• Journal of KIISE:Software and Applications
• /
• v.27 no.1
• /
• pp.24-32
• /
• 2000

BCI(Brain-Computer Interface) is studied to control the machines with brain. In this study, an EEG(Electroencephalography) signal classification model is proposed. The model gets EEG pattern from each subject's brain and extracts characteristic features. The model discriminates the EEG patterns by using those extracted characteristic features of each subject. The proposed method classifies each pair of the given tasks and combines the results to give the final result. Four tasks such as rest, movement, mental-arithmetic calculation and point-fixing were used in the experiment. Over 90% of the trials, the model yielded successful results. The model exploits characteristic features of the subjects and the weight table that was produced after training. The analysis results of the model such as its high success rates and short processing time show that it can be used in a real-time brain-computer interface system.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.4
• /
• pp.341-348
• /
• 2017

This study examined the effects of the location and direction of the scolioti curve on postural balance in patients with idiopathic scoliosis. Fifteen subjects were divided into three groups: right thoracic curve group, left lumbar curve group, and double curve group. The dynamic trunk motion (angle variation in the lumbar, thoracolumbar, lower thoracic and upper thoracic region) and plantar pressure distribution (maximum force and peak pressure) were assessed using an ultrasound-based motion analysis system and Emed-at platform system. From the results, it was confirmed that patients with idiopathic scoliosis showed postural imbalance with an increased angle and pressure asymmetry according to the location and direction of the scoliotic curve for dynamic trunk motion and plantar pressure distribution. In addition, there were differences in the postural balance pattern between the single curve and double curve groups. Further studies for developing a rehabilitation training device will be conducted to improve the postural control ability and trunk balance as well as treat scoliosis based on the results of this study.

• Journal of KIISE:Software and Applications
• /
• v.32 no.7
• /
• pp.674-682
• /
• 2005

This paper proposes classification of multi-spectral satellite image based on fusion of fuzzy G-K (Gustafson-Kessel) algorithm and PCM algorithm. The suggested algorithm establishes the initial cluster centers by selecting training data from each category, and then executes the fuzzy G-K algorithm. PCM algorithm perform using classification result of the fuzzy G-K algorithm. The classification categories are allocated to the corresponding category when the results of classification by fuzzy G-K algorithm and PCM algorithm belong to the same category. If the classification result of two algorithms belongs to the different category, the pixels are allocated by Bayesian maximum likelihood algorithm. Bayesian maximum likelihood algorithm uses the data from the interior of the average intracluster distance. The information of the pixels within the average intracluster distance has a positive normal distribution. It improves classification result by giving a positive effect in Bayesian maximum likelihood algorithm. The proposed method is applied to IKONOS and Landsat TM remote sensing satellite image for the test. As a result, the overall accuracy showed a better outcome than individual Fuzzy G-K algorithm and PCM algorithm or the conventional maximum likelihood classification algorithm.

• Journal of the Korea Convergence Society
• /
• v.12 no.12
• /
• pp.83-91
• /
• 2021

For agricultural products, supply is irregular due to changes in meteorological conditions, and it has high price elasticity. For example, if the supply decreases by 10%, the price increases by 50%. Due to these fluctuations in the prices of agricultural products, the Korean government guarantees the safety of prices to producers through small merchants' auctions. However, when prices plummet due to overproduction, protection measures for producers are insufficient. Therefore, in this paper, we designed a business model that can be used in the electronic transaction system by predicting the price of agricultural products with an artificial intelligence algorithm. To this end, the trained model with the training pattern pairs and a predictive model was designed by applying ARIMA, SARIMA, RNN, and CNN. Finally, the agricultural product forecast price data was classified into short-term forecast and medium-term forecast and verified. As a result of verification, based on 2018 data, the actual price and predicted price showed an accuracy of 91.08%.

• Smart Media Journal
• /
• v.10 no.2
• /
• pp.70-75
• /
• 2021

Grouping and classifying similar designs in design increase efficiency in terms of management and provide convenience in terms of use. Using artificial intelligence algorithms, this study attempted to classify textile designs into four categories: dots, flower patterns, stripes, and geometry. In particular, we explored whether it is possible to find and explain the regions of interest underlying classification from the perspective of artificial intelligence. We randomly extracted a total of 4,536 designs at a ratio of 8:2, comprising 3,629 for training and 907 for testing. The models used in the classification were VGG-16 and ResNet-34, both of which showed excellent classification performance with precision on flower pattern designs of 0.79%, 0.89% and recall of 0.95% and 0.38%. Analysis using the Local Interpretable Model-agnostic Explanation (LIME) technique has shown that geometry and flower-patterned designs derived shapes and petals from the region of interest on which classification was based.

• The Journal of Fisheries Business Administration
• /
• v.49 no.3
• /
• pp.67-83
• /
• 2018

This study is aimed at finding policy directions for Korean fisheries and fishing villages by using Delphi method for fisheries experts. Fisheries experts have highly evaluated the achievements of fostering aquaculture industry, seafood export support measures, and natural disasters relief and recovery arrangements among the policies promoted as so far. And it was recognized that policies such as fishery resources management, creation and recovery of fishery resources, improvement hygiene and seafood safety, and provision young fishermen with training and capacity building will be important. Future megatrends, for example changes in food consumption pattern, climate change, and demographic structure changes are expected to have a significant impact on fisheries and fishing villages. The Delphi survey indicates that the most important policy objective is to secure a stable fisheries production. In other words, fisheries policy in the future should be aimed at suppling sustainable seafood for popular consumption. Finding strategies and action plans that can achieve this goal will be an important policy issue. In conclusion, it is necessary that a number of fundamental researches carry out in Korea, which can lead to finding out a multifunctionality of fisheries and fishing village. In addition, it is important to expand the scope of fisheries policy, which can consider not only the fisheries producers but also seafood consumer's and young fishermen perspectives. Furthermore, it recommends that fishery policy needs to include fishery related industry as well as application of 4th industrial revolution technology to fishery.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.33 no.6
• /
• pp.359-366
• /
• 2020

In this study, a simulation-based damage estimation method for helidecks is proposed using an artificial neural network. The structural members that share a connecting node in the helideck are regarded as a damage group, and a total of 37,400 damage scenarios are numerically generated by applying randomly assigned damage to up to three damage groups. Modal analysis is then performed for all the damage scenarios, which are selectively used as either training or validation or verification sets based on the purpose of use. An artificial neural network with three hidden layers is constructed using a PyTorch program to recognize the patterns of the modal responses of the helideck model under both damaged and undamaged states, and the network is successively trained to minimize the loss function. Finally, the estimated damage rate from the proposed artificial neural network is compared to the actual assigned damage rate using 400 verification scenarios to show that the neural network is able to estimate the location and amount of structural damage precisely.

• Journal of Convergence for Information Technology
• /
• v.11 no.3
• /
• pp.95-106
• /
• 2021

The study is a descriptive research to determine how female university students' life patterns have an effect on dysmenorrhea and to provide the basis about healthy care programs through changing life patterns. We collected 133 data female university students who have dysmenorrhea attending J university. The study period lasted two weeks, going from Nov 18 to Nov 29, 2019. As a result of this study, the correlated factors of dysmenorrhea included dietary habits(r=-.441, p<.001), salt-related dietary(r=-.214, p=.013). The prevalent factors influencing dysmenorrhea are dietary hibits(β=-.457), smoking(β=.175), and phone calls(<2 hours)(β=.163).Therefore, it will be needed patterns of healthy lifestyle including positive dietary habits, non-smoking, phone calls (less than 2 hours) to relieve female university students' dysmenorrhea through education and training.

• Journal of Information Technology Applications and Management
• /
• v.28 no.1
• /
• pp.83-93
• /
• 2021

The purpose of this study was to develop a personalized SMT (smart monitor target) game interface for game users who enjoy airsoft sports as individual purchases of SMT have increased since the advent of the untouched era. For this study, the UX (user experience) of the game interface was designed based on previous research. In particular, the personalized game service was reinforced by adding the CP (command post) of the SMT system that performs the home function of the console game, which was intended to help the user maintain immersed in the game in the personalized space of the SMT. Major design elements for the SMT game interface included layout, color, graphics, buttons, and text, and the interface design was proceeded based on them. After composing a grid with a layout in which the tab function was applied to the interface with a vertical three-segment structure and the outer margin value secured, the military camouflage pattern and texture were applied to the colored tone to perform graphics work. Targets and thumbnails were produced as illustrations using experts to ensure the consistency of the interface, and then function buttons and texts on each page were used concisely for intuitive information delivery. The design sources organized in this way were developed using the Unity engine. In the future, we hope that game user-centered personalized interfaces will continue to develop and provide differentiated services unique to SMT systems in the airsoft gun market.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.11
• /
• pp.1649-1654
• /
• 2021

In this paper, we introduce a regularization of long short-term memory (LSTM) based fall detection system using TensorFlow that can detect falls that can occur in the elderly. Fall detection uses data from a 3-axis acceleration sensor attached to the body of an elderly person and learns about a total of 7 behavior patterns, each of which is a pattern that occurs in daily life, and the remaining 3 are patterns for falls. During training, a normalization process is performed to effectively reduce the loss function, and the normalization performs a maximum-minimum normalization for data and a L2 regularization for the loss function. The optimal regularization conditions of LSTM using several falling parameters obtained from the 3-axis accelerometer is explained. When normalization and regularization rate λ for sum vector magnitude (SVM) are 127 and 0.00015, respectively, the best sensitivity, specificity, and accuracy are 98.4, 94.8, and 96.9%, respectively.