a training set, and other 45% of reports are designated as a testing set. Before constructing the model, all reports of a training set are classified by stocks, and their entities are extracted using named entity recognition tool which is the KKMA. for each stocks, top 100 entities based on appearance frequency are selected, and become vectorized using one-hot encoding. After that, by using neural tensor network, the same number of score functions as stocks are trained. Thus, if a new entity from a testing set appears, we can try to calculate the score by putting it into every single score function, and the stock of the function with the highest score is predicted as the related item with the entity. To evaluate presented models, we confirm prediction power and determining whether the score functions are well constructed by calculating hit ratio for all reports of testing set. As a result of the empirical study, the presented model shows 69.3% hit accuracy for testing set which consists of 2,526 reports. this hit ratio is meaningfully high despite of some constraints for conducting research. Looking at the prediction performance of the model for each stocks, only 3 stocks, which are LG ELECTRONICS, KiaMtr, and Mando, show extremely low performance than average. this result maybe due to the interference effect with other similar items and generation of new knowledge. In this paper, we propose a methodology to find out key entities or their combinations which are necessary to search related information in accordance with the user's investment intention. Graph data is generated by using only the named entity recognition tool and applied to the neural tensor network without learning corpus or word vectors for the field. From the empirical test, we confirm the effectiveness of the presented model as described above. However, there also exist some limits and things to complement. Representatively, the phenomenon that the model performance is especially bad for only some stocks shows the need for further researches. Finally, through the empirical study, we confirmed that the learning method presented in this study can be used for the purpose of matching the new text information semantically with the related stocks.

• 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.