• 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.

• English Language & Literature Teaching
• /
• v.17 no.2
• /
• pp.219-245
• /
• 2011

This case study aims to investigate how a primary English teacher's professional development was pursued through novice teacher mentoring after the six-month intensive in-service teacher training program(IIETTP). The teacher was involved in mentoring two novice teachers working at the same school. They observed each other's classes and exchanged their views on the classes, focusing on areas to be improved. The observation was done within a framework that consisted of pre-, during- and post-observation sessions. Data was gathered through retrospective entries kept after the post-observation meetings. The entries were categorized according to their saliency, frequency and recurring patterns identified. The findings reveal that learning from the training course could be applied professionally and could serve to bridge the gap between training and teaching. It is also shown that the mentee teachers' professional development was enhanced and the mentor teacher herself benefited from the collaborative learning process involved with working with the novice teachers. Some suggestions are made for the effective implementation of school-based teacher development programs after the IIETTP.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.9
• /
• pp.4386-4404
• /
• 2016

Most existing salient object detection algorithms commonly employed segmentation techniques to eliminate background noise and reduce computation by treating each segment as a processing unit. However, individual small segments provide little information about global contents. Such schemes have limited capability on modeling global perceptual phenomena. In this paper, a novel salient object detection algorithm is proposed based on region merging. An adaptive-based merging scheme is developed to reassemble regions based on their color dissimilarities. The merging strategy can be described as that a region R is merged with its adjacent region Q if Q has the lowest dissimilarity with Q among all Q's adjacent regions. To guide the merging process, superpixels that located at the boundary of the image are treated as the seeds. However, it is possible for a boundary in the input image to be occupied by the foreground object. To avoid this case, we optimize the boundary influences by locating and eliminating erroneous boundaries before the region merging. We show that even though three simple region saliency measurements are adopted for each region, encouraging performance can be obtained. Experiments on four benchmark datasets including MSRA-B, SOD, SED and iCoSeg show the proposed method results in uniform object enhancement and achieve state-of-the-art performance by comparing with nine existing methods.

• Proceedings of the KIEE Conference
• /
• 1994.07a
• /
• pp.588-590
• /
• 1994

This paper describes current controlled PWM technique of IPM synchronous motors for a wide variety of speed control applications. The IPM synchronous motors have a saliency, in which the q-axis inductance is larger than the d-axis inductance. As a consequence, there exists a reluctance torque component Thus when this component is added to the torque component produced by the stator currents and the air-gap flux, IPM motor drives are readily applicable where full torque Is required up to full or base speed. They are however limited in their ability to operate in the power limited regime where the available torque is reduced as the speed is increased above its base value. This paper reviews the operation of the IPMSM drives when they are constrained to be within the permissible envelope of maximum inverter voltage and current to produce the rated power and to provide this with the highest attainable rotor speed. The wide variety of speed control strategy is analyzed and the performance is investigated by the computer simulation using actual parameters of a drive system. Simulation results are given and discussed.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.62 no.10
• /
• pp.1425-1435
• /
• 2013

The useful method for determining parameters of weighting functions used to design the $H_{\infty}$ current controller for attenuating the current ripple due to saliencies which SPMSM(Surface Permanent Magnet Synchronous Motor) also incorporates is described. To analyze the effect, the current ripple due to the structural and the saturation saliencies, the SPMSM model with nonlinear inductance function depending on the two independent variables, rotor position and stator current is simulated. After analysis, parameters of the weighting functions for $H_{\infty}$ current controller is selected to satisfy the robust stability, robust performance and specific performance in time and frequency domain by using the PSO(Particle Swarm Optimization) algorithm in the linear SPMSM model. Especially, the robust performance is proved that the selected weighting functions play a role in reducing the current ripple caused by the saliencies of SPMSM at the desired frequency range by the simple experiment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.1
• /
• pp.272-287
• /
• 2016

Recently, various and effective contrast based salient object detection models to focus on a single target have been proposed. However, there is a lack of research on detection of multiple objects, and also it is a more challenging task than single target process. In the multiple target problem, we are confronted by new difficulties caused by distinct difference between properties of objects. The characteristic of existing models depending on the global maximum distribution of data point would become a drawback for detection of multiple objects. In this paper, by analyzing limitations of the existing methods, we have devised three main processes to detect multiple salient objects. In the first stage, regional features are extracted from over-segmented regions. In the second stage, the regional features are categorized into homogeneous cluster using the mean-shift algorithm with the kernel function having various sizes. In the final stage, we compute saliency scores of the categorized regions using only spatial features without the contrast features, and then all scores are integrated for the final salient regions. In the experimental results, the scheme achieved superior detection accuracy for the SED2 and MSRA-ASD benchmarks with both a higher precision and better recall than state-of-the-art approaches. Especially, given multiple objects having different properties, our model significantly outperforms all existing models.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.4
• /
• pp.229-236
• /
• 2017

This paper presents an efficient object-based color image-retrieval algorithm that is suitable for the classification and retrieval of images from small to mid-scale datasets, such as images in PCs, tablets, phones, and cameras. The proposed method first finds salient regions by using regional feature vectors, and also finds several dominant colors in each region. Then, each salient region is partitioned into small sub-blocks, which are assigned 1 or 0 with respect to the number of pixels corresponding to a dominant color in the sub-block. This gives a binary map for the dominant color, and this process is repeated for the predefined number of dominant colors. Finally, we have several binary maps, each of which corresponds to a dominant color in a salient region. Hence, the binary maps represent the spatial distribution of the dominant colors in the salient region, and the union (OR operation) of the maps can describe the approximate shapes of salient objects. Also proposed in this paper is a matching method that uses these binary maps and which needs very few computations, because most operations are binary. Experiments on widely used color image databases show that the proposed method performs better than state-of-the-art and previous color-based methods.

• Journal of Power Electronics
• /
• v.11 no.4
• /
• pp.464-470
• /
• 2011

In this paper, the feasibility of applying a position sensorless control technique to hybrid electric vehicles (HEVs) is practically evaluated. The proposed position estimator has a straightforward structure with properties that combines the model and the saliency tracking-based rotor position estimation for interior permanent magnet synchronous motors (IPMSMs). The proposed method can be used in the event of sensor loss or sensor recovery to sustain continuity of operations. The developed system takes into account the estimated position transition between two distinct sensorless methods. The transition is enhanced by introducing a synchronized transition algorithm based on a single tracking observer. Extensive experimental results are presented to verify the principles and show a reliable estimation performance over the entire speed range including standstill under 150% load conditions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.3
• /
• pp.539-557
• /
• 2013

A novel multifocus image fusion algorithm based on NSCT is proposed in this paper. In order to not only attain the image focusing properties and more visual information in the fused image, but also sensitive to the human visual perception, a local multidirection variance (LEOV) fusion rule is proposed for lowpass subband coefficient. In order to introduce more visual saliency, a modified local contrast is defined. In addition, according to the feature of distribution of highpass subband coefficients, a direction vector is proposed to constrain the modified local contrast and construct the new fusion rule for highpass subband coefficients selection The NSCT is a flexible multiscale, multidirection, and shift-invariant tool for image decomposition, which can be implemented via the atrous algorithm. The proposed fusion algorithm based on NSCT not only can prevent artifacts and erroneous from introducing into the fused image, but also can eliminate 'block effect' and 'frequency aliasing' phenomenon. Experimental results show that the proposed method achieved better fusion results than wavelet-based and CT-based fusion method in contrast and clarity.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.11
• /
• pp.5563-5582
• /
• 2016

Parametric min-cuts is an object proposal algorithm, which can be used for accurate image segmentation. In parametric min-cuts, foreground seeds generation plays an important role since the number and quality of foreground seeds have great effect on its efficiency and accuracy. To improve the performance of parametric min-cuts, this paper proposes a new framework for foreground seeds generation. First, to increase the odds of finding objects, saliency detection at multiple scales is used to generate a large set of diverse candidate seeds. Second, to further select good-quality seeds, a two-stage cascaded ranking classifier is used to filter and rank the candidates based on their appearance features. Experimental results show that parametric min-cuts using our seeding strategy can obtain a relative small pool of proposals with high accuracy.