• The Journal of Bigdata
• /
• v.2 no.2
• /
• pp.75-86
• /
• 2017

In this study, I propose a method to automate the method to diagnose the quality of big data. The reason for automating the quality diagnosis of Big Data is that as the Fourth Industrial Revolution becomes a issue, there is a growing demand for more volumes of data to be generated and utilized. Data is growing rapidly. However, if it takes a lot of time to diagnose the quality of the data, it can take a long time to utilize the data or the quality of the data may be lowered. If you make decisions or predictions from these low-quality data, then the results will also give you the wrong direction. To solve this problem, I have developed a model that can automate diagnosis for improving the quality of Big Data using machine learning which can quickly diagnose and improve the data. Machine learning is used to automate domain classification tasks to prevent errors that may occur during domain classification and reduce work time. Based on the results of the research, I can contribute to the improvement of data quality to utilize big data by continuing research on the importance of data conversion, learning methods for unlearned data, and development of classification models for each domain.

• Child Health Nursing Research
• /
• v.7 no.2
• /
• pp.161-178
• /
• 2001

The purpose of this study was to identify nursing interventions performed by neonatal nursing unit nurses. For data collection this study used the taxonomy of Nursing Intervention Classification(NIC : 486 nursing intervention) which was modified by McCloskey & Bulecheck(2000). The new 58 nursing interventions was translated into Korean, and then modified by pannel group, which consist of clinical experts and nursing scholars and finally the 419 nursing interventions was selected. The data were collected from 112 nurses. 168 nursing interventions were performed at least monthly by 50％ or more of the nurses. The high frequency of performed nursing interventions were Family domain. 37 nursing interventions were performed at least once a day. The nursing interventions receiving the highest item mean score were neonatal care, neonatal monitoring, photo-therapy; neonate, bottle feeding and temperature regulation. 56 nursing interventions were rarely performed by 90％ or more of the nurses. Most of them were in the behavioral domain. The rarely used interventions were urinary bladder training, art therapy, religious addiction prevention, religious ritual enhancement and bladder irrigation. Therefore, neonatal nursing units nurses used interventions in the Physiological: basic domain most often on a daily basis and the interventions in the behavioral domain least often. These findings will help in building of a standardized language for the neonatal nursing units and enhance the quality of nursing care. Further study will be needed to classify each intervention class and nursing activity and validate NIC in pediatric care unit.

• Journal of KIISE
• /
• v.43 no.6
• /
• pp.678-685
• /
• 2016

Named Entity Recognition and Classification (NERC) is a task for recognition and classification of named entities such as a person's name, location, and organization. There have been various studies carried out on Korean NERC, but they have some problems, for example lacking some features as compared with English NERC. In this paper, we propose a method that uses word embedding as features for Korean NERC. We generate a word vector using a Continuous-Bag-of-Word (CBOW) model from POS-tagged corpus, and a word cluster symbol using a K-means algorithm from a word vector. We use the word vector and word cluster symbol as word embedding features in Conditional Random Fields (CRFs). From the result of the experiment, performance improved 1.17%, 0.61% and 1.19% respectively for TV domain, Sports domain and IT domain over the baseline system. Showing better performance than other NERC systems, we demonstrate the effectiveness and efficiency of the proposed method.

• Journal of the Korea Convergence Society
• /
• v.13 no.3
• /
• pp.1-9
• /
• 2022

UML class diagrams are used to visualize the static aspects of a software system and are involved from analysis and design to documentation and testing. Software modeling using class diagrams is essential for software development, but it may be not an easy activity for inexperienced modelers. The modeling productivity could be improved with a dataset of class diagrams which are classified by domain categories. To this end, this paper provides a classification method for a dataset of class diagram images. First, real class diagrams are selected from collected images. Then, class names are extracted from the real class diagram images and the class diagram images are classified according to domain categories. The proposed classification model has achieved 100.00%, 95.59%, 97.74%, and 97.77% in precision, recall, F1-score, and accuracy, respectively. The accuracy scores for the domain categorization are distributed between 81.1% and 95.2%. Although the number of class diagram images in the experiment is not large enough, the experimental results indicate that it is worth considering the proposed approach to class diagram image classification.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.1
• /
• pp.115-126
• /
• 2023

Due to the fluctuating random and periodical nature of renewable energy generation power quality disturbances occurred more frequently in power generation transformation transmission and distribution. Various power quality disturbances may lead to equipment damage or even power outages. Therefore it is essential to detect and classify different power quality disturbances in real time automatically. The traditional PQD identification method consists of three steps: feature extraction feature selection and classification. However, the handcrafted features are imprecise in the feature selection stage, resulting in low classification accuracy. This paper proposes a deep neural architecture based on Convolution Neural Network and Long Short Term Memory combining the time and frequency domain features to recognize 16 types of Power Quality signals. The frequency-domain data were obtained from the Fast Fourier Transform which could efficiently extract the frequency-domain features. The performance in synthetic data and real 6kV power system data indicate that our proposed method generalizes well compared with other deep learning methods.

• International Journal of Computer Science & Network Security
• /
• v.23 no.3
• /
• pp.177-186
• /
• 2023

Hyperspectral imaging technology is one of the most efficient and fast-growing technologies in recent years. Hyperspectral image (HSI) comprises contiguous spectral bands for every pixel that is used to detect the object with significant accuracy and details. HSI contains high dimensionality of spectral information which is not easy to classify every pixel. To confront the problem, we propose a novel RGB channel Assimilation for classification methods. The color features are extracted by using chromaticity computation. Additionally, this work discusses the classification of hyperspectral image based on Domain Transform Interpolated Convolution Filter (DTICF) and 3D-CNN with Bi-directional-Long Short Term Memory (Bi-LSTM). There are three steps for the proposed techniques: First, HSI data is converted to RGB images with spatial features. Before using the DTICF, the RGB images of HSI and patch of the input image from raw HSI are integrated. Afterward, the pair features of spectral and spatial are excerpted using DTICF from integrated HSI. Those obtained spatial and spectral features are finally given into the designed 3D-CNN with Bi-LSTM framework. In the second step, the excerpted color features are classified by 2D-CNN. The probabilistic classification map of 3D-CNN-Bi-LSTM, and 2D-CNN are fused. In the last step, additionally, Markov Random Field (MRF) is utilized for improving the fused probabilistic classification map efficiently. Based on the experimental results, two different hyperspectral images prove that novel RGB channel assimilation of DTICF-3D-CNN-Bi-LSTM approach is more important and provides good classification results compared to other classification approaches.

• Proceedings of the IEEK Conference
• /
• 2001.06d
• /
• pp.109-112
• /
• 2001

This paper proposes a method to classify different video contents using features of digital video. Classified video types are the news, drama, show, sports, and talk program. Features, such as intra-coded macroblock number St motion vector in P-picture in MPEG domain are used. The frame difference of YCbCr is also employed as a measure of classification. We detect the occurrences of cuts in a video for a measure of classification. Finally, back-propagation neural-network of 3 layers is used to classify video contents.

• Journal of Korea Multimedia Society
• /
• v.20 no.10
• /
• pp.1637-1645
• /
• 2017

Target/Nontarget classification can be divided into the study of shape estimation of the target analysing reflected echo signal and of type classification of the target using acoustical features. In active sonar system, the feature vectors are extracted from the signal reflected from the target, and an classification algorithm is applied to determine whether the received signal is a target or not. However, received sonar signals can be distorted in the underwater environments, and the spatio-temporal characteristics of active sonar signals change according to the aspect of the target. In addition, it is very difficult to collect real sea-trial data for research. In this paper, target/non-target classification were performed using real sea-trial data. Feature vectors are extracted using MFCC(Mel-Frequency Cepstral Coefficients), filterbank energy in the Fourier spectrum and wavelet domain. For the performance verification, classification experiments were performed using backpropagation neural network classifiers.

• Journal of KIISE:Software and Applications
• /
• v.35 no.9
• /
• pp.562-571
• /
• 2008

For the purpose of building domain ontology, this paper proposes a methodology for building core ontology first, and then enriching the core ontology with the concepts and relations in the domain thesaurus. First, the top-level concept taxonomy of the core ontology is built using domain dictionary and general domain thesaurus. Then, the concepts of the domain thesaurus are classified into top-level concepts in the core ontology, and relations between broader terms (BT) - narrower terms (NT) and related terms (RT) are classified into semantic relations defined for the core ontology. To classify concepts, a two-step approach is adopted, in which a frequency-based approach is complemented with a similarity-based approach. To classify relations, two techniques are applied: (i) for the case of insufficient training data, a rule-based module is for identifying isa relation out of non-isa ones; a pattern-based approach is for classifying non-taxonomic semantic relations from non-isa. (ii) For the case of sufficient training data, a maximum-entropy model is adopted in the feature-based classification, where k-NN approach is for noisy filtering of training data. A series of experiments show that performances of the proposed systems are quite promising and comparable to judgments by human experts.

• Journal of Korean Academic Society of Home Health Care Nursing
• /
• v.5
• /
• pp.47-60
• /
• 1998

This study was done to identify basic information in classifying nursing diagnoses and nursing interventions needed for the further development of computerized nursing care plans. Data were collected by reviewing charts of 123 home care clients who had active disease, for whom at least one nursing diagnosis was on the chart, and who had been discharged. Data included demographics, medical orders, nursing diagnoses and nursing interventions. The results of the study, which found the most frequent medical diagnoses to be cancer (40.7%) and brain injury (26.8%), showed that 'Impaired Skin Integrity'(18.3%), 'Risk for Infection'(15.0%), 'Altered Nutrition, Less than Body Requirements'(13.8%), and 'Risk for Impaired Skin Integ rity'(9.9%) were the most frequent nursing diagnoses. 'Pressure Ulcer Care'(28.4%) was the most frequent intervention for 'Impaired Skin Integrity', 'Infection Protection'(16.0%) for 'Risk of Infection', 'Nutrition Counseling'(26.8%) for 'Altered Nutrition' and 'Positioning'(22.0%) for 'Risk for Skin Integrity Impairment', Comparison of interventions with the Nursing Intervention Classification(NIC) showed that the most frequent interventions were in the domain 'Basic Physiological' (33.94%), followed by 'Behavioral'(27.8%), and 'Complex Physiological' (22.6%). Interventions related to teaching family to give care at home could not be classified in the NIC scheme. Examination of the frequency of NIC interventions showed that for the domain 'Activity & Exercise Management', 75% of the interventions were used, but for seven domains, none were used. For the domain 'Immobility Management', 93% of the times that an intervention was used, it was 'Positioning', for the domain 'Tissue Perfusion Management', 'IV Therapy' (59.1%) and for the domain 'Elimination Management', 'Tube Care: Urinary'(54.0%). The nursing diagnoses 'Altered Urinary Elimination' and 'Im paired Physical Mobility' were both used with these clients, but neither 'Fluid Volume Deficit' nor 'Risk of Fluid Volume Deficit' were used rather 'IV Therapy' was an intervention for 'Altered Nutrition, Less than Body Requirements', A comparison of clients with cancer and those with brain injury showed that interventions for the nursing diagnosis 'Impaired Skin Integrity' were more frequent for the clients with cancer, interventions for 'Risk of Infection' were similar for the two groups but for clients with cancer there were more interventions for' Altered Nutrition'. Examination of the nursing diagnoses leading to the intervention 'Positioning' showed that for both groups, it was either 'Impaired Skin Integrity' or 'Risk for Skin Integrity Impairment'. This study identified a need for further refinement in the classification of nursing interventions to include those unique to home care and that for the purposes of computerization identification of the nursing activities to be included in each intervention needs to be done.