• KIEE International Transaction on Systems and Control
• /
• v.2D no.2
• /
• pp.97-107
• /
• 2002

In this paper, we propose the concept of orthonormalized compressed measurement for the stability analysis of discrete linear time-varying Kalman filters. Unlike previous studies that deal with the homogeneous portion of Kalman filters, the proposed Lyapunov method directly deals with the stochastically-driven system. The orthonorrmalized compressed measurement provides information on the a priori state estimate of the Kalman filter at the k-th step that is propagated from the a posteriori state estimate at the previous block of time. Since the complex multiple-step propagations of a candidate Lyapunov function with process and measurement noises can be simplified to a one-step Lyapunov propagation by the orthonormalized compressed measurement, a stochastic radius of attraction can be derived that would be impractically difficult to obtain by the conventional multiple-step Lyapunov method.

• Journal of Electrical Engineering and information Science
• /
• v.2 no.5
• /
• pp.79-88
• /
• 1997

This paper introduces a new energy function, as maximum a posteriori(MAP) estimate of binocular disparity, that can deal with both random dot stereo-gram(RDS) and natural scenes. The energy function uses phase-magnitude as features to detect only the shift for a pair of corrupted conjugate images. Also we adopted Fleet singularity that effectively detects unstable areas of image plant and thus eliminates in advance error-prone stereo mathcing. The multi-scale concept is applied to the multi laser architecture that can search the solutions systematically from coarse to fine details and thereby avoids drastically the local minima. Using mean field approximation, we obtained a compact representation that is suitable for fast computation. In this manner, the energy function satisfies major natural constraints and requirements for implementing parallel relaxation. As an experiment, the proposed algorithm is applied to RDS and natural stereo images. As a result we will see that it reveals good performance in terms of recognition errors, parallel implementation, and noise characteristics.

• Journal of Communications and Networks
• /
• v.17 no.6
• /
• pp.609-621
• /
• 2015

Recently, a variety of reduced complexity soft-in soft-output detection algorithms have been introduced for iterative detection and decoding (IDD) systems. However, it is still challenging to implement soft-in soft-output detectors for MIMO systems due to heavy burden in computational complexity. In this paper, we propose a soft detection algorithm for MIMO systems which performs close to the full dimensional joint detection, yet offers significant complexity reduction over the existing detectors. The proposed algorithm, referred to as soft-input soft-output successive group (SSG) detector, detects a subset of symbols (called a symbol group) successively using a deliberately designed preprocessing to suppress the inter-group interference. In fact, the proposed preprocessor mitigates the effect of the interfering symbol groups successively using a priori information of the undetected groups and a posteriori information of the detected groups. Simulation results on realistic MIMO systems demonstrate that the proposed SSG detector achieves considerable complexity reduction over the conventional approaches with negligible performance loss.

• ETRI Journal
• /
• v.30 no.1
• /
• pp.89-100
• /
• 2008

We consider the feature recombination technique in a multiband approach to speaker identification and verification. To overcome the ineffectiveness of conventional feature recombination in broadband noisy environments, we propose a new subband feature recombination which uses subband likelihoods and a subband reliable-feature selection technique with an adaptive noise model. In the decision step of speaker recognition, a few very low unreliable feature likelihood scores can cause a speaker recognition system to make an incorrect decision. To overcome this problem, reliable-feature selection adjusts the likelihood scores of an unreliable feature by comparison with those of an adaptive noise model, which is estimated by the maximum a posteriori adaptation technique using noise features directly obtained from noisy test speech. To evaluate the effectiveness of the proposed methods in noisy environments, we use the TIMIT database and the NTIMIT database, which is the corresponding telephone version of TIMIT database. The proposed subband feature recombination with subband reliable-feature selection achieves better performance than the conventional feature recombination system with reliable-feature selection.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.261-262
• /
• 2006

According to the previous work, various well known methods including maximum a posteriori probability classifier (MAP) and multi layer perceptron networks classifier (MLP) showed competitive results. Since even the small errors often leads to a fatal result, we investigated the method that reduces classification error perfectly by screening out some ambiguous patterns. Those ambiguous patterns can be examined by routine biopsy. We incorporated an ambiguous category in MAP and MLP. Classification results involving 216 spectra gave 100% sensitivity for the case of MLP.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.255-256
• /
• 2006

Raman spectroscopy has strong potential for providing noninvasive dermatological diagnosis of skin cancer. In this study, we investigated two classification methods with maximum a posteriori (MAP) probability and multi-layer perceptron (MLP) classification. The classification framework consists of preprocessing of Raman spectra, feature extraction, and classification. In the preprocessing step, a simple windowing method is proposed to obtain robust features. Classification results with MLP involving 216 spectra preprocessed with the proposed method gave 97.3% sensitivity, which is very promising results for automatic Basal Cell Carcinoma (BCC) detection.

• Communications for Statistical Applications and Methods
• /
• v.12 no.2
• /
• pp.531-538
• /
• 2005

In k-means clustering, we standardize variables before clustering and iterate two steps: units allocation by Euclidean sense and centroids updating. In applications to DB marketing where clusters are to be used as customer segments with similar consumption behaviors, we frequently acquire additional variables on the customers or the units through marketing campaigns a posteriori. Hence we need to modify the clusters originally formed after each campaign. The aim of this study is to propose a revision method of k-means clusters, incorporating added information by weighting clustering variables. We illustrate the proposed method in an empirical case.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.9
• /
• pp.4476-4490
• /
• 2017

The aim of image annotation is to determine labels that can accurately describe the semantic information of images. Many approaches have been proposed to automate the image annotation task while achieving good performance. However, in most cases, the semantic similarities of images are ignored. Towards this end, we propose a novel Visual-Semantic Nearest Neighbor (VS-KNN) method by collectively exploring visual and semantic similarities for image annotation. First, for each label, visual nearest neighbors of a given test image are constructed from training images associated with this label. Second, each neighboring subset is determined by mining the semantic similarity and the visual similarity. Finally, the relevance between the images and labels is determined based on maximum a posteriori estimation. Extensive experiments were conducted using three widely used image datasets. The experimental results show the effectiveness of the proposed method in comparison with state-of-the-arts methods.

• ETRI Journal
• /
• v.45 no.5
• /
• pp.899-909
• /
• 2023

In mobile communication, the most exploratory technology of fifth generation is massive multiple input multiple output (MIMO). The minimum mean square error and zero forcing based linear detectors are used in multiuser detection for MIMO single-carrier frequency division multiple access (SCFDMA). When the received signal is detected and regularization sequence is joined in the equalization of spectral null amplification, these schemes experience an error performance and the signal detection assesses an inversion of a matrix computation that grows into complexity. Ordered successive interference cancelation (OSIC) detection is considered for MIMO SC-FDMA, which uses a posteriori information to eradicate these problems in a realistic environment. To cancel the interference, sorting is preferred based on signal-to-noise ratio and log-likelihood ratio. The distinctiveness of the methodology is to predict the symbol with the lowest error probability. The proposed work is compared with the existing methods, and simulation results prove that the defined algorithm outperforms conventional detection methods and accomplishes better performance with lower complication.

• ETRI Journal
• /
• v.36 no.5
• /
• pp.721-729
• /
• 2014

We propose a novel phase-based method for single-channel speech enhancement to extract and enhance the desired signals in noisy environments by utilizing the phase information. In the method, a phase-dependent a priori signal-to-noise ratio (SNR) is estimated in the log-mel spectral domain to utilize both the magnitude and phase information of input speech signals. The phase-dependent estimator is incorporated into the conventional magnitude-based decision-directed approach that recursively computes the a priori SNR from noisy speech. Additionally, we reduce the performance degradation owing to the one-frame delay of the estimated phase-dependent a priori SNR by using a minimum mean square error (MMSE)-based and maximum a posteriori (MAP)-based estimator. In our speech enhancement experiments, the proposed phase-dependent a priori SNR estimator is shown to improve the output SNR by 2.6 dB for both the MMSE-based and MAP-based estimator cases as compared to a conventional magnitude-based estimator.