• Information Systems Review
• /
• v.24 no.1
• /
• pp.105-123
• /
• 2022

Thanks to the remarkable success of Artificial Intelligence (A.I.) techniques, a new possibility for its application on the real-world problem has begun. One of the prominent applications is the bankruptcy prediction model as it is often used as a basic knowledge base for credit scoring models in the financial industry. As a result, there has been extensive research on how to improve the prediction accuracy of the model. However, despite its impressive performance, it is difficult to implement machine learning (ML)-based models due to its intrinsic trait of obscurity, especially when the field requires or values an explanation about the result obtained by the model. The financial domain is one of the areas where explanation matters to stakeholders such as domain experts and customers. In this paper, we propose a novel approach to incorporate financial domain knowledge into local rule generation to provide explanations for the bankruptcy prediction model at instance level. The result shows the proposed method successfully selects and classifies the extracted rules based on the feasibility and information they convey to the users.

• Journal of Korea Water Resources Association
• /
• v.57 no.1
• /
• pp.35-44
• /
• 2024

Research in dam inflow prediction has actively explored the utilization of data-driven machine learning and deep learning (ML&DL) tools across diverse domains. Enhancing not just the inherent model performance but also accounting for model characteristics and preprocessing data are crucial elements for precise dam inflow prediction. Particularly, existing rainfall data, derived from snowfall amounts through heating facilities, introduces distortions in the correlation between snow accumulation and rainfall, especially in dam basins influenced by snow accumulation, such as Soyang Dam. This study focuses on the preprocessing of rainfall data essential for the application of ML&DL models in predicting dam inflow in basins affected by snow accumulation. This is vital to address phenomena like reduced outflow during winter due to low snowfall and increased outflow during spring despite minimal or no rain, both of which are physical occurrences. Three machine learning models (SVM, RF, LGBM) and two deep learning models (LSTM, TCN) were built by combining rainfall and inflow series. With optimal hyperparameter tuning, the appropriate model was selected, resulting in a high level of predictive performance with NSE ranging from 0.842 to 0.894. Moreover, to generate rainfall correction data considering snow accumulation, a simulated snow accumulation algorithm was developed. Applying this correction to machine learning and deep learning models yielded NSE values ranging from 0.841 to 0.896, indicating a similarly high level of predictive performance compared to the pre-snow accumulation application. Notably, during the snow accumulation period, adjusting rainfall during the training phase was observed to lead to a more accurate simulation of observed inflow when predicted. This underscores the importance of thoughtful data preprocessing, taking into account physical factors such as snowfall and snowmelt, in constructing data models.

• Proceedings of the IEEK Conference
• /
• 2004.06a
• /
• pp.43-46
• /
• 2004

In this paper, we present a carrier phase estimation algorithm for LDPC coded systems. LDPC coded system can not achieve the ideal performance if phase offset is introduced by channel. However, the estimation of phase offset is very hard since the operating point of LDPC is very low SNR. To solve this problem, the algorithm using the tentative soft decision value and based on Maximum Likelihood (ML), was proposed in [2]. But this algorithm has problem which works only under constant phase offset. If phase offset is time variant, it has a severe degradation in performance. To solve this problem. we propose two types of estimators. symbol by symbol estimator: Unidirectional estimator (UDE) and hi-directional estimator (BDE), and sub-block estimator (SBE).

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.10 s.352
• /
• pp.1-7
• /
• 2006

Lattice decoding concept has been proposed for the implementation of the Maximum-Likelihood detection which is the optimal receiver from the viewpoint of the BER (Bit Error Rate) performance for MIMO (Multiple Input Multiple Output) systems. Sphere decoding algorithm and K-best decoding algorithm are based on the lattice decoding concept. A K-best decoding algorithm shows a good BER performance with relatively low complexity. However, with small K value, the error propagation effect severely degrades the performance. In this paper, we propose an adaptive K-best decoding algorithm which has lower average complexity and better BER performance than conventional K-best decoding algorithm.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.5
• /
• pp.863-871
• /
• 2010

Until now, many studies related circular data are carried out, but the focuses are mainly on mildly peaked symmetric or asymmetric cases. In this paper we studied a modeling process for sharply peaked asymmetric circular data. By using wrapped Laplace, which was firstly introduced by Jammalamadaka and Kozbowski (2003), and its mixture distributions, we considered the model fitting problem of multi-modal circular data as well as unimodal one. In particular we suggested EM algorithm to find ML estimates of the mixture of wrapped Laplace distributions. Simulation results showed that the suggested EM algorithm is very accurate and useful.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.6
• /
• pp.38-47
• /
• 2000

In pattern classification, the Bhattacharyya distance has been used as a class separability measure. Furthemore, it is recently reported that the Bhattacharyya distance can be used to estimate error of Gaussian ML classifier within 1-2% margin. In this paper, we propose a feature extraction method utilizing the Bhattacharyya distance. In the proposed method, we first predict the classification error with the error estimation equation based on the Bhauacharyya distance. Then we find the feature vector that minimizes the classification error using two search algorithms: sequential search and global search. Experimental reslts show that the proposed method compares favorably with conventional feature extraction methods. In addition, it is possible to determine how man, feature vectors arc needed for achieving the same classification accuracy as in the original space.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.7
• /
• pp.72-85
• /
• 1998

In this paper, we propose a new method that sequentially estimates TDOA(Time Delay Of Arrival) and FDOA(Frequency Delay Of Arrival) for extracting the information about the bearing and relative velocity of a target in passive radar or sonar arrays. The objective is to efficiently estimate the TDOA and FDOA between two sensor signal measurements, corrupted by correlated Gaussian noise sources in an unknown way. The proposed method utilizes the one dimensional slice function of the third order cumulants between the two sensor measurements, by which the effect of correlated Gaussian measurement noises can be significantly suppressed for the estimation of TDOA. Because the proposed sequential algoritjhm uses the one dimensional complex ambiguity function based on the TDOA estimate from the first step, the amount of computations needed for accurate estimationof FDOA can be dramatically reduced, especially for the cases where high frequency resolution is required. It is demonstrated that the proposed algorithm outperforms existing TDOA/FDOA estimation algorithms based on the ML(maximum likelihood) criterionandthe complex ambiguity function of the third order cumulant as well, in the MSE(mean squared error) sense and computational burden. Various numerical resutls on the detection probability, MSE and the floatingpoint computational burden are presented via Monte-Carlo simulations for different types of noises, different lengths of data, and different signal-to-noise ratios.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.5
• /
• pp.217-220
• /
• 2024

Predicting earthquake occurrences accurately is challenging, and preparing all buildings with seismic design for such random events is a difficult task. Analyzing building features to predict potential damage and reinforcing vulnerabilities based on this analysis can minimize damages even in buildings without seismic design. Therefore, research analyzing the efficiency of building damage prediction models is essential. In this paper, we compare the accuracy of earthquake damage prediction models using machine learning classification algorithms, including Random Forest, Extreme Gradient Boosting, LightGBM, and CatBoost, utilizing data from buildings damaged during the 2015 Nepal earthquake.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.16 no.2
• /
• pp.110-114
• /
• 2012

Purpose : PET/CT is widely used for early checking up of cancer and following up of pre and post operation. Image reconstruction method is advanced with mechanical function. We want to evaluate image quality of each reconstruction program based on time of flight (TOF). Materials and Methods : After acquiring phantom images during 2 minutes with Gemini TF (Philips, USA), Biograph mCT (Siemens, USA) and Discovery 690 (GE, USA), we reconstructed image applied to Astonish TF (Philips, USA), ultraHD PET (Siemens, USA), Sharp IR (GE, USA) and not applied. inside of Flangeless Esser PET phantom (Data Spectrum corp., USA) was filled with $^{18}F$-FDG 1.11 kBq/ml (30 Ci/ml) and 4 hot inserts (8. 12. 16. 25 mm) were filled with 8.88 kBq/ml (240 ${\mu}Ci/ml$) the ratio of background activity and hot inserts activity was 1 : 8. Inside of triple line phantom (Data Spectrum corp., USA) was filled with $^{18}F$-FDG 37 MBq/ml (1 mCi). Three of lines were filled with 0.37 MBq (100 ${\mu}Ci$). Contrast ratio and background variability were acquired from reconstruction image used Flangeless Esser PET phantom and resolution was acquired from reconstruction image used triple line phantom. Results : The contrast ratio of image which was not applied to Astonish TF was 8.69, 12.28, 19.31, 25.80% in phantom lid of which size was 8, 12, 16, 25 mm and it which was applied to Astonish TF was 6.24, 13.24, 19.55, 27.60%. It which was not applied to ultraHD PET was 4.94, 12.68, 22.09, 30.14%, it which was applied to ultraHD PET was 4.76, 13.23, 23.72, 31.65%. It which was not applied to SharpIR was 13.18, 17.44, 28.76, 34.67%, it which was applied to SharpIR was 13.15, 18.32, 30.33, 35.73%. The background variability of image which was not applied to Astonish TF was 5.51, 5.42, 7.13, 6.28%. it which was applied to Astonish TF was 7.81, 7.94, 6.40 6.28%. It which was not applied to ultraHD PET was 6.46, 6.63, 5.33, 5.21%, it which was applied to ultraHD PET was 6.08, 6.08, 4.45, 4.58%. It which was not applied to SharpIR was 5.93, 4.82, 4.45, 5.09%, it which was applied to SharpIR was 4.80, 3.92, 3.63, 4.50%. The resolution of phantom line of which location was upper, center, right, which was not applied to Astonish TF was 10.77, 11.54, 9.34 mm it which was applied to Astonish TF was 9.54, 8.90, 8.88 mm. It which was not applied to ultraHD PET was 7.84, 6.95, 8.32 mm, it which was applied to ultraHD PET was 7.51, 6.66, 8.27 mm. It which was not applied to SharpIR was 9.35, 8.69, 8.99, it which was applied to SharpIR was 9.88, 9.18, 9.00 mm. Conclusion : Image quality was advanced generally while reconstruction program which is based on time of flight was used. Futhermore difference of result compared each manufacture reconstruction program showed up, however this is caused by specification of instrument of each manufacture and difference of reconstruction algorithm. Therefore we need further examination to find out appropriate reconstruction condition while using reconstruction program used for advance of image quality.

• Korean Chemical Engineering Research
• /
• v.57 no.2
• /
• pp.274-282
• /
• 2019

In recent years, big data analysis has been expanded to include automatic control through reinforcement learning as well as prediction through modeling. Research on the utilization of image data is actively carried out in various industrial fields such as chemical, manufacturing, agriculture, and bio-industry. In this paper, we applied NASNet, which is an AutoML reinforced learning algorithm, to DeepU-Net neural network that modified U-Net to improve image semantic segmentation performance. We used BRATS2015 MRI data for performance verification. Simulation results show that DeepU-Net has more performance than the U-Net neural network. In order to improve the image segmentation performance, remove dropouts that are typically applied to neural networks, when the number of kernels and filters obtained through reinforcement learning in DeepU-Net was selected as a hyperparameter of neural network. The results show that the training accuracy is 0.5% and the verification accuracy is 0.3% better than DeepU-Net. The results of this study can be applied to various fields such as MRI brain imaging diagnosis, thermal imaging camera abnormality diagnosis, Nondestructive inspection diagnosis, chemical leakage monitoring, and monitoring forest fire through CCTV.