• International Journal of Control, Automation, and Systems
• /
• v.6 no.6
• /
• pp.818-827
• /
• 2008

In this paper, we propose a new noise estimation and reduction algorithm for stationary and nonstationary noisy environments. This approach uses an algorithm that classifies the speech and noise signal contributions in time-frequency bins. It relies on the ratio of the normalized standard deviation of the noisy power spectrum in time-frequency bins to its average. If the ratio is greater than an adaptive estimator, speech is considered to be present. The propose method uses an auto control parameter for an adaptive estimator to work well in highly nonstationary noisy environments. The auto control parameter is controlled by a linear function using a posteriori signal to noise ratio(SNR) according to the increase or the decrease of the noise level. The estimated clean speech power spectrum is obtained by a modified gain function and the updated noisy power spectrum of the time-frequency bin. This new algorithm has the advantages of much more simplicity and light computational load for estimating the stationary and nonstationary noise environments. The proposed algorithm is superior to conventional methods. To evaluate the algorithm's performance, we test it using the NOIZEUS database, and use the segment signal-to-noise ratio(SNR) and ITU-T P.835 as evaluation criteria.

• International Journal of Control, Automation, and Systems
• /
• v.6 no.6
• /
• pp.800-808
• /
• 2008

A fingerprint verification system based on a set of invariant moment features and a nonlinear Back Propagation Neural Network(BPNN) verifier is proposed. An image-based method with invariant moment features for fingerprint verification is used to overcome the demerits of traditional minutiae-based methods and other image-based methods. The proposed system contains two stages: an off-line stage for template processing and an on-line stage for testing with input fingerprints. The system preprocesses fingerprints and reliably detects a unique reference point to determine a Region-of-Interest(ROI). A total of four sets of seven invariant moment features are extracted from four partitioned sub-images of an ROI. Matching between the feature vectors of a test fingerprint and those of a template fingerprint in the database is evaluated by a nonlinear BPNN and its performance is compared with other methods in terms of absolute distance as a similarity measure. The experimental results show that the proposed method with BPNN matching has a higher matching accuracy, while the method with absolute distance has a faster matching speed. Comparison results with other famous methods also show that the proposed method outperforms them in verification accuracy.

• Journal of KIISE:Software and Applications
• /
• v.27 no.5
• /
• pp.563-574
• /
• 2000

Recognition of numeral fields is a very important task for many document automation applications. Conventional methods are based on the two-steps process, segmentation of touching numerals and recognition of the individual numerals. However, due to a large variation of touching types this approach has not produced a robust result. In this paper, we present a new segmentation-free method for recognizing the two touching numerals. In this approach, two touching numerals are regarded as a single pattern coming from 100 classes ('00', '01', '02', ..., '98', '99'). For the test set, we manually extract two touching numerals from the data set of NIST numeral fields. Due to the limitation of conventional neural network in case of large-set classification, we use a modular neural network and Drove its superiority through recognition experimen.

• International Journal of Control, Automation, and Systems
• /
• v.1 no.1
• /
• pp.68-75
• /
• 2003

This paper presents an effective trajectory planning algorithm for industrial robot manipulators. Given the end-effector trajectory in Cartesian space, together with the relevant constraints and task specifications, the proposed method is capable of planning the optimum end-effector trajectory. The proposed trajectory planning algorithm considers the joint acceleration limit, end-effector velocity limits, and trajectory allowance. A feedforward compensator is also incorporated in the proposed algorithm to counteract the delay in joint dynamics. The algorithm is carefully designed so that it can be directly adopted with the existing industrial manipulators. The proposed algorithm can be easily programmed for various tasks given the specifications and constraints. A three-dimensional test trajectory was planned with the proposed algorithm and tested with the Performer MK3s industrial manipulator. The results verified effective manipulator performance within the constraints.

• International Journal of Control, Automation, and Systems
• /
• v.2 no.1
• /
• pp.83-91
• /
• 2004

The purpose of this paper is to obtain an accurate nonlinear system model to test various control schemes for a motion control system that requires high speed, robustness and accuracy. An industrial sewing machine equipped with a Brushless DC motor is considered. It is modeled by a neural network that is configured as an output-error dynamical system. The identified model is essentially a one step ahead prediction structure in which past inputs and outputs are used to calculate the current output. Using the model, a 2 degree-of-freedom PID controller to compensate the effects of disturbance without degrading tracking performance has been de-signed. In this experiment, it is not preferable for safety reasons to tune the controller online on the actual machinery. Experimental results confirm that the model is a good approximation of sewing machine dynamics and that the proposed control methodology is effective.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1338-1343
• /
• 2003

Data is the expression of the language or numerical values that show some characteristics. And information is extracted from data for the specific purposes. The knowledge is utilized as information to construct rules that recognize patterns and make decisions. Today, knowledge extraction and application of the knowledge are broadly accomplished to improve the comprehension and to elevate the performance of systems in several industrial fields. The knowledge extraction could be achieved by some steps that include the knowledge acquisition, expression, and implementation. Such extracted knowledge can be drawn by rules. Clustering (CU, input space partition (ISP), neuro-fuzzy (NF), neural network (NN), extension matrix (EM), etc. are employed for expression the knowledge by rules. In this paper, the various approaches of the knowledge extraction are examined by categories that separate the methods by the applied industrial fields. Also, the several test data and the experimental results are compared and analysed based upon the applied techniques that include CL, ISP, NF, NN, EM, and so on.

• Journal of the Korean Society for Precision Engineering
• /
• v.33 no.7
• /
• pp.579-586
• /
• 2016

This paper describes kinematic analysis of a 6-degrees-of-freedom (DOF) ultra-precision positioning stage based on a flexure hinge. The stage is designed for processes which require ultra-precision and high load capacities, e.g. wafer-level precision bonding/assembly. During the initial design process, inverse and forward kinematic analyses were performed to actuate the precision positioning stage and to calculate workspace. A two-step procedure was used for inverse kinematic analysis. The first step involved calculating the amount of actuation of the horizontal actuation units. The second step involved calculating the amount of actuation of the vertical actuation unit, given the the results of the first step, by including a lever hinge mechanism adopted for motion amplification. Forward kinematic analysis was performed by defining six distance relationships between hinge positions for in-plane and out-of-plane motion. Finally, the result of a circular path actuation test with respect to the x-y, y-z, and x-z planes is presented.

• Advances in materials Research
• /
• v.3 no.4
• /
• pp.217-225
• /
• 2014

In this study, a forging steel alloyed with both Nb and V was used as experimental material and the hot deformation behavior has been studied for this steel by conducting the compressive deformation test at temperature of $900-1150^{\circ}C$ and strain rate of $0.01-0.01s^{-1}$ in a MMS-300 thermo-mechanical simulator. The microstructure evolution, particularly the dynamically recrystallized microstructure, of the experimental steel at elevated temperatures, strain rates and strain levels, was characterized by optical microstructural observation and the constitutive equation in association with the activation energy and Zener-Hollomon parameter. The curves of strain hardening rate versus stress were used to determine the critical strain and peak strain, and their relation was connected with Zener-Hollomon parameter. Under the conditions of processing temperature $900^{\circ}C$ and strain rate $0.01s^{-1}$, the dynamic recrystallization took place and the austenite grain size was refined from $164.5{\mu}m$ to $28.9{\mu}m$.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.22 no.4
• /
• pp.652-657
• /
• 2013

In this study, we developed a counting method for non-contact ID cards using an optical fiber displacement sensor instead of the traditionally used friction counting method. The proposed method has the advantage of high speed and automated measurement. For counting non-contact ID cards, an H-type optical fiber sensor, jig part, and counting program are developed separately to build the system and adjust it. Through the experimental test results, it was confirmed that counting is possible with one type of international ID card and one type of financial security card based on ISO7810. Furthermore, by applying the proposed method to 100 ID cards 100 times repeatedly, it was confirmed that it has high accuracy and an error ratio of 0%. We experimentally demonstrated that the proposed counting method for non-contact ID cards using an optical fiber displacement sensor can perform measurements with high accuracy and high speed.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2006.04a
• /
• pp.181-185
• /
• 2006

Image co-registration is the process of overlaying two images of the same scene, one of which represents a reference image, while the other is geometrically transformed to the one. In order to improve efficiency and effectiveness of the co-registration approach, the author proposed a pre-qualified area matching algorithm which is composed of feature extraction with canny operator and area matching algorithm with cross correlation coefficient. For refining matching points, outlier detection using studentized residual was used and iteratively removes outliers at the level of three standard deviation. Throughout the pre-qualification and the refining processes, the computation time was significantly improved and the registration accuracy is enhanced. A prototype of the proposed algorithm was implemented and the performance test of 3 Landsat images of Korea showed: (1) average RMSE error of the approach was 0.436 Pixel (2) the average number of matching points was over 38,475 (3) the average processing time was 489 seconds per image with a regular workstation equipped with a 3 GHz Intel Pentium 4 CPU and 1 Gbytes Ram. The proposed approach achieved robustness, full automation, and time efficiency.