• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.2
• /
• pp.395-400
• /
• 2017

The paper discussed the air-to-fuel ratio control of automotive fuel-injection systems using the cerebellar model articulation controller(CMAC) neural network. Because of the internal combustion engines and fuel-injection's dynamics is extremely nonlinear, it leads to the discontinuous of the fuel-injection and the traditional method of control based on table look up has the question of control accuracy low. The advantages about CMAC neural network are distributed storage information, parallel processing information, self-organizing and self-educated function. The unique structure of CMAC neural network and the processing method lets it have extensive application. In addition, by analyzing the output characteristics of oxygen sensor, calculating the rate of fuel-injection to maintain the air-to-fuel ratio. The CMAC may easily compensate for time delay. Experimental results proved that the way is more good than traditional for petrol control and the CMAC fuel-injection controller can keep ideal mixing ratio (A/F) for engine at any working conditions. The performance of power and economy is evidently improved.

• Journal of Information Technology and Architecture
• /
• v.9 no.3
• /
• pp.275-285
• /
• 2012

DIFs (Data Interchange Formats) are needed to enhance interoperability of physically distributed organizations in SBA (Simulation Based Acquisition) process. DIFs play a role as a template of DPDs (Distributed Product Descriptions) and provide capability to use information directly without data format interchange process by allowing access to DPDs, which include various information and M&S (Modeling & Simulation) resources. This characteristic is essential for interoperability in ICE (Integrated Collaborative Environment) based SBA. This paper proposes a framework for the DIF and outputs from each phase of acquisition process for configuration data related to design and manufacturing in SBA process - Conceptual Data Model, Logical Data Model, Physical Data Model and Physical DIF based on XML. Finally, we propose the DIF model architecture and demonstrate the implementation of DIF example based on it.

• Journal of Advanced Navigation Technology
• /
• v.17 no.6
• /
• pp.609-615
• /
• 2013

As with any ships, adequate power provision is crucial, especially on the ocean navigating ships far from the land. In order to resolve the effective and economic power supply system of any ship in operation, in this paper, we propose a power management system that intelligently controls the power supply in ships. Power management systems in this design consist of a power load detection system, a generator configuration system, and a power monitoring system respectively. The CT / PT sensor is used to measure amount of current and power in the power detection system, and according to the collected information from various sensor, the generator configuration system will switch on and off the main / sub generator effectively. Finally, the power monitoring system will display all status information of this power management system at a glance for users. This power management systems implemented in this paper is evaluated via real-time experiments, which works well as designed, and certified by KSCIEC61892-1:2012 and KSCIEC60950-1:2008.

• Journal of the Korea Convergence Society
• /
• v.9 no.12
• /
• pp.47-52
• /
• 2018

Named Entity Recognition is a system that extracts entity names such as Persons(PS), Locations(LC), and Organizations(OG) that can have a unique meaning from a document and determines the categories of extracted entity names. Recently, Bi-LSTM-CRF, which is a combination of CRF using the transition probability between output data from LSTM-based Bi-LSTM model considering forward and backward directions of input data, showed excellent performance in the study of object name recognition using deep-learning, and it has a good performance on the efficient embedding vector creation by character and word unit and the model using CNN and LSTM. In this research, we describe the Bi-LSTM-CNN-CRF model that enhances the features of the Korean named entity recognition system and propose a method for constructing the traditional culture corpus. We also present the results of learning the constructed corpus with the feature augmentation model for the recognition of Korean object names.

• Journal of the Korean Institute of Gas
• /
• v.22 no.6
• /
• pp.34-39
• /
• 2018

Natural gas is attracting attention as an alternative to existing fossil fuels. Natural gas has a high octane number. Therefore, knocking does not occur even if the compression ratio is increased, so that the thermal efficiency and the output can be improved. And it is relatively easy to apply the natural gas supply system to the internal combustion engine hardware system. In this study, a gasoline direct injection turbo engine was converted into a natural gas port injection type turbo engine. Therefore, the combustion and performance of the engine are measured and compared comprehensively in the region where the turbo operates.

• The Korean Journal of Archival Studies
• /
• no.52
• /
• pp.277-313
• /
• 2017

With the enactment of regulations on confidential records management, the management of confidential records has become more important than ever. However, there remains no management method in the field of records management that takes the feature and values of confidential records into consideration. For this, this study processed electronically confidential records managed in a non-electronic environment. In addition, we developed a system that will allow public institutions to manage confidential records independently, that will prevent loss of information because of loss of or damage to the confidential records, and that can be used conveniently in the digital security environment of authorized users to establish a foundation for commercial management. In this study, we analyzed the system configuration requirements according to the international standard for the records management of a confidential records management system and system-related issues such as system design based on the analyzed requirements, system security and encryption, and metadata, the overall process of establishing and outputting secret management records and standard management.

• Journal of the Korean Institute of Gas
• /
• v.24 no.6
• /
• pp.55-60
• /
• 2020

As research and development of eco-friendly vehicles are expanding worldwide, additional devices of vehicles are reduced or deleted to increase the mileage, or research is being conducted to reduce weight. Among them, the multi-stage transmission that was applied to the internal combustion engine vehicle was deleted and replaced with a reducer, and the initial driving power is secured by increasing the torque through the control of the motor output value. However, since frequent motor speed change can result in a load increase, this study attempts to develop a compact and lightweight manual two-stage reducer with a general reducer structure. Therefore, a two-speed transmission with two gear ratio was designed by inserting a large gear and a small gear in a structure with a parallel shaft to connect the gears with a V-belt in the form of a parallel shaft reducer, and setting the gear ratio of the low and high gears respectively. In addition, power performance according to the rotational speed and load of the transmission was checked through a test, and the heat generation characteristics generated during driving were checked to verify the validity of the transmission.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.333-340
• /
• 2023

Efficient prediction of corporate bankruptcy is an important part of making appropriate lending decisions for financial institutions and reducing loan default rates. In many studies, classification models using artificial intelligence technology have been used. In the financial industry, even if the performance of the new predictive models is excellent, it should be accompanied by an intuitive explanation of the basis on which the result was determined. Recently, the US, EU, and South Korea have commonly presented the right to request explanations of algorithms, so transparency in the use of AI in the financial sector must be secured. In this paper, an artificial intelligence-based interpretable classification prediction model was proposed using corporate bankruptcy data that was open to the outside world. First, data preprocessing, 5-fold cross-validation, etc. were performed, and classification performance was compared through optimization of 10 supervised learning classification models such as logistic regression, SVM, XGBoost, and LightGBM. As a result, LightGBM was confirmed as the best performance model, and SHAP, an explainable artificial intelligence technique, was applied to provide a post-explanation of the bankruptcy prediction process.

• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.91-102
• /
• 2022

As artificial intelligence develops, AI chatbot systems are actively taking place. For example, in public institutions, the use of chatbots is expanding to work assistance and professional knowledge services in civil complaints and administration, and private companies are using chatbots for interactive customer response services. In this study, we propose a scenario-based AI voice chatbot system to reduce museum operating costs and provide interactive guidance services to visitors. The implemented voice chatbot system consists of a watcher object that detects the user's voice by monitoring a specific directory in real-time, and an event handler object that outputs AI's response voice by performing inference by model sequentially when a voice file is created. And Including a function to prevent duplication using thread and a deque, GPU operations are not duplicated during inference in a single GPU environment.

• Radiation Oncology Journal
• /
• v.10 no.1
• /
• pp.1-6
• /
• 1992

The usefulness of hyperthermia for cancer therapy has been established. The purpose of the present investigation was to access feasibility of heating normal lung and the temperature and power requirement were compared with that for liver as solid organ in rabbits by using radiofrequent heating machine. In this study, 20 rabbits were divided into 2 groups according to the heating site and the method of temperature measurement; in group I : lung heating and temperature measuring in skin, esophagus and lung parenchyme; in group II : liver heating and temperature measuring in skin and liver parenchyme. The results were as follows; 1) When the maximum temperature was almost same in lung heating group and liver heating group, the power for liver heating was lesser required than the power for lung heating (p<0.05). 2) The temperature of esophagus for the measurement of mediastinum temperature was $1.1{\pm}0.9^{\circ}C$ higher than the temperature of lung parenchyme (p<0.05). Therefore the above findings suggest lung, air containing organ, is well heated as same as liver, solid organ. So more active trials of lung heating in the lung cancer must be likely considered. But when the lung is heated, the esophageal temperature is higher than lung parenchyme, so the mediastinum damage must be considered seriously.