• Journal of Korea Multimedia Society
• /
• v.25 no.5
• /
• pp.676-684
• /
• 2022

As realistic media are widespread in various image processing areas, image or video compression is one of the key technologies to enable real-time applications with limited network bandwidth. Generally, image or video compression cause the unnecessary compression artifacts, such as blocking artifacts and ringing effects. In this study, we propose a Deep Residual Channel-attention Network, so called DRCAN, which consists of an input layer, a feature extractor and an output layer. Experimental results showed that the proposed DRCAN can reduced the total memory size and the inference time by as low as 47% and 59%, respectively. In addition, DRCAN can achieve a better peak signal-to-noise ratio and structural similarity index measure for compressed images compared to the previous methods.

• The Journal of the Acoustical Society of Korea
• /
• v.36 no.2
• /
• pp.144-150
• /
• 2017

Musical genre is indispensible in constructing music information retrieval system, such as music search and classification. In general, the spectral characteristics of a music signal are obtained based on a subband decomposition to represent the relative distribution of the harmonic and the non-harmonic components. In this paper, we investigate the subband decomposition parameters in extracting features, which improves musical genre classification accuracy. In addition, the linear projection methods are studied to reduce the resulting feature dimension. Experiments on the widely used music datasets confirmed that the subband decomposition finer than the widely-adopted octave scale is conducive in improving genre-classification accuracy and showed that the feature-dimension reduction is effective reducing a classifier's computational complexity.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.2
• /
• pp.280-286
• /
• 2013

In this paper, a noise reduction system is proposed for the speech interface in intelligent TV applications. To reduce TV speaker sound which are very serious noises degrading recognition performance, a noise reduction algorithm utilizing the direct TV sound as the reference noise input is implemented. In the proposed algorithm, transfer functions are estimated to compensate for the difference between the direct TV sound and that recorded with the microphone installed on the TV frame. Then, the noise power spectrum in the received signal is calculated to perform Wiener filter-based noise cancellation. Additionally, a postprocessing step is applied to reduce remaining noises. Experimental results show that the proposed algorithm shows 88% recognition rate for isolated Korean words at 5 dB input SNR.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.6
• /
• pp.2485-2492
• /
• 2018

The rapid development of large-scale integrated circuits has brought great challenges to the circuit testing and diagnosis, and due to the lack of exact fault models, inaccurate analog components tolerance, and some nonlinear factors, the analog circuit fault diagnosis is still regarded as an extremely difficult problem. To cope with the problem that it's difficult to extract fault features effectively from masses of original data of the nonlinear continuous analog circuit output signal, a novel approach of feature extraction and dimension reduction for analog circuit fault diagnosis based on wavelet packet decomposition, local linear embedding algorithm, and clone selection algorithm (WPD-LLE-CSA) is proposed. The proposed method can identify faulty components in complicated analog circuits with a high accuracy above 99%. Compared with the existing feature extraction methods, the proposed method can significantly reduce the quantity of features with less time spent under the premise of maintaining a high level of diagnosing rate, and also the ratio of dimensionality reduction was discussed. Several groups of experiments are conducted to demonstrate the efficiency of the proposed method.

• Structural Monitoring and Maintenance
• /
• v.5 no.1
• /
• pp.111-127
• /
• 2018

Horizontal displacement of high-rise building is an essential index for assessing the structural performance and safety. In this paper, a novel inclinometer-based method is proposed to address this issue and an algorithm based on three spline interpolation principle is presented to estimate the horizontal displacement of high-rise buildings. In this method, the whole structure is divided into different elements by different measured points. The story drift angle curve of each element is modeled as a three spline curve. The horizontal displacement can be estimated after integration of the story drift angle curve. A numerical example is designed to verify the proposed method and the result shows this method can effectively estimate the horizontal displacement with high accuracy. After that, this method is applied to a practical slender structure - Shanghai Tower. Nature frequencies identification and deformation monitoring are conducted from the signal of inclinometers. It is concluded that inclinometer-based technology can not only be used for spectrum analysis and modal identification, but also for monitoring deformation of the whole structure. This inclinometer-based technology provides a novel method for future structural health monitoring.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.35 no.1
• /
• pp.24-31
• /
• 2012

This study is designed to predict the overall electric power load, to apply the method of time sharing and to reduce simultaneous load factor of electric power when authorized by user entering demand plans and using schedules into the user's interface for a certain period of time. This is about smart grid, which reduces electric power load through simultaneous load factor of electric power reduction system supervision agent. Also, this study has the following characteristics. First, it is the user interface which enables authorized users to enter and send/receive such data as demand plan and using schedule for a certain period of time. Second, it is the database server, which collects, classifies, analyzes, saves and manages demand forecast data for a certain period of time. Third, is the simultaneous load factor of electric power control agent, which controls usage of electric power by getting control signal, which is intended to reduce the simultaneous load factor of electric power by the use of the time sharing control system, form the user interface, which also integrate and compare the data which were gained from the interface and the demand forecast data of the certain period of time.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.14 no.1
• /
• pp.57-62
• /
• 2015

The wet brakes used on a forklift often produce noise upon engagement. The elimination or reduction of this squeal noise is an important task for the improvement of the comfort of those operating these machines. In this paper, a test rig was developed for the testing of brake noise, and the squeal noise was measured with this apparatus. Automatic transmission fluid and grooves in the material of the friction-plate pad were found to be the main factors causing squeal noise. In order to identify the characteristics of this type of noise, signal analyses of the noise were conducted using different frequency spectra. The experimental results showed that the viscosity of the automatic transmission fluid and the groove pattern on the friction-plate pad largely affected the reduction of the wet brake squeal noise made by an industrial forklift.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.7 no.3
• /
• pp.475-483
• /
• 2012

The characteristic features of speech signal do not vary significantly from frame to frame. Therefore, it is advisable to reduce the redundancy involved in the similar feature vectors. The objective of this paper is to search for the optimal condition of minimum redundancy and maximum relevancy of the speech feature vectors in speech recognition. For this purpose, we realize redundancy reduction by way of a vigilance parameter and investigate the resultant effect on the speaker-independent speech recognition of isolated words by using FVQ/HMM. Experimental results showed that the number of feature vectors might be reduced by 30% without deteriorating the speech recognition accuracy.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.20 no.3
• /
• pp.201-208
• /
• 2015

The effects of dead-time and offset error, which cause output current distortion in single-phase grid-connected inverters are investigated this paper. Offset error is typically generated by measuring phase current, including the voltage unbalance of analog devices and non-ideal characteristics in current measurement paths. Dead-time inevitably occurs during generation of the gate signal for controlling power semiconductor switches. Hence, the performance of the grid-connected inverter is significantly degraded because of the current ripples. The current and voltage, including ripple components on the synchronous reference frame and stationary reference frame, are analyzed in detail. An algorithm, which has the proportional resonant controller, is also proposed to reduce current ripple components in the synchronous PI current regulator. As a result, computational complexity of the proposed algorithm is greatly simplified, and the magnitude of the current ripples is significantly decreased. The simulation and experimental results are presented to verify the usefulness of the proposed current ripple reduction algorithm.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.20 no.5
• /
• pp.1573-1581
• /
• 1996

This paper present as experimental demonstratio of DSP and a sensory actuator that is used to actively control sound transmission/radiation through a vibrating plate. A plane acoustic wave incident on a clamped, thin circular plate was used as a noise source, and a sensory actuator bounded to the plate was used to control and sense vibration of the plate. The sound transmission reduction problem was tranformed as a structural vibration control problem that actively control the structural vibration modes coupled to acoustic modes. The results show that the first structural vibration mode is controlled with a reduction of 78 percent in the displacement and velocity of the plate. This corresponds to a 13dB reduction in the acoustic response. These experimental results indicate that a sensory actuator bounded to the plate can be employed to attenuate the sound transmitted to radiated from the plate.