• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.57-78
• /
• 2023

COVID-19, which started in Wuhan, China in November 2019, spread beyond China in 2020 and spread worldwide in March 2020. It is important to prevent a highly contagious virus like COVID-19 in advance and to actively treat it when confirmed, but it is more important to identify the confirmed fact quickly and prevent its spread since it is a virus that spreads quickly. However, PCR test to check for infection is costly and time consuming, and self-kit test is also easy to access, but the cost of the kit is not easy to receive every time. Therefore, if it is possible to determine whether or not a person is positive for COVID-19 based on the sound of a cough so that anyone can use it easily, anyone can easily check whether or not they are confirmed at anytime, anywhere, and it can have great economic advantages. In this study, an experiment was conducted on a method to identify whether or not COVID-19 was confirmed based on a cough sound. Cough sound features were extracted through MFCC, Mel-Spectrogram, and spectral contrast. For the quality of cough sound, noisy data was deleted through SNR, and only the cough sound was extracted from the voice file through chunk. Since the objective is COVID-19 positive and negative classification, learning was performed through XGBoost, LightGBM, and FCNN algorithms, which are often used for classification, and the results were compared. Additionally, we conducted a comparative experiment on the performance of the model using multidimensional vectors obtained by converting cough sounds into both images and vectors. The experimental results showed that the LightGBM model utilizing features obtained by converting basic information about health status and cough sounds into multidimensional vectors through MFCC, Mel-Spectogram, Spectral contrast, and Spectrogram achieved the highest accuracy of 0.74.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1211-1224
• /
• 2023

Clouds cause many difficult problems in observing land surface phenomena using optical satellites, such as national land observation, disaster response, and change detection. In addition, the presence of clouds affects not only the image processing stage but also the final data quality, so it is necessary to identify and remove them. Therefore, in this study, we developed a new cloud detection technique that automatically performs a series of processes to search and extract the pixels closest to the spectral pattern of clouds in satellite images, select the optimal threshold, and produce a cloud mask based on the threshold. The cloud detection technique largely consists of three steps. In the first step, the process of converting the Digital Number (DN) unit image into top-of-atmosphere reflectance units was performed. In the second step, preprocessing such as Hue-Value-Saturation (HSV) transformation, triangle thresholding, and maximum likelihood classification was applied using the top of the atmosphere reflectance image, and the threshold for generating the initial cloud mask was determined for each image. In the third post-processing step, the noise included in the initial cloud mask created was removed and the cloud boundaries and interior were improved. As experimental data for cloud detection, CAS500-1 L2G images acquired in the Korean Peninsula from April to November, which show the diversity of spatial and seasonal distribution of clouds, were used. To verify the performance of the proposed method, the results generated by a simple thresholding method were compared. As a result of the experiment, compared to the existing method, the proposed method was able to detect clouds more accurately by considering the radiometric characteristics of each image through the preprocessing process. In addition, the results showed that the influence of bright objects (panel roofs, concrete roads, sand, etc.) other than cloud objects was minimized. The proposed method showed more than 30% improved results(F1-score) compared to the existing method but showed limitations in certain images containing snow.

• Journal of Korea Water Resources Association
• /
• v.57 no.3
• /
• pp.181-193
• /
• 2024

The increasing atmospheric imbalance caused by climate change leads to an elevation in precipitation, resulting in a heightened frequency of flooding. Consequently, there is a growing need for technology to detect and monitor these occurrences, especially as the frequency of flooding events rises. To minimize flood damage, continuous monitoring is essential, and flood areas can be detected by the Synthetic Aperture Radar (SAR) imagery, which is not affected by climate conditions. The observed data undergoes a preprocessing step, utilizing a median filter to reduce noise. Classification techniques were employed to classify water bodies and non-water bodies, with the aim of evaluating the effectiveness of each method in flood detection. In this study, the Otsu method and Support Vector Machine (SVM) technique were utilized for the classification of water bodies and non-water bodies. The overall performance of the models was assessed using a Confusion Matrix. The suitability of flood detection was evaluated by comparing the Otsu method, an optimal threshold-based classifier, with SVM, a machine learning technique that minimizes misclassifications through training. The Otsu method demonstrated suitability in delineating boundaries between water and non-water bodies but exhibited a higher rate of misclassifications due to the influence of mixed substances. Conversely, the use of SVM resulted in a lower false positive rate and proved less sensitive to mixed substances. Consequently, SVM exhibited higher accuracy under conditions excluding flooding. While the Otsu method showed slightly higher accuracy in flood conditions compared to SVM, the difference in accuracy was less than 5% (Otsu: 0.93, SVM: 0.90). However, in pre-flooding and post-flooding conditions, the accuracy difference was more than 15%, indicating that SVM is more suitable for water body and flood detection (Otsu: 0.77, SVM: 0.92). Based on the findings of this study, it is anticipated that more accurate detection of water bodies and floods could contribute to minimizing flood-related damages and losses.

• Clinics in Shoulder and Elbow
• /
• v.15 no.2
• /
• pp.130-137
• /
• 2012

Purpose: To evaluate and report the clinical outcome after surgical treatment of intra-articular comminuted fracture of distal humerus in the elderly with osteoporosis. Materials and Methods: From January 2007 to October 2009, 24 patients aged older than 65 years with intra-articular comminuted fracture of distal humerus underwent surgical treatment. 18 patients (Group I) were managed using primary open reduction and internal fixation (OR IF) through the modified posterior approach and 6 patients (Group II) were taken primary total elbow arthroplasty. The average follow up period was 17.2 months. According to the AO classification, there were 8 C2, 16 C3 type fractures. All enrolled patients were evaluated radiographically and clinically. Clinical outcomes were assessed with the Mayo Elbow Performance, Disabilities of Arm and Shoulder and Hand, and Musculoskeletal Functional Assessment functional questionnaires. Results: The bony union was observed in 18 patients in group I at average 14 weeks. There were 2 patients with neurapraxia of whom the ulnar nerve symptom did not improve despite of anterior transposition. And non-union at osteotomy sites was seen in 2 patients. The mean Mayo Elbow Performance score was 87.0. The mean DASH score was 32.4. The average arc of elbow flexion was $121.0^{\circ}$ (range, $95{\sim}145^{\circ}$) with mean flexion-contracture of $12.0^{\circ}$ (range, 0 to 35). 6 patients in Group II showed no complication during follow up periods. The mean Mayo Elbow Performance score was 89.1. The mean DASH score was 44.3. The average arc of elbow flexion was $125.1^{\circ}$ (range, $100{\sim}145^{\circ}$) with mean flexion-contracture of $12.6^{\circ}$ (range, 0 to 30). Conclusions: With careful patient selection, Total elbow arthroplasty as well as OR IF could achieve good outcomes in elderly of comminuted intra-articular distal humerus fracture with osteoporosis.

• Korean Journal of Construction Engineering and Management
• /
• v.16 no.1
• /
• pp.52-63
• /
• 2015

Business facilities among domestic architectures have rapidly been constructed along with domestic economic development. It is an important facility taking the second largest proportion next to apartment buildings among current 31 building types of fire department classification of 2012 year for urban architectures. The expected service life of business facilities is 15 years, but 70% of those in urban areas have surpassed the 15 year service life as of the present 2014. Thus, the demand for urgent rehabilitation of such facilities is constantly increasing due to the aging and performance deterioration of the facilities'main finishing materials. Especially, the business facilities are being used for the lease of company office or private office, and such problems as aging and performance deterioration of the facilities could cause less competitive edge for leasing and real estate value depreciation for the O&M (Operation & Management) agent and the owner, respectively. Therefore, an effective planned rehabilitation as a preventive measure according to the standardized repair rate by the number of years after the construction is in need in order to prevent the aging and performance deterioration of the facilities(La et al. 2001). Nonetheless, domestic repair/rehabilitation standards based on the repair rate are mainly limited to apartment buildings and pubic institutions, resulting in impractical application of such standards to business facilities. It has been investigated and analyzed that annual repair rate data for each finishing material are required for examination of the applicability of the repair rate standard for the purpose of establishment of a repair plan. Hence, this study aimed at developing a repair rate computation model for finishing materials of the facilities and verifying the appropriateness of the annual repair rate for each finishing material through a case study after collecting and analyzing the repair history data of six business facilities. The results of this study are expected to contribute to the planning and implementation of more efficient repair/rehabilitation budget by preventing the waste of unpredicted repair cost and opportunity cost for the sake of the business facilities' owners and O&M agents.

• Journal of Korean Society of Forest Science
• /
• v.107 no.1
• /
• pp.96-107
• /
• 2018

This study analyzed the linkage between the Forestry sector Official Development Assistance (ODA) Project in South Korea and the Sustainable Development Goals (SDGs) of United Nations (UN), Suggested direction of ODA project focusing on the implementation of the SDGs. Forestry sector ODA project data in South Korea have collected from Economic Development Cooperation Fund (EDCF) statistical inquiry system developed by The Export-Import Bank of Korea. According to the analysis result, Forestry sector ODA project in South Korea have been actively implemented in the fields of forestry development, forestry policy and administration. In both fields, Korea Forest Service and Korea International Cooperation Agency (KOICA) carried out the most projects. The Forestry sector ODA project data in South Korea are classified technical development, capacity building, construction of infrastructure and afforestation based on their objectives and contents. SDGs emphasizes the importance of national implementation assessment and this study analyze linkage between ODA activity content in each classification item and 2016 Korea Forest Service Performance Management Plan indicator. Analyzed the 2016 Korea Forest Service Performance Management Plan indicator and SDGs target and SDGs indicator were identified. finally, SDGs goals were recognized. In conclusion, Forestry sector ODA project in South Korea are associated with the SDGs Goal 1 (No Poverty), Goal 2 (Zero Hunger), Goal 6 (Clean Water and Sanitation), Goal 13 (Climate Action), Goal 15 (Life on Land) and Goal 17 (Partnership for The Goals). Therefore, With the launch of the SDGs, This study analyzed the linkage among the Forestry sector ODA Project in South Korea, the 2016 Korea Forest Service Performance Management Plan and the SDGs. it presented the limitations of Forestry sector ODA Project in South Korea and made proposals for the implementation of the SDGs.

• Radiation Oncology Journal
• /
• v.12 no.2
• /
• pp.175-184
• /
• 1994

From March 1983 through January 1990, two hundred sixty six patients with non-small cell lung cancer were treated with external radiation therapy at the Department of Therapeutic Radiology, Kangnam St. Mary's Hospital, Catholic University Medical College. A retrospective analysis was performed on eligible 116 patients who had been treated with radiation dose over 40 Gy and had been able to be followed up. There were 104 men and 12 women. The age ranged from 33 years to 80 years (median ; 53 years). Median follow up period was 18.8 months ranging from 2 months to 78 months. According to AJC staging system, there were 18($15.5\%$) patients in stage II, 79($68.1\%$) patients in stage III and 19($16.4\%$) patients in stage IV. The Pathologic classification showed 72($62.8\%$) squamous cell carcinomas, 16($13.8\%$) adenocarcinomas, 7($6\%$) large cell carcinomas, 5($4\%$) undifferentiated carcinomas, and 16($13.8\%$) un-known histology. In Karnofsky performance status, six ($5.2\%$) patients were in range below 50, 12($10.4\%$) patients between 50 and 60, 46($39.6\%$) patients between 60 and 70, 50($44.0\%$) patients between 70 and 80 and only one ($0.8\%$) patient was in the range over 80. Sixty ($51.7\%$) patients were treated with radiation therapy (RT) alone. Thirty three ($28.4\%$) patients were treated in combination RT and chemotherapy, twenty three ($19.8\%$) patients were treated with surgery followed by postoperative adjuvant RT and of 23 Patients above, five ($4.3\%$) patients, were treated with postoperative RT and chemotherapy. Overall response according to follow-up chest X-ray and chest CT scans was noted in $92.5\%$ at post RT 3 months. We observed that overall survival rates at 1 year were $38.9\%$ in stage II, $27.8\%$ in stage III, and $11.5\%$ in stage IV, and 2 year overall survival rates were $11.1\%$ in stage II, $20.8\%$ in stage III and $10.5\%$ in stage IV, respectively. We evaluated the performance status, radiation dose, age, type of histology, and the combination of chemotherapy and/or surgery to see the influence on the results fellowing radiation therapy as prognostic factors. Of these factors, only performance status and response after radiation therapy showed statistical significance (P<0.05)

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.1-23
• /
• 2018

From the 21st century, various high-quality services have come up with the growth of the internet or 'Information and Communication Technologies'. Especially, the scale of E-commerce industry in which Amazon and E-bay are standing out is exploding in a large way. As E-commerce grows, Customers could get what they want to buy easily while comparing various products because more products have been registered at online shopping malls. However, a problem has arisen with the growth of E-commerce. As too many products have been registered, it has become difficult for customers to search what they really need in the flood of products. When customers search for desired products with a generalized keyword, too many products have come out as a result. On the contrary, few products have been searched if customers type in details of products because concrete product-attributes have been registered rarely. In this situation, recognizing texts in images automatically with a machine can be a solution. Because bulk of product details are written in catalogs as image format, most of product information are not searched with text inputs in the current text-based searching system. It means if information in images can be converted to text format, customers can search products with product-details, which make them shop more conveniently. There are various existing OCR(Optical Character Recognition) programs which can recognize texts in images. But existing OCR programs are hard to be applied to catalog because they have problems in recognizing texts in certain circumstances, like texts are not big enough or fonts are not consistent. Therefore, this research suggests the way to recognize keywords in catalog with the Deep Learning algorithm which is state of the art in image-recognition area from 2010s. Single Shot Multibox Detector(SSD), which is a credited model for object-detection performance, can be used with structures re-designed to take into account the difference of text from object. But there is an issue that SSD model needs a lot of labeled-train data to be trained, because of the characteristic of deep learning algorithms, that it should be trained by supervised-learning. To collect data, we can try labelling location and classification information to texts in catalog manually. But if data are collected manually, many problems would come up. Some keywords would be missed because human can make mistakes while labelling train data. And it becomes too time-consuming to collect train data considering the scale of data needed or costly if a lot of workers are hired to shorten the time. Furthermore, if some specific keywords are needed to be trained, searching images that have the words would be difficult, as well. To solve the data issue, this research developed a program which create train data automatically. This program can make images which have various keywords and pictures like catalog and save location-information of keywords at the same time. With this program, not only data can be collected efficiently, but also the performance of SSD model becomes better. The SSD model recorded 81.99% of recognition rate with 20,000 data created by the program. Moreover, this research had an efficiency test of SSD model according to data differences to analyze what feature of data exert influence upon the performance of recognizing texts in images. As a result, it is figured out that the number of labeled keywords, the addition of overlapped keyword label, the existence of keywords that is not labeled, the spaces among keywords and the differences of background images are related to the performance of SSD model. This test can lead performance improvement of SSD model or other text-recognizing machine based on deep learning algorithm with high-quality data. SSD model which is re-designed to recognize texts in images and the program developed for creating train data are expected to contribute to improvement of searching system in E-commerce. Suppliers can put less time to register keywords for products and customers can search products with product-details which is written on the catalog.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.1-21
• /
• 2020

With the rapid development of artificial intelligence technology, various techniques have been developed to extract meaningful information from unstructured text data which constitutes a large portion of big data. Over the past decades, text mining technologies have been utilized in various industries for practical applications. In the field of business intelligence, it has been employed to discover new market and/or technology opportunities and support rational decision making of business participants. The market information such as market size, market growth rate, and market share is essential for setting companies' business strategies. There has been a continuous demand in various fields for specific product level-market information. However, the information has been generally provided at industry level or broad categories based on classification standards, making it difficult to obtain specific and proper information. In this regard, we propose a new methodology that can estimate the market sizes of product groups at more detailed levels than that of previously offered. We applied Word2Vec algorithm, a neural network based semantic word embedding model, to enable automatic market size estimation from individual companies' product information in a bottom-up manner. The overall process is as follows: First, the data related to product information is collected, refined, and restructured into suitable form for applying Word2Vec model. Next, the preprocessed data is embedded into vector space by Word2Vec and then the product groups are derived by extracting similar products names based on cosine similarity calculation. Finally, the sales data on the extracted products is summated to estimate the market size of the product groups. As an experimental data, text data of product names from Statistics Korea's microdata (345,103 cases) were mapped in multidimensional vector space by Word2Vec training. We performed parameters optimization for training and then applied vector dimension of 300 and window size of 15 as optimized parameters for further experiments. We employed index words of Korean Standard Industry Classification (KSIC) as a product name dataset to more efficiently cluster product groups. The product names which are similar to KSIC indexes were extracted based on cosine similarity. The market size of extracted products as one product category was calculated from individual companies' sales data. The market sizes of 11,654 specific product lines were automatically estimated by the proposed model. For the performance verification, the results were compared with actual market size of some items. The Pearson's correlation coefficient was 0.513. Our approach has several advantages differing from the previous studies. First, text mining and machine learning techniques were applied for the first time on market size estimation, overcoming the limitations of traditional sampling based- or multiple assumption required-methods. In addition, the level of market category can be easily and efficiently adjusted according to the purpose of information use by changing cosine similarity threshold. Furthermore, it has a high potential of practical applications since it can resolve unmet needs for detailed market size information in public and private sectors. Specifically, it can be utilized in technology evaluation and technology commercialization support program conducted by governmental institutions, as well as business strategies consulting and market analysis report publishing by private firms. The limitation of our study is that the presented model needs to be improved in terms of accuracy and reliability. The semantic-based word embedding module can be advanced by giving a proper order in the preprocessed dataset or by combining another algorithm such as Jaccard similarity with Word2Vec. Also, the methods of product group clustering can be changed to other types of unsupervised machine learning algorithm. Our group is currently working on subsequent studies and we expect that it can further improve the performance of the conceptually proposed basic model in this study.

• Journal of the Korea Computer Graphics Society
• /
• v.22 no.3
• /
• pp.21-29
• /
• 2016

Cell segmentation is an important but time-consuming and laborious task in biological image analysis. An automated, robust, and fast method is required to overcome such burdensome processes. These needs are, however, challenging due to various cell shapes, intensity, and incomplete boundaries. A precise cell segmentation will allow to making a pathological diagnosis of tissue samples. A vast body of literature exists on cell segmentation in microscopy images [1]. The majority of existing work is based on input images and predefined feature models only - for example, using a deformable model to extract edge boundaries in the image. Only a handful of recent methods employ data-driven approaches, such as supervised learning. In this paper, we propose a novel data-driven cell segmentation algorithm for bright-field microscopy images. The proposed method minimizes an energy formula defined by two dictionaries - one is for input images and the other is for their manual segmentation results - and a common sparse code, which aims to find the pixel-level classification by deploying the learned dictionaries on new images. In contrast to deformable models, we do not need to know a prior knowledge of objects. We also employed convolutional sparse coding and Alternating Direction of Multiplier Method (ADMM) for fast dictionary learning and energy minimization. Unlike an existing method [1], our method trains both dictionaries concurrently, and is implemented using the GPU device for faster performance.