• Journal of Korea Water Resources Association
• /
• v.55 no.11
• /
• pp.903-911
• /
• 2022

Groundwater, one of the resources for supplying water, fluctuates in water level due to various natural factors. Recently, research has been conducted to predict fluctuations in groundwater levels using Artificial Neural Network (ANN). Previously, among operators in ANN, Gradient Descent (GD)-based Optimizers were used as Optimizer that affect learning. GD-based Optimizers have disadvantages of initial correlation dependence and absence of solution comparison and storage structure. This study developed Gradient Descent combined with Harmony Search (GDHS), a new Optimizer that combined GD and Harmony Search (HS) to improve the shortcomings of GD-based Optimizers. To evaluate the performance of GDHS, groundwater level at Icheon Yullhyeon observation station were learned and predicted using Multi Layer Perceptron (MLP). Mean Squared Error (MSE) and Mean Absolute Error (MAE) were used to compare the performance of MLP using GD and GDHS. Comparing the learning results, GDHS had lower maximum, minimum, average and Standard Deviation (SD) of MSE than GD. Comparing the prediction results, GDHS was evaluated to have a lower error in all of the evaluation index than GD.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.7
• /
• pp.1749-1756
• /
• 2014

Knowledge about protein subcellular localization provides important information about protein function. This paper improves a label power-set multi-label classification for the accurate prediction of subcellular localization of proteins which simultaneously exist at multiple subcellular locations. Among multi-label classification methods, label power-set method can effectively model the correlation between subcellular locations of proteins performing certain biological function. With constrained optimization, this paper calculates combination weights which are used in the linear combination representation of a multi-label by other multi-labels. Using these weights, the prediction probabilities of multi-labels are combined to give final prediction results. Experimental results on human protein dataset show that the proposed method achieves higher performance than other prediction methods for protein subcellular localization. This shows that the proposed method can successfully enrich the prediction probability of multi-labels by exploiting the overlapping information between multi-labels.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.1A
• /
• pp.27-33
• /
• 2009

This paper proposes transmit power control techniques with fading channel prediction scheme based on recurrent neural network for high-speed mobile communication systems. The operation result of recurrent neural network which is derived interpretively solves complexity problems of neural network circuit, and channel gain of multiple transmit antenna is derived with maximum ratio combining(MRC) by using the operation result, and this channel gain control transmit power of each antenna. simulation results show that proposed method has a outstanding performance compared to method that is not to be controlled power based on channel prediction. Most of legacy studies are for robust receive technique of fading signals or channel prediction of fading signals limited low-speed mobility, but in open loop Power control, proposed channel prediction method decrease system complexity with removal of fading effect in transmitter.

• The KIPS Transactions:PartA
• /
• v.18A no.6
• /
• pp.249-254
• /
• 2011

This paper describes an efficient design of the interpolation circuit to generate the luma and chroma sub-pixels for H.264 motion estimation. The circuit based on the proposed architecture does not require any input data buffering and processes the horizontal, vertical and diagonal sub-pixel interpolations in parallel. The performance of the circuit is further improved by simultaneously processing the 1/2-pixel and 1/4-pixel interpolations for luma components and the 1/8-pixel interpolations for chroma components. In order to reduce the circuit size, we store the intermediate data required to process all the interpolations in parallel in the internal SRAM's instead of registers. We described the proposed circuit at register transfer level and verified its operation on FPGA board. We also synthesized the gate-level circuit using 130nm CMOS standard cell library. It consists of 20,674 gates and has the maximum operating frequency of 244MHz. The total number of SPSRAM bits used in our circuit is 3,232. The size of our circuit (including logic gates and SRAM's) is smaller than others and the performance is still comparable to them.

• Journal of Korea Water Resources Association
• /
• v.56 no.7
• /
• pp.431-438
• /
• 2023

Many shorelines are facing the beach erosion. Considering the climate change and the increment of coastal population, the erosion problem could be accelerated. To address this issue, developing a sediment transport model for rapidly predicting terrain change is crucial. In this study, a sediment transport model based on GPU parallel arithmetic was introduced, and it was supposed to simulate the terrain change well with a higher computing speed compared to the CPU based model. We also aim to investigate the model performance and the GPU computational efficiency. We applied several dam break cases to verified model, and we found that the simulated results were close to the observed results. The computational efficiency of GPU was defined by comparing operation time of CPU based model, and it showed that the GPU based model were more efficient than the CPU based model.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.46-46
• /
• 2022

유기물의 복잡한 혼합물인 CDOM(Colored or Chromophoric Dissolved Organic Matter)은 하천 내 BOD(Biological Oxygen Demand), COD(Chemical Oxygen Demand) 및 유기 오염물질과 상당한 관련이 있다. CDOM은 가시광선 영역에서 빛을 흡수하는 성질을 가지고 있으며, 최근 원격감지 기술로 CDOM을 모니터링하기 위한 연구가 진행되고 있다. 본 연구에서는 백제보 상류 23km 구간에서 3년(2016~2018) 중 13일의 초분광영상을 활용하여 머신러닝 기반 CDOM을 추정 알고리즘을 개발하고자 한다. 초분광영상은 400~970 nm의 범위의 4 nm 간격 127개 대역의 분광해상도와 2 m의 공간해상도를 가진 항공기 탑재 AsiaFENIX 초분광 센서를 통해 수집하였으며 CDOM은 Millipore polycarbonate filter (𝚽47, 0.2 ㎛)에서 여과된 CDOM 샘플 자료를 200~800 nm의 흡수계수 스펙트럼으로 추출하여 사용하였다. CDOM 값은 전체기간 동안 2.0~11.0 m^-1의 값 분포를 보였으며 5 m^-1이상의 고농도 구간 자료개수가 전체 153개 샘플자료 중 21개로 불균형하다. 따라서 ADASYN(Adaptive Synthesis Sampling Approach)의 oversampling 방법으로 생성된 합성 데이터를 사용하여 원본 데이터의 소수계층 데이터 불균형을 해결하고 모델 예측 성능을 개선하고자 하였다. 생성된 합성 데이터를 입력변수로 하여 ANN(Artificial Neural Netowk)을 활용한 CDOM 예측 알고리즘을 구축하였다. ADASYN 기법을 통한 합성 데이터는 관측된 데이터의 불균형을 해결하여 기계학습 모델의 CDOM 탐지 성능을 향상시킬 수 있으며, 저수지 내 유기 오염물질 관리를 위한 설계를 지원하는데 사용할 수 있을 것으로 판단된다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.1
• /
• pp.20-27
• /
• 2013

Recently, variety of methods have been studied to improve automotive fuel economy and the reduction of exhaust emissions. The purpose of this study is to identify the change in the molecular structure of gasoline and diesel by the ion ceramic bar according to the immersion time and to predict the effect for the fuel economy and exhaust emissions by the immersion time. In order to achieve the purpose, we got sedimentation samples for physical analysis and chemical analysis by experiments and characteristics were analyzed. As a result, the changes in the molecular structure by the ceramic bar in the engine by the chemical and physical analysis was able to predict the performance improvement in the case of gasoline. But there is a need to produce suitable ceramic bar for the diesel because there was an irregular change depending on the time of sedimentation in the diesel.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.1
• /
• pp.7-14
• /
• 2022

Sensor Registry System (SRS) has been devised for maintaining semantic interoperability of data on heterogeneous sensor networks. SRS measures the connectability of the mobile device to ambient sensors based on positions and only provides metadata of sensors that may be successfully connected. The step of identifying the ambient sensors which can be successfully connected is called sensor filtering. Improving the performance of sensor filtering is one of the core issues of SRS research. In reality, GPS sometimes shows the wrong position and thus leads to failed sensor filtering. Therefore, this paper proposes a new sensor filtering strategy using geographical embedding and neural network-based path prediction. This paper also evaluates the service provision rate with the Monte Carlo approach. The empirical study shows that the proposed method can compensate for position abnormalities and is an effective model for sensor filtering in SRS.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.10 s.352
• /
• pp.8-17
• /
• 2006

Recently, the high-speed Internet users increase rapidly and broadband networks have been widely deployed. However, the current TCP congestion control algorithm was designed for relatively narrowband network environments, and thus its performance is inefficient for traffic transport in broadband networks. To remedy this problem, the TCP having an enhanced congestion control algorithm is required for broadband networks. In this paper, we propose an improved TCP congestion control that can sufficiently utilize the large available bandwidth in broadband networks. The proposed algorithm predicts the available bandwidth by using ACK information and RTT variation, and prevents large packet losses by adjusting congestion window size appropriately. Also, it can rapidly utilize the large available bandwidth by enhancing the legacy TCP algorithm in congestion avoidance phase. In order to evaluate the performance of the proposed algorithm, we use the ns-2 simulator. The simulation results show that the proposed algorithm improves not only the utilization of the available bandwidth but also RTT fairness and the fairness between contending TCP flows better than the HSTCP in high bandwidth delay product network environment.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_1
• /
• pp.807-821
• /
• 2020

The objective of this study is to evaluate the applicability of representative spatio-temporal fusion models developed for the fusion of mid- and low-resolution satellite images in order to construct a set of time-series high-resolution images for crop monitoring. Particularly, the effects of the characteristics of input image pairs on the prediction performance are investigated by considering the principle of spatio-temporal fusion. An experiment on the fusion of multi-temporal Sentinel-2 and RapidEye images in agricultural fields was conducted to evaluate the prediction performance. Three representative fusion models, including Spatial and Temporal Adaptive Reflectance Fusion Model (STARFM), SParse-representation-based SpatioTemporal reflectance Fusion Model (SPSTFM), and Flexible Spatiotemporal DAta Fusion (FSDAF), were applied to this comparative experiment. The three spatio-temporal fusion models exhibited different prediction performance in terms of prediction errors and spatial similarity. However, regardless of the model types, the correlation between coarse resolution images acquired on the pair dates and the prediction date was more significant than the difference between the pair dates and the prediction date to improve the prediction performance. In addition, using vegetation index as input for spatio-temporal fusion showed better prediction performance by alleviating error propagation problems, compared with using fused reflectance values in the calculation of vegetation index. These experimental results can be used as basic information for both the selection of optimal image pairs and input types, and the development of an advanced model in spatio-temporal fusion for crop monitoring.