• 스마트미디어저널
• /
• 제11권4호
• /
• pp.62-68
• /
• 2022

수산 양식장 질병 감염의 확산을 사전에 차단을 위해서는 양식장의 수질 환경 및 생육 어류의 상태를 실시간 모니터링하면서 어류의 질병을 예측하는 시스템이 필요하다. 어류 질병 예측의 기존 연구는 이미지 처리 기법이 대부분이었으나 최근에는 딥러닝 기법을 통한 질병 예측방법의 연구가 활발히 진행되고 있다. 본 논문에서는 수산 양식장에서 발생할 수 있는 넙치의 질병을 딥러닝 기술로 예측하는 방법에 대한 연구결과를 소개하고자 한다. 이 방법은 양식장에서 수집된 카메라 영상에 데이터 증강과 전처리 포함하여 질병 인식률의 성능을 높인다. 이것을 통해 질병 어류를 조기 발견으로 양식 어업에서 어류 집단 폐사 등 어업 재해를 예방하고 지역 수산 양식장으로 어류의 질병 확산 피해를 줄여 매출액 감소 차단될 것으로 기대한다.

• 한국안전학회지
• /
• 제37권2호
• /
• pp.35-42
• /
• 2022

When an accident occurs, the associated human activity is typically regarded as a "human error," or a temporal deviation. On the other hand, if the accident results in a serious loss or if it evokes a social issue, the person determined to be responsible may be punished with a "violation" of related laws or regulations. However, as Heinrich stated, it is neither appropriate nor reasonable in terms of probability theory and cognitive science to distinguish whether it is a "human error" or a "violation" with a criterion of resultant accident severity. Nonetheless, some in society get on the social climate to strengthen regulations on workers who have caused accidents, especially violations. This response can present a social issue due to the lack of systematic judgment procedure which distinguishes violations from human errors. The purpose of this study was to develop an objective and systematic procedure to assess whether workers' activities which induced industrial accidents should be categorized as violations rather than human errors. Various analysis techniques for the determination of violation procedure were investigated and compared using an analysis approach method. An appropriate technique was not found, however, for judging the culpability of intentional violations. As an alternative, this study developed the process of creating violations, based on cognitive procedure, as well as the criteria to determine and categorize an activity as a violation. In addition, the developed procedure was applied to cases of industrial accidents and nuclear power plant issues to test its practical applicability. The study demonstrated that the proposed model could be used to determine the existence of a violation even in the case of multiple workers who work simultaneously.

• 대한원격탐사학회지
• /
• 제38권6_1호
• /
• pp.1081-1089
• /
• 2022

본 연구는 시계열 Small Baseline Subset (SBAS)-InSAR 기법을 이용하여 울산시의 지반 침하를 조사하였으며, 79개의 Sentinel-1 SAR 영상과 385개의 간섭도 영상(interferogram)을 사용하여 2015년 5월부터 2021년 12월 울산광역시의 지상 변위(surface displacement)를 추정하였다. 지반 침하율은 북구와 남구 삼산동 2지역에서 연 3.44 cm, 1.68 cm로 계측되었다. 또한 Generic Atmospheric Correction Online Service (GACOS)로 생성한 Zenith Total Delay (ZTD) 지도를 활용하여 unwrapping된 간섭도 위상에서 대기 지연(tropospheric delay)의 영향을 제거할 수 있는 가능성을 평가하였으며, GACOS ZTD 보정 전후의 SBAS-InSAR 지상 변위 측정의 차이가 연 1 mm 미만임을 발견하였다.

• 한국환경복원기술학회지
• /
• 제25권5호
• /
• pp.29-41
• /
• 2022

Alien species cause problems in various ecosystems, reduce biodiversity, and destroy ecosystems. Due to these problems, the problem of a management plan is increasing, and it is difficult to accurately identify each individual and calculate the number of individuals, especially when researching alien turtle species such as GPS and PIT based on capture. this study intends to conduct an individual recognition study using a UAV. Recently, UAVs can take various sensor-based photos and easily obtain high-definition image data at low altitudes. Therefore, based on previous studies, this study investigated five variables to be considered in UAV flights and produced a test paper using them. OCR was used to monitor the displayed turtles using the manufactured test paper, and this confirmed the recognition rate. As a result, the use of yellow numbers showed the highest recognition rate. In addition, the minimum threat distance was confirmed to be 3 to 6m, and turtles with a shell size of 6 to 8cm were also identified during the flight. Therefore, we tried to propose an object recognition methodology for turtle display text using OCR, and it is expected to be used as a new turtle monitoring technique.

• 한국환경복원기술학회지
• /
• 제25권5호
• /
• pp.77-88
• /
• 2022

This study aims to understand the relationship between the distribution of fish species in the two water ecosystems and the habitat factors according to the survey period targeting Gwanggyo Lake Park in the city. There are studies on the appearance and distribution of species by applying eDNA to freshwater ecosystems. However, in the domestic, streams are the target, and studies on the relationship between species distribution and habitat environment in two water environments are lacking. We conducted to analyze the species list and relationship with habitat factors using eDNA research in May and October at 21 points in Gwanggyo Lake Park, Suwon City, which were connected to lakes and streams. As a result, there was no species difference in the water environment according to the survey period. However, the total number of reads during the spawning season(May) was 3,126,482, which was more than double that after the spawning season(October). Tolerant species appeared in Woncheon Lake with a slow or stagnant flow, but there was no significant correlation between species and habitat factors depending on the survey period. On the other hand, intermediate and sensitive species appeared in the Woncheon stream with high flow. There was a significant correlation between the low temperature during the spawning season and the high dissolved oxygen content after the spawning season(P<0.001, Tem.: 20.7±2.6℃, DO: 8.6±1.7). It is expected that environmental DNA will be used to survey species and suggest monitoring methods according to the survey period.

• 인간식물환경학회지
• /
• 제23권3호
• /
• pp.333-345
• /
• 2020

Background and objective: The purpose of this study was to provide basic data on trees that can be used for planting design and construction for permanently shaded areas by grasping the growth status of trees according to the daylight conditions of the outdoor spaces of apartment complexes. Methods: On the recently completed apartment complexes, daylight conditions were analyzed by using daylight simulations utilizing Solar Access Analysis of Ecotect Analysis. With a criteria for assessment of tree condition, the defect rate of trees planted in permanently shaded areas and green spaces with good daylight conditions was analyzed to suggest trees applicable to permanently shaded areas. The first tree survey was conducted from November 18, 2019 to February 15, 2020, focusing on trees planted in permanently shaded areas, and the second tree survey of all the trees planted on the study sites including permanently shaded areas was conducted from March 16 to March 30, 2020. Results: Evergreen trees which are classified as shade intolerant trees including Pinus densiflora, Thuja occidentalis, and Abies holophylla showed a higher defect rate of trees among the trees planted in permanently shaded areas. Taxus cuspidata, Zelkova serrata, Cornus kousa, Chionanthus retusus and Acer palmatum which are classified as shade tolerant trees and shade moderate tolerance trees seemed to be able to be used in the plant design of permanently shaded areas in apartment complexes because the trees showed good growth and a low tree defect rate. In addition, although it was excluded from the analysis due to a small number of samples, Sorbus commixta and Prunus cerasifera var. atropurpurea also can be used for planting in permanently shaded areas. Conclusion: The daylight simulation technique used to analyze permanent shaded areas in this study can be used as an analysis tool considering the daylight environment at the stages of design and construction, and additional research will be required to analyze tree growth according to daylight conditions through data accumulation and monitoring by managing records throughout the entire life cycle of trees in the process of planting and maintenance.

• Smart Structures and Systems
• /
• 제30권1호
• /
• pp.75-88
• /
• 2022

Engineering structures in operation essentially belong to time-varying or nonlinear structures and the resultant response signals are usually non-stationary. For such time-varying structures, it is of great importance to extract time-dependent dynamic parameters from non-stationary response signals, which benefits structural health monitoring, safety assessment and vibration control. However, various traditional signal processing methods are unable to extract the embedded meaningful information. As a newly developed technique, variational mode decomposition (VMD) shows its superiority on signal decomposition, however, it still suffers two main problems. The foremost problem is that the number of modal components is required to be defined in advance. Another problem needs to be addressed is that VMD cannot effectively separate non-stationary signals composed of closely spaced or overlapped modes. As such, a new method named generalized adaptive variational modal decomposition (GAVMD) is proposed. In this new method, the number of component signals is adaptively estimated by an index of mean frequency, while the generalized demodulation algorithm is introduced to yield a generalized VMD that can decompose mode overlapped signals successfully. After that, synchrosqueezing wavelet transform (SWT) is applied to extract instantaneous frequencies (IFs) of the decomposed mono-component signals. To verify the validity and accuracy of the proposed method, three numerical examples and a steel cable with time-varying tension force are investigated. The results demonstrate that the proposed GAVMD method can decompose the multi-component signal with overlapped modes well and its combination with SWT enables a successful IF extraction of each individual component.

• Journal of Veterinary Science
• /
• 제21권3호
• /
• pp.45.1-45.15
• /
• 2020

Background: Feline mammary carcinoma is the third most common cancer that affects female cats. Objectives: The purpose of this study was to screen differential serum proteins in feline and clarify the relationship between them and the occurrence of feline mammary carcinoma. Methods: Chinese pastoral cats were used as experimental animals. Six serum samples from cats with mammary carcinoma (group T) and six serum samples from healthy cats (group C) were selected. Differential protein analysis was performed using a Label-free technique, while parallel reaction monitoring (PRM) was performed to verify the screened differential proteins. Results: A total of 82 differential proteins were detected between group T and group C, of which 55 proteins were down regulated and 27 proteins were up regulated. Apolipoprotein A-I, Apolipoprotein A-II (ApoA-II), Apolipoprotein B (ApoB), Apolipoprotein C-III (ApoC-III), coagulation factor V, coagulation factor X, C1q, albumen (ALB) were all associated with the occurrence of feline mammary carcinoma. Differential proteins were involved in a total of 40 signaling pathways, among which the metabolic pathways associated with feline mammary carcinoma were the complement and coagulation cascade and cholesterol metabolism. According to the Label-free results, ApoB, ApoC-III, ApoA-II, FN1, an uncharacterized protein, and ALB were selected for PRM target verification. The results were consistent with the trend of the label-free. Conclusions: This experimen is the first to confirm ApoA-II and ApoB maybe new feline mammary carcinoma biomarkers and to analyze their mechanisms in the development of such carcinoma in feline.

• 한국해양공학회지
• /
• 제36권1호
• /
• pp.32-40
• /
• 2022

Underwater optical images face various limitations that degrade the image quality compared with optical images taken in our atmosphere. Attenuation according to the wavelength of light and reflection by very small floating objects cause low contrast, blurry clarity, and color degradation in underwater images. We constructed an image data of the Korean sea and enhanced it by learning the characteristics of underwater images using the deep learning techniques of CycleGAN (cycle-consistent adversarial network), UGAN (underwater GAN), FUnIE-GAN (fast underwater image enhancement GAN). In addition, the underwater optical image was enhanced using the image processing technique of Image Fusion. For a quantitative performance comparison, UIQM (underwater image quality measure), which evaluates the performance of the enhancement in terms of colorfulness, sharpness, and contrast, and UCIQE (underwater color image quality evaluation), which evaluates the performance in terms of chroma, luminance, and saturation were calculated. For 100 underwater images taken in Korean seas, the average UIQMs of CycleGAN, UGAN, and FUnIE-GAN were 3.91, 3.42, and 2.66, respectively, and the average UCIQEs were measured to be 29.9, 26.77, and 22.88, respectively. The average UIQM and UCIQE of Image Fusion were 3.63 and 23.59, respectively. CycleGAN and UGAN qualitatively and quantitatively improved the image quality in various underwater environments, and FUnIE-GAN had performance differences depending on the underwater environment. Image Fusion showed good performance in terms of color correction and sharpness enhancement. It is expected that this method can be used for monitoring underwater works and the autonomous operation of unmanned vehicles by improving the visibility of underwater situations more accurately.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.17-28
• /
• 2022

The cable component of cable-stayed bridges is gradually impacted by weather conditions, vehicle loads, and material corrosion. The stayed cable is a critical load-carrying part that closely affects the operational stability of a cable-stayed bridge. Damaged cables might lead to the bridge collapse due to their tension capacity reduction. Thus, it is necessary to develop structural health monitoring (SHM) techniques that accurately identify damaged cables. In this work, a combinational identification method of three efficient techniques, including statistical analysis, clustering, and neural network models, is proposed to detect the damaged cable in a cable-stayed bridge. The measured dataset from the bridge was initially preprocessed to remove the outlier channels. Then, the theory and application of each technique for damage detection were introduced. In general, the statistical approach extracts the parameters representing the damage within time series, and the clustering approach identifies the outliers from the data signals as damaged members, while the deep learning approach uses the nonlinear data dependencies in SHM for the training model. The performance of these approaches in classifying the damaged cable was assessed, and the combinational identification method was obtained using the voting ensemble. Finally, the combination method was compared with an existing outlier detection algorithm, support vector machines (SVM). The results demonstrate that the proposed method is robust and provides higher accuracy for the damaged cable detection in the cable-stayed bridge.