• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4664-4681
• /
• 2020

Modulation recognition (MR) plays a key role in cognitive radar, cognitive radio, and some other civilian and military fields. While existing methods can identify the signal modulation type by extracting the signal characteristics, the quality of feature extraction has a serious impact on the recognition results. In this paper, an end-to-end MR method based on long short-term memory (LSTM) and the gated recurrent unit (GRU) is put forward, which can directly predict the modulation type from a sampled signal. Additionally, the sliding window method is applied to fast-changing mixed-modulation signals for which the signal modulation type changes over time. The recognition accuracy on training datasets in different SNR ranges and the proportion of each modulation method in misclassified samples are analyzed, and it is found to be reasonable to select the evenly-distributed and full range of SNR data as the training data. With the improvement of the SNR, the recognition accuracy increases rapidly. When the length of the training dataset increases, the neural network recognition effect is better. The loss function value of the neural network decreases with the increase of the training dataset length, and then tends to be stable. Moreover, when the fast-changing period is less than 20ms, the error rate is as high as 50%. As the fast-changing period is increased to 30ms, the error rates of the GRU and LSTM neural networks are less than 5%.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.379-381
• /
• 2011

The image signal is often affected by the existence of noise, noise can occur during image capture, transmission or processing phases. noises caused the degradation phenomenon and demage the original signal information. Many studies are being accomplished to restore those signals which corrupted by mixed noise. In this paper, we proposed mixed weighted filter for removing Gaussian and impulse noise. we first charge the noise type, then, Gaussian is removed by a weighted mean filter and impulse noise is removed by self-adaptive weighted median filter that can not only remove mixed noise but also preserve the details. And through the simulation, we compared with the conventional algorithms and indicated that proposed method significant improvement over many other existing algorithms and can preserve image details efficiently.

• Journal of the Institute of Convergence Signal Processing
• /
• v.13 no.2
• /
• pp.63-69
• /
• 2012

Noise is regarded as an unwanted component of the image because it significantly reduces image quality. And image is often corrupted by mixed noise. In this paper an efficient modified weighted filter algorithm which combines spatial weight and intensity weight is proposed for removing mixed noise. In the proposed method, the filtering mask is separated into the four sub-windows and the parameters of the weights are confirmed by calculating local standard deviation and the mean of four sub-windows' standard deviations. Considering the spatial information and intensity information, the proposed method has good performance on not only noise elimination but also preservation of details. Simulation results demonstrate that the proposed method performs better than conventional algorithms.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.44 no.2 s.314
• /
• pp.10-17
• /
• 2007

The echo signal on ultrasonic transducer is a mixed signal from tissues, blood vessel walls, blood cells and noise. In this mixed-signal, the signal reflected from tissues and blood vessel walls is called clutter. It is necessary to extract pure blood signal from this mixed-signal, when measuring blood flow velocity with medical ultrasonic system The quality of measured blood flow velocity is highly dependent on sufficient attenuation of the clutter signals. In this paper, we suggest a clutter rejection method using ICA For simulation, the echo signals are generated by Field n ultrasonic simulation program In this echo signals, independent signals are separated by using ICA Then the blood signal is obtained from the separated signals. Blood flow velocity is measured by 2D autocorrelation method. We compare ICA clutter rejection method with PCA-based eigen filter method using both measured blood flow velocity profiles by 2D autocorrelation. In simulation results, ICA clutter rejection method can be better applied measuring blood flow velocity in noisy echo signals.

• Imaging Science in Dentistry
• /
• v.35 no.4
• /
• pp.207-213
• /
• 2005

Purpose: To classify and describe the characteristic features of MRI of some ameloblastoma variants. Materials and Methods: The MR images, CT images, and panoramic radiographs in 5 cases were retrospectively examined as follows. First, the contents of ameloblastomas were devided into two portions of either solid or cystic components on the basis of MR signal intensities. The signal intensity within the solid or cystic portions was classified as homogeneous or heterogeneous. Next, the characteristic internal feature of the lesion on T1W1 or T2WI was described. The signal intensities were classified into low, intermediate, slightly high, high, and strong high signal intensity. Results: Unicystic lesion showed homogeneous high signal intensity (SI) on T2W2 and the rim enhancement of the surrounding area including the mural nodule and the thick wall except the central portion on Gd- T1W1. Solid type revealed heterogeneous and high SI area with strong high SI area on T2W2. On Gd- T1W1, the area corresponding to the low signal spot on T1W1 and the strong high signal spot on T2W1 showed low SI. Hybrid type showed slightly enhanced capsular structures and low SI for the round bony septa and the areas connecting the mixed and cystic lesions on T2Wl and Gd-T1W1. Conclusion: MRI could easily assess the relationship between the mixed and cystic findings in ameloblastoma.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.62 no.6
• /
• pp.825-832
• /
• 2013

In this study, Independent Component Analysis (ICA) algorithms are suggested to extract the original ECG part from the mixed signal contaminated with the unwanted frequency components and especially 60Hz power line disturbances. With this aim, we implement a novel method to suppress the baseline-wandering disturbances and power line artefacts contained in patch-electrodes sensory ECG data by separating the unmixed signal with finding the optimal weight W based on Kurtosis value. With applying brutal force and gradient ascent searching algorithm to find W, we can conclude that the unwanted frequency components especially in the ambulatory ECG data can be eliminated by Independent Component Analysis.

• ETRI Journal
• /
• v.32 no.1
• /
• pp.154-156
• /
• 2010

Oscillation-based testing of analog-to-digital converters represents a viable option for low-cost built-in self-testing in mixed-signal design. While numerous papers have addressed implementation issues, little attention has been paid to the measurement accuracy. In this letter, we highlight an inherent measurement uncertainty which has to be considered when deriving the parameters from the oscillation frequency.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.633-634
• /
• 2006

A new specification-based analog and mixed-signal test technique using high performance current sensors is proposed. The proposed technique using current sensors built in external ATE has little hardware overhead in circuit under test and high testability without time consuming operation of test point placement algorithm.

• The Magazine of the IEIE
• /
• v.30 no.9
• /
• pp.957-964
• /
• 2003

• The Magazine of the IEIE
• /
• v.19 no.6
• /
• pp.46-54
• /
• 1992