• Asian-Australasian Journal of Animal Sciences
• /
• v.29 no.1
• /
• pp.36-42
• /
• 2016

Milk-related traits (milk yield, fat and protein) have been crucial to selection of Holstein. It is essential to find the current selection trends of Holstein. Despite this, uncovering the current trends of selection have been ignored in previous studies. We suggest a new formula to detect the current selection trends based on single nucleotide polymorphisms (SNP). This suggestion is based on the best linear unbiased prediction (BLUP) and the Fisher's fundamental theorem of natural selection both of which are trait-dependent. Fisher's theorem links the additive genetic variance to the selection coefficient. For Holstein milk production traits, we estimated the additive genetic variance using SNP effect from BLUP and selection coefficients based on genetic variance to search highly selective SNPs. Through these processes, we identified significantly selective SNPs. The number of genes containing highly selective SNPs with p-value <0.01 (nearly top 1% SNPs) in all traits and p-value <0.001 (nearly top 0.1%) in any traits was 14. They are phosphodiesterase 4B (PDE4B), serine/threonine kinase 40 (STK40), collagen, type XI, alpha 1 (COL11A1), ephrin-A1 (EFNA1), netrin 4 (NTN4), neuron specific gene family member 1 (NSG1), estrogen receptor 1 (ESR1), neurexin 3 (NRXN3), spectrin, beta, non-erythrocytic 1 (SPTBN1), ADP-ribosylation factor interacting protein 1 (ARFIP1), mutL homolog 1 (MLH1), transmembrane channel-like 7 (TMC7), carboxypeptidase X, member 2 (CPXM2) and ADAM metallopeptidase domain 12 (ADAM12). These genes may be important for future artificial selection trends. Also, we found that the SNP effect predicted from BLUP was the key factor to determine the expected current selection coefficient of SNP. Under Hardy-Weinberg equilibrium of SNP markers in current generation, the selection coefficient is equivalent to $2^*SNP$ effect.

• Convergence Security Journal
• /
• v.21 no.1
• /
• pp.191-200
• /
• 2021

Artificial intelligence technology is developing in an environment where a lot of data is produced due to the development of computing technology, a cloud environment that can store data, and the spread of personal mobile phones. Among these artificial intelligence technologies, the deep neural network provides excellent performance in image recognition and image classification. There have been many studies on image detection for forest fires and fire prevention using such a deep neural network, but studies on detection of cigarette smoking were insufficient. Meanwhile, military units are establishing surveillance systems for various facilities through CCTV, and it is necessary to detect smoking near ammunition stores or non-smoking areas to prevent fires and explosions. In this paper, by reflecting experimentally optimized numerical values such as activation function and learning rate, we did the detection of smoking pictures and non-smoking pictures in two cases. As experimental data, data was constructed by crawling using pictures of smoking and non-smoking published on the Internet, and a machine learning library was used. As a result of the experiment, when the learning rate is 0.004 and the optimization algorithm Adam is used, it can be seen that the accuracy of 93% and F1-score of 94% are obtained.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.5
• /
• pp.7-14
• /
• 2021

Tomato crops are highly affected by tomato diseases, and if not prevented, a disease can cause severe losses for the agricultural economy. Therefore, there is a need for a system that quickly and accurately diagnoses various tomato diseases. In this paper, we propose a system that classifies nine diseases as well as healthy tomato plants by applying various pretrained deep learning-based CNN models trained on an ImageNet dataset. The tomato leaf image dataset obtained from PlantVillage is provided as input to ResNet, Xception, and DenseNet, which have deep learning-based CNN architectures. The proposed models were constructed by adding a top-level classifier to the basic CNN model, and they were trained by applying a 5-fold cross-validation strategy. All three of the proposed models were trained in two stages: transfer learning (which freezes the layers of the basic CNN model and then trains only the top-level classifiers), and fine-tuned learning (which sets the learning rate to a very small number and trains after unfreezing basic CNN layers). SGD, RMSprop, and Adam were applied as optimization algorithms. The experimental results show that the DenseNet CNN model to which the RMSprop algorithm was applied output the best results, with 98.63% accuracy.

• Journal of the Korean Society of Radiology
• /
• v.16 no.3
• /
• pp.295-302
• /
• 2022

Sparse-view computed tomography (CT) imaging technique is able to reduce radiation dose, ensure the uniformity of image characteristics among projections and suppress noise. However, the reconstructed images obtained by the sparse-view CT imaging technique suffer from severe artifacts, resulting in the distortion of image quality and internal structures. In this study, we proposed a convolutional neural network (CNN) with wavelet transformation and residual learning for reducing artifacts in sparse-view CT image, and the performance of the trained model was quantitatively analyzed. The CNN consisted of wavelet transformation, convolutional and inverse wavelet transformation layers, and input and output images were configured as sparse-view CT images and residual images, respectively. For training the CNN, the loss function was calculated by using mean squared error (MSE), and the Adam function was used as an optimizer. Result images were obtained by subtracting the residual images, which were predicted by the trained model, from sparse-view CT images. The quantitative accuracy of the result images were measured in terms of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). The results showed that the trained model is able to improve the spatial resolution of the result images as well as reduce artifacts in sparse-view CT images effectively. Also, the trained model increased the PSNR and SSIM by 8.18% and 19.71% in comparison to the imaging model trained without wavelet transformation and residual learning, respectively. Therefore, the imaging model proposed in this study can restore the image quality of sparse-view CT image by reducing artifacts, improving spatial resolution and quantitative accuracy.

• Journal of Software Assessment and Valuation
• /
• v.17 no.1
• /
• pp.101-113
• /
• 2021

In this paper, we introduce a speaker overlap system and look at the process of converting the existed system on the specific framework of artificial intelligence. Speaker overlap is when two or more speakers speak at the same time during a conversation, and can lead to performance degradation in the fields of speech recognition or speaker recognition, and a lot of research is being conducted because it can prevent performance degradation. Recently, as application of artificial intelligence is increasing, there is a demand for switching between artificial intelligence frameworks. However, when switching frameworks, performance degradation is observed due to the unique characteristics of each framework, making it difficult to switch frameworks. In this paper, the process of converting the speaker overlap detection system based on the Keras framework to the pytorch-based system is explained and considers components. As a result of the framework switching, the pytorch-based system showed better performance than the existing Keras-based speaker overlap detection system, so it can be said that it is valuable as a fundamental study on systematic framework conversion.

• Korean Journal of Mineralogy and Petrology
• /
• v.35 no.3
• /
• pp.273-281
• /
• 2022

Mantle heterogeneity is closely related to the distribution and circulation of volatile components in the Earth's interior, and the behavior of volatiles in the mantle strongly influences the rheological properties of silicate rocks. In mantle xenoliths, these physicochemical properties of the upper mantle can be recorded in the form of microstructures and fluid inclusions. In this paper, I summarized and reviewed the results of previous studies related to the characteristics of microstructures and fluid inclusions from peridotite xenoliths beneath the Rio Grande Rift (RGR) in order to understand the evolution and heterogeneity of upper mantle. In the RGR, the mantle peridotites are mainly reported in the rift axis (EB: Elephant Butte, KB: Kilbourne Hole) and rift flank (AD: Adam's Diggings) regions. In the case of the former (EB and KB peridotites), the type-A lattice preferred orientation (LPO), formed under low-stress and low-water content, was reported. In the case of the latter (AD peridotites), the type-C LPO, formed under low-stress and high-water content, was reported. In particular, in the case of AD peridotites, at least two fluid infiltration events, such as early (type-1: CO₂-N₂) and late (type-2: CO₂-H₂O), have been recorded in orthopyroxene. The upper mantle heterogeneity recorded by these microstructures and fluid inclusions is considered to be due to the interaction between the North American plate and the Farallon plate.

• Journal of Korea Water Resources Association
• /
• v.57 no.2
• /
• pp.73-85
• /
• 2024

Predicting water quality of rivers and reservoirs is necessary for the management of water resources. Artificial Neural Networks (ANNs) have been used in many studies to predict water quality with high accuracy. Previous studies have used Gradient Descent (GD)-based optimizers as an optimizer, an operator of ANN that searches parameters. However, GD-based optimizers have the disadvantages of the possibility of local optimal convergence and absence of a solution storage and comparison structure. This study developed improved optimizers to overcome the disadvantages of GD-based optimizers. Proposed optimizers are optimizers that combine adaptive moments (Adam) and Nesterov-accelerated adaptive moments (Nadam), which have low learning errors among GD-based optimizers, with Harmony Search (HS) or Novel Self-adaptive Harmony Search (NSHS). To evaluate the performance of Long Short-Term Memory (LSTM) using improved optimizers, the water quality data from the Dasan water quality monitoring station were used for training and prediction. Comparing the learning results, Mean Squared Error (MSE) of LSTM using Nadam combined with NSHS (NadamNSHS) was the lowest at 0.002921. In addition, the prediction rankings according to MSE and R² for the four water quality indices for each optimizer were compared. Comparing the average of ranking for each optimizer, it was confirmed that LSTM using NadamNSHS was the highest at 2.25.

• Journal of Bio-Environment Control
• /
• v.33 no.1
• /
• pp.1-11
• /
• 2024

In this study, five artificial intelligence (AI) models: Inception v3, SqueezeNet (local), VGG-16, Painters, and DeepLoc were used to classify tea leaf diseases. Eight image categories were used: healthy, algal leaf spot, anthracnose, bird's eye spot, brown blight, gray blight, red leaf spot, and white spot. Software used in this study was Orange 3 which functions as a Python library for visual programming, that operates through an interface that generates workflows to visually manipulate and analyze the data. The precision of each AI model was recorded to select the ideal AI model. All models were trained using the Adam solver, rectified linear unit activation function, 100 neurons in the hidden layers, 200 maximum number of iterations in the neural network, and 0.0001 regularizations. To extend the functionality of Orange 3, new add-ons can be installed and, this study image analytics add-on was newly added which is required for image analysis. For the training model, the import image, image embedding, neural network, test and score, and confusion matrix widgets were used, whereas the import images, image embedding, predictions, and image viewer widgets were used for the prediction. Precisions of the neural networks of the five AI models (Inception v3, SqueezeNet (local), VGG-16, Painters, and DeepLoc) were 0.807, 0.901, 0.780, 0.800, and 0.771, respectively. Finally, the SqueezeNet (local) model was selected as the optimal AI model for the detection of tea diseases using tea leaf images owing to its high precision and good performance throughout the confusion matrix.

• Parasites, Hosts and Diseases
• /
• v.48 no.1
• /
• pp.71-73
• /
• 2010

This cross sectional study was conducted in the city of Taiz, Yemen, during the period from August 2006 to August 2007 in order to investigate the seroprevalence and incidence of toxoplasmosis among apparently healthy children (AHC) and visually and/or hearing disabled children (DC). The seroprevalence was 16.0% among AHC compared to 32.5% among DC. The effect of gender was clear as the seroprevalence rate was significantly higher among females (18.3 and 43.8% for AHC and DC, respectively) than males (13.8 and 25% for AHC and DC, respectively). The seroprevalence was proportionally increased with the age, and the highest rates (20.9 and 53.0%) were reported among the oldest age group (> 10-14 years) for AHC and DC groups, respectively. The incidence rate was also higher (4.2%) in DC group compared to AHC group (2.4%) during 1 year period. These data indicate that the seroprevalence and incidence of toxoplasmosis are significantly higher in DC group than those of AHC group. We need to check further relationship between toxoplasmosis and visual and/or hearing disability.

• Journal of Hydrogen and New Energy
• /
• v.27 no.4
• /
• pp.341-348
• /
• 2016

The experiments related on structure and water electrolysis performance of HALE UAV stack were conducted in this study. Anode catalyst $IrRuO_2$ was prepared by Adam's fusion methods as 2~3 nm nano sized particles, and the cathode catalyst was used as commercial product of Premetek. The MEA (membrane electrode assembly) was manufactured by decal methods, anode and anode catalytic layers were prepared by electro-spray. HALE stack was composed of 5 multi-cells as $0.2Nm^3/hr$ hydrogen production rate with hydrogen pressure as 10 bar. The water electrolysis performance was investigated at atmospheric pressure and temperature of $55^{\circ}C$. Best performance of HALE UAV stack was recorded as cell voltage efficiency as 86%.