• The KIPS Transactions:PartA
• /
• v.9A no.3
• /
• pp.295-300
• /
• 2002

In this paper, we apply the 3-dimension algorithm to the random interleaver and s-random interleaver and analyze the performance of the turbo code system with random interleaver (or s-random interleaver). In general, the performance of interleaver is determined by minimum distance between neighbor data, thus we could improve the performance of interleaver by increasing the distance of the nearest data. The interleaver using 3-dimension algorithm has longer minimum distance and average distance compared to existing random-interleaver (s-random interleaver) because the output data is generated randomly from 3-dimension storage. To verify and compare the performance of our proposed system, the computer simulations have been performed in turbo code system under gaussian noise environment.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.4 s.310
• /
• pp.50-57
• /
• 2006

In Electronic Commerce, the latest most of the personalized recommender systems have applied to the collaborative filtering technique. This method calculates the weight of similarity among users who have a similar preference degree in order to predict and recommend the item which hits to propensity of users. In this case, we commonly use Pearson Correlation Coefficient. However, this method is feasible to calculate a correlation if only there are the items that two users evaluated a preference degree in common. Accordingly, the accuracy of prediction falls. The weight of similarity can affect not only the case which predicts the item which hits to propensity of users, but also the performance of the personalized recommender system. In this study, we verify the improvement of the prediction accuracy through an experiment after observing the rule of the weight of similarity applying Vector similarity, Entropy, Inverse user frequency, and Default voting of Information Retrieval field. The result shows that the method combining the weight of similarity using the Entropy with Default voting got the most efficient performance.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.4
• /
• pp.116-123
• /
• 2009

Feature point matching, which is finding the corresponding points from two images with different viewpoint, has been used in various vision-based applications and the demand for the real-time operation of the matching is increasing these days. This paper presents a real-time feature point matching method by using a local descriptor derived by Zernike moments. From an input image, we find a set of feature points by using an existing fast corner detection algorithm and compute a local descriptor derived by Zernike moments at each feature point. The local descriptor based on Zernike moments represents the properties of the image patch around the feature points efficiently and is robust to rotation and illumination changes. In order to speed up the computation of Zernike moments, we compute the Zernike basis functions with fixed size in advance and store them in lookup tables. The initial matching results are acquired by an Approximate Nearest Neighbor (ANN) method and false matchings are eliminated by a RANSAC algorithm. In the experiments we confirmed that the proposed method matches the feature points in images with various transformations in real-time and outperforms existing methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.7
• /
• pp.1518-1524
• /
• 2014

In this paper, a new method of spatial query, which is called Surround Search (SuSe) is suggested. This method makes it possible to search for the closest spatial object of interest to the user from a query point. SuSe is differentiated from the existing spatial object query schemes, because it locates the closest spatial object of interest around the query point. While SuSe searches the surroundings, the spatial object is saved on an R-tree, and MINDIST, the distance between the query location and objects, is measured by considering an angle that the existing spatial object query methods have not previously considered. The angle between targeted-search objects is found from a query point that is hidden behind another object in order to distinguish hidden objects from them. The distinct feature of this proposed scheme is that it can search the faraway or hidden objects, in contrast to the existing method. SuSe is able to search for spatial objects more precisely, and users can be confident that this scheme will have superior performance to its predecessor.

• Journal of dental hygiene science
• /
• v.20 no.1
• /
• pp.44-50
• /
• 2020

Background: Smartphones are a modern necessity. While they are convenient to use, smartphones also have side effects such as addiction. This study assessed the relationship between smartphone use, a part of everyday life in modern society, and oral health. Methods: An analysis was conducted using 2017 Korea Youth Risk Behavior Web-based Survey data. The propensity score estimation algorithm used logistic regression and 1:1 matching algorithm using nearest-neighbor matching. After matching, a total of 15,032 participants were classified into two groups containing 7,516 teenagers each who did and did not use smartphones, respectively. Results: Comparison of oral health behaviors according to smartphone use revealed a statistically significant difference in the frequency of tooth brushing per day, use of oral hygiene products, intake of foods harmful to oral health, and experience of oral health education (p<0.05). The factors affecting oral pain experience of adolescents were examined. Compared to male participants, female participants had an odds ratio of 1.627 for oral pain (p<0.05). According to the household income level, compared to the group with higher income, the group with lower income showed higher oral pain experience (p<0.05). Oral pain experience was 1.601 times more frequent among teenagers using smartphones (p<0.05). Conclusion: The results of this study indicated that use of smartphones by adolescents affected their oral health. These findings indicate the need for improved oral health management through the use of effective school oral health programs and individual counseling by oral health professionals, promotion of information dissemination through public media, and development of prevention strategies.

• Journal of Digital Convergence
• /
• v.15 no.4
• /
• pp.191-198
• /
• 2017

It is needed to support intelligent customized health information service for user convenience in PHR based Personal Health Care Service Platform. In this paper, we specify an ontology-based health data model for Personal Health Care Service Platform. We also design a knowledge search algorithm that can be used to figure out similar health record by applying machine learning and data mining techniques. Axis-based mining algorithm, which we proposed, can be performed based on axis-attributes in order to improve relevance of knowledge exploration and to provide efficient search time by reducing the size of candidate item set. And K-Nearest Neighbor algorithm is used to perform to do grouping users byaccording to the similarity of the user profile. These algorithms improves the efficiency of customized information exploration according to the user 's disease and health condition. It can be useful to apply the proposed algorithm to a process of inference in the Personal Health Care Service Platform and makes it possible to recommend customized health information to the user. It is useful for people to manage smart health care in aging society.

• Journal of Digital Convergence
• /
• v.17 no.9
• /
• pp.71-78
• /
• 2019

This study aims to identify good borrowers within the context of P2P lending. P2P lending is a growing platform that allows individuals to lend and borrow money from each other. Inherent in any loans is credit risk of borrowers and needs to be considered before any lending. Specifically in the context of P2P lending, traditional models fall short and thus this study aimed to rectify this as well as explore the problem of class imbalances seen within credit risk data sets. This study implemented an over-sampling technique known as Synthetic Minority Over-sampling Technique (SMOTE). To test our approach, we implemented five benchmarking classifiers such as support vector machines, logistic regression, k-nearest neighbor, random forest, and deep neural network. The data sample used was retrieved from the publicly available LendingClub dataset. The proposed SMOTE revealed significantly improved results in comparison with the benchmarking classifiers. These results should help actors engaged within P2P lending to make better informed decisions when selecting potential borrowers eliminating the higher risks present in P2P lending.

• Advances in nano research
• /
• v.7 no.3
• /
• pp.209-221
• /
• 2019

Graphene, with impressive electronic properties, have high potential in the microelectronic field. However, graphene itself is a zero bandgap material which is not suitable for digital logic gates and its application. Thus, much focus is on graphene nanoribbons (GNRs) that are narrow strips of graphene. During GNRs fabrication process, the occurrence of defects that ultimately change electronic properties of graphene is difficult to avoid. The modelling of GNRs with defects is crucial to study the non-idealities effects. In this work, nearest-neighbor tight-binding (TB) model for GNRs is presented with three main simplifying assumptions. They are utilization of basis function, Hamiltonian operator discretization and plane wave approximation. Two major edges of GNRs, armchair-edged GNRs (AGNRs) and zigzag-edged GNRs (ZGNRs) are explored. With single vacancy (SV) defects, the components within the Hamiltonian operator are transformed due to the disappearance of tight-binding energies around the missing carbon atoms in GNRs. The size of the lattices namely width and length are varied and studied. Non-equilibrium Green's function (NEGF) formalism is employed to obtain the electronics structure namely band structure and density of states (DOS) and all simulation is implemented in MATLAB. The band structure and DOS plot are then compared between pristine and defected GNRs under varying length and width of GNRs. It is revealed that there are clear distinctions between band structure, numerical DOS and Green's function DOS of pristine and defective GNRs.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.6
• /
• pp.19-28
• /
• 2021

Nowadays, interest in health care is increasing due to Coronavirus (COVID-19), and a lot of people are doing home training as there are more difficulties in using fitness centers and public facilities that are used together. In this paper, we propose a personalized exercise recommendation algorithm using personalized propensity information to provide more accurate and meaningful exercise recommendation to home training users. Thus, we classify the data according to the criteria for obesity with a k-nearest neighbor algorithm using personal information that can represent individuals, such as eating habits information and physical conditions. Furthermore, we differentiate the exercise dataset by the level of exercise activities. Based on the neighborhood information of each dataset, we provide personalized exercise recommendations to users through a dimensionality reduction algorithm (SVD) among model-based collaborative filtering methods. Therefore, we can solve the problem of data sparsity and scalability of memory-based collaborative filtering recommendation techniques and we verify the accuracy and performance of the proposed algorithms.

• International Journal of Computer Science & Network Security
• /
• v.21 no.2
• /
• pp.148-157
• /
• 2021

The effectiveness of recommendation systems depends on the performance of the algorithms with which these systems are designed. The quality of the algorithms themselves depends on the quality of the strategies with which they were designed. These strategies differ from author to author. Thus, designing a good recommendation system means implementing the good strategies. It's in this context that several research works have been proposed on various strategies applied to algorithms to meet the needs of recommendations. Researchers are trying indefinitely to address this objective of seeking the qualities of recommendation algorithms. In this paper, we propose a new algorithm for recommending learning items. Learner performance predictions and collaborative recommendation methods are used as strategies for this algorithm. The proposed performance prediction model is based on convolutional neural networks (CNN). The results of the performance predictions are used by the proposed recommendation algorithm. The results of the predictions obtained show the efficiency of Deep Learning compared to the k-nearest neighbor (k-NN) algorithm. The proposed recommendation algorithm improves the recommendations of the learners' learning items. This algorithm also has the particularity of dissuading learning items in the learner's profile that are deemed inadequate for his or her training.