• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.7
• /
• pp.14-22
• /
• 2016

Because fuses have many parts, human error can occur during visual inspections. This paper proposes an automatic ammunition test algorithm for preventing human error during an inspection. The automatic ammunition test algorithm consists of the following three steps. First, the image input and preprocessing step is where an inspection image is rotated using an image rotation algorithm and the image is converted to a binary image. Second, the inspection step of arming determines if the ammunition is armed using Masked Template Matching algorithm, etc. Third, the inspection step of the parts determines if the parts are omitted using an image searching algorithm, etc. The arming or parts omission of the fuse are detected efficiently using the ammunition automatic test algorithm. The ammunition automatic test algorithm is expected to help improve the safety and reliability of 40 mm grenade fuse.

• The KIPS Transactions:PartA
• /
• v.13A no.5 s.102
• /
• pp.421-428
• /
• 2006

This paper proposes an integrated recovery approach applying retry and rollback techniques to recover the TMR failure. Combining the time redundancy techniques with W system is apparently effective to recover the TMR failure(or masked error) primarily caused by transient faults. These policies need fewer reconfigurations at the cost of extra time required for the time redundant schemes. The optimal numbers of retry and rollback to minimize the mean execution time of tasks are derived for the proposed method through computing the likelihoods of all possible states of the failed system. The effectiveness of the proposed method is validated through examining certain numerical examples and simulations conducted with a variety of parameters governing environmental characteristics.

• Proceedings of the IEEK Conference
• /
• 2002.06e
• /
• pp.211-214
• /
• 2002

Under a continuous manufacturing process, two dimension inspection system causes problems as blurring effect and low resolution and requires position calibration between frames. One dimension inspection system is, therefore, being researched as a substitution. In this paper, we implement mechanism of switching memory and processing data for reasonable one dimension inspection system. Redundant weft image and noise was suggested to be reduced by new method using modified morphological process and masked erosion process. From resulting image, line data and possible error information were obtained and constructed as a structure. Finally, error detecting algorithm was performed with this data structure. Processing time of error detecting was 0.625ms per line in applied system and experiment showed 94.7% of error detecting ability. This method is 20% faster in speed and 2.7% higher in error detecting ability comparing with the present method.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06b
• /
• pp.313-316
• /
• 2011

SRAM-based FPGAs are very sensitive to single event upset(SEU) induced by space irradiation. To mitigate SEU effects, space applications employ some mitigation schemes. The triple modular redundancy(TMR) is a well-known mitigation scheme. It uses one or three voters as well as three identical blocks performing the same work. The voters can mask out one error in the outputs from the three replicated blocks. One SEU error in TMRed circuits can be masked but it needs to be detected for some reasons such as to analyze the SEU effects in the satellite or to recover the circuits from the error before additional error occur. In this paper, we developed a fault detection circuit and reporting system to detect a fault on the TMRed circuits. To verify our error detection circuit and reporting circuit, we performed an irradiation test at MC-50 Cyclotron. Experimental results showed that error detection circuit can detect a fault on the TMRed test circuit in radiation environment.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.497-504
• /
• 2020

Constructing speaker embeddings in speaker verification is an important issue. In general, a self-attention mechanism has been applied for speaker embedding encoding. Previous studies focused on training the self-attention in a high-level layer, such as the last pooling layer. In this case, the effect of low-level layers is not well represented in the speaker embedding encoding. In this study, we propose Masked Cross Self-Attentive Encoding (MCSAE) using ResNet. It focuses on training the features of both high-level and low-level layers. Based on multi-layer aggregation, the output features of each residual layer are used for the MCSAE. In the MCSAE, the interdependence of each input features is trained by cross self-attention module. A random masking regularization module is also applied to prevent overfitting problem. The MCSAE enhances the weight of frames representing the speaker information. Then, the output features are concatenated and encoded in the speaker embedding. Therefore, a more informative speaker embedding is encoded by using the MCSAE. The experimental results showed an equal error rate of 2.63 % using the VoxCeleb1 evaluation dataset. It improved performance compared with the previous self-attentive encoding and state-of-the-art methods.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.6
• /
• pp.89-100
• /
• 2024

The primary goal of software testing is to identify and correct errors within software. A key challenge in this process is error masking, where errors disappear internally before reaching the output. This paper investigates the causes and characteristics of error masking, which complicates software testing. The study involved injecting artificial errors into three software programs to examine the extent of error masking by various test cases and to explore the underlying reasons. The experiment yielded four major findings. First, about 50% of the error masking occurred because the errors were not executed. Second, among various operators, logical and arithmetic operators masked errors less frequently, while relational and temporal operators tended to mask errors more extensively. Third, certain test cases demonstrated exceptional effectiveness in propagating errors to the output. Fourth, the type of error injected influenced the masking effect.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.8
• /
• pp.2555-2564
• /
• 2000

In this paper, a new unsupervised image segmentation algorithm is proposed. To model the contextual information presented in images, the characteristics of the Markov random fields (MRF) are utilized. Textured images are modeled as realizations of the stationary Gaussian MRF on a two-dimensional square lattice using the conditional autoregressive (CAR) equations with a second-order noncausal neighborhood. To detect boundaries, hypothesis tests over two masked areas are performed. Under the hypothesis, masked areas are assumed to belong to the same class of textures and CAR equation parameters are estimated in a minimum-mean-square-error (MMSE) sense. If the hypothesis is rejected, a measure of dissimilarity between two areas is accumulated on the rejected area. This approach produces potential edge maps. Using these maps, boundary detection can be performed, which resulting no micro edges. The performance of the proposed algorithm is evaluated by some experiments using real images as weB as synthetic ones. The experiments demonstrate that the proposed algorithm can produce satisfactorY segmentation without any a priori information.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.104-107
• /
• 2022

autoencoder deep learning model has excellent ability to restore abnormal data to normal data, so it is not appropriate for anomaly detection. In addition, the Inpainting method, which is a method of restoring hidden data after masking (masking) a part of the data, has a problem in that the restoring ability is poor for noisy images. In this paper, we use a method of modifying and improving the MLP-Mixer model to mask the image at a certain ratio and to reconstruct the image by delivering compressed information of the masked image to the model. After constructing a model learned with normal data from the MVTec AD dataset, a reconstruction error was obtained by inputting normal and abnormal images, respectively, and anomaly detection was performed through this. As a result of the performance evaluation, it was found that the proposed method has superior anomaly detection performance compared to the existing method.

• Journal of the Korean Society of Visualization
• /
• v.14 no.2
• /
• pp.46-51
• /
• 2016

In this study, a Masked Omni-Directional Integration(MODI) method for pressure calculation is proposed using the Particle Image Velocimetry (PIV) data. To obtain the velocity field, the Affine PIV method was adopted. Synthetic images were generated for a solid body rotation. Calculation on the pressure was based on the Navier-Stokes equation. The results obtained by the MODI were compared with those obtained by theoretical pressure and by the Omni-Directional Integration(ODI) method. It was shown that the minimum error by the proposed MODI method was attained when the mask size was 1.

• Korean Journal of Cognitive Science
• /
• v.26 no.1
• /
• pp.1-26
• /
• 2015

The purpose of this study was to examine whether the phonological information or the orthographic information plays a major role in visual word recognition. To do so, we used a non-word lexical decision task(LDT) in Experiment 1 and masked priming tasks in Experiement 2 and 3. The results of Experiment 1 showed that reaction times and the error rates were affected by the orthographic characteristics of the non-word stimuli such that orthographically similar non-words condition showed prolonged reaction times and higher error rates than control condition. In Experiment 2 and Experiment 3, the participants performed masked priming lexical decision tasks in two SOA conditions(60ms, 150ms). The results of the both experiments showed that the orthographically identical first syllable priming facilitated lexical decision of the target words while both of the pseudo-homophone priming and the phonologically identical first syllable priming did not. The dual route hypothesis(Coltheart et al, 2001), assuming that orthographic information rather than phonological information is the major source for the visual word recognition processes, fits well with the results of the current study.