• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.298-301
• /
• 2004

The aim of this study is to cross-validate of spatial probability model, artificial neural network at Boun, Korea, using a Geographic Information System (GIS). Landslide locations were identified in the Boun, Janghung and Youngin areas from interpretation of aerial photographs, field surveys, and maps of the topography, soil type, forest cover and land use were constructed to spatial data-sets. The factors that influence landslide occurrence, such as slope, aspect and curvature of topography, were calculated from the topographic database. Topographic type, texture, material, drainage and effective soil thickness were extracted from the soil database, and type, diameter, age and density of forest were extracted from the forest database. Lithology was extracted from the geological database, and land use was classified from the Landsat TM image satellite image. Landslide susceptibility was analyzed using the landslide­occurrence factors by artificial neural network model. For the validation and cross-validation, the result of the analysis was applied to each study areas. The validation and cross-validate results showed satisfactory agreement between the susceptibility map and the existing data on landslide locations.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.710-712
• /
• 2006

The aim of this study was to analyze limestone deposits potential using an artificial neural network and a Geographic Information System (GIS) environment to identify areas that have not been subjected to the same degree of exploration. For this, a variety of spatial geological data were compiled, evaluated and integrated to produce a map of potential deposits in the Gangreung area, Korea. A spatial database considering deposit, topographic, geologic, geophysical and geochemical data was constructed for the study area using a GIS. The factors relating to 44 limestone deposits were the geological data, geochemical data and geophysical data. These factors were used with an artificial neural network to analyze mineral potential. Each factor’s weight was determined by the back-propagation training method. Training area was applied to analyze and verify the effect of training. Then the mineral deposit potential indices were calculated using the trained back-propagation weights, and potential map was constructed from GIS data. The mineral potential map was then verified by comparison with the known mineral deposit areas. The verification result gave accuracy of 87.31% for training area.

• Journal of Korean Society of Steel Construction
• /
• v.15 no.4 s.65
• /
• pp.413-422
• /
• 2003

Most engineers tend to rely on their intuition or existing data in formulating structural design or preliminary estimate of various conditions. Because of these variations, the artificial neural network is used as an alternative design model of the warren truss since it can handle uncertainty through the probability method. This research validated the approximate structural design model of the warren truss, with its proper parameter values of the neural network and design process falling within 10 percent torrence of the different designs that resulted between this model and the MIDAS program. The suggested model for the process was adapted for the truss design using the member section table, while time saving and efficiency are based on the allowed range of torrence.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.39 no.1
• /
• pp.42-50
• /
• 2002

In this paper, we propose an FDI(fault detection and isolation) method using neural network-based multi-fault models to detect and isolate faults in nonlinear systems. When a change in the system occurs, the errors between the system output and the neural network nominal system output cross a threshold, and once a fault in the system is detected, the fault classifier statistically isolates the fault by using the error between each neural network-based fault model output and the system output. From the computer simulation results, it is verified that the proposed fault diagonal method can be performed successfully to detect and isolate faults in a nonlinear system.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2003.10a
• /
• pp.267-270
• /
• 2003

An intelligent performance diagnostic computer program of a gas turbine using the NN(Neural Network) was developed. Recently on-condition performance monitoring of major gas path components using the GPA(Gas Path Analysis) method has been performed in analyzing of engine faults. However because the types and severities of engine faults are various and complex, it is not easy that all fault conditions of the engine would be monitored only by the GPA approach. Therefore in order to solve this problem, application of using the NNs for learning and diagnosis would be required. Among then, a BPN (Back Propagation Neural Network) with one hidden layer, which can use an updating learning rate, was proposed for diagnostics of PT6A-62 turboprop engine in this work.

• Korean Journal of Agricultural Science
• /
• v.46 no.4
• /
• pp.843-856
• /
• 2019

Real-time flood prediction has an important role in significantly reducing potential damage caused by floods for urban residential areas located downstream of river basins. This paper presents an effective approach for flood forecasting based on the construction of a deep neural network (DNN) model. In addition, this research depends closely on the open-source software library, TensorFlow, which was developed by Google for machine and deep learning applications and research. The proposed model was applied to forecast the flowrate one, two, and three days in advance at the Son Tay hydrological station on the Red River, Vietnam. The input data of the model was a series of discharge data observed at five gauge stations on the Red River system, without requiring rainfall data, water levels and topographic characteristics. The research results indicate that the DNN model achieved a high performance for flood forecasting even though only a modest amount of data is required. When forecasting one and two days in advance, the Nash-Sutcliffe Efficiency (NSE) reached 0.993 and 0.938, respectively. The findings of this study suggest that the DNN model can be used to construct a real-time flood warning system on the Red River and for other river basins in Vietnam.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2000.11a
• /
• pp.699-702
• /
• 2000

The automation and control of robotic welding process is a very complex assignment because the system is affected by a number of variables which are very difficult to determine or predict in practice. Not only the optimization of the robotic welding process is considered from the point of view of the time and the cost of manufacturing. as well as quality of the weldment. the human factors of the production and many other factors must taken into consideration. hi order to determine the optimal parameters of robotic welding process, it is necessary to build a computer model representing all parameters influencing the welding process as well as the mutual dependence between them. This paper presents an approach to modeling the robotic welding process in which all parameters affecting the welding process are included using a neural network. A detailed analysis of the simulation results has been carried out to evaluate the proposed neural network model.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.1
• /
• pp.13-20
• /
• 2005

This paper addresses a new blind channel equalization method using fourth-order cumulants of channel inputs and a three-layer neural network equalizer. The proposed algorithm is robust with respect to the existence of heavy Gaussian noise in a channel and does not require the minimum-phase characteristic of the channel. The transmitted signals at the receiver are over-sampled to ensure the channel described by a full-column rank matrix. It changes a single-input/single-output (SISO) finite-impulse response (FIR) channel to a single-input/multi-output (SIMO) channel. Based on the properties of the fourth-order cumulants of the over-sampled channel inputs, the iterative algorithm is derived to estimate the deconvolution matrix which makes the overall transfer matrix transparent, i.e., it can be reduced to the identity matrix by simple recordering and scaling. By using this estimated deconvolution matrix, which is the inverse of the over-sampled unknown channel, a three-layer neural network equalizer is implemented at the receiver. In simulation studies, the stochastic version of the proposed algorithm is tested with three-ray multi-path channels for on-line operation, and its performance is compared with a method based on conventional second-order statistics. Relatively good results, withe fast convergence speed, are achieved, even when the transmitted symbols are significantly corrupted with Gaussian noise.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.05a
• /
• pp.125-129
• /
• 2006

By advent of NNC(Neural Network Chip), it is possible that process in parallel and discern the importance of signal with learning oneself by experience in external signal. So, the design of general purpose operation unit using VHDL(VHSIC Hardware Description Language) on the existing FPGA(Field Programmable Gate Array) can replaced EN(Expert Network) and learning algorithm. Also, neural network operation unit is possible various operation using learning of NN(Neural Network). This paper present general purpose operation unit using hierarchical structure of EN. EN of presented structure learn from logical gate which constitute a operation unit, it relocated several layer. The overall structure is hierarchical using a module, it has generality more than FPGA operation unit.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.2
• /
• pp.228-236
• /
• 2012

In this paper, a controller for two wheeled inverted pendulum robot is designed to have more stable balancing capability than conventional controller. Fuzzy control structure is chosen for the two wheeled inverted pendulum robot, and fuzzy membership function factors for the controller are obtained for specified 3 users' weights using trial-and-error method. Next a neural network is employed to generate fuzzy membership function factors for more stable control performance when the user's weight is arbitrarily selected. Through the simulation study we find that the designed fuzzy controller using the neural network is superior to the conventional fuzzy controller.