• The Transactions of the Korea Information Processing Society
• /
• v.1 no.3
• /
• pp.279-289
• /
• 1994

A Geographic Database System is a database system which supports map-formed output and allows users to store, retrieve, manage and analyze spatial and aspatial data. Because of large data amount, takes too much time to input spatial data into a Geographic Database System and too much storage. Therefore, an efficient spatial data collecting system is highly required for a Geographic Database System to reduce the input processing time and to use the storage efficiently. In this paper, we analyze conventional vectorizing methods and suggest a different approach. Our approach vectorizes specific geographic data when the users input its aspatial data, instead of vectorizing all the map data. And also, we propose optimized vector data format using tag bit to use the storage that collected data efficiently.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.491-493
• /
• 2022

Flood damage due to torrential rains and typhoons is occurring in many parts of the world. In this paper, we propose a water level prediction model using water level, precipitation, and humidity data, which are key parameters for flood prediction, as input data. Based on the LSTM and GRU models, which have already proven time-series data prediction performance in many research fields, different input datasets were constructed using the ASOS(Automated Synoptic Observing System) data and AWS(Automatic Weather System) data provided by the Korea Meteorological Administration, and performance comparison experiments were conducted. As a result, the best results were obtained when using ASOS data. Through this paper, a performance comparison experiment was conducted according to the input data, and as a future study, it is thought that it can be used as an initial study to develop a system that can make an evacuation decision in advance in connection with the flood risk determination model.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.11
• /
• pp.473-478
• /
• 2022

Evaluation learning based on code testing is becoming a popular solution in programming education via Online judge(OJ). In the recent past, many papers have been published on how to detect plagiarism through source code similarity analysis to support OJ. However, deep learning-based research to support automated tutoring is insufficient. In this paper, we propose Input & Output side FiLM models to predict whether the input code will pass or fail. By applying Feature-wise Linear Modulation(FiLM) technique to GRU, our model can learn combined information of Java byte codes and problem information that it tries to solve. On experimental design, a balanced sampling technique was applied to evenly distribute the data due to the occurrence of asymmetry in data collected by OJ. Among the proposed models, the Input Side FiLM model showed the highest performance of 73.63%. Based on result, it has been shown that students can check whether their codes will pass or fail before receiving the OJ evaluation which could provide basic feedback for improvements.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.1
• /
• pp.41.2-41.2
• /
• 2021

In this study, we generate He I 1083 nm images from Solar Dynamic Observatory (SDO)/Atmospheric Imaging Assembly (AIA) images using a novel deep learning method (pix2pixHD) based on conditional Generative Adversarial Networks (cGAN). He I 1083 nm images from National Solar Observatory (NSO)/Synoptic Optical Long-term Investigations of the Sun (SOLIS) are used as target data. We make three models: single input SDO/AIA 19.3 nm image for Model I, single input 30.4 nm image for Model II, and double input (19.3 and 30.4 nm) images for Model III. We use data from 2010 October to 2015 July except for June and December for training and the remaining one for test. Major results of our study are as follows. First, the models successfully generate He I 1083 nm images with high correlations. Second, the model with two input images shows better results than those with one input image in terms of metrics such as correlation coefficient (CC) and root mean squared error (RMSE). CC and RMSE between real and AI-generated ones for the model III with 4 by 4 binnings are 0.84 and 11.80, respectively. Third, AI-generated images show well observational features such as active regions, filaments, and coronal holes. This work is meaningful in that our model can produce He I 1083 nm images with higher cadence without data gaps, which would be useful for studying the time evolution of chromosphere and coronal holes.

• Structural Monitoring and Maintenance
• /
• v.7 no.2
• /
• pp.109-124
• /
• 2020

Benefiting from the massive monitoring data collected by the Structural health monitoring (SHM) system, scholars can grasp the complex environmental effects and structural state during structure operation. However, the monitoring data is often missing due to sensor faults and other reasons. It is necessary to study the recovery method of missing monitoring data. Taking the structural temperature monitoring data of Nanjing Dashengguan Yangtze River Bridge as an example, the long short-term memory (LSTM) network-based recovery method for missing structural temperature data is proposed in this paper. Firstly, the prediction results of temperature data using LSTM network, support vector machine (SVM), and wavelet neural network (WNN) are compared to verify the accuracy advantage of LSTM network in predicting time series data (such as structural temperature). Secondly, the application of LSTM network in the recovery of missing structural temperature data is discussed in detail. The results show that: the LSTM network can effectively recover the missing structural temperature data; incorporating more intact sensor data as input will further improve the recovery effect of missing data; selecting the sensor data which has a higher correlation coefficient with the data we want to recover as the input can achieve higher accuracy.

• IE interfaces
• /
• v.22 no.1
• /
• pp.44-55
• /
• 2009

We propose a method for selection of input-output factors in DEA. It is designed to select better combinations of input-output factors that are well suited for evaluating substantial performance of DMUs. Several selected DEA models with different input-output factors combinations are evaluated, and the relationship between the computed efficiency scores and a single performance criterion of DMUs is investigated using decision tree. Based on the results of decision tree analysis, a relatively better DEA model can be chosen, which is expected to well represent the true performance of DMUs. We illustrate the effectiveness of the proposed method by applying it to the efficiency evaluation of 101 listed companies in steel and metal industry.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.3
• /
• pp.169-175
• /
• 1996

In this paper, a new parallel neural network system that performs dynamic competitive learning is proposed. Conventional learning mehtods utilize the full dimension of the original input patterns. However, a particular attribute or dimension of the input patterns does not necessarily contribute to classification. The proposed system consists of parallel neural networks with the reduced input dimension in order to take advantage of the information in each dimension of the input patterns. Consensus schemes were developed to decide the netowrks performs a competitive learning that dynamically generates output neurons as learning proceeds. Each output neuron has it sown class threshold in the proposed dynamic competitive learning. Because the class threshold in the proposed dynamic learning phase, the proposed neural netowrk adapts properly to the input patterns distribution. Experimental results with remote sensing and speech data indicate the improved performance of the proposed method compared to the conventional learning methods.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.2562-2567
• /
• 2005

This paper suggests a new method discretization of nonlinear system using Taylor series expansion and zero-order hold assumption. This method is applied into the sampled-data representation of a nonlinear system with input time delay. Additionally, the delayed input is time varying and its amplitude is bounded. The maximum time-delayed input is assumed to be two sampling periods. Them mathematical expressions of the discretization method are presented and the ability of the algorithm is tested for some of the examples. And 'hybrid' discretization scheme that result from a combination of the ‘scaling and squaring' technique with the Taylor method are also proposed, especially under condition of very low sampling rates. The computer simulation proves the proposed algorithm discretized the nonlinear system with the variable time-delayed input accurately.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.153.3-153
• /
• 2001

Recently, the researches on the mobile computing technologies for palm computers, PDA´s and wearable computers became very active. In the development of mobile devices, one of the key technologies is the human interface. So, this paper suggests a new input device for PDA´s and wearable computers so-called key-glove. The design methods of key-glove are discussed in this paper and we manufactured the key-glove which recognizes that character is typed in though the hand´s movements analysis and is designed as an input device for wearable computers and virtual environment. Also, we are executes a performance test for alphanumeric data entry, command entry and X-Y pointer input. In the results, we are confirmed in its ...

• Proceedings of the IEEK Conference
• /
• 2001.06b
• /
• pp.137-140
• /
• 2001

This paper shows an asynchronous comparator circuit for 1.2Gbps signal receiver that converts 1.2Gbps data rate input signals with less than 100㎷ swing to on-chip CMOS compatible voltage levels in a 0.35${\mu}{\textrm}{m}$ CMOS process. Folded-cascode nMOS input stage with source-coupled pMOS input stage cover rail-to-rail input common-mode range. Drastic gain-bandwidth increment due to gain-boosting stage with positive-feedback latch as well as wide input common-mode range make designed circuit be suitable for a fully differential signal receiver. HSPICE simulation results show that worst-case sensitivity is less than 20㎷ and maximum propagation delay is 640-psec. And also we verified 3.97㎽ power consumption with 150㎷ differential swing amplitude at 1.2Gbps.