• Journal of the Korea Safety Management & Science
• /
• v.17 no.4
• /
• pp.87-96
• /
• 2015

This study analyzed the safety management efficiency through input-oriented BCC Model using DEA by making of Models, in which this study selected the number of staff affiliated with the construction site, number of staff members on the construction team, and number of safety personnel as Input Factor, along with the number of disaster victims and zero-accident accomplished hours as output elements, targeting 40-or-so apartment building construction sites which are being built by 3 domestic construction companies. As a result of efficiency, it was 0.643, the number of efficient DMU was 4. In the aspect of returns to scale, 21 construction sites(52.5%) found to be in a state of increasing returns while 14 construction sites(35%) was in a state of Decreasing returns. The reason for inefficiency was found to lie in technical factors in case of 30 construction sites(75%). Lastly, inefficient DMU is in need of 38.9 % and 66% reduction in site personnel and safety personnel. Based on study results, the 29 construction sites accounting for 72.5% of DMU for safety management efficiency evaluation object turned out to do inefficient safety management that doesn't fit the size of each company.

• Environmental Engineering Research
• /
• v.25 no.3
• /
• pp.418-425
• /
• 2020

In this study soft computing techniques including, Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) were investigated for the prediction of Cr(VI) transport efficiency by novel Polymer Inclusion Membranes (PIMs). Transport experiments carried out by varying parameters such as time, film thickness, carrier type, carier rate, plasticizer type, and plasticizer rate. The predictive performance of ANN and ANFIS model was evaluated by using statistical performance criteria such as Root Mean Standard Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R²). Moreover, Sensitivity Analysis (SA) was carried out to investigate the effect of each input on PIMs Cr(VI) removal efficiency. The proposed ANN model presented reliable and valid results, followed by ANFIS model results. RMSE and MAE values were 0.00556, 0.00163 for ANN and 0.00924, 0.00493 for ANFIS model in the prediction of Cr(VI) removal efficiency on testing data sets. The R² values were 0.973 and 0.867 on testing data sets by ANN and ANFIS, respectively. Results show that the ANN-based prediction model performed better than ANFIS. SA demonstrated that time; film thickness; carrier type and plasticizer type are major operating parameters having 33.61%, 26.85%, 21.07% and 8.917% contribution, respectively.

• Proceedings of the KSPS conference
• /
• 2006.05a
• /
• pp.89-93
• /
• 2006

This paper presents ETRI broadcast news speech recognition system. There are two major issues on the broadcast news speech recognition: 1) real-time processing and 2) out-of-vocabulary handling. For real-time processing, we devised the dual decoder architecture. The input speech signal is segmented based on the long-pause between utterances, and each decoder processes the speech segment alternatively. One decoder can start to recognize the current speech segment without waiting for the other decoder to recognize the previous speech segment completely. Thus, the processing delay is not accumulated. For out-of-vocabulary handling, we updated both the vocabulary and the language model, based on the recent news articles on the internet. By updating the language model as well as the vocabulary, we can improve the performance up to 17.2% ERR.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.33-36
• /
• 2002

We implemented a robust Korean broadcast news transcription system for out-of-vocabulary (OOV), tested its performance. The occurrence of OOV words in the input speech is inevitable in large vocabulary continuous speech recognition (LVCSR). The known vocabulary will never be complete due to the existence of for instance neologisms, proper names, and compounds in some languages. The fixed vocabulary and language model of LVCSR system directly face with these OOV words. Therefore our Broadcast news recognition system has an offline OOV update module of language model and vocabulary to solve OOV problem and selects morpheme-based recognition unit (so called, pseudo-morpheme) for OOV robustness.

• Journal of Internet of Things and Convergence
• /
• v.9 no.1
• /
• pp.65-70
• /
• 2023

In this paper, we propose an autonomous driving system using an end-to-end model to improve lane departure and misrecognition of traffic lights in a vision sensor-based system. End-to-end learning can be extended to a variety of environmental conditions. Driving data is collected using a model car based on a vision sensor. Using the collected data, it is composed of existing data and data with outlayers removed. A class was formed with camera image data as input data and speed and steering data as output data, and data learning was performed using an end-to-end model. The reliability of the trained model was verified. Apply the learned end-to-end model to the model car to predict the steering angle with image data. As a result of the learning of the model car, it can be seen that the model with the outlayer removed is improved than the existing model.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.9 no.3
• /
• pp.263-273
• /
• 2007

When a tunnel or an underground structure is excavated in deep geological environments, the failure process is affected and eventually dominated by stress-induced fractures growing preferentially parallel to the excavation boundary. This fracturing is generally referred to as brittle failure by spatting and slabbing. Continuum models with traditional failure criteria such as Hoek-Brown or Mohr-Coulomb criteria have not been successful in prediction of the extent and depth of brittle failure. Instead cohesion weakening and frictional strengthening (CWFS) model is known to predict brittle failure well. In this study, CWFS model was applied to predict the brittle failure around a circular opening observed in physical model experiments. To obtain the input parameters for CWFS model, damage-controlled tests were carried out. The predicted depth and extent of brittle failure using CWFS model were compared to the results of the physical model experiment and numerical simulation using traditional model.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.5
• /
• pp.369-379
• /
• 2017

The purpose of this study was to improve an university tutoring program qualitatively, evaluating and analyzing the case of tutoring program that students attended in order to strengthen their learning competences through CIPP(Context-Input-Process-Product). To do this, a tutoring survey with satisfaction survey was carried out for 90 students who participated in the final reporting meeting among those who joined the tutoring program at the second semester of 2016 year at the B university. In addition, a tutor interim checking workshop was held for the 49 tutors and qualitative analyses were carried out on the reflection papers submitted by students who were involved in the tutoring program. Tutoring program assessments were carried out in terms of several steps and their view points. They were the necessity of tutoring program for the context evaluation, the appropriacy of human-material resources and program planning for the input evaluation, the teaching and learning activity for the process evaluation and the influence, effectiveness, sustainability, transferability for the product evaluation. Survey results showed that the average scores were presented 4.05 for the context evaluation, 3.88 for the input evaluation, 4.08 for the process evaluation and 3.92 for the product evaluation respectively. Similar analysis results were represented from the tutor workshops and the reflection paper analysis results. Learners were satisfied with all the evaluation items, scoring more than the average level. However, it was necessary for the evaluation items that were rated low range to improve the program through detail modification plans.

• Computational Structural Engineering
• /
• v.3 no.4
• /
• pp.143-148
• /
• 1990

The modal parameter estimations of linear multi-degree-of-freedom structural dynamic systems are carried out in time domain. For this purpose, the equation of motion is transformed into the auto regressive and moving average model with auxiliary stochastic input(ARMAX) model. The parameters of the ARMAX model are estimated by using the sequential prediction error method. Then the modal parameters of the system are obtained thereafter. Experimental results are given for a 3-story budding model subject to ground exitations.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10a
• /
• pp.502-506
• /
• 1992

In this study, we proposed the fuzzy modeling method and designed a model-based logic controller for Activated and Sludge Process(A.S.P.) in sewage treatment. The identification of the structure of fuzzy implications is carreid out by use of fuzzy c-means clustering algorithm. And to identify the parameters of fuzzy implications, we used the complex and the least square method. To tune the premise parameters automatically the complex method is implemented. The model-based fuzzy controller is designed by rules generated from the identified A.S.P. fuzzy model. The feasibility of the proposed approach is evaluated through the identification of the fuzzy model to describe an input-output relation of the A.S.P.. The performance of identified model-based fuzzy controller is evaluated through the computer simulations.

• Proceedings of the KSR Conference
• /
• 2001.10a
• /
• pp.35.1-40
• /
• 2001

This study is on the behavior analysis which can define and verify a system requirement through a behavior diagram for High speed rail system. The model considered in this study is limited to the preconditioning control of the control system specification for HSRS. To build an executable model, requirements should be decomposed first into leaf node requirements. The behavior model is composed of input, output, and functions which are linked with leaf node requirements. It is important that a single requirement must specify a single Auction. Using the developed executable model and the traceability between requirements and functions, this study found out a lot of static and dynamic inconsistency, missed and derived requirements. This is to develop and executable behavior model to do functional analysis and be able to verify the integrity of a specification.