• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.139-156
• /
• 2021

The biggest reason for using a deep learning model in image classification is that it is possible to consider the relationship between each region by extracting each region's features from the overall information of the image. However, the CNN model may not be suitable for emotional image data without the image's regional features. To solve the difficulty of classifying emotion images, many researchers each year propose a CNN-based architecture suitable for emotion images. Studies on the relationship between color and human emotion were also conducted, and results were derived that different emotions are induced according to color. In studies using deep learning, there have been studies that apply color information to image subtraction classification. The case where the image's color information is additionally used than the case where the classification model is trained with only the image improves the accuracy of classifying image emotions. This study proposes two ways to increase the accuracy by incorporating the result value after the model classifies an image's emotion. Both methods improve accuracy by modifying the result value based on statistics using the color of the picture. When performing the test by finding the two-color combinations most distributed for all training data, the two-color combinations most distributed for each test data image were found. The result values were corrected according to the color combination distribution. This method weights the result value obtained after the model classifies an image's emotion by creating an expression based on the log function and the exponential function. Emotion6, classified into six emotions, and Artphoto classified into eight categories were used for the image data. Densenet169, Mnasnet, Resnet101, Resnet152, and Vgg19 architectures were used for the CNN model, and the performance evaluation was compared before and after applying the two-stage learning to the CNN model. Inspired by color psychology, which deals with the relationship between colors and emotions, when creating a model that classifies an image's sentiment, we studied how to improve accuracy by modifying the result values based on color. Sixteen colors were used: red, orange, yellow, green, blue, indigo, purple, turquoise, pink, magenta, brown, gray, silver, gold, white, and black. It has meaning. Using Scikit-learn's Clustering, the seven colors that are primarily distributed in the image are checked. Then, the RGB coordinate values of the colors from the image are compared with the RGB coordinate values of the 16 colors presented in the above data. That is, it was converted to the closest color. Suppose three or more color combinations are selected. In that case, too many color combinations occur, resulting in a problem in which the distribution is scattered, so a situation fewer influences the result value. Therefore, to solve this problem, two-color combinations were found and weighted to the model. Before training, the most distributed color combinations were found for all training data images. The distribution of color combinations for each class was stored in a Python dictionary format to be used during testing. During the test, the two-color combinations that are most distributed for each test data image are found. After that, we checked how the color combinations were distributed in the training data and corrected the result. We devised several equations to weight the result value from the model based on the extracted color as described above. The data set was randomly divided by 80:20, and the model was verified using 20% of the data as a test set. After splitting the remaining 80% of the data into five divisions to perform 5-fold cross-validation, the model was trained five times using different verification datasets. Finally, the performance was checked using the test dataset that was previously separated. Adam was used as the activation function, and the learning rate was set to 0.01. The training was performed as much as 20 epochs, and if the validation loss value did not decrease during five epochs of learning, the experiment was stopped. Early tapping was set to load the model with the best validation loss value. The classification accuracy was better when the extracted information using color properties was used together than the case using only the CNN architecture.

• Atmosphere
• /
• v.20 no.4
• /
• pp.467-482
• /
• 2010

In this study, characteristics of various stability indexes (SI) and environmental parameters (EP) for the lightning are analysed by using 5 upper air observatories (Osan, Gwangju, Jeju, Pohang, and Baengnyeongdo) for the years 2002-2006 over South Korea. The analysed SI and EP are the lifted index, K-index, Showalter stability index, total precipitable water, mixing ratio, wind shear and temperature of lifting condensation level. The lightning data occurred on the range of -2 hr~+1 hr and within 100 km based on the launch time of rawinsonde and observing location are selected. In general, summer averaged temperature and mixing ratio of lower troposphere for the lightning cases are higher about 1 K and $1{\sim}2gkg^{-1}$ than no lightning cases, respectively. The Box-Whisker plot shows that the range of various SI and EP values for lightning and no lightning cases are well separated but overlapping of SI and EP values between lightning and no lightning are not a little. The optimized threshold values for the detection of lightning are determined objectively based on the highest Heidke skill socre (HSS), which is the most favorable validation parameter for the rare event, such as lightning, by using the simulation of SI and EP threshold values. Although the HSS is not high (0.15~0.30) and the number and values of selected SI and EP are dependent on geographic location, the new threshold values can be used as a supplementary tool for the detection or forecast of lightning over South Korea.

• International Journal of Highway Engineering
• /
• v.8 no.3 s.29
• /
• pp.129-141
• /
• 2006

The vertical soil pressure developed in the granular layer of asphalt pavement system is influenced by various factors, including the wheel load magnitude, the loading speed, and asphalt pavement temperature. This research observed the distribution of vertical soil pressure in pavement supporting layer by investigating measured data from soil pressure gage in the KHC Test Road. The existing specification of subbase and subgrade compaction was also evaluated with measured vertical pressure. The finite element analysis was conducted to verify the accuracy of results with measured data because it can maximize research capacity without significant field test. The test data was collected from A5, A7, A14, and A15 test sections at August, September, and November 2004 and August 2005. Those test sections and test data were selected because they had best quality. The size of influence area was evaluated and the vertical pressure variation was investigated with respect to load level, load speed, and pavement temperature. The lower speed, higher load level, and higher pavement temperature increased the vertical pressure and reduced the area of influence. The finite element result showed the similar trend of vertical pressure variation in comparison with measured data. The specification of compaction quality for subbase and subgrade is higher than the level of vertical pressure measured with truck load so that it should be lurker investigated.

• Spatial Information Research
• /
• v.11 no.3
• /
• pp.261-274
• /
• 2003

The effective probability-based tile pre-fetching algorithm and the collaborative cache replacement algorithm are able to reduce the response time for user's requests by transferring tiles which will be used in advance and determining tiles which should be removed from the restrictive cache space of a client based on the future access probabilities in Web GISs(Geographical Information Systems). The Web GISs have multi-level abstracted data for the quick response time when zoom-in and zoom-out queries are requested. But, the previous pre-fetching algorithm is applied on only two-dimensional pre-fetching space, and doesn't consider expanded pre-fetching space for multi-level abstracted data in Web GISs. In this thesis, a probability-based pre-fetching algorithm for multi-level abstracted in Web GISs was proposed. This algorithm expanded the previous two-dimensional pre-fetching space into three-dimensional one for pre-fetching tiles of the upper levels or lower levels. Moreover, we evaluated the effect of the proposed pre-fetching algorithm by using a simulation method. Through the experimental results, the response time for user requests was improved 1.8%∼21.6% on the average. Consequently, in Web GISs with multi-level abstracted data, the proposed pre-fetching algorithm and the collaborative cache replacement algorithm can reduce the response time for user requests substantially.

• The Korean Journal of Nuclear Medicine
• /
• v.37 no.5
• /
• pp.278-287
• /
• 2003

Purpose: The performance of nitroglycerin-challenged Tc-99m-MIBI quantitative gated SPECT for the detection of viable myocardium was compared with rest/24-hour redistribution Tl-201 SPECT Materials and Methods: In 22 patients with coronary artery disease, rest Tl-20l/ dipyridamole stress Tc-99m-MIBI gated/24-hour redistribution Tl-201 SPECT were peformed, and gated SPECT was repeated on-site after sublingual administration of nitroglycerin (0.6 mg). Follow-up gated SPECT was done 3 months after coronary artery bypass graft surgery. For 20 segments per patient, perfusion at rest and 24-hour redistribution, and wall motion and thickening at baseline and nitroglycerin-challenged state were quantified. Quantitative viability markers were evaluated and compared;(1) rest thallium uptake, (2) thallium uptake on 24-hour redistribution SPECT, (3) systolic wall thickening at baseline, and (4) systolic wall thickening with nitroglycerin-challenge. Results: Among 100 revascularized dysfunctional segments, wall motion improved in 66 segments (66%) on follow-up gated myocardial SPECT after bypass surgery. On receiver operating characteristic (ROC) curve analysis, the sensitivity and specificity of rest and 24-hour delayed redistribution Tl-201 SPECT were 79%, 44% and 82%, 44%, respectively, at the optimal cutoff value of 50% of Tl-201 uptake. The sensitivity and specificity of systolic wall thickening at baseline and nitroglycerin-challenge were 49%, 50% and 64%, 65% at the optimal cutoff value of 15% of systolic wall thickening. Area under the ROC curve of nitroglycerin-challenged systolic wall thickening was significantly larger than that of baseline systolic wall thickening (p=0.004). Conclusion: Nitroglycerin-challenged quantitative gated Tc-99m-MIBI SPECT was a useful method for predicting functional recovery of dysfunctional myocardium.

• Journal of the Society of Disaster Information
• /
• v.11 no.1
• /
• pp.135-147
• /
• 2015

Recent underground common utility tunnels are underground facilities for jointly accommodating more than 2 kinds of air-conditioning and heating facilities, vacuum dust collector, information processing cables as well as electricity, telecommunications, waterworks, city gas, sewerage system required when citizens live their daily lives and facilities responsible for the central function of the country but it is difficult to cope with fire accidents quickly and hard to enter into common utility tunnels to extinguish a fire due to toxic gases and smoke generated when various cables are burnt. Thus, in the event of a fire, not only the nerve center of the country is paralyzed such as significant property damage and loss of communication etc. but citizen inconveniences are caused. Therefore, noticing that most fires break out by a short circuit due to electrical works and degradation contact due to combustible cables as the main causes of fires in domestic and foreign common utility tunnels fire cases that have occurred so far, the purpose of this paper is to scientifically analyze the behavior of a fire by producing the model of actual common utility tunnels and reproducing the fire. A fire experiment was conducted in a state that line type fixed temperature detector, fire door, connection deluge set and ventilation equipment are installed in underground common utility tunnels and transmission power distribution cables are coated with fire proof paints in a certain section and heating pipes are fire proof covered. As a result, in the case of Type II, the maximum temperature was measured as $932^{\circ}C$ and line type fixed temperature detector displayed the fire location exactly in the receiver at a constant temperature. And transmission power distribution cables painted with fire proof paints in a certain section, the case of Type III, were found not to be fire resistant and fire proof covered heating pipes to be fire resistant for about 30 minutes. Also, fire simulation was carried out by entering fire load during a real fire test and as a result, the maximum temperature is $943^{\circ}C$, almost identical with $932^{\circ}C$ during a real fire test. Therefore, it is considered that fire behaviour can be predicted by conducting fire simulation only with common utility tunnels fire load and result values of heat release rate, height of the smoke layer, concentration of O2, CO, CO2 etc. obtained by simulation are determined to be applied as the values during a real fire experiment. In the future, it is expected that more reliable information on domestic underground common utility tunnels fire accidents can be provided and it will contribute to construction and maintenance repair effectively and systematically by analyzing and accumulating experimental data on domestic underground common utility tunnels fire accidents built in this study and fire cases continuously every year and complementing laws and regulations and administration manuals etc.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.43-56
• /
• 2020

Recommender systems help users make the best choice among various options. Especially, recommender systems play important roles in internet sites as digital information is generated innumerable every second. Many studies on recommender systems have focused on an accurate recommendation. However, there are some problems to overcome in order for the recommendation system to be commercially successful. First, there is a lack of transparency in the recommender system. That is, users cannot know why products are recommended. Second, the recommender system cannot immediately reflect changes in user preferences. That is, although the preference of the user's product changes over time, the recommender system must rebuild the model to reflect the user's preference. Therefore, in this study, we proposed a recommendation methodology using topic modeling and sequential association rule mining to solve these problems from review data. Product reviews provide useful information for recommendations because product reviews include not only rating of the product but also various contents such as user experiences and emotional state. So, reviews imply user preference for the product. So, topic modeling is useful for explaining why items are recommended to users. In addition, sequential association rule mining is useful for identifying changes in user preferences. The proposed methodology is largely divided into two phases. The first phase is to create user profile based on topic modeling. After extracting topics from user reviews on products, user profile on topics is created. The second phase is to recommend products using sequential rules that appear in buying behaviors of users as time passes. The buying behaviors are derived from a change in the topic of each user. A collaborative filtering-based recommendation system was developed as a benchmark system, and we compared the performance of the proposed methodology with that of the collaborative filtering-based recommendation system using Amazon's review dataset. As evaluation metrics, accuracy, recall, precision, and F1 were used. For topic modeling, collapsed Gibbs sampling was conducted. And we extracted 15 topics. Looking at the main topics, topic 1, top 3, topic 4, topic 7, topic 9, topic 13, topic 14 are related to "comedy shows", "high-teen drama series", "crime investigation drama", "horror theme", "British drama", "medical drama", "science fiction drama", respectively. As a result of comparative analysis, the proposed methodology outperformed the collaborative filtering-based recommendation system. From the results, we found that the time just prior to the recommendation was very important for inferring changes in user preference. Therefore, the proposed methodology not only can secure the transparency of the recommender system but also can reflect the user's preferences that change over time. However, the proposed methodology has some limitations. The proposed methodology cannot recommend product elaborately if the number of products included in the topic is large. In addition, the number of sequential patterns is small because the number of topics is too small. Therefore, future research needs to consider these limitations.

• Journal of Korea Spatial Information System Society
• /
• v.6 no.1 s.11
• /
• pp.73-85
• /
• 2004

Recently, as the growth of the wireless Internet, PDA and HPC, the focus of research and development related with GIS(Geographic Information System) has been changed to the Real-Time Mobile GIS to service LBS. To offer LBS efficiently, there must be the Real-Time GIS platform that can deal with dynamic status of moving objects and a location index which can deal with the characteristics of location data. Location data can use the same data type(e.g., point) of GIS, but the management of location data is very different. Therefore, in this paper, we studied the Real-Time Mobile GIS using the HBR-tree to manage mass of location data efficiently. The Real-Time Mobile GIS which is developed in this paper consists of the HBR-tree and the Real-Time GIS Platform HBR-tree. we proposed in this paper, is a combined index type of the R-tree and the spatial hash Although location data are updated frequently, update operations are done within the same hash table in the HBR-tree, so it costs less than other tree-based indexes Since the HBR-tree uses the same search mechanism of the R-tree, it is possible to search location data quickly. The Real-Time GIS platform consists of a Real-Time GIS engine that is extended from a main memory database system. a middleware which can transfer spatial, aspatial data to clients and receive location data from clients, and a mobile client which operates on the mobile devices. Especially, this paper described the performance evaluation conducted with practical tests if the HBR-tree and the Real-Time GIS engine respectively.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.3
• /
• pp.149-155
• /
• 2021

Early warning systems for weather risk management in the agricultural sector have been developed to predict potential wind damage to crops. These systems take into account the daily maximum wind speed to determine the critical wind speed that causes fruit drops and provide the weather risk information to farmers. In an effort to increase the accuracy of wind risk predictions, an artificial neural network for binary classification was implemented. In the present study, the daily wind speed and other weather data, which were measured at weather stations at sites of interest in Jeollabuk-do and Jeollanam-do as well as Gyeongsangbuk- do and part of Gyeongsangnam- do provinces in 2019, were used for training the neural network. These weather stations include 210 synoptic and automated weather stations operated by the Korean Meteorological Administration (KMA). The wind speed data collected at the same locations between January 1 and December 12, 2020 were used to validate the neural network model. The data collected from December 13, 2020 to February 18, 2021 were used to evaluate the wind risk prediction performance before and after the use of the artificial neural network. The critical wind speed of damage risk was determined to be 11 m/s, which is the wind speed reported to cause fruit drops and damages. Furthermore, the maximum wind speeds were expressed using Weibull distribution probability density function for warning of wind damage. It was found that the accuracy of wind damage risk prediction was improved from 65.36% to 93.62% after re-classification using the artificial neural network. Nevertheless, the error rate also increased from 13.46% to 37.64%, as well. It is likely that the machine learning approach used in the present study would benefit case studies where no prediction by risk warning systems becomes a relatively serious issue.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_2
• /
• pp.1615-1633
• /
• 2023

Sargassum horneri is one of the floating algae in the sea, which breeds in large quantities in the Yellow Sea and East China Sea and then flows into the coast of Republic of Korea, causing various problems such as destroying the environment and damaging fish farms. In order to effectively prevent damage and preserve the coastal environment, the development of Sargassum horneri detection algorithms using satellite-based remote sensing technology has been actively developed. However, incorrect detection information causes an increase in the moving distance of ships collecting Sargassum horneri and confusion in the response of related local governments or institutions,so it is very important to minimize false detections when producing Sargassum horneri spatial information. This study applied technology to automatically remove false detection results using the GOCI-II-based Sargassum horneri detection algorithm of the National Ocean Satellite Center (NOSC) of the Korea Hydrographic and Oceanography Agency (KHOA). Based on the results of analyzing the causes of major false detection results, it includes a process of removing linear and sporadic false detections and green algae that occurs in large quantities along the coast of China in spring and summer by considering them as false detections. The technology to automatically remove false detection was applied to the dates when Sargassum horneri occurred from February 24 to June 25, 2022. Visual assessment results were generated using mid-resolution satellite images, qualitative and quantitative evaluations were performed. Linear false detection results were completely removed, and most of the sporadic and green algae false detection results that affected the distribution were removed. Even after the automatic false detection removal process, it was possible to confirm the distribution area of Sargassum horneri compared to the visual assessment results, and the accuracy and precision calculated using the binary classification model averaged 97.73% and 95.4%, respectively. Recall value was very low at 29.03%, which is presumed to be due to the effect of Sargassum horneri movement due to the observation time discrepancy between GOCI-II and mid-resolution satellite images, differences in spatial resolution, location deviation by orthocorrection, and cloud masking. The results of this study's removal of false detections of Sargassum horneri can determine the spatial distribution status in near real-time, but there are limitations in accurately estimating biomass. Therefore, continuous research on upgrading the Sargassum horneri monitoring system must be conducted to use it as data for establishing future Sargassum horneri response plans.