• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.89-103
• /
• 2019

Recently, various approaches to recommendation systems have been studied in terms of the quality of recommendation system. A recommender system basically aims to provide personalized recommendations to users for specific items. Most of these systems always recommend the most relevant items of users or items. Traditionally, the evaluation of recommender system quality has focused on the various predictive accuracy metrics of these. However, recommender system must be not only accurate but also useful to users. User satisfaction with recommender systems as an evaluation criterion of recommender system is related not only to how accurately the system recommends but also to how much it supports the user's decision making. In particular, highly serendipitous recommendation would help a user to find a surprising and interesting item. Serendipity in this study is defined as a measure of the extent to which the recommended items are both attractive and surprising to the users. Therefore, this paper proposes an application of serendipity measure to recommender systems to evaluate the performance of recommender systems in terms of recommendation system quality. In this study we define relevant or attractive unexpectedness as serendipity measure for assessing recommendation systems. That is, serendipity measure is evaluated as the measure indicating how the recommender system can find unexpected and useful items for users. Our experimental results show that highly serendipitous recommendation such as item-based collaborative filtering method has better performance than the other recommendations, i.e. user-based collaborative filtering method in terms of recommendation system quality.

• Journal of The Korean Ophthalmological Society
• /
• v.59 no.12
• /
• pp.1173-1180
• /
• 2018

Purpose: We evaluated the postoperative accuracy of intraocular lens power prediction for patients undergoing phacotrabeculectomy and identified preoperative factors associated with refractive outcome in those with primary open-angle glaucoma (POAG). Methods: We retrospectively reviewed the medical records of 27 patients who underwent phacotrabeculectomy to treat POAG. We recorded all discrepancies between predicted and actual postoperative refractions. We compared the data to those of an age- and sex-matched control group that underwent uncomplicated cataract surgery during the same time period. Preoperative factors associated with the mean absolute error (MAE) were identified via multivariate regression analyses. Results: The mean refractive error of the 27 eyes that underwent phacotrabeculectomy was comparable to that of the 27 eyes treated via phacoemulsification (+0.02 vs. -0.01 D, p = 0.802). The phacotrabeculectomy group exhibited a significantly higher MAE (0.65 vs. 0.35 D, p = 0.035) and more postoperative astigmatism (-1.07 vs. -0.66 D, p = 0.020) than the phacoemulsification group. The preoperative anterior chamber depth (ACD) and the changes in the postoperative intraocular pressure (IOP) were significantly associated with a greater MAE after phacotrabeculectomy. Conclusions: POAG treatment via combined phacoemulsification/trabeculectomy was associated with greater error in terms of final refraction prediction, and more postoperative astigmatism. As both a shallow preoperative ACD and a greater postoperative change in IOP appear to increase the predictive error, these two factors should be considered when planning phacotrabeculectomy.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.4
• /
• pp.228-234
• /
• 2021

Real estate market participants need to have a sense of predicting real estate prices in decision-making. Commonly used methodologies, such as regression analysis, ARIMA, and VAR, have limitations in predicting the value of an asset, which fluctuates due to unknown variables. Therefore, to mitigate the limitations, an artificial neural was is used to predict the price trend of apartments in Seoul, the hottest real estate market in South Korea. For artificial neural network learning, the learning model is designed with 12 variables, which are divided into macro and micro factors. The study was conducted in three ways: (Ed note: What is the difference between case 1 and 2? Is case 1 micro factors?)CASE1 with macro factors, CASE2 with macro factors, and CASE3 with the combination of both factors. As a result, CASE1 and CASE2 show 87.5% predictive accuracy during the two-year experiment, and CASE3 shows 95.8%. This study defines various factors affecting apartment prices in macro and microscopic terms. The study also proposes an artificial network technique in predicting the price trend of apartments and analyzes its effectiveness. Therefore, it is expected that the recently developed learning technique can be applied to the real estate industry, enabling more efficient decision-making by market participants.

• Korean Journal of Otorhinolaryngology-Head and Neck Surgery
• /
• v.61 no.11
• /
• pp.600-604
• /
• 2018

Background and Objectives This study aimed to identify a reliable preoperative predictive factor for the development of thyroid cancer in patients with atypia of undetermined significance (AUS) identified by fine needle aspiration biopsy (FNAB). Subjects and Method This was a retrospective cohort study. Two hundred and ninety-nine patients diagnosed with AUS by preoperative FNAB who underwent curative thyroid surgery at our institution between September 2005 and February 2014 were analyzed. Clinical, radiological and molecular features were investigated as preoperative predictors for postoperative permanent malignant pathology. Results The final pathologic results revealed 36 benign tumors including nodular hyperplasia, follicular adenoma, adenomatous goiter, nontoxic goiter, and lymphocytic thyroiditis, as well as 263 malignant tumors including 1 follicular carcinoma and 1 invasive follicular carcinoma; the rest were papillary thyroid carcinomas. The malignancy rate was 87.9%. The following were identified as risk factors for malignancy by univariate analysis: $BRAF^{V600E}$ gene mutation, specific ultrasonographic findings including smaller nodule size, low echogenicity of the nodule, and irregular or spiculated margin (p<0.05). Multivariate analysis revealed that only $BRAF^{V600E}$ mutation was a statistically significant risk factor for malignancy (p<0.05). When $BRAF^{V600E}$ mutation was positive, 98.5% of enrolled patients developed malignant tumors. In addition, the diagnostic rate of malignancy in these cases was approximately 16-fold higher than BRAF-negative cases. Conclusion Patients with AUS thyroid nodules should undergo $BRAF^{V600E}$ gene mutation analysis to improve diagnostic accuracy and if the mutation is confirmed, surgery is recommended due to the high risk of malignancy.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.155-170
• /
• 2018

Predicting a company's financial bankruptcy is traditionally one of the most crucial forecasting problems in business analytics. In previous studies, prediction models have been proposed by applying or combining statistical and machine learning-based techniques. In this paper, we propose a novel intelligent prediction model based on the simulated annealing which is one of the well-known optimization techniques. The simulated annealing is known to have comparable optimization performance to the genetic algorithms. Nevertheless, since there has been little research on the prediction and classification of business decision-making problems using the simulated annealing, it is meaningful to confirm the usefulness of the proposed model in business analytics. In this study, we use the combined model of simulated annealing and machine learning to select the input features of the bankruptcy prediction model. Typical types of combining optimization and machine learning techniques are feature selection, feature weighting, and instance selection. This study proposes a combining model for feature selection, which has been studied the most. In order to confirm the superiority of the proposed model in this study, we apply the real-world financial data of the Korean companies and analyze the results. The results show that the predictive accuracy of the proposed model is better than that of the naïve model. Notably, the performance is significantly improved as compared with the traditional decision tree, random forests, artificial neural network, SVM, and logistic regression analysis.

• Investigative Magnetic Resonance Imaging
• /
• v.25 no.3
• /
• pp.164-171
• /
• 2021

Purpose: Mild cognitive impairment (MCI) is a prodromal stage of Alzheimer's disease (AD). Brain atrophy in this disease spectrum begins in the medial temporal lobe structure, which can be recognized by magnetic resonance imaging. To overcome the unsatisfactory inter-observer reliability of visual evaluation, quantitative brain volumetry has been developed and widely investigated for the diagnosis of MCI and AD. The aim of this study was to assess the prediction accuracy of quantitative brain volumetry using a fully automated segmentation software package, NeuroQuant^®, for the diagnosis of MCI. Materials and Methods: A total of 418 subjects from the Korean Brain Aging Study for Early Diagnosis and Prediction of Alzheimer's Disease cohort were included in our study. Each participant was allocated to either a cognitively normal old group (n = 285) or an MCI group (n = 133). Brain volumetric data were obtained from T1-weighted images using the NeuroQuant software package. Logistic regression and receiver operating characteristic (ROC) curve analyses were performed to investigate relevant brain regions and their prediction accuracies. Results: Multivariate logistic regression analysis revealed that normative percentiles of the hippocampus (P < 0.001), amygdala (P = 0.003), frontal lobe (P = 0.049), medial parietal lobe (P = 0.023), and third ventricle (P = 0.012) were independent predictive factors for MCI. In ROC analysis, normative percentiles of the hippocampus and amygdala showed fair accuracies in the diagnosis of MCI (area under the curve: 0.739 and 0.727, respectively). Conclusion: Normative percentiles of the hippocampus and amygdala provided by the fully automated segmentation software could be used for screening MCI with a reasonable post-processing time. This information might help us interpret structural MRI in patients with cognitive impairment.

• Journal of the Korean Wood Science and Technology
• /
• v.49 no.3
• /
• pp.213-225
• /
• 2021

In this paper, we investigated the carbonization characteristics of lignin hydrochar prepared by hydrothermal carbonization and established a model for predicting the carbonization degree using near-infrared spectroscopy and partial least squares regression. The carbon content of the hydrothermally carbonized lignin at the temperature of 200 ℃ was higher by approximately 3 wt% than that of the untreated sample, and the carbon content tended to gradually increase as the heating time increased. Hydrothermal carbonization made lignin more carbon-intensive and more homogeneous by eliminating the microparticles. The discriminant and predictive models using near-infrared spectroscopy and partial least squares regression approppriately determined whether hydrothermal carbonization has been applied and predicted the carbon content of hydrothermal carbonized lignin with high accuracy. In this study, we confirmed that we can quickly and nondestructively predict the carbonization characteristics of lignin hydrochar manufactured by hydrothermal carbonization using a partial least squares regression model combined with near-infrared spectroscopy.

• Korean Chemical Engineering Research
• /
• v.59 no.2
• /
• pp.209-218
• /
• 2021

First principle-based modeling studies have been performed to improve the heat exchange efficiency of ORV and optimize operation, but the heat transfer coefficient of ORV is an irregular system according to time and location, and it undergoes a complex modeling process. In this study, FNN, LSTM, and AutoML-based modeling were performed to confirm the effectiveness of data-based modeling for complex systems. The prediction accuracy indicated high performance in the order of LSTM > AutoML > FNN in MSE. The performance of AutoML, an automatic design method for machine learning models, was superior to developed FNN, and the total time required for model development was 1/15 compared to LSTM, showing the possibility of using AutoML. The prediction of NG and seawater discharged temperatures using LSTM and AutoML showed an error of less than 0.5K. Using the predictive model, real-time optimization of the amount of LNG vaporized that can be processed using ORV in winter is performed, confirming that up to 23.5% of LNG can be additionally processed, and an ORV optimal operation guideline based on the developed dynamic prediction model was presented.

• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.23-35
• /
• 2021

In the era of the 4th industrial revolution, smart factories have received great attention, where production and manufacturing technology and ICT converge. With the development of IoT technology and big data, automation of production systems has become possible. In the advanced manufacturing industry, production systems are subject to unscheduled performance degradation and downtime, and there is a demand to reduce safety risks by detecting and reparing potential errors as soon as possible. This study designs a model based on supervised and unsupervised learning for detecting anomalies. The accuracy of XGBoost, LightGBM, and CNN models was compared as a supervised learning analysis method. Through the evaluation index based on the confusion matrix, it was confirmed that LightGBM is most predictive (97%). In addition, as an unsupervised learning analysis method, MD, AE, and LSTM-AE models were constructed. Comparing three unsupervised learning analysis methods, the LSTM-AE model detected 75% of anomalies and showed the best performance. This study aims to contribute to the advancement of the smart factory by combining supervised and unsupervised learning techniques to accurately diagnose equipment failures and predict when abnormal situations occur, thereby laying the foundation for preemptive responses to abnormal situations. do.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.10
• /
• pp.397-402
• /
• 2019

Accurately predicting cancer prognosis to provide appropriate treatment strategies for patients is one of the critical challenges in bioinformatics. Many researches have suggested machine learning models to predict patients' outcomes based on their gene expression data. Gene expression data is high-dimensional numerical data containing about 17,000 genes, so traditional researches used feature selection or dimensionality reduction approaches to elevate the performance of prognostic prediction models. These approaches, however, have an issue of making it difficult for the predictive models to grasp any biological interaction between the selected genes because feature selection and model training stages are performed independently. In this paper, we propose a novel two-dimensional image formatting approach for gene expression data to achieve feature selection and prognostic prediction effectively. Node2Vec is exploited to integrate biological interaction network and gene expression data and a convolutional neural network learns the integrated two-dimensional gene expression image data and predicts cancer prognosis. We evaluated our proposed model through double cross-validation and confirmed superior prognostic prediction accuracy to traditional machine learning models based on raw gene expression data. As our proposed approach is able to improve prediction models without loss of information caused by feature selection steps, we expect this will contribute to development of personalized medicine.