• Journal of Korean Society of Disaster and Security
• /
• v.16 no.2
• /
• pp.15-32
• /
• 2023

There are some difficulties such as safety problem and need of manpower in measuring discharge by submerging the instruments because of many floating debris and very fast flow in the river during the flood season. As an alternative, microwave water surface current meters have been increasingly used these days, which are easy to measure the discharge in the field without contacting the water surface directly. But it is also hard to apply the method in the sudden and rapidly changing field conditions. Therefore, the estimation of the discharge using the surface velocity in flood conditions requires a theoretical and economical approach. In this study, the measurements from microwave water surface current meter and rating curve were collected and then analyzed by the discharge estimation method using the surface velocity. Generally, the measured and converted discharge are analyzed to be similar in all methods at a hydraulic radius of 3 m or over or a mean velocity of 2 ㎧ or more. Besides, the study computed the discharge by the index velocity method and the velocity profile method with the maximum surface velocity in the section where the maximum velocity occurs at the high water level range of the rating curve among the target locations. As a result, the mean relative error with the converted discharge was within 10%. That is, in flood season, the discharge estimation method using one maximum surface velocity measurement, index velocity method, and velocity profile method can be applied to develop high-level extrapolation, therefore, it is judged that the reliability for the range of extrapolation estimation could be improved. Therefore, the discharge estimation method using the surface velocity is expected to become a fast and efficient discharge measurement method during the flood season.

• Korean Chemical Engineering Research
• /
• v.61 no.4
• /
• pp.555-560
• /
• 2023

Conventional aqueous amine-based CO₂ capture has a problem in that a large amount of renewable energy is required for CO₂ stripping and solvent regeneration in its industrial applications. This work proposes a water-lean absorbent that can reduce regeneration energy by lowering the water content in the absorbent with high absorption capacity for CO₂. To this purpose, this water-lean solvent introduced NMP (N-methyl-2-pyrrolidone), which has a higher physical solubility in CO₂ and a low specific heat capacity comparing to water, along with 3-methylaminopropylamine (MAPA), a diamine, into the absorbent. The circulating absorption capacity and absorption rate for CO₂ of this water-lean solvent were measured using a packed tower. When NMP was added to the absorbent, the absorption rate was improved. In the case of the absorbent containing 2.5M MAPA was used, the maximum circulating absorption capacity was obtained when 10 wt% of NMP was included in absorbent. The overall mass transfer coefficient increased as the concentration of NMP increased. However, at loading values higher than 0.5, the increment in mass transfer coefficient decreased as the concentration of NMP increased. When the lean loading value is low, the mass transfer resistance due to viscosity of the absorbent is low, so the overall mass transfer coefficient increases with the addition of NMP. However, as the lean loading value increases, the viscosity of the absorbent increases, and the diffusivity of CO₂ and MAPA decreases, resulting in sharply decreasing of the overall mass transfer coefficient.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.52 no.1
• /
• pp.46-58
• /
• 2024

Pollinators are organisms that carry out the pollination process of plants and include Hymenoptera, Lepidoptera, Diptera, and Coleoptera. Among them, bees not only pollinate plants but also improve urban green spaces damaged by land use changes, providing a habitat and food for birds and insects. Today, however, the number of pollinating plants is decreasing due to issues such as early flowering due to climate change, fragmentation of green spaces due to urbanization, and pesticide use, which in turn leads to a decline in bee populations. The decline of bee populations directly translates into problems, such as reduced biodiversity in cities and decreased food production. Urban beekeeping has been proposed as a strategy to address the decline of bee populations. However, there is a problem asurban beekeeping strategies are proposed without considering the complex structure of the socio-ecological system consisting of bees foraging and pollination activities and are therefore unsustainable. Therefore, this study aims to analyze the socio-ecological system of honeybees, which are pollinators, structurally using system thinking and propose a green space planning strategy to revitalize urban beekeeping. For this study, previous studies that centered on the social and ecological system of bees in cities were collected and reviewed to establish the system area and derive the main variables for creating a causal loop diagram. Second, the ecological structure of bees' foraging and pollination activities and the structure of bees' ecological system in the city were analyzed, as was the social-ecological system structure of urban beekeeping by creating an individual causal loop diagram. Finally, the socio-ecological system structure of honey bees was analyzed from a holistic perspective through the creation of an integrated causal loop diagram. Citizen participation programs, local government investment, and the creation of urban parks and green spaces in idle spaces were suggestedas green space planning strategies to revitalize urban beekeeping. The results of this study differ from previous studies in that the ecological structure of bees and the social structure of urban beekeeping were analyzed from a holistic perspective using systems thinking to propose strategies, policy recommendations, and implications for introducing sustainable urban beekeeping.

• 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.

• Phonetics and Speech Sciences
• /
• v.16 no.3
• /
• pp.59-69
• /
• 2024

Among the subgroups of speech sound disorder (SSD), the motor speech disorder (MSD) group is characterized by weak articulatory force. This study quantitatively measured and compared articulatory muscle strength between SSD and typically developing (TD) children. The Iowa Oral Performance Instrument (IOPI) was used to measure lip and tongue strength in 15 children with SSD and 15 TD children. We additionally measured peak lip and tongue pressure and endurance, and analyzed the correlation between each strength measure and the percentage of consonants correct (PCC). The findings were as follows: First, lip strength for the bilabial sounds did not differ between the two groups in the initial position but was significantly weaker in the SSD group in the final position. Tongue strength for alveolar sounds was weaker in the SSD group than in the TD group for the initial and final positions. Second, for lip and tongue strength, the difference in voicing features was significant in the TD group but not in the SSD group. Third, the peak pressure and endurance of the lips and tongue were significantly lower in the SSD group than in the TD group. Fourth, significantly higher static correlations were observed between most strength measures and the PCC. These findings suggest that weakness in articulatory motor execution may be an unrecognized underlying problem of SSD with unknown origin.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.95-112
• /
• 2021

In university education, the choice of major class plays an important role in students' careers. However, in line with the changes in the industry, the fields of major subjects by department are diversifying and increasing in number in university education. As a result, students have difficulty to choose and take classes according to their career paths. In general, students choose classes based on experiences such as choices of peers or advice from seniors. This has the advantage of being able to take into account the general situation, but it does not reflect individual tendencies and considerations of existing courses, and has a problem that leads to information inequality that is shared only among specific students. In addition, as non-face-to-face classes have recently been conducted and exchanges between students have decreased, even experience-based decisions have not been made as well. Therefore, this study proposes a recommendation system model that can recommend college major classes suitable for individual characteristics based on data rather than experience. The recommendation system recommends information and content (music, movies, books, images, etc.) that a specific user may be interested in. It is already widely used in services where it is important to consider individual tendencies such as YouTube and Facebook, and you can experience it familiarly in providing personalized services in content services such as over-the-top media services (OTT). Classes are also a kind of content consumption in terms of selecting classes suitable for individuals from a set content list. However, unlike other content consumption, it is characterized by a large influence of selection results. For example, in the case of music and movies, it is usually consumed once and the time required to consume content is short. Therefore, the importance of each item is relatively low, and there is no deep concern in selecting. Major classes usually have a long consumption time because they have to be taken for one semester, and each item has a high importance and requires greater caution in choice because it affects many things such as career and graduation requirements depending on the composition of the selected classes. Depending on the unique characteristics of these major classes, the recommendation system in the education field supports decision-making that reflects individual characteristics that are meaningful and cannot be reflected in experience-based decision-making, even though it has a relatively small number of item ranges. This study aims to realize personalized education and enhance students' educational satisfaction by presenting a recommendation model for university major class. In the model study, class history data of undergraduate students at University from 2015 to 2017 were used, and students and their major names were used as metadata. The class history data is implicit feedback data that only indicates whether content is consumed, not reflecting preferences for classes. Therefore, when we derive embedding vectors that characterize students and classes, their expressive power is low. With these issues in mind, this study proposes a Net-NeuMF model that generates vectors of students, classes through network analysis and utilizes them as input values of the model. The model was based on the structure of NeuMF using one-hot vectors, a representative model using data with implicit feedback. The input vectors of the model are generated to represent the characteristic of students and classes through network analysis. To generate a vector representing a student, each student is set to a node and the edge is designed to connect with a weight if the two students take the same class. Similarly, to generate a vector representing the class, each class was set as a node, and the edge connected if any students had taken the classes in common. Thus, we utilize Node2Vec, a representation learning methodology that quantifies the characteristics of each node. For the evaluation of the model, we used four indicators that are mainly utilized by recommendation systems, and experiments were conducted on three different dimensions to analyze the impact of embedding dimensions on the model. The results show better performance on evaluation metrics regardless of dimension than when using one-hot vectors in existing NeuMF structures. Thus, this work contributes to a network of students (users) and classes (items) to increase expressiveness over existing one-hot embeddings, to match the characteristics of each structure that constitutes the model, and to show better performance on various kinds of evaluation metrics compared to existing methodologies.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.205-225
• /
• 2018

Convolutional Neural Network (ConvNet) is one class of the powerful Deep Neural Network that can analyze and learn hierarchies of visual features. Originally, first neural network (Neocognitron) was introduced in the 80s. At that time, the neural network was not broadly used in both industry and academic field by cause of large-scale dataset shortage and low computational power. However, after a few decades later in 2012, Krizhevsky made a breakthrough on ILSVRC-12 visual recognition competition using Convolutional Neural Network. That breakthrough revived people interest in the neural network. The success of Convolutional Neural Network is achieved with two main factors. First of them is the emergence of advanced hardware (GPUs) for sufficient parallel computation. Second is the availability of large-scale datasets such as ImageNet (ILSVRC) dataset for training. Unfortunately, many new domains are bottlenecked by these factors. For most domains, it is difficult and requires lots of effort to gather large-scale dataset to train a ConvNet. Moreover, even if we have a large-scale dataset, training ConvNet from scratch is required expensive resource and time-consuming. These two obstacles can be solved by using transfer learning. Transfer learning is a method for transferring the knowledge from a source domain to new domain. There are two major Transfer learning cases. First one is ConvNet as fixed feature extractor, and the second one is Fine-tune the ConvNet on a new dataset. In the first case, using pre-trained ConvNet (such as on ImageNet) to compute feed-forward activations of the image into the ConvNet and extract activation features from specific layers. In the second case, replacing and retraining the ConvNet classifier on the new dataset, then fine-tune the weights of the pre-trained network with the backpropagation. In this paper, we focus on using multiple ConvNet layers as a fixed feature extractor only. However, applying features with high dimensional complexity that is directly extracted from multiple ConvNet layers is still a challenging problem. We observe that features extracted from multiple ConvNet layers address the different characteristics of the image which means better representation could be obtained by finding the optimal combination of multiple ConvNet layers. Based on that observation, we propose to employ multiple ConvNet layer representations for transfer learning instead of a single ConvNet layer representation. Overall, our primary pipeline has three steps. Firstly, images from target task are given as input to ConvNet, then that image will be feed-forwarded into pre-trained AlexNet, and the activation features from three fully connected convolutional layers are extracted. Secondly, activation features of three ConvNet layers are concatenated to obtain multiple ConvNet layers representation because it will gain more information about an image. When three fully connected layer features concatenated, the occurring image representation would have 9192 (4096+4096+1000) dimension features. However, features extracted from multiple ConvNet layers are redundant and noisy since they are extracted from the same ConvNet. Thus, a third step, we will use Principal Component Analysis (PCA) to select salient features before the training phase. When salient features are obtained, the classifier can classify image more accurately, and the performance of transfer learning can be improved. To evaluate proposed method, experiments are conducted in three standard datasets (Caltech-256, VOC07, and SUN397) to compare multiple ConvNet layer representations against single ConvNet layer representation by using PCA for feature selection and dimension reduction. Our experiments demonstrated the importance of feature selection for multiple ConvNet layer representation. Moreover, our proposed approach achieved 75.6% accuracy compared to 73.9% accuracy achieved by FC7 layer on the Caltech-256 dataset, 73.1% accuracy compared to 69.2% accuracy achieved by FC8 layer on the VOC07 dataset, 52.2% accuracy compared to 48.7% accuracy achieved by FC7 layer on the SUN397 dataset. We also showed that our proposed approach achieved superior performance, 2.8%, 2.1% and 3.1% accuracy improvement on Caltech-256, VOC07, and SUN397 dataset respectively compare to existing work.

• Journal of Internet Computing and Services
• /
• v.16 no.1
• /
• pp.67-74
• /
• 2015

In recent years, frequent itemset mining for considering the importance of each item has been intensively studied as one of important issues in the data mining field. According to strategies utilizing the item importance, itemset mining approaches for discovering itemsets based on the item importance are classified as follows: weighted frequent itemset mining, frequent itemset mining using transactional weights, and utility itemset mining. In this paper, we perform empirical analysis with respect to frequent itemset mining algorithms based on transactional weights. The mining algorithms compute transactional weights by utilizing the weight for each item in large databases. In addition, these algorithms discover weighted frequent itemsets on the basis of the item frequency and weight of each transaction. Consequently, we can see the importance of a certain transaction through the database analysis because the weight for the transaction has higher value if it contains many items with high values. We not only analyze the advantages and disadvantages but also compare the performance of the most famous algorithms in the frequent itemset mining field based on the transactional weights. As a representative of the frequent itemset mining using transactional weights, WIS introduces the concept and strategies of transactional weights. In addition, there are various other state-of-the-art algorithms, WIT-FWIs, WIT-FWIs-MODIFY, and WIT-FWIs-DIFF, for extracting itemsets with the weight information. To efficiently conduct processes for mining weighted frequent itemsets, three algorithms use the special Lattice-like data structure, called WIT-tree. The algorithms do not need to an additional database scanning operation after the construction of WIT-tree is finished since each node of WIT-tree has item information such as item and transaction IDs. In particular, the traditional algorithms conduct a number of database scanning operations to mine weighted itemsets, whereas the algorithms based on WIT-tree solve the overhead problem that can occur in the mining processes by reading databases only one time. Additionally, the algorithms use the technique for generating each new itemset of length N+1 on the basis of two different itemsets of length N. To discover new weighted itemsets, WIT-FWIs performs the itemset combination processes by using the information of transactions that contain all the itemsets. WIT-FWIs-MODIFY has a unique feature decreasing operations for calculating the frequency of the new itemset. WIT-FWIs-DIFF utilizes a technique using the difference of two itemsets. To compare and analyze the performance of the algorithms in various environments, we use real datasets of two types (i.e., dense and sparse) in terms of the runtime and maximum memory usage. Moreover, a scalability test is conducted to evaluate the stability for each algorithm when the size of a database is changed. As a result, WIT-FWIs and WIT-FWIs-MODIFY show the best performance in the dense dataset, and in sparse dataset, WIT-FWI-DIFF has mining efficiency better than the other algorithms. Compared to the algorithms using WIT-tree, WIS based on the Apriori technique has the worst efficiency because it requires a large number of computations more than the others on average.

• Journal of Internet Computing and Services
• /
• v.16 no.1
• /
• pp.47-55
• /
• 2015

Recently, the environment of a hospital information system is a trend to combine various SMART technologies. Accordingly, various smart devices, such as a smart phone, Tablet PC is utilized in the medical information system. Also, these environments consist of various applications executing on heterogeneous sensors, devices, systems and networks. In these hospital information system environment, applying a security service by traditional access control method cause a problems. Most of the existing security system uses the access control list structure. It is only permitted access defined by an access control matrix such as client name, service object method name. The major problem with the static approach cannot quickly adapt to changed situations. Hence, we needs to new security mechanisms which provides more flexible and can be easily adapted to various environments with very different security requirements. In addition, for addressing the changing of service medical treatment of the patient, the researching is needed. In this paper, we suggest a dynamic approach to medical information systems in smart mobile environments. We focus on how to access medical information systems according to dynamic access control methods based on the existence of the hospital's information system environments. The physical environments consist of a mobile x-ray imaging devices, dedicated mobile/general smart devices, PACS, EMR server and authorization server. The software environment was developed based on the .Net Framework for synchronization and monitoring services based on mobile X-ray imaging equipment Windows7 OS. And dedicated a smart device application, we implemented a dynamic access services through JSP and Java SDK is based on the Android OS. PACS and mobile X-ray image devices in hospital, medical information between the dedicated smart devices are based on the DICOM medical image standard information. In addition, EMR information is based on H7. In order to providing dynamic access control service, we classify the context of the patients according to conditions of bio-information such as oxygen saturation, heart rate, BP and body temperature etc. It shows event trace diagrams which divided into two parts like general situation, emergency situation. And, we designed the dynamic approach of the medical care information by authentication method. The authentication Information are contained ID/PWD, the roles, position and working hours, emergency certification codes for emergency patients. General situations of dynamic access control method may have access to medical information by the value of the authentication information. In the case of an emergency, was to have access to medical information by an emergency code, without the authentication information. And, we constructed the medical information integration database scheme that is consist medical information, patient, medical staff and medical image information according to medical information standards.y Finally, we show the usefulness of the dynamic access application service based on the smart devices for execution results of the proposed system according to patient contexts such as general and emergency situation. Especially, the proposed systems are providing effective medical information services with smart devices in emergency situation by dynamic access control methods. As results, we expect the proposed systems to be useful for u-hospital information systems and services.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.22 no.3
• /
• pp.182-191
• /
• 2011

Objectives: The aim of this study was to investigate the sleep patterns of South Korean elementary school children and whether the differences in sleep patterns were related to behavior, emotional problems, attention and academic performance. Method: This study included a community sample of 268 boys and girls from fourth-, fifth- and sixth-grade classes in a South Korean metropolitan city from November to December 2010. The primary caregivers completed a questionnaire that included information on demographic characteristics, as well as the Child's Sleep Habit Questionnaire (CSHQ), the Korean version of Child Behavior Checklist (K-CBCL), the Korean version of the Learning Disability Evaluation Scale (K-LDES), the Korean version of ADHD Rating Scale (K-ARS) and the Disruptive Behavior Disorder Scale (DBDS). We conducted analyses on the CSHQ individual items, between the subscales, on the total scores and on the K-CBCL, the K-LEDS, the K-ARS and the DBDS. Results: Based on the findings from the CHSQ, the subjects had significantly higher scores for bedtime resistance ($9.18{\pm}2.17$), delayed sleep onset ($1.32{\pm}0.62$), the sleep duration ($4.19{\pm}1.52$) and daytime sleepiness ($14.10{\pm}3.55$) than the scores from the previous reports on children from western countries. The total CHSQ score showed positive correlations to all subscales of the K-CBCL : withdrawn (r=0.24, p<.005), somatic complaint (r=0.24, p<.005) and anxious/depressive (r=0.38, p<.005). Bedtime resistance was associated with oppositional defiant disorder (r=0.15, p<.05) and a positive correlation was demonstrated between sleep anxiety and the oppositional defiant disorder score (r=0.13, p<.05), night waking and the conduct disorder score (r=0.16, p<.05). Delayed sleep onset was related with low performance on the K-LDES with respect to thinking (r=-0.17, p<.05) and mathematical calculation (r=-0.17, p<.05). Conclusion: The results of this study reconfirm Korean children's problematic sleep patterns. Taken together the results provide that the reduced sleep duration and disruption of sleep pattern can have a significant impact on emotion, behavior, performance of learning in children. Further studies concerning more diverse psychosocial factors affecting sleep pattern will be helpful to understanding of the sleep health in Korean children.