KJC Korea
Journal Central

In this paper, we propose a feature selection technique for multi-label classification. Many existing feature selection techniques have selected features by calculating the relation between features and labels such as a mutual information scale. However, since the mutual information measure requires a joint probability, it is difficult to calculate the joint probability from an actual premise feature set. Therefore, it has the disadvantage that only a few features can be calculated and only local optimization is possible. Away from this regional optimization problem, we propose a feature selection technique that constructs a low-rank space in the entire given feature space and selects features with sparsity. To this end, we designed a regression-based objective function using Nuclear norm, and proposed an algorithm of gradient descent method to solve the optimization problem of this objective function. Based on the results of multi-label classification experiments on four data and three multi-label classification performance, the proposed methodology showed better performance than the existing feature selection technique. In addition, it was showed by experimental results that the performance change is insensitive even to the parameter value change of the proposed objective function.

In this study, we propose a part of the CDSS(Clinical Decision Support System) study, a system that can classify chemotherapy, one of the treatment methods for colorectal cancer patients. In the treatment of colorectal cancer, the selection of chemotherapy according to the patient's condition is very important because it is directly related to the patient's survival period. Therefore, in this study, chemotherapy was classified using a machine learning algorithm by creating a baseline model, a pathological model, and a combined model using both characteristics of the patient using the individual and pathological characteristics of colorectal cancer patients. As a result of comparing the prediction accuracy with Top-n Accuracy, ROC curve, and AUC, it was found that the combined model showed the best prediction accuracy, and that the LGBM algorithm had the best performance. In this study, a chemotherapy classification model suitable for the patient's condition was constructed by classifying the model by patient characteristics using a machine learning algorithm. Based on the results of this study in future studies, it will be helpful for CDSS research by creating a better performing chemotherapy classification model.

In this paper, we propose a method for detecting characters in images and detecting facial regions, which consists of two tasks. First, we separate two different characters to detect the face position of the characters in the frame. For fast detection, we use You Only Look Once (YOLO), which finds faces in the image in real time, to extract the location of the face and mark them as object detection boxes. Second, we present three image processing methods to detect accurate face area based on object detection boxes. Each method uses HSV values extracted from the region estimated by the detection figure to detect the face region of the characters, and changes the size and shape of the detection figure to compare the accuracy of each method. Each face detection method is compared and analyzed with comparative data and image processing data for reliability verification. As a result, we achieved the highest accuracy of 87% when using the split rectangular method among circular, rectangular, and split rectangular methods.

In this paper, we classify ECG signal data for mobile devices using deep learning models. To classify abnormal heartbeats with high accuracy, three factors of the deep learning model are selected, and the classification accuracy is compared according to the changes in the conditions of the factors. We apply a CNN model that can self-extract features of ECG data and compare the performance of a total of 48 combinations by combining conditions of the depth of model, optimization method, and activation functions that compose the model. Deriving the combination of conditions with the highest accuracy, we obtained the highest classification accuracy of 97.88% when we applied 19 convolutional layers, an optimization method SGD, and an activation function Mish. In this experiment, we confirmed the suitability of feature extraction and abnormal beat detection of 1-channel ECG signals using CNN.

Automatic classification of brain MRI images play an important role in early diagnosis of brain tumors. In this work, we present a deep learning-based brain tumor classification model in MRI images using ensemble of deep features. In our proposed framework, three different deep features from brain MR image are extracted using three different pre-trained models. After that, the extracted deep features are fed to the classification module. In the classification module, the three different deep features are first fed into the fully-connected layers individually to reduce the dimension of the features. After that, the output features from the fully-connected layers are concatenated and fed into the fully-connected layer to predict the final output. To evaluate our proposed model, we use openly accessible brain MRI dataset from web. Experimental results show that our proposed model outperforms other machine learning-based models.

Information obtained through various sensors embedded in a smartphone can be used to identify and analyze user’s movements and situations. In this paper, we propose two rule-based motion detection systems that can detect three alphabet motions, ‘I’, ‘S’, and ‘Z’ by analyzing data obtained by the acceleration and gyroscope sensors in a smartphone. First of all, the characteristics of acceleration and angular velocity for each motion are analyzed. Based on the analysis, two rule-based systems are proposed and implemented as an android application and it is used to verify the detection performance for each motion. Two rule-based systems show high recognition rate over 90% for each motion and the rule-based system using ensemble shows better performance than another one.

In this paper, we propose and test the efficacy of an easy-to-use user location certification system for public places that relies on frequencies outside the audible range for humans. The inaudible frequencies come in signal frequency between 18–20 kHz and are generated by general audio speaker. After an individual’s smart device detects the signal frequency, it sends the frequency value, user’s personal ID, and user’s location to a system server that certifies the user’s visit location currently. The system server then saves a user visit record and categorizes it by individual. To show the usefulness of this proposed system, we developed a user visit certification application for smart devices linked to a system server. We then conducted a user visit certification experiment using the proposed system, with the result showing 99.6% accuracy. For a comparison, we then held a user visit certification experiment using a QR code, which confirmed that our proposed system performs better than QR code location certification. This proposed system can thus provide restaurants and other facilities reliable user contact tracing and electronic visitor access lists in the age of COVID-19.

The purpose of this study is to cornpare the differences in clinical competence, knowledge of patient safety management and confidence of patient safety management according to the clinical practice experience of nursing students, Of the 73 nursing students who experienced clinical practice and 35 nursing students who did not experience, a total of 108 students in the third grade were analyzed, In the results of this study, clinical competence(t=.88, p=.377) knowledge of patient safety management(t=-.29, p=.773), and confidence of patient safety management(t=1.11, p=.267) the difference between was not statistically significant in the two groups. In the two groups, the score of the sub-area according to each variable is the lowest. First, the sub-area of the nursing process a lowest score in clinical competence, and the second, the sub-area of measuring knowledge about concept of near miss was the Knowledge of patient safety management. The score was the lowest in, and thirdly, the sub-area of writing an incident report when an error occurred had the lowest score in confidence of patient safety management. Therefore, in order to improve the quality of clinical competence of nursing students, it is necessary to develop a strategic educational guideline to improve the clinical practice education environment, to improve patient safety management capabilities and to cultivate correct attitudes toward patient safety management.

The purpose of the current study was to investigate the causal relationship between university students’ aggression and college life adjustment and to test whether smartphone addiction had a mediating effect between the two variables. A sample of 368 students from 5 universities in G Metropolitan City were included in the analysis and structural equation modeling (SEM) was employed to test the hypotheses. The major results were as follows. First, university students’ aggression had a significant positive effect on smartphone addiction. Second, the effect of aggression on college life adjustment was not significant. Third, university students’ smartphone addiction had a significant negative effect on college life adjustment. Fourth, university students’ aggression had a significant effect on college life adjustment through smartphone addiction. Finally, theoretical and practical implications were discussed in terms of enhancing college life adjustment.

This study explore the perceived differences of factors influencing the shared accommodation in China, and the influencing paths of consumers’ use of shared accommodation. This paper collects the questionnaire survey of the Chinese shared accommodation user and applies method of Amos V23.0. The results showed that perceived usefulness and perceived pleasure had positive effects on trust, and they also have indirect positive effects on perceived intention through trust, while perceived risk and perceived ease of use had no significant effects on trust. The conclusion is helpful to promote the long-term development of sharing accommodation companies by satisfying the needs of consumers from the point of view of consumers.

The effectiveness of informatization can vary depending on the level of operation of the information system as well as investment and installation. This study investigates and analyzes the information system operating environment and quality level of small and medium-sized manufacturing companies in Korea, and investigates how it affects the performance indicators of companies. The influence of the environmental factors operating the information system on the productivity performance and financial performance through the quality level of the information system was analyzed through the structural model. As a result of the analysis, it can be said that the higher the level of information system operating environment factors, the higher the quality level, the higher the quality level, the higher the productivity performance, and the higher the productivity performance, the higher the financial performance. It is judged that the effect of informatization depends on the operating environment and quality level after the installation of the information system.

In this paper, we an empirical study of the effects of control types on Tie strength and filed project performance of project participants in field project organization for Korean domestic construction industry. In the study, we try to tell what significant impact output control, process control and tie strength among field project participants have on field project performance and features unique to field project organization for Korean construction industry through empirical analysis. And the findings of the empirical analysis are that output control appeared to have significant impacts on tie strength among the participants and process control, and process control also appear to have significant impact on field project performance.

Different from previous studies, this study focuses on accommodation providers' personalization services and platform convenience variables, identifying how these prior factors affect perceived value and trust in accommodation services on a shared homestay platform, and how consumers' innovation plays a role in the process. Through this, we would like to identify the mechanism of interaction between accommodation service providers and consumers mediated by the shared homestay platform and present implications for a more customer-centered platform operation strategy. This study has an extended meaning for prior research, empirically confirming that the increase in personalized offline service quality of personalized hosts in shared economic models has a positive impact on perceived value and platform trust of consumers. At the same time, we confirm that under the shared economy model, consumers' innovation propensity plays an important positive role in regulating their perceived value aspects as well as their confidence in the platform.

Due to the prolonged COVID-19, distance lectures are expected to continue for a considerable period of time. Research on factors affecting distance lecture quality and learner satisfaction is essential. The purpose of this study is to examine the relationship between distance lecture quality (system quality, information quality, service quality, interaction quality), self-efficacy, and learner satisfaction, and to suggest theoretical and practical implications for the effective operation of distance lectures. A survey was conducted for university students taking distance lectures, and 197 questionnaires were used for empirical analysis. The collected data were analyzed by SPSS 25.0 and AMOS 21.0. As a result; First, distance lecture quality (system quality, information quality, service quality, interaction quality) was found to have a positive effect on self-efficacy. Second, distance lecture quality (system quality, information quality, service quality, interaction quality) was found to have a positive effect on learner satisfaction. Third, self-efficacy was found to have a positive effect on learner satisfaction. Based on the analysis results, the implications and limitations of this study are presented.

This paper applies a machine learning model to forecasting freight rates in dry bulk and tanker markets with wavelet decomposition and empirical mode decomposition because they can refect both information scattered in the time and frequency domain. The decomposition with wavelet is outperformed for the dry bulk market, and EMD is the more proper model in the tanker market. This result provides market players with a practical short-term forecasting method. This study contributes to expanding a variety of predictive methodologies for one of the highly volatile markets. Furthermore, the proposed model is expected to improve the quality of decision-making in spot freight trading, which is the most frequent transaction in the shipping industry.