• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.4
• /
• pp.149-155
• /
• 2021

In this study, we intend to develop a defective road surface object recognition model that automatically detects road surface defects that restrict the movement of the transportation handicapped using electric mobile devices with deep learning. For this purpose, road surface information was collected from the pedestrian and running routes where the electric mobility aid device is expected to move in five areas within the city of Busan. For data, images were collected by dividing the road surface and surroundings into objects constituting the surroundings. A series of recognition items such as the detection of breakage levels of sidewalk blocks were defined by classifying according to the degree of impeding the movement of the transportation handicapped in traffic from the collected data. A road surface object recognition deep learning model was implemented. In the final stage of the study, the performance verification process of a deep learning model that automatically detects defective road surface objects through model learning and validation after processing, refining, and annotation of image data separated and collected in units of objects through actual driving. proceeded.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.2
• /
• pp.18-27
• /
• 2022

In this study, the time-dependent chloride ingress behavior in GGBFS concrete was evaluated considering marine exposure conditions and the properties of concrete mixtures. The concrete mixture for this study had 3 levels of water to binder ratio and the substitution rate of GGBFS, and outdoor exposure tests were performed considering submerged area, tidal area, and splash area. According to the evaluation results of diffusion coefficient considering properties of concrete mixtures, as the substitution rate of GGBFS increased, the decreasing rate of the diffusion coefficient decreased based on exposure periods of 730 days(2 years). As the evaluation result of the diffusion behavior according to the marine exposure conditions, the diffusion coefficient was evaluated in the order of submerged area, tidal area, and splash area. In tidal area, a relatively high diffusion coefficient was evaluated due to the repetition of wet and dry seawater. In this study, the effects of GGBFS substitution rate on the decreasing behavior of apparent chloride diffusion coefficient was analyzed in consideration of exposure conditions and periods. Linear regression analysis was performed with apparent chloride diffusion coefficient as output value and GGBFS substitution rate as input value. After 730 days of exposure, the effect of GGBFS on diffusion coefficient was significantly reduced. Even for OPC concrete, after 730 days, the diffusion coefficient was as low as that of GGBFS concrete, so the gradient of the regression equation decreased significantly. It is thought that improved durability performance for chloride ingress can be secured before 730 days through the use of GGBFS.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.7
• /
• pp.299-306
• /
• 2022

In recent, sensors embedded in robots, equipment, and circuits have become common, and research for diagnosing device failures by learning measured sensor data is being actively conducted. This failure diagnosis study is divided into a classification model for predicting failure situations or types and a regression model for numerically predicting failure conditions. In the case of a classification model, it simply checks the presence or absence of a failure or defect (Class), whereas a regression model has a higher learning difficulty because it has to predict one value among countless numbers. So, the reason that regression modeling is more difficult is that there are many irregular situations in which it is difficult to determine one output from a similar input when predicting by matching input and output. Therefore, in this paper, we focus on input and output data with periodicity, analyze the input/output relationship, and secure regularity between input and output data by performing sliding window-based input data patterning. In order to apply the proposed method, in this study, current and temperature data with periodicity were collected from MMC(Modular Multilevel Converter) circuit system and learning was carried out using ANN. As a result of the experiment, it was confirmed that when a window of 2% or more of one cycle was applied, performance of 97% or more of fit could be secured.

• Journal of Internet Computing and Services
• /
• v.23 no.5
• /
• pp.79-85
• /
• 2022

Anomaly detection is a method to detect and block abnormal data flows in general users' data sets. The previously known method is a method of detecting and defending an attack based on a signature using the signature of an already known attack. This has the advantage of a low false positive rate, but the problem is that it is very vulnerable to a zero-day vulnerability attack or a modified attack. However, in the case of anomaly detection, there is a disadvantage that the false positive rate is high, but it has the advantage of being able to identify, detect, and block zero-day vulnerability attacks or modified attacks, so related studies are being actively conducted. In this study, we want to deal with these anomaly detection mechanisms, and we propose a new mechanism that performs both anomaly detection and classification while supplementing the high false positive rate mentioned above. In this study, the experiment was conducted with five configurations considering the characteristics of various algorithms. As a result, the model showing the best accuracy was proposed as the result of this study. After detecting an attack by applying the Extra Tree and Three-layer ANN at the same time, the attack type is classified using the Extra Tree for the classified attack data. In this study, verification was performed on the NSL-KDD data set, and the accuracy was 99.8%, 99.1%, 98.9%, 98.7%, and 97.9% for Normal, Dos, Probe, U2R, and R2L, respectively. This configuration showed superior performance compared to other models.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.24 no.3
• /
• pp.155-163
• /
• 2022

The optimization of long-range ensemble climate prediction for rice phenology model with advanced bias correction method is conducted. The daily long-range forecast(6-month) of mean/ minimum/maximum temperature and observation of January to October during 1991-2021 is collected for rice phenology prediction. In this study, the concept of "buffer period" is newly introduced to reduce the problem after bias correction by quantile mapping with constructing the transfer function by month, which evokes the discontinuity at the borders of each month. The four experiments with different lengths of buffer periods(5, 10, 15, 20 days) are implemented, and the best combinations of buffer periods are selected per month and variable. As a result, it is found that root mean square error(RMSE) of temperatures decreases in the range of 4.51 to 15.37%. Furthermore, this improvement of climatic variables quality is linked to the performance of the rice phenology model, thereby reducing RMSE in every rice phenology step at more than 75~100% of Automated Synoptic Observing System stations. Our results indicate the possibility and added values of interdisciplinary study between atmospheric and agriculture sciences.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.4
• /
• pp.48-56
• /
• 2022

Controlling the setting time of cementitious materials is one of the most important factors in securing early-age performance of concrete structures. Recently, the use of retarding admixtures, which enable the inhibition of some hydration products to control the securing time due to average temperature rise is suggested. Although various non-destructive evaluation methods have been proposed to evaluate cement hydration and hardening of cement-based materials to overcome the limitations of Vicat needle test, experimental research is still required to use the non-destructive evaluation method with added retarding admixtures. In this study, measurements of electrical resistivity and ultrasonic wave velocity in early-aged cement pastes were performed according to the addition of retarding admixture(tartaric acid). The setting time of the cement pastes was evaluated by obtained rising time of the both non-destructive measurements. As a result, the possibility of evaluating the setting delay in cement pastes was confirmed through comparative analysis with the initial and final setting times by Vicat test. In addition, X-ray diffraction results at the rising time of electrical resistivity showed a key hydration product affecting the setting delay.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.4
• /
• pp.73-80
• /
• 2022

This study evaluated changes in fluidity and rheological properties over time for 3D printed composite materials, and evaluated compressive strength and splitting tensile strength properties for laminated and molded specimens. The composite material for 3D printing starts to change rapidly after 30 minutes of extrusion, and the viscosity of the material tends to be maintained up to 90 minutes, but it was confirmed that construction within 60 minutes after mixing is effective. The compressive strength of the laminated test specimen showed equivalent or better performance at all ages compared to the molded test specimen. In the stress-strain curve of the laminated specimen, the initial slope was similar to that of the molded specimen, but the descending slope was on average 1.9 times higher than that of the molded specimen, indicating relatively brittle behavior. The splitting tensile strength of the P-V laminated specimen was about 6% lower than that of the molded specimen. It is judged that this is because the interfacial adhesion force against the vertical load is affected by the pattern direction of the laminated test specimen.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.25 no.5
• /
• pp.173-181
• /
• 2021

Reinforced concrete structures are exposed to various environments, resulting in reinforcement corrosion due to moisture and ions penetration. Reinforced concrete corrosion causes a decrease in the durability performance of reinforced concrete structures. One solution to mitigate such issues is using FRP rebars, which offer several advantages such as high tensile strength, corrosion resistance, and light-weight than conventional rebars, in reinforced concrete instead of conventional steel rebars. The FRP rebar used should be examined at the limit state because FRP reinforced concrete has linear behavior until its fracture and can generate excessive deflection due to the low elastic modulus. It should be considered while designing FRP reinforced concrete for flexure. In the ultimate limit state, the flexural strength of FRP reinforced concrete as per ACI 440.1R is significantly lower than the flexural strength by applying both the environmental reduction and strength reduction factors accounting for the material uncertainty of FRP rebar. Therefore, in this study, the experimental results were compared with the deflection of the proposed effective moment of inertia referring to the local and international standards. The experimental results of GFRP and BFRP reinforced concrete were compared with the flexural strength as determined by ACI 440.1R and Fib bulletin 40. The flexural strength obtained by the experimental results was more similar to that obtained by Fib bulletin 40 than ACI 440.1R. The flexural strength of ACI 440.1R was conservatively evaluated in the tension-controlled section.

• Journal of the Korean Geotechnical Society
• /
• v.38 no.12
• /
• pp.67-78
• /
• 2022

In this study, the measurement results of the coastal deep soft ground buried in the upper part of the dredged clay were analyzed and compared with the current specification standards. Based on the results, a suitable proposal was suggested for the selection, installation, data arrangement, and analysis of each instrument used in the deep soft ground improvement construction. The pore water pressure meter has a range of 1.5 times or more of the expected measurement range, considering the field conditions of the soft ground. The groundwater level meter installed in the horizontal drainage layer checks the change in the groundwater level during the embanking as well as the performance of the catchment well and the horizontal drainage layer. Therefore, it is important to manage so that the groundwater level exists inside the horizontal drainage layer during embanking. It is enough to install the inclinometer in the gravel layer below the soft ground or weathered rock with an N value of 40 or more for the deep soft ground. It seems desirable to install a screw type for differential settlement meter. However, the screw type should not settle due to its own weight. Considering that it is a dredged landfill where subsidence occurs significantly, it is sufficient to manage the tolerance of leveling at about 10 mm (L is the one-way distance (km)).

• Journal of Space Technology and Applications
• /
• v.1 no.1
• /
• pp.33-40
• /
• 2021

Based on the requirements of a total weight of 42 kg or less, the NEXTSat-2 SAR (synthetic aperture radar) system was developed. As the NEXTSat-2 is a small-sized satellite, the SAR system was designed to account for about 40% of the dry mass of the payload relative to the total mass. Among the major components of the SAR system - which are an antenna, an RF transceiver, a baseband signal processor, and a power unit - a part with a particularly large dry mass is the antenna, the core of the SAR system. Whereas various selections are possible in consideration of gain and efficiency when designing the antenna, the micro-strip patch array antenna was adopted by reflecting the dry mass, power, and resolution required by the NEXTSat-2 project. In order to meet the mission requirement of the NEXTSat-2, the antenna was developed with a frequency of 9.65 GHz, a gain of 42.7 dBi, and a return loss of -15 dB. The performance of the antenna was verified by conducting a field test onboard the vehicle.