• Journal of International Academy of Physical Therapy Research
• /
• v.12 no.1
• /
• pp.2261-2266
• /
• 2021

Background: Deep learning related research works on website medical images have been actively conducted in the field of health care, however, articles related to the musculoskeletal system have been introduced insufficiently, deep learning-based studies on classifying orthopedic manual therapy images would also just be entered. Objectives: To create a deep learning model that categorizes cervical mobilization images and establish a web application to find out its clinical utility. Design: Research and development. Methods: Three types of cervical mobilization images (central posteroanterior (CPA) mobilization, unilateral posteroanterior (UPA) mobilization, and anteroposterior (AP) mobilization) were obtained using functions of 'Download All Images' and a web crawler. Unnecessary images were filtered from 'Auslogics Duplicate File Finder' to obtain the final 144 data (CPA=62, UPA=46, AP=36). Training classified into 3 classes was conducted in Teachable Machine. The next procedures, the trained model source was uploaded to the web application cloud integrated development environment (https://ide.goorm.io/) and the frame was built. The trained model was tested in three environments: Teachable Machine File Upload (TMFU), Teachable Machine Webcam (TMW), and Web Service webcam (WSW). Results: In three environments (TMFU, TMW, WSW), the accuracy of CPA mobilization images was 81-96%. The accuracy of the UPA mobilization image was 43~94%, and the accuracy deviation was greater than that of CPA. The accuracy of the AP mobilization image was 65-75%, and the deviation was not large compared to the other groups. In the three environments, the average accuracy of CPA was 92%, and the accuracy of UPA and AP was similar up to 70%. Conclusion: This study suggests that training of images of orthopedic manual therapy using machine learning open software is possible, and that web applications made using this training model can be used clinically.

• The KIPS Transactions:PartD
• /
• v.12D no.2 s.98
• /
• pp.267-274
• /
• 2005

New game softwares usually have much similarities with old one in the sense of properties and procedures. But nevertheless, the development could be duplicated several times without referencing or reusing of others. In addition, because there is no standardized process about the game engine, the products generated by other software development processes are difficult to understand and to reuse. Therefore, the enterprise developing new game software newly analyze and design although it is same process as the old one. This paper proposes the improved process of the game engine, analysis of structures and relations, classification of the class and the module and their combination methods, implementation of storage, and processor model to apply the component based development method to the game engine.

• Clean Technology
• /
• v.8 no.2
• /
• pp.101-110
• /
• 2002

Concurrent development system which includes design, analysis, basic experiment and performance test procedure for rotary atomizing painting equipment was established. Basic design specifications of the equipment parts were determined according to the overall design requirements of painting equipment using conceptual design model. On the basis of derived design specifications, design and analysis procedures was proposed for developing each equipment part. Also proposed are experiment and test methods to investigate the spray and transfer characteristics of designed painting equipment, and their measurement variable, process and evaluation criteria are constructed. The present development system was validated by applying its entire processes to the actual painting equipment.

• Journal of the Korea Concrete Institute
• /
• v.25 no.2
• /
• pp.225-232
• /
• 2013

The recent worldwide trend in construction industry tends to put emphasis on the performance based design which focuses on the suggestion of the performance of final products rather than method and procedures. A proper model should be employed when predicting the concrete strength, which reflects the material age, in order to verify the function of concrete structures and their materials. Accordingly, this paper proposes the concrete strength development constant (${\alpha}_{sc}$) reflecting the characteristics of domestic materials and then evaluates its suitability.

• Journal of Information Technology Applications and Management
• /
• v.20 no.2
• /
• pp.147-160
• /
• 2013

Today, the management environments of intelligence firm are changing the way of production planning and logistics management, and are changing the process of supply chain management system. This paper shows the development of information system software for intelligence enterprises is used in supply chain management for robot engineering industry. Specifically, supply chain management system in this paper has been developed to analyze the impact of multi plant and multi distribution environment, showing the process analysis and system development of hierarchical assembly manufacturing industry. In this paper we consider a production planning and distribution management system of intelligence firm in the supply chain. We focus on a capacitated production resource and distribution volume allocation problem, develop a mixed integer programming model, and propose an efficient heuristic procedure using a genetic algorithm to solve it efficiently. This method makes it possible for the population to reach the feasible approximate solution easily. The proposed regeneration procedures, which evaluate each infeasible chromosome, makes the solution converge to the feasible approximate solution quickly.

• Journal of Radiation Industry
• /
• v.11 no.1
• /
• pp.33-38
• /
• 2017

RI-Biomics technology is advanced convergence technologies that can be measured in real time and track in vivo behavior and metabolism of substances using characteristics of the radioactive isotope. Its application fields are increasing such as drug development, agriculture, development of new materials and their utilization, etc. In addition, according to domestic and international developments and changes in the RI-Biomics environment, RI-Biomics professionals are needed to train continuously. To develop systematic human resources basement and competency-based curriculum, we perform competency modeling of pedagogical perspective to targeted at high-performance on RI-Biomics. Furthermore, we redefine the competency model and verified by industry experts with focus group interviews. In the result, two general competencies and three professional competencies were extracted by interview. Each competencies are organized six sub-competencies and nine sub-competencies. In the finial steps, the same procedures were repeated to obtain the consensus of experts on derived competencies and behavioral objectives. The results of the study are applicable to enhance human resource management and to develop the curriculum for RI-Biomics expert training. It is expected to be used as reference material of long term-planning for RI-Biomics professional.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.4B
• /
• pp.379-387
• /
• 2006

An urban inundation model coupling an one-dimensional stormwater model, SWMM(Storm Water Management Model), and a two-dimensional inundation model was developed to simulate inundation caused by the surcharge of storm sewers in urban areas. The limitation of this model which can not simulate the interaction between drainage systems and surcharged flow was resolved by developing Dual-Drainage inundation analysis model which was based upon hydraulic flow routing procedures for surface flow and pipe flow. The Dual-Drainage inundation analysis model can simulate the effect of complex storm drainage system. The developed model was applied to Dorim, catchment. The computed inundated depth and area have good agreement with the observed data during the flood events. The developed model can help the decision support system of flood control authority for redesigning and constructing flood prevention structures and making the potential inundation zone, and establishing flood-mitigation measures.

• Proceedings of the KOR-KST Conference
• /
• 1996.02a
• /
• pp.59-86
• /
• 1996

Current methods for evaluating unsignalized intersections, and estimating level-of-service (LOS) is determined from efficiency-based criteria such as little or no delay to very long delays. At present, similar procedures to evaluate intersections using safety-based criteria do not exist. The improvement of sight distances at intersections is the most effective way of improving intersection safety. However, a set of procedures is necessary to account for the limitations in current methodology. Such an approach would build upon such methods, but also account for: deficiencies in the current deterministic solution for the determination of intersection sight distances; opportunity for an accident and severity of an accident; and cost-effectiveness of attaining various levels of sight distances. In this research, a model that estimates the degree of safety at two-way stop-controlled intersections is described. Only crossing maneuvers are considered in this study because accidents caused by the crossing maneuvers are the dominate type among intersection accidents. Monte Carlo methods are used to estimate the hazard at an intersection as a function of roadway features and traffic conditions. Driver`s minimum gap acceptance in the crossing vehicles and headway distribution on the major road are used in the crossing vehicles and headway distribution on the major road are used in the model to simulate the real intersectional maneuvers. Other random variables addressed in the model are: traffic speeds; preception-reaction times of both drivers in the crossing vehicles and drivers in oncoming vehicles on the major road; and vehicles on the major roads. The developed model produces the total number of conflicts per year per vehicle and total potential kinetic energy per year per vehicle dissipated during conflicts as measurements of safety at intersections. Based on the results from the developed simulation model, desirable sight distances for various speeds were determined as 350 feet, 450 feet and 550 feet for 40 mph, 50 mph and 60 mph prevailing speed on the major road, respectively. These values are seven to eight percent less than those values recommended by AASHTO. A safety based level-of-service (LOS) is also developed using the results of the simulation model. When the total number of conflicts per vehicle is less than 0.05 at an intersection, the LOS of the intersection is `A' and when the total number of conflicts per vehicle is larger than 0.25 at an intersection, the LOS is `F'. Similarly, when the total hazard per vehicle is less than 350, 000 1b-ft2/sec2, the LOS is `F'. Once evaluation of the current safety at the intersection is complete, a sensitivity analysis can be done by changing one or more input parameters. This will estimate the benefit in terms of time and budget of hazard reduction based upon improving geometric and traffic characteristics at the intersection. This method will also enable traffic engineers in local governments to generate a priority list of intersection improvement projects.

• Korean Journal of Social Welfare
• /
• v.38
• /
• pp.33-67
• /
• 1999

This study is the second phase of the author's larger attempt to investigate the factors affecting housewives' caregiving behavior to their elderly parents-in-law. Specifically, it revises and expands the previous model (1998) and develops a new one by rectifying the three major problems inherent in the previous study: (1) misspecification error; (2) non-equivalent comparison of results between the father-in-law model and mother-in-law model that stems from the inclusion of heterogeneous group of caregivers; (3) measurement problems for the two endogenous variables of eldercare attitude and behavior. To do this, the current study proposes a more comprehensive model by additionally incorporating other salient exogenous variables, renders the comparison of results between the father-in-law and mother-in-law models equivalent by including only homogeneous group of caregivers (i. e., only those housewives whose parents-in-law are both alive), and introduces standardized measurement scales for the endogenous variables. Estimation of the model in terms of maximum likelihood procedures in LISREL8 attests to a better overall performance over the previous model when judged from several criteria such as coefficient of determination, model fit statistics, proportion of significant causal paths, and measurement properties of reliability and validity for the variables. Interpretation of the findings suggests several salient theoretical implications that concern such crucial issues as the inconsistency between eldercare attitude and behavior, patterns of association among the subdimensions of eldercare, and the difference in the antecedents explaining attitude as opposed to behavior of eldercare. In particular, the finding that indicates almost no differences in the determinants between the father-in-law and mother-in-law models suggests a strong case to argue that caregiving behavior to fathers-in-law and mothers-in-law, respectively, is likely to be a uniform phenomenon sharing virtual1y the same antecedents, and that a unified single model is sufficient to account for caregiving behavior to both parties.

• Journal of Korean Society of Transportation
• /
• v.27 no.2
• /
• pp.35-46
• /
• 2009

This paper presents an evaluation index for the supply levels of pedestrian facilities in residential area planning. The pedestrian facility supply levels reveal the quality of a residential area, and can be associated with the resident living standards and satisfaction, pedestrian safety levels, and the effectiveness of the construction cost. This research conducted multifaceted procedures for the index development, and these procedures start first by identifying dominant influencing factors on pedestrian travel demand by reviewing the final reports of site planning in more than eight already-completed residential development sites. Second, based on the Space Syntax model, which was initially developed in the UK by establishing statistical relationships among an integration index, population size (persons/day), and the total development area, this research formulated a set of pedestrian demand estimation models. Then these models were utilized in forming a pedestrian facility supply index by integrating the new models and their results with the available accepted practice in the residential planning sector. This was necessary because planners want to understand the total supply level of pedestrian facilities in a residential area during the initial design stage. Finally, to test the model validity in satisfying pedestrian satisfaction, the research included a resident satisfaction interview, and it was revealed that the evaluation index developed in this research could provide planners and engineers with more promising results. It is therefore anticipated that this research can be of service when designing pedestrian facilities in future residential area planning and design activities.