• Journal of the Korean Society for Railway
• /
• v.20 no.4
• /
• pp.433-439
• /
• 2017

Urban railway tunnels are polluted by resuspension of deposited bottom dust or newly generated wear dust. A hybrid type dust collector consisting of a baffle and an electrostatic precipitator was developed to remove these types of airborne dust when trains are running in the tunnel. Since dust collection efficiency of the hybrid dust collector is inversely proportional to the airflow rate, the relationship between airflow rate and dust collection efficiency was experimentally investigated for two baffle models. Collection efficiencies for dust larger than $0.5{\mu}m$ for the hybrid dust collector model A1, operated at 3.4 m/s, were greater than 30%; those for the hybrid dust collector model A2, operated at 4.7 m/s, were higher than 20%. When the applied voltage was 13 kV, the amounts of $PM_{10}$ collected with model A1 and model A2 dust collectors were estimated at $253{\mu}g$ and $242{\mu}g$ per hour, respectively.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_1
• /
• pp.1685-1695
• /
• 2021

To generate a deep learning model with high performance, a large training dataset should be required. However, it requires a lot of time and cost to generate a large training dataset in remote sensing. Therefore, the importance of transfer learning of deep learning model using a small dataset have been increased. In this paper, we performed transfer learning of trained model based on open datasets by using orthoimages and digital maps to detect changes of building objects in multitemporal orthoimages. For this, an initial training was performed on open dataset for change detection through the HRNet-v2 model, and transfer learning was performed on dataset by orthoimages and digital maps. To analyze the effect of transfer learning, change detection results of various deep learning models including deep learning model by transfer learning were evaluated at two test sites. In the experiments, results by transfer learning represented best accuracy, compared to those by other deep learning models. Therefore, it was confirmed that the problem of insufficient training dataset could be solved by using transfer learning, and the change detection algorithm could be effectively applied to various remote sensed imagery.

• Journal of Broadcast Engineering
• /
• v.26 no.2
• /
• pp.125-131
• /
• 2021

In recent years, Convolutional Neural Networks (CNNs) have achieved outstanding performance in the fields of computer vision such as image classification, object detection, visual quality enhancement, etc. However, as huge amount of computation and memory are required in CNN models, there is a limitation in the application of CNN to low-power environments such as mobile or IoT devices. Therefore, the need for neural network compression to reduce the model size while keeping the task performance as much as possible has been emerging. In this paper, we propose a method to compress CNN models by combining matrix decomposition methods of LR (Low-Rank) approximation and CP (Canonical Polyadic) decomposition. Unlike conventional methods that apply one matrix decomposition method to CNN models, we selectively apply two decomposition methods depending on the layer types of CNN to enhance the compression performance. To evaluate the performance of the proposed method, we use the models for image classification such as VGG-16, RestNet50 and MobileNetV2 models. The experimental results show that the proposed method gives improved classification performance at the same range of 1.5 to 12.1 times compression ratio than the existing method that applies only the LR approximation.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.33-43
• /
• 2024

This research assessed the applicability of the You Only Look Once (YOLO)v8 and DeepLabv3+ models for the effective detection of compost heaps, identified as a significant source of non-point source pollution. Utilizing high-resolution imagery acquired through Unmanned Aerial Vehicles(UAVs), the study conducted a comprehensive comparison and analysis of the quantitative and qualitative performances. In the quantitative evaluation, the YOLOv8 model demonstrated superior performance across various metrics, particularly in its ability to accurately distinguish the presence or absence of covers on compost heaps. These outcomes imply that the YOLOv8 model is highly effective in the precise detection and classification of compost heaps, thereby providing a novel approach for assessing the management grades of compost heaps and contributing to non-point source pollution management. This study suggests that utilizing UAVs and deep learning technologies for detecting and managing compost heaps can address the constraints linked to traditional field survey methods, thereby facilitating the establishment of accurate and effective non-point source pollution management strategies, and contributing to the safeguarding of aquatic environments.

• Journal of the Korean Applied Science and Technology
• /
• v.41 no.2
• /
• pp.472-483
• /
• 2024

This study evaluated the attitudes of the Korean population towards sunscreen use through the Health Belief Model (HBM) construct and investigated the psychological factors that influence sunscreen use. For this purpose, an online survey was conducted from 1 November 2023 to 1 January 2024, and a total of 303 participants were collected. The collected data were analysed using SPSS v. 25.0 programme using Cronbach's 𝛼, frequency analysis, descriptive statistics, correlation analysis, independent samples t-test, one way ANOVA, Scheffe's test, and multiple regression analysis. The results of the study showed that the mean score of sunscreen use was 3.26±1.384 out of 5, and there was a significant correlation between the variables of the health belief model and sunscreen use (p<.01). Gender, age, and skin colour were also associated with each variable, with women, the elderly, and those with lighter skin tending to be more proactive in sun protection. Multiple regression analyses revealed that self-efficacy (𝛽=.629, p<.001) and perceived vulnerability (𝛽=.139, p<.001), sub-factors of the Health Belief Model, had a statistically significant positive effect on sunscreen use, while perceived barriers (𝛽=-.261, p<.001) had a statistically significant negative effect on sunscreen use. These results may have important theoretical implications for the development and implementation of educational programmes to promote sunscreen use by providing insight into the psychosocial factors that influence sun protection.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.4
• /
• pp.99-107
• /
• 2017

This paper proposes a battery model coefficient correction method for improving the accuracy of existing lithium battery equivalent models. BMS(battery management system) has been researched and developed to minimize shortening of battery life by keeping SOC(state of charge) and state of charge of lithium battery used in various industrial fields such as EV. However, the cell balancing operation based on the battery cell voltage can not follow the SOC change due to the internal resistance and the capacitor. Various battery equivalent models have been studied for estimation of battery SOC according to the internal resistance of the battery and capacitors. However, it is difficult to apply the same to all the batteries, and it tis difficult to estimate the battery state in the transient state. The existing battery electrical equivalent model study simulates charging and discharging dynamic characteristics of one kind of battery with error rate of 5~10% and it is not suitable to apply to actual battery having different electric characteristics. Therefore, this paper proposes a battery model coefficient correction algorithm that is suitable for real battery operating environments with different models and capacities, and can simulate dynamic characteristics with an error rate of less than 5%. To verify proposed battery model coefficient calibration method, a lithium battery of 3.7V rated voltage, 280 mAh, 1600 mAh capacity used, and a two stage RC tank model was used as an electrical equivalent model of a lithium battery. The battery charge/discharge test and model verification were performed using four C-rate of 0.25C, 0.5C, 0.75C, and 1C. The proposed battery model coefficient correction algorithm was applied to two battery models, The error rate of the discharge characteristics and the transient state characteristics is 2.13% at the maximum.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.193-205
• /
• 2023

A large amount of floating debris from land-based sources during heavy rainfall has negative social, economic, and environmental impacts, but there is a lack of monitoring systems for floating debris accumulation areas and amounts. With the recent development of artificial intelligence technology, there is a need to quickly and efficiently study large areas of water systems using drone imagery and deep learning-based object detection models. In this study, we acquired various images as well as drone images and trained with You Only Look Once (YOLO)v5s and the recently developed YOLO7 and YOLOv8s to compare the performance of each model to propose an efficient detection technique for land-based floating debris. The qualitative performance evaluation of each model showed that all three models are good at detecting floating debris under normal circumstances, but the YOLOv8s model missed or duplicated objects when the image was overexposed or the water surface was highly reflective of sunlight. The quantitative performance evaluation showed that YOLOv7 had the best performance with a mean Average Precision (intersection over union, IoU 0.5) of 0.940, which was better than YOLOv5s (0.922) and YOLOv8s (0.922). As a result of generating distortion in the color and high-frequency components to compare the performance of models according to data quality, the performance degradation of the YOLOv8s model was the most obvious, and the YOLOv7 model showed the lowest performance degradation. This study confirms that the YOLOv7 model is more robust than the YOLOv5s and YOLOv8s models in detecting land-based floating debris. The deep learning-based floating debris detection technique proposed in this study can identify the spatial distribution of floating debris by category, which can contribute to the planning of future cleanup work.

• Korean Journal of Food Science and Technology
• /
• v.36 no.4
• /
• pp.580-585
• /
• 2004

Respiration of 'Fuyu' persimmon (Diospyros kaki) fruits were measured in terms of oxygen consumption rate and carbon dioxide evolution by closed system experiments at 0, 5, and $20^{\circ}C$. Enzyme kinetics-based respiration model was used to describe respiration rate as function of $O_2\;and\;CO_2$ gas concentrations $(R=V_m[O_2]/K_m+(1+[CO_2]/K_i)[O_2])$, and Arrhenius equation was applied to analyze temperature effect. $V_m\;and\;K_m$ increased, while $K_i$ decreased, with increasing temperature. $K_m\;of\;O_2$ consumption was greater than that of $CO_2$ evolution at equal temperature. Inhibitory effect of reduced $O_2$ level on $O_2$ consumption was more prominent than that on $CO_2$ evolution. Activation energy of respiration decreased with reduced $O_2$ and elevated $CO_2$ concentrations. Activation energy of $CO_2$ evolution was greater than that of $O_2$ consumption. Permeable package experiments verified respiration model parameters by showing good agreement between predicted and experimental gas concentrations in package.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 1991.06a
• /
• pp.37-44
• /
• 1991

영산강 하구언 방조제의 건설로 인한 항만 및 이의 인접해역 해면의 변화는 예상한 바 있으며 실제 여러개소에서 월 2회정도의 주기로 목포 구항부근 상업지역에서 해면상승에 따라 주기적으로 침수되는 현상이 나타나고 있다 목포항의 영산강 하구언 방조제 조성으로 인한 조류성분중 최고기록을 가진 수로에서는 6kts 정도로 감소된 것으로 보고되고 있으나 주위자연환경 변화에 따른 수면 상승 및 해수면의 주기적인 변화 등에 대한 상세한 언급 및 깊이 있는 분석은 회피되어왔다. 수자원의 효율적관리를 위해 하구언 방조제는 이미 건설되었고 앞으로 대규모의 항만개발과 대불산업단지조성을 위해 추가 3개의 만입해안해역에 댐으로 해역을 막아 매립공사를 추진하고 있다 그러나 이 지역에 대한 분석은 타당성의 여부만을 강조한 상업적 용역이 이루어지고 있고 장래 개발에 대해 학술적이고 실질적인 문제점 추출과 해결방아네 대해서는 무시하거나 경시한 바가 많다 더구나 태풍 저기압 등과 같은 자연재해를 고려한 분석은 시도되지 못하고 있다 따라서 개발전후의 현상에 대한 상세한 자료 및 현장 조사와 극한 상태를 고려하여 개발에 따른 수위상승 부진동, 조류 수질등 이해역의 변화요소를 수집하고 분석하며 과학적 접근방법에 기초를 둔 수치모델의 실험을 포함하여 현장관측 및 측정자료를 검증하는 것이 필수적이라고 사료되어 종합분석의 한단계로 여기서는 하구언 및 하구간척(Land Reclamatic of Estuary barren)으로 해역축소에 따른 해면변화의 실제현상을 조사하여 정리하고 이를 수치모델을 통해 시뮬레이션하여 보았다 이는 종합개발의 좋은 기초자료로 이용됨은 물론이로 이지역의 개발에 기여할 것으로본다.적절하게 가정된 지반의 응력-변형률 관계와 간극수압특성에 의하여 고려되었다. 그 결과 응력 및 변위가 심하게 발생하는 지역은 황색 점토층이었으며 이로부터 황색 점토층에서 부터 파괴면이 생성되어 다른 지역으로 전파되었음을 유추할 수 있었다.form trap with 2.88[eV] deep of injected space charge from the chathode in the crystaline regions. The origin of ${\alpha}$$_2$ peak was regarded as the detrapping process of ions trapped with 0.9[eV] deep originated from impurity-ion remained in the specimen during production process of the material, in the crystalline regions. The origin of ${\beta}$ peak was concluded to be due to the depolarization process of "C=0"dipole with the activation energy of 0.75[eV] in the amorphous regions. The origin of ${\gamma}$ peak was responsible to the process combined with the depolarization of "CH$_3$", chain segment, with the activation energy of ca

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.24 no.2
• /
• pp.60-67
• /
• 2020

Recently, many studies have been conducted on the structural behavior of HPFRCC, but most of the studies focused on the flexural behavior while studies on the shear behavior are limited. In this study, a model has been developed to reasonably predict the shear strength of a HPFRCC beam without stirrups. To develop the model, a HPFRCC beam was simply idealized with upper & lower chords resisting bending moment and a web shear element resisting shear forces. Then, taking into the account of the tensile behavior of HPFRCC, the main diagonal compressive strut angle and shear stress of the web shear element were evaluated on shear failure. Then, the shear strength of the HPFRCC beam could be evaluated. For the verification of the proposed model, the predictions by the proposed model were compared with the test results of 48 HPFRCC beams exhibiting shear failure. The results showed that the proposed model reasonably predicted the actual shear strength with an average of 1.045 and CoV of 0.125. This study are expected to be useful for related researches and design of members or structures to which HPFRCC is applied.