• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.446-452
• /
• 2021

As a higher standard for food consumption is required, the consumption of chicken meat that can satisfy the subdivided food preferences is increasing. In March 2003, the quality criteria for chicken carcasses notified by the Livestock Quality Assessment Service suggested quality grades according to fecal contamination and the size and weight of blood and bruises. On the other hand, it is too difficult for human inspection to qualify mass products, which is key to maintaining consistency for grading thousands of chicken carcasses. This paper proposed the computer vision algorithm as a non-destructive inspection, which can identify chicken carcass parts according to the detailed standards. To inspect the chicken carcasses conveyed at high speed, the image calibration was involved in providing robustness to the side effect of external lighting interference. The separation between chicken and background was achieved by a series of image processing, such as binarization based on Expectation Maximization, Erosion, and Labeling. In terms of shape analysis of chicken carcasses, the features are presented to reveal geometric information. After applying the algorithm to 78 chicken carcass samples, the algorithm was effective in segmenting chicken carcass against a background and analyzing its geometric features.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.1
• /
• pp.1-7
• /
• 2022

As a power transmission element, the timing belt is a toothed transmission belt that takes advantages of V-belts and gears. It has characteristics of non-slip and low noise. It is used as a power transmission device when transmitting power from a rotating shaft or linear motion in a mechanism. Rotation can be accurately transmitted through a belt pulley with grooves like a gear and a timing belt with grooves to precisely match with the belt pulley. In particular, in the mechanism in which the timing belt is used for the output shaft, the dynamic characteristics including the rigidity of the timing belt determine the transmission characteristics of the system, so its importance increases. In this paper, a stiffness reinforced belt that can be applied to a timing belt with a limited range of motion to increase its stiffness is proposed. To study the dynamic characteristics of the stiffness reinforced belt, the equation of motion for the stiffness reinforced belt was established, and a simulation model for the stiffness reinforced belt was created and analyzed. In order to confirm the analysis results of the motion equation and simulation model, a 1-axis rotation experimental equipment using a stiffness reinforcing belt was developed and the experiment was conducted. Through motion equations, simulation models, and experiment results, it was confirmed that the stiffness and dynamic characteristics of the timing belt could be improved by applying the proposed stiffness reinforcement belt.

• Journal of the Korea Society for Simulation
• /
• v.31 no.1
• /
• pp.11-18
• /
• 2022

Recently, research to classify human activity using imagery has been actively conducted for the purpose of crime prevention and facility safety in public places and facilities. In order to improve the performance of human activity classification, most studies have applied deep learning based-transfer learning. However, despite the increase in the number of backbone network models that are the basis of deep learning as well as the diversification of architectures, research on finding a backbone network model suitable for the purpose of operation is insufficient due to the atmosphere of using a certain model. Thus, this study applies the transfer learning into recently developed deep learning backborn network models to build an intelligent system that classifies human activity using imagery. For this, 12 types of active and high-contact human activities based on sports, not basic human behaviors, were determined and 7,200 images were collected. After 20 epochs of transfer learning were equally applied to five backbone network models, we quantitatively analyzed them to find the best backbone network model for human activity classification in terms of learning process and resultant performance. As a result, XceptionNet model demonstrated 0.99 and 0.91 in training and validation accuracy, 0.96 and 0.91 in Top 2 accuracy and average precision, 1,566 sec in train process time and 260.4MB in model memory size. It was confirmed that the performance of XceptionNet was higher than that of other models.

• Journal of IKEEE
• /
• v.26 no.4
• /
• pp.633-638
• /
• 2022

Rencently, neuromorphic systems of spiking neural networks (SNNs) that imitate the human brain have attracted attention. Neuromorphic technology has the advantage of high speed and low power consumption in cognitive applications and processing. Resistive random-access memory (RRAM) for SNNs are the most efficient structure for parallel calculation and perform the gradual switching operation of spike-timing-dependent plasticity (STDP). RRAM as synaptic device operation has low-power processing and expresses various memory states. However, the integration of RRAM device causes high switching voltage and current, resulting in high power consumption. To reduce the operation voltage of the RRAM, it is important to develop new materials of the switching layer and metal electrode. This study suggested a optimized new structure that is the Metal/Al₂O₃/HfO_x/SWCNTs/N+silicon (MOCS) with single-walled carbon nanotubes (SWCNTs), which have excellent electrical and mechanical properties in order to lower the switching voltage. Therefore, we show an improvement in the gradual switching behavior and low-power I/V curve of SWCNTs-based memristors.

• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.31-41
• /
• 2022

Steel is one of the most fundamental components to mechanical industry. However, the quality of products are greatly impacted by the surface defects in the steel. Thus, researchers pay attention to the need for surface defects detector and the deep learning methods are the current trend of object detector. There are still limitations and rooms for improvements, for example, related works focus on developing the models but don't take into account real-time application with practical implication on industrial settings. In this paper, a real-time application of steel surface defects detection based on YOLOv4 is proposed. Firstly, as the aim of this work to deploying model on real-time application, we studied related works on this field, particularly focusing on one-stage detector and YOLO algorithm, which is one of the most famous algorithm for real-time object detectors. Secondly, using pre-trained Yolov4-Darknet platform models and transfer learning, we trained and test on the hot rolled steel defects open-source dataset NEU-DET. In our study, we applied our application with 4 types of typical defects of a steel surface, namely patches, pitted surface, inclusion and scratches. Thirdly, we evaluated YOLOv4 trained model real-time performance to deploying our system with accuracy of 87.1 % mAP@0.5 and over 60 fps with GPU processing.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.165-184
• /
• 2023

Recently, Deep learning analysis of unstructured text data using language models, such as Google's BERT and OpenAI's GPT has shown remarkable results in various applications. Most language models are used to learn generalized linguistic information from pre-training data and then update their weights for downstream tasks through a fine-tuning process. However, some concerns have been raised that privacy may be violated in the process of using these language models, i.e., data privacy may be violated when data owner provides large amounts of data to the model owner to perform fine-tuning of the language model. Conversely, when the model owner discloses the entire model to the data owner, the structure and weights of the model are disclosed, which may violate the privacy of the model. The concept of offsite tuning has been recently proposed to perform fine-tuning of language models while protecting privacy in such situations. But the study has a limitation that it does not provide a concrete way to apply the proposed methodology to text classification models. In this study, we propose a concrete method to apply offsite tuning with an additional classifier to protect the privacy of the model and data when performing multi-classification fine-tuning on Korean documents. To evaluate the performance of the proposed methodology, we conducted experiments on about 200,000 Korean documents from five major fields, ICT, electrical, electronic, mechanical, and medical, provided by AIHub, and found that the proposed plug-in model outperforms the zero-shot model and the offsite model in terms of classification accuracy.

• Journal of the Korean Geotechnical Society
• /
• v.40 no.1
• /
• pp.5-14
• /
• 2024

PHC piles demonstrate superior resistance to compression and bending moments, and their factory-based production enhances quality assurance and management processes. Despite these advantages that have resulted in widespread use in civil engineering and construction projects, the design process frequently relies on empirical formulas or N-values to estimate the soil-pile friction, which is crucial for bearing capacity, and this reliance underscores a significant lack of experimental validation. In addition, environmental factors, e.g., the pH levels in groundwater and the effects of seawater, are commonly not considered. Thus, this study investigates the influence of vibrating machine foundations on PHC pile models in consideration of the effects of varying pH conditions. Concrete model piles were subjected to a one-month conditioning period in different pH environments (acidic, neutral, and alkaline) and under the influence of seawater. Subsequent repeated direct shear tests were performed on the pile-soil interface, and the disturbed state concept was employed to derive parameters that effectively quantify the dynamic behavior of this interface. The results revealed a descending order of shear stress in neutral, acidic, and alkaline conditions, with the pH-influenced samples exhibiting a more pronounced reduction in shear stress than those affected by seawater.

• Composites Research
• /
• v.37 no.3
• /
• pp.238-245
• /
• 2024

In this study, as part of the development of a monitoring system for the efficient maintenance of steel pipes, an experimental study was conducted to evaluate the performance of steel pipes treated with modified polyethylene coating. In the case of the conventional mechanical pre-coating method, there was a deterioration in polyethylene adhesion during expansion testing, which led to the application of a chemical pre-treatment process using a calcium-mixed phosphate zinc film to resolve this issue. SEM and EDX analyses showed that the densest structure was observed at a Zn/Ca ratio of 1.0, and improved heat resistance compared to the conventional method was confirmed. Additionally, to prevent coating detachment during expansion, an evaluation of adhesion and elongation was conducted on steel pipes with modified polyethylene coating, incorporating materials such as elastomers based on maleic anhydride grafting, metal oxides, blocking agents, and slip agents. Experimental results showed that the specimen (S4) containing all modified materials exhibited more than a 25% performance improvement compared to the specimen (S2) containing only metal oxides. Lastly, the development and performance evaluation of wedge-shaped socketing and pressing wheels, which are part of the pipe fixing accessories, were conducted to prevent surface coating damage on the completed pipes.

• Resources Recycling
• /
• v.15 no.3 s.71
• /
• pp.38-45
• /
• 2006

The thermal filter press dewatering(TFPD) technology to improve the dewaterability through increasing the inner vapor pressure, lowering the filtration viscosity and forming the porosity easily within cake as applying the heat at the sludge layer was developed in this study. The hot water with temperature of $95^{\circ}C$ and pressure of $1.2kg_f/cm^2$ was supplied to the heating plate equipped between filter plates with plate size of $470{\times}470mm$ and material of polypropylene. Sludge was dewaterd by supplying pressure of $5kg_f/cm^2$ and then by squeezing pressure of $15kg_f/cm^2$. As a results of estimating the characteristics of thermal dewatering to consider the initial water content and organic content to be influenced by a period of water shortage and rainwater, the dewatered cake water content was about 35 wt% and dewatering velocity was $4DSkg/m^2{\cdot}hr$ under the rainwater period, and the dewatered cake water content was about 50 wt% and dewatering velocity was $1.5DSkg/m^2{\cdot}hr$ in the case of sludge of water shortage season. These results was superior to the mechanical dewatering performance with water content of 70wt% and dewatering velocity of $0.9DSkg/m^2{\cdot}hr$. On the base of the results of TFPD, energy consumpted to deal with DS(Dry Solid) of 1kg was estimated by 300 kJ. It was analyzed that the energy consumption of TFPD was decreased about one third with comparison to the dryer system. Dewatering velocity of this technology was faster than the one of mechanical dewatering equipment and it was easier to product low water content cake. Therefore, this technology was recognized that dewaterability was predominant because of the fast of dewatering velocity and production of low water content cake, and also this known as economical efficiency was excellent because of low energy consumption in comparison with dryer.

• KEPCO Journal on Electric Power and Energy
• /
• v.5 no.3
• /
• pp.209-213
• /
• 2019

Recently, demand for high energy density and long cycling stability of energy storage system has increased for application using with frequency regulation (F/R) in power grid. Supercapacitor have long lifetime and high charge and discharge rate, it is very adaptable to apply a frequency regulation in power grid. Supercapacitor can complement batteries to reduce the size and installation of batteries. Because their utilization in a system can potentially eliminate the need for short-term frequent replacement as required by batteries, hence, saving the resources invested in the upkeep of the whole system or extension of lifecycle of batteries in the long run of power grid. However, low energy density in supercapacitor is critical weakness to utilization for huge energy storage system of power grid. So, it is still far from being able to replace batteries and struggle in meeting the demand for a high energy density. But, today, LIC (Lithium Ion Capacitor) considered as an attractive structure to improve energy density much more than EDLC (Electric double layer capacitor) because LIC has high voltage range up to 3.8 V. But, many aspects of the electrochemical performance of LIC still need to be examined closely in order to apply for commercial use. In this study, in order to improve the capacitance of LIC related with energy density, we designed new method of pre-doping in anode electrode. The electrode in cathode were fabricated in dry room which has a relative humidity under 0.1% and constant electrode thickness over $100{\mu}m$ was manufactured for stable mechanical strength and anode doping. To minimize of contact resistance, fabricated electrode was conducted hot compression process from room temperature to $65^{\circ}C$. We designed various pre-doping method for LIC structure and analyzing the doping mechanism issues. Finally, we suggest new pre-doping method to improve the capacitance and electrochemical stability for LIC.