• Journal of Broadcast Engineering
• /
• v.17 no.1
• /
• pp.73-80
• /
• 2012

Recently, medical equipments are developed and used for diagnosis or studies. In addition, demand of techniques which automatically deal with three dimensional medical images obtained from the medical equipments is growing. One of the techniques is automatic bone segmentation which is expected to enhance the diagnosis efficiency of osteoporosis, fracture, and other bone diseases. Although various researches have been proposed to solve it, they are unable to be used in practice since a size of the medical data is large and there are many low contrast boundaries with other tissues. In this paper, we present a fast and accurate automatic framework for bone segmentation based on multi-resolutions. On a low resolution step, a position of the bone is roughly detected using constrained branch and mincut which find the optimal template from the training set. Then, the segmentation and the registration are iteratively conducted on the multiple resolutions. To evaluate the performance of the proposed method, we make an experiment with femur and tibia from 50 test knee magnetic resonance images using 100 training set. The proposed method outperformed the constrained branch and mincut in aspect of segmentation accuracy and implementation time.

• (The) Korean Journal of Educational Psychology
• /
• v.26 no.4
• /
• pp.1225-1248
• /
• 2012

The present study explored how ADHD assessment, identification, and diagnosis were conducted in research through an overview of research papers on ADHD in the last 10 years. The collected studies were categorized and analyzed by topics including data collection settings, assessment and identification, coexistence with other disabilities, considerable variables throughout evaluation, and biological basis. They were categorized and analyzed according to the identification methods, the number of assessment(s) and the number of informant(s). The results were as follows: First, the assessment and identifying studies on children with ADHD were excessively biased toward clinical settings. Second, the majority of the previous studies explored more the development or validation of tools for the assessment and identifying of ADHD than the other topics. Finally, a high preference for the use of a multiple assessment method in identifying ADHD was found. However, considering methodological aspects, there was a lack of practical application of multi-step process such as including a personal interview, reviewing school records or direct observing rating criteria. Considering these results, we discussed an urgent need for the diagnosis and identification guidelines of ADHD for teachers to effectively identifying ADHD children at schools. The implications of school-based ADHD assessment and diagnosis research were suggested.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.3
• /
• pp.166-171
• /
• 2023

Efficient energy management is a very important factor in sensor networks with limited resources, and cluster techniques have been studied a lot in this respect. However, a problem may occur in which energy use of the cluster header is concentrated, and when the cluster header is not evenly distributed over the entire area but concentrated in a specific area, the transmission distance of the cluster members may be large or very uneven. The transmission distance can be directly related to the problem of energy consumption. Since the energy of a specific node is quickly exhausted, the lifetime of the sensor network is shortened, and the efficiency of the entire sensor network is reduced. Thus, balanced energy consumption of sensor nodes is a very important research task. In this study, factors for balanced energy consumption by cluster headers and sensor nodes are analyzed, and a balancing distribution clustering method in which cluster headers are balanced distributed throughout the sensor network is proposed. The proposed cluster method uses multi-hop routing to reduce energy consumption of sensor nodes due to long-distance transmission. Existing multi-hop cluster studies sets up a multi-hop cluster path through a two-step process of cluster setup and routing path setup, whereas the proposed method establishes a hierarchical cluster routing path in the process of selecting cluster headers to minimize the overhead of control messages.

• Journal of Radiation Protection and Research
• /
• v.42 no.2
• /
• pp.91-97
• /
• 2017

Background: A gamma energy identifying algorithm using spectral decomposition combined with smoothing method was suggested to confirm the existence of the artificial radio isotopes. The algorithm is composed by original pattern recognition method and smoothing method to enhance the performance to identify gamma energy of radiation sensors that have low energy resolution. Materials and Methods: The gamma energy identifying algorithm for the compact radiation sensor is a three-step of refinement process. Firstly, the magnitude set is calculated by the original spectral decomposition. Secondly, the magnitude of modeling error in the magnitude set is reduced by the smoothing method. Thirdly, the expected gamma energy is finally decided based on the enhanced magnitude set as a result of the spectral decomposition with the smoothing method. The algorithm was optimized for the designed radiation sensor composed of a CsI (Tl) scintillator and a silicon pin diode. Results and Discussion: The two performance parameters used to estimate the algorithm are the accuracy of expected gamma energy and the number of repeated calculations. The original gamma energy was accurately identified with the single energy of gamma radiation by adapting this modeling error reduction method. Also the average error decreased by half with the multi energies of gamma radiation in comparison to the original spectral decomposition. In addition, the number of repeated calculations also decreased by half even in low fluence conditions under $10^4$ ($/0.09cm^2$ of the scintillator surface). Conclusion: Through the development of this algorithm, we have confirmed the possibility of developing a product that can identify artificial radionuclides nearby using inexpensive radiation sensors that are easy to use by the public. Therefore, it can contribute to reduce the anxiety of the public exposure by determining the presence of artificial radionuclides in the vicinity.

• Journal of Digital Contents Society
• /
• v.12 no.1
• /
• pp.1-9
• /
• 2011

JPEG2000 offers the technique which compresses the interested regions with higher quality than the background. It is called by an ROI(Region-of-Interest) coding method. In this paper, we use images including the human faces, which are processed uppermost and compressed with high quality. The proposed method consists of 2 steps. The first step extracts some faces and the second one is ROI coding. To extract the faces, the method cuts or scale-downs some regions with $20{\times}20$ window pixels for all the pixels of the image, and after preprocessing, recognizes the faces using neural networks. Each extracted region is identified by ROI mask and then ROI-coded using Maxshift method. After then, the image is compressed and saved using EBCOT. The existing methods searched the ROI by edge distributions. On the contrary, the proposed method uses human intellect. And the experiment shows that the method is sufficiently useful with images having several human faces.

• Database Research
• /
• v.34 no.3
• /
• pp.148-158
• /
• 2018

The optical character recognition (OCR) is a technique to extract and recognize texts from images. It is an important preprocessing step in data analysis since most actual text information is embedded in images. Many OCR engines have high recognition accuracy for images where texts are clearly separable from background, such as white background and black lettering. However, they have low recognition accuracy for images where texts are not easily separable from complex background. To improve this low accuracy problem with complex images, it is necessary to transform the input image to make texts more noticeable. In this paper, we propose a method to segment an input image into text lines to enable OCR engines to recognize each line more efficiently, and to determine the final output by comparing the recognition rates of CLAHE module and Two-step module which distinguish texts from background regions based on image processing techniques. Through thorough experiments comparing with well-known OCR engines, Tesseract and Abbyy, we show that our proposed method have the best recognition accuracy with complex background images.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.39-54
• /
• 2013

Recent explosive increase of electronic commerce provides many advantageous purchase opportunities to customers. In this situation, customers who do not have enough knowledge about their purchases, may accept product recommendations. Product recommender systems automatically reflect user's preference and provide recommendation list to the users. Thus, product recommender system in online shopping store has been known as one of the most popular tools for one-to-one marketing. However, recommender systems which do not properly reflect user's preference cause user's disappointment and waste of time. In this study, we propose a novel recommender system which uses data mining and multi-model ensemble techniques to enhance the recommendation performance through reflecting the precise user's preference. The research data is collected from the real-world online shopping store, which deals products from famous art galleries and museums in Korea. The data initially contain 5759 transaction data, but finally remain 3167 transaction data after deletion of null data. In this study, we transform the categorical variables into dummy variables and exclude outlier data. The proposed model consists of two steps. The first step predicts customers who have high likelihood to purchase products in the online shopping store. In this step, we first use logistic regression, decision trees, and artificial neural networks to predict customers who have high likelihood to purchase products in each product group. We perform above data mining techniques using SAS E-Miner software. In this study, we partition datasets into two sets as modeling and validation sets for the logistic regression and decision trees. We also partition datasets into three sets as training, test, and validation sets for the artificial neural network model. The validation dataset is equal for the all experiments. Then we composite the results of each predictor using the multi-model ensemble techniques such as bagging and bumping. Bagging is the abbreviation of "Bootstrap Aggregation" and it composite outputs from several machine learning techniques for raising the performance and stability of prediction or classification. This technique is special form of the averaging method. Bumping is the abbreviation of "Bootstrap Umbrella of Model Parameter," and it only considers the model which has the lowest error value. The results show that bumping outperforms bagging and the other predictors except for "Poster" product group. For the "Poster" product group, artificial neural network model performs better than the other models. In the second step, we use the market basket analysis to extract association rules for co-purchased products. We can extract thirty one association rules according to values of Lift, Support, and Confidence measure. We set the minimum transaction frequency to support associations as 5%, maximum number of items in an association as 4, and minimum confidence for rule generation as 10%. This study also excludes the extracted association rules below 1 of lift value. We finally get fifteen association rules by excluding duplicate rules. Among the fifteen association rules, eleven rules contain association between products in "Office Supplies" product group, one rules include the association between "Office Supplies" and "Fashion" product groups, and other three rules contain association between "Office Supplies" and "Home Decoration" product groups. Finally, the proposed product recommender systems provides list of recommendations to the proper customers. We test the usability of the proposed system by using prototype and real-world transaction and profile data. For this end, we construct the prototype system by using the ASP, Java Script and Microsoft Access. In addition, we survey about user satisfaction for the recommended product list from the proposed system and the randomly selected product lists. The participants for the survey are 173 persons who use MSN Messenger, Daum Caf$\acute{e}$, and P2P services. We evaluate the user satisfaction using five-scale Likert measure. This study also performs "Paired Sample T-test" for the results of the survey. The results show that the proposed model outperforms the random selection model with 1% statistical significance level. It means that the users satisfied the recommended product list significantly. The results also show that the proposed system may be useful in real-world online shopping store.

• Journal of Biomedical Engineering Research
• /
• v.21 no.4
• /
• pp.333-338
• /
• 2000

In this paper, an automated segmentation algorithm is proposed for MR brain images using T1-weighted, T2-weighted, and PD images complementarily. The proposed segmentation algorithm is composed of 3 step. In the first step, cerebrum images are extracted by putting a cerebrum mask upon the three input images. In the second step, outstanding clusters that represent inner tissues of the cerebrum are chosen among 3-dimensional(3D) clusters. 3D clusters are determined by intersecting densely distributed parts of 2D histogram in the 3D space formed with three optimal scale images. Optimal scale image is made up of applying scale space filtering to each 2D histogram and searching graph structure. Optimal scale image best describes the shape of densely distributed parts of pixels in 2D histogram and searching graph structure. Optimal scale image best describes the shape of densely distributed parts of pixels in 2D histogram. In the final step, cerebrum images are segmented using FCM algorithm with its initial centroid value as the outstanding clusters centroid value. The proposed cluster's centroid accurately. And also can get better segmentation results from the proposed segmentation algorithm with multi spectral analysis than the method of single spectral analysis.

• The Journal of Korean Academy of Prosthodontics
• /
• v.45 no.5
• /
• pp.653-664
• /
• 2007

Statement of problem: The screw detorque value is a measure of the preload remaining in the screw just before detorquing. Purpose: This study evaluated the effect of different screw tightening sequences and tightening methods on detorque values for a well-fitting implant superstructure. Material and method: An implant superstructure that connected directly to four implants (Astra Tech) was fabricated on a fully edentulous mandibular acrylic resin model. Six well-fitting dental stone casts were made with a pickup impression of the superstructure from the acrylic resin model. To evaluate the effect of three screw tightening sequences (1-2-3-4, 2-4-3-1, and 2-3-1-4) and two tightening methods (2-step and 1-step) on the stability of screw joint, the detorque values for a well-fitting implant superstructure were measured twice after screw tightening using 20 Ncm. Detorque values were analyzed using multi-way analysis of variance and two-way analysis of variance at a .05 level of significance. Results: 1. The mean detorque values for three screw tightening sequences were 12.3 Ncm, 12.6 Ncm, and 12.0 Ncm, respectively. 2. The mean detorque values for two screw tightening methods were 12.0 Ncm, and 12.2 Ncm, respectively. 3. The mean of mimimum detorque values for three screw tightening sequences and for two tightening methods were 10.6 Ncm, 11.1 Ncm, 10.5 Ncm, and 9.8 Ncm, respectively. 4. No statistically significant differences among the variables of screw tightening sequence and tightening method were found (p>.05) for detorque values and for mimimum detorque values. Conclusion: Within the limitations of this study, the screw tightening sequence and tightening method did not have a significant effect on the detorque values for a well-fitting implant superstructure.

• Proceedings of the CALSEC Conference
• /
• 2002.01a
• /
• pp.107-131
• /
• 2002

Recently, it is an important problem that combines part of sale, technical development etc.. as well as function that is the multi-item and small quantity production environment and production to computer network that supports synthetic efficiency of general corporation activity in manufacturing industry. Integration production information system is developed by these requests and globalization of production system and marketing by tough international competition of various industry product need IMS(Intelligent Manufacturing System) that cope in these change. Therefore, this paper searches analysis method, problem and development way for information system of manufacture field to construct this IMS efficiently, and develops each information strategy planning establishment step, product and integral way of products which is the systematic establishment way of essential information strategy planning in efficient manufacturing information system construction. Also, this paper presents detailed system design methods of each step and templates for efficient methodology of information strategy planning to support IMS efficiently.