• Journal of KIISE:Software and Applications
• /
• v.31 no.12
• /
• pp.1591-1601
• /
• 2004

Clustering, a technique for the analysis of the genes, organizes the patterns into groups by the similarity of the dataset and has been used for identifying the functions of the genes in the cluster or analyzing the functions of unknown gones. Since the genes usually belong to multiple functional families, fuzzy clustering methods are more appropriate than the conventional hard clustering methods which assign a sample to a group. In this paper, a Bayesian validation method is proposed to evaluate the fuzzy partitions effectively. Bayesian validation method is a probability-based approach, selecting a fuzzy partition with the largest posterior probability given the dataset. At first, the proposed Bayesian validation method is compared to the 4 representative conventional fuzzy cluster validity measures in 4 well-known datasets where foray c-means algorithm is used. Then, we have analyzed the results of Saccharomyces cell cycle expression data evaluated by the proposed method.

• Journal of Korea Society of Industrial Information Systems
• /
• v.23 no.6
• /
• pp.79-94
• /
• 2018

The purpose of this study is to specify a probabilistic tracking mechanism for customer luxury purchase implemented by hidden Markov model, Bayesian inference, customer satisfaction and net promoter score. In this paper, we have designed a probabilistic model based on customer's actual data containing purchase or non-purchase states by tracking the SPC chain : customer satisfaction -> customer referral -> purchase/non-purchase. By applying hidden Markov model and Viterbi algorithm to marketing theory, we have developed the statistical model related to probability theories and have found the best purchase pattern scenario from customer's purchase records.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.9
• /
• pp.1060-1069
• /
• 2019

Pedestrian-based camera self-calibration methods are suitable for video surveillance systems since they do not require complex calibration devices or procedures. However, using arbitrary pedestrians as calibration targets may result in poor calibration accuracy due to the unknown height of each pedestrian. To solve this problem in the real surveillance environments, this paper proposes a novel Bayesian approach. By assuming known statistics on the height of pedestrians, we construct a probabilistic model that takes into account uncertainties in both the foot/head locations and the pedestrian heights, using foot-head homology. Since solving the model directly is infeasible, we use variational Bayesian inference, an approximate inference algorithm. Accordingly, this makes it possible to estimate the height of pedestrians and to obtain accurate camera parameters simultaneously. Experimental results show that the proposed algorithm is robust to noise and provides accurate confidence in the calibration.

• The KIPS Transactions:PartD
• /
• v.13D no.3 s.106
• /
• pp.369-376
• /
• 2006

This paper presents a new method of significantly improving conventional Bayesian statistical text classifier by incorporating accelerated EM(Expectation Maximization) algorithm. EM algorithm experiences a slow convergence and performance degrade in its iterative process, especially when real online-textual documents do not follow EM's assumptions. In this study, we propose a new accelerated EM algorithm with uncertainty-based selective sampling, which is simple yet has a fast convergence speed and allow to estimate a more accurate classification model on Naive Bayesian text classifier. Experiments using the popular Reuters-21578 document collection showed that the proposed algorithm effectively improves classification accuracy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.4
• /
• pp.1200-1215
• /
• 2023

With the development of IoT and artificial intelligence, location-based services are getting more and more attention. For solving the current problem that indoor positioning error is large and generalization is poor, this paper proposes a Model Stacking Algorithm for Indoor Positioning System using WiFi fingerprinting. Firstly, we adopt a model stacking method based on Bayesian optimization to predict the location of indoor targets to improve indoor localization accuracy and model generalization. Secondly, Taking the predicted position based on model stacking as the observation value of particle filter, collaborative particle filter localization based on model stacking algorithm is realized. The experimental results show that the algorithm can control the position error within 2m, which is superior to KNN, GBDT, Xgboost, LightGBM, RF. The location accuracy of the fusion particle filter algorithm is improved by 31%, and the predicted trajectory is close to the real trajectory. The algorithm can also adapt to the application scenarios with fewer wireless access points.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.5
• /
• pp.335-342
• /
• 2016

When dynamics changes occurred in an existing Bayesian Network (BN), the related parameters embedding on the BN have to be updated to new parameters adapting to changed patterns. In this case, these parameters have to be updated with the consideration of the causalities in the BN. This research suggests a framework for updating parameters dynamically using Expectation Maximization (EM) algorithm and Harmony Search (HS) algorithm among several Meta-Heuristics techniques. While EM is an effective algorithm for estimating hidden parameters, it has a limitation that the generated solution converges a local optimum in usual. In order to overcome the limitation, this paper applies HS for tracking the global optimum values of Maximum Likelihood Estimators (MLE) of parameters. The proposed method suggests a learning and propagation framework of BN with dynamic changes for overcoming disadvantages of EM algorithm and converging a global optimum value of MLE of parameters.

• Korean Journal of Remote Sensing
• /
• v.25 no.5
• /
• pp.455-464
• /
• 2009

Lee(2009) proposed the boundary-adaptive despeckling method using a Bayesian model which is based on the lognormal distribution for image intensity and a Markov random field(MRF) for image texture. This method employs the Point-Jacobian iteration to obtain a maximum a posteriori(MAP) estimate of despeckled imagery. The boundary-adaptive algorithm is designed to use less information from more distant neighbors as the pixel is closer to boundary. It can reduce the possibility to involve the pixel values of adjacent region with different characteristics. The boundary-adaptive scheme was comprehensively evaluated using simulation data and the effectiveness of boundary adaption was proved in Lee(2009). This study, as an extension of Lee(2009), has suggested a modified iteration algorithm of MAP estimation to enhance computational efficiency and to combine classification. The experiment of simulation data shows that the boundary-adaption results in yielding clear boundary as well as reducing error in classification. The boundary-adaptive scheme has also been applied to high resolution Terra-SAR data acquired from the west coast of Youngjong-do, and the results imply that it can improve analytical accuracy in SAR application.

• The Korean Journal of Applied Statistics
• /
• v.27 no.4
• /
• pp.589-603
• /
• 2014

When consecutive data follows different distributions(depending on the time interval) change-point detection infers where the changes occur first and then finds further inferences for each sub-interval. In this paper, we investigate the Bayesian detection of multiple change points. Utilizing the reversible jump MCMC, we can explore parameter spaces with unknown dimensions. In particular, we consider a model where the signal is a piecewise linear function. For the Bayesian inference, we propose a new Bayesian structure and build our own MCMC algorithm. Through the simulation study and the real data analysis, we verified the performance of our method.

• Structural Engineering and Mechanics
• /
• v.63 no.6
• /
• pp.825-835
• /
• 2017

Significant improvements to methodologies on structural damage detection (SDD) have emerged in recent years. However, many methods are related to inversion computation which is prone to be ill-posed or ill-conditioning, leading to low-computing efficiency or inaccurate results. To explore a more accurate solution with satisfactory efficiency, a PSO-INM algorithm, combining particle swarm optimization (PSO) algorithm and an improved Nelder-Mead method (INM), is proposed to solve multi-sample objective function defined based on Bayesian inference in this study. The PSO-based algorithm, as a heuristic algorithm, is reliable to explore solution to SDD problem converted into a constrained optimization problem in mathematics. And the multi-sample objective function provides a stable pattern under different level of noise. Advantages of multi-sample objective function and its superior over traditional objective function are studied. Numerical simulation results of a two-storey frame structure show that the proposed method is sensitive to multi-damage cases. For further confirming accuracy of the proposed method, the ASCE 4-storey benchmark frame structure subjected to single and multiple damage cases is employed. Different kinds of modal identification methods are utilized to extract structural modal data from noise-contaminating acceleration responses. The illustrated results show that the proposed method is efficient to exact locations and extents of induced damages in structures.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.4
• /
• pp.202-208
• /
• 2015

In this study, we propose a new inference algorithm for a multiclass Gaussian process classification model using a variational EM framework and the Laplace approximation (LA) technique. This is performed in two steps, called expectation and maximization. First, in the expectation step (E-step), using Bayes' theorem and the LA technique, we derive the approximate posterior distribution of the latent function, indicating the possibility that each observation belongs to a certain class in the Gaussian process classification model. In the maximization step, we compute the maximum likelihood estimators for hyper-parameters of a covariance matrix necessary to define the prior distribution of the latent function by using the posterior distribution derived in the E-step. These steps iteratively repeat until a convergence condition is satisfied. Moreover, we conducted the experiments by using synthetic data and Iris data in order to verify the performance of the proposed algorithm. Experimental results reveal that the proposed algorithm shows good performance on these datasets.