• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.6
• /
• pp.629-635
• /
• 2019

In Deep Learning models derivative is implemented by error back-propagation which enables the model to learn the error and update parameters. It can find the global (or local) optimal points of parameters even in the complex models taking advantage of a huge improvement in computing power. However, deliberately generated data points can 'fool' models and degrade the performance such as prediction accuracy. Not only these adversarial examples reduce the performance but also these examples are not easily detectable with human's eyes. In this work, we propose the method to detect adversarial datasets with random noise addition. We exploit the fact that when random noise is added, prediction accuracy of non-adversarial dataset remains almost unchanged, but that of adversarial dataset changes. We set attack methods (FGSM, Saliency Map) and noise level (0-19 with max pixel value 255) as independent variables and difference of prediction accuracy when noise was added as dependent variable in a simulation experiment. We have succeeded in extracting the threshold that separates non-adversarial and adversarial dataset. We detected the adversarial dataset using this threshold.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.11
• /
• pp.1813-1819
• /
• 2016

In this paper, LS-SynRM (Line Start-Synchronous Reluctance Motor) has been attracting attention in replace of induction motor which hardly provides high efficiency. Compared to induction motor, LS-SynRM has better efficiency per unit area. This study demonstrated the electromagnetic design methods of LS-SynRM while maintaining the frame of existing IE3 induction motor for blower. We documented the design procedures for generating high saliency which is the most essential and mechanical stress analysis is also treated. In conclusion, we proved the validity of our design by manufacturing and testing our LS-SynRM models.

• Journal of Electrical Engineering and information Science
• /
• v.1 no.1
• /
• pp.58-69
• /
• 1996

This paper presents a new approach to derive an energy integral based on an Equivalent Mechanical Model(EMM), which is developed by introducing imaginary springs for line resistances. The proposed EMM shows that phasor currents and voltages are directly analogous to the two-dimensional force and displacement vectors, respectively. Through rigorous energy analysis of the proposed EMM, an exact energy integral expression is derived for multimachine systems, and several useful theorems are developed to derive an energy integral for power systems with detailed generator models the energy integral exactly reflects the internal resistance, saliency and flux-decaying effects of the generator. Finally, an illustrative example is given for a multimachine system adopting the Eq'-model for generators, which shows that the consideration of a detailed generator model does not aggravate the complicacy of the direct method of stability analysis in multimachine systems.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.29 no.11
• /
• pp.35-40
• /
• 2015

In accordance with global energy conservation policies such as MEPS (Minimum Energy Performance Standard), electric motor industry is moving to super-high-efficiency machines and research to develop IE4 (International Energy Efficiency Class 4) motors has been launched. In this situation, SynRM (Synchronous Reluctance Motor) has been attracting attention in place of induction motor which hardly provides super premium efficiency. As a result, much research on SynRM is being performed at home and abroad. Also, some products have already been appearing in the market. Compared to induction motor, SynRM has better efficiency per unit area and wider operating range. Although the utilization of control system in synchronous motor results in higher prices, we still need to concentrate on developments of SynRM so as to comply with the new policies. This study demonstrated the electromagnetic design methods of super premium SynRM while maintaining the frame of existing IE3 induction motor. We documented the design procedures for generating high saliency which is the most essential and mechanical stress anlaysis is also treated. In conclusion, we proved the validity of our design by manufacturing and testing our 3 models.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.6
• /
• pp.132-142
• /
• 2014

In this paper, we propose a traffic lights detection method using visual attention and spot-lights detection. To detect traffic lights in city streets at day and night time, the proposed method is used the structural form of a traffic lights such as colors, intensity, shape, textures. In general, traffic lights are installed at a position to increase the visibility of the drivers. The proposed method detects the candidate traffic lights regions using the top-down visual saliency model and spot-lights detect models. The visual saliency and spot-lights regions are positions of its difference from the neighboring locations in multiple features and multiple scales. For detecting traffic lights, by not using a color thresholding method, the proposed method can be applied to urban environments of variety changes in illumination and night times.

• Journal of KIISE
• /
• v.44 no.12
• /
• pp.1282-1289
• /
• 2017

Since the study of deep convolutional neural network became prevalent, one of the important discoveries is that a feature map from a convolutional network can be extracted before going into the fully connected layer and can be used as a saliency map for object detection. Furthermore, the model can use features from each different layer for accurate object detection: the features from different layers can have different properties. As the model goes deeper, it has many latent skip connections and feature maps to elaborate object detection. Although there are many intermediate layers that we can use for semantic segmentation through skip connection, still the characteristics of each skip connection and the best skip connection for this task are uncertain. Therefore, in this study, we exhaustively research skip connections of state-of-the-art deep convolutional networks and investigate the characteristics of the features from each intermediate layer. In addition, this study would suggest how to use a recent deep neural network model for semantic segmentation and it would therefore become a cornerstone for later studies with the state-of-the-art network models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.2
• /
• pp.769-786
• /
• 2016

Object recognition and object location have always drawn much interest. Also, recently various computational models have been designed. One of the big issues in this domain is the lack of an appropriate model for extracting important part of the picture and estimating the object place in the same environments that caused low accuracy. To solve this problem, a new Salient Based Bag of Visual Word (SBBoVW) model for object recognition and object location estimation is presented. Contributions lied in the present study are two-fold. One is to introduce a new approach, which is a Salient Based Bag of Visual Word model (SBBoVW) to recognize difficult objects that have had low accuracy in previous methods. This method integrates SIFT features of the original and salient parts of pictures and fuses them together to generate better codebooks using bag of visual word method. The second contribution is to introduce a new algorithm for finding object place based on the salient map automatically. The performance evaluation on several data sets proves that the new approach outperforms other state-of-the-arts.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.3
• /
• pp.411-418
• /
• 2016

In accordance with global energy conservation policies such as MEPS(Minimum Energy Performance Standard), electric motor industry is moving to super-high-efficiency machines and research to develop IE4 (International Energy Efficiency Class4) motors has been launched. In this situation, SynRM (Synchronous Reluctance Motor) has been attracting attention in place of induction motor which hardly provides super premium efficiency. As a result, much research on SynRM is being performed at home and abroad. Also, some products have already been appearing in the market. Compared to induction motor, SynRM has better efficiency per unit area and wider operating range. Although the utilization of control system in synchronous motor results in higher prices, we still need to concentrate on developments of SynRM so as to comply with the new policies. This study demonstrated the electromagnetic design methods of super-premium SynRM while maintaining the frame of existing IE3 induction motor for blower. We documented the design procedures for generating high saliency which is the most essential and mechanical stress analysis is also treated. In conclusion, we proved the validity of our design by manufacturing and testing our SynRM models.