• Asian-Australasian Journal of Animal Sciences
• /
• v.32 no.9
• /
• pp.1389-1396
• /
• 2019

Objective: The current study analysed the relationships between methane ($CH_4$) output from animal and dietary factors. Methods: The dataset was obtained from 159 Dorper${\times}$thin-tailed Han lambs from our seven studies, and $CH_4$ production and energy metabolism data were measured in vivo by an opencircuit respiratory method. All lambs were confined indoors and fed pelleted diet during the whole experimental period in all studies. Data from two-thirds of lambs were used to develop linear and multiple regressions to describe the relationship between $CH_4$ emission and dietary variables, and data from the remaining one third of lambs were used to validate the established models. Results: $CH_4$ emission (g/d) was positively related to dry matter intake (DMI) and gross energy intake (GEI) (p<0.001). $CH_4$ energy/GEI was negatively related to metabolizable energy/gross energy and metabolizable energy/digestible energy (p<0.001). Using DMI to predict $CH_4$ emission (g/d) resulted in a coefficient of determination ($R^2$) of 0.80. Using GEI, digestible energy intake, and metabolizable energy intake predict $CH_4$ energy/GEI resulted in a $R^2$ of 0.92. Conclusion: the prediction equations established in the current study are useful to develop appropriate feeding and management strategies to mitigate $CH_4$ emissions from sheep.

• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.175-182
• /
• 2022

In our daily life, we come across different types of information, for example in the format of multimedia and text. We all need different types of information for our common routines as watching/reading the news, listening to the radio, and watching different types of videos. However, sometimes we could run into problems when a certain type of information is required. For example, someone is listening to the radio and wants to listen to jazz, and unfortunately, all the radio channels play pop music mixed with advertisements. The listener gets stuck with pop music and gives up searching for jazz. So, the above example can be solved with an automatic audio classification system. Deep Learning (DL) models could make human life easy by using audio classifications, but it is expensive and difficult to deploy such models at edge devices like nano BLE sense raspberry pi, because these models require huge computational power like graphics processing unit (G.P.U), to solve the problem, we proposed DL model. In our proposed work, we had gone for a low complexity model for Audio Event Detection (AED), we extracted Mel-spectrograms of dimension 128×431×1 from audio signals and applied normalization. A total of 3 data augmentation methods were applied as follows: frequency masking, time masking, and mixup. In addition, we designed Convolutional Neural Network (CNN) with spatial dropout, batch normalization, and separable 2D inspired by VGGnet [1]. In addition, we reduced the model size by using model quantization of float16 to the trained model. Experiments were conducted on the updated dataset provided by the Detection and Classification of Acoustic Events and Scenes (DCASE) 2020 challenge. We confirm that our model achieved a val_loss of 0.33 and an accuracy of 90.34% within the 132.50KB model size.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1880-1889
• /
• 2022

The online portal platform provides online news with online comments, but the anonymity of comments causes incivility, and online comments are considered social problems. While there are many foreign language-based incivility detection studies, in-depth research is not being conducted in Korea since there has not been implemented Korean language dataset which is labeled detailed criteria of incivility. In this study, the incivility notation of comments was conducted in a total of 13 items, uncivil words were summarized. Furthermore, Attention algorithm was applied to each comment and summary to extract embedding vectors. 2-d CNN followed at the end to detect incivility in given data. As a result, we showed that the proposed algorithm is useful for anti-citizen detection such as name-calling and offensive tones. This study is expected to contribute to the formation of a healthy online comment culture by detecting uncivil comments which hinder democratic discourse.

• Journal of the Korean Society for information Management
• /
• v.30 no.3
• /
• pp.273-296
• /
• 2013

The purpose of this study is to examine the data coverage and citation threshold for analyzing SPLC(Search Path Link Count) as a main path of a historiograph of a certain topic in order to provide 'core' papers of global research trends to a researcher affiliated with a local R&D institution. 5 datasets were constructed by retrieving and collecting 2,318 articles on RGB LED on Web of Science published from 1990-2013 and 20,109 articles which cited these original 2,318. The SPLC analysis was performed on each dataset by increasing the threshold of citation counts, and the changes and resilience of the 28 extraced networks were compared. The results of user feedback on 198 unique core papers from 28 SPLC networks received from LED researchers affiliated with a Korean government-sponsored research institution were also analyzed. As a result, it is found that the nodes in each SPLC network in each dataset were differentiated by the citation counts, while the changes in the structure of SPLC networks were slight after the networks' citation counts were set at 40. Additionally, the user feedback showed that personalized research interest generally matched to the global research trends identified by the SPLC analysis.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.461-467
• /
• 2020

In noisy and multi-speaker environments, the performance of speech recognition is unavoidably lower than in a clean environment. To improve speech recognition, in this paper, the signal of the speaker of interest is extracted from the mixed speech signals with multiple speakers. The VoiceFilter model is used to effectively separate overlapped speech signals. In this work, clustering by Probabilistic Linear Discriminant Analysis (PLDA) similarity score was employed to detect the speech signal of the interested speaker, which is used as the reference speaker to VoiceFilter-based separation. Therefore, by utilizing the speaker feature extracted from the detected speech by the proposed clustering method, this paper propose a speaker diarization system using only the mixed speech without an explicit reference speaker signal. We use phone-dataset consisting of two speakers to evaluate the performance of the speaker diarization system. Source to Distortion Ratio (SDR) of the operator (Rx) speech and customer speech (Tx) are 5.22 dB and -5.22 dB respectively before separation, and the results of the proposed separation system show 11.26 dB and 8.53 dB respectively.

• Journal of the Korean Society of Visualization
• /
• v.12 no.3
• /
• pp.15-20
• /
• 2014

Direct numerical simulation (DNS) dataset of a turbulent boundary layer (TBL) with a step change from smooth to rough surface is analyzed to examine spatially developing flow characteristics. The roughness elements are periodically arranged two-dimensional (2-D) spanwise rods with a streamwise pitch of ${\lambda}=8k$ ($=12{\theta}_{in}$), and the roughness height is $k=15{\theta}_{in}$, where ${\theta}_{in}$ is the inlet momentum thickness. The step change is introduced $80{\theta}_{in}$ downstream from the inlet. For the first time, full images from the DNS data with the step change from the smooth to rough walls is present to get some idea of the geometry of turbulent coherent structures over rough wall, especially focusing on their existence and partial dynamics over the rough wall. The results show predominance of hairpin vortices over the rough wall and their spanwise scale growth mechanism by merging.

• Korean Journal of Ecology and Environment
• /
• v.42 no.2
• /
• pp.221-231
• /
• 2009

This study was carried out to comparatively identify characteristics of turbid water influence in Imha Reservoir, Soyang Reservoir, and Daecheong Reservoir in Korea. We used 3 years dataset from 2002 to 2004 and analyzed seasonal water quality characteristics, particular parameters in association with turbidity, and light transparency to figure out the trends. All parameters to be used in the study were total phosphate (TP), total nitrogen (TN), chlorophyll-${\alpha}$ (Chl), suspended solids (SS), Secchi depth (SD), conductivity, and verticallight extinction coefficienct($K_d$), euphotic zone ($Z_{eu}$), and critical depth ($Z_p$). All parameters depend on season and watershed. Suspended solids from Soyang Reservoir were usually caused by TP, mainly related to living wastes and agricultures in upper stream. Daecheong Reservoir was influenced by organic matters related to large phytoplankton biomass in summer and inorganic suspended solids by nutrients in the winter. However, in case of Imha Reservoir, turbid water, consisted in silt and clay through heavy precipitation remained in the waterbody to decrease water transparency along with TP and caused the light limitation in winter. Overall results suggest that it was necessary to establish various management programs because the reasons occurring turbidity were varied according to the reservoir circumstances.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.1
• /
• pp.82.2-82.3
• /
• 2019

Korea Astronomy and Space Science Institute (KASI), in collaboration with the NASA Goddard Sparce Flight Center (GSFC), will develop a next generation coronagraph for the International Space Station (ISS). COronal Diagnostic EXperiment (CODEX) uses multiple filters to obtain simultaneous measurements of electron density, temperature, and velocity within a single instrument. CODEX's regular, systematic, comprehensive dataset will test theories of solar wind acceleration and source, as well as serve to validate and enable improvement of space-weather/operational models in the crucial source region of the solar wind. CODEX subsystems include the coronagraph, pointing system, command and data handling (C&DH) electronics, and power distribution unit. CODEX is integrated onto a standard interface which provides power and communication. All full resolution images are telemeters to the ground, where data from multiple images and sequences are co-added, spatially binned, and ratioed as needed for analysis.

• Nuclear Engineering and Technology
• /
• v.54 no.2
• /
• pp.617-626
• /
• 2022

To effectively monitor the variety of distributions of neutron flux, fuel power or temperatures in the reactor core, usually the ex-core and in-core neutron detectors are employed. The thermocouples for temperature measurement are installed in the coolant inlet or outlet of the respective fuel assemblies. It is necessary to reconstruct the measurement information of the whole reactor position. However, the reading of different types of detector in the core reflects different aspects of the 3D power distribution. The feasibility of reconstruction the core three-dimension power distribution by using different combinations of in-core, ex-core and thermocouples detectors is analyzed in this paper to synthesize the useful information of various detectors. A comparison of multilayer perceptron (MLP) network and radial basis function (RBF) network is performed. RBF results are more extreme precision but also more sensitivity to detector failure and uncertainty, compare to MLP networks. This is because that localized neural network could offer conservative regression in RBF. Adding random disturbance in training dataset is helpful to reduce the influence of detector failure and uncertainty. Some convolution neural networks seem to be helpful to get more accurate results by use more spatial layout information, though relative researches are still under way.

• Steel and Composite Structures
• /
• v.44 no.1
• /
• pp.49-63
• /
• 2022

This study aims to develop ensemble machine learning (ML) models for estimating the peak floor acceleration and maximum top drift of steel moment frames. For this purpose, random forest, adaptive boosting, gradient boosting regression tree (GBRT), and extreme gradient boosting (XGBoost) models were considered. A total of 621 steel moment frames were analyzed under 240 ground motions using OpenSees software to generate the dataset for ML models. From the results, the GBRT and XGBoost models exhibited the highest performance for predicting peak floor acceleration and maximum top drift, respectively. The significance of each input variable on the prediction was examined using the best-performing models and Shapley additive explanations approach (SHAP). It turned out that the peak ground acceleration had the most significant impact on the peak floor acceleration prediction. Meanwhile, the spectral accelerations at 1 and 2 s had the most considerable influence on the maximum top drift prediction. Finally, a graphical user interface module was created that places a pioneering step for the application of ML to estimate the seismic demands of building structures in practical design.