• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.4
• /
• pp.400-406
• /
• 2014

In this paper, we propose an approach to minimizing total power consumption by deploying multiple clean-up robots simultaneously in a given area. For this, we propose to use the cooperative game theoretic approaches (i.e., Nash bargaining solution (NBS)) such that the robots can optimally and fairly negotiate the area division based on available resources and characteristics of the area, thereby leading to the minimum total power consumption. We define a utility function that includes power consumptions for characteristics of areas and the robots can agree on a utility pair based on the NBS. Simulation results show that the proposed approach can reduce the total average power consumption by 15-30% compared to a random area division approach.

• Clean Technology
• /
• v.8 no.1
• /
• pp.27-37
• /
• 2002

To verify the performance and effectiveness of bilinear model for the development of ozone prediction system, the simulation experiments of the model identification for ozone formation were performed by using bilinear and linear models. And the prediction results of the ozone formation by bilinear model were compared to those of linear model and the measured data of Seoul. ARMA(Autoregressive Moving Average) model was used in the model identification. A recursive parameter estimation algorithm based on an equation error method was used to estimate parameters of model. From the results of model identification experiment, the ozone formation by bilinear model showed good agreement with the ozone formation from the simulator. From the comparison of the prediction results and the measured data, it appears that the method proposed in this work is a reasonable means of developing real-time short-term prediction of ozone formation for an ozone forecast system.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.1
• /
• pp.175-182
• /
• 2010

In this paper, we propose a robust speech reinforcement technique to enhance the intelligibility of the degraded speech signal under the ambient noise environments based on soft decision scheme incorporating a speech absence probability (SAP) with speech reinforcement gains. Since the ambient noise significantly decreases the intelligibility of the speech signal, the speech reinforcement approach to amplify the estimated clean speech signal from the background noise environments for improving the intelligibility and clarity of the corrupted speech signal was proposed. In order to estimate the robust reinforcement gain rather than the conventional speech reinforcement method between speech active periods and nonspeech periods or transient intervals, we propose the speech reinforcement algorithm based on soft decision applying the SAP to the estimation of speech reinforcement gains. The performances of the proposed algorithm are evaluated by the Comparison Category Rating (CCR) of the measurement for subjective determination of transmission quality in ITU-T P.800 under various ambient noise environments and show better performances compared with the conventional method.

• Journal of Broadcast Engineering
• /
• v.13 no.5
• /
• pp.760-770
• /
• 2008

Though flash images are in general less noisy and present details better than no-flash images, they may sometimes be unnaturally saturated to white/gray-tone and have ridiculously strong shadows around the foreground objects due to the strong flashlight. In this paper, we propose a new algorithm to improve the color quality of the flash images by transfer of the color information of the same-scene no-flash images. The proposed algorithm preserves the vivid edges and the clean details of the flash image while transferring natural colors of the no-flash image, so that it makes the constructed images of the better subjective quality. The performance of the proposed algorithm is verified by experiment which applied to the two types of images with different noise levels.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.6
• /
• pp.1227-1236
• /
• 2021

Adversarial attack, one of the attacks on deep learning classification model, is attack that add indistinguishable perturbations to input data and cause deep learning classification model to misclassify the input data. There are various adversarial attack algorithms. Accordingly, many studies have been conducted to detect adversarial attack but few studies have been conducted to classify what adversarial attack algorithms to generate adversarial input. if adversarial attacks can be classified, more robust deep learning classification model can be established by analyzing differences between attacks. In this paper, we proposed a model that detects and classifies adversarial attacks by constructing a random forest classification model with input features extracted from a target deep learning model. In feature extraction, feature is extracted from a output value of hidden layer based on class predicted by the target deep learning model. Through Experiments the model proposed has shown 3.02% accuracy on clean data, 0.80% accuracy on adversarial data higher than the result of pre-existing studies and classify new adversarial attack that was not classified in pre-existing studies.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.1
• /
• pp.1-8
• /
• 2023

It is impossible to overwrite on an already allocated page in SSDs, so whenever a write operation occurs a page replacement with a clean page is required. To resolve this problem, SSDs have an internal flash translation layer called FTL that maps logical pages managed by a file system of operating system to currently allocated physical pages. SSD pages discarded due to write operations must be recycled through initialization, but since the number of initialization times is limited the FTL provides a caching function to reduce the number of writes in addition to the page mapping function, which is a core function. In this study, we focus on the FTL cache methodologies reducing the number of page writes and analyze the related algorithms, and propose a write-only cache strategy. As a result of experimenting with the write-only cache using a simulator, it showed an improvement of up to 29%.

• Smart Media Journal
• /
• v.9 no.4
• /
• pp.102-108
• /
• 2020

In this paper, we propose a real-time method of detecting hand motions and extracting the signal frame induced by EF(Electric Field) sensors. The signal induced by hand motion includes not only noises caused by various environmental sources as well as sensor's physical placement, but also different initial off-set conditions. Thus, it has been considered as a challenging problem to detect the motion signal and extract the motion frame automatically in real-time. In this study, we remove the PLN(Power Line Noise) using LPF with 10Hz cut-off and successively apply MA(Moving Average) filter to obtain clean and smooth input motion signals. To sense a hand motion, we use two thresholds(positive and negative thresholds) with offset value to detect a starting as well as an ending moment of the motion. Using this approach, we can achieve the correct motion detection rate over 98%. Once the final motion frame is determined, the motion signals are normalized to be used in next process of classification or recognition stage such as LSTN deep neural networks. Our experiment and analysis show that our proposed methods produce better than 98% performance in correct motion detection rate as well as in frame-matching rate.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.3
• /
• pp.51-55
• /
• 2020

In this paper, an improved FAM is proposed by adopting similarity learning in the existing FAM (Fuzzy Associative Memory) used in image restoration. Image restoration refers to the recovery of the latent clean image from its noise-corrupted version. In serious application like face recognition, this process should be noise-tolerant, robust, fast, and scalable. The existing FAM is a simple single layered neural network that can be applied to this domain with its robust fuzzy control but has low capacity problem in real world applications. That similarity measure is implied to the connection strength of the FAM structure to minimize the root mean square error between the recovered and the original image. The efficacy of the proposed algorithm is verified with significant low error magnitude from random noise in our experiment.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.4
• /
• pp.357-362
• /
• 2010

This paper proposes the speech and noise recognition system by using a neural network in order to detect the speech and noise sections at each frame. The proposed neural network consists of a layered neural network training by back-propagation algorithm. First, a power spectrum obtained by fast Fourier transform and linear predictive coefficients are used as the input to the neural network for each frame, then the neural network is trained using these power spectrum and linear predictive coefficients. Therefore, the proposed neural network can train using clean speech and noise. The performance of the proposed recognition system was evaluated based on the recognition rate using various speeches and white, printer, road, and car noises. In this experiment, the recognition rates were 92% or more for such speech and noise when training data and evaluation data were the different.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.2
• /
• pp.36-40
• /
• 1997

In speech signal processing, it is necessary and important to detect exactly the pitch. The algorithms of pitch extraction which have been proposed until now are difficult exactly pitches over wide range speech signals. In this paper, thus, we proposed a new pitch detection algorithm that finds the fundamental period of speech signal in the residual signal quantized by the uniform quantizer as PCM. The proposed method shows little gross error of average 0.25% for clean speech and average 3.39% for SNR of 0dB. It also achieves results of the pitch contours, improving the accuracy of pitch detection in transient phonemes and noise environments.