• Journal of Korean Institute of Industrial Engineers
• /
• v.43 no.3
• /
• pp.192-202
• /
• 2017

This study develops a text spam filtering system for Facebook based on two variable categories: keywords learned from Instagram and meta-information of Facebook posts. Since there is no explicit labels for spam/ham posts, we utilize hash tags in Instagram to train classification models. In addition, the filtering accuracy is enhanced by considering meta-information of Facebook posts. To verify the proposed filtering system, we conduct an empirical experiment based on a total of 1,795,067 and 761,861 Facebook and Instagram documents, respectively. Employing random forest as a base classification algorithm, experimental result shows that the proposed filtering system yield 99% and 98% in terms of filtering accuracy and F1-measure, respectively. We expect that the proposed filtering scheme can be applied other web services suffering from massive spam posts but no explicit spam labels are available.

• 한국전산유체공학회:학술대회논문집
• /
• 2008.03b
• /
• pp.634-637
• /
• 2008

A large eddy simulation with an explicit filter on unstructured mesh is presented. The flow filed is semi-implicitly marched by a fractional step method. Spatial discretization of the solver is designed to guarantee the second order accuracy. An isotropic explicit filter is adopted for measuring the level of subgrid scale velocity fluctuation. The filter is linearity-preserving and has second order commutation error. The developed subgrid scale model is basically eddy viscosity model which depends on the explicitly filtered fields and needs no additional ad hoc wall treatment, such as van Driest damping function. For the validation, the flows in a channel and a pipe are calculated and compared to experimental data and numerical results in the literature.

• Journal of Information Technology Services
• /
• v.13 no.2
• /
• pp.173-184
• /
• 2014

As social network services has become one of the most successful web-based business, recommendation in social network sites that assist people to choose various products and services is also widely adopted. Collaborative Filtering is one of the most widely adopted recommendation approaches, but recommendation technique that use explicit or implicit social network information from social networks has become proposed in recent research works. In this paper, we reviewed and compared research works about recommendation using social network analysis and collaborative filtering in social network sites. As the results of the analysis, we suggested the trends and implications for future research of recommendation in SNSs. It is expected that graph-based analysis on the semantic social network and systematic comparative analysis on the performances of social filtering and collaborative filtering are required.

• Proceedings of the IEEK Conference
• /
• 2003.11b
• /
• pp.175-178
• /
• 2003

Two defects have been pointed out in existing user-based collaborative filtering such as sparsity and scalability, and the research has been also made progress, which tries to improve these defects using item-based collaborative filtering. Actually there were many results, but the problem of sparsity still remains because of being based on an explicit data. In addition, the issue has been pointed out. which attributes of item arenot reflected in the recommendation. This paper suggests a recommendation method using nave Bayesian algorithm in hybrid user and item-based collaborative filtering to improve above-mentioned defects of existing item-based collaborative filtering. This method generates a similarity table for each user and item, then it improves the accuracy of prediction and recommendation item using naive Bayesianalgorithm. It was compared and evaluated with existing item-based collaborative filtering technique to estimate the accuracy.

• 한국전산유체공학회:학술대회논문집
• /
• 2007.04a
• /
• pp.41-44
• /
• 2007

A large eddy simulation method with unstructured mesh is presented. Two explicit filtering procedures are adopted for reducing the aliasing error of the nonlinear convective term and measuring the level of subgrid scale velocity fluctuation, respectively. The developed subgrid scale model is basically an eddy viscosity model which depends on both local velocity fluctuation level and local grid scale. As a validation problem, the flows around a sphere of several Reynolds numbers are simulated and some characteristic quantities are compared to experimental data and numerical results in the literature.

• International Journal of Control, Automation, and Systems
• /
• v.4 no.6
• /
• pp.697-704
• /
• 2006

The paper is concerned with $H_{\infty}$ filtering for descriptor systems. A necessary and sufficient condition is established in terms of linear matrix inequalities(LMIs) for the existence of normal filters such that the error systems are admissible and the transfer function from the disturbance to the filtering error output satisfies a prescribed $H_{\infty}$-norm bound constraint. When these LMIs are feasible, an explicit parameterization expression of all desired normal filter is given. All these results are yielded without decomposing the original descriptor systems, which makes the filter design procedure simple and direct. Finally, a numerical example is derived to demonstrate the applicability of the proposed approach.

• International Journal of Control, Automation, and Systems
• /
• v.5 no.2
• /
• pp.170-183
• /
• 2007

This paper presents a delay-dependent approach to robust filtering for linear parameter-varying (LPV) systems with discrete and distributed time-invariant delays in the states and outputs. It is assumed that the state-space matrices affinely depend on parameters that are measurable in real-time. Some new parameter-dependent delay-dependent stability conditions are established in terms of linear matrix inequalities (LMIs) such that the filtering process remains asymptotically stable and satisfies a prescribed $H_{\infty}$ performance level. Using polynomially parameter-dependent quadratic (PPDQ) functions and some Lagrange multiplier matrices, we establish the parameter-independent delay-dependent conditions with high precision under which the desired robust $H_{\infty}$ filters exist and derive the explicit expression of these filters. A numerical example is provided to demonstrate the validity of the proposed design approach.

• 한국전산유체공학회:학술대회논문집
• /
• 2006.10a
• /
• pp.106-109
• /
• 2006

A large eddy simulation with explicit filters on unstructured mesh is presented. Two explicit filters are adopted for reducing the aliasing error of the nonlinear convective term and measuring the level of subgrid scale velocity fluctuation, respectively. The developed subgrid scale model is basically eddy viscosity model which depends on the explicitly filtered fields and needs no additional ad hoc wall treatment such as van Driest damping function. As a validation problem, the flows around a sphere at several Reynolds numbers, including laminar and turbulent regimes, are calculated and compared to experimental data and numerical results in the literature.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.361-362
• /
• 2006

Magnetic Flux Leakage (MFL) inspection is a general non-destructive testing (NDT) method to detect the corrosion of natural gas pipelines. Currently, it is subjectively analyzed by trained analysts. In spite of investing much time and human resources, the inspection results may be different according to the analysts' expertise. So, many gas suppliers are keenly interested in the automation of the interpretation process. This paper presents a Gaussian variance filtering method of MFL signals, which is taken from MFL pigging of underground pipelines. In the proposed algorithm the original MFL signals are filtered by multiple Gaussians with different variance. Experimental results show that this approach does not need to align bias and to use explicit noise reduction algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.5
• /
• pp.2381-2399
• /
• 2019

Traditional recommendation algorithms on Collaborative Filtering (CF) mainly focus on the rating prediction with explicit ratings, and cannot be applied to the top-N recommendation with implicit feedbacks. To tackle this problem, we propose a new collaborative filtering approach namely Maximize MAP with Matrix Factorization (MFMAP). In addition, in order to solve the problem of non-smoothing loss function in learning to rank (LTR) algorithm based on pairwise, we also propose a smooth MAP measure which can be easily implemented by standard optimization approaches. We perform experiments on three different datasets, and the experimental results show that the performance of MFMAP is significantly better than other recommendation approaches.