• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.53-65
• /
• 2019

Object tracking is one of important steps to achieve video-based surveillance systems. Object tracking is considered as an essential task similar to object detection and recognition. In order to perform object tracking, various machine learning methods (e.g., least-squares, perceptron and support vector machine) can be applied for different designs of tracking systems. In general, generative methods (e.g., principal component analysis) were utilized due to its simplicity and effectiveness. However, the generative methods were only focused on modeling the target object. Due to this limitation, discriminative methods (e.g., binary classification) were adopted to distinguish the target object and the background. Among the machine learning methods for binary classification, total error rate minimization can be used as one of successful machine learning methods for binary classification. The total error rate minimization can achieve a global minimum due to a quadratic approximation to a step function while other methods (e.g., support vector machine) seek local minima using nonlinear functions (e.g., hinge loss function). Due to this quadratic approximation, the total error rate minimization could obtain appropriate properties in solving optimization problems for binary classification. However, this total error rate minimization was based on a batch mode setting. The batch mode setting can be limited to several applications under offline learning. Due to limited computing resources, offline learning could not handle large scale data sets. Compared to offline learning, online learning can update its solution without storing all training samples in learning process. Due to increment of large scale data sets, online learning becomes one of essential properties for various applications. Since object tracking needs to handle data samples in real time, online learning based total error rate minimization methods are necessary to efficiently address object tracking problems. Due to the need of the online learning, an online learning based total error rate minimization method was developed. However, an approximately reweighted technique was developed. Although the approximation technique is utilized, this online version of the total error rate minimization could achieve good performances in biometric applications. However, this method is assumed that the total error rate minimization can be asymptotically achieved when only the number of training samples is infinite. Although there is the assumption to achieve the total error rate minimization, the approximation issue can continuously accumulate learning errors according to increment of training samples. Due to this reason, the approximated online learning solution can then lead a wrong solution. The wrong solution can make significant errors when it is applied to surveillance systems. In this paper, we propose an exactly reweighted technique to recursively update the solution of the total error rate minimization in online learning manner. Compared to the approximately reweighted online total error rate minimization, an exactly reweighted online total error rate minimization is achieved. The proposed exact online learning method based on the total error rate minimization is then applied to object tracking problems. In our object tracking system, particle filtering is adopted. In particle filtering, our observation model is consisted of both generative and discriminative methods to leverage the advantages between generative and discriminative properties. In our experiments, our proposed object tracking system achieves promising performances on 8 public video sequences over competing object tracking systems. The paired t-test is also reported to evaluate its quality of the results. Our proposed online learning method can be extended under the deep learning architecture which can cover the shallow and deep networks. Moreover, online learning methods, that need the exact reweighting process, can use our proposed reweighting technique. In addition to object tracking, the proposed online learning method can be easily applied to object detection and recognition. Therefore, our proposed methods can contribute to online learning community and object tracking, detection and recognition communities.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.67-88
• /
• 2019

Webtoon is a Korean-style digital comics platform that distributes comics content produced using the characteristic elements of the Internet in a form that can be consumed online. With the recent rapid growth of the webtoon industry and the exponential increase in the supply of webtoon content, the need for effective webtoon content recommendation measures is growing. Webtoons are digital content products that combine pictorial, literary and digital elements. Therefore, webtoons stimulate consumer sentiment by making readers have fun and engaging and empathizing with the situations in which webtoons are produced. In this context, it can be expected that the sentiment that webtoons evoke to consumers will serve as an important criterion for consumers' choice of webtoons. However, there is a lack of research to improve webtoons' recommendation performance by utilizing consumer sentiment. This study is aimed at developing consumer sentiment pattern maps that can support effective recommendations of webtoon content, focusing on consumer sentiments that have not been fully discussed previously. Metadata and consumer sentiments data were collected for 200 works serviced on the Korean webtoon platform 'Naver Webtoon' to conduct this study. 488 sentiment terms were collected for 127 works, excluding those that did not meet the purpose of the analysis. Next, similar or duplicate terms were combined or abstracted in accordance with the bottom-up approach. As a result, we have built webtoons specialized sentiment-index, which are reduced to a total of 63 emotive adjectives. By performing exploratory factor analysis on the constructed sentiment-index, we have derived three important dimensions for classifying webtoon types. The exploratory factor analysis was performed through the Principal Component Analysis (PCA) using varimax factor rotation. The three dimensions were named 'Immersion', 'Touch' and 'Irritant' respectively. Based on this, K-Means clustering was performed and the entire webtoons were classified into four types. Each type was named 'Snack', 'Drama', 'Irritant', and 'Romance'. For each type of webtoon, we wrote webtoon-sentiment 2-Mode network graphs and looked at the characteristics of the sentiment pattern appearing for each type. In addition, through profiling analysis, we were able to derive meaningful strategic implications for each type of webtoon. First, The 'Snack' cluster is a collection of webtoons that are fast-paced and highly entertaining. Many consumers are interested in these webtoons, but they don't rate them well. Also, consumers mostly use simple expressions of sentiment when talking about these webtoons. Webtoons belonging to 'Snack' are expected to appeal to modern people who want to consume content easily and quickly during short travel time, such as commuting time. Secondly, webtoons belonging to 'Drama' are expected to evoke realistic and everyday sentiments rather than exaggerated and light comic ones. When consumers talk about webtoons belonging to a 'Drama' cluster in online, they are found to express a variety of sentiments. It is appropriate to establish an OSMU(One source multi-use) strategy to extend these webtoons to other content such as movies and TV series. Third, the sentiment pattern map of 'Irritant' shows the sentiments that discourage customer interest by stimulating discomfort. Webtoons that evoke these sentiments are hard to get public attention. Artists should pay attention to these sentiments that cause inconvenience to consumers in creating webtoons. Finally, Webtoons belonging to 'Romance' do not evoke a variety of consumer sentiments, but they are interpreted as touching consumers. They are expected to be consumed as 'healing content' targeted at consumers with high levels of stress or mental fatigue in their lives. The results of this study are meaningful in that it identifies the applicability of consumer sentiment in the areas of recommendation and classification of webtoons, and provides guidelines to help members of webtoons' ecosystem better understand consumers and formulate strategies.

• Health Policy and Management
• /
• v.11 no.2
• /
• pp.141-168
• /
• 2001

Healthcare service organizations can apply the cost of quality(COQ) model as a method to evaluate a service quality improvement project such as Total Quality Management (TQM). COQ model has been used to quantify and evaluate the efficiency and effectiveness of TQM project through estimation between cost and benefit in intervention for a quality Improvement to provide satisfied services for a customer, and to identify a non value added process. For estimating cost of quality, We used activities and activity costs based on Activity Based Costing(ABC) system. These procedures let the researchers know whether the process is value-added by each activity, and identify a process to require improvement in TQM project. Through the series of procedures, health care organizations are service organizations can identify a problem in their quality improvement programs, solve the problem, and improve their quality of care for their costumers with optimized cost. The study subject was a quality improvement program of the department of radiology department in a hospital with n bed sizes in Metropolitan Statistical Area (MSA). The principal source of data for developing the COQ model was total cases of retaking shots for diagnoses during five months period from December of the 1998 to April of the 1999 in the department. First of the procedures, for estimating activity based cost of the department of diagnostic radiology, the researchers analyzed total department health insurance claims to identify activities and activity costs using one year period health insurance claims from September of the 1998 to August of the 1999. COQ model in this study applied Simpson & Multher's COQ(SM's COQ) model, and SM's COQ model divided cost of quality into failure cost with external and internal failure cost, and evaluation/prevention cost. The researchers identified contents for cost of quality, defined activities and activity costs for each content with the SM's COQ model, and finally made the formula for estimating activity costs relating to implementing service quality improvement program. The results from the formula for estimating cost of quality were following: 1. The reasons for retaking shots were largely classified into technique, appliances, patients, quality management, non-appliances, doctors, and unclassified. These classifications by reasons were allocated into each office doing re-taking shots. Therefore, total retaking shots categorized by reasons and offices, the researchers identified internal and external failure costs based on these categories. 2. The researchers have developed cost of quality (COQ) model, identified activities by content for cost of quality, assessed activity driving factors and activity contribution rate, and calculated total cost by each content for cost for quality, except for activity cost. 3. According to estimation of cost of quality for retaking shots in department of diagnostic radiology, the failure cost was ￦35,880, evaluation/preventive cost was ￦72,521, two times as much as failure cost. The proportion between internal failure cost and external failure cost in failure cost is similar. The study cannot identify trends on input cost and quality improving in cost of qualify over the time, because the study employs cross-sectional design. Even with this limitation, results of this study are much meaningful. This study shows possibility to evaluate value on the process of TQM subjects using activities and activity costs by ABC system, and this study can objectively evaluate quality improvement program through quantitative comparing input costs with marginal benefits in quality improvement.

• Anxiety and mood
• /
• v.7 no.1
• /
• pp.48-53
• /
• 2011

Objective : Korean Version of Beck-II Depression Inventory to verify the reliability and validity of the proposed standards are practical and standardized, cut-off score by establishing a baseline indicating the presence of depression and depression On in the evaluation was to evaluate the clinical usefulness. Methods : 739 patients with major depression using the SCID and normal controls were 302 study subjects. Of patients with clinically significant medical condition, or psychotic disorders, organic mental disorder, epilepsy or seizure disorder, eating disorders are associated with patients taking anti-convulsants experienced in the past, patients were excluded from the study. Results : The main findings of this study were as follows. First, with respect to the KBDI-II items, the correlation between them ranged from 0.51 to 0.74, and was 0.60 over all questions. Further, the overall correlation of the KBDI-II plates showing confidence 'normal' than it was verified that. Second, the BDIII was used in each group to examine internal consistency and thus, whether Cronbach's alpha values were greater than 0.94. Third, the principal component analysis sought to extract factors in a way consistent with the results inspected last 3 factors were extracted and the total variance explained was 47.3%. Fourth, the Cutting calculated the score on the KBDI-II for ROC (Receiver operator characteristic) analysis yielding 18 dot, with the highest sensitivity and specificity was seen. Conclusion : Based on the results of this Study, the KBDI-II cut-off point should be valid as prescribed in 18 is considered.

• Korean Journal of Remote Sensing
• /
• v.21 no.6
• /
• pp.445-456
• /
• 2005

The land surface parameters should be determined with sufficient accuracy, because these play an important role in climate change near the ground. As the surface reflectance presents strong anisotropy, off-nadir viewing results a strong dependency of observations on the Sun - target - sensor geometry. They contribute to the random noise which is produced by surface angular effects. The principal objective of the study is to provide a database of accurate surface reflectance eliminated the angular effects from MODIS 250m reflective channel data over Korea. The MODIS (Moderate Resolution Imaging Spectroradiometer) sensor has provided visible and near infrared channel reflectance at 250m resolution on a daily basis. The successive analytic processing steps were firstly performed on a per-pixel basis to remove cloudy pixels. And for the geometric distortion, the correction process were performed by the nearest neighbor resampling using 2nd-order polynomial obtained from the geolocation information of MODIS Data set. In order to correct the surface anisotropy effects, this paper attempted the semiempirical kernel-driven Bi- directional Reflectance Distribution Function(BRDF) model. The algorithm yields an inversion of the kernel-driven model to the angular components, such as viewing zenith angle, solar zenith angle, viewing azimuth angle, solar azimuth angle from reflectance observed by satellite. First we consider sets of the model observations comprised with a 31-day period to perform the BRDF model. In the next step, Nadir view reflectance normalization is carried out through the modification of the angular components, separated by BRDF model for each spectral band and each pixel. Modeled reflectance values show a good agreement with measured reflectance values and their RMSE(Root Mean Square Error) was totally about 0.01(maximum=0.03). Finally, we provide a normalized surface reflectance database consisted of 36 images for 2001 over Korea.

• Journal of Korean Classical Literature and Education
• /
• no.32
• /
• pp.193-224
• /
• 2016

The North Korean animation is a puppet movie that is adapted The Brother and Sister Who Became the Sun and the Moon, a traditional Korean lore. The quality of this animation is acknowledged because of not only North Korea's considerably advanced animation technology but also the animation's retention of the folklore's traditional essence rather than intention to disseminate ideological propaganda. Nevertheless, the animation reveals the trasformation of its original purpose from general educative intentions for children to the educative concept of salvation by heaven is replaced by salvation by people and cultural education insteadof salvation by heaven. The appearance of the hero Jangsoe is the key adaptation of this animation, and it suggests the main principal of salvation lies in man rather than in heaven. Such adaptation complies with the requirements of children's literature suggested by the North Korea's literary history office. Furthemore the hero Jangsoe as the examplary figure of revolutionary self-reliance ideology and as a leader. Theory of self-reliance literature stipulates that children's literature is used for ideological education that develops people to be successors of revolutionary feats and become active workers for the construction of socialism and communism, therefore it is possible to understand the purpose of the adaptation to reflect the educational aims. This study investigates the change in meaning form the original folktale through such adaptation, and highlights problems related to limiting the meaning implied in "heaven's salvation" in the original story only to the vague meaning of religious hope. This vague implied meaning is considered as "an awareness activity to examine their own existence in the universe". With regard to this, the concept of heaven's salvation that is prevalent in the classic stories can be interpreted as a positive self-belief that enables the use of rationality in any helpless situation that cannot be understood with existing empirical knowledge. It considers that heaven expresses the power that exists in the human mind through self-viability and self-belief. This creates the power of reason in the character to fight against the evil disguised as the mother, in the absence of the real mother.

• Korean Journal of Environment and Ecology
• /
• v.33 no.5
• /
• pp.515-524
• /
• 2019

The purpose of this study is to investigate the effects of artificial disturbance by analyzing and comparing the survey data of the Yeongju dam located in Yeongju-si, Gyeongbuk before and after impoundment. We surveyed four sites between the downstream of sediment control to the downstream of Yeongju Dam four times between April and October 2018. The macroinvertebrate data before the survey were gathered from the literature. The total number of benthic macroinvertebrates we observed was $35,037ind./m^2$, including 77 species, 48 families, 14 orders, 7 classes, and 3 phyla. The result of the community analysis showed that the dominant index increased from 0.44(${\pm}0.11$) before impoundment to 0.62(${\pm}0.16$) after impoundment. The diversity index increased from 2.26(${\pm}0.30$) to 1.75(${\pm}0.45$), the evenness index from 0.75(${\pm}0.10$) to 0.66(${\pm}0.14$), and the richness index from 3.11(${\pm}0.98$) to 2.25(${\pm}0.81$). The most dominant species changed from Hydropsychidae spp. to Chironomidae sp. The result of the Principal Components Analysis (PCA) based on Axis 1 showed that the sites of 2014 and Hydropsychidae spp. had a negative value, while the sites of 2018 and Chironomidae sp. had a positive value. In all study sites, the dominance increased while the diversity decreased. The community change was the largest in St. 2. The results of the functional group analysis showed that the scrapers increased while gathering-collectors increased among the functional feeding group and that the clingers decreased while borrows increased among the habitat oriented group. The Benthic Macroinvertebrate Streambed Index (BMSI) decreased from an average of 57.1(${\pm}8.0$, C class) to an average of 30.0(${\pm}12.1$, C class). St. 3 and St. 4, in particular, showed a high reduction rate.

• Korean Journal of Plant Taxonomy
• /
• v.34 no.3
• /
• pp.221-244
• /
• 2004

Prunus sargentii complex of subgenus Cerasus is an Eastem Asiatic plant group that exhibits a broad range of morphological variation and includes P. takesimensis, P. yedosensis, P. verecunda, and P. sargentii. In this study, a morphological analysis was undertaken to determine whether the observed morphological variation was primarily attributable to morphological discontinuities among the taxa. P. sargentii, which distributed eastem area in Korea, northern area in Japan and far east Russia had umbel like inflorescence and additionally was characterized by sticky bud and leaf twigs, compared with P. serrulata complex. Also, P. verecunda in Korea and Japan was characterized by umbel like inflorescence and presence of hair in leaf, petiole and pedicel, and was treated as a variety of P. sargentii. Evidence obtained from multivariate morphometric analyses indicated that the entity of P. takesimensis formed a cohesive group somewhat distinct from P. sargenti.. Especially, P. takesimensis was characterized by relatively small flowers (26-32mm in diameter) and many flowers [(2)3-5] per umbel inflorescence, compared with P. sargentii (34-48mm and 2(3) per inflorescence) and should be recognized as an independent and endeImic taxon in Korea. Additionally, P. yedosensis, which was known to have umbel inflorescence (short peduncle type) with pubescent style based on the type specimen, was comprised of corymb inflorescence (long peduncle type) as well. The morphological differentiation between these two types of P. yedosensis was not considered sufficient to warrant recognition of specific status because of the putative hybrid origin, no distinctive geographical distribution pattern, and existence of various peduncle length on Island Jeju-do of Korea.

• The Journal of the Petrological Society of Korea
• /
• v.25 no.3
• /
• pp.195-209
• /
• 2016

The understanding of geometric complexity of strike-slip Fault system can be an important factor to control fault reactivation and surface rupture propagation under the regional stress regime. The Kumamoto earthquake was caused by dextral reactivation of the Futagawa-Hinagu Fault system under the E-W maximum horizontal principal stress. The earthquakes are a set of earthquakes, including a foreshock earthquake with a magnitude 6.2 at the northern tip of the Hinagu Fault on April 14, 2016 and a magnitude 7.0 mainshock which generated at the intersection of the two faults on April 16, 2016. The hypocenters of the main shock and aftershocks have moved toward NE direction along the Futagawa Fault and terminated at Mt. Aso area. The intersection of the two faults has a similar configuration of ${\lambda}$-fault. The geometries and kinematics, of these faults were comparable to the Yansan-Ulsan Fault system in SE Korea. But slip rate is little different. The results of age dating show that the Quaternary faults distributed along the northern segment of the Yangsan Fault and the Ulsan Fault are younger than those along the southern segment of the Yansan Fault. This result is well consistent with the previous study with Column stress model. Thus, the seismic activity along the middle and northern segment of the Yangsan Fault and the Ulsan Fault might be relatively active compared with that of the southern segment of the Yangsan Fault. Therefore, more detailed seismic hazard and paleoseismic studies should be carried out in this area.

• Korean Journal of Soil Science and Fertilizer
• /
• v.44 no.3
• /
• pp.485-491
• /
• 2011

The present study evaluated the soil microbial communities by fatty acid methyl ester (FAME) in upland soils at 25 sites in Gyeongnam Province. The total bacteria content was $143nmol\;g^{-1}$ for in inclined piedmont, $75nmol\;g^{-1}$ for fan and valley, $49nmol\;g^{-1}$ for hill areas, and $44nmol\;g^{-1}$ for riversider plain. The fungi content was 2.4 times higher in sandy loam than $21nmol\;g^{-1}$ in silt loam (p<0.01). In addition, inclined piedmont soils had a significantly higher ratio of monounsaturated fatty acids to saturated fatty acids compared with fan and valley soils (p<0.05). The communities of total bacteria and arbuscular mycorrhizal fungi in the inclined piedmont soils were significantly higher than those in the fan and valley soils and in the riversider plain soils (p<0.05), whereas the community of fungi was significantly lower (p<0.05). In principal component analyses of soil microbial communities, our findings showed that inclined piedmont was positive relationship with total bacteria and actinomycetes in upland soils.