• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.288-295
• /
• 1998

This paper proposes a new data classification method based on the tolerant rough set that extends the existing equivalent rough set. Similarity measure between two data is described by a distance function of all constituent attributes and they are defined to be tolerant when their similarity measure exceeds a similarity threshold value. The determination of optimal similarity theshold value is very important for the accurate classification. So, we determine it optimally by using the genetic algorithm (GA), where the goal of evolution is to balance two requirements such that (1) some tolerant objects are required to be included in the same class as many as possible. After finding the optimal similarity threshold value, a tolerant set of each object is obtained and the data set is grounded into the lower and upper approximation set depending on the coincidence of their classes. We propose a two-stage classification method that all data are classified by using the lower approxi ation at the first stage and then the non-classified data at the first stage are classified again by using the rough membership functions obtained from the upper approximation set. We apply the proposed classification method to the handwritten numeral character classification. problem and compare its classification performance and learning time with those of the feed forward neural network's back propagation algorithm.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.2
• /
• pp.94-102
• /
• 2000

This paper presents a new FDI scheme based on dynamic fuzzy model(DFM) for the unknown nonlinear system, which can detect and isolate process faults continuously over all ranges of operating condition. The dynamic behavior of a nonlinear process is represented by a set of local linear models. The parameters of the DFM are identified by an on-line methods. The residual vector of the FDI system is consisted of the parameter deviations from nominal model and the set of grade of membership values indicating the operating condition of the nonlinear process. The detection and isolation of faults are performed via a neural network classifier that are learned the relationship between the residual vector and fault type. We apply the proposed FDI scheme to the FDI system design for a two-tank system and show the usefulness of the proposed scheme.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.1
• /
• pp.97-104
• /
• 2015

An 'associative cube', a class of auto-associative memories, is revisited here, in which training data and hidden orthogonal basis functions such as wavelet packets or Fourier kernels, are combined in the weight cube. This weight cube has hidden units in its depth, represented by a three dimensional cubic structure. We develop an unsupervised incremental learning mechanism based upon the adaptive least squares method. Training data are mapped into orthogonal basis vectors in a least-squares sense by updating the weights which minimize an energy function. Therefore, a prescribed orthogonal kernel is incrementally assigned to an incoming data. Next, we show how a decoding procedure finds the closest one with a competitive network in the hidden layer. As noisy test data are applied to an associative cube, the nearest one among the original training data are restored in an optimal sense. The simulation results confirm robustness of associative cubes even if test data are heavily distorted by various types of noise.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.12
• /
• pp.1833-1840
• /
• 2013

A golf ball collecting robot in a golf ball driving range has been recently required because it is safer and more economic than a human being. In this paper, the golf ball recognition and distance estimation system based on a neural network and OpenCV is developed for the robot. The simulation results show that the recognition ratio is over 87% for the distance of less than 120cm and accurate rate for distance estimation is over 85% for golf balls in 30-180cm from a webcam.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.3
• /
• pp.571-578
• /
• 2018

Recently, deep learning techniques have shown superior performance in various kinds of pattern recognition. However, there have been some arguments whether the DNN performs better than the conventional machine learning techniques when classification experiments are done using a small amount of training data. In this study, we compared the performance of the conventional GMM and SVM with DNN, a kind of deep learning techniques, in audio event detection. When tested on the same data, DNN has shown superior overall performance but SVM was better than DNN in segment-based F-score.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.26 no.6
• /
• pp.1092-1098
• /
• 2002

This paper discusses the composition of the theory of reinforcement teaming, which is applied in real-time teaming, and evolutionary strategy, which proves its the superiority in the finding of the optimal solution at the off-line teaming method. The individuals are reduced in order to team the evolutionary strategy in real-time, and new method that guarantee the convergence of evolutionary mutations are proposed. It is possible to control the control object varied as time changes. As the state value of the control object is generated, applied evolutionary strategy each sampling time because of the teaming process of an estimation, selection, mutation in real-time. These algorithms can be applied, the people who do not have knowledge about the technical tuning of dynamic systems could design the controller or problems in which the characteristics of the system dynamics are slightly varied as time changes. In the future, studies are needed on the proof of the theory through experiments and the characteristic considerations of the robustness against the outside disturbances.

• Journal of Advanced Marine Engineering and Technology
• /
• v.36 no.5
• /
• pp.645-661
• /
• 2012

Recently, pirates are infesting on the sea and they have been hijacking the several vessels for example Samho Dream and Samho Jewelry of Korea. One of the items to reduce the risk is to adopt the invader detection system. If the pirates break in to the ship, the detection system can monitor the pirates and then call the security alarm. The crew can gain time to hide to the safe room and the report can be automatically sent to the control room to cope with the situation. For the invader detection, an unmanned observation system was proposed using the image detection algorithm that extracts the invader image from the recording image. To detect the motion area, the difference value was calculated between the current image and the prior image of the invader, and the 'AND' operator was used in calculated image and edge line. The image noise was reduced based on the morphology operation and then the image was transformed into morphological information. Finally, a neural network model was applied to recognize the invader. In the experimental results, it was confirmed that the proposed approach can improve the performance of the recognition in the invader monitoring system.

• Proceedings of the KSME Conference
• /
• 2004.11a
• /
• pp.708-713
• /
• 2004

This research develops a sensorless hydraulic servo system of Parallel-Typed robot for harbour construction. Purpose of the robot is to mechanize the construction, which is accomplished through a joystick's operating by a stoneworker (or diver). The robot is attached on the end of an excavator as its attachment or transported by a crane to reach the desired place. The embedded compact controller is installed on the robot body and controlled by wireless telecommunication. For underwater work, it is necessary to waterproof the robot and its sensors. Especially, a sensor waterproof is a main drawback for the underwater robot. This leads us to develop a hydraulic robot position controller using an observer which gives the position information without any position sensor. We design a neural network to identify the displacement change according to the command voltage to servo valve. To verify the sensorless controller, this paper presents the performance of the sensorless control for which the position is given by the observer comparing with that of the sensor control for which the position is measured by LVDT sensors.

• Journal of Sensor Science and Technology
• /
• v.8 no.1
• /
• pp.45-52
• /
• 1999

In this raper, an enhanced learning method is proposed for improving the learning speed of the error back propagation learning algorithm. In order to cope with the premature saturation phenomenon at the initial learning stage, a variation scheme of active functions is introduced by using higher order functions, which does not need much increase of computation load. It naturally changes the learning rate of inter-connection weights to a large value as the derivative of sigmoid function abnormally decrease to a small value during the learning epoch. Also, we suggest the hybrid learning method incorporated the proposed method with the momentum training algorithm. Computer simulation results show that the proposed learning algorithm outperforms the conventional methods such as momentum and delta-bar-delta algorithms.

• Journal of Sensor Science and Technology
• /
• v.27 no.2
• /
• pp.118-125
• /
• 2018

An evaluation system for an electronic-nose concept using three types of metal oxide gas sensors that react similarly to the human olfactory cells was constructed for the quantitative and qualitative evaluation of aroma fragrances. Four types of aroma fragrances (lavender, orange, jasmine, and Roman chamomile), which are commonly used in aromatherapy, were evaluated. All the gas sensors reacted remarkably to the aroma fragrances and the good correlation of r=0.58-0.88 with the aromatic odor intensities by olfaction was confirmed. From the results of the analysis of an electronic-nose concept for classifying the characteristics of aroma oil fragrances, aroma oils could be classified using the fragrance characteristics and oil extraction methods with the cumulative variability contribution rate of 95.65% (F1: 69.65%, F2: 26.03%) by principal component analysis. In the pattern recognition based on the artificial neural network, the four aroma fragrances were 100% recognized through the training data of 56 cases (70%) out of 80 cases, and the pattern recognition rate was 57.1%-71.4% through the validation and testing data of 24 cases (30%). The pattern recognition success rate through all confusion matrices was 82.1%, indicating that the classification of aroma oil fragrances using the three types of gas sensors was successful.