• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.19 no.39
• /
• pp.47-61
• /
• 1996

We propose a parallel neural network model in which patterns are clustered and patterns in a cluster are studied in a parallel neural network. The learning algorithm used in this paper is based on LVQ algorithm of Kohonen(1990) for clustering and ADALINE(Adaptive Linear Neuron) network of Widrow and Hoff(1990) for parallel learning. The proposed algorithm consists of two parts. First, N patterns to be learned are categorized into C clusters by LVQ clustering algorithm. Second, C patterns that was selected from each cluster of C are learned as input pattern of ADALINE(Adaptive Linear Neuron). Data used in this paper consists of 250 patterns of ASCII characters normalized into $8\times16$ and 1124. The proposed algorithm consists of two parts. First, N patterns to be learned are categorized into C clusters by LVQ clustering algorithm. Second, C patterns that was selected from each cluster of C are learned as input pattern of ADALINE(Adaptive Linear Neuron). Data used in this paper consists 250 patterns of ASCII characters normalized into $8\times16$ and 1124 samples acquired from signals generated from 9 car models that passed Inductive Loop Detector(ILD) at 10 points. In ASCII character experiment, 191(179) out of 250 patterns are recognized with 3%(5%) noise and with 1124 car model data. 807 car models were recognized showing 71.8% recognition ratio. This result is 10.2% improvement over backpropagation algorithm.

• Membrane and Water Treatment
• /
• v.13 no.5
• /
• pp.219-225
• /
• 2022

5th Assessment Report of the Intergovernmental Panel on Climate Change Weather (AR5) predicts that recent severe hydrological events will affect the quality of water and increase water pollution. To analyze changes in water quality due to future climate change, input data (precipitation, average temperature, relative humidity, average wind speed, and solar radiation) were compiled into a representative concentration curve (RC), defined using 8.5. AR5 and future use are calculated based on land use. Semi-distributed emission model Calculate emissions for each target period. Meteorological factors affecting water quality (precipitation, temperature, and flow) were input into a multiple linear regression (MLR) model and an artificial neural network (ANN) to analyze the data. Extensive experimental studies of flow properties have been carried out. In addition, an Acoustic Doppler Velocity (ADV) device was used to monitor the flow of a large open channel connection in a wastewater treatment plant in Ho Chi Minh City. Observations were made along different streams at different locations and at different depths. Analysis of measurement data shows average speed profile, aspect ratio, vertical position Measure, and ratio the vertical to bottom distance for maximum speed and water depth. This result indicates that the transport effect of the compound was considered when preparing the hazard analysis.

• Advances in concrete construction
• /
• v.13 no.6
• /
• pp.411-422
• /
• 2022

Aggregates mineralogical, and petrographic properties directly affect the mechanical properties of the produced high strength. This study is focused on the effects of magmatic, sedimentary, and metamorphic aggregates on the performance of high strength concrete. In this study, the effect of the mineralogical properties of aggregates on the compressive strength and modulus of elasticity of high-strength concrete was estimated by Artifical Neural Network (ANN). To estimate the compressive strength and elasticity modules, 96 test specimens were produced. After 28 days under suitable conditions, tests were carried out to determine the compressive strength and modulus of elasticity of the test specimens. This study also focused on the application of artificial neural networks (ANN) to predict the 28-day compressive strength and the modulus of elasticity of high-strength concrete. An ANN model is developed, trained, and tested by using the available test data obtained from the experimental studies. The ANN model is found to predict the modulus of elasticity, and 28 days compressive strength of high strength concrete well, within the ranges of the input parameters. These comparisons show that ANNs have a strong potential to predict the compressive strength and modulus of elasticity of high-strength concrete over the range of input parameters considered.

• Journal of Information Technology Services
• /
• v.17 no.1
• /
• pp.79-89
• /
• 2018

Sentiment analysis is a technique of text mining that extracts feelings of the person who wrote the sentence like movie review. The preliminary researches of sentiment analysis identify sentiments by using the dictionary which contains negative and positive words collected in advance. As researches on deep learning are actively carried out, sentiment analysis using deep learning model with morpheme or word unit has been done. However, this model has disadvantages in that the word dictionary varies according to the domain and the number of morphemes or words gets relatively larger than that of phonemes. Therefore, the size of the dictionary becomes large and the complexity of the model increases accordingly. We construct a sentiment analysis model using recurrent neural network by dividing input data into phoneme-level which is smaller than morpheme-level. To verify the performance, we use 30,000 movie reviews from the Korean biggest portal, Naver. Morpheme-level sentiment analysis model is also implemented and compared. As a result, the phoneme-level sentiment analysis model is superior to that of the morpheme-level, and in particular, the phoneme-level model using LSTM performs better than that of using GRU model. It is expected that Korean text processing based on a phoneme-level model can be applied to various text mining and language models.

• Computers and Concrete
• /
• v.33 no.2
• /
• pp.137-145
• /
• 2024

The technique of experimentally determining concrete's compressive strength for a given mix design is time-consuming and difficult. The goal of the current work is to propose a best working predictive model based on different machine learning algorithms such as Gradient Boosting Machine (GBM), Stacked Ensemble (SE), Distributed Random Forest (DRF), Extremely Randomized Trees (XRT), Generalized Linear Model (GLM), and Deep Learning (DL) that can forecast the compressive strength of ternary geopolymer concrete mix without carrying out any experimental procedure. A geopolymer mix uses supplementary cementitious materials obtained as industrial by-products instead of cement. The input variables used for assessing the best machine learning algorithm not only include individual ingredient quantities, but molarity of the alkali activator and age of testing as well. Myriad statistical parameters used to measure the effectiveness of the models in forecasting the compressive strength of ternary geopolymer concrete mix, it has been found that GBM performs better than all other algorithms. A sensitivity analysis carried out towards the end of the study suggests that GBM model predicts results close to the experimental conditions with an accuracy between 95.6 % to 98.2 % for testing and training datasets.

• Journal of Environmental Science International
• /
• v.9 no.1
• /
• pp.35-42
• /
• 2000

In this study, the movable bed model testing was carried out so as to analyze bed profile changes including predicting scouring and deposition of bed profile and to solve hydraulic problems affecting with bed and both-bank between upstream and downstream of intake weir in the Nakdong river channel. The movable bed model testing consists of fundamental test, movable model test and numerical analysis method respectively. The fundamental test was enforced to analyze relationship of discharge and sediment load in the tilting flume. When the movable model test was worked, it was shown that sediment budget between input sediment load and output sediment load was balanced exactly. As a result of movable model test, it was presented that scouring and deposition changes in quantities between the upstream and downstream of modification weir were less than those of nature and planning weir. Finally, numerical analysis method was operated by 1-dimensional bed profile changes model ; HEC-6 model so as to complement unsolving hard problems during movable model test. So, modification weir will sustained the stable bed profile changes than any other weirs in the study channel.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.17 no.3
• /
• pp.266-273
• /
• 2012

In this paper, the new open fault detection and tolerant operation method for 3 phase PWM rectifier is proposed. When open fault occurred on the inverter switches of 3 Phase PWM rectifier, the DC link voltage ripple is increased because the input current of the faulty phase is distorted. In this case, the quality of electric power would decrease, and the life time of DC link capacitor is decreased. The open fault is detected by a simple MRAS(Model Reference Adaptive System) without additional hardware sensors, and the tolerant operation carried out by turning on the opposite switch of the faulty switch without any redundancy. By the proposed method, the faulty phase input current can be controlled, so that 3-phase input current is balanced relatively under the faulty condition and the voltage ripple of DC link output is reduced. The validity of the proposed technique is proved on the 6kW 3-phase PWM rectifier system by simulation and experiment.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.10
• /
• pp.451-459
• /
• 2020

This study aims to examine the causality between production input and the price of rice in East Java, Indonesia. This study applied a quantitative method to understand in a comprehensive way the correlation between variables. The data used for this study were collected from several sources, including East Java Agriculture Office, Siskaperbapo.com, and Statistics Indonesia (BPS) of East Java. This research was carried out over five years, starting from 2014 to 2018. Furthermore, the data were analyzed using the Vector Error Correction Model (VECM) by employing E-Views (version 7). The findings of this study indicated that, in the long run, the population, rice production, and changes in people's income have a positive effect on price stability, but are inversely proportional if seen in the short term. In comparison, in the long run, farmer exchange rates variable has a negative impact on price stability, and inversely proportional in the short term, which has a positive effect. There are different implications when the people's income increases and the rice price declines; these have great potential to alleviate poverty in East Java, Indonesia. This is due to the fact that the price stability also concerns the welfare of the community.

• Coupled systems mechanics
• /
• v.12 no.5
• /
• pp.429-444
• /
• 2023

The comprehension and structural modeling of masonry constructions is fundamental to safeguard the integrity of built cultural assets and intervene through adequate actions, especially in earthquake-prone regions. Despite the availability of several modeling strategies and modern computing power, modeling masonry remains a great challenge because of still demanding computational efforts, constraints in performing destructive or semi-destructive in-situ tests, and material uncertainties. This paper investigates the shear behavior of masonry walls by applying a plane-stress FE continuum model with the Modified Masonry-like Material (MMLM). Epistemic uncertainty affecting input parameters of the MMLM is considered in a probabilistic framework. After appointing a suitable probability density function to input quantities according to prior engineering knowledge, uncertainties are propagated to outputs relying on gPCE-based surrogate models to considerably speed up the forward problem-solving. The sensitivity of the response to input parameters is evaluated through the computation of Sobol' indices pointing out the parameters more worthy to be further investigated, when dealing with the seismic assessment of masonry buildings. Finally, masonry mechanical properties are calibrated in a probabilistic setting with the Bayesian approach to the inverse problem based on the available measurements obtained from the experimental load-displacement curves provided by shear compression in-situ tests.

• Journal of Engineering Education Research
• /
• v.16 no.3
• /
• pp.79-86
• /
• 2013

The purpose of this study was to analyze the factors related to the satisfaction of the introductory engineering education program for the employees, who majored liberal arts or commerce, among the educational programs for industrial workers which are performed as an effort to spread the performance of the Innovation Center for Engineering Education, and reinforce the competitiveness through effective program operation. This study was performed on the basis of CIPP evaluation model (context, input, process, product). A factorial analysis and a regression analysis were conducted based on a survey made on 87 persons who completed the introductory engineering education program among the employees of D group who majored liberal arts or commerce. It is expected that this study will contribute toward suggesting the implications for designing and operating the educational programs for industrial workers in order to find out the important factors of satisfaction and to conduct the education operation with professionalism.