• Journal of the Korean Institute of Intelligent Systems
• /
• 제24권6호
• /
• pp.609-614
• /
• 2014

Cerebellar ataxia is a steadily progressive neurodegenerative disease associated with loss of motor control, leaving patients unable to walk, talk, or perform activities of daily living. Direct motor instruction in cerebella ataxia patients has limited effectiveness, presumably because an inappropriate closed-loop cerebellar response to the inevitable observed error confounds motor learning mechanisms. Recent studies have validated the age-old technique of employing motor imagery training (mental rehearsal of a movement) to boost motor performance in athletes, much as a champion downhill skier visualizes the course prior to embarking on a run. Could the use of EEG based BCI provide advanced biofeedback to improve motor imagery and provide a "backdoor" to improving motor performance in ataxia patients? In order to determine the feasibility of using EEG-based BCI control in this population, we compare the ability to modulate mu-band power (8-12 Hz) by performing a cued motor imagery task in an ataxia patient and healthy control.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• 제36권8B호
• /
• pp.947-953
• /
• 2011

These days, a consistent and fatal attack attribute toward a database has proportionally evolved in the similar development form to that of security policy. Because of access control-based defensive techniques regarding information created in closed networks and attacks on a limited access pathway, cases of infringement of many systems and databases based on accumulated and learned attack patterns from the past are increasing. Therefore, the paper aims to separate attack information by its types based on a virtual infringement pattern system loaded with dualistic VM in order to ensure stability to limited certification and authority to access, to propose a system that blocks infringement through the intensive management of infringement pattern concerning attack networks, and to improve the mechanism for implementing a test that defends the final database, the optimal defensive techniques, and the security policies, through research.

• The Journal of the Korea institute of electronic communication sciences
• /
• 제7권1호
• /
• pp.45-51
• /
• 2012

Programming is an area that many students have difficulty on because it requires various skills, such as problem analysis, logical thinking, and procedural problem-solving skills. In this paper, a system visualizing algorithm was used to set up algorithmic concepts easily and effectiveness of the system was analyzed through scholastic achievement test and survey after learning through this process. For evaluation, we divided students who take courses on programming language and algorithm in 3 universities into 2 groups with 6 teams in each group. The group that trained this system visualizing algorithm had scored 17.4 points higher in terms of scholastic achievement than the group that did not train such method. Moreover, according to the survey, the group had higher scores in terms of interest level, concentration level, comprehension, effectiveness, and convenience.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 한국정보통신학회 2017년도 추계학술대회
• /
• pp.501-503
• /
• 2017

In the water sector, various data such as flow rate, pressure, water quality and water level are collected during the whole process of water purification plant and piping system. The collected data is stored in each water treatment plant's DB, and the collected data are combined in the regional DB and finally stored in the database server of the head office of the Korea Water Resources Corporation. Various abnormal data can be generated when a measuring instrument measures data or data is communicated over various processes, and it can be classified into missing data and wrong data. The cause of each abnormal data is different. Therefore, there is a difference in the method of detecting the wrong side and the missing side data, but the method of cleansing the data is the same. In this study, a program that can automatically refine missing or wrong data by applying deep learning LSTM (Long Short Term Memory) algorithm will be studied.

• KIEAE Journal
• /
• 제17권5호
• /
• pp.69-76
• /
• 2017

Purpose: This study aimed at developing an Artificial Neural Network (ANN) model for predicting the amount of cooling energy consumption of the variable refrigerant flow (VRF) cooling system by the different set-points of the control variables, such as supply air temperature of air handling unit (AHU), condenser fluid temperature, condenser fluid pressure, and refrigerant evaporation temperature. Applying the predicted results for the different set-points, the control algorithm, which embedded the ANN model, will determine the most energy efficient control strategy. Method: The ANN model was developed and tested its prediction accuracy by using matrix laboratory (MATLAB) and its neural network toolbox. The field data sets were collected for the model training and performance evaluation. For completing the prediction model, three major steps were conducted - i) initial model development including input variable selection, ii) model optimization, and iii) performance evaluation. Result: Eight meaningful input variables were selected in the initial model development such as outdoor temperature, outdoor humidity, indoor temperature, cooling load of the previous cycle, supply air temperature of AHU, condenser fluid temperature, condenser fluid pressure, and refrigerant evaporation temperature. The initial model was optimized to have 2 hidden layers with 15 hidden neurons each, 0.3 learning rate, and 0.3 momentum. The optimized model proved its prediction accuracy with stable prediction results.

• Journal of Convergence for Information Technology
• /
• 제11권12호
• /
• pp.39-48
• /
• 2021

The purpose of this study was to identify the degree of grit, resilience, academic self-efficacy, and learning flow of nursing college students in the COVID-19 situation to identify the factors that influence burnout. Data were collected by using questionnaires from 155 students who were in 3rd year of the nursing college in G city, from May 11 to May 25, 2021. Data were analyzed by t-test, ANOVA, Scheffe, Kruskal-Wallis test, Pearson's correlation, and multiple regression. Statistically, burnout showed a significantly negative correlation with grit, resilience and academic self-efficacy. Influencing factors on burnout were resilience, satisfaction of major, academic self-efficacy and satisfaction of clinic practice accounting for 60% of the total change. Based on this study, strategies to enhance resilience, satisfaction of major, academic self-efficacy and satisfaction of clinic practice are required to reduce the burnout of nursing college students in the COVID-19 situation.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• 제19권3호
• /
• pp.165-171
• /
• 2019

The study of the computer architecture has shown that major improvements in price-to-energy performance stems from domain-specific hardware development. This paper analyzes the tensor processing unit (TPU) ASIC which can accelerate the reasoning of the artificial neural network (NN). The core device of the TPU is a MAC matrix multiplier capable of high-speed operation and software-managed on-chip memory. The execution model of the TPU can meet the reaction time requirements of the artificial neural network better than the existing CPU and the GPU execution models, with the small area and the low power consumption even though it has many MAC and large memory. Utilizing the TPU for the tensor flow benchmark framework, it can achieve higher performance and better power efficiency than the CPU or CPU. In this paper, we analyze TPU, simulate the Python modeled OpenTPU, and synthesize the matrix multiplication unit, which is the key hardware.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권10호
• /
• pp.3729-3749
• /
• 2021

At present, deep convolution network-based salient object detection (SOD) has achieved impressive performance. However, it is still a challenging problem to make full use of the multi-scale information of the extracted features and which appropriate feature fusion method is adopted to process feature mapping. In this paper, we propose a new adjacency auxiliary network (AANet) based on multi-scale feature fusion for SOD. Firstly, we design the parallel connection feature enhancement module (PFEM) for each layer of feature extraction, which improves the feature density by connecting different dilated convolution branches in parallel, and add channel attention flow to fully extract the context information of features. Then the adjacent layer features with close degree of abstraction but different characteristic properties are fused through the adjacent auxiliary module (AAM) to eliminate the ambiguity and noise of the features. Besides, in order to refine the features effectively to get more accurate object boundaries, we design adjacency decoder (AAM_D) based on adjacency auxiliary module (AAM), which concatenates the features of adjacent layers, extracts their spatial attention, and then combines them with the output of AAM. The outputs of AAM_D features with semantic information and spatial detail obtained from each feature are used as salient prediction maps for multi-level feature joint supervising. Experiment results on six benchmark SOD datasets demonstrate that the proposed method outperforms similar previous methods.

• Journal of Convergence for Information Technology
• /
• 제11권1호
• /
• pp.28-33
• /
• 2021

Since the stock price is a measure of the future value of the company, when analyzing the stock price, the company's growth potential, such as sales and profits, is considered and invested in stocks. In order to set the criteria for selecting stocks, institutional investors look at current industry trends and macroeconomic indicators, first select relevant fields that can grow, then select related companies, analyze them, set a target price, then buy, and sell when the target price is reached. Stock trading is carried out in the same way. However, general individual investors do not have any knowledge of investment, and invest in items recommended by experts or acquaintances without analysis of financial statements or growth potential of the company, which is lower in terms of return than institutional investors and foreign investors. Therefore, in this study, we propose a research method to select undervalued stocks by analyzing ROE, an indicator that considers the growth potential of a company, such as sales and profits, and predict the stock price flow of the selected stock through deep learning algorithms. This study is conducted to help with investment.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• 제25권1호
• /
• pp.69-74
• /
• 2021

Internet access is also increasing as online activities increase due to the influence of Corona 19. However, network attacks are also diversifying by malicious users, and DDoS among the attacks are increasing year by year. These attacks are detected by intrusion detection systems and can be prevented at an early stage. Various data sets are used to verify intrusion detection algorithms, but in this paper, CICIDS2017, the latest traffic, is used. DDoS attack traffic was analyzed using the decision tree. In this paper, we analyzed the traffic by using the decision tree. Through the analysis, a decisive feature was found, and the accuracy of the decisive feature was confirmed by proceeding the decision tree to prove the accuracy of detection. And the contents of false positive and false negative traffic were analyzed. As a result, learning the feature and the two features showed that the accuracy was 98% and 99.8% respectively.