• Atmosphere
• /
• v.17 no.3
• /
• pp.217-230
• /
• 2007

Using the Lorenz-95 simple model, which can simulate many atmospheric characteristics, we compare the performance of ensemble strategies such as bred vectors, the bred vectors rotated (to be orthogonal to each bred member), and the Ensemble Transform Kalman Filter (ETKF). The performance metrics used are the RMSE of ensemble means, the ratio of RMS error of ensemble mean to the spread of ensemble, rank histograms to see if the ensemble member can well represent the true probability density function (pdf), and the distribution of eigen-values of the forecast ensemble, which can provide useful information on the independence of each member. In the meantime, the orthogonal bred vectors can achieve the considerable progress comparing the bred vectors in all aspects of RMSE, spread, and independence of members. When we rotate the bred vectors for orthogonalization, the improvement rate for the spread of ensemble is almost as double as that for RMS error of ensemble mean compared to the non-rotated bred vectors on a simple model. It appears that the result is consistent with the tentative test on the operational model in KMA. In conclusion, ETKF is superior to the other two methods in all terms of the assesment ways we used when it comes to ensemble prediction. But we cannot decide which perturbation strategy is better in aspect of the structure of the background error covariance. It appears that further studies on the best perturbation way for hybrid variational data assimilation to consider an error-of-the-day(EOTD) should be needed.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.4 s.310
• /
• pp.50-57
• /
• 2006

In Electronic Commerce, the latest most of the personalized recommender systems have applied to the collaborative filtering technique. This method calculates the weight of similarity among users who have a similar preference degree in order to predict and recommend the item which hits to propensity of users. In this case, we commonly use Pearson Correlation Coefficient. However, this method is feasible to calculate a correlation if only there are the items that two users evaluated a preference degree in common. Accordingly, the accuracy of prediction falls. The weight of similarity can affect not only the case which predicts the item which hits to propensity of users, but also the performance of the personalized recommender system. In this study, we verify the improvement of the prediction accuracy through an experiment after observing the rule of the weight of similarity applying Vector similarity, Entropy, Inverse user frequency, and Default voting of Information Retrieval field. The result shows that the method combining the weight of similarity using the Entropy with Default voting got the most efficient performance.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.2
• /
• pp.53-60
• /
• 2012

Nearest-neighbor classification predicts the class of an input data with the most frequent class among the near training data of the input data. Even though nearest-neighbor classification doesn't have a training stage, all of the training data are necessary in a predictive stage and the generalization performance depends on the quality of training data. Therefore, as the training data size increase, a nearest-neighbor classification requires the large amount of memory and the large computation time in prediction. In this paper, we propose a prototype selection algorithm that predicts the class of test data with the new set of prototypes which are near-boundary training data. Based on Tomek links and distance metric, the proposed algorithm selects boundary data and decides whether the selected data is added to the set of prototypes by considering classes and distance relationships. In the experiments, the number of prototypes is much smaller than the size of original training data and we takes advantages of storage reduction and fast prediction in a nearest-neighbor classification.

• Atmosphere
• /
• v.31 no.5
• /
• pp.637-656
• /
• 2021

The United States has been known as the world's major producer of crops such as wheat, corn, and soybeans. Therefore, using meteorological long-term forecast data to project reliable crop yields in the United States is important for planning domestic food policies. The current study is part of an effort to improve the seasonal predictability of regional-scale precipitation across the United States for estimating crop production in the country. For the purpose, a dynamic downscaling method using Weather Research and Forecasting (WRF) model is utilized. The WRF simulation covers the crop-growing period (March to October) during 2000-2020. The initial and lateral boundary conditions of WRF are derived from the Pusan National University Coupled General Circulation Model (PNU CGCM), a participant model of Asia-Pacific Economic Cooperation Climate Center (APCC) Long-Term Multi-Model Ensemble Prediction System. For bias correction of downscaled daily precipitation, empirical quantile mapping (EQM) is applied. The downscaled data set without and with correction are called WRF_UC and WRF_C, respectively. In terms of mean precipitation, the EQM effectively reduces the wet biases over most of the United States and improves the spatial correlation coefficient with observation. The daily precipitation of WRF_C shows the better performance in terms of frequency and extreme precipitation intensity compared to WRF_UC. In addition, WRF_C shows a more reasonable performance in predicting drought frequency according to intensity than WRF_UC.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.203-210
• /
• 2020

Memory-based collaborative filtering is one of the representative types of the recommender system, but it suffers from the inherent problem of data sparsity. Although many works have been devoted to solving this problem, there is still a request for more systematic approaches to the problem. This study exploits distribution of user ratings given to items for computing similarity. All user ratings are utilized in the proposed method, compared to previous ones which use ratings for only common items between users. Moreover, for similarity computation, it takes a global view of ratings for items by reflecting other users' ratings for that item. Performance is evaluated through experiments and compared to that of other relevant methods. The results reveal that the proposed demonstrates superior performance in prediction and rank accuracies. This improvement in prediction accuracy is as high as 2.6 times more than that achieved by the state-of-the-art method over the traditional similarity measures.

• Atmosphere
• /
• v.31 no.1
• /
• pp.85-100
• /
• 2021

The necessity of accurate high-resolution meteorological forecasts becomes increasing in socio-economical applications and disaster risk management. The Korea Meteorological Administration Post-Processing (KMAPP) system has been operated to provide high-resolution meteorological forecasts of 100 m over the South Korea region. This study evaluates and improves the KMAPP performance in simulating wind speeds over complex terrain areas using the ICE-POP 2018 field campaign measurements. The mountainous measurements give a unique opportunity to evaluate the operational wind speed forecasts over the complex terrain area. The one-month wintertime forecasts revealed that the operational Local Data Assimilation and Prediction System (LDAPS) has systematic errors over the complex mountainous area, especially in deep valley areas, due to the orographic smoothing effect. The KMAPP reproduced the orographic height variation over the complex terrain area but failed to reduce the wind speed forecast errors of the LDAPS model. It even showed unreasonable values (~0.1 m s-1) for deep valley sites due to topographic overcorrection. The model's static parameters have been revised and applied to the KMAPP-Wind system, developed newly in this study, to represent the local topographic characteristics better over the region. Besides, sensitivity tests were conducted to investigate the effects of the model's physical correction methods. The KMAPP-Wind system showed better performance in predicting near-surface wind speed during the ICE-POP period than the original KMAPP version, reducing the forecast error by 21.2%. It suggests that a realistic representation of the topographic parameters is a prerequisite for the physical downscaling of near-ground wind speed over complex terrain areas.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.283-294
• /
• 2022

The feature map used in the network for deep learning generally has larger data than the image and a higher compression rate than the image compression rate is required to transmit the feature map. This paper proposes a method for transmitting a pyramid feature map with high compression rate, which is used in a network with an FPN structure that has robustness to object size in deep learning-based image processing. In order to efficiently compress the pyramid feature map, this paper proposes a structure that predicts a pyramid feature map of a level that is not transmitted with pyramid feature map of some levels that transmitted through the proposed prediction network to efficiently compress the pyramid feature map and restores compression damage through the proposed reconstruction network. Suggested mAP, the performance of object detection for the COCO data set 2017 Train images of the proposed method, showed a performance improvement of 31.25% in BD-rate compared to the result of compressing the feature map through VTM12.0 in the rate-precision graph, and compared to the method of performing compression through PCA and DeepCABAC, the BD-rate improved by 57.79%.

• Journal of KIISE:Information Networking
• /
• v.37 no.4
• /
• pp.284-293
• /
• 2010

For the successful deployment of Mobile Internet, fast handover technologies are essential. For the past few years several handover mechanisms are suggested, and Fast Handover for Proxy Mobile IPv6 (PFMIPv6) is one of the promising schemes for this purpose. In this paper, we propose a novel L2/L3 cross layer handover scheme based on ARIMA prediction model to apply PFMIPv6 to Mobile Internet environment effectively. Performance gains are evaluated in terms of probabilities of predictive-mode operation, handover latencies, packet loss probabilities, and signaling costs. Three mobilities models are used for our simulation: Manhattan Model, Open Area Model, and Freeway Model. Simulation results show that the proposed scheme can increase probabilities of predictive-mode operation and reduce handover latency, packet loss probabilities, and signaling cost.

• The Journal of the Korea Contents Association
• /
• v.11 no.2
• /
• pp.69-78
• /
• 2011

Recently, the bandwidth available to an end user has been dramatically increasing with the advancing of network technologies. This high-speed network naturally requires faster and/or stable data transmission techniques. The UDT(UDP based Data Transfer protocol) is a UDP based transport protocol, and shows more efficient throughput than TCP in the long RTT environment, with benefit of rate control for a SYN time. With a NAK event, however, it is difficult to expect an optimum performance due to the increase of fixed sendInterval and the flow control based on the previous RTT. This paper proposes a rate control method on following a NAK, by adjusting the sendInterval according to some degree of RTT period which calculated from a set of experimental results. In addition, it suggests an improved flow control method based on the TCP vegas, in order to predict the network congestion afterward. An experimental results show that the revised flow control method improves UDT's throughput about 20Mbps. With combining the rate control and flow control proposed, the UDT throughput can be improved up to 26Mbps in average.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.2
• /
• pp.65-76
• /
• 2022

Recently, not only traditional statistical techniques but also machine learning algorithms have been used to make more accurate bankruptcy predictions. But the insolvency rate of companies dealing with financial institutions is very low, resulting in a data imbalance problem. In particular, since data imbalance negatively affects the performance of artificial intelligence models, it is necessary to first perform the data imbalance process. In additional, as artificial intelligence algorithms are advanced for precise decision-making, regulatory pressure related to securing transparency of Artificial Intelligence models is gradually increasing, such as mandating the installation of explanation functions for Artificial Intelligence models. Therefore, this study aims to present guidelines for eXplainable Artificial Intelligence-based corporate bankruptcy prediction methodology applying SMOTE techniques and LIME algorithms to solve a data imbalance problem and model transparency problem in predicting corporate bankruptcy. The implications of this study are as follows. First, it was confirmed that SMOTE can effectively solve the data imbalance issue, a problem that can be easily overlooked in predicting corporate bankruptcy. Second, through the LIME algorithm, the basis for predicting bankruptcy of the machine learning model was visualized, and derive improvement priorities of financial variables that increase the possibility of bankruptcy of companies. Third, the scope of application of the algorithm in future research was expanded by confirming the possibility of using SMOTE and LIME through case application.