• Journal of Korean Institute of Industrial Engineers
• /
• v.41 no.1
• /
• pp.10-16
• /
• 2015

In this study, we suggest a method to predict probability distribution of a new customer's degree of loyalty using C-CRF that reflects the RFM score and similarity to the neighbors of the customer. An RFM score prediction model is introduced to construct the first feature function of C-CRF. Integrating demographical similarity, purchasing characteristic similarity and purchase history similarity, we make a unified similarity variable to configure the second feature function of C-CRF. Then parameters of each feature function are estimated and we train our C-CRF model by training data set and suggest a probabilistic distribution to estimate a new customer's degree of loyalty. An example is provided to illustrate our model.

• International Journal of Aeronautical and Space Sciences
• /
• v.12 no.4
• /
• pp.396-402
• /
• 2011

Aircraft combat survivability is an essential factor in the design of combat aircrafts that operate in an enemy air defense area. The combat aircrafts will be confronted with anti-aircraft artillery and/or surface-to-air missiles (SAM) from the ground, and their survivability can be divided into two categories: susceptibility and vulnerability. This article studies the prediction of susceptibility in the case of a one-on-one engagement between the combat aircraft and a surface-based threat. The weighted score method is suggested for the prediction of susceptibility parameters, and Monte Carlo simulations are carried out to draw qualitative interpretation of the susceptibility characteristics of combat aircraft systems, such as the F-16 C/D, and the hypersonic aircraft, which is under development in the United States, versus ground threat from the SAM SA-10.

• Food Science and Preservation
• /
• v.30 no.4
• /
• pp.573-588
• /
• 2023

The purpose of this study was to monitor changes in the quality of ginseng and predict its shelf-life. As the storage period of ginseng increased, some quality indicators, such as water-soluble pectin (WSP), CDTA-soluble pectin (CSP), cellulose, weight loss, and microbial growth increased, while others (Na₂CO₃-soluble pectin/NSP, hemicellulose, starch, and firmness) decreased. Principal component analysis (PCA) was performed using the quality attribute data and the principal component 1 (PC1) scores extracted from the PCA results were applied to the multivariate analysis. The reaction rate at different temperatures and the temperature dependence of the reaction rate were determined using kinetic and Arrhenius models, respectively. Among the kinetic models, zeroth-order models with cellulose and a PC1 score provided an adequate fit for reaction rate estimation. Hence, the prediction model was constructed by applying the cellulose and PC1 scores to the zeroth-order kinetic and Arrhenius models. The prediction model with PC1 score showed higher R² values (0.877-0.919) than those of cellulose (0.797-0.863), indicating that multivariate analysis using PC1 score is more accurate for the shelf-life prediction of ginseng. The predicted shelf-life using the multivariate accelerated shelf-life test at 5, 20, and 35℃ was 40, 16, and 7 days, respectively.

• Journal of Information Processing Systems
• /
• v.18 no.2
• /
• pp.282-291
• /
• 2022

This research applies a pre-trained bidirectional encoder representations from transformers (BERT) handwriting recognition model to predict foreign Korean-language learners' writing scores. A corpus of 586 answers to midterm and final exams written by foreign learners at the Intermediate 1 level was acquired and used for pre-training, resulting in consistent performance, even with small datasets. The test data were pre-processed and fine-tuned, and the results were calculated in the form of a score prediction. The difference between the prediction and actual score was then calculated. An accuracy of 95.8% was demonstrated, indicating that the prediction results were strong overall; hence, the tool is suitable for the automatic scoring of Korean written test answers, including grammatical errors, written by foreigners. These results are particularly meaningful in that the data included written language text produced by foreign learners, not native speakers.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.134-144
• /
• 2023

Nowadays, Deep Learning (DL) technology is being used in several government departments. South Korea imports a lot of seafood. If the demand for fishery products is not accurately predicted, then there will be a shortage of fishery products and the price of the fishery product may rise sharply. So, South Korea's Ministry of Ocean and Fisheries is attempting to accurately predict seafood imports using deep learning. This paper introduces the solution for the fish import prediction in South Korea using the Long Short-Term Memory (LSTM) method. It was found that there was a huge gap between the sum of consumption and export against the sum of production especially in the case of two species that are Hairtail and Pollock. An import prediction is suggested in this research to fill the gap with some advanced Deep Learning methods. This research focuses on import prediction using Machine Learning (ML) and Deep Learning methods to predict the import amount more precisely. For the prediction, two Deep Learning methods were chosen which are Artificial Neural Network (ANN) and Long Short-Term Memory (LSTM). Moreover, the Machine Learning method was also selected for the comparison between the DL and ML. Root Mean Square Error (RMSE) was selected for the error measurement which shows the difference between the predicted and actual values. The results obtained were compared with the average RMSE scores and in terms of percentage. It was found that the LSTM has the lowest RMSE score which showed the prediction with higher accuracy. Meanwhile, ML's RMSE score was higher which shows lower accuracy in prediction. Moreover, Google Trend Search data was used as a new feature to find its impact on prediction outcomes. It was found that it had a positive impact on results as the RMSE values were lowered, increasing the accuracy of the prediction.

• Journal of Biomedical Engineering Research
• /
• v.30 no.1
• /
• pp.94-102
• /
• 2009

In this paper, we propose a hearing impairment simulator considering reduced frequency selectivity of the hearing impaired, and verify it's performance through experiments. The reduced frequency selectivity was embodied by spectral smearing using linear prediction coding(LPC). The experiments are composed of 4 kinds of tests; pure tone test, speech reception threshold(SRT) test, and word recognition score(WRS) test without spectral smearing and with spectral smearing. The experiments of the hearing impairment simulator were performed with 9 subjects who have normal hearing. The amount of spectral smearing was controlled by LPC order. The percentile score of WRS test without smearing is $89.78{\pm}2.420%$. The scores of WRS with 24th LPC order and with 8th LPC order are $88.00{\pm}3.556%$ and $83.78{\pm}2.123%$ respectively. It is verified that WRS score is lowered by decreasing LPC order. This is a reasonable result considering that spectral smearing is getting heavier according to decreasing LPC order. It is confirmed that spectral smearing using LPC simulates the reduced frequency selectivity of the hearing impaired and affects the clearness of speech reception.

• Journal of Multimedia Information System
• /
• v.9 no.2
• /
• pp.75-86
• /
• 2022

The existing image quality assessment (IQA) datasets have a small number of samples. Some methods based on transfer learning or data augmentation cannot make good use of image quality-related features. A No Reference (NR)-IQA method based on multi-task training and quality awareness is proposed. First, single or multiple distortion types and levels are imposed on the original image, and different strategies are used to augment different types of distortion datasets. With the idea of weak supervision, we use the Full Reference (FR)-IQA methods to obtain the pseudo-score label of the generated image. Then, we combine the classification information of the distortion type, level, and the information of the image quality score. The ResNet50 network is trained in the pre-train stage on the augmented dataset to obtain more quality-aware pre-training weights. Finally, the fine-tuning stage training is performed on the target IQA dataset using the quality-aware weights to predicate the final prediction score. Various experiments designed on the synthetic distortions and authentic distortions datasets (LIVE, CSIQ, TID2013, LIVEC, KonIQ-10K) prove that the proposed method can utilize the image quality-related features better than the method using only single-task training. The extracted quality-aware features improve the accuracy of the model.

• Journal of Trauma and Injury
• /
• v.18 no.2
• /
• pp.141-147
• /
• 2005

Purpose: Recently, The new Injury Severity Score (NISS) has become a more accurate predictor of mortality than the traditional Injury Severity Score (ISS) in the trauma population. Trauma Score Injury Severity Score (TRISS) method, regarded as the gold standard for mortality prediction in trauma patients, still contains the ISS as an essential factor within its formula. The purpose of this study was to determine whether a simple modification of the TRISS by replacing the ISS with the NISS would improve the prediction of in-hospital mortality in a trauma population with blunt head and neck trauma. Objects and Methods: The study population consisted of 641 patients from a regional emergency medical center in Kyoungsangnam-do. Demographic data, clinical information, the final diagnosis, and the outcome for each patient were collected in a retrospective manner. the ISS, NISS, TRISS, and modified TRISS were calculated for each patients. The discrimination and the calibration of the ISS, NISS, modified TRISS and conventional TRISS models were compared using receiver operator characteristic (ROC) curves, areas under the ROC curve (AUC) and Hosmer-Lemeshow statistics. Results: The AUC of the ISS, NISS, modified TRISS, and conventional TRISS were 0.885, 0.941, 0.971, and 0.918 respectively. Statistical differences were found between the ISS and the NISS (p=0.008) and between the modified TRISS and the conventional TRISS (p=0.009). Hosmer-Lemeshow chi square values were 13.2, 2.3, 50.1, and 13.8, respectively; only the conventional TRISS failed to achieve the level of and an excellent calibration model (p<0.001). Conclusion: The modified TRISS is a more accurate predictor of in-hospital mortality than the conventional TRISS in a trauma population of blunt head and neck trauma.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.38-59
• /
• 2022

Web services instances can be classified into two categories, namely trusted and untrusted from users. A web service with high throughput (TP) and low response time (RT) instance values is a trusted web service. Web services are not trustworthy due to the mismatch in the guaranteed instance values and the actual values achieved by users. To perform web services selection from users' attained TP and RT values, we need to verify the correct prediction of trusted and untrusted instances from invoked web services. This accurate prediction of web services instances is used to perform the selection of web services. We propose to construct fuzzy rules to label web services instances correctly. This paper presents web services selection using a well-known machine learning algorithm, namely REPTree, for the correct prediction of trusted and untrusted instances. Performance comparison of REPTree with five machine learning models is conducted on web services datasets. We have performed experiments on web services datasets using a ten k-fold cross-validation method. To evaluate the performance of the REPTree classifier, we used accuracy metrics (Sensitivity and Specificity). Experimental results showed that web service (WS1) gained top selection score with the (47.0588%) trusted instances, and web service (WS2) was selected the least with (25.00%) trusted instances. Evaluation results of the proposed web services selection approach were found as (asymptotic sig. = 0.019), demonstrating the relationship between final selection and recommended trust score of web services.

• Economic and Environmental Geology
• /
• v.56 no.1
• /
• pp.65-73
• /
• 2023

As one of the most vulnerable countries to floods, there should be an increased necessity for accurate and reliable flood forecasting in Indonesia. Therefore, a new prediction model using a machine learning algorithm is proposed to provide daily flood prediction in Indonesia. Data crawling was conducted to obtain daily rainfall, streamflow, land cover, and flood data from 2008 to 2021. The model was built using a Random Forest (RF) algorithm for classification to predict future floods by inputting three days of rainfall rate, forest ratio, and stream flow. The accuracy, specificity, precision, recall, and F1-score on the test dataset using the RF algorithm are approximately 94.93%, 68.24%, 94.34%, 99.97%, and 97.08%, respectively. Moreover, the AUC (Area Under the Curve) of the ROC (Receiver Operating Characteristics) curve results in 71%. The objective of this research is providing a model that predicts flood events accurately in Indonesian regions 3 months prior the day of flood. As a trial, we used the month of June 2022 and the model predicted the flood events accurately. The result of prediction is then published to the website as a warning system as a form of flood mitigation.