• Korean Journal of Agricultural and Forest Meteorology
• /
• v.5 no.2
• /
• pp.128-137
• /
• 2003

Net radiation (Rn) is one of the most fundamental components in surface energy budget. For an accurate measurement of Rn, periodic and consistent calibrations of net radiometers are required. With a 4-month time interval, two field experiments were conducted to inter-compare and calibrate two types of net radiometers (the Q-7.1 and the CNR1), widely used in flux measurements. Differences between the Q-7.1 and the CNR1 net radiometers were within 7.7%, and the errors after calibration against the standard net radiometer were ＜3.2%. Radiometric responses and calibration factors appeared to have changed with sky renditions, especially temperature difference with season's progress. We concluded that the periodically calibrated Q-7.1 can replace more expensive, more accurate CNR1 net radiometer for long-term field measurements, providing that field calibrations of net radiometers are performed every 4-6 months interval.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.454-460
• /
• 2020

Artificial intelligence assistants that provide speech recognition operate through cloud-based voice recognition with high accuracy. In cloud-based speech recognition, Wake-Up-Word (WUW) detection plays an important role in activating devices on standby. In this paper, we compare the performance of Convolutional Neural Network (CNN)-based WUW detection models for mobile devices by using Google's speech commands dataset, using the spectrogram and mel-frequency cepstral coefficient features as inputs. The CNN models used in this paper are multi-layer perceptron, general convolutional neural network, VGG16, VGG19, ResNet50, ResNet101, ResNet152, MobileNet. We also propose network that reduces the model size to 1/25 while maintaining the performance of MobileNet is also proposed.

• Journal of Veterinary Clinics
• /
• v.37 no.5
• /
• pp.249-254
• /
• 2020

Neutrophil extracellular trap (NET) formation is an immune response for the invasion of microbes. The purpose of this study is to examine the effect of zinc on NET formation of porcine peripheral blood polymorphonuclear cells (PMNs). The NET formation of PMNs was measured by fluorescence microplate reader. The production of tumor necrosis factor (TNF)-α in the culture supernatants from zinc-treated peripheral blood mononuclear cells (PBMCs) was measured by enzyme-linked immunosorbent assay (ELISA). Zinc itself did not have no effect on NET formation. However, the NET formation of PMNs was increased by culture supernatants from PBMCs treated with zinc. Also, the NET formation of PMNs was increased by recombinant porcine (rp) TNF-α. The production of TNF-α in PBMCs culture supernatants was shown to increase upon zinc treatments. These NET formations of PMNs increased by either culture supernatant from PBMCs treated with zinc or rpTNF-α were inhibited by treatment of anti-rpTNF-α polyclonal antibody (pAb). These results suggested that zinc has an immunostimulating effect on the NET formation of PMNs, which is mediated by TNF-α released from zinc-treated PBMCs. Therefore, zinc may play an important role for NET formation in the defense of porcine inflammatory diseases.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.53 no.3
• /
• pp.246-255
• /
• 2017

The species composition and variation in abundance of fishery resources near Oenarodo, Go-heung Peninsula, Korea, were investigated by gill net, trap net, and longline in May, July, and October 2015 and 2016. During the study period, the total catch included 14 species in the gill net, 11 species in the trap net, and 4 species in the longline. The dominant species were Portunus trituberculatus and Raja pulchrain the gill net, Charybdis japonicaand and Octopus vulgarisin in the trap net, and Muraenesox cinereusin in the longline. The Catch Per Unit Effort (CPUE) per individual and per weight in the gill net were similar in May and July of 2015 and 2016. In October 2015, the CPUE per individual was 2.1 ind./h and the CPUE per weight was 505 g/h higher than the results in 2016, but there was no significant difference in the total CPUE between 2015 and 2016. In the trap net, the CPUE per weight was similar in both 2015 and 2016, but the CPUE per individual was 2.7 ind./h higher in October 2015 than in October 2016 and the total CPUE was not significantly different from 2015 to 2016. The CPUE per individual and weight in the longline were significantly higher in July and October 2015 than in the same months of 2016, but the total CPUE in 2015 and 2016 did not show a significant difference.

• Smart Media Journal
• /
• v.11 no.5
• /
• pp.48-55
• /
• 2022

Tomato crops are easy to expose to disease and spread in a short period of time, so late measures against disease are directly related to production and sales, which can cause damage. Therefore, there is a need for a service that enables early prevention by simply and accurately diagnosing tomato diseases in the field. In this paper, we construct a system that applies a deep learning-based model in which ImageNet transition is learned in advance to classify and serve nine classes of tomatoes for disease and normal cases. We use the input of MobileNet, ResNet, with a deep learning-based CNN structure that builds a lighter neural network using a composite product for the image set of leaves classifying tomato disease and normal from the Plant Village dataset. Through the learning of two proposed models, it is possible to provide fast and convenient services using MobileNet with high accuracy and learning speed.

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.267-274
• /
• 2023

There is a problem that the size of the dataset is insufficient due to the limitation of the collection of the medical image public data, so there is a possibility that the existing studies are overfitted to the public dataset. In this paper, we compare the performance of eight (Unet, X-Net, HarDNet, SegNet, PSPNet, SwinUnet, 3D-ResU-Net, UNETR) medical image semantic segmentation models to revalidate the superiority of existing models. Anatomical Tracings of Lesions After Stroke (ATLAS) V1.2, a public dataset for stroke diagnosis, is used to compare the performance of the models and the performance of the models in ATLAS V2.0. Experimental results show that most models have similar performance in V1.2 and V2.0, but X-net and 3D-ResU-Net have higher performance in V1.2 datasets. These results can be interpreted that the models may be overfitted to V1.2.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.1
• /
• pp.11-17
• /
• 2023

This paper proposes a lightweight deep learning network for detecting an image splicing forgery. The research on image forgery detection using CNN, a deep learning network, and research on detecting and localizing forgery in pixel units are in progress. Among them, CAT-Net, which learns the discrete cosine transform coefficients of images together with images, was released in 2022. The DCT coefficients presented by CAT-Net are combined with the JPEG artifact learning module and the backbone model as pre-learning, and the weights are fixed. The dataset used for pre-training is not included in the public dataset, and the backbone model has a relatively large number of network parameters, which causes overfitting in a small dataset, hindering generalization performance. In this paper, this learning module is designed to learn the characterization depending on the DCT domain in real-time during network training without pre-training. The DCT RRU-Net proposed in this paper is a network that combines RRU-Net which detects forgery by learning only images and JPEG artifact learning module. It is confirmed that the network parameters are less than those of CAT-Net, the detection performance of forgery is better than that of RRU-Net, and the generalization performance for various datasets improves through the network architecture and training method of DCT RRU-Net.

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.2
• /
• pp.253-259
• /
• 2024

This paper proposes a new speech enhancement model based on a complex nested U-Net with a dual-branch decoder. The proposed model consists of a complex nested U-Net to simultaneously estimate the magnitude and phase components of the speech signal, and the decoder has a dual-branch decoder structure that performs spectral mapping and time-frequency masking in each branch. At this time, compared to the single-branch decoder structure, the dual-branch decoder structure allows noise to be effectively removed while minimizing the loss of speech information. The experiment was conducted on the VoiceBank + DEMAND database, commonly used for speech enhancement model training, and was evaluated through various objective evaluation metrics. As a result of the experiment, the complex nested U-Net-based speech enhancement model using a dual-branch decoder increased the Perceptual Evaluation of Speech Quality (PESQ) score by about 0.13 compared to the baseline, and showed a higher objective evaluation score than recently proposed speech enhancement models.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.4
• /
• pp.25-34
• /
• 2024

This paper presents the development of a mobile application that detects and identifies canine skin diseases by training a deep learning-based U-Net model to infer the presence and location of skin lesions from images. U-Net, primarily used in medical imaging for image segmentation, is effective in distinguishing specific regions of an image in a polygonal form, making it suitable for identifying lesion areas in dogs. In this study, six major canine skin diseases were defined as classes, and the U-Net model was trained to differentiate among them. The model was then implemented in a mobile app, allowing users to perform lesion analysis and prediction through simple camera shots, with the results provided directly to the user. This enables pet owners to monitor the health of their pets and obtain information that aids in early diagnosis. By providing a quick and accurate diagnostic tool for pet health management through deep learning, this study emphasizes the significance of developing an easily accessible service for home use.

• Korean Journal of Medicinal Crop Science
• /
• v.15 no.3
• /
• pp.194-198
• /
• 2007

Yield and ginsenoside contents of ginseng (Panax ginseng C. A. Meyer) is affected by light intensity and quality, and the color and the thickness of PE shading net when PE net is utilized for shading material. This study was carried out to investigate the effect of light quality on root yield and ginsenoside contents off-year-old ginseng by using polyethylene shading net with each blue and yellow color, Spectral irradiance under blue and yellow shading net showed the peak at 498 nm and 606 nm, respectively, which made distinct difference in light quality. Heat injury ratio of blue shading net was increased distinctly more than that of yellow shading net in summer season because of higher transmitted quantum (23%)and air temperature (0.3 $^{\circ}$C) in blue shading net than those of yellow shading net. Chlorophyll content and leaf area under yellow shading net were higher than those of blue shading net, and its heat injury ratio was lower than those of blue. These effects may led to 48% higher increase of root yield under yellow shading net than that under blue shading net. The content of total ginsenoside in taproot was not significantly differed between blue and yellow shading net, while the content in lateral and fine root was significantly increased in blue shading net compared to yellow shading net. PDM ratio of blue shading net showed more significant increase in lateral root than that of yellow shading net. All of Rb$_1$/Rg$_1$ ratio in three parts of root under blue shading net was higher than that of yellow shading net, but there were no significant increase in the ratio of lateral root.