• Journal of the Korea Convergence Society
• /
• v.12 no.4
• /
• pp.259-266
• /
• 2021

This study is a study to systematize the R&D activities of social enterprises to derive a logical model of the R&D support policy, and aims to systematize the R&D activities based on the R&D demand survey and R&D activity analysis of social enterprises. R&D activities of social enterprises are at an early stage or are not systematic compared to general enterprises, so the process modeling method is used to group detailed activity elements to standardize and systemize them. As a result of the research, social enterprises are aware of the necessity and importance of R&D activities to secure competitiveness of products and services to increase social value, and because of their lack of R&D experience and capabilities, R&D specialized institutes (R&D planning institutes, government-funded research institutes), Universities, etc.) and are expected to improve R&D capabilities. The performance indicators of social enterprise R&D activities are derived in units of input-process-performance indicators through demand survey, activity analysis, and in-depth interview (FGI), and the logical model of R&D support policy is in the areas related to business strategy and performance.

• Journal of Convergence for Information Technology
• /
• v.12 no.5
• /
• pp.51-61
• /
• 2022

The purpose of this study was to identify whether need of cognition have a mediating effect on media multitasking on learning engagement in online education. The subjects were 168 university students who had received online education for more than one semester, and data were collected using questionnaires on media multitasking, need of cognition, and learning engagement. For data analysis, correlation, hierarchical regression and Sobel test were performed using SPSS WIN 20.0 program. As a result of the study, there was a significant positive correlation between media multitasking and learning engagement (r=.52, p<.001), and a between need of cognition and learning engagement(r=.39, p<.001). Media multitasking had a significant effect on learning participation (β=.52, p<.001), and explanatory power was 27%. When need of cognition was input, the effect of media multitasking on learning engagement decreased (β=.52 ⟶ .44), so it was found that need of cognition had a partial mediating effect in the effect of media multitasking on learning engagement(Z=2.77). p<.01). Therefore, it is suggested to use online contents with learning to organizing a g a lesson syllabus for distance education, and to organize activities promoting media multitasking activities. Also, it is proposed to develop and apply various teaching strategies to promoting the need of cognition in the distance education.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.342-350
• /
• 2022

In this paper, actual drone noise samples are collected for speech processing in disaster environments to build noise-corrupted speech database, and speech enhancement performance is evaluated by applying spectrum subtraction and mask-based speech enhancement techniques. To improve the performance of VoiceFilter (VF), an existing deep neural network-based speech enhancement model, we apply the Self-Attention operation and use the estimated noise information as input to the Attention model. Compared to existing VF model techniques, the experimental results show 3.77%, 1.66% and 0.32% improvements for Source to Distortion Ratio (SDR), Perceptual Evaluation of Speech Quality (PESQ), and Short-Time Objective Intelligence (STOI), respectively. When trained with a 75% mix of speech data with drone sounds collected from the Internet, the relative performance drop rates for SDR, PESQ, and STOI are 3.18%, 2.79% and 0.96%, respectively, compared to using only actual drone noise. This confirms that data similar to real data can be collected and effectively used for model training for speech enhancement in environments where real data is difficult to obtain.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.1
• /
• pp.175-183
• /
• 2022

The collision between a ship and bridge across a waterway may result in extremely serious consequences that may endanger the safety of life and property. Therefore, factors affecting ship bridge collision must be investigated, and the impact force should be discussed based on various collision conditions. In this study, a finite element model of ship bridge collision is established, and the peak impact force of a ship bridge collision based on 50 operating conditions combined with three input parameters, i.e., ship loading condition, ship speed, and ship bridge collision angle, is calculated via numerical simulation. Using neural network models trained with the numerical simulation results, the prediction model of the peak impact force of ship bridge collision involving an extremely short calculation time on the order of milliseconds is established. The neural network models used in this study are the basic backpropagation neural network model and Elman neural network model, which can manage temporal information. The accuracy of the neural network models is verified using 10 test samples based on the operating conditions. Results of a verification test show that the Elman neural network model performs better than the backpropagation neural network model, with a mean relative error of 4.566% and relative errors of less than 5% in 8 among 10 test cases. The trained neural network can yield a reliable ship bridge collision force instantaneously only when the required parameters are specified and a nonlinear finite element solution process is not required. The proposed model can be used to predict whether a catastrophic collision will occur during ship navigation, and thus hence the safety of crew operating the ship.

• Smart Media Journal
• /
• v.11 no.10
• /
• pp.65-75
• /
• 2022

Deep learning is used as a creative tool that could overcome the limitations of existing analysis models and generate various types of results such as text, image, and music. In this paper, we propose a method necessary to preprocess audio data using the Niko's MIDI Pack sound source file as a data set and to generate music using Bi-LSTM. Based on the generated root note, the hidden layers are composed of multi-layers to create a new note suitable for the musical composition, and an attention mechanism is applied to the output gate of the decoder to apply the weight of the factors that affect the data input from the encoder. Setting variables such as loss function and optimization method are applied as parameters for improving the LSTM model. The proposed model is a multi-channel Bi-LSTM with attention that applies notes pitch generated from separating treble clef and bass clef, length of notes, rests, length of rests, and chords to improve the efficiency and prediction of MIDI deep learning process. The results of the learning generate a sound that matches the development of music scale distinct from noise, and we are aiming to contribute to generating a harmonistic stable music.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.341-354
• /
• 2023

The title of a document is the brief summarization of the document. Readers can easily understand a document if we provide them with its title in their preferred styles and the languages. In this research, we propose a cross-lingual and style-based title generation model using multiple adapters. To train the model, we need a parallel corpus in several languages with different styles. It is quite difficult to construct this kind of parallel corpus; however, a monolingual title generation corpus of the same style can be built easily. Therefore, we apply a zero-shot strategy to generate a title in a different language and with a different style for an input document. A baseline model is Transformer consisting of an encoder and a decoder, pre-trained by several languages. The model is then equipped with multiple adapters for translation, languages, and styles. After the model learns a translation task from parallel corpus, it learns a title generation task from monolingual title generation corpus. When training the model with a task, we only activate an adapter that corresponds to the task. When generating a cross-lingual and style-based title, we only activate adapters that correspond to a target language and a target style. An experimental result shows that our proposed model is only as good as a pipeline model that first translates into a target language and then generates a title. There have been significant changes in natural language generation due to the emergence of large-scale language models. However, research to improve the performance of natural language generation using limited resources and limited data needs to continue. In this regard, this study seeks to explore the significance of such research.

• Journal of Environmental Impact Assessment
• /
• v.32 no.4
• /
• pp.203-213
• /
• 2023

The AERMOD model was the most used, accounting for 89.0%, based on the analysis of the environmental impact assessment reports published in the Environmental Impact Assessment Information Support System (EIASS) between 2021 and 2022. The mismatch of versions between AERMET and AERMOD was found to be 25.3%. There was the operational time discrepancy of 50.6% from industrial complexes, urban development projects between used in the model and applied in estimating pollutant emissions. The results of applying various versions of the AERMET and AERMOD models to both area sources and point sources in both simple and complex terrain in the Gunsan area showed similar values after AERMOD version 12 (15181). Emissions are assessed as 24-hour operation, and the predicted concentration in both simple and complex terrain when using the variable emission coefficient option that applies an 8-hour daytime operation in the model is lowered by 37.42% ~ 74.27% for area sources and by 32.06% ~ 54.45% for point sources. Therefore, to prevent the error in using the variable emission coefficient, it is required to clearly present the emission calculation process and provide a detailed explanation of the composition of modeling input data in the environmental impact assessment reports. Also, thorough reviews by special institutions are essential.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.3
• /
• pp.133-140
• /
• 2023

The performance of lithium ion batteries depends on the usage environment and the combination ratio of cathode materials. In order to develop a high-performance lithium-ion battery, it is necessary to manufacture the battery and measure its performance while varying the cathode material ratio. However, it takes a lot of time and money to directly develop batteries and measure their performance for all combinations of variables. Therefore, research to predict the performance of a battery using an artificial intelligence model has been actively conducted. However, since measurement experiments were conducted with the same battery in the existing published battery data, the cathode material combination ratio was fixed and was not included as a data attribute. In this paper, we define a training data model required to develop an artificial intelligence model that can predict battery performance according to the combination ratio of cathode materials. We analyzed the factors that can affect the performance of lithium-ion batteries and defined the mass of each cathode material and battery usage environment (cycle, current, temperature, time) as input data and the battery power and capacity as target data. In the battery data in different experimental environments, each battery data maintained a unique pattern, and the battery classification model showed that each battery was classified with an error of about 2%.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.12
• /
• pp.499-508
• /
• 2022

A lot of research has been carried out on the Hangeul generation model using deep learning, and recently, research is being carried out how to minimize the number of characters input to generate one set of Hangul (Few-Shot Learning). In this paper, we propose a CKFont2 model using only 14 letters by analyzing and improving the CKFont (hereafter CKFont1) model using 28 letters. The CKFont2 model improves the performance of the CKFont1 model as a model that generates all Hangul using only 14 characters including 24 components (14 consonants and 10 vowels), where the CKFont1 model generates all Hangul by extracting 51 Hangul components from 28 characters. It uses the minimum number of characters for currently known models. From the basic consonants/vowels of Hangul, 27 components such as 5 double consonants, 11/11 compound consonants/vowels respectively are learned by deep learning and generated, and the generated 27 components are combined with 24 basic consonants/vowels. All Hangul characters are automatically generated from the combined 51 components. The superiority of the performance was verified by comparative analysis with results of the zi2zi, CKFont1, and MX-Font model. It is an efficient and effective model that has a simple structure and saves time and resources, and can be extended to Chinese, Thai, and Japanese.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.6
• /
• pp.610-620
• /
• 2022

An acoustic vector sensor can simultaneously receive vector quantities, such as particle velocity and acceleration, as well as acoustic pressure at one location, and thus it can be used as a single input multiple output receiver in underwater acoustic communication systems. On the other hand, vector signals received by a single vector sensor have different channel characteristics due to the azimuth angle between the source and receiver and the difference in propagation angle of multipath in each component, producing different communication performances. In this paper, we propose a channel parameter-based weighting method to improve the performance of an acoustic communication system using a single vector sensor. To verify the proposed method, we used communication data collected from the experiment conducted during the KOREX-17 (Korea Reverberation Experiment). For communication demodulation, block-based time reversal technique which is robust against time-varying channels were utilized. Finally, the communication results showed that the effectiveness of the channel parameter-based weighting method for the underwater communication system using a single vector sensor was verified.