• Computers and Concrete
• /
• v.15 no.5
• /
• pp.759-770
• /
• 2015

In this study, a multi-layer perceptron neural network (MLPNN) prediction model for compressive strength of the cement mortars has been developed. For purpose of constructing this model, 8 different mixes with 240 specimens of the 2, 7, 28, 56 and 90 days compressive strength experimental results of cement mortars containing fly ash (FA), silica fume (SF) and FA+SF used in training and testing for MLPNN system was gathered from the standard cement tests. The data used in the MLPNN model are arranged in a format of four input parameters that cover the FA, SF, FA+SF and age of samples and an output parameter which is compressive strength of cement mortars. In the model, the training and testing results have shown that MLPNN system has strong potential as a feasible tool for predicting 2, 7, 28, 56 and 90 days compressive strength of cement mortars.

• Journal of the Korean Institute of Navigation
• /
• v.14 no.4
• /
• pp.53-70
• /
• 1990

Much efforts have been made to improve the training education system for last decades. however, it still leaves much room form improving the system. The reason for this is that the have been many changes in given educational conditions, national and international, and that there existed the lack of training facilities on shore and the limits of capacity on the training ship. The existing program adopts a straight-through system of which the course has to be completed at same time, and also forces students to study the course, disregarding their aptitude for sea life. Consequently, the program resulted in frustrating the learning desire of some students and, as a consequence, in deteriorating the quality of the entire training education. This paper aims to develop an efficient training program including curriculla by the literature survey and the teaching and sea experiences on the training ship "HANBADA" and merchant ships, where the authors have been for many years. Compared with the existing one, the new training model suggested in this paper has some advantages as follows : First, the new model adopts multi-state system which consists of various short-term training courses according to each purpose. This system will be helpful for student to find their aptitude for sea life earlier and to understand classes of major subjection shore. Second, the model includes new curriculla which consist of core subjects (for example, navigation, marine operation, marine transportation, watch keeping and nautical English for deck cadets and internal and external combustion engine, auxiliary machinery, electric and electronics and engine maintenance for engine cadets), by incorporating existing 20 subjects in 5 subjects. These curriculla may contribute to embodying the characteristics of training education where the above mentioned subjects must be linked with each other. In order to implement this new training model efficiently and effectively, the following prerequisties must be prepared : $\circled1$ The contents of each subject included in the new model should be systematically developed. $\circled2$ The educational schedule should be adjusted according to the new model.new model.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.55 no.1
• /
• pp.74-81
• /
• 2019

According to the recent presentation by the Korean Maritime Safety Tribunal, about 70% of marine accident occurs from fishing vessel, and 90% of cause of entire marine accidents attributes to human error. As fishing vessels require basic operations, fishing operations, other additional operations and techniques such as fish handling, cultivating excellent marine officer to prevent marine accident and develop industry is very important. A fisheries training ship is still very difficult to satisfy the demand for diversity of fishery training and sense of realism of the industry. As the result of employment expectation by category of business survey targeting 266 marine industry high school graduates who hope to board fishing vessels for the last four years, tuna purse seine was the highest with 132 cadets (49.6%), followed by offshore large purse seine (65 cadets, 22.4%), and tuna long line (35 cadets, 13.2%). The Korea Institute of Maritime and Fisheries Technology (KIMFT) has replaced old jigging and fish pot fishery training ships and proceeded developing and building multi-purpose fisheries training ships considering the demand of industry and the promotion of employment; however, the basic fishing method was set for a tuna purse seine. As a result of seakeeping model test, it can conduct the satisfiable operation at sea state 5, and survive at sea state 8.

• Journal of Distribution Science
• /
• v.17 no.3
• /
• pp.5-19
• /
• 2019

Purpose - The purpose of this research is to investigate the factors contributing to sustainable competitive advantage for multi-level marketing (MLM) firms in Malaysia. The selected variables in this study are company image, product innovation, leadership, distributor rewards system and distributor training system. Research design, data, and methodology - Quantitative research method is employed with collected sample size of 398 respondents using judgmental sampling technique. Normality and reliability test were performed in the first stage utilizing SPSS 22 and Confirmatory Factory Analysis (CFA) and variance analysis were obtained in the subsequent stage, following up with the overall fit of the measurement model, Structural Equation Model (SEM) using AMOS 22 with maximum likelihood estimation to assess the internal consistency, convergent validity and discriminant validity. Results - The research findings show that company image, leadership, distributor rewards system and distributor training system were supported and are factors affecting the sustainable competitive advantage of MLM companies in Malaysia. However, in this study, product innovation was not supported but this result does not depict that it is trivial and inconsequential in maintain sustainable advantage. Conclusion - Companies can build sustainable competitive advantage by focusing on these contributing factors. Several other comments and implications were brought to light and discussed in the paper.

• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1467-1472
• /
• 2018

For the problem that the face image of surveillance video cannot be accurately identified due to the low resolution, this paper proposes a low resolution face recognition solution based on convolutional neural network model. Convolutional Neural Networks (CNN) model for multi-scale input The CNN model for multi-scale input is an improvement over the existing "two-step method" in which low-resolution images are up-sampled using a simple bi-cubic interpolation method. Then, the up sampled image and the high-resolution image are mixed as a model training sample. The CNN model learns the common feature space of the high- and low-resolution images, and then measures the feature similarity through the cosine distance. Finally, the recognition result is given. The experiments on the CMU PIE and Extended Yale B datasets show that the accuracy of the model is better than other comparison methods. Compared with the CMDA_BGE algorithm with the highest recognition rate, the accuracy rate is 2.5%~9.9%.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.9 no.5
• /
• pp.191-197
• /
• 2009

In this paper, multi-variable fuzzy model for efficient combustion control of refuse incineration plant is obtained. First, to obtain model of incineration plant which is complex and nonlinear multi-variable fuzzy modeling is performed. Obtained multi-variable fuzzy model predicts outputs of incinerator almost exactly. Then using multi-variable fuzzy model we can build simulator which is used as operation simulator for building of control strategy and training of operator.

• Nuclear Engineering and Technology
• /
• v.54 no.8
• /
• pp.3027-3033
• /
• 2022

Background: In this study, various types of deep-learning models for predicting in vitro radiosensitivity from gene-expression profiling were compared. Methods: The clonogenic surviving fractions at 2 Gy from previous publications and microarray gene-expression data from the National Cancer Institute-60 cell lines were used to measure the radiosensitivity. Seven different prediction models including three distinct multi-layered perceptrons (MLP), four different convolutional neural networks (CNN) were compared. Folded cross-validation was applied to train and evaluate model performance. The criteria for correct prediction were absolute error < 0.02 or relative error < 10%. The models were compared in terms of prediction accuracy, training time per epoch, training fluctuations, and required calculation resources. Results: The strength of MLP-based models was their fast initial convergence and short training time per epoch. They represented significantly different prediction accuracy depending on the model configuration. The CNN-based models showed relatively high prediction accuracy, low training fluctuations, and a relatively small increase in the memory requirement as the model deepens. Conclusion: Our findings suggest that a CNN-based model with moderate depth would be appropriate when the prediction accuracy is important, and a shallow MLP-based model can be recommended when either the training resources or time are limited.

• Structural Engineering and Mechanics
• /
• v.90 no.2
• /
• pp.189-208
• /
• 2024

Artificial intelligence is one of the efficient methods that can be developed to simulate nonlinear behavior and predict the response of building structures. In this regard, an adaptive method based on optimization algorithms is used to train the TSK model of the fuzzy inference system to estimate the seismic behavior of building structures based on analytical data. The optimization algorithm is implemented to determine the parameters of the TSK model based on the minimization of prediction error for the training data set. The adaptive training is designed on the feedback of the results of previous time steps, in which three training cases of 2, 5, and 10 previous time steps were used. The training data is collected from the results of nonlinear time history analysis under 100 ground motion records with different seismic properties. Also, 10 records were used to test the inference system. The performance of the proposed inference system is evaluated on two 3 and 20-story models of nonlinear steel moment frame. The results show that the inference system of the TSK model by combining the optimization method is an efficient computational method for predicting the response of nonlinear structures. Meanwhile, the multi-vers optimization (MVO) algorithm is more accurate in determining the optimal parameters of the TSK model. Also, the accuracy of the results increases significantly with increasing the number of previous steps.

• Phonetics and Speech Sciences
• /
• v.9 no.2
• /
• pp.95-101
• /
• 2017

This paper proposes a new method to train Deep Neural Network (DNN)-based acoustic models for speech recognition of native and foreign speakers. The proposed method consists of determining multi-set state clusters with various acoustic properties, training a DNN-based acoustic model, and recognizing speech based on the model. In the proposed method, hidden nodes of DNN are shared, but output nodes are separated to accommodate different acoustic properties for native and foreign speech. In an English speech recognition task for speakers of Korean and English respectively, the proposed method is shown to slightly improve recognition accuracy compared to the conventional multi-condition training method.

• International Journal of Contents
• /
• v.16 no.2
• /
• pp.8-18
• /
• 2020

Data is critical in deep learning but the scarcity of data often occurs in research, especially in the preparation of the paired training data. In this paper, document image binarization with unpaired data is studied by introducing adversarial learning, excluding the need for supervised or labeled datasets. However, the simple extension of the previous unpaired training to binarization inevitably leads to poor performance compared to paired data training. Thus, a new deep learning approach is proposed by introducing a multi-diversity of higher quality generated images. In this paper, a two-stage model is proposed that comprises the generative adversarial network (GAN) followed by the U-net network. In the first stage, the GAN uses the unpaired image data to create paired image data. With the second stage, the generated paired image data are passed through the U-net network for binarization. Thus, the trained U-net becomes the binarization model during the testing. The proposed model has been evaluated over the publicly available DIBCO dataset and it outperforms other techniques on unpaired training data. The paper shows the potential of using unpaired data for binarization, for the first time in the literature, which can be further improved to replace paired data training for binarization in the future.