• The Journal of the Acoustical Society of Korea
• /
• v.13 no.1E
• /
• pp.64-70
• /
• 1994

Predictive neural network models are powerful speech recognition models based on a nonlinear pattern prediction. But those models suffer from poor discrimination between acoustically similar words. In this paper we propose an discriminative training algorithm for predictive neural network models. This algorithm is derived from GPD (Generalized Probabilistic Descent) algorithm coupled with MCEF(Minimum Classification Error Formulation). It allows direct minimization of a recognition error rate. Evaluation of our training algoritym on ten Korean digits shows its effectiveness by 30% reduction of recognition error.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.6
• /
• pp.94-99
• /
• 1997

This paper describes a technique of probabilistic spectral subtraction which uses the knowledge of both noise and speech so as to reduce automatic speech recognition errors in noisy environments. Spectral subtraction method estimates a noise prototype in non-speech intervals and the spectrum of clean speech is obtained from the spectrum of noisy speech by subtracting this noise prototype. Thus noise can not be suppressed effectively using a single noise prototype in case the characteristics of the noise prototype are different from those of the noise contained in input noisy speech. To modify such a drawback, multiple noise prototypes are used in probabilistic subtraction method. In this paper, the probabilistic characteristics of noise and the knowledge of speech which is embedded in hidden Markov models trained in clean environments are used to suppress noise. Futhermore, dynamic feature parameters are considered as well as static feature parameters for effective noise suppression. The proposed method reduced error rates in the recognition of 50 Korean words. The recognition rate was 86.25% with the probabilistic subtraction, 72.75% without any noise suppression method and 80.25% with spectral subtraction at SNR(Signal-to-Noise Ratio) 10 dB.

• Korean Journal of Construction Engineering and Management
• /
• v.8 no.5
• /
• pp.71-79
• /
• 2007

It is common that the analysis of VE/LCC is performed in design phase of quay wall structures. The analysis is mainly executed based on experience and engineering sense of expert considering the selection of construction method, construction and maintenance cost. Recently there are increasing demands on the analysis that includes uncertainty and vulnerability of input parameters, for this purpose, fuzzy reliability based probabilistic VE/LCC analysis model for quay wall structures is suggested. In VE/LCC analysis for quay wall structures, the application of probabilistic analysis method give very similar results compare with those of deterministic analysis method. It is anticipated that the methodology proposed in this paper can also be utilized in the design and maintenance phase of other facilities where decision making is made for the probabilistic life cycle cost and value analysis.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.8
• /
• pp.2895-2912
• /
• 2014

Content-based image retrieval has been the most important technique for managing huge amount of images. The fundamental yet highly challenging problem in this field is how to measure the content-level similarity based on the low-level image features. The primary difficulties lie in the great variance within images, e.g. background, illumination, viewpoint and pose. Intuitively, an ideal similarity measure should be able to adapt the data distribution, discover and highlight the content-level information, and be robust to those variances. Motivated by these observations, we in this paper propose a probabilistic similarity learning approach. We first model the distribution of low-level image features and derive the free energy kernel (FEK), i.e., similarity measure, based on the distribution. Then, we propose a learning approach for the derived kernel, under the criterion that the kernel outputs high similarity for those images sharing the same class labels and output low similarity for those without the same label. The advantages of the proposed approach, in comparison with previous approaches, are threefold. (1) With the ability inherited from probabilistic models, the similarity measure can well adapt to data distribution. (2) Benefitting from the content-level hidden variables within the probabilistic models, the similarity measure is able to capture content-level cues. (3) It fully exploits class label in the supervised learning procedure. The proposed approach is extensively evaluated on two well-known databases. It achieves highly competitive performance on most experiments, which validates its advantages.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.33 no.4
• /
• pp.1651-1664
• /
• 2013

Precise analysis on deterioration processes of road pavements is not so simple matter due to severe uncertainty originated from a lot of explanatory variables engaged in. For those reasons, most analytical models for pavement deterioration prediction have often preferred to probabilistic approaches than deterministic models. However, the general probabilistic approaches that treat overall characteristics of population or entire sample would not be suitable for providing detail or localized information on their changing process. Considering the aspects, this paper aimed to suggest a stochastic disaggregation method to analyze the localized deterioration speeds and its variances changed by time and condition states. In addition, life expectancies and their uncertainty were estimated by probabilistic algorithm using the disaggregated stochastic process. For an empirical study, pavement inspection data (crack) accumulated from 2003 to 2010 from Korean national highway network was applied. This study can contribute to securing reliability of life cycle cost analysis, which is one of the primary analyses in road asset management, with much advanced deterioration forecasting functions. In addition, it would be meaningful trials as fundamental research for preventive maintenance strategy that demands essential understanding on changing process of the deterioration speed of pavement.

• Journal of KIISE:Software and Applications
• /
• v.35 no.2
• /
• pp.128-136
• /
• 2008

Recognition of parallel structure at early stage of sentence parsing can reduce the complexity of parsing. In this paper, we propose an unsupervised language-independent probabilistic model for recongition of parallel noun structures. The proposed model is based on the idea of swapping constituents, which replies the properties of symmetry (two or more identical constituents are repeated) and of reversibility (the order of constituents is inter-changeable) in parallel structures. The non-symmetric patterns that cannot be captured by the general symmetry rule are resolved additionally by the modifier information. In particular this paper shows how the proposed model is applied to recognize Korean parallel noun phrases connected by "wa/kwa" particle. Our model is compared with other models including supervised models and performs better on recongition of parallel noun phrases.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.3
• /
• pp.224-232
• /
• 2015

In order to develop an active safety system which avoids or mitigates collisions with preceding vehicles such as autonomous emergency braking (AEB), accurate state estimation of the nearby vehicles is very important. In this paper, an algorithm is proposed using 3 dynamic models to better estimate the state of a vehicle which has various dynamic patterns in both longitudinal and lateral direction. In particular, the proposed algorithm is based on the Interacting Multiple Model (IMM) method which employs three different dynamic models, in cruise mode, lateral maneuver mode and longitudinal maneuver mode. In addition, a Probabilistic Data Association Filter (PDAF) is utilized as a data association algorithm which can improve the reliability of the measurement under a clutter environment. In order to verify the performance of the proposed method, it is simulated in comparison with a Kalman filter method which employs a single dynamic model. Finally, the proposed method is validated using radar data obtained from the field test in the proving ground.

• Nuclear Engineering and Technology
• /
• v.49 no.2
• /
• pp.349-359
• /
• 2017

During the past 25 years, in the context of probabilistic safety assessment, efforts have been directed towards establishment of comprehensive pipe failure event databases as a foundation for exploratory research to better understand how to effectively organize a piping reliability analysis task. The focused pipe failure database development efforts have progressed well with the development of piping reliability analysis frameworks that utilize the full body of service experience data, fracture mechanics analysis insights, expert elicitation results that are rolled into an integrated and risk-informed approach to the estimation of piping reliability parameters with full recognition of the embedded uncertainties. The discussion in this paper builds on a major collection of operating experience data (more than 11,000 pipe failure records) and the associated lessons learned from data analysis and data applications spanning three decades. The piping reliability analysis lessons learned have been obtained from the derivation of pipe leak and rupture frequencies for corrosion resistant piping in a raw water environment, loss-of-coolant-accident frequencies given degradation mitigation, high-energy pipe break analysis, moderate-energy pipe break analysis, and numerous plant-specific applications of a statistical piping reliability model framework. Conclusions are presented regarding the feasibility of determining and incorporating aging effects into probabilistic safety assessment models.

• Earthquakes and Structures
• /
• v.15 no.4
• /
• pp.443-452
• /
• 2018

In this paper the new intensity measures (IMs) for probabilistic seismic analysis of RC high-rise buildings with core wall structural system are proposed. The existing IMs are analysed and the new optimal ones are presented. The newly proposed IMs are based on the existing ones which: 1) comprise a wider range of frequency velocity spectrum content and 2) are defined as the integral along the velocity spectrum. In analysis characteristics of optimal IMs such as: efficiency, practicality, proficiency and sufficiency are considered. As prototype buildings, RC high-rise buildings with core wall structural system and with characteristic heights: 20-storey, 30-storey and 40-storey, are selected. The non-linear 3D models of the prototype buildings are constructed. 720 non-linear time-history analyses are conducted for 60 ground motion records with a wide range of magnitudes, distances to source and various soil types. Statistical processing of results and detailed regression analysis are performed and appropriate demand models which relate IMs to demand measures (DMs), are obtained. The conducted analysis has shown that the newly proposed IMs can efficiently predict the DMs with minimum dispersion and satisfactory practicality as compared to the other commonly used IMs (e.g., PGA and $S_a(T_1)$). The newly proposed IMs overcome difficulties in calculating of integral along the velocity spectrum and present adequate replacement for IMs which comprise a wider range of frequency velocity spectrum content.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• autumn
• /
• pp.383-386
• /
• 2001

The ability to make good cost overruns predictions is a very important aspect of in major construction project. The probabilistic cost models can provide more reliable than traditional cost models which have been used in korea to prepare Bill of Quantities, if the actual cost data are sufficient enough to analyze the trends of the variables. The paper considers non-deterministic methods in a cost estimate. The method(referred to as the 'Monte Carlo simulation' method) interprets cost data indirectly, to generate a probability distribution for total costs from the deficient elemental experience cost distribution. The objectives of this research is to develop a method to forecast the probabilistic total construction cost and the elemental work cost