• Smart Structures and Systems
• /
• v.26 no.4
• /
• pp.495-506
• /
• 2020

Monitoring of complex processes faces several challenges mainly due to the lack of relevant sensory information or insufficient elaborated decision-making strategies. These challenges motivate researchers to adopt complex data processing and analysis in order to improve the process representation. This paper presents the development and implementation of quality monitoring framework based on a model-driven approach using embedded artificial intelligence strategies. In this work, the strategies are applied to the supervision of a microfabrication process aiming at showing the great performance of the framework in a very complex system in the manufacturing sector. The procedure involves two methods for modelling a representative quality variable, such as surface roughness. Firstly, the hybrid incremental modelling strategy is applied. Secondly, a generalized fuzzy clustering c-means method is developed. Finally, a comparative study of the behavior of the two models for predicting a quality indicator, represented by surface roughness of manufactured components, is presented for specific manufacturing process. The manufactured part used in this study is a critical structural aerospace component. In addition, the validation and testing are performed at laboratory and industrial levels, demonstrating proper real-time operation for non-linear processes with relatively fast dynamics. The results of this study are very promising in terms of computational efficiency and transfer of knowledge to manufacturing industry.

• The Journal of Pediatrics of Korean Medicine
• /
• v.38 no.2
• /
• pp.32-40
• /
• 2024

Objectives The main aim was to quantify forward head posture using POM Checker®, a postural balance analyzer, among elementary school students. Additionally, the study aimed to investigate whether postural imbalance improved following three sessions of the school doctor program focused on body posture correction. Methods The program was conducted as part of the school doctor program in Korean Medicine, featuring lectures by a designated Korean Medicine doctor at an elementary school. The curriculum covered the importance of maintaining correct posture and included posture correction exercises. Pre- and post-program self-reported surveys were administered, alongside postural measurements taken over three months at one-month intervals. The survey included data on gender, grade, lifestyle habits, and awareness of correct posture. Result Out of 73 participating students, 63 underwent body balance measurements from the upper grades of one elementary school. Survey results revealed significant variations in daily sitting hours and weekly exercise levels. Attendance at lectures increased knowledge about correct posture. Initial measurements of forward head posture categorized 41.0% and 1.6% of participants into caution and risk groups, respectively. After the second measurement, the caution group representation decreased to 3.2%, and by the third measurement, only 1.6% of participants remained in the caution group. Conclusions Improvements in the angle and understanding of forward head posture among elementary school students were observed before and after the Korean Medicine school doctor program. However, posture improvement may be temporary, necessitating consistent follow-up management and monitoring.

• Archives of Plastic Surgery
• /
• v.44 no.3
• /
• pp.223-227
• /
• 2017

Background Carpal tunnel release is one of the most common surgical procedures performed by hand surgeons. The authors created a surgical simulation of open carpal tunnel release utilizing a mobile and rehearsal platform app. This study was performed in order to validate the simulator as an effective training platform for carpal tunnel release. Methods The simulator was evaluated using a number of metrics: construct validity (the ability to identify variability in skill levels), face validity (the perceived ability of the simulator to teach the intended material), content validity (that the simulator was an accurate representation of the intended operation), and acceptability validity (willingness of the desired user group to adopt this method of training). Novices and experts were recruited. Each group was tested, and all participants were assigned an objective score, which served as construct validation. A Likert-scale questionnaire was administered to gauge face, content, and acceptability validity. Results Twenty novices and 10 experts were recruited for this study. The objective performance scores from the expert group were significantly higher than those of the novice group, with surgeons scoring a median of 74% and medical students scoring a median of 45%. The questionnaire responses indicated face, content, and acceptability validation. Conclusions This mobile-based surgical simulation platform provides step-by-step instruction for a variety of surgical procedures. The findings of this study help to demonstrate its utility as a learning tool, as we confirmed construct, face, content, and acceptability validity for carpal tunnel release. This easy-to-use educational tool may help bring surgical education to a new- and highly mobile-level.

• Korean Journal of Oriental Medicine
• /
• v.18 no.3
• /
• pp.133-139
• /
• 2012

Objective : UMLS is 'Ontology' which establishes the database for medical terminology by gathering various medical vocabularies representing same fundamental concepts. Method : Although Chinese character are represented in the Chinese part of Korean Unicode system in a computer, writing of Chinese characters is vary depending on Chinese input systems and Chinese writers' levels of knowledge. As the result of this, representation of Chinese writing in a computer will be considerably different from an old Chinese document. Therefore, a meaningful relationship between digital Chinese terminology and translated Korean is necessary in order to build Ontology for Chinese medical terms from Oriental medical prescription in a computer system. Result : This research will present 1:1 mapping information among the Chinese characters used in the Oriental medical prescription with analysis of 'same character different sound' and 'same meaning different shape' in Chinese part of Unicode systems. Conclusions : Furthermore, the research will provide top-down menu of relationship between Chinese term and Korean term in medical prescription with assumption of that the Oriental medical prescription has its own unique meaning.

• Nuclear Engineering and Technology
• /
• v.52 no.7
• /
• pp.1429-1435
• /
• 2020

Applying an accurate parametric prediction model to identify abnormal or false pressurizer water levels (PWLs) is critical to the safe operation of marine pressurized water reactors (PWRs). Recently, deep-learning-based models have proved to be a powerful feature extractor to perform high-accuracy prediction. However, the effectiveness of models still suffers from two issues in PWL prediction: the correlations shifting over time between PWL and other feature parameters, and the example imbalance between fluctuation examples (minority) and stable examples (majority). To address these problems, we propose a cost-sensitive mechanism to facilitate the model to learn the feature representation of later examples and fluctuation examples. By weighting the standard mean square error loss with a cost-sensitive factor, we develop a Cost-Sensitive Long Short-Term Memory (CSLSTM) model to predict the PWL of PWRs. The overall performance of the CSLSTM is assessed by a variety of evaluation metrics with the experimental data collected from a marine PWR simulator. The comparisons with the Long Short-Term Memory (LSTM) model and the Support Vector Regression (SVR) model demonstrate the effectiveness of the CSLSTM.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.4
• /
• pp.1730-1747
• /
• 2018

Multi-view video plus depth (MVD) is a mainstream format of 3D scene representation in free viewpoint video systems. The advanced 3D extension of the high efficiency video coding (3D-HEVC) standard introduces new prediction tools to improve the coding performance of depth video. However, the depth video in 3D-HEVC is time consuming. To reduce the complexity of the depth video inter coding, we propose a fast coding unit (CU) size and mode decision algorithm. First, an off-line trained Bayesian model is built which the feature vector contains the depth levels of the corresponding spatial, temporal, and inter-component (texture-depth) neighboring largest CUs (LCUs). Then, the model is used to predict the depth level of the current LCU, and terminate the CU recursive splitting process. Finally, the CU mode search process is early terminated by making use of the mode correlation of spatial, inter-component (texture-depth), and inter-view neighboring CUs. Compared to the 3D-HEVC reference software HTM-10.0, the proposed algorithm reduces the encoding time of depth video and the total encoding time by 65.03% and 41.04% on average, respectively, with negligible quality degradation of the synthesized virtual view.

• Structural Engineering and Mechanics
• /
• v.68 no.6
• /
• pp.747-760
• /
• 2018

In the present study, a methodology for developing fragilities of arch concrete dams to assess their performance against seismic hazards is introduced. Firstly, the probability risk and fragility curves are presented, followed by implementation and representation of the way this method is used. Amirkabir arch concrete dam was subjected to non-linear dynamic analyses. A modified three dimensional rotating smeared crack model was used to take the nonlinear behavior of mass concrete into account. The proposed model considers major characteristics of mass concrete. These characteristics are pre-softening behavior, softening initiation criteria, fracture energy conservation, suitable damping mechanism and strain rate effect. In the present analysis, complete fluid-structure interaction is included to account for appropriate fluid compressibility and absorptive reservoir boundary conditions. In this study, the Amirkabir arch concrete dam is subjected to a set of 8 three-component earthquakes each scaled to 10 increasing intensity levels. Using proposed nonlinear smeared crack model, nonlinear analysis is performed where the structure is subjected to a large set of scaled and un-scaled ground motions and the maximum responses are extracted for each one and plotted. Based on the results, fragility curves were plotted according to various and possible damages indexes. Discrete damage probabilities were calculated using statistical methods for each considered performance level and incremental nonlinear analysis. Then, fragility curves were constructed based on the lognormal distribution assumption. Two damage indexes were introduced and compared to one another. The results indicate that the dam has a proper stability under earthquake conditions at MCE level. Moreover, displacement damages index is more conservative and impractical in the fragility analysis than tensional damage index.

• Journal of the Korea Convergence Society
• /
• v.9 no.1
• /
• pp.405-418
• /
• 2018

This paper was carried out to provide basic data for career search of the free school system. Putting the goal of career education into cultivating expertise, the review was made on the results of the previous studies on the requirements of professional practice. However, As the controversy over the requirements of professional practice has not been solved, so the core elements related to expert performance were examined as a whole through a fundamental cognitive mechanism from which diverse human cognitive characteristics appear. The results show that expert domains consists of content and representation that can exist in an integrated to a great variety of combinations between the two or independent manner, and each domain or field expert performance require different levels of the elements such as intelligence, internal thinking, curiosity (motivation), and obsession (task commitment); and the birth of 1% experts in a domain or field is determined by the obsession. Based on the results, this paper discusses issues related to professionalism and provides a concrete approach to career search during the free semester.

• International conference on construction engineering and project management
• /
• 2011.02a
• /
• pp.299-303
• /
• 2011

Congestion is a growing concern of many global cities and the demands on Infrastructure services within a locale coupled by the rising expectations from the growing population places stress on these cities. This entails the ability to build a sustainable community that requires an understanding and recognition of Population growth, changing demographics and the ever changing urban development on both a macro and micro level. Infrastructure is an integral part of Australian economy, particularly the 'Infrastructure Assets Management' which highlights the importance towards the development of sustainable communities for Melbourne's future. Melbourne 2030 is a comprehensive representation of government's response to a wide-ranging population growth within Melbourne metropolitan and surrounding areas. Urban plan and specific Infrastructure Assets Planning needs not only to provide sufficient Infrastructure to a community, but it must also be efficient and innovative so that it produces an optimised management system. A system that incorporates engineering techniques that will be sustainable for decades to come by maintaining an acceptable level of services to its intended community in an effective manner, which also strengthens service delivery. The fundamental challenges for optimization of Infrastructure with the Melbourne urban plan is, the ability to manage and sustain maintenance of Infrastructure to provide the acceptable level of service required by the community in a most effective manner which also strengthens service delivery to contribute towards Melbourne 2030. This paper particularly investigates some of the fundamental issues within the Melbourne urban plan such as Infrastructure Asset Management, AusLink and the Australian Road Management Act 2004, which the Governments at all levels must deal with to provide an economically viable solution to the changing Infrastructure so it may suits the needs and services the strategies of a metropolis.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.1
• /
• pp.144-150
• /
• 2017

Recently, deep learning is used for intelligent processing and accuracy improvement of data. It is formed calculation model composed of multi data processing layer that train the data representation through an abstraction of the various levels. A category of deep learning, convolution neural network is utilized in various research fields, which are human pose estimation, face recognition, image classification, speech recognition. When using the deep layer and lots of class, CNN that show a good performance on image classification obtain higher classification rate but occur the overfitting problem, when using a few data. So, we design the training network based on convolution neural network and trained our image data set for object classification in few class problem. The experiment show the higher classification rate of 7.06% in average than the previous networks designed to classify the object in 1000 class problem.