• Journal of KIISE:Software and Applications
• /
• v.35 no.9
• /
• pp.554-561
• /
• 2008

Prediction technique of user's intention can be used as a post-processing method for reducing the search space of an automatic speech recognizer. Prediction technique of system's intention can be used as a pre-processing method for generating a flexible sentence. To satisfy these practical needs, we propose a statistical model to predict speakers' intentions that are generalized into pairs of a speech act and a concept sequence. Contrary to the previous model using simple n-gram statistic of speech acts, the proposed model represents a dialogue history of a current utterance to a feature set with various linguistic levels (i.e. n-grams of speech act and a concept sequence pairs, clue words, and state information of a domain frame). Then, the proposed model predicts the intention of the next utterance by using the feature set as inputs of CRFs (Conditional Random Fields). In the experiment in a schedule management domain, The proposed model showed the precision of 76.25% on prediction of user's speech act and the precision of 64.21% on prediction of user's concept sequence. The proposed model also showed the precision of 88.11% on prediction of system's speech act and the Precision of 87.19% on prediction of system's concept sequence. In addition, the proposed model showed 29.32% higher average precision than the previous model.

• Journal of the Korea Institute of Building Construction
• /
• v.17 no.3
• /
• pp.295-303
• /
• 2017

Over the past 7 years, the number of victims of construction disasters has been gradually increasing. Compared with projects in other industries, construction projects are highly exposed to safety risks. For this reason, the research methods of predicting and managing the risk of construction disasters are urgently needed that can be applied to a construction site. This study aims to propose a prediction model for a construction disaster using the decision tree technique. The developed the model is reviewed the applicability by evaluating its accuracy based on disaster data. The top three of the prediction values obtained from the proposed model were enumerated, and then the cumulative accuracy were also calculated. The prediction accuracy was 40 percent for the first value, but the cumulative accuracy was 80 percent. Thus, as more disaster data was accumulated, the cumulative accuracy appeared to be higher. If utilized in construction sites, the model proposed in this study would contribute to a reduction in the rate of construction disasters.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.3B
• /
• pp.297-304
• /
• 2011

MIMO wireless communication embedded systems, and for propagation prediction for indoor and outdoor propagation prediction program incorporates an indoor/outdoor propagation through the simulator can be predicted. This analysis technique developed by the interference between multiple transmitters and a maximum transmission distance issues, the frequency utilization efficiency for a variety of issues, including analysis and prediction becomes possible. Development of the prediction of the conventional methods, but I can consider the environmental characteristics of the ray tracing simulation software to develop and implement an efficient ray tracing, ray tracing techniques and are designed to enable tracked beam analysis of propagation characteristics using information technology by combining the theoretical characteristics of an efficient and well-reflected propagation prediction technique was employed. The frequency of domestic embedded systems, ensure the frequency characteristics and frequency of 3-5GHz band for propagation to investigate the development of local wireless communication technology-based skills needed for securing and jeonpaganseopdeung frequency management techniques to ensure the verification and verified through experiments.

• The Journal of Information Systems
• /
• v.28 no.3
• /
• pp.249-276
• /
• 2019

Purpose The purpose of this study is to develop a prediction model and decision rules for the elderly's suicidal ideation based on the Korean Welfare Panel survey data. By utilizing this data, we obtained many decision rules to predict the elderly's suicide ideation. Design/methodology/approach This study used classification analysis to derive decision rules to predict on the basis of decision tree technique. Weka 3.8 is used as the data mining tool in this study. The decision tree algorithm uses J48, also known as C4.5. In addition, 66.6% of the total data was divided into learning data and verification data. We considered all possible variables based on previous studies in predicting suicidal ideation of the elderly. Finally, 99 variables including the target variable were used. Classification analysis was performed by introducing sampling technique through backward elimination and data balancing. Findings As a result, there were significant differences between the data sets. The selected data sets have different, various decision tree and several rules. Based on the decision tree method, we derived the rules for suicide prevention. The decision tree derives not only the rules for the suicidal ideation of the depressed group, but also the rules for the suicidal ideation of the non-depressed group. In addition, in developing the predictive model, the problem of over-fitting due to the data imbalance phenomenon was directly identified through the application of data balancing. We could conclude that it is necessary to balance the data on the target variables in order to perform the correct classification analysis without over-fitting. In addition, although data balancing is applied, it is shown that performance is not inferior in prediction rate when compared with a biased prediction model.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.5
• /
• pp.1-10
• /
• 2016

Magnetic disks have been used for decades in auxiliary storage devices of computer systems. In recent years, the use of NAND flash memory, which is called SSD, is increased as auxiliary storage devices. However, NAND flash memory, unlike traditional magnetic disks, necessarily performs the erase operation before the write operation in order to overwrite data and this leads to degrade the system lifetime and performance of overall NAND flash memory system. Moreover, NAND flash memory has the lower endurance, compared to traditional magnetic disks. To overcome this problem, this paper proposes EPET (Enhanced Prediction and Elapsed Time) wear leveling technique, which is especially efficient to portable devices. EPET wear leveling uses the advantage of PET (Prediction of Elapsed Time) wear leveling and solves long-term system failure time problem. Moreover, EPET wear leveling further improves space efficiency. In our experiments, EPET wear leveling prolonged the first bad time up to 328.9% and prolonged the system lifetime up to 305.9%, compared to other techniques.

• Asian-Australasian Journal of Animal Sciences
• /
• v.24 no.5
• /
• pp.603-609
• /
• 2011

Telomeres are special structures at the ends of eukaryotic chromosomes. Vertebrate telomeres consist of tandem repeats of conserved TTAGGG sequence and associated proteins. Birds are interesting models for molecular studies on aging and cellular senescence because of their slow aging rates and longer life spans for their body size. In this longitudinal study, we explored the possibility of using telomeres as an age-marker to predict age in Single Comb White Leghorn layer chickens. We quantified the relative amount of telomeric DNA in isolated peripheral blood lymphocytes by the Quantitative Fluorescence in situ Hybridization technique on interphase nuclei (IQ FISH) using telomere-specific DNA probes. We found that the amount of telomeric DNA (ATD) reduced significantly with an increase in chronological age of the chicken. Especially, the telomere shortening rates are greatly increased in growing individuals compared to laying and old-aged individuals. Therefore, using the ATD values obtained by IQ FISH we established the possibility of age prediction in chickens based on the telomere theory of aging. By regression analysis of the ATD values at each age interval, we formulated an equation to predict the age of chickens. In conclusion, the telomeric DNA values by IQ FISH analyses can be used as an effective age-marker in predicting the chronological age of chickens. The study has implications in the breeding and population genetics of poultry, especially the reproductive potential.

• Water Engineering Research
• /
• v.4 no.2
• /
• pp.59-68
• /
• 2003

The applicabilities and validities of two methodologies fur the prediction of THM (trihalomethane) formation in a water pipeline system were proposed and discussed. One is the multiple regression technique and the other is an artificial neural network technique. There are many factors which influence water quality, especially THMs formations in water pipeline systems. In this study, the prediction models of THM formation in water pipeline systems are developed based on the independent variables proposed by American Water Works Association(AWWA). Multiple linear/nonlinear regression models are estimated and three layer feed-forward artificial neural networks have been used to predict the THM formation in a water pipeline system. Input parameters of the models consist of organic compounds measured in water pipeline systems such as TOC, DOC and UV254. Also, the reaction time to each measuring site along pipeline is used as input parameter calculated by a hydraulic analysis. Using these variables as model parameters, four models are developed. And the predicted results from the four developed models are compared statistically to the measured THMs data set. It is shown that the artificial neural network approaches are much superior to the conventional regression approaches and that the developed models by neural network can be used more efficiently and reproduce more accurately the THMs formation in water pipeline systems, than the conventional regression methods proposed by AWWA.

• Journal of information and communication convergence engineering
• /
• v.15 no.1
• /
• pp.43-48
• /
• 2017

Movie ratings are crucial for recommendation engines that track the behavior of all users and utilize the information to suggest items the users might like. It is intuitively appealing that information about the viewing preferences in terms of movie genres is sufficient for predicting a genre of an unlabeled movie. In order to predict movie genres, we treat ratings as a feature vector, apply a Bernoulli event model to estimate the likelihood of a movie being assigned a certain genre, and evaluate the posterior probability of the genre of a given movie by using the Bayes rule. The goal of the proposed technique is to efficiently use movie ratings for the task of predicting movie genres. In our approach, we attempted to answer the question: "Given the set of users who watched a movie, is it possible to predict the genre of a movie on the basis of its ratings?" The simulation results with MovieLens 1M data demonstrated the efficiency and accuracy of the proposed technique, achieving an 83.8% prediction rate for exact prediction and 84.8% when including correlated genres.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.25 no.5
• /
• pp.874-882
• /
• 2001

The static and fatigue tests have been carried out to verify the validity of a generalized residual strength degradation model. And a new method of parameter determination in the model is verified experimentally to account for the effect of tension-compression fatigue loading of spheroidal graphite cast iron. It is shown that the correlation between the experimental results and the theoretical prediction on the statistical distribution of fatigue life by using the proposed method is very reasonable. Furthermore, it is found that the correlation between the theoretical prediction and the experimental results of fatigue life in case of tension-tension fatigue data in composite material appears to be reasonable. Therefore, the proposed method is more adjustable in the determination of the parameter than maximum likelihood method and minimization technique.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.20 no.11
• /
• pp.995-1000
• /
• 2010

With the development of the auto industry, the automobile manufacturers demand to shorten development period and reduce the cost. Compared with the traditional method, applying the virtual prototype is more economical. This paper presents a method for parameters sensitivity analysis and optimizing the performance of vehicle noise and vibration. The existing design processes were repeatedly analyzed with a focus on vehicle performance to decide the design parameters of dimension, thickness, mounting type of body and chassis systems in the vehicle development period. This paper describes the prediction technique of vehicle performance using L18 orthogonal array layout, quality deviation analysis and parameter sensitivity analysis for robust design. This paper analyzed the performance correlation equation through the frequency and sensitivity database according to a design factor change. The new concept is that the performance prediction is possible without repeated activities of test and analysis. This paper described the parameter analysis applications such as bush dynamic stiffness and bush void direction of rear suspension. Design engineer could efficiently decide the design variable using parameter analysis database in early design stage. These improvements can reduce man hour and test development period as well as to achieve stable NVH performance.