• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.2
• /
• pp.270-279
• /
• 2022

In this paper, system dynamics considering dynamics and time was examined to study the changes in system structure according to reinforcement (policy intervention) of regulation and punishment for fishing boats, and the strategizing directions were analyzed. Until now, regulations and punishments on fishing boats have been conducted temporarily and short-term as a precautionary measure to prevent accidents and imposed penalties. However, due to various anomalous side effects, the expected results were not achieved, negligent accidents occurred constantly, and follow-up measures were repeated. Resultantly, the regulation and punishment of fishing boats is a reinforced safety standard, and there is a necessity to improve facilities, equipment, and industry, and develop technology (including time delay) to prevent accidents. However, as the negative (illegal) activities continue without immediate and significant resistance, the safety blind spot for accident prevention cannot be minimized. Thus, policy intervention based on linear thinking without sufficiently considering variables of the dynamic mechanism and time can distort the basic values pursued by the policy. For the regulation and punishment of fishing boats, a strategy to supplement the mechanism should be prepared prior to the preparation of reinforced safety standards. Improvement and development of related technologies, mandatory training hours for anglers, fishing industry, and related organizations, proposal of specific action plan for Fishing Management and Promotion Act for growing fishing-related industries.

• KNOM Review
• /
• v.23 no.2
• /
• pp.18-28
• /
• 2020

With the development of the virtual community, the benefits that IT technology provides to people in fields such as healthcare, industry, communication, and culture are increasing, and the quality of life is also improving. Accordingly, there are various malicious attacks targeting the developed network environment. Firewalls and intrusion detection systems exist to detect these attacks in advance, but there is a limit to detecting malicious attacks that are evolving day by day. In order to solve this problem, intrusion detection research using machine learning is being actively conducted, but false positives and false negatives are occurring due to imbalance of the learning dataset. In this paper, a Random Oversampling method is used to solve the unbalance problem of the UNSW-NB15 dataset used for network intrusion detection. And through experiments, we compared and analyzed the accuracy, precision, recall, F1-score, training and prediction time, and hardware resource consumption of the models. Based on this study using the Random Oversampling method, we develop a more efficient network intrusion detection model study using other methods and high-performance models that can solve the unbalanced data problem.

• 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.

• Geophysics and Geophysical Exploration
• /
• v.26 no.3
• /
• pp.126-137
• /
• 2023

In this study, a recurrent neural network (RNN) was employed as a methodological approach to classify dolphin click signals derived from ocean monitoring data. To improve the accuracy of click signal classification, the single time series data were transformed into fractional domains using fractional Fourier transform to expand its features. Transformed data were used as input for three RNN models: long short-term memory (LSTM), gated recurrent unit (GRU), and bidirectional LSTM (BiLSTM), which were compared to determine the optimal network for the classification of signals. Because the fractional Fourier transform displayed different characteristics depending on the chosen angle parameter, the optimal angle range for each RNN was first determined. To evaluate network performance, metrics such as accuracy, precision, recall, and F1-score were employed. Numerical experiments demonstrated that all three networks performed well, however, the BiLSTM network outperformed LSTM and GRU in terms of learning results. Furthermore, the BiLSTM network provided lower misclassification than the other networks and was deemed the most practically appliable to field data.

• Animal Bioscience
• /
• v.36 no.5
• /
• pp.740-752
• /
• 2023

Objective: Dietary phytase increases bioavailability of phytate-bound phosphorus (P) in pig nutrition affecting dietary calcium (Ca) to P ratio, intestinal uptake, and systemic utilization of both minerals, which may contribute to improper bone mineralization. We used phytase to assess long-term effects of two dietary available P (aP) levels using a one-phase feeding system on gene expression related to Ca and P homeostasis along the intestinal tract and in the kidney, short-chain fatty acids in stomach, cecum, and colon, serum, and bone parameters in growing gilts and barrows. Methods: Growing pigs (37.9±6.2 kg) had either free access to a diet without (Con; 75 gilts and 69 barrows) or with phytase (650 phytase units; n = 72/diet) for 56 days. Samples of blood, duodenal, jejunal, ileal, cecal, and colonic mucosa and digesta, kidney, and metacarpal bones were collected from 24 pigs (6 gilts and 6 barrows per diet). Results: Phytase decreased daily feed intake and average daily gain, whereas aP intake increased with phytase versus Con diet (p<0.05). Gilts had higher colonic expression of TRPV5, CDH1, CLDN4, ZO1, and OCLN and renal expression of TRPV5 and SLC34A3 compared to barrows (p<0.05). Phytase increased duodenal expression of TRPV5, TRPV6, CALB1, PMCA1b, CDH1, CLDN4, ZO1, and OCLN compared to Con diet (p<0.05). Furthermore, phytase increased expression of SCL34A2 in cecum and of FGF23 and CLDN4 in colon compared to Con diet (p<0.05). Alongside, phytase decreased gastric propionate, cecal valerate, and colonic caproate versus Con diet (p<0.05). Phytase reduced cortical wall thickness and index of metacarpal bones (p<0.05). Conclusion: Gene expression results suggested an intestinal adaptation to increased dietary aP amount by increasing duodenal trans- and paracellular Ca absorption to balance the systemically available Ca and P levels, whereas no adaption of relevant gene expression in kidney occurred. Greater average daily gain in barrows related to higher feed intake.

• ALGAE
• /
• v.38 no.2
• /
• pp.141-150
• /
• 2023

Light quality is a common environmental factor which influences the metabolism of biochemical substances in algae and leads to the response of algal growth and development. Pyropia yezoensis is a kind of economic macroalgae that naturally grows in the intertidal zone where the light environment changes dramatically. In the present study, P. yezoensis thalli were treated under white light (control) and monochromatic lights with primary colors (blue, green, and red) for 14 days to explore their physiological response to light quality. During the first 3 days of treatment, P. yezoensis grew faster under blue light than other light qualities. In the next 11 days, it showed better adaptation to green light, with higher growth rate and photosynthetic capacity (reflected by a higher rETR_max = 61.58 and E_k = 237.78). A higher non-photochemical quenching was observed in the treatment of red light than others for 14 days. Furthermore, the response of P. yezoensis to light quality also results in the difference of photosynthetic pigment contents. The monochromatic light could reduce the synthesis of all pigments, but the reduction degree was different, which may relate to the spectral absorption characteristics of pigments. It was speculated that P. yezoensis adapted to a specific or changing light environments by regulating the synthesis of pigments to achieve the best use of light energy in photosynthesis and premium growth and metabolism.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.6B
• /
• pp.597-603
• /
• 2006

The purpose of this study is to improve the short term rainfall forecast skill using neural network model that can deal with the non-linear behavior between satellite data and ground observation, and minimize the flood damage. To overcome the geographical limitation of Korean peninsula and get the long forecast lead time of 3 to 6 hour, the developed rainfall forecast model took satellite imageries and wide range AWS data. The architecture of neural network model is a multi-layer neural network which consists of one input layer, one hidden layer, and one output layer. Neural network is trained using a momentum back propagation algorithm. Flood was estimated using rainfall forecasts. We developed a dynamic flood inundation model which is associated with 1-dimensional flood routing model. Therefore the model can forecast flood aspect in a protected lowland by levee failure of river. In the case of multiple levee breaks at main stream and tributaries, the developed flood inundation model can estimate flood level in a river and inundation level and area in a protected lowland simultaneously.

• Journal of Korea Entertainment Industry Association
• /
• v.13 no.8
• /
• pp.303-311
• /
• 2019

is a film festival in conjunction with that shows about 50 works from 25 countries. It has become the only martial arts action film festival going on in Korea, with 32 feature films and 24 short films for a total of six days during the event from August 30 to September 6. has the slogan 'Muye, change the history of movies!' Through the movie, it sheds light on the value of life pursued by the martial arts spirit around Samjae, the core value of martial arts, and explores the aesthetic value of the most beautiful gesture that humans can make through the movement of martial arts centered on the space of dots, good and cotton. And through this film festival, I saw the potential to grow into a festival with the world. With this film festival, the identity of is established as a sustainable film festival, not as a single film festival, and image of martial arts action movies, which are part of genre movies, through the certainty of this image, differentiates itself from domestic and international film festivals, and does not stay in Northeast Asia or in Southeast Asia. Then, let's study the value of the future through the results of this film festival. In addition, we will study ways to increase the probability of growth as the best cultural and arts festival held along with the world's only international martial arts competition.

• Journal of Korea Entertainment Industry Association
• /
• v.6 no.4
• /
• pp.82-92
• /
• 2012

Recently people who enjoy social game via mobile devices significantly are increasing depending on the rapid adoption of smart phones and the development of the network such as LTE. Most of them are enjoying the casual gaming mobile social games that you are able to play easily, but social issues like health problems due to long play time are emerging. The users, however, do not last long because of the simplicity of the game, and there are few people who actually buy game items even though they play it long time. This study has been conducted aiming to overcome such difficulties. This study suggests ways to generate constantly revenue avoiding short-term box-office after the release of mobile social games based on the analysis for market trend and profitability of the mobile social game. In addition, by applying profitability model analyzed to Japan's most successful game practices, this paper suggests the concrete methods about the commitment of the users. For summarizing the main achievements of this paper, providing the latest market information about mobile social games, analysis of profitability, practical implications for the commitment of the users are presented.

• Korean Journal of Legislative Studies
• /
• v.26 no.3
• /
• pp.125-159
• /
• 2020

Amid global pandemic of covid-19, Korean government's response has drawn wide attention among social scientists as well as medical studies. The role of Korean state and civil society has attracted particular attention among others. Yet, this paper criticizes extant studies on Korean case which focus on the extensive intervention of the strong state and subjective attitude of Korean citizens in coping with covid-19. The concept of the strong state lacks social scientific specification and subjective citizens do not match with Korean realities. This article argues that Korean state's capacity in collecting and mobilizing digital data may offer better understanding for the successful responses to the pandemic. First, Korean state is the ultimate coordinator in collecting, analyzing and applying big data about the expansion of covid-19 with its huge network of dataveillance. Also, such role has been largely based upon relevant legal framework and well prepared manuals and cooperation with civic actors and companies. In other words, Korean digital dataveillance had demonstrated its transparency and cooperative governance. Second, such dataveillance capacity has deep roots in the long-term development of Korean state's big data management. Korean state has evolved about thirty years while enhancing digital data network within governments, companies and private sectors. Third, the relationship between Korean state's dataveillance and civil society can be characterized as a state centered push model. This model demonstrates highly effective governmental responses to covid-19 crisis but fall short of building social consensus in balancing individual freedom, human rights and effective containment policies. It means communitarian solidarity among citizens has not been a major factor in Korea's successful response yet.