• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.5
• /
• pp.683-687
• /
• 2010

This paper studied some methods which use frequency warping method that is the one of the speech transformation method to develope the robust speech recognition system for the emotional variation. For this purpose, the effect of emotional variations on the speech signal were studied using speech database containing various emotions and it is observed that speech spectrum is affected by the emotional variation and this effect is one of the reasons that makes the performance of the speech recognition system worse. In this paper, new training method that uses frequency warping in training process is presented to reduce the effect of emotional variation and the speech recognition system based on vocal tract length normalization method is developed to be compared with proposed system. Experimental results from the isolated word recognition using HMM showed that new training method reduced the error rate of the conventional recognition system using speech signal containing various emotions.

• Nuclear Engineering and Technology
• /
• v.49 no.3
• /
• pp.504-516
• /
• 2017

The Jordan Research and Training Reactor (JRTR) is the first research reactor in Jordan, the commissioning of which is ongoing. The reactor is a 5-MWth, open-pool type, light-water-moderated, and cooled reactor with a heavy water reflector system. The neutron measurement system (NMS) applied to the JRTR employs a wide-range fission chamber that can cover from source range to power range. A high-sensitivity boron trifluoride counter was added to obtain more accurate measurements of the neutron signals and to calibrate the log power signals; the NMS has a major role in the entire commissioning stage. However, few case studies exist concerning the application of the NMS to a research reactor. This study introduces the features of the NMS and the boron trifluoride counter in the JRTR and shares valuable experiences from lessons learned from the system installation to its early commissioning. In particular, the background noise relative to the signal-to-noise ratio and the NMS signal interlock are elaborated. The results of the count rates with the neutron source and the effects of the discriminator threshold are summarized.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2003.06a
• /
• pp.94-97
• /
• 2003

In this Paper, propose for MLP(multilayer perception) neural network that uses optimization recognition training scheme for the wavelet transform and the numeral image add to noise, and apply this system in Numeral Recognition. As important part of original image information preserves maximum using the wavelet transform, node number of neural network and the loaming convergence time did size of input vector so that decrease. Apply in training vector, examine about change of the recognition rate as optimization recognition training scheme raises noise of data gradually. We used original image and original image added 0, 10, 20, 30, 40, 50㏈ noise (or the increase of numeral recognition rate. In case of test image added 30∼50㏈, numeral recognition rate between the original image and image added noise for training Is a little But, in case of test image added 0∼20㏈ noise, the image added 0, 10, 20, 30, 40 , 50㏈ noise is used training. Then numeral recognition rate improved 9 percent.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.4
• /
• pp.338-344
• /
• 2002

In this paper, neural network force tracking control is proposed. The conventional impedance function is reformulated to have direct farce tracking capability. Neural network is used to compensate for all the uncertainties such as unknown robot dynamics, unknown environment stiffness, and unknown environment position. On line training signal of farce error for neural network is formulated. A large x-y table is built as a test-bed and neural network loaming algorithm is implemented on a DSP board mounted in a PC. Experimental studies of farce tracking on unknown environment for x-y table robot are presented to confirm the performance of the proposed technique.

• Proceedings of the KIEE Conference
• /
• 2002.11c
• /
• pp.529-532
• /
• 2002

This research treated development of real time pitch tracer for training of musical tune of speech signal and pre-processing and post-processing technics were proposed to get higher accuracy in extraction of pitch. Autocorrelation Function was used to get pitch frequency from 64Hz to 980Hz in real time. Half Rectifier method and Envelop extraction method as a pre-processing was used to get higher accuracy in pitch detection, and improved results were obtained on noised speech signal. Post-processing method using periodicity of Autocorrelation was proposed to get higher accuracy in the high frequency region.

• Journal of the Institute of Convergence Signal Processing
• /
• v.18 no.1
• /
• pp.1-5
• /
• 2017

It is important to train lower limb muscle strength using a tilting table to recover the lower extremity function of hemiplegia patients. It is known that the foot deformity and poor posture of hemiplegia patients can reduce the effectiveness of lower limb rehabilitation training. In this study, we developed a sensor system that can measure the foot pressure distribution of the patients for the load control of the lower extremity during lower limb rehabilitation training and it can be substituted for conventional high-cost technologies.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.13 no.2
• /
• pp.11-19
• /
• 1993

It is very essential to get the accurate classification of defects in primary pressure vessel weld for the safety of nuclear power plant. The signal analysis using the digital signal processing and pattern recognition is performed to classify UT defects extracting feature vector from ultrasonic signals. The minimum distance classifier and the maximum likelihood classifier based on statistics were applied in this experiment to discriminate ultrasonics data obtained form both the training specimens (slit, hole) and the testing specimens(crack, slag). The classification rate was measured using pattern classifier. Results of this study show the promise in solving the many flaw classification problems that exist today.

• Korean Journal of Applied Biomechanics
• /
• v.16 no.4
• /
• pp.1-12
• /
• 2006

This research was to know EMG tendency on increasing record in snatch weightlifting. In order to perform this research, we choiced 3 man national weightlifters, EMG analysis were executed on 8 major muscle(Latissimus Dorsi, Trapezius, Anterior Deltoid, Posterior Deltoid, Gastrocenemius, Vastus Medialis, Erector spinae, Abdominal). First trial record of athletics is 80% of each maximal record and increase the $5{\sim}10kg$ gradually. In this study, EMG signal scale of all muscle except posterior Deltoid muscle don't increased according to increasing the barbell weight, This showed a difference between general recognition and experiment result. In posterior Deltoid muscle, EMG signal scale increased according to increasing the barbell weight. It was assumed that EMG signal of protagonist shows possibility of linear increasing if motion have a consistency. It was assumed that In present, In order to increase one's record to $5{\sim}10kg$, Motion consistency training is more effective training method than increasing the muscle force.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2001.06a
• /
• pp.101-104
• /
• 2001

In this paper, we propose the Digital Automatic Gain Controller for IEEE 802.11a High-speed Physical Layer in the 5 GHz Band. The input gain is estimated by calculating the energy of the training symbol that is a synchronizing signal. The renewal gain is calculated by comparing the estimated gain with the ideal gain. The renewal gain is converted into the controlled voltage for GCA to reduce or amplify the input signals. We used a piecewise-linear approximation to reduce the hardware size. The gain control is performed seven times to provide more accurate gain control. The proposed automatic gain controller is designed with VHDL and verified by using the Xilinx FPGA.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.3 no.1
• /
• pp.58-65
• /
• 2000

A target signal simulation method for passive sonar systems is introduced. The method uses multirate signal processing techniques to simulate moving target signals in the multi-path sound propagation environment by introducing Lloyd's mirror and Doppler effect. Time and frequency variation of target signal due to the target maneuvering is also considered to provide realistic ship signatures in the LOFAR gram so that the simulated target is used for sonar operator training. Synthesized target characteristics is analyzed and compared with real target signal in terms of interference pattern and frequency variation in the LOFAR gram.