• 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 the Korean Institute of Landscape Architecture
• /
• v.42 no.6
• /
• pp.10-20
• /
• 2014

Today, most roof spaces are being designed as places for resting. The use of the roof spaces needs to be raised otherwise, budgeting or costs involved can be wasteful. A well-made plan is needed to increase the use of the roof spaces. The behavior of and preference for roof spaces could differ depending on building usage because the users of these roof spaces can be different. Therefore, this study selected 4 building types depending on usage: public buildings, educational and research buildings, medical buildings, and commercial buildings. Two buildings that created roof spaces per building type were selected. A survey was undertaken of the user experience of roof spaces on the buildings. The behavior and preference of roof spaces depending on building types were analyzed and the results are as follows. The behavior of using roof spaces regarding purpose, motivation, frequency, and average length of stay were different depending on the building types. In terms of purpose, over all four building types, taking a rest was the primary reason for using roof spaces. However, talking and smoking in public buildings, smoking, taking a walk or stretching, and viewing the exterior landscape in educational and research buildings, taking a walk or stretching and talking in medical buildings, taking care of children and talking in commercial buildings were also important reasons for using roof spaces. The preference of roof space components such as plants, paving materials, and facilities were different depending on the building types. In terms of plants, the users of public buildings preferred herbaceous plants and vegetables/aquatic plants more than the users of other building types. The users of medical buildings preferred vegetables/aquatic plants, and the users of commercial buildings preferred arbores, herbaceous plants, and vegetables/aquatic plants more than the users of other building types. This study provides empirical data for the behavior and the preference of roof spaces depending on building types. These findings could provide new insights into how to increase the use of roof spaces.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.30 no.1
• /
• pp.146-158
• /
• 2012

This study aims to discussion the characteristics of location and spatial organization of the Seoul Sajikdan that has significance as one of national ceremonial place in Joseon Dynasty to understand its landscape architectural characteristics. To do this, we studied in two ways; review of historical documents and analysis of the present conditions and photographing, research materials about the form of physical structure. Through these ways, the results are as follows. First, in case of construction, Sajikdan took fundamental shape in Tae-jong 16 year(1416), since then it had been changed during Imjin War, reign of Suk-jong, and Japanese Colonial Era. It took present shape through restoration of Seoul Sajikdan in 1998. Second, in case of location, Sajikdan abuts onto southeastern range of Mt. Inwang that is Wubaekho(右白虎) of inner four mountain(內四山) of Hanyang, and it has a topography of west-high-east-low type. Also its territory is up to Maedong elementary school, the office of Sajik-dong, and a Dangun shrine. Third, in case of spatial organization, Sadan and Jikdan are in harmony of Yin-Yang(陰陽) and arranged in the center. As making Yumun and Sinmun(神門) at the center of four side of Yuwon and Juwon(周垣), they show organization of the Five Elements. And subsidiary buildings are thought that its arrangement was considered functional similarity and use convenience. Finally, in case of spatial component, Danyu structures are Sadan and Jikdan that hold a Sajikdaeje(社稷大祭), Yuwon that surround two altars, and Juwon that is outer fence of Yuwon. Architectures are Sajikdan Jeongmun, Sinsil, and Anhyangcheong. Also Prunus yedoensis, Zelkova serrata, Acer palmatum, are planted, but Pinus densiflora was main species and there needs to be replanted suitably to the site.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.9
• /
• pp.6080-6088
• /
• 2015

The purpose of study is to find difference in the quality of life and related factors according to the employment status. Using data from the fifth National Health and Nutrition Survey, economically active population of 20-69 years old 3,429 participants who said to questions of 'economic activity status' were finally used as analysis subjects in Korea. According to economic activity status, individuals were divided by the six different employment status and their quality of life was inspected using the EQ-5D dimensions and index score as well as analyzing the factors affecting the quality of life. As a result, unemployed compared to full-time workers, had significantly higher needs of four dimensions and Unpaid family workers had in the dimensions of Mobility, Self-care and Usual activities and temporary job had in the dimensions of Self-care and Usual activities. After figuring out life quality factors according to employment status, it was found that compared to full-time workers greater age(${\beta}=-0.089$, p<0.001), more stress(${\beta}=-0.143$, p<0.0001), hyperlipidemia(${\beta}=-0.064$, p<0.0001), stroke, arthritis(${\beta}=-0.160$, p<0.0001), respiratory diseases(${\beta}=-0.055$, p<0.001) and chronic health conditions were more influential to low quality of life for temporary job(${\beta}=-0.034$, p<0.05), day workers(${\beta}=-0.078$, p<0.0001) and unemplyed(${\beta}=-0.052$, p<0.01). The study is reported that it is to find difference in the quality of life and related factors according to the employment status and it is considered to provide basis for health evaluation of utilization in the same field of study.

• Journal of Soil and Groundwater Environment
• /
• v.10 no.4
• /
• pp.1-12
• /
• 2005

Policies regarding to soil quality of the United States, the United Kingdom, the Netherlands, Germany, and Demark were analyzed to suggest Korean policy for improving soil quality concept and it's implementation. All countries met four criteria: I) Soil quality levels of contaminants are indebt to concept of contaminant risk to recipients (human and ecosystem); ii) Any soil quality value can't be a magic number to determine whether a site is contaminated or not. To determine risk of sites, risk assessment of the sites should be followed; iii) Concentrations of contaminants of sites are not always significantly certain to risk of human and ecosystem of the sites; and iv) Soil quality levels are adopted based on land uses and plans. Considering our rooms to improve policies and analysis of the other country reports on their legislations about soil quality levels, our policy implementation could be approached from these directions: i) Our concept for soil quality levels needs to develop in scientific and rational. ii) Soil quality levels and risk assessment should be implemented as determining tools of site contamination in parallel, and iii) Soil quality levels depending on land uses and plans should be developed in debt with rational and scientific concept of risk. Increasing efficacy of Korea policy regarding the soil quality levels would be in dept to applying concepts of SCL (Soil Contamination Level) and SRL (Soil Regulatory Level) developed, implementing soil quality levels and risk assessment of contaminated sites in conjunction, and classifying three distinctions of land uses based on sensitiveness of recipients (human and ecosystem) to contaminants in soil in this research.

• Journal of Korean Society of Transportation
• /
• v.19 no.1
• /
• pp.101-114
• /
• 2001

Transportation enterprises should maintain constant and qualitative operation. Thus, in short period, transportation enterprises don't change supply in accordance with demand. In the result, transportation enterprises don't reduce operation in spite of management deficit at will. In freight transportation type, less-than-truckload(LTL) has more relation with above transportation feature than truckload(TL) does. Because freight transportation supply of TL is more flexible than that of LTL in correspondence of freight transportation demand. Relating to above mention, it appears that shortage of road and freight terminal of LTL is larger than that of TL. Especially in road and freight terminal comparison, shortage of freight terminal is larger than that of road. Shortage of road is the largest in 1990, and improved after-ward. But shortage of freight terminal is serious lately. So freight terminal needs more expansion than road, and shows better investment condition than road. Freight terminal expansion brings road expansion in LTL, on the contrary, freight terminal expansion substitutes freight terminal for road in TL. In transportation revenue, freight terminal's contribution to LTL is larger than that to TL. However, when we adjust quasi-fixed factor - road and freight terminal - to optimal level in the long run, in TL, diseconomies of scale becomes large, but in LTL, economies of scale becomes large. Consequently, it is necessary for TL to make counterplans to activate management of small size enterprises and owner drivers. And LTL should make use of economies of scale by solving the problem, such as nonprofit route, excess of rental freight handling of office, insufficiency of freight terminal, shortage of driver, and unpreparedness of freight insurance.

• Journal of Wetlands Research
• /
• v.12 no.1
• /
• pp.95-103
• /
• 2010

Discharge data examine the process of hydrologic cycle and used significantly in water resource planning and irrigation and flood control planning. However, it needs lots of time and money to get the discharge data. So discharge rating curve is usually used in converting discharge data. Therefore reliability of discharge rating curve absolutely depends on quality of discharge data. Many engineers who study hydrologic engineering make high quality discharge data to develop reliable discharge rating curve. And they carry out research on standard and method of discharge measurement, and equipment improvement. Now various flow meters are utilized to make discharge data in Korea. However, accuracy of equipment and experimental research data from measurement are not enough. In this paper, constant discharge flowed through standard concrete channel, and the velocity is measured using various flow meters. Also Discharge is calculated by measured data to compare and analyze. The equipment for the experiment is Price AA(USGS Type AA Current meter), flow meter, ADC, C2 small current meter, flow tracker, Electromagnetic current meter. The discharge got form various flow meters which are widely used for discharge measurement. The various depths of water were examined and compared such as 0.30 m, 0.35 m, 0.40 m, 0.45 m, 0.50 m, 0.55 m. The experiment progresses a round-measurement on 6-case. Wading measurement(one point method : the 60 % height in surface of the water) was applied to improve creditability and accuracy among measurement methods. USGS Type AA current Meter, Flow Meter, ADC, C2 Small Current meter got the certificate of quality guaranteed. So the results of experiment were used to compare discharge. The Results showed the difference based on USGS Type AA current Meter at average discharge and velocity. Electromagnetic current meter made differences over $\pm$ 10 % and Flow Meter made differences under $\pm$ 10 %. Also ADC, Flow Meter, C2 Small Current meter made differences under $\pm$ 5 %.

• Journal of the Korean Society of Radiology
• /
• v.8 no.4
• /
• pp.189-201
• /
• 2014

The purpose of this study was to survey guardian's opinion on assisting pediatric radiography and their level of awareness of radiation, improving the quality of pediatric radiography. In this study, the recognition was analyzed for 210 parents of child patients in Pusan National University Hospital from August 20 to September 15, 2013. A total of 66.2 percent of the respondents said they had participated in pediatric radiography in the past. The reason why they did is "Radiologist's request", the highest. According to the survey, 84.3 percent said they thought it is necessary to attending patient in pediatric radiography. "The stability of the child" is the reason for it. And respondents who thought there's no need to do that answered back, the reason for this is "Radiologist's work." There was a significant difference on the psychological state for the medical radiation by gender and child age. (p<0.05) In the analysis of recognition for the radiation, there was the significance by gender and education. (p<0.05) Regarding the awareness of the radiation protector, there was a statistical significance in age, gender, child age and education. (p<0.05) Considering the results, pediatric patient's guardians recognized that it is necessary to attend a child on X-ray for their child's stability and accurate exam above all. It must make guardians wear X-ray protector and radiologist should let the guardians recognize the X-ray examination method, before starting pediatric x-ray. It needs to improve the atmosphere of the examination room and to be considered to take visual and auditory approaches in comfort for reducing the children's fear and anxiety.

• Childhood Kidney Diseases
• /
• v.7 no.2
• /
• pp.125-132
• /
• 2003

Purpose : Lipoprotein(a) is a genetically determined risk factor for atherosclerotic vascular disease and is elevated in patients with renal disease. Especially the patients with nephrotic syndrome exhibit excessively high Lp(a) plasma concentrations. Also the patients with end-stage renal disease have elevated Lp(a) levels. But the mechanism underlying this elevation is unclear. Thus, in this study, by measuring the level of serum Lp(a) in common renal diseases in children, we hoped to see whether there would be a change in Lp(a) in renal diseases other than nephrotic syndrome. Then, we figured out its implications, and looked for the factors that affect the Lp(a) concentrations. Methods : A total of 75 patients(34 patients with hematuria of unknown etiology, 10 with hematuria and hypercalciuria, 8 with IgA nephropathy, 8 with poststreptococcal glomerulone phritis, 3 with $Henoch-Sch\"{o}nlein$ nephritis, 7 with urinary tract infection, and 5 with or- thostatic proteinuria) were studied. The control group included 20 patients without renal and liver disease. Serum Lp(a), total protein, and albumin levels, 24-hour urine protein and calcium excretions, creatinine clearance and the number of RBCs and WBCs in the urinary sediment were evaluated. Data analysis was peformed using the Student t-test and a P-value less than 0.05 was considered to be statistically significant. Results : LP(a) was not correlated with 24-hour urine calcium and creatinine. Lp(a) level had a positive correlation with proteinuria and negative correlation with serum albumin and serum protein. Among the common renal diseases in children, Lp(a) was elevated only in orthostatic proteinuria (P<0.05). Conclusion : Lp(a) is correlated with proteinuria, serum protein, and serum albumin, but not with any kind of specific renal disease. Afterward, Lp(a) needs to be assessed in patients with orthostatic proteinuria and its possible role as a prognostic factor could be confirmed.

• Asia pacific journal of information systems
• /
• v.19 no.4
• /
• pp.77-100
• /
• 2009

Information Systems (IS) is an essential tool for any organizations. The last decade has seen an increasing body of knowledge on IS usage. Yet, IS often fails because of its misuse or non-use. In general, decisions regarding the selection of a system, which involve the evaluation of many IS vendors and an enormous initial investment, are made not through the consensus of employees but through the top-down decision making by top managers. In situations where the selected system does not satisfy the needs of the employees, the forced use of the selected IS will only result in their resistance to it. Many organizations have been either integrating dispersed legacy systems such as archipelago or adopting a new ERP (Enterprise Resource Planning) system to enhance employee efficiency. This study examines user resistance prior to the adoption of the selected IS or ERP system. As such, this study identifies the importance of managing organizational resistance that may appear in the pre-adoption context of an integrated IS or ERP system, explores key factors influencing user resistance, and investigates how prior experience with other integrated IS or ERP systems may change the relationship between the affecting factors and user resistance. This study focuses on organizational members' resistance and the affecting factors in the pre-adoption context of an integrated IS or ERP system rather than in the context of an ERP adoption itself or ERP post-adoption. Based on prior literature, this study proposes a research model that considers six key variables, including perceived benefit, system complexity, fitness with existing tasks, attitude toward change, the psychological reactance trait, and perceived IT competence. They are considered as independent variables affecting user resistance toward an integrated IS or ERP system. This study also introduces the concept of prior experience (i.e., whether a user has prior experience with an integrated IS or ERP system) as a moderating variable to examine the impact of perceived benefit and attitude toward change in user resistance. As such, we propose eight hypotheses with respect to the model. For the empirical validation of the hypotheses, we developed relevant instruments for each research variable based on prior literature and surveyed 95 professional researchers and the administrative staff of the Korea Photonics Technology Institute (KOPTI). We examined the organizational characteristics of KOPTI, the reasons behind their adoption of an ERP system, process changes caused by the introduction of the system, and employees' resistance/attitude toward the system at the time of the introduction. The results of the multiple regression analysis suggest that, among the six variables, perceived benefit, complexity, attitude toward change, and the psychological reactance trait significantly influence user resistance. These results further suggest that top management should manage the psychological states of their employees in order to minimize their resistance to the forced IS, even in the new system pre-adoption context. In addition, the moderating variable-prior experience was found to change the strength of the relationship between attitude toward change and system resistance. That is, the effect of attitude toward change in user resistance was significantly stronger in those with prior experience than those with no prior experience. This result implies that those with prior experience should be identified and provided with some type of attitude training or change management programs to minimize their resistance to the adoption of a system. This study contributes to the IS field by providing practical implications for IS practitioners. This study identifies system resistance stimuli of users, focusing on the pre-adoption context in a forced ERP system environment. We have empirically validated the proposed research model by examining several significant factors affecting user resistance against the adoption of an ERP system. In particular, we find a clear and significant role of the moderating variable, prior ERP usage experience, in the relationship between the affecting factors and user resistance. The results of the study suggest the importance of appropriately managing the factors that affect user resistance in organizations that plan to introduce a new ERP system or integrate legacy systems. Moreover, this study offers to practitioners several specific strategies (in particular, the categorization of users by their prior usage experience) for alleviating the resistant behaviors of users in the process of the ERP adoption before a system becomes available to them. Despite the valuable contributions of this study, there are also some limitations which will be discussed in this paper to make the study more complete and consistent.