• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.35-52
• /
• 2019

As public services are provided in various forms, including e-government, the level of public demand for public service quality is increasing. Although continuous measurement and improvement of the quality of public services is needed to improve the quality of public services, traditional surveys are costly and time-consuming and have limitations. Therefore, there is a need for an analytical technique that can measure the quality of public services quickly and accurately at any time based on the data generated from public services. In this study, we analyzed the quality of public services based on data using process mining techniques for civil licensing services in N city. It is because the N city's building license complaint service can secure data necessary for analysis and can be spread to other institutions through public service quality management. This study conducted process mining on a total of 3678 building license complaint services in N city for two years from January 2014, and identified process maps and departments with high frequency and long processing time. According to the analysis results, there was a case where a department was crowded or relatively few at a certain point in time. In addition, there was a reasonable doubt that the increase in the number of complaints would increase the time required to complete the complaints. According to the analysis results, the time required to complete the complaint was varied from the same day to a year and 146 days. The cumulative frequency of the top four departments of the Sewage Treatment Division, the Waterworks Division, the Urban Design Division, and the Green Growth Division exceeded 50% and the cumulative frequency of the top nine departments exceeded 70%. Higher departments were limited and there was a great deal of unbalanced load among departments. Most complaint services have a variety of different patterns of processes. Research shows that the number of 'complementary' decisions has the greatest impact on the length of a complaint. This is interpreted as a lengthy period until the completion of the entire complaint is required because the 'complement' decision requires a physical period in which the complainant supplements and submits the documents again. In order to solve these problems, it is possible to drastically reduce the overall processing time of the complaints by preparing thoroughly before the filing of the complaints or in the preparation of the complaints, or the 'complementary' decision of other complaints. By clarifying and disclosing the cause and solution of one of the important data in the system, it helps the complainant to prepare in advance and convinces that the documents prepared by the public information will be passed. The transparency of complaints can be sufficiently predictable. Documents prepared by pre-disclosed information are likely to be processed without problems, which not only shortens the processing period but also improves work efficiency by eliminating the need for renegotiation or multiple tasks from the point of view of the processor. The results of this study can be used to find departments with high burdens of civil complaints at certain points of time and to flexibly manage the workforce allocation between departments. In addition, as a result of analyzing the pattern of the departments participating in the consultation by the characteristics of the complaints, it is possible to use it for automation or recommendation when requesting the consultation department. In addition, by using various data generated during the complaint process and using machine learning techniques, the pattern of the complaint process can be found. It can be used for automation / intelligence of civil complaint processing by making this algorithm and applying it to the system. This study is expected to be used to suggest future public service quality improvement through process mining analysis on civil service.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.123-139
• /
• 2019

The job classification system of major job sites differs from site to site and is different from the job classification system of the 'SQF(Sectoral Qualifications Framework)' proposed by the SW field. Therefore, a new job classification system is needed for SW companies, SW job seekers, and job sites to understand. The purpose of this study is to establish a standard job classification system that reflects market demand by analyzing SQF based on job offer information of major job sites and the NCS(National Competency Standards). For this purpose, the association analysis between occupations of major job sites is conducted and the association rule between SQF and occupation is conducted to derive the association rule between occupations. Using this association rule, we proposed an intelligent job classification system based on data mapping the job classification system of major job sites and SQF and job classification system. First, major job sites are selected to obtain information on the job classification system of the SW market. Then We identify ways to collect job information from each site and collect data through open API. Focusing on the relationship between the data, filtering only the job information posted on each job site at the same time, other job information is deleted. Next, we will map the job classification system between job sites using the association rules derived from the association analysis. We will complete the mapping between these market segments, discuss with the experts, further map the SQF, and finally propose a new job classification system. As a result, more than 30,000 job listings were collected in XML format using open API in 'WORKNET,' 'JOBKOREA,' and 'saramin', which are the main job sites in Korea. After filtering out about 900 job postings simultaneously posted on multiple job sites, 800 association rules were derived by applying the Apriori algorithm, which is a frequent pattern mining. Based on 800 related rules, the job classification system of WORKNET, JOBKOREA, and saramin and the SQF job classification system were mapped and classified into 1st and 4th stages. In the new job taxonomy, the first primary class, IT consulting, computer system, network, and security related job system, consisted of three secondary classifications, five tertiary classifications, and five fourth classifications. The second primary classification, the database and the job system related to system operation, consisted of three secondary classifications, three tertiary classifications, and four fourth classifications. The third primary category, Web Planning, Web Programming, Web Design, and Game, was composed of four secondary classifications, nine tertiary classifications, and two fourth classifications. The last primary classification, job systems related to ICT management, computer and communication engineering technology, consisted of three secondary classifications and six tertiary classifications. In particular, the new job classification system has a relatively flexible stage of classification, unlike other existing classification systems. WORKNET divides jobs into third categories, JOBKOREA divides jobs into second categories, and the subdivided jobs into keywords. saramin divided the job into the second classification, and the subdivided the job into keyword form. The newly proposed standard job classification system accepts some keyword-based jobs, and treats some product names as jobs. In the classification system, not only are jobs suspended in the second classification, but there are also jobs that are subdivided into the fourth classification. This reflected the idea that not all jobs could be broken down into the same steps. We also proposed a combination of rules and experts' opinions from market data collected and conducted associative analysis. Therefore, the newly proposed job classification system can be regarded as a data-based intelligent job classification system that reflects the market demand, unlike the existing job classification system. This study is meaningful in that it suggests a new job classification system that reflects market demand by attempting mapping between occupations based on data through the association analysis between occupations rather than intuition of some experts. However, this study has a limitation in that it cannot fully reflect the market demand that changes over time because the data collection point is temporary. As market demands change over time, including seasonal factors and major corporate public recruitment timings, continuous data monitoring and repeated experiments are needed to achieve more accurate matching. The results of this study can be used to suggest the direction of improvement of SQF in the SW industry in the future, and it is expected to be transferred to other industries with the experience of success in the SW industry.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.131-145
• /
• 2020

In line with the trend of industrial innovation, IoT technology utilized in a variety of fields is emerging as a key element in creation of new business models and the provision of user-friendly services through the combination of big data. The accumulated data from devices with the Internet-of-Things (IoT) is being used in many ways to build a convenience-based smart system as it can provide customized intelligent systems through user environment and pattern analysis. Recently, it has been applied to innovation in the public domain and has been using it for smart city and smart transportation, such as solving traffic and crime problems using CCTV. In particular, it is necessary to comprehensively consider the easiness of securing real-time service data and the stability of security when planning underground services or establishing movement amount control information system to enhance citizens' or commuters' convenience in circumstances with the congestion of public transportation such as subways, urban railways, etc. However, previous studies that utilize image data have limitations in reducing the performance of object detection under private issue and abnormal conditions. The IoT device-based sensor data used in this study is free from private issue because it does not require identification for individuals, and can be effectively utilized to build intelligent public services for unspecified people. Especially, sensor data stored by the IoT device need not be identified to an individual, and can be effectively utilized for constructing intelligent public services for many and unspecified people as data free form private issue. We utilize the IoT-based infrared sensor devices for an intelligent pedestrian tracking system in metro service which many people use on a daily basis and temperature data measured by sensors are therein transmitted in real time. The experimental environment for collecting data detected in real time from sensors was established for the equally-spaced midpoints of 4×4 upper parts in the ceiling of subway entrances where the actual movement amount of passengers is high, and it measured the temperature change for objects entering and leaving the detection spots. The measured data have gone through a preprocessing in which the reference values for 16 different areas are set and the difference values between the temperatures in 16 distinct areas and their reference values per unit of time are calculated. This corresponds to the methodology that maximizes movement within the detection area. In addition, the size of the data was increased by 10 times in order to more sensitively reflect the difference in temperature by area. For example, if the temperature data collected from the sensor at a given time were 28.5℃, the data analysis was conducted by changing the value to 285. As above, the data collected from sensors have the characteristics of time series data and image data with 4×4 resolution. Reflecting the characteristics of the measured, preprocessed data, we finally propose a hybrid algorithm that combines CNN in superior performance for image classification and LSTM, especially suitable for analyzing time series data, as referred to CNN-LSTM (Convolutional Neural Network-Long Short Term Memory). In the study, the CNN-LSTM algorithm is used to predict the number of passing persons in one of 4×4 detection areas. We verified the validation of the proposed model by taking performance comparison with other artificial intelligence algorithms such as Multi-Layer Perceptron (MLP), Long Short Term Memory (LSTM) and RNN-LSTM (Recurrent Neural Network-Long Short Term Memory). As a result of the experiment, proposed CNN-LSTM hybrid model compared to MLP, LSTM and RNN-LSTM has the best predictive performance. By utilizing the proposed devices and models, it is expected various metro services will be provided with no illegal issue about the personal information such as real-time monitoring of public transport facilities and emergency situation response services on the basis of congestion. However, the data have been collected by selecting one side of the entrances as the subject of analysis, and the data collected for a short period of time have been applied to the prediction. There exists the limitation that the verification of application in other environments needs to be carried out. In the future, it is expected that more reliability will be provided for the proposed model if experimental data is sufficiently collected in various environments or if learning data is further configured by measuring data in other sensors.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.30 no.1
• /
• pp.14-21
• /
• 2012

The object of the study, Yousang-Dae(流觴臺) and engraved Go broad text on the flat rock in Gangneung-si Yungok-myun Yoodung-ri Baemgol, reveals that the place was for appreciating arts like Yusang Goksu and Taoist hermit's games. three times of detail reconnaissance survey brought about the results as follows. There is a the text, Manwolsan(滿月山) Baegundongcheon(白雲洞天), engraved on the rock in Baegunsa(白雲寺) that had been built by Doun at the first year of King Hungang(in 875) of the United Shilla, became in ruins in the middle of Joseon, and then was rebuilt in 1954. The text is an invaluable evidence indicating that the tradition of Taoist hermit and Sunbee(classical scholars) culture has been generated in Baemgol Valley. According to the 2nd vol. of Donghoseungram(東湖勝覽), the chronicle of Gangneung published by Choi Baeksoon in 1934, there is a record saying that 'Baegunsa in Namjeonhyeon is the classroom where famous teachers like Yulgok Lee Yi or Seongje Choi Ok were teaching' that verifies the historic property of the place. In addition, the management of Nujeong(樓亭) and Dongcheon can be traced through Baegunjeong(白雲亭) constructed by Kim Yoonkyung(金潤卿) in Muo year, the 9th year of Cheoljong(1858) according to Donghoseungram and the completed version of Jeungboyimyoungji(增補臨瀛誌). Also, Baegundongdongcheon(白雲亭洞天), the text engraved on the standing stone across the stream from Yousang-Dae stone, was created 3 years after the Baegunjeong construction in the 12th year of Cheoljong(1861), which refers a symbolic sign closely related with Yousang-Dae. Based on this premise and circumstance, with careful studying the remains of 'Yusang-dae' Goksuro, we discovered that the Sebun-seok(細分石) controling the amount and the speed of moving water and the remains of furrows of Keumbae-soek(擒盃石) and Yubae-gong(留盃孔) containing water stream with cups through the mountain stream and rocks around Yusang-Dae. In addition, as 21 people's names engraved under the statement of 'Oh-Seong(午星)' were discovered on the bottom of the rock, this clearly confirms that the place was one of the main cultural footholds of tasting the arts which have characteristics of Yu-Sang-Gok-Su-Yeon(流觴曲水宴) until the middle of the 20th century. It implies that the arts tasting culture of Sunbees had been inherited centering on Yusang-dae in this particular place until the middle of the 20th century. It is necessary to be studied in depth because the place is a historic and unique cultural place where 'Confucianism, Buddhism, and Zen'were combined together. Based on the result of the study, the identification of 23 people as well as the writer of Yusang-Dae text should be carefully studied in depth in terms of the characteristics of the place through gathering data about appreciation of arts like Yusanggoksu. Likewise, we should make efforts to discover the chess board engraved on the rock described on the documents, thus we should consider to establish plans to recover the original shape of the place, for example, breaking the cement pavement of the road, additional excavation, changing the existing route, and so fourth.

• Journal of Chest Surgery
• /
• v.31 no.5
• /
• pp.472-480
• /
• 1998

We reviewed the surgical results of intracardiac lateral tunnel Fontan procedure for the repair of functional single ventricles. Between 1990 and 1996, 104 patients underwent total cavopulmonary anastomosis. Patients' age and body weight averaged 35.9(range 10 to 173) months and 12.8(range 6.5 to 37.8) kg. Preoperative diagnoses included 18 tricuspid atresias and 53 double inlet ventricles with univentricular atrioventricular connection and 33 other complex lesions. Previous palliative operations were performed in 50 of these patients, including 37 systemic to pulmonary artery shunts, 13 pulmonary artery bandings, 15 surgical atrial septectomies, 2 arterial switch procedures, 2 resections of subaortic conus, 2 repairs of total anomalous pulmonary venous connection and 1 Damus-Stansel-Kaye procedure. In 19 patients bidirectional cavopulmonary shunt operation was performed before the Fontan procedure and in 1 patient a Kawashima procedure was required. Preoperative hemodynamics revealed a mean pulmonary artery pressure of 14.6(range 5 to 28) mmHg, a mean pulmonary vascular resistance of 2.2(range 0.4 to 6.9) wood-unit, a mean pulmonary to systemic flow ratio of 0.9(range 0.3 to 3.0), a mean ventricular end-diastolic pressure of 9.0 (range 3.0 to 21.0) mmHg, and a mean arterial oxygen saturation of 76.0(range 45.6 to 88.0)%. The operative procedure consisted of a longitudinal right atriotomy 2cm lateral to the terminal crest up to the right atrial auricle, followed by the creation of a lateral tunnel connecting the orifices of either the superior caval vein or the right atrial auricle to the inferior caval vein, using a Gore-Tex vascular graft with or without a fenestration. Concomitant procedures at the time of Fontan procedure included 22 pulmonary artery angioplasties, 21 atrial septectomies, 4 atrioventricular valve replacements or repairs, 4 corrections of anomalous pulmonary venous connection, and 3 permanent pacemaker implantations. In 31, a fenestration was created, and in 1 an adjustable communication was made in the lateral tunnel pathway. One lateral tunnel conversion was performed in a patient with recurrent intractable tachyarrhythmia 4 years after the initial atriopulmonary connection. Post-extubation hemodynamic data revealed a mean pulmonary artery pressure of 12.7(range 8 to 21) mmHg, a mean ventricular end-diastolic pressure of 7.6(range 4 to 12) mmHg, and a mean room-air arterial oxygen saturation of 89.9(range 68 to 100) %. The follow-up duration was, on average, 27(range 1 to 85) months. Post-Fontan complications included 11 prolonged pleural effusions, 8 arrhythmias, 9 chylothoraces, 5 of damage to the central nervous system, 5 infectious complications, and 4 of acute renal failure. Seven early(6.7%) and 5 late(4.8%) deaths occured. These results proved that the lateral tunnel Fontan procedure provided excellent hemodynamic improvements with acceptable mortality and morbidity for hearts with various types of functional single ventricle.

• Journal of Chest Surgery
• /
• v.39 no.4 s.261
• /
• pp.269-274
• /
• 2006

Background: Tetralogy of Fallot (TOF) with pulmonary atresia and major aortopulmonary collateral arteries (MAPCAS) is complex lesion with marked heterogeneity of pulmonary blood supply and arborization anomalies. Patients with TOF with PA and MAPCAS have traditionally required multiple staged unifocalization of pulmonary blood supply before undergoing complete repair. In this report, we describe recent change of strategy and the results in our institution. Material and Method: We established surgical stratagies: early correction, central mediastinal approach, initial RV-PA conduit interposition, and aggressive intervention. Between July 1998 and August 2004, 23 patients were surgically treated at our institution. We divided them into 3 groups by initial operation method; group I: one stage total correction, group II: RV-PA conduit and unifocalization, group III: RV-PA conduit interposition only. Result: Mean ages at initial operation in each group were $13.9{\pm}16.0$ months (group 1), $10.4{\pm}15.6$ months (group II), and $7.9{\pm}7.7$ months (group III). True pulmonary arteries were not present in f patient and the pulmonary arteries were confluent in 22 patients. The balloon angioplasty was done in average 1.3 times (range: $1{\sim}6$). There were 4 early deaths relating initial operation, and 1 late death due to incracranial hemorrhage after definitive repair. The operative mortalities of initial procedures in each group were 25.0% (1/4: group I), 20.0% (2/10: group II), and 12.2% (1/9: group III). The causes of operative mortality were hypoxia (2), low cardiac output (1) and sudden cardiac arrest (1). Definitive repair rates in each group were 75% (3/4) in group I, 20% (2/10, fenestration: 2) in group II, and 55.0% (5/9, fenestration: 1) in group III. Conclusion: In patients of TOF with PA and MAPCAS, RV-PA connection as a initial procedure could be performed with relatively low risk, and high rate of definitive repair can be obtained in the help of balloon pulmonary angioplasty. One stage RV-PA connection and unifocalization appeared to be successful in selected patients.

• Radiation Oncology Journal
• /
• v.20 no.3
• /
• pp.237-245
• /
• 2002

Purpose : This study was conducted to evaluate the treatment results, prognostic factors, and complication rates after high dose rate (HDR) brachytherapy in patients with uterine cervix cancer who were treated with curative aim. Materials and Methods : Of 269 cervix cancer patients treated at the department of radiation oncology, Samsung Medical Center from September 1994 to July 1998, the 106 who were treated with radical radio-therapy were analyzed. The median age was 61 years (range 22 to 89). All patients except 4 with carcinoma in situ (CIS) were given external beam radiotherapy (range $30.6\~50.4\;Gy$ to whole pelvis) and HDR brachytherapy. The common regimens of HDR brachytherapy were a total dose of $24\~28\;Gy$ with $6\~7$ fractions to point A at two fractions per week. The median overall treatment time was 55 days (range 44 to 104) in patients given both external beam radiotherapy and HDR brachytherapy. Results : Early responses of radiotherapy were evaluated by gynecologic examination and follow-up MRI 1 month after radiotherapy. Treatment responses were complete remission in 72 patients, partial response in 33 and no response in 1. The overall survival (OS) rate of all patients was $82\%,\;and\;73\%$, and the disease free survival (DFS) rate was $72\%,\;and\;69\%$, at 3, and 5 years, respectively. The pelvic control rate (PCR) was $79\%$ at both 3 and 5 years. According to the FIGO stage,3 and 5 year OS were $100\%\;and\;50\%$ in CIS/IA, $100\%\;and\;100%$ in IB, $83\%\;and\;69\%$ in IIA, $87\%\;and\;80\%$ in IIB, and $62\%\;and\;62\%$ in III, respectively. The 3 year OS in 4 patients with stage IVA was $100\%$. Three-year DFS were $80\%$ in CIS/IA, $88\%$ in IB, $100\%$ in IIA, $64\%$ in IIB, $58\%$ in III, and $75\%$ in IVA. Three-year PCR were $100\%$ in CIS/IA, $94\%$ in IB, $100\%$ in IIA, $84\%$ in IIB, $69\%$ in III, and $50\%$ in IVA. By univariate analysis, FIGO stage and treatment response were significant factors for OS. The significant factors for DFS were age, FIGO stage, treatment response and overall treatment time (OTT). For pelvic control rate, treatment response and OTT were significant factors. By multivariate analysis, FIGO stage had a borderline significance for OS (p=0.0825) and treatment response had a borderline significance for DFS (0=0.0872). A total of 14 patients $(13\%)$ experienced rectal bleeding, which occurred from 3 to 44 months (median, 13 months) after the completion of radiotherapy. Conclusion : HDR brachytherapy protocol of Samsung Medical Center combined with properly optimal external beam pelvic irradiation is a safe and effective treatment for patients with uterine cervix cancer. The authors found that OTT of less than 55 days had a positive impact on pelvic control and survival rate.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.19 no.4
• /
• pp.243-255
• /
• 2014

This study was investigated to estimate the relations between benthic environments and benthic polychaetous community from April 2012 to February 2013. Twenty four stations were selected sequentially with Seomjin River Estuary from the northern part of Gwangyang Bay. The study area could be divided into three characteristic zones based on salinity, water temperature, dissolved oxygen and pH such as Saline Water Zone (SWZ), Brackish Water Zone (BWZ), and Fresh Water Zone (FWZ). Salinity was above 30.0 psu in SWZ, drastically decreased toward inland in BWZ, and nearly zero psu in FWZ. SWZ showed its specific environmental characters like that water temperature fluctuated with little seasonal change and DO showed the lowest values among three zones, and pH maintained as consistent value without seasonal fluctuation. In FWZ, on the other hand, water temperature showed high seasonal fluctuation, DO showed the highest values among three zones, and pH fluctuated greatly. In sedimentary environment, mud, sand and sand/gravel were found as dominant sedimentary deposits in SWZ, BWZ and FWZ, respectively. Organic matter content and AVS in surface sediment were high in SWZ, while Chl-a content high in FWZ. This study area showed a marked environmental difference between FWZ and SWZ as follows: FWZ has coarse sediment and low salinity, low organic matter content, low AVS in FWZ but SWZ has fine sediment and high salinity, high organic matter content and AVS. Species number and mean density of benthic polychaete community was highest in Saline Water Zone (SWZ), drastically decreased in Brackish Water Zone (BWZ), and lowest in Fresh Water Zone (FWZ). Dominant polychates above 5.0% of individual numbers were 6 taxa. Lumbrineris longifolia, Prionospio cirrifera, Tharyx sp. occurred as main dominant species of all study periods, and Hediste sp., Praxillella affinis, Tylorrhynchus sp. dominantly occurred at some seasons. Inhabiting areas of dominant species were separated characteristically. Representative species in SWZ were Lumbrineris longifolia, Tharyx sp., Mediomastus sp.. Wide-appearing species between SWZ and BWZ were Prionospio cirrifera, Heteromastus filiformis, Aricidea sp.. Characteristic species in FWZ were Tylorrhynchus sp. and Hediste sp.. As the results of cluster analysis and nMDS based on the species composition of polychaetous community, unique station groups were established in SWZ and FWZ. Stations in BWZ were sub-divided into several groups with season. Pearson's correlation analysis and PCA between benthic environments and ecological characteristics of polychaetous community showed that salinity, sediment composition, organic content and dissolved oxygen played a role to determine the temporal and spatial distribution of the ecological characteristics as species number, mean density, abundance of main species, and ecological indices.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.23 no.1
• /
• pp.69-74
• /
• 2019

Purpose $^{18}F$-FDOPA using amino acid is particularly attractive for imaging of brain tumors because of the high uptake in tumor tissue and the low uptake in normal brain tissue. But, on the other hand, $^{18}F$-FDG is highly uptake in both tumor tissue and normal brain tissue. The purpose of study is to evaluate comparison of contrasts in $^{18}F$-FDOPA Brain PET/CT and $^{18}F$-FDG Brain PET/CT and to find out optimal scan time by analysis of variation in SUV with the passage of uptake time. Materials and Methods A region of interest of approximately $350mm^2$ at the center of the tumor and cerebellum in 12 patients ($51.4{\pm}12.8yrs$) who $^{18}F$-FDG Brain PET/CT and $^{18}F$-FDOPA Brain PET/CT were examined more than once each. The $SUV_{max}$ was measured, and the $SUV_{max}$ ratio (T/C ratio) of the tumor cerebellum was calculated. In the analysis of SUV, T/C ratio was calculated for each frame after dividing into 15 frames of 2 minutes each using List mode data in 25 patients ($49.{\pm}10.3yrs$). SPSS 21 was used to compare T/C ratio of $^{18}F$-FDOPA and T/C ratio of $^{18}F$-FDG. Results The T/C ratio of $^{18}F$-FDOPA Brain PET/CT was higher than the T/C ratio of $^{18}F$-FDG Brain, and show a significant difference according to a paired t-test(t=-5.214, p=0.000). As a result of analyzing changes in $SUV_{max}$ and T/C ratio, the peak point of $SUV_{max}$ was $5.6{\pm}2.9$ and appeared in the fourth frame (6 to 8 minutes), and the peak of T/C ratio also appeared in the fourth frame (6 to 8 minutes). Taking this into consideration and comparing the existing 10 to 30 minutes image and 6 to 26 minutes image, the $SUV_{max}$ and T/C ratio increased by 0.2 and 0.1 each, compared to the 10 to 30 minutes image for 6 to 26 minutes image. Conclusion From this study, $^{18}F$-FDOPA Brain PET/CT is effective when reading the image, because the T/C ratio of $^{18}F$-FDOPA Brain PET/CT was higher than T/C ratio of $^{18}F$-FDG Brain PET/CT. In addition, in the case of $^{18}F$-FDOPA Brain PET/CT, there was no difference between the existing 10 to 30 minutes image and 6 to 26 minutes image. Through continuous research, we can find possibility of shortening examination time in $^{18}F$-FDOPA Brain PET/CT. Also, we can help physician to accurate reading using additional scan data.

• 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.