• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.429-431
• /
• 2003

The induced learning retardation method involves the temporary inhibition of the artificial neural network’s active units from participating in the error reduction process during training. This stimulates the less active units to contribute significantly to reduce the network error. However, some less active units are not sensitive to stimulation making them almost useless. The network can then be pruned by removing the less active units to make it smaller and more efficient. This study focuses on making the network more efficient and accurate by developing the induced learning retardation and pruning sequence training method. The developed procedure results to faster learning and more accurate artificial neural network for satellite image classification.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.4
• /
• pp.1229-1239
• /
• 2014

Optimal Distributed Generation (DG) output and reconfiguration are among the well accepted approach to reduce power loss in a distribution network. In the past, most of the researchers employed optimal DG output and reconfiguration separately. In this work, a simultaneous DG output and reconfiguration analysis is proposed to maximize power loss reduction. The impact of the separated analysis and simultaneous analysis are investigated. The test result on the 33 bus distribution network with 3 units of DG operated in PV mode showed the simultaneous analysis gave the lowest power loss (global optimal) and faster results compared to other combined methods. All the analyses for optimizing the DG as well as reconfiguration are used the Artificial Bee Colony Optimization technique.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.7
• /
• pp.3714-3732
• /
• 2019

With the rapid development of network, Intrusion Detection System(IDS) plays a more and more important role in network applications. Many data mining algorithms are used to build IDS. However, due to the advent of big data era, massive data are generated. When dealing with large-scale data sets, most data mining algorithms suffer from a high computational burden which makes IDS much less efficient. To build an efficient IDS over big data, we propose a classification algorithm based on data clustering and data reduction. In the training stage, the training data are divided into clusters with similar size by Mini Batch K-Means algorithm, meanwhile, the center of each cluster is used as its index. Then, we select representative instances for each cluster to perform the task of data reduction and use the clusters that consist of representative instances to build a K-Nearest Neighbor(KNN) detection model. In the detection stage, we sort clusters according to the distances between the test sample and cluster indexes, and obtain k nearest clusters where we find k nearest neighbors. Experimental results show that searching neighbors by cluster indexes reduces the computational complexity significantly, and classification with reduced data of representative instances not only improves the efficiency, but also maintains high accuracy.

• ETRI Journal
• /
• v.41 no.4
• /
• pp.415-425
• /
• 2019

Generative adversarial networks (GAN) have been successfully used in many image restoration tasks, including image denoising, super-resolution, and compression artifact reduction. By fully exploiting its characteristics, state-of-the-art image restoration techniques can be used to generate images with photorealistic details. However, there are many applications that require faithful rather than visually appealing image reconstruction, such as medical imaging, surveillance, and video coding. We found that previous GAN-training methods that used a loss function in the form of a weighted sum of fidelity and adversarial loss fails to reduce fidelity loss. This results in non-negligible degradation of the objective image quality, including peak signal-to-noise ratio. Our approach is to alternate between fidelity and adversarial loss in a way that the minimization of adversarial loss does not deteriorate the fidelity. Experimental results on compression-artifact reduction and super-resolution tasks show that the proposed method can perform faithful and photorealistic image restoration.

• Asian Journal of Atmospheric Environment
• /
• v.5 no.4
• /
• pp.228-236
• /
• 2011

Since most Green House Gases (GHGs) and air pollutants are generated from the same sources, it will be cost-effective to develop a GHGs reduction plan in combination with simultaneous removal of air pollutants. However, effects on air pollutants reduction according to implementing any GHG abatement plans have been rarely studied. Reflecting simultaneous removal of air pollutants along with the GHGs emission reduction, this study investigated relative cost effectiveness among GHGs reduction action plans in Busan Metropolitan City. We employed the Data Envelopment Analysis (DEA), a methodology that evaluates relative efficiency of decision-making units (DMUs) producing multiple outputs with multiple inputs, for the investigation. Assigning each GHGs reduction action plan to a DMU, implementation cost of each GHGs reduction action plan to an input, and reduction potential of GHGs and air pollutants by each GHGs reduction action plan to an output, we calculated efficiency scores for each GHGs reduction action plan. When the simultaneous removal of air pollutants with the GHGs reduction were considered, green house supply-insulation improvement and intelligent transportation system (ITS) projects had high efficiency scores for cost-positive action plans. For cost-negative action plans, green start network formation and running, and daily car use control program had high efficiency scores. When only the GHGs reduction was considered, project priority orders based on efficiency scores were somewhat different from those when both the removal of air pollutants and GHGs reduction were considered at the same time. The expected action plan priority difference is attributed to great difference of air pollutants reduction potential according to types of energy sources to be reduced.

• Journal of Environmental Science International
• /
• v.22 no.4
• /
• pp.425-433
• /
• 2013

A mass balance of process was calculated by using the analysis of basic unit and environmental assessment of all the processes of Busan fashion color industry cooperative that operates a combined heat and power plant and a bio treatment plant. The mass balance for the combined heat and power plant was done, based on boiler and water treatment processes while each unit reactor was used for the bio treatment plant. From the results above, a resource recycle network, a treatment flowchart for food waste water/wastewater treatment and a carbon reduction program were established.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 1999.05a
• /
• pp.56-59
• /
• 1999

In the present study, in order to investigate the effect of the corner filling in the drawing of the rectangular rod from a round bar, the drawing of the square rod from a round bar has been simulated by using rigid-plastic finite element method and artificial neural network has been introduced to reduce the number of simulation. The experimental investigation has been also implemented to verify the efficiency of the application of results of present and previous study. According to the results of present and pervious study, the combination of semi-die angle gives a great effect on the corner filling in case of the irregular shaped drawing process, but, in case of the regular shaped drawing process, the main process variable on the corner filling is reduction in area.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.55 no.9
• /
• pp.459-464
• /
• 2006

The detent force by end-effect has an undesired influence on moving coil type Permanent Magnet Linear Synchronous Motor(PMLSM). So, the reduction of detent force by end-effect is especially required for the improvement of thrust characteristics. In this paper, in order to reduce detent force by end-effect, the auxiliary-teeth is installed at the end part of mover. It is also analyzed by Finite Element Analysis(FEA) and optimized by using neural network. By comparison, the detent force is reduced about 41.4[%] comparing to that of basic model.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 1999.03b
• /
• pp.99-102
• /
• 1999

In this study, to investigate the effect of process variables such as reduction in area, semi-die angle and the rectangular ratio to the corner filling which influences the dimensional accuracy of the final product in the drawing of the cluadrangle rod from a round bar, it has been simulated by three dimensional rigid-plastic finite element method. In order to reduce the number of simulation artificial neural network has been introduced. Also, through the experimental investigation, the present results have been implemented on the industrial product. In results, the main process variable is the combination of the semi-die angle in case of the irregular shaped drawing process and reduction in area in the event of regular shaped drawing process, respectively.

• Proceedings of the Korea Association of Information Systems Conference
• /
• 2000.11a
• /
• pp.36-44
• /
• 2000

The purpose of this study is to introduce a more efficient forecasting technique, which could help result the reduction of cost in removing the waste of airline in-flight meals. We will use a neural network approach known to many researchers as the “Outstanding Forecasting Technique”. We employed a multi-layer perceptron neural network using a backpropagation algorithm. We also suggested using other related information to improve the forecasting performances of neural networks. We divided the data into three sets, which are training data set, cross validation data set, and test data set. Time lag variables are still employed in our model according to the general view of time series forecasting. We measured the accuracy of our model by “Mean Square Error”(MSE). The suggested model proved most excellent in serving economy class in-flight meals. Forecasting the exact amount of meals needed for each airline could reduce the waste of meals and therefore, lead to the reduction of cost. Better yet, it could enhance the cost competition of each airline, keep the schedules on time, and lead to better service.