• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.9
• /
• pp.777-781
• /
• 2001

This paper presents an image contrast enhancement technique for improving the low contrast images using the improved IAFC(Integrated Adaptive Fuzzy Clustering) model. The low pictorial information of a low contrast image is due to the vagueness or fuzziness of the multivalued levels of brightness rather than randomness. Fuzzy image processing has three main stages, namely, image fuzzification, modification of membership values, and image defuzzification. Using a new model of automatic crossover point selection, optimal crossover point is selected automatically. The problem of crossover point selection can be considered as the two-category classification problem. The improved IAFC model is used to classify the image into two classes. The proposed method is applied to several experimental images with 256 gray levels and the results are compared with those of the histogram equalization technique. We utilized the index of fuzziness as a measure of image quality. The results show that the proposed method is better than the histogram equalization technique.

• Journal of Information Technology Applications and Management
• /
• v.21 no.2
• /
• pp.81-98
• /
• 2014

Recently, due to external environment like the changes in health policy and various healthcare accreditations, along with hospital's internal efforts to improve the quality of medical services, demands for the development of medical information systems are increasing. Some examples are clinical information like DUR (Drug Utilization Review), CVR (Critical Value Report), and automatic benefit processing by treatment purposes, or hospital DSS (Decision Support System) on overall medical practice. Such systems act as a guide in making clinic judgments during practice or in other medical practice, and their effects on the medical treatment improvements are being proven by previous studies. In the reality of increasing attention in the effects of medical treatment improvement, studies related to hospital DDS were mostly focused on clinical, technical, and engineering points of view, and studies focusing on the user viewpoint are very limited. In order to verify the effects of DSS on practice improvements and hospital's management performance, this study used a research model constructed to verify how SERVQUAL of hospital DSS affects hospital management performance in BSC (Balanced Score Card) point of view. To empirically verify the research model, a questionnaire was conducted on the basis of "K-University Hospital's DSS" on clinicians and hospital employees related to system development, and the relationships between the factors were analyzed through path analysis. As a result of path analysis, excluding reactivity, tangibility, confidence, reliability, empathy among service qualities, had partially significant effects on management performance factors (learning and growth, internal process, financial affairs). This study is to prepare the theoretical ground on the management performance analysis of hospital DSS, and suggest the service quality of the system that should be considered in the planning and development stages for improved system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.12
• /
• pp.2975-2981
• /
• 2014

Micro-magnetic detection system is used to detect small particles in an automatic transmission valve body, which signal noise and time-delay may occurs in process of signal transmitting and filtering. In this paper, we present the design and implement of a micro-magnetic detection system based on wireless sensor networks in conveyer belt. Micro-magnetic detection system consists of five modules which are magnetic sensor detector, signal processing unit, wireless sensor networks, system control unit and system monitoring unit. Our experimental results show that the proposed wireless micro-magnetic detection system improves both accuracy and time delay compared to the wired system; therefore, it may apply for wireless micro-magnetic detection system by analysis of packet reception rate.

• The KIPS Transactions:PartD
• /
• v.11D no.3
• /
• pp.703-708
• /
• 2004

Currently the amount of general letter mail in Korea is on an increasing trend; especially it shows the seasonality that is concentrated in the end of the month or the year. However, the situation is not treated appropriately Moreover. manpower insufficiency if the carriers causes the poor service and the heavy burden of work. Under the existing conditions, the various efforts such as development of the automatic sequence sorting system and construction of the address database are given in order to quicken mall process and lighten the carriers' burden But the inconsistent addressing and the various expressions of address drop the systems and the carriers off in efficiency. In this study, we present the Korean postal addressing standards to make it possible to improve the performance of address recognition and help postmen to sort the mail; particularly focusing on the substance. After analyzing the domestic system, the information structure and the problems of postal address, we propose four fundamentals and the standards including synonyms and acronyms. In addition, we suggest several considerations for mail format. We expect that this study could support the postal service in Korea as a basic standard.

• The KIPS Transactions:PartB
• /
• v.11B no.5
• /
• pp.545-554
• /
• 2004

Combining multiple classifiers to obtain improved performance over the individual classifier has been a widely used technique. The task of constructing a multiple classifier system(MCS) contains two different Issues how to generate a diverse set of base-level classifiers and how to combine their predictions. In this paper, we review the characteristics of existing multiple classifier systems : Bagging, Boosting, and Slaking. For document classification, we propose new MCSs such as Stacked Bagging, Stacked Boosting, Bagged Stacking, Boosted Stacking. These MCSs are a sort of hybrid MCSs that combine advantages of existing MCSs such as Bugging, Boosting, and Stacking. We conducted some experiments of document classification to evaluate the performances of the proposed schemes on MEDLINE, Usenet news, and Web document collections. The result of experiments demonstrate the superiority of our hybrid MCSs over the existing ones.

• The KIPS Transactions:PartB
• /
• v.10B no.5
• /
• pp.497-502
• /
• 2003

Fingerprint classification plays a role of reduction of precise joining time and improvement of the accuracy in a large volume of database. Patterns of fingerprint are classified as 5 patterns : left loop, right loop, arch, whorl, and tented arch by numbers and the location of core point and delta point. The existing fingerprint classification is useful in a captured fingerprint image of core point and delta point using paper and ink. However, this system is unapplicable in modern Automatic Fingerprint Identification System (AFIS) because of problems such as size of input and way of input. To solve the problem, this study is to suggest the way of being able to improve accuracy of fingerprint by fingerprint classification based on the entropy of ridges using fingerprint captured mage of core point and prove this through the experiment.

• The KIPS Transactions:PartD
• /
• v.18D no.5
• /
• pp.343-356
• /
• 2011

When preparing test cases and running the test the existing GUI test tools require many tester's interventions. To cope with such problem this paper suggests a new method to build test cases for GUI test. This method identifies the potential control flows within the GUI and constructs the GUI map. The UIA library in .NET Framework is used to extract information about the GUI controls and the GUI map is constructed by the extracted information. Test scenarios are generated from the extracted information about the GUI controls using the grouping mechanism. Based on the grouping mechanism, various test scenarios which are test cases in GUI tests can be made by replacing a GUI control by another one in the same group. The existing GUI test tools do not support the concept of test coverage. Since, however, our method survey which part of the GUI map is executed or not during running the test, the test coverage can be measured by using the GUI map.

• The KIPS Transactions:PartB
• /
• v.14B no.3 s.113
• /
• pp.231-240
• /
• 2007

In this paper, we propose an automatic extraction model for unknown translations and implement an unknown translation extraction system using the proposed model. The proposed model as a phrase-alignment model is incorporated with three models: a phrase-boundary model, a language model, and a translation model. Using the proposed model we implement the system for extracting unknown translations, which consists of three parts: construction of parallel corpora, alignment of Korean and English words, extraction of unknown translations. To evaluate the performance of the proposed system we have established the reference corpus for extracting unknown translation, which comprises of 2,220 parallel sentences including about 1,500 unknown translations. Through several experiments, we have observed that the proposed model is very useful for extracting unknown translations. In the future, researches on objective evaluation and establishment of parallel corpora with good quality should be performed and studies on improving the performance of unknown translation extraction should be kept up.

• The KIPS Transactions:PartB
• /
• v.16B no.6
• /
• pp.451-462
• /
• 2009

The spread of satellite image increases various services using it. Especially, 3D visualization services of the whole earth such as $Google\;Earth^{TM}$ and $Virtual\;Earth^{TM}$ or 3D GIS services for several cities provide realistic geometry information of buildings and terrain of wide areas. These service can be used in the various fields such as urban planning, improvement of roads, entertainment, military simulation and emergency response. The research about extracting the building and terrain information effectively from the high-resolution satellite image is required. In this paper, presents a system for effective extraction of the building model from a single high-resolution satellite image, after examine requirements for building model extraction. The proposed system utilizes geometric features of satellite image and the geometric relationship among the building, the shadow of the building, the positions of the sun and the satellite to minimize user interaction. Finally, after extracting the 3D building, the fact that effective extraction of the model from single high-resolution satellite will be show.

• The KIPS Transactions:PartB
• /
• v.16B no.6
• /
• pp.479-488
• /
• 2009

This paper shows a reinforced construction scheme of training data for improvement of text classification by automatic search of boundary category. The documents laid on boundary area are usually misclassified as they are including multiple topics and features. which is the main factor that we focus on. In this paper, we propose an automated exploring methodology of optimal boundary category based on previous research. We consider the boundary area among target categories to new category to be required training, which are then added to the target category sementically. In experiments, we applied our method to complex documents by intentionally making errors in training process. The experimental results show that our system has high accuracy and reliability in noisy environment.