• Information Systems Review
• /
• v.24 no.2
• /
• pp.67-88
• /
• 2022

This study proposed a research model that can explain the usage intentions of users and non-users by considering the performance aspects of personal mobility and external environmental factors based on the SOR (Stimulus-Organism-Response) model, A survey was conducted targeting domestic users and non-users, and research models and hypotheses were verified through Partial Least Square (PLS) and Artificial Neural Network (ANN). As a result of the analysis, it was confirmed that the users' perceived satisfaction and perceived trust had a positive effect on their intention to use, and that perceived risk and environmental value had a significant relationship with perceived satisfaction and perceived trust. For non-users, it was found that there was a positive correlation between perceived satisfaction and intention to use, and it was verified that perceived risk and environmental value, like users, were significant antecedents of perceived satisfaction and perceived trust. Among the remaining variables, the perceived mobility of users and the perceived ease of use of non-users were respectively presented as important influencing factors on perceived satisfaction.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.6
• /
• pp.284-290
• /
• 2024

Speech emotion recognition (SER) is a technique that is used to analyze the speaker's voice patterns, including vibration, intensity, and tone, to determine their emotional state. There has been an increase in interest in artificial intelligence (AI) techniques, which are now widely used in medicine, education, industry, and the military. Nevertheless, existing researchers have attained impressive results by utilizing acted-out speech from skilled actors in a controlled environment for various scenarios. In particular, there is a mismatch between acted and spontaneous speech since acted speech includes more explicit emotional expressions than spontaneous speech. For this reason, spontaneous speech-emotion recognition remains a challenging task. This paper aims to conduct emotion recognition and improve performance using spontaneous speech data. To this end, we implement deep learning-based speech emotion recognition using the VGG (Visual Geometry Group) after converting 1-dimensional audio signals into a 2-dimensional spectrogram image. The experimental evaluations are performed on the Korean spontaneous emotional speech database from AI-Hub, consisting of 7 emotions, i.e., joy, love, anger, fear, sadness, surprise, and neutral. As a result, we achieved an average accuracy of 83.5% and 73.0% for adults and young people using a time-frequency 2-dimension spectrogram, respectively. In conclusion, our findings demonstrated that the suggested framework outperformed current state-of-the-art techniques for spontaneous speech and showed a promising performance despite the difficulty in quantifying spontaneous speech emotional expression.

• Korean Journal of Radiology
• /
• v.22 no.2
• /
• pp.168-178
• /
• 2021

Objective: To provide an automatic method for segmentation and diameter measurement of type B aortic dissection (TBAD). Materials and Methods: Aortic computed tomography angiographic images from 139 patients with TBAD were consecutively collected. We implemented a deep learning method based on a three-dimensional (3D) deep convolutional neural (CNN) network, which realizes automatic segmentation and measurement of the entire aorta (EA), true lumen (TL), and false lumen (FL). The accuracy, stability, and measurement time were compared between deep learning and manual methods. The intra- and inter-observer reproducibility of the manual method was also evaluated. Results: The mean dice coefficient scores were 0.958, 0.961, and 0.932 for EA, TL, and FL, respectively. There was a linear relationship between the reference standard and measurement by the manual and deep learning method (r = 0.964 and 0.991, respectively). The average measurement error of the deep learning method was less than that of the manual method (EA, 1.64% vs. 4.13%; TL, 2.46% vs. 11.67%; FL, 2.50% vs. 8.02%). Bland-Altman plots revealed that the deviations of the diameters between the deep learning method and the reference standard were -0.042 mm (-3.412 to 3.330 mm), -0.376 mm (-3.328 to 2.577 mm), and 0.026 mm (-3.040 to 3.092 mm) for EA, TL, and FL, respectively. For the manual method, the corresponding deviations were -0.166 mm (-1.419 to 1.086 mm), -0.050 mm (-0.970 to 1.070 mm), and -0.085 mm (-1.010 to 0.084 mm). Intra- and inter-observer differences were found in measurements with the manual method, but not with the deep learning method. The measurement time with the deep learning method was markedly shorter than with the manual method (21.7 ± 1.1 vs. 82.5 ± 16.1 minutes, p < 0.001). Conclusion: The performance of efficient segmentation and diameter measurement of TBADs based on the 3D deep CNN was both accurate and stable. This method is promising for evaluating aortic morphology automatically and alleviating the workload of radiologists in the near future.

• Korean Journal of Radiology
• /
• v.22 no.3
• /
• pp.344-353
• /
• 2021

Objective: The mitotic count of gastrointestinal stromal tumors (GIST) is closely associated with the risk of planting and metastasis. The purpose of this study was to develop a predictive model for the mitotic index of local primary GIST, based on deep learning algorithm. Materials and Methods: Abdominal contrast-enhanced CT images of 148 pathologically confirmed GIST cases were retrospectively collected for the development of a deep learning classification algorithm. The areas of GIST masses on the CT images were retrospectively labelled by an experienced radiologist. The postoperative pathological mitotic count was considered as the gold standard (high mitotic count, > 5/50 high-power fields [HPFs]; low mitotic count, ≤ 5/50 HPFs). A binary classification model was trained on the basis of the VGG16 convolutional neural network, using the CT images with the training set (n = 108), validation set (n = 20), and the test set (n = 20). The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated at both, the image level and the patient level. The receiver operating characteristic curves were generated on the basis of the model prediction results and the area under curves (AUCs) were calculated. The risk categories of the tumors were predicted according to the Armed Forces Institute of Pathology criteria. Results: At the image level, the classification prediction results of the mitotic counts in the test cohort were as follows: sensitivity 85.7% (95% confidence interval [CI]: 0.834-0.877), specificity 67.5% (95% CI: 0.636-0.712), PPV 82.1% (95% CI: 0.797-0.843), NPV 73.0% (95% CI: 0.691-0.766), and AUC 0.771 (95% CI: 0.750-0.791). At the patient level, the classification prediction results in the test cohort were as follows: sensitivity 90.0% (95% CI: 0.541-0.995), specificity 70.0% (95% CI: 0.354-0.919), PPV 75.0% (95% CI: 0.428-0.933), NPV 87.5% (95% CI: 0.467-0.993), and AUC 0.800 (95% CI: 0.563-0.943). Conclusion: We developed and preliminarily verified the GIST mitotic count binary prediction model, based on the VGG convolutional neural network. The model displayed a good predictive performance.

• The Korean Journal of Applied Statistics
• /
• v.37 no.1
• /
• pp.73-86
• /
• 2024

A radial chart of Excel is very useful graphical method in delivering information for numerical data. However, it is not easy to discriminate or classify many individuals. In this case, after shaping each individual of a radial chart, we need to apply shape analysis. For a radial chart, since landmarks for shaping are formed as many as the number of variables representing the characteristics of the object, we consider a shape that connects them to a line. If the shape becomes complicated due to the large number of variables, it is difficult to easily grasp even if visualized using a radial chart. Principal component analysis (PCA) is performed on variables to create a visually effective shape. The classification table and classification rate are checked by applying the techniques of traditional discriminant analysis, support vector machine (SVM), and artificial neural network (ANN), before and after principal component analysis. In addition, the difference in discrimination between the two coordinates of generalized procrustes analysis (GPA) coordinates and Bookstein coordinates is compared. Bookstein coordinates are obtained by converting the position, rotation, and scale of the shape around the base landmarks, and show higher rate than GPA coordinates for the classification rate.

• Information Systems Review
• /
• v.25 no.1
• /
• pp.27-46
• /
• 2023

Research on restaurant recommender systems has been proposed due to the development of the food service industry and the increasing demand for restaurants. Existing restaurant recommendation studies extracted consumer preference information through quantitative information or online review sensitivity analysis, but there is a limitation that it cannot reflect consumer semantic preference information. In addition, there is a lack of recommendation research that reflects the detailed attributes of restaurants. To solve this problem, this study proposed a model that can learn the interaction between consumer preferences and restaurant attributes by applying deep learning techniques. First, the convolutional neural network was applied to online reviews to extract semantic preference information from consumers, and embedded techniques were applied to restaurant information to extract detailed attributes of restaurants. Finally, the interaction between consumer preference and restaurant attributes was learned through the element-wise products to predict the consumer preference rating. Experiments using an online review of Yelp.com to evaluate the performance of the proposed model in this study confirmed that the proposed model in this study showed excellent recommendation performance. By proposing a customized restaurant recommendation system using big data from the restaurant industry, this study expects to provide various academic and practical implications.

• Information Systems Review
• /
• v.25 no.1
• /
• pp.129-143
• /
• 2023

In the era of big data, the field of artificial intelligence is showing remarkable growth, and in particular, the image classification learning methods by deep learning are becoming an important area. Various studies have been actively conducted to further improve the performance of CNNs, which have been widely used in image classification, among which a representative method is the Convolutional Recurrent Neural Network (CRNN) algorithm. The CRNN algorithm consists of a combination of CNN for image classification and RNNs for recognizing time series elements. However, since the inputs used in the RNN area of CRNN are the flatten values extracted by applying the convolution and pooling technique to the image, pixel values in the same phase in the image appear in different order. And this makes it difficult to properly learn the sequence of arrangements in the image intended by the RNN. Therefore, this study aims to improve image classification performance by proposing a novel hybrid method of CNN and RNN applying the concepts of encoder and decoder. In this study, the effectiveness of the new hybrid method was verified through various experiments. This study has academic implications in that it broadens the applicability of encoder and decoder concepts, and the proposed method has advantages in terms of model learning time and infrastructure construction costs as it does not significantly increase complexity compared to conventional hybrid methods. In addition, this study has practical implications in that it presents the possibility of improving the quality of services provided in various fields that require accurate image classification.

• Korean Journal of Radiology
• /
• v.24 no.11
• /
• pp.1151-1163
• /
• 2023

Objective: To develop a deep-learning-based bone age prediction model optimized for Korean children and adolescents and evaluate its feasibility by comparing it with a Greulich-Pyle-based deep-learning model. Materials and Methods: A convolutional neural network was trained to predict age according to the bone development shown on a hand radiograph (bone age) using 21036 hand radiographs of Korean children and adolescents without known bone development-affecting diseases/conditions obtained between 1998 and 2019 (median age [interquartile range {IQR}], 9 [7-12] years; male:female, 11794:9242) and their chronological ages as labels (Korean model). We constructed 2 separate external datasets consisting of Korean children and adolescents with healthy bone development (Institution 1: n = 343; median age [IQR], 10 [4-15] years; male: female, 183:160; Institution 2: n = 321; median age [IQR], 9 [5-14] years; male: female, 164:157) to test the model performance. The mean absolute error (MAE), root mean square error (RMSE), and proportions of bone age predictions within 6, 12, 18, and 24 months of the reference age (chronological age) were compared between the Korean model and a commercial model (VUNO Med-BoneAge version 1.1; VUNO) trained with Greulich-Pyle-based age as the label (GP-based model). Results: Compared with the GP-based model, the Korean model showed a lower RMSE (11.2 vs. 13.8 months; P = 0.004) and MAE (8.2 vs. 10.5 months; P = 0.002), a higher proportion of bone age predictions within 18 months of chronological age (88.3% vs. 82.2%; P = 0.031) for Institution 1, and a lower MAE (9.5 vs. 11.0 months; P = 0.022) and higher proportion of bone age predictions within 6 months (44.5% vs. 36.4%; P = 0.044) for Institution 2. Conclusion: The Korean model trained using the chronological ages of Korean children and adolescents without known bone development-affecting diseases/conditions as labels performed better in bone age assessment than the GP-based model in the Korean pediatric population. Further validation is required to confirm its accuracy.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.3
• /
• pp.461-466
• /
• 2024

Korean local governments operates the participatory budgeting system autonomously. This study is to classify these entities into clusters. Among the diverse machine learning methodologies(Neural Network, Rule Induction(CN2), KNN, Decision Tree, Random Forest, Gradient Boosting, SVM, Naïve Bayes), the Support Vector Machine technique emerged as the most efficacious in the analysis of 2022 Korean municipalities data. The first cluster C1 is characterized by minimal committee activity but a substantial allocation of participatory budgeting; another cluster C3 comprises cities that exhibit a passive stance. The majority of cities falls into the final cluster C2 which is noted for its proactive engagement in. Overall, most Korean local government operates the participatory busgeting system in good shape. Only a small number of cities is less active in this system. We anticipate that analyzing time-series data from the past decade in follow-up studies will further enhance the reliability of classifying local government types regarding participatory budgeting.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.4
• /
• pp.236-244
• /
• 2024

A representative problem in domestic chestnut industry is the high loss of flesh due to excessive knife peeling in order to increase the peeling rate, resulting in a decrease in production efficiency. In this study, a prediction model for weight loss rate of chestnut by stage of knife peeling process was developed as undergarment study to optimize conditions of the machine. 51 control conditions of the two-stage blade peeler used in the experiment were derived and repeated three times to obtain a total of 153 data. Machine learning(ML) models including artificial neural network (ANN) and random forest (RF) were implemented to predict the weight loss rate by chestnut peel stage (after 1st peeling, 2nd peeling, and after final discharge). The performance of the models were evaluated by calculating the values of coefficient of determination (R), normalized root mean square error (nRMSE), and mean absolute error (MAE). After all peeling stages, RF model have better prediction accuracy with higher R values and low prediction error with lower nRMSE and MAE values, compared to ANN model. The final selected RF prediction model showed excellent performance with insignificant error between the experimental and predicted values. As a result, the proposed model can be useful to set optimum condition of knife peeling for the purpose of minimizing the weight loss of domestic chestnut flesh with maximizing peeling rate.