• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.327-329
• /
• 1998

Up-Propagation is an algorithm for inverting and learning neural network generative models. Sensory input is processed by inverting a model that generates patterns from hidden variables using top-down connections. The inversion process is iterative, utilizing a negative feedback loop that depends on an error signal propagated by bottom-up connections. The error signal is also used to learn the generative model from examples. the algorithm is benchmarked against principal component analysis in experiments on images of handwritten digits.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.18 no.1
• /
• pp.4021-4037
• /
• 1976

This paper describes the actual experiments of the error propagation and studies of analytical photogrammetry using the simulation method in which we can find the causes of the errors. These studies and the results give the valuable data which are very effective for systematically controlling the errors in aerial triangulation. The main contents in my paper are as follows: 1. Dose the scale errors in the successive models in the form of normal distribution appear when the observation errors propagate in the form of normal distribution\ulcorner 2. In what form does this scale error propagation in the actual model appear\ulcorner 3. When the causes of the scale error propagation are found, is the evaluation standard determined normally\ulcorner 4. What degree of influence is there form the constant errors\ulcorner I have done several experiments using the simulation method technique to solve the complicated error propgation of aerial triangulation which is the effective means to research the relations between cause and effect. In this paper, the studies have concentrated on the following points of simulation experiments. (1) The first part descries how we can produce the soft program of the simulation experiment. (2) The second part is the method propagating the errors in the simulation models and the kinds of errors. (3) The final part is the most important; that is the analyzing and evaluation of control during actual work. From the above-mentioned points, it is said that these studies are a very important development in the field of controlling and managing aerial photogrammetry and especially in the case of error propagation, we can clearly find the causes of the errors and steps and parts of errors generated when we use these techniques.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.18 no.2
• /
• pp.167-172
• /
• 2015

In this paper, we have compared some radio propagation models in order to verify the performance of W.C.Y LEE propagation model in mountain area. The four propagation models, which are Okumura-Hata, ITU-R P.525, Egli and W.C.Y. LEE, are analyzed by comparing the differences between measured values and propagation loss estimation values. And a correction method for W.C.Y LEE model is suggested to improve the performance of W.C.Y. LEE model with measured data in mountain area. Simulation results show that the estimation error using W.C.Y LEE model is the lowest among four propagation models. Also, the results show that the corrected W.C.Y LEE model with suggested method improves the performance of propagation loss estimation.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.12 no.3
• /
• pp.231-238
• /
• 1992

Error vector propagation method is applied to the elliptic mild slope equation in order to reduce the computation time. Results from the elliptic, parabolic, and hyperbolic models are compared with experimental data for an elliptic shoal. Also, results of the elliptic and hyperbolic models are compared with experimental data for a detached breakwater. As a result of applying this model. it is concluded that the present model satisfactorily reduces the computation time compared with other numerical models. In the accuracy of solutions, there are some oscillations but the trend compares well with other models.

• Journal of KIISE:Information Networking
• /
• v.31 no.4
• /
• pp.375-383
• /
• 2004

As wireless mobile networks have been widely adopted due to their convenience for deployment, the research for improving their performance has been actively conducted. Since their throughput is restrained by the packet corruption rate not by congestion as in wired networks, however, network simulations for performance evaluation need to select the appropriate wireless channel model representing the behavior of propagation errors for the evaluated channel. The selection of the right model should depend on various factors such as the adopted frequency band, the level of signal power, the existence of obstacles against signal propagation, the sensitivity of protocols to bit errors, and etc. This paper analyzes 10-day bit traces collected from real sensor channels exhibiting the high bit error rate to determine a suitable sensor channel model. For selection, it also evaluates the performance of two error recovery algorithms such as a link layer FEC algorithm and three TCPs (Tahoe, Reno, and Vegas) over several channel models. The comparison analysis shows that CM(Chaotic Map) model predicts 3-time less BER variance and 10-time larger PER(Packet Error Rate) than traces while these differences between the other models and traces are larger than 10-time. The simulation experiments, furthermore, prove that CM model evaluates the performance of these algorithms over sensor channels with the precision at least 10-time more accurate than any other models.

• Korean Journal of Biological Psychiatry
• /
• v.4 no.2
• /
• pp.194-197
• /
• 1997

Neural network models, also known as connectionist models or PDP models, simulate some functions of the brain and may promise to give insight in understanding the cognitive brain functions. The models composed of neuron-like elements that are linked into circuits can learn and adapt to its environment in a trial and error fashion. In this article, the history and principles of the neural network modeling are briefly reviewed, and its applications to psychiatry are discussed.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.45 no.2
• /
• pp.45-57
• /
• 2003

An artificial neural network model was developed to analyze and forecast Short-term river runoff from the Naju watershed, in Korea. Error back propagation neural networks (EBPN) of hourly rainfall and runoff data were found to have a high performance In forecasting runoff. The number of hidden nodes were optimized using total error and Bayesian information criterion. Model forecasts are very accurate (i.e., relative error is less than 3% and $R^2$is greater than 0.99) for calibration and verification data sets. Increasing the time horizon for application data sets, thus mating the model suitable for flood forecasting. decreases the accuracy of the model. The resulting optimal EBPN models for forecasting hourly runoff consists of ten rainfall and four runoff data(ANN0410 model) and ten rainfall and ten runoff data(ANN1010 model). Performances of the ANN0410 and ANN1010 models remain satisfactory up to 6 hours (i.e., $R^2$is greater than 0.92).

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.1
• /
• pp.118-124
• /
• 2004

In this paper, we present a indirect adaptive control method using a wavelet neural network (WNN) for the control of chaotic nonlinear systems without precise mathematical models. The proposed indirect adaptive control method includes the off-line identification and on-line control procedure for chaotic nonlinear systems. In the off-line identification procedure, the WNN based identification model identifies the chaotic nonlinear system by using the serial-parallel identification structure and is trained by the gradient-descent method. And, in the on-line control procedure, a WNN controller is designed by using the off-line identification model and is trained by the error back-propagation algorithm. Finally, the effectiveness and feasibility of the proposed control method is demonstrated with applications to the chaotic nonlinear systems.

• Structural Engineering and Mechanics
• /
• v.70 no.6
• /
• pp.671-681
• /
• 2019

This paper examines the applicability of artificial neural network (ANN) and multivariate adaptive regression splines (MARS) to predict the compressive strength of bacteria incorporated geopolymer concrete (GPC). The mix is composed of new bacterial strain, manufactured sand, ground granulated blast furnace slag, silica fume, metakaolin and fly ash. The concentration of sodium hydroxide (NaOH) is maintained at 8 Molar, sodium silicate ($Na_2SiO_3$) to NaOH weight ratio is 2.33 and the alkaline liquid to binder ratio of 0.35 and ambient curing temperature ($28^{\circ}C$) is maintained for all the mixtures. In ANN, back-propagation training technique was employed for updating the weights of each layer based on the error in the network output. Levenberg-Marquardt algorithm was used for feed-forward back-propagation. MARS model was developed by establishing a relationship between a set of predictors and dependent variables. MARS is based on a divide and conquers strategy partitioning the training data sets into separate regions; each gets its own regression line. Six models based on ANN and MARS were developed to predict the compressive strength of bacteria incorporated GPC for 1, 3, 7, 28, 56 and 90 days. About 70% of the total 84 data sets obtained from experiments were used for development of the models and remaining 30% data was utilized for testing. From the study, it is observed that the predicted values from the models are found to be in good agreement with the corresponding experimental values and the developed models are robust and reliable.

• The Bulletin of The Korean Astronomical Society
• /
• v.37 no.2
• /
• pp.124.1-124.1
• /
• 2012

We have made a comparison of the WSA-ENLIL CME propagation model with three cone types and an empirical model using 29 halo CMEs from 2001 to 2002. These halo CMEs have cone model parameters from Michalek et al. (2007) as well as their associated interplanetary (IP) shocks. For this study we consider three different cone models (an asymmetric cone model, an ice-cream cone model and an elliptical cone model) to determine CME cone parameters (radial velocity, angular width and source location), which are used for input parameters of the WSA-ENLIL CME propagation model. The mean absolute error (MAE) of the arrival times at the Earth for the elliptical cone model is 10 hours, which is about 2 hours smaller than those of the other models. However, this value is still larger than that (8.7 hours) of an empirical model by Kim et al. (2007). We are investigating several possibilities on relatively large errors of the WSA-ENLIL cone model, which may be caused by CME-CME interaction, background solar wind speed, and/or CME density enhancement.