• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.28 no.3
• /
• pp.271-280
• /
• 2004

Assessment of image registration for Pressure Sensitive Paint (PSP) was performed. A 16 bit camera and LED lamp were used with Uni-FIB paint (ISSI). Because of model displacement and deformation at 'wind-on' condition, a large error of the intensity ratio was induced between 'wind-on' and' wind-off images. To correct the error, many kinds of image registrations were tested. At first, control points were marked on the model surface to find the coefficients of polynomial transform functions between the 'wind-off' 'wind-on' images. The 2nd-order polynomial function was sufficient for representing the model displacement and deformation. An automatic detection scheme was introduced to find the exact coordinates of the control points. The present automatic detection algorithm showed more accurate and user-friendly than the manual detection algorithm. Since the coordinates of transformed pixel were not integer, five interpolation methods were applied to get the exact pixel intensity after transforming the 'wind-on' image. Among these methods, the cubic convolution interpolation scheme gave the best result.

• Journal of Power System Engineering
• /
• v.19 no.3
• /
• pp.11-15
• /
• 2015

In this paper, the multi-point hydrogen detection system based on the combination of the hetero-core optical fiber SPR hydrogen tip sensor and interrogator by pseudorandom noise (PN) code correlation reflectometry has been developed. In a light intensity-based experiment with an LED operating at 850 nm, it has been presented that a transmitted loss change of 0.32dB was induced with a response time of 25 s for 4% $H_2$ in $N_2$ in the case of the 25-nm Au, 60-nm $Ta_2O_5$, and 5-nm Pd multi-layers film. The proposed sensor characteristic shows excellent reproducibility in terms of loss level and time response for the in- and out- $H_2$ action. In addition, in the experiment for multi-point hydrogen detection, all sensors show the real-time response for 4% hydrogen adding with reproducible working. As a result, the real-time multi-point hydrogen detection could be realized by means of the combination of interrogating system and hetero-core optical fiber SPR hydrogen tip sensors.

• Journal of Korea Society of Industrial Information Systems
• /
• v.23 no.4
• /
• pp.41-53
• /
• 2018

Recently, the development of machine learning technology has led to the application of deep learning technology to existing image based application systems. In this context, some researches have been made to apply CNN (Convolutional Neural Network) to the field of fire detection. To verify the effects of existing preprocessing and feature extraction methods on fire detection when combined with CNN, in this paper, the recognition performance and learning time are evaluated by changing the VGG19 CNN structure while gradually increasing the convolution layer. In general, the accuracy is better when the image is not preprocessed. Also it's shown that the preprocessing method and the feature extraction method have many benefits in terms of learning speed.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.5
• /
• pp.1780-1787
• /
• 2014

Arterial oxygen saturation ($SpO_2$) monitoring for newborns requires special attention in neonatal intensive care units (NICUs). Newborns have very low photo-plethysmogram (PPG) amplitudes and their body movements are difficult to contain. Hardware design and its associated signal processing algorithms should be robust enough so that faulty measurements can be avoided. In this study, improved designs were implemented to deal with low perfusion, motion artifact, and the influence of ambient light. Dynamic range was increased by using different LED intensities and a feedback system. To minimize the effects of motion artifact and to discard other unqualified data, four additional algorithms were used, which were based on dual-trace detection, continuity of DC level, morphology of PPG, and simultaneity check of $SpO_2$. Our $SpO_2$ system was tested with newborns with normal respiration in the NICU. Our system provided fast, real-time responses and 100% artifact detection was accomplished under 84% of $SpO_2$.

• Journal of Korea Multimedia Society
• /
• v.24 no.9
• /
• pp.1224-1241
• /
• 2021

Recent development of deep learning techniques for image generation has led to straightforward generation of sophisticated deepfakes. However, as a result, privacy violations through deepfakes has also became increased. To solve this issue, a number of techniques for deepfake detection have been proposed, which are mainly focused on RGB channel-based analysis. Although existing studies have suggested the effectiveness of other color model-based analysis (i.e., Grayscale), their effectiveness has not been quantitatively validated yet. Thus, in this paper, we compare the effectiveness of Grayscale channel-based analysis with RGB channel-based analysis in deepfake detection. Based on the selected CNN-based models and deepfake datasets, we measured the performance of each color model-based analysis in terms of accuracy and time. The evaluation results confirmed that Grayscale channel-based analysis performs better than RGB-channel analysis in several cases.

• Computers and Concrete
• /
• v.27 no.5
• /
• pp.447-455
• /
• 2021

Research on damage detection methods in structures began a few decades ago with the introduction of methods based on structural vibration frequencies, which, of course, continues to this day. The value of important structures, on the one hand, and the countless maintenance costs on the other hand, have led researchers to always try to identify more accurate methods to diagnose damage to structures in the early stages. Among these, one of the most important and widely used methods in damage detection is the use of time-frequency representations. By using time-frequency representations, it is possible to process signals simultaneously in the time and frequency domains. In this research, the Short-Time Fourier transform, a known time-frequency function, has been used to process signals and identify the system. Besides, a new damage index has been introduced to identify damages in concrete piers of bridges. The proposed method has relatively simple calculations. To evaluate the method, the finite element model of an existing concrete bridge was created using as-built details. Based on the results, the method identifies the damages with high accuracy.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.36 no.10
• /
• pp.1189-1193
• /
• 2012

The Miniaturized Fingerprint Imager (MFI) is a slim optical mouse that can be used as an input device for application to wireless portable personnel communication devices such as smartphones. In this study, we have fabricated key optical components of an MFI, including the illumination optical components and imaging lens. An LED beam-shaping lens consisting of an aspheric lens and a Fresnel facet was successfully machined using a diamond turning machine (DTM). A customized V-shaped groove for beam path banding was fabricated by the bulk micromachining of silicon that was coated with aluminum using the shadow effect in thermal evaporation. The imaging lens and arrayed multilevel Fresnel lenses were fabricated by electron beam lithography and FAB etching, respectively. The proposed optical components are extremely compact and have high optical efficiency; therefore, they are applicable to ultraslim optical systems.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.4
• /
• pp.210-219
• /
• 2023

The decline in the rural populace and an aging workforce have led to fatalities due to worsening environments and hazards within vinyl greenhouses. Therefore, it is necessary to automate crop cultivation and disease detection system in greenhouses to prevent labor loss. In this paper, an object detection-based model is used to detect diseased crop in greenhouses. In addition, the system proposed configures the environment of the artificial intelligence model in the cloud to ensure stability. The system captures images taken inside the vinyl greenhouse and stores them in a database, and then downloads the images to the cloud to perform inference based on Yolo-v4 for detection, generating JSON files for the results. Analyze this file and send it to the database for storage. From the experimental results, it was confirmed that disease detection through object detection showed high performance in real environments like vinyl greenhouses. It was also verified that efficient monitoring is possible through the database

• Journal of Sensor Science and Technology
• /
• v.32 no.3
• /
• pp.131-139
• /
• 2023

Ascorbic acid plays a crucial role in the regulation of neurotransmitters and enzymes in the central nervous system. Maintaining an optimal level of ascorbic acid, which is between 0.6-2 mg/dL, is vital for preventing oxidative stress and associated health conditions, such as cancer, diabetes, and liver disease. Therefore, the detection of ascorbic acid is of the utmost importance. Electrochemical sensing has gained significant attention among the various detection methods, owing to its simplicity, speed, affordability, high selectivity, and real-time analysis capabilities. However, conventional electrodes have poor signal response, which has led to the development of modified electrodes with better signal response and selectivity. Carbon nanotubes (CNTs) and their composites have emerged as promising materials for the electrochemical detection of ascorbic acid. CNTs possess unique mechanical, electrical, and chemical properties that depend on their structure, and their large surface area and excellent electron transport properties make them ideal candidates for electrochemical sensing. Recently, various CNT composites with different materials and nanoparticles have been studied to enhance the electrochemical detection of ascorbic acid. Therefore, this review aims to highlight the significance of CNTs and their composites for improving the sensitivity and selectivity of ascorbic acid detection. Specifically, it focuses on the use of CNTs and their composites in electrochemical sensing to revolutionize the detection of ascorbic acid and contribute to the prevention of oxidative stress-related health conditions. The potential benefits of this technology make it a promising area for future research and development.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.5
• /
• pp.1433-1449
• /
• 2023

In recent years, the rapid development of social networks has led to a rapid increase in the amount of information available on the Internet, which contains a large amount of sensitive information related to pornography, politics, and terrorism. In the aspect of sensitive image detection, the existing machine learning algorithms are confronted with problems such as large model size, long training time, and slow detection speed when auditing and supervising. In order to detect sensitive images more accurately and quickly, this paper proposes a multiclassification sensitive image detection method based on lightweight Convolutional Neural Network. On the basis of the EfficientNet model, this method combines the Ghost Module idea of the GhostNet model and adds the SE channel attention mechanism in the Ghost Module for feature extraction training. The experimental results on the sensitive image data set constructed in this paper show that the accuracy of the proposed method in sensitive information detection is 94.46% higher than that of the similar methods. Then, the model is pruned through an ablation experiment, and the activation function is replaced by Hard-Swish, which reduces the parameters of the original model by 54.67%. Under the condition of ensuring accuracy, the detection time of a single image is reduced from 8.88ms to 6.37ms. The results of the experiment demonstrate that the method put forward has successfully enhanced the precision of identifying multi-class sensitive images, significantly decreased the number of parameters in the model, and achieved higher accuracy than comparable algorithms while using a more lightweight model design.