• Journal of The Korean Society of Emergency Medicine
• /
• v.29 no.5
• /
• pp.455-464
• /
• 2018

Objective: Machine learning is not yet widely used in the medical field. Therefore, this study was conducted to compare the performance of preexisting severity prediction models and machine learning based models (random forest [RF], gradient boosting [GB]) for mortality prediction in pneumonia patients. Methods: We retrospectively collected data from patients who visited the emergency department of a tertiary training hospital in Seoul, Korea from January to March of 2015. The Pneumonia Severity Index (PSI) and Sequential Organ Failure Assessment (SOFA) scores were calculated for both groups and the area under the curve (AUC) for mortality prediction was computed. For the RF and GB models, data were divided into a test set and a validation set by the random split method. The training set was learned in RF and GB models and the AUC was obtained from the validation set. The mean AUC was compared with the other two AUCs. Results: Of the 536 investigated patients, 395 were enrolled and 41 of them died. The AUC values of PSI and SOFA scores were 0.799 (0.737-0.862) and 0.865 (0.811-0.918), respectively. The mean AUC values obtained by the RF and GB models were 0.928 (0.899-0.957) and 0.919 (0.886-0.952), respectively. There were significant differences between preexisting severity prediction models and machine learning based models (P<0.001). Conclusion: Classification through machine learning may help predict the mortality of pneumonia patients visiting the emergency department.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.12
• /
• pp.2314-2318
• /
• 2010

For human-robot interaction, a robot should recognize the meaning of human behavior. In the case of static behavior such as face expression and sign language, the information contained in a single image is sufficient to deliver the meaning to the robot. In the case of dynamic behavior such as gestures, however, the information of sequential images is required. This paper proposes behavior classification by using fuzzy classifier to deliver the meaning of dynamic behavior to the robot. The proposed method extracts feature points from input images by a skeleton model, generates a vector space from a differential image of the extracted feature points, and uses this information as the learning data for fuzzy classifier. Finally, we show the effectiveness and the feasibility of the proposed method through experiments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.10
• /
• pp.1275-1281
• /
• 2019

The automatic modulation recognition of a radio signal is a major task of an intelligent receiver, with various civilian and military applications. In this paper, we propose a method to recognize the modulation of radio signals in wireless communication based on the deep neural network. We classify the modulation pattern of radio signal by using the LSTM model, which can catch the long-term pattern for the sequential data as the input data of the deep neural network. The amplitude and phase of the modulated signal, the in-phase carrier, and the quadrature-phase carrier are used as input data in the LSTM model. In order to verify the performance of the proposed learning method, we use a large dataset for training and test, including the ten types of modulation signal under various signal-to-noise ratios.

• The KIPS Transactions:PartB
• /
• v.11B no.4
• /
• pp.449-456
• /
• 2004

This paper proposes a novel recognition model, a recurrent fuzzy associative memory(RFAM), for recognizing time-series patterns contained an ambiguity. RFAM is basically extended from FAM(Fuzzy Associative memory) by adding a recurrent layer which can be used to deal with sequential input patterns and to characterize their temporal relations. RFAM provides a Hebbian-style learning method which establishes the degree of association between input and output. The error back-propagation algorithm is also adopted to train the weights of the recurrent layer of RFAM. To evaluate the performance of the proposed model, we applied it to a word boundary detection problem of speech signal.

• Journal of The Korean Association of Information Education
• /
• v.1 no.1
• /
• pp.82-91
• /
• 1997

The purpose of thesis is to design and implement an efficient Internet-Based courseware which facilitates the problem solving learning. This courseware was developed in order to provide important foundations of learning in open-education environment using WWW. The targeted level is elementary students, To do this, the definition of problem solving, its processes, and advantages or pitfalls of computer-based problem solving learning were examined, with the advantage of using WWW as an educational tool. The theme of implemented courseware was selected from SATIS which is relevant for the problem solving learning. The courseware has three main parts; learning activity module, teaching activity module, and learning tool module. The learning activity module controls courseware flows and was implemented in accordance with the problem-based teaming processes. It: can be proceeded either sequential way or random access by setting linker. The advantage of random accessing method is that it may facilitate student learning because each student can regulate their learning processes which correspond to their own experiences. The teaching activity module provides for teachers useful informations for helping student's learning and it also can be used as an assessment tool for student's achievements, The learning: tool module consists of conversational note, e-mail address, help, and search tool. It is linked with learning activity module and teaching activity module so that teachers and students can actively participate in teaching-learning processes.

• Computers and Concrete
• /
• v.31 no.5
• /
• pp.405-417
• /
• 2023

The submerged floating tunnel (SFT) is tethered by mooring lines anchored to the seabed, therefore, the structural integrity of the anchor should be sensitively managed. Despite their importance, reaction forces cannot be simply measured by attaching sensors or load cells because of the structural and environmental characteristics of the submerged structure. Therefore, we propose an effective method for estimating the reaction forces at the seabed anchor of a submerged floating tunnel using a structural pattern model. First, a structural pattern model is established to use the correlation between tunnel motion and anchor reactions via a deep learning algorithm. Once the pattern model is established, it is directly used to estimate the reaction forces by inputting the tunnel motion data, which can be directly measured inside the tunnel. Because the sequential characteristics of responses in the time domain should be considered, the long short-term memory (LSTM) algorithm is mainly used to recognize structural behavioral patterns. Using hydrodynamics-based simulations, big data on the structural behavior of the SFT under various waves were generated, and the prepared datasets were used to validate the proposed method. The simulation-based validation results clearly show that the proposed method can precisely estimate time-series reactions using only acceleration data. In addition to real-time structural health monitoring, the proposed method can be useful for forensics when an unexpected accident or failure is related to the seabed anchors of the SFT.

• International Journal of Computer Science & Network Security
• /
• v.21 no.12
• /
• pp.165-174
• /
• 2021

This study aimed to ascertain whether electronic courses at the deanship of electronic learning and distance education at Umm Al-Qura University meet the quality standards developed by the Quality Matters (QM) organization. This endeavor adopted a mixed method of an explanatory sequential research design for an in-depth understanding of the topic under scrutiny. The sample of the study consisted of ten courses designed at the deanship and reviewed using an evaluation form. The results showed that the courses in focus did not meet the criteria of QM. Based on this finding, a semi-structured interview was designed to collect relevant data from the syllabus designers at the deanship. The interviews yielded information on the difficulties the course designers faced when designing QM-criteria-based courses. The results obtained from the interviews showed that the designers experienced administrative, technical, and faculty-member-related challenges that, when producing online courses, intercepted their way to achieving the QM standards. The study closed with some recommendations, the most important of which is a call for re-developing online courses in alignment with the well-recognized QM standards.

• Journal of Navigation and Port Research
• /
• v.46 no.4
• /
• pp.367-374
• /
• 2022

The purpose of this study was to propose a deep learning algorithm that applies to the fault diagnosis of fuel pumps and purifiers of autonomous ships. A deep learning algorithm reflecting the time dependence of the measured signal was configured, and the failure pattern was trained using the vibration signal, measured in the equipment's regular operation and failure state. Considering the sequential time-dependence of deterioration implied in the vibration signal, this study adopts Conv1D with sliding window computation for fault detection. The time dependence was also reflected, by transferring the measured signal from two-dimensional to three-dimensional. Additionally, the optimal values of the hyper-parameters of the Conv1D model were determined, using the grid search technique. Finally, the results show that the proposed data preprocessing method as well as the Conv1D model, can reflect the sequential dependency between the fault and its effect on the measured signal, and appropriately perform anomaly as well as failure detection, of the equipment chosen for application.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.10
• /
• pp.373-380
• /
• 2022

This paper presents a deep learning based group synchronization that supports networked immersive interactions between remote users. The goal of group synchronization is to enable all participants to synchronously interact with others for increasing user presence Most previous methods focus on NTP-based clock synchronization to enhance time accuracy. Moving average filters are used to control media playout time on the synchronization server. As an example, the exponentially weighted moving average(EWMA) would be able to track and estimate accurate playout time if the changes in input data are not significant. However it needs more time to be stable for any given change over time due to codec and system loads or fluctuations in network status. To tackle this problem, this work proposes the Deep Group Synchronization(DeepGroupSync), a group synchronization based on deep learning that models important features from the data. This model consists of two Gated Recurrent Unit(GRU) layers and one fully-connected layer, which predicts an optimal playout time by utilizing the sequential playout delays. The experiments are conducted with an existing method that uses the EWMA and the proposed method that uses the DeepGroupSync. The results show that the proposed method are more robust against unpredictable or rapid network condition changes than the existing method.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.6
• /
• pp.44-55
• /
• 2009

Diagnosis of diseases using gene expression data obtained from microarray chip is an active research area recently. It has been done by general machine learning algorithms, because it is difficult to analyze directly. However, recent research results about the analysis based on the interaction between genes is essential for the gene expression analysis, which means the analysis using the traditional machine learning algorithms has limitations. In this paper, we classify the gene expression data using the hyper-network model that considers the higher-order correlations between the features, and then compares the classification accuracies. And also, we present the new hypo-network model that improve the disadvantage of existing model, and compare the processing performances of the existing hypo-network model based on general sequential processor and the improved hypo-network model implemented on parallel processors. In the experimental results, we show that the performance of our model shows improved and competitive classification performance than traditional machine learning methods, as well as, the existing hypo-network model. We show that the performance is maximized when the hypernetwork model is implemented on our parallel processors.