• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.805-807
• /
• 2021

In-hospital cardiac arrest is a significant problem for medical systems. Although the traditional early warning systems have been widely applied, they still contain many drawbacks, such as the high false warning rate and low sensitivity. This paper proposed a strategy that involves a deep learning approach based on a novel interpretable deep tabular data learning architecture, named TabNet, for the Rapid Response System. This study has been processed and validated on a dataset collected from two hospitals of Chonnam National University, Korea, in over 10 years. The learning metrics used for the experiment are the area under the receiver operating characteristic curve score (AUROC) and the area under the precision-recall curve score (AUPRC). The experiment on a large real-time dataset shows that our method improves compared to other machine learning-based approaches.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.3
• /
• pp.91-98
• /
• 2021

Today's information and communication technology is rapidly developing, the security of IT infrastructure is becoming more important, and at the same time, cyber attacks of various forms are becoming more advanced and sophisticated like intelligent persistent attacks (Advanced Persistent Threat). Early defense or prediction of increasingly sophisticated cyber attacks is extremely important, and in many cases, the analysis of network-based intrusion detection systems (NIDS) related data alone cannot prevent rapidly changing cyber attacks. Therefore, we are currently using data generated by intrusion detection systems to protect against cyber attacks described above through Host-based Intrusion Detection System (HIDS) data analysis. In this paper, we conducted a comparative study on machine learning algorithms using LID-DS (Leipzig Intrusion Detection-Data Set) host-based intrusion detection data including thread information, metadata, and buffer data missing from previously used data sets. The algorithms used were Decision Tree, Naive Bayes, MLP (Multi-Layer Perceptron), Logistic Regression, LSTM (Long Short-Term Memory model), and RNN (Recurrent Neural Network). Accuracy, accuracy, recall, F1-Score indicators and error rates were measured for evaluation. As a result, the LSTM algorithm had the highest accuracy.

• Journal of Korean Society for Quality Management
• /
• v.49 no.3
• /
• pp.327-340
• /
• 2021

Purpose: The purpose of this study is to propose a system predicting whether an electricity distribution system is abnormal by analyzing the temperature of the deteriorated system. Traditional electricity distribution system abnormality diagnosis was mainly limited to post-inspection. This research presents a remote monitoring system for detecting thermal images of the deteriorated electricity distribution system efficiently hereby providing safe and efficient abnormal diagnosis to electricians. Methods: In this study, an object detection algorithm (YOLOv5) is performed using 16,866 thermal images of electricity distribution systems provided by KEPCO(Korea Electric Power Corporation). Abnormality/Normality of the extracted system images from the algorithm are classified via the limit temperature. Each classification model, Random Forest, Support Vector Machine, XGBOOST is performed to explore 463,053 temperature datasets. The process capability index is employed to indicate the quality of the electricity distribution system. Results: This research performs case study with transformers representing the electricity distribution systems. The case study shows the following states: accuracy 100%, precision 100%, recall 100%, F1-score 100%. Also the case study shows the process capability index of the transformers with the following states: steady state 99.47%, caution state 0.16%, and risk state 0.37%. Conclusion: The sum of caution and risk state is 0.53%, which is higher than the actual failure rate. Also most transformer abnormalities can be detected through this monitoring system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.5
• /
• pp.859-876
• /
• 2010

In this paper, we propose a hierarchical application traffic classification system as an alternative means to overcome the limitations of the port number and payload based methodologies, which are traditionally considered traffic classification methods. The proposed system is a new classification model that hierarchically combines a binary classifier SVM and Support Vector Data Descriptions (SVDDs). The proposed system selects an optimal attribute subset from the bi-directional traffic flows generated by our traffic analysis system (KU-MON) that enables real-time collection and analysis of campus traffic. The system is composed of three layers: The first layer is a binary classifier SVM that performs rapid classification between P2P and non-P2P traffic. The second layer classifies P2P traffic into file-sharing, messenger and TV, based on three SVDDs. The third layer performs specialized classification of all individual application traffic types. Since the proposed system enables both coarse- and fine-grained classification, it can guarantee efficient resource management, such as a stable network environment, seamless bandwidth guarantee and appropriate QoS. Moreover, even when a new application emerges, it can be easily adapted for incremental updating and scaling. Only additional training for the new part of the application traffic is needed instead of retraining the entire system. The performance of the proposed system is validated via experiments which confirm that its recall and precision measures are satisfactory.

• Journal of Biosystems Engineering
• /
• v.12 no.2
• /
• pp.28-37
• /
• 1987

Operation of rice whiteners has been depending on operator's experience only and very limitted data are available for operational criteria of rice whiteners in Korea. With developments of new rice varieties and with a tendency of automation of machine operations for precision control, operational criteria depending on physical characteristics of rice grains arc required for an improvement of milled rice recovery and the performance of rice whitening systems. An experimental study was conducted to identify operational criteria of a rice whitening system consisted with an abrasive-aerated whitener developed newly and a frictional-aerated whitener being used commercially. Further, comparisons were made between the performance of the rice whitening system adopted for this study and a commercial system used in small scale milling plants. Results of this study are summarized as follows: 1. Total number of passes necessary for the final white rice in the combined whitening system depended exclusively on the counter pressure level of the frictional whitener successive to the abrasive whitener. 2. The counter pressure required for whitening Japonica type rice variety (Akibare) was higher by about 1.6 times than that for Japonica type (Pung-san), when other conditions were kept at the same. 3. Radial pressure in the whitening chamber of the frictional whitener should be maintained between 1.5 to $2.1kg/cm^2$ for the completion of whitening within 5 to 3 passes regardless of rice varieties. Hence, it was found that the radial pressure in the whitening chamber could be used as an operational criteria to control the counter pressure level. 4. The following regression equation was found between radial pressure($R_p$) in whitening chamber and electric power consumption of the whitening system: $$EPC=-0.545\;R^2_p+1.277\;R_p+0.874[KWH/100kg]$$ 5. The following multiple regression equation was found among radial pressure ($R_p$), counter pressure ($C_p$), and bioyield point ($B_i$), length (L) and width (W) of brown rice. $$R_p/(B_i/W^2)=0.547\{C_p/(B_i/W^2)\}^{0.365}(L/W)^{0.120}(R^2=0.9897)$$ 6. The milled rice recovery and machine efficiency (kg/KWH) from the combined whitening system were higher by about 2.0% point and by 15 to 27% point than those from the conventional system, respectively.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.2170-2174
• /
• 2005

Selective Laser Sintering (SLS) is a useful rapid prototyping technique for the manufacture of three dimensional (3D) solid objects directly from a scanning data. A new approach called a Selective Multi-Laser Sintering (SMLS) system has been developed at Korea Institute Machinery & Materials (KIMM) as an industrial type SFFS. This SMLS machine is built with a frame, heaters, nitrogen supply part, laser system. This system uses the dual laser and 3D scanner made in $Solutionix^{TM}$ to improve the precision and speed for large objects. The three-dimensional solid objects are made of polyamide powder. The investigation on each part of SMLS system is performed to determine the proper theirs design and the effect of experimental parameters on making the 3D objects. The temperature of the system has a great influence on sintering the polymer. Because the stability of the powder temperature prevents the deformation of each layer, the controls of the temperature in both the system and the powders are very important during the process. Therefore, we simulated the temperature distribution of build room using the temperature analysis with ANSYS program. Selected radiant heater is used to raise temperature of powder to melting point temperature. The laser parameters such as scan spacing, scan speed, laser power and laser delay time affect the production the 3D objects too. The combination of the slow scan speed and the high laser power shows the good results without the layer curling. The work is under way to evaluate the effect of experimental parameters on process and to produce the various objects. We are going to experiment continuously to improve the size accuracy and surface roughness.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.28 no.12
• /
• pp.502-508
• /
• 2016

An optimized PI controller design method is presented to promote the control performance of an oil cooler system for high precision machine tools. First, a transfer function model of the oil cooler system with a variable rotating speed compressor was obtained by the perturbation method as the first order system with a negligible dead time. Then, the closed-loop control system was described as the second order system with a zero. Its dynamic behaviors are mostly governed by characteristic parameters, the damping ratio, and the natural frequency which is incorporated in PI gains. Next, an optimum integral of the time-weighted absolute error (ITAE) criterion was applied to the second order system. The characteristic parameters can be determined by the given design specifications, percent overshoots and settling times and comparisons with the ITAE criterion. Hence, the PI gains were plainly identified in a deterministic way. Finally, the PI gains were fine-tuned to obtain desirable dynamics in real systems, considering the zero effect and parameter variations. The validity of the proposed method was proven by computer simulations and real experiments for selected cases.

• Journal of Korean Neurosurgical Society
• /
• v.66 no.6
• /
• pp.632-641
• /
• 2023

Central nervous system tumors are identified as tumors of the brain and spinal cord. The associated morbidity and mortality of cerebrospinal tumors are disproportionately high compared to other malignancies. While minimally invasive techniques have initiated a revolution in neurosurgery, artificial intelligence (AI) is expediting it. Our study aims to analyze AI's role in the neurosurgical management of cerebrospinal tumors. We conducted a scoping review using the Arksey and O'Malley framework. Upon screening, data extraction and analysis were focused on exploring all potential implications of AI, classification of these implications in the management of cerebrospinal tumors. AI has enhanced the precision of diagnosis of these tumors, enables surgeons to excise the tumor margins completely, thereby reducing the risk of recurrence, and helps to make a more accurate prediction of the patient's prognosis than the conventional methods. AI also offers real-time training to neurosurgeons using virtual and 3D simulation, thereby increasing their confidence and skills during procedures. In addition, robotics is integrated into neurosurgery and identified to increase patient outcomes by making surgery less invasive. AI, including machine learning, is rigorously considered for its applications in the neurosurgical management of cerebrospinal tumors. This field requires further research focused on areas clinically essential in improving the outcome that is also economically feasible for clinical use. The authors suggest that data analysts and neurosurgeons collaborate to explore the full potential of AI.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.4
• /
• pp.208-219
• /
• 2021

In the era of the 4th industrial revolution driven by the convergence of ICT(information and communication technology) and manufacturing, research on smart factories is being actively conducted. In particular, the manufacturing industry prefers smart factories that autonomously connect and analyze data. For the efficient implementation of smart factories, it is essential to have an integrated production system that vertically integrates separately operated production equipment and heterogeneous S/W systems such as ERP, MES. In addition, it is necessary to double-verify production data by using automatic data collection technology so that the production process can be traced transparently. In this study, we want to show a case of data-centered integration of a large aircraft parts processing factory that requires high precision, takes a long time, and has the characteristics of processing large raw materials. For this, the components of the data-oriented integrated production system were identified and the connection structure between them was explained. And we would like to share the experience gained through the design and implementation case. The integrated production system proposed in this study integrates internal components based on data, which is expected to serve as a basis for SMEs to develop into an advanced stage, and traces materials with RFID technology.

• The KIPS Transactions:PartB
• /
• v.11B no.4
• /
• pp.491-500
• /
• 2004

This paper presents an ontology construction method using various computational language resources, and an ontology-based word sense disambiguation method. In order to acquire a reasonably practical ontology the Kadokawa thesaurus is extended by inserting additional semantic relations into its hierarchy, which are classified as case relations and other semantic relations. To apply the ontology to disambiguate word senses, we apply the previously-secured dictionary information to select the correct senses of some ambiguous words with high precision, and then use the ontology to disambiguate the remaining ambiguous words. The mutual information between concepts in the ontology was calculated before using the ontology as knowledge for disambiguating word senses. If mutual information is regarded as a weight between ontology concepts, the ontology can be treated as a graph with weighted edges, and then we locate the weighted path from one concept to the other concept. In our practical machine translation system, our word sense disambiguation method achieved a 9% improvement over methods which do not use ontology for Korean translation.