• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.10
• /
• pp.2028-2042
• /
• 1994

Properly defining signal and noise in a self-organizing system like ART(Adaptive Resonance Theory) neural network model raises a number of subtle issues. Pattern context must enter the definition so that input features, treated as irrelevant noise when they are embedded in a given input pattern, may be treated as informative signals when they are embedded in a different input pattern. The ATR automatically self-scales their computational units to embody context and learning dependent definitions of a signal and noise and there is no problem in categorizing input pattern that have features similar in nature. However, when we have imput patterns that have features that are different in size and nature, the use of only one vigilance parameter is not enough to differentiate a signal from noise for a good categorization. For example, if the value fo vigilance parameter is large, then noise may be processed as an informative signal and unnecessary categories are generated: and if the value of vigilance parameter is small, an informative signal may be ignored and treated as noise. Hence it is no easy to achieve a good pattern categorization. To overcome such problems, a Coupled-ART neural network capable of modularized categorization of patterns is proposed. The Coupled-ART has two layer of tightly coupled modules. the upper and the lower. The lower layer processes the global features of a pattern and the structural features, separately in parallel. The upper layer combines the categorized outputs from the lower layer and categorizes the combined output, Hence, due to the modularized categorization of patterns, the Coupled-ART classifies patterns more efficiently than the ART1 model.

• Geophysics and Geophysical Exploration
• /
• v.8 no.4
• /
• pp.262-269
• /
• 2005

Since the buried cultural relics are three-dimensional (3-D) objects in nature, 3-D survey is more preferable in archeological exploration. 3-D Ground Penetrating Radar (GPR) survey based on very dense data in principle, however, might need much higher cost and longer time of exploration than other geophysical methods commonly used for the archeological exploration, such as magnetic and electromagnetic methods. We developed a small-scale continuous data acquisition system which consists of two sets of GPR antennas and the precise positioning device tracking the moving-path of GPR antenna automatically and continuously. Since the high cost of field work may be partly attributed to establishing many profile lines, we adopted a concept of data acquisition at arbitrary locations not along the pre-established profile lines. Besides this hardware system, we also developed several software packages in order to effectively process and visualize the 3-D data obtained by the developed system and the data acquisition concept. Using the developed system, we performed 3-D GPR survey to investigate the possible historical remains of Baekje Kingdom at Buyeo city, South Korea, prior to the excavation. Owing to the newly devised system, we could obtain 3-D GPR data of this survey area having areal extent over about $17,000m^2$ within only six-hours field work. Although the GPR data were obtained at random locations not along the pre-established profile lines, we could obtain high-resolution 3-D images showing many distinctive anomalies, which could be interpreted as old agricultural lands, waterways, and artificial structures or remains. This cast: history led us to the conclusion that 3-D GPR method is very useful not only to examine a small anomalous area but also to investigate the wider region of the archeological interests.

• Korean Journal of Soil Science and Fertilizer
• /
• v.43 no.3
• /
• pp.374-383
• /
• 2010

Microwave radar can penetrate cloud cover regardless of weather conditions and can be used day and night. Especially a ground-based polarimetric scatterometer has advantages of monitoring crop conditions continuously with full polarization and different frequencies. Kim et al. (2009) have measured backscattering coefficients of paddy rice using L-, C-, X-band scatterometer system with full polarization and various angles during the rice growth period and have revealed the necessity of near-continuous automatic measurement to eliminate the difficulties, inaccuracy and sparseness of data acquisitions arising from manual operation of the system. In this study, we constructed an X-band automatic scatterometer system, analyzed scattering characteristics of paddy rice from X-band scatterometer data and estimated rice growth parameter using backscattering coefficients in X-band. The system was installed inside a shelter in an experimental paddy field at the National Academy of Agricultural Science (NAAS) before rice transplanting. The scatterometer system consists of X-band antennas, HP8720D vector network analyzer, RF cables and personal computer that controls frequency, polarization and data storage. This system using automatically measures fully-polarimetric backscattering coefficients of rice crop every 10 minutes. The backscattering coefficients were calculated from the measured data at a fixed incidence angle of $45^{\circ}$ and with full polarization (HH, VV, HV, VH) by applying the radar equation and compared with rice growth data such as plant height, stem number, fresh dry weight and Leaf Area Index (LAI) that were collected at the same time of each rice growth parameter. We examined the temporal behaviour of the backscattering coefficients of the rice crop at X-band during rice growth period. The HH-, VV-polarization backscattering coefficients steadily increased toward panicle initiation stage, thereafter decreased and again increased in early-September. We analyzed the relationships between backscattering coefficients in X-band and plant parameters and predicted the rice growth parameters using backscattering coefficients. It was confirmed that X-band is sensitive to grain maturity at near harvesting season.

• The korean journal of orthodontics
• /
• v.27 no.5 s.64
• /
• pp.815-824
• /
• 1997

The purpose of this study is to develop the basic algorithm for the finite element method modeling of individual malocclusions. Usually, a great deal of time is spent in preprocessing. To reduce the time required, we developed a standardized procedure for measuring the position of each tooth and a program to automatically preprocess. The following procedures were carried to complete this study. 1. Twenty-eight teeth morphologies were constructed three-dimensionally for the finite element analysis and saved as separate files. 2. Standard brackets were attached so that the FA points coincide with the center of the brackets. 3. The study model of a patient was made. 4. Using the study model, the crown inclination, angulation, and the vertical distance from the tip of a tooth was measured by using specially designed tools. 5. The arch form was determined from a picture of the model with an image processing technique. 6. The measured data were input as a rotational matrix. 7. The program provides an output file containing the necessary information about the three-dimensional position of teeth, which is applicable to several finite element programs commonly used. The program for a basic algorithm was made with Turbo-C and the subsequent outfile was applied to ANSYS. This standardized model measuring procedure and the program reduce the time required, especially for preprocessing and can be applied to other malocclusions easily.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.6 s.312
• /
• pp.28-35
• /
• 2006

Statistical models of shape variability based on active shape models (ASMs) have been successfully utilized to perform segmentation and recognition tasks in two-dimensional (2D) images. Three-dimensional (3D) model-based approaches are more promising than 2D approaches since they can bring in more realistic shape constraints for recognizing and delineating the object boundary. For 3D model-based approaches, however, building the 3D shape model from a training set of segmented instances of an object is a major challenge and currently it remains an open problem in building the 3D shape model, one essential step is to generate a point distribution model (PDM). Corresponding landmarks must be selected in all1 training shapes for generating PDM, and manual determination of landmark correspondences is very time-consuming, tedious, and error-prone. In this paper, we propose a novel automatic method for generating 3D statistical shape models. Given a set of training 3D shapes, we generate a 3D model by 1) building the mean shape fro]n the distance transform of the training shapes, 2) utilizing a tetrahedron method for automatically selecting landmarks on the mean shape, and 3) subsequently propagating these landmarks to each training shape via a distance labeling method. In this paper, we investigate the accuracy and compactness of the 3D model for the human liver built from 50 segmented individual CT data sets. The proposed method is very general without such assumptions and can be applied to other data sets.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.39-70
• /
• 2017

Data-drive analytics techniques have been recently applied to public surveys. Instead of simply gathering survey results or expert opinions to research the preference for a recently launched product, enterprises need a way to collect and analyze various types of online data and then accurately figure out customer preferences. In the main concept of existing data-based survey methods, the sentiment lexicon for a particular domain is first constructed by domain experts who usually judge the positive, neutral, or negative meanings of the frequently used words from the collected text documents. In order to research the preference for a particular product, the existing approach collects (1) review posts, which are related to the product, from several product review web sites; (2) extracts sentences (or phrases) in the collection after the pre-processing step such as stemming and removal of stop words is performed; (3) classifies the polarity (either positive or negative sense) of each sentence (or phrase) based on the sentiment lexicon; and (4) estimates the positive and negative ratios of the product by dividing the total numbers of the positive and negative sentences (or phrases) by the total number of the sentences (or phrases) in the collection. Furthermore, the existing approach automatically finds important sentences (or phrases) including the positive and negative meaning to/against the product. As a motivated example, given a product like Sonata made by Hyundai Motors, customers often want to see the summary note including what positive points are in the 'car design' aspect as well as what negative points are in thesame aspect. They also want to gain more useful information regarding other aspects such as 'car quality', 'car performance', and 'car service.' Such an information will enable customers to make good choice when they attempt to purchase brand-new vehicles. In addition, automobile makers will be able to figure out the preference and positive/negative points for new models on market. In the near future, the weak points of the models will be improved by the sentiment analysis. For this, the existing approach computes the sentiment score of each sentence (or phrase) and then selects top-k sentences (or phrases) with the highest positive and negative scores. However, the existing approach has several shortcomings and is limited to apply to real applications. The main disadvantages of the existing approach is as follows: (1) The main aspects (e.g., car design, quality, performance, and service) to a product (e.g., Hyundai Sonata) are not considered. Through the sentiment analysis without considering aspects, as a result, the summary note including the positive and negative ratios of the product and top-k sentences (or phrases) with the highest sentiment scores in the entire corpus is just reported to customers and car makers. This approach is not enough and main aspects of the target product need to be considered in the sentiment analysis. (2) In general, since the same word has different meanings across different domains, the sentiment lexicon which is proper to each domain needs to be constructed. The efficient way to construct the sentiment lexicon per domain is required because the sentiment lexicon construction is labor intensive and time consuming. To address the above problems, in this article, we propose a novel product reputation mining algorithm that (1) extracts topics hidden in review documents written by customers; (2) mines main aspects based on the extracted topics; (3) measures the positive and negative ratios of the product using the aspects; and (4) presents the digest in which a few important sentences with the positive and negative meanings are listed in each aspect. Unlike the existing approach, using hidden topics makes experts construct the sentimental lexicon easily and quickly. Furthermore, reinforcing topic semantics, we can improve the accuracy of the product reputation mining algorithms more largely than that of the existing approach. In the experiments, we collected large review documents to the domestic vehicles such as K5, SM5, and Avante; measured the positive and negative ratios of the three cars; showed top-k positive and negative summaries per aspect; and conducted statistical analysis. Our experimental results clearly show the effectiveness of the proposed method, compared with the existing method.

• Journal of Internet Computing and Services
• /
• v.21 no.4
• /
• pp.25-34
• /
• 2020

In the current medical information system, a system environment is constructed in which Biometric data generated by using IoT or medical equipment connected to a patient can be stored in a medical information server and monitored at the same time. Also, the patient's biometric data, medical information, and personal information after simple authentication using only the ID / PW via the mobile terminal of the medical staff are easily accessible. However, the method of accessing these medical information needs to be improved in the dimension of protecting patient's personal information, and provides a quick authentication system for first aid. In this paper, we implemented an automatic authentication system based on the patient's situation and evaluated its performance. Patient's situation was graded into normal and emergency situation, and the situation of the patient was determined in real time using incoming patient biometric data from the ward. If the patient's situation is an emergency, an emergency message including an emergency code is send to the mobile terminal of the medical staff, and they attempted automatic authentication to access the upper medical information of the patient. Automatic authentication is a combination of user authentication(ID/PW, emergency code) and mobile terminal authentication(medical staff's role, working hours, work location). After user authentication, mobile terminal authentication is proceeded automatically without additional intervention by medical staff. After completing all authentications, medical staffs get authorization according to the role of medical staffs and patient's situations, and can access to the patient's graded medical information and personal information through the mobile terminal. We protected the patient's medical information through limited medical information access by the medical staff according to the patient's situation, and provided an automatic authentication without additional intervention in an emergency situation. We performed performance evaluation to verify the performance of the implemented automatic authentication system.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.1
• /
• pp.95-107
• /
• 2017

In this study, a preliminary study was undertaken for development of a tunnel incident automatic detection system based on a machine learning algorithm which is to detect a number of incidents taking place in tunnel in real time and also to be able to identify the type of incident. Two road sites where CCTVs are operating have been selected and a part of CCTV images are treated to produce sets of training data. The data sets are composed of position and time information of moving objects on CCTV screen which are extracted by initially detecting and tracking of incoming objects into CCTV screen by using a conventional image processing technique available in this study. And the data sets are matched with 6 categories of events such as lane change, stoping, etc which are also involved in the training data sets. The training data are learnt by a resilience neural network where two hidden layers are applied and 9 architectural models are set up for parametric studies, from which the architectural model, 300(first hidden layer)-150(second hidden layer) is found to be optimum in highest accuracy with respect to training data as well as testing data not used for training. From this study, it was shown that the highly variable and complex traffic and incident features could be well identified without any definition of feature regulation by using a concept of machine learning. In addition, detection capability and accuracy of the machine learning based system will be automatically enhanced as much as big data of CCTV images in tunnel becomes rich.

• Korean Journal of Soil Science and Fertilizer
• /
• v.31 no.2
• /
• pp.170-176
• /
• 1998

Nitrogen and phosphorus loads from an agricultural watershed of the Yulmun-chon tributary in the Buk-Han River Basin were quantified based on total amounts of water stream flow. The water quality and soil loss were estimated. Levels of the stream were recorded automatically using the water level meter. The flow velocities, along with the cross-sectional areas of the riverbed, were measured to estimate total amounts of water flow at three monitoring sites in this tributary. Water samples were collected at nine sites with two weeks interval from May to August and analyzed for the water quality parameters. Amounts of soil loss were estimated by the USLE. The size of the Yulmunchon watershed was 3,210 ha, of which paddy and upland soil areas were composed about 41%. The total amounts of soil loss from the watershed areas were estimated to be $13,273Mg\;year^{-1}$, showing 53%, 46% and 0.7% of the soil loss ratio from upland, forest, and paddy areas, respectively. Electrical conductivities and Nitrogen concentrations of the stream water were higher in the lower watershed area than in the upper area. Increments of N were higher for $NO_3-N$ than $NH_4-N$. Nitrate nitrogen was the major N form to pollute the water due to the agricultural activity. Total runoff was about 72% of the total precipitation in the watershed. The maximum loads of T-N and T-P due to the runoff were estimated to be 1,500 and $5kg\;day^{-1}$, respectively. Concentrations of $NO_3-N$ and $NH_4-N$ in the runoff were 13.5 and 1.8 times higher than those in precipitation. The N loads were mainly from soil loss, application of fertilizer, and livestock wastes, which were 52% of total N load. Results demonstrated that reduction of fertilizer use and the soil loss would be essential for water quality protection of the agricultural watershed.

• The Journal of Korean Society for Radiation Therapy
• /
• v.28 no.1
• /
• pp.77-86
• /
• 2016

Purpose : When a radiation treatment, there is an attenuation by Carbon Fiber Couch. In this study, we tried to evaluate the usability of the Varian Standard Couch(VSC) by modeling with Treatment Planning System (TPS) Materials and Methods : VSC was scanned by CBCT(Cone Beam Computed Tomography) of the Linac(Clinac IX, VARIAN, USA), following the three conditions of VSC, Side Rail OutGrid(SROG), Side Rail InGrid(SRIG), Side Rail In OutSpine Down Bar(SRIOS). After scan, the data was transferred to TPS and modeled by contouring Side Rail, Side Bar Upper, Side Bar Lower, Spine Down Bar automatically. We scanned the Cheese Phantom(Middelton, USA) using Computed Tomography(Light Speed RT 16, GE, USA) and transfer the data to TPS, and apply VSC modeled previously with TPS to it. Dose was measured at the isocenter of Ion Chamber(A1SL, Standard imaging, USA) in Cheese Phantom using 4 and 10 MV radiation for every $5^{\circ}$ gantry angle in a different filed size($3{\times}3cm^2$, $10{\times}10cm^2$) without any change of MU(=100), and then we compared the calculated dose and measured dose. Also we included dose at the $127^{\circ}$ in SRIG to compare the attenuation by Side Bar Upper. Results : The density of VSC by CBCT in TPS was $0.9g/cm^3$, and in the case of Spine Down Bar, it was $0.7g/cm^3$. The radiation was attenuated by 17.49%, 16.49%, 8.54%, and 7.59% at the Side Rail, Side Bar Upper, Side Bar Lower, and Spine Down Bar. For the accuracy of modeling, calculated dose and measured dose were compared. The average error was 1.13% and the maximum error was 1.98% at the $170^{\circ}beam$ crossing the Spine Down Bar. Conclusion : To evaluate the usability for the VSC modeled by TPS, the maximum error was 1.98% as a result of compassion between calculated dose and measured dose. We found out that VSC modeling helped expect the dose, so we think that it will be helpful for the more accurate treatment.