• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.38 no.2
• /
• pp.211-218
• /
• 2014

Recently, software-based programmable logic controller (PLC) systems, which are implemented in standard PLC languages on general hardware, are gaining popularity because they overcome the limitations of classical hardware PLC systems. Another noticeable trend is that the use of integrated development environment (IDE) is becoming important. IDEs can help developers to easily manage the growing complexity of modern control systems. Furthermore, industrial Ethernet, e.g. EtherCAT, is becoming widely accepted as a replacement for conventional fieldbuses in the distributed control domain because it offers favorable features such as short transmission delay, high bandwidth, and low cost. In this paper, we implemented the extension of open source IDE, called Beremiz, for developing EtherCAT-based real-time, synchronized motion control applications. We validated the EtherCAT system management features and the real-time responsiveness of the control function by using commercial EtherCAT drives and evaluation boards.

• Journal of KIISE:Software and Applications
• /
• v.26 no.11
• /
• pp.1372-1380
• /
• 1999

본 논문에서는 자연언어 문장의 객관적 정량적인 질 측정 방법의 구축에 대해 설명하고, 이를 문장 퇴고 시스템의 사례에 적용해 본다. 문장의 질을 평가한다는 것은 본질적으로 주관적이고 정량화가 어려운 작업이기 때문에, 이 과정에서 질의 객관적 계량화가 가능한지 여부가 가장 중요한 문제가 된다. 이 논문에서는 이러한 문제를 해결하기 위해 유전자 알고리즘을 이용한 진화적 접근 방법을 통해 객관적이고 정량적인 질의 측정 공식을 유도하는 방법론을 제시하였다. 이 논문에서 제시한 방법론의 핵심은 간단히 말해서 사람이 행하는 정성적인 판단을, 이에 가장 근접하는 정량적 측정 체계로 전환시키는 것이라고 보면 된다. 이것을 위해 정량화 문제를 문장의 단순 언어 특징들의 변화값을 이용한 최적화 문제로 환원시키고, 다시 이 최적화 문제를 유전자 알고리즘을 이용해 해결함으로써 문제를 효과적으로 해결할 수 있었다. 실험 결과를 보면, 본 논문에서 제시한 최적화 방법은 주어진 훈련용 예제와 검증용 예제 중 각각 99.84%, 99.88%를 만족시키는 해를 찾아내었으므로 정량적 질 평가 공식의 유도에 매우 효과적임을 알 수 있었다. 또한 도출된 측정 공식을 이용해서 실제 퇴고 시스템 평가에 적용한 결과 문장 질의 측정에 매우 유용하게 이용될 수 있음을 알 수 있었다. 이와 같이 질의 정량적 평가가 가능하다는 사실이 갖는 또 한가지 중요한 의미는 최종 사용자의 구매 의사나 개발자의 공학적 의사 결정을 위한 객관적 성능 평가 자료의 제공에 이 방법이 유용하게 사용될 수 있다는 점이다.Abstract This paper describes a method of building a quantitative measure of the quality of natural language sentences, particularly produced by document revision systems. Evaluating the quality of natural language sentences is intrinsically subjective, so what is most important as to the evaluation is whether the quality can be measured objectively. To solve such problem of objective measurability, genetic algorithm, an evolutionary learning method, is employed in this paper. The underlying standpoint of this approach is that building the quality measures is a task of constructing a formulae that produces as close results as can to the qualitative decisions made by humans. For doing this, the problem of measurability has been simply reduced to an optimization problem using the change of the values of simple linguistic parameters found in sentences, and the reduced problem has been solved effectively by the genetic algorithm. Experimental result shows that the optimization task satisfied 99.84% and 99.88% of the given objectives for training and validation samples, respectively, which means the method is quite effective in constructing the quantitative measure of the quality of natural language sentences. The actual evaluation result of a revision system shows that the measure is useful to quantize the quality of sentences. Another important contribution of this measure would be to provide an objective performance evaluation data of natural language systems on a basis of which end-users and developers can make their decision to fit their own needs.

• Korean Journal of Construction Engineering and Management
• /
• v.22 no.5
• /
• pp.86-98
• /
• 2021

In this study, we developed a simulation model for supply chain management of Precast Concrete (PC) based construction. To this end, information on the Factory Production/Site Construction system was collected through literature review and field research, and based on this information, a simulation model was defined by describing the supply chain, entities, resources, and processes. Next, using the Arena simulation software, a simulation model for the PC supply chain was developed by setting model frameworks, data modules, flowchart modules, and animation modules. Finally, verification and validation were performed using five review methodologies such as model check, animation check, extreme value test, average value test, and actual case test to the developed model. As a result, it was found that the model adequately represented the flows and characteristics of the PC supply chain without any logical errors and provided accurate performance evaluation values for the target supply chains. It is expected that the proposed simulation model will faithfully play a role as a performance evaluation platform in the future for developing management techniques in order to optimally operate the PC supply chain.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.10
• /
• pp.397-402
• /
• 2019

Accurately predicting cancer prognosis to provide appropriate treatment strategies for patients is one of the critical challenges in bioinformatics. Many researches have suggested machine learning models to predict patients' outcomes based on their gene expression data. Gene expression data is high-dimensional numerical data containing about 17,000 genes, so traditional researches used feature selection or dimensionality reduction approaches to elevate the performance of prognostic prediction models. These approaches, however, have an issue of making it difficult for the predictive models to grasp any biological interaction between the selected genes because feature selection and model training stages are performed independently. In this paper, we propose a novel two-dimensional image formatting approach for gene expression data to achieve feature selection and prognostic prediction effectively. Node2Vec is exploited to integrate biological interaction network and gene expression data and a convolutional neural network learns the integrated two-dimensional gene expression image data and predicts cancer prognosis. We evaluated our proposed model through double cross-validation and confirmed superior prognostic prediction accuracy to traditional machine learning models based on raw gene expression data. As our proposed approach is able to improve prediction models without loss of information caused by feature selection steps, we expect this will contribute to development of personalized medicine.

• Therapeutic Science for Rehabilitation
• /
• v.10 no.3
• /
• pp.137-149
• /
• 2021

Objective : This study aimed to verify the effectiveness of ICT-Living Lab-based programs to promote the health of elderly residents in small and medium-sized cities, thus, providing basic data for solving the health and quality of life problems faced by modern society. Methods : The tow-month program included 14 elderly individuals visiting senior center located in W City, from October to November 2019. The program was organized by consulting four senior experts and one ICT expert. The program consisted of 10 min for advance assessment, 10 min for preparation activities, 30 min for main activities, and 10 min for finishing, and 60 min for eight sessions over two months, once a week. Results : EQ-5D increased from 0.76 to 0.84, compared to pre-assessment(p=.009^*). EQ-VAS scores increased from 36.43 to 65.71 (p=.001^*). MMSE-DS increased from 21.21 to 24.14 (p=.000^*). SGDS-K decreased from 3.36 to 3.21, but this was not statistically significant (p=.854). Conclusion : The ICT·Living Lab-based program could be used as a basic material for future research as one of the ways to improve health and quality of life by preventing and addressing the problems faced by the elderly in modern society.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.4
• /
• pp.133-142
• /
• 2021

With the recent advancements of deep learning, companies such as smart home, healthcare, and intelligent transportation systems are utilizing its functionality to provide high-quality services for vehicle detection, emergency situation detection, and controlling energy consumption. To provide reliable services in such sensitive systems, deep learning models are required to have high accuracy. In order to develop a deep learning model for analyzing previously mentioned services, developers should utilize the state of the art deep learning models that have already been verified for higher accuracy. The developers can verify the accuracy of the referenced model by validating the model on the dataset. For this validation, the developer needs structural information to document and apply deep learning models, including metadata such as learning dataset, network architecture, and development environments. In this paper, we propose a description language that represents the network architecture of the deep learning model along with its metadata that are necessary to develop a deep learning model. Through the proposed description language, developers can easily verify the accuracy of the referenced deep learning model. Our experiments demonstrate the application scenario of a deep learning description document that focuses on the license plate recognition for the detection of illegally parked vehicles.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.8
• /
• pp.315-324
• /
• 2022

In this paper, we propose KoEPT, a Transformer-based generative model for automatic math word problems solving. A math word problem written in human language which describes everyday situations in a mathematical form. Math word problem solving requires an artificial intelligence model to understand the implied logic within the problem. Therefore, it is being studied variously across the world to improve the language understanding ability of artificial intelligence. In the case of the Korean language, studies so far have mainly attempted to solve problems by classifying them into templates, but there is a limitation in that these techniques are difficult to apply to datasets with high classification difficulty. To solve this problem, this paper used the KoEPT model which uses 'expression' tokens and pointer networks. To measure the performance of this model, the classification difficulty scores of IL, CC, and ALG514, which are existing Korean mathematical sentence problem datasets, were measured, and then the performance of KoEPT was evaluated using 5-fold cross-validation. For the Korean datasets used for evaluation, KoEPT obtained the state-of-the-art(SOTA) performance with 99.1% in CC, which is comparable to the existing SOTA performance, and 89.3% and 80.5% in IL and ALG514, respectively. In addition, as a result of evaluation, KoEPT showed a relatively improved performance for datasets with high classification difficulty. Through an ablation study, we uncovered that the use of the 'expression' tokens and pointer networks contributed to KoEPT's state of being less affected by classification difficulty while obtaining good performance.

• Journal of Nutrition and Health
• /
• v.56 no.4
• /
• pp.391-403
• /
• 2023

Purpose: This study evaluated the validity of a physical activity classification table (PACT) based on total energy expenditure (TEE) and physical activity level (PAL) measured using the doubly labeled water (DLW) method in Korean adults and the elderly. Methods: A total of 141 (male 70, female 71) adults and elderly were included. The reference standards TEE_DLW, PAL_DLW were measured over a 14-day period using DLW. A 24-hour physical activity diary was kept for three days (two days during the week and one day on the weekend). PAL_PACT was calculated by classifying the activity type and intensity using the PACT. PAL_PACT was multiplied by resting energy expenditure measured by indirect calorimetry to estimate TEE_PACT. Results: The mean age of the study participants was 50.5 ± 18.8 years, and the mean body mass index was 23.4 ± 3.3 kg/m². A comparison of TEE_DLW and TEE_PACT by sex and age showed no significant differences. The bias, the difference between TEE_DLW and TEE_PACT, was male 17.3 kcal/day and female -4.5 kcal/day. The percentage of accurate predictions (values within ± 10% of the TEE_DLW) of TEE_PACT was 58.6% in males and 54.9% in females, with the highest prediction values in the age group 40-64 years (70.9%) in males and over 65 years (73.9%) in females. The spearman correlation coefficient (r) between TEE_PACT and TEE_DLW was 0.769, indicating a significant positive correlation (p < 0.001). Conclusion: In this study, the use of a new PACT for calculating TEE and PAL was evaluated as valid. A web version of the software program and a smartphone application need to be developed using PACT to make it easier to apply for research purposes.

• Journal of Aerospace System Engineering
• /
• v.16 no.1
• /
• pp.97-103
• /
• 2022

An aircraft component can only be mounted on an aircraft if it has been certified to have a structural robustness under flight load conditions. Among the major components of the aircraft, a pylon is a structure that connects external equipment such as an engine, and external attachments with the main wing of an aircraft and transmits the loads acting on it to the main structure of the aircraft. In civil aircraft, when there is an incident of fire in the engine area, the pylon prevents the fire from spreading to the wings. This study presents the results of structural static tests performed to verify the structural robustness of a fuel pylon used to mount external fuel tank in an aircraft. In the main text, we present the test set-up diagram consisting of test fixture, hydraulic pressure unit, load control system, and data acquisition equipment used in the structure static test of the fuel pylon. In addition, we introduce the software that controls the load actuator, and provide a test profile for each test load condition. As a result of the structural static test, it was found that the load actuator was properly controlled within the allowable error range in each test, and the reliability of the numerical analysis was verified by comparing the numerical analysis results and the strain obtained from the structural test at the main positions of the test specimen. In conclusion, it was proved that the fuel pylon covered in this study has sufficient structural strength for the required load conditions through structural static tests.

• The Journal of Advanced Prosthodontics
• /
• v.15 no.6
• /
• pp.281-289
• /
• 2023

PURPOSE. This study aimed to predict the positional coordinates of incisor points from the scan data of conventional complete dentures and verify their accuracy. MATERIALS AND METHODS. The standard triangulated language (STL) data of the scanned 100 pairs of complete upper and lower dentures were imported into the computer-aided design software from which the position coordinates of the points corresponding to each landmark of the jaw were obtained. The x, y, and z coordinates of the incisor point (X_P, Y_P, and Z_P) were obtained from the maxillary and mandibular landmark coordinates using regression or calculation formulas, and the accuracy was verified to determine the deviation between the measured and predicted coordinate values. Y_P was obtained in two ways using the hamularincisive-papilla plane (HIP) and facial measurements. Multiple regression analysis was used to predict Z_P. The root mean squared error (RMSE) values were used to verify the accuracy of the X_P and Y_P. The RMSE value was obtained after crossvalidation using the remaining 30 cases of denture STL data to verify the accuracy of Z_P. RESULTS. The RMSE was 2.22 for predicting X_P. When predicting Y_P, the RMSE of the method using the HIP plane and facial measurements was 3.18 and 0.73, respectively. Cross-validation revealed the RMSE to be 1.53. CONCLUSION. Y_P and Z_P could be predicted from anatomical landmarks of the maxillary and mandibular edentulous jaw, suggesting that Y_P could be predicted with better accuracy with the addition of the position of the lower border of the upper lip.