• Journal of Korean Society for Geospatial Information Science
• /
• v.5 no.2 s.10
• /
• pp.13-27
• /
• 1997

For the National Geo-Spatial Information System the development of the National Digital Basemap database is actively underway in Korea. For the National Digital Basemap database to be truly useful for various applications development it is essential to maintain its reliability. To maintain the reliability of the database it is necessary to understand the nature and the frequency of the errors in it. In general, a data inspection under the standardized quality control process is required to maintain the quality of a large database. In addition, it is important to maintain complete and detailed records of the inspection results so as to understand the relationship between the m and other factors causing errors. These records can be used as a reference for map updates and future application development. The goal of this study is to count the frequency of errors based on the typology of errors found in the digitized map inspection process and to analyze the correlation between errors and topographic composite quotient This study also provides guidelines for the inspection process regarding the error-prone cartographic elements in the digital map generation process.

• Proceedings of the KIEE Conference
• /
• 2001.11a
• /
• pp.224-226
• /
• 2001

In this paper, a novel high-voltage motor monitoring system (HVMMS) is proposed. This system monitors the insulation condition of the stator winding by on-line measurements of partial discharge (PD). Sensor, EMC (Epoxy-Mica Coupler) is used for PD measurement PD signals are continuously measured and digitized with a peak-hold A/D converter to build the database of the high-voltage motor's insulation condition. Also, this system can communicate with the central monitoring system via RS-485. This helps more efficient operation and maintenance of the generator.

• Proceedings of the KIEE Conference
• /
• 1999.07e
• /
• pp.2212-2214
• /
• 1999

In this paper, a novel Generator On-line Diagnosis System (GODS) is proposed. This system monitors the insulation condition of the stator winding by on-line measurements of partial discharge (PD). Sensor, such as SSC (Stator Slot Coupler) and RFCT (Radio Frequency Current Transformer) are used for PD measurement. PD signals are continuously measured and digitized with a high speed A/D converter to build the database of the generator's insulation condition. Also this system can communicate with the central monitoring system via RS-485. This helps more efficient operation and maintenance of the generator.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2006.05a
• /
• pp.481-486
• /
• 2006

In this paper, a new on-line high-voltage motor monitoring system is proposed. This system monitors the insulation condition of the stator winding by on-line measurements of partial discharge (PD). And this system displays magnitude and phase angle distribution of PD. Sensor, CC (Ceramic Coupler) is used for PD measurement. PD signals are continuously measured and digitized with a A/D converter to build the database of the high-voltage motor's insulation condition. Also, this system can communicate with the central monitoring system via RS-232, 422, and TCP/IP. This helps more efficient operation and maintenance of the high-voltage motor.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3218-3241
• /
• 2023

Financial fraud undermines the sustainable development of financial markets. Financial statements can be regarded as the key source of information to obtain the operating conditions of listed companies. Current research focuses more on mining financial digital data instead of looking into text data. However, text data can reveal emotional information, which is an important basis for detecting financial fraud. The audit opinion of the financial statement is especially the fair opinion of a certified public accountant on the quality of enterprise financial reports. Therefore, this research was carried out by using the data features of 4,153 listed companies' financial annual reports and audits of text opinions in the past six years, and the paper puts forward a financial fraud detection model integrating audit opinions. First, the financial data index database and audit opinion text database were built. Second, digitized audit opinions with deep learning Bert model was employed. Finally, both the extracted audit numerical characteristics and the financial numerical indicators were used as the training data of the LightGBM model. What is worth paying attention to is that the imbalanced distribution of sample labels is also one of the focuses of financial fraud research. To solve this problem, data enhancement and Focal Loss feature learning functions were used in data processing and model training respectively. The experimental results show that compared with the conventional financial fraud detection model, the performance of the proposed model is improved greatly, with Area Under the Curve (AUC) and Accuracy reaching 81.42% and 78.15%, respectively.

• Journal of Biomedical Engineering Research
• /
• v.19 no.3
• /
• pp.261-268
• /
• 1998

Electrogastrography(EGG), the cutaneous recording of the myoelectrical activity of the stomach using surface electrodes, is a non-invasive technique to detect gastric motility disorder, We developed a detection and analysis system for the EGG signal, which consists of hardware(bio-amplifier, filter) and softwere(user interface, analysis algorithm, patient database). The EGG signal was amplified and filtered by 3 channel bio-amplifiers, and simultaneously digitized and stored on IBM PC with a sampling frequency of 16 Hz. The stored EGG signal was analyzed using developed algorithm to extract clinically useful information from the signal. The developed system has tested through animal experiments, and is under clinical evaluation.

• Journal of Biomedical Engineering Research
• /
• v.16 no.1
• /
• pp.17-24
• /
• 1995

This paper presents a new compression method (or ECG data using iterated contractive transformations. The method represents any range of ECG signal by piecewise self-afrine fractal Interpolation (PSAFI). The piecewise self-afrine rractal model is used where a discrete data set is viewed as being composed of contractive arfine transformation of pieces of itself. This algorithm was evaluated using MIT/BIH arrhythmia database. PSAFI is found to yield a relatively low reconstruction error for a given compression ratio than conventional direct compression methods. The compression ratio achieved was 883.9 bits per second (bps) - an average percent rms difference (AFRD) of 5.39 percent -with the original 12b ECG samples digitized at 400 Hz.

• Proceedings of the KOSOMBE Conference
• /
• v.1996 no.11
• /
• pp.189-191
• /
• 1996

Computerized spirometer was developed in a form of proto type system. The system consisted of pneumotachometer, flow measurement unit, fan ventilator unit, and software program. Patient's respiratory flow signal was first converted to corresponding pressure drop signal by a screen type pneumotachometer, sensed by a differential pressure transducer, amplified and low pass filtered, and digitized at a rate of 100 Hz, then fed into a PC thru RS-232C serial port. Customized application software controls data acquisition followed by computation of test parameters. The fan ventilator unit dries and eliminates microorganism in the pneumotachometer after each test. The system performs conventional spirometic tests and manages the test results in a database for retrograde research. The proto type system was fully developed and the commercialized system is currently being built up.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.284-291
• /
• 2022

Historical data from comparable projects can serve as benchmarking data for an ongoing project's planning during the project scoping phase. As project owners typically store substantial amounts of data generated throughout project life cycles in digitized databases, they can capture appropriate data to support various project planning activities by accessing digital databases. One of the most important work tasks in this process is identifying one or more past projects comparable to a new project. The uniqueness and complexity of construction projects along with unorganized data, impede the reliable identification of comparable past projects. A project scope document provides the preliminary overview of a project in terms of the extent of the project and project requirements. However, narratives and free-formatted descriptions of project scopes are a significant and time-consuming barrier if a human needs to review them and determine similar projects. This study proposes an Artificial Intelligence-driven model for analyzing project scope descriptions and evaluating project similarity using natural language processing (NLP) techniques. The proposed algorithm can intelligently a) extract major work activities from unstructured descriptions held in a database and b) quantify similarities by considering the semantic features of texts representing work activities. The proposed model enhances historical comparable project identification by systematically analyzing project scopes.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2023.05a
• /
• pp.389-390
• /
• 2023

To improve the cost performance of construction sites, various systems and standards are constantly being developed and implemented. Although legal requirements for these system and standard improvements have been increasing, the cost efficiency performance of construction sites remains stagnant. We have digitized documents generated through construction supervision work at 39 building construction sites and proposed a model that can support decision-making in cost efficiency evaluation. This model selects key keywords that are considered to be highly related to cost efficiency by identifying the patterns and relationships of keywords through associated rule analysis and social network analysis using keywords derived from documents. In addition, it is expected to be used as a decision-making aid to determine the cost efficiency of a specific building construction site by establishing a logistic regression model using core keywords. As a systematic database of construction supervision documents and an integrated system of massive data generated by digital technology are established in the future, the accuracy and reliability of the cost efficiency evaluation model are expected to be reinforced.