• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.115-117
• /
• 2021

Currently, as IoT technology develops, monitoring systems are being used in various fields, and image processing is being used in various forms. Image data causes noise due to various causes during the transmission and reception process, and if it is not removed, loss of image information or error propagation occurs. Therefore, denoising images is essential. Typical methods of eliminating Salt and Pepper noise in images include AF, MF, and A-TMF. However, existing methods have the disadvantage of being somewhat inadequate in high-density noise. Therefore, in this paper, we propose an algorithm for determining noise for Salt and Pepper denoising and replacing the central pixel with an original pixel if it is non-noise, and processing the filtering mask by segmenting and averaging it in eight directions. We evaluate the performance by comparing and analyzing the proposed algorithms with existing methods.

• International Journal of Computer Science & Network Security
• /
• v.23 no.7
• /
• pp.1-8
• /
• 2023

An Orthogonal Frequency Division Multiplexing (OFDM) based wireless communication system has drawn wide attention for its high transmission rate and high spectrum efficiency in not only radio but also Underwater Acoustic (UWA) applications. Because of the narrow sub-carrier spacing of OFDM, orthogonality between sub-carriers is easily affected by Doppler effect caused by the movement of transmitter or receiver. Previously, Doppler compensation signal processing algorithm for Desired propagation path was proposed. However, other Doppler shifts caused by delayed Undesired signal arriving from different directions cannot be perfectly compensated. Then Receiver Bit Error Rate (BER) is degraded by Inter-Carrier-Interference (ICI) caused in the case of Multi-path Doppler channel. To mitigate the ICI effect, a modified Delay and Doppler Profiler (mDDP), which estimates not only attenuation, relative delay and Doppler shift but also sampling clock shift of each multi-path component, is proposed. Based on the outputs of mDDP, an ICI canceling multi-tap equalizer is also proposed. Computer simulated performances of one-tap equalizer with the conventional Time domain linear interpolated Channel Transfer Function (CTF) estimator, multi-tap equalizer based on mDDP are compared. According to the simulation results, BER improvement has been observed. Especially, in the condition of 16QAM modulation, transmitting vessel speed of 6m/s, two-path multipath channel with direct path and ocean surface reflection path; more than one order of magnitude BER reduction has been observed at CNR=30dB.

• Journal of Positioning, Navigation, and Timing
• /
• v.12 no.4
• /
• pp.359-367
• /
• 2023

In order to ensure the high-integrity of reference stations of satellite navigation system, cycle slip should be precisely monitored and compensated. In this paper, we proposed a cycle slip algorithm for the integrity monitoring of the reference stations. Unlike the legacy method using the Melbourne-Wübbena (MW) combination and ionosphere combination, the proposed algorithm is based on ionosphere combination only, which uses high precision carrier phase observations without pseudorange observations. Two independent and complementary ionosphere combinations, Ionospheric Negative (IN) and Ionospheric Positive (IP), were adopted to avoid insensitive cycle slip pairs. In addition, a second-order time difference was applied to the IN and IP combinations to minimize the influence of ionospheric and tropospheric delay even under severe atmosphere conditions. Then, the cycle slip was detected by the thresholds determined based on error propagation rules, and the cycle slip was identified through weighted least square method. The performance of the proposed cycle slip algorithm was validated with the 1 Hz dual-frequency carrier phase data collected under the difference levels of ionospheric activities. For this experiment, 15 insensitive cycle slip pairs were intentionally inserted into the raw carrier phase observations, which is difficult to be detected with the traditional cycle slip approach. The results indicate that the proposed approach can successfully detect and compensate all of the inserted cycle slip pairs regardless of ionospheric activity. As a consequence, the proposed cycle slip algorithm is confirmed to be suitable for the reference station where real time high-integrity monitoring is crucial.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.4
• /
• pp.229-236
• /
• 2010

Phase coherent modulation techniques in underwater acoustic channel can improve bandwidth efficiency and data reliability, but they are made difficult by time-varying intersymbol interference. This paper proposes an adaptive equalizer combined with phase estimator which compensates distortions caused by time-varying multipath and phase variation. The experiment in the East sea demonstrates phase coherent signals are distorted by time-varying multipath propagation and the proposed scheme equalizes them. Bit error rate of BPSK and QPSK are 0.0078 and 0.0376 at 300 meter horizontal distance and 0.0146 and 0.0293 at 1000 meter respectively.

• The Journal of Engineering Geology
• /
• v.30 no.4
• /
• pp.457-468
• /
• 2020

Problems arising during pile design works for plant construction, civil and architecture work are mostly come from uncertainty of geotechnical characteristics. In particular, obtaining the N-value measured through the Standard Penetration Test (SPT) is the most important data. However, it is difficult to obtain N-value by drilling investigation throughout the all target area. There are many constraints such as licensing, time, cost, equipment access and residential complaints etc. it is impossible to obtain geotechnical characteristics through drilling investigation within a short bidding period in overseas. The geotechnical characteristics at non-drilling investigation points are usually determined by the engineer's empirical judgment, which can leads to errors in pile design and quantity calculation causing construction delay and cost increase. It would be possible to overcome this problem if N-value could be predicted at the non-drilling investigation points using limited minimum drilling investigation data. This study was conducted to predicted the N-value using an Artificial Neural Network (ANN) which one of the Artificial intelligence (AI) method. An Artificial Neural Network treats a limited amount of geotechnical characteristics as a biological logic process, providing more reliable results for input variables. The purpose of this study is to predict N-value at the non-drilling investigation points through patterns which is studied by multi-layer perceptron and error back-propagation algorithms using the minimum geotechnical data. It has been reviewed the reliability of the values that predicted by AI method compared to the measured values, and we were able to confirm the high reliability as a result. To solving geotechnical uncertainty, we will perform sensitivity analysis of input variables to increase learning effect in next steps and it may need some technical update of program. We hope that our study will be helpful to design works in the future.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.127-142
• /
• 2016

Deep learning model is a kind of neural networks that allows multiple hidden layers. There are various deep learning architectures such as convolutional neural networks, deep belief networks and recurrent neural networks. Those have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. Among those architectures, convolutional neural networks and recurrent neural networks are classified as the supervised learning model. And in recent years, those supervised learning models have gained more popularity than unsupervised learning models such as deep belief networks, because supervised learning models have shown fashionable applications in such fields mentioned above. Deep learning models can be trained with backpropagation algorithm. Backpropagation is an abbreviation for "backward propagation of errors" and a common method of training artificial neural networks used in conjunction with an optimization method such as gradient descent. The method calculates the gradient of an error function with respect to all the weights in the network. The gradient is fed to the optimization method which in turn uses it to update the weights, in an attempt to minimize the error function. Convolutional neural networks use a special architecture which is particularly well-adapted to classify images. Using this architecture makes convolutional networks fast to train. This, in turn, helps us train deep, muti-layer networks, which are very good at classifying images. These days, deep convolutional networks are used in most neural networks for image recognition. Convolutional neural networks use three basic ideas: local receptive fields, shared weights, and pooling. By local receptive fields, we mean that each neuron in the first(or any) hidden layer will be connected to a small region of the input(or previous layer's) neurons. Shared weights mean that we're going to use the same weights and bias for each of the local receptive field. This means that all the neurons in the hidden layer detect exactly the same feature, just at different locations in the input image. In addition to the convolutional layers just described, convolutional neural networks also contain pooling layers. Pooling layers are usually used immediately after convolutional layers. What the pooling layers do is to simplify the information in the output from the convolutional layer. Recent convolutional network architectures have 10 to 20 hidden layers and billions of connections between units. Training deep learning networks has taken weeks several years ago, but thanks to progress in GPU and algorithm enhancement, training time has reduced to several hours. Neural networks with time-varying behavior are known as recurrent neural networks or RNNs. A recurrent neural network is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior. Unlike feedforward neural networks, RNNs can use their internal memory to process arbitrary sequences of inputs. Early RNN models turned out to be very difficult to train, harder even than deep feedforward networks. The reason is the unstable gradient problem such as vanishing gradient and exploding gradient. The gradient can get smaller and smaller as it is propagated back through layers. This makes learning in early layers extremely slow. The problem actually gets worse in RNNs, since gradients aren't just propagated backward through layers, they're propagated backward through time. If the network runs for a long time, that can make the gradient extremely unstable and hard to learn from. It has been possible to incorporate an idea known as long short-term memory units (LSTMs) into RNNs. LSTMs make it much easier to get good results when training RNNs, and many recent papers make use of LSTMs or related ideas.

• Journal of Navigation and Port Research
• /
• v.46 no.3
• /
• pp.179-190
• /
• 2022

In this study, we investigated the characteristic impedance and bandwidth of CPW3DCS (coplanar waveguide employing periodic 3D coupling structures), and examined its potential for the development of a marine radio communication FISoC (fully-integrated system on chip) semiconductor device. To extract bandwidth and characteristic impedance of the CPW3DC, we induced a measurement-based equation reflecting measured insertion loss, and compared the measured results of the propagation constant β and characteristic impedance with the measured ones. According to the results of the comparison, the calculated results show a good agreement with the measured ones. Concretely, the propagation constant β and characteristic impedance exhibited an maximum error of 3.9% and 6.4%, respectively. According to the results of this study, in a range of LT = 30 ~ 150 ㎛ for the length of periodic structures, the CPW3DC exhibited a passband characteristic of 121 GHz, and a very small dependency of characteristic impedance on frequency. We could realize a low impedance transmission line with a characteristic impedance lower than 20 Ω by using CPW3DCS with a line width of 20 ㎛, which was highly reduced, compared with a 3mm line width of conventional transmission line with the same impedance. The characteristic impedance was easily adjusted by changing LT. The above results indicate that the CPW3DC can be usefully used for the development of a wireless communication FISoC (fully-integrated system on chip) semiconductor device. This is the first report of a study on the bandwidth of the CPW3DC.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.33 no.6
• /
• pp.2293-2302
• /
• 2013

Flood inundation map has been used as a fundamental information in flood risk management. However, there are various sources of uncertainty in flood inundation mapping, which can be another risk in preventing damage from flood. Therefore, it is necessary to remove or reduce uncertainty sources to improve the accuracy of flood inundation maps. However, the entire removal of uncertainty source may be impossible and inefficient due to limitations of knowledge and finance. Sensitivity analysis of uncertainty sources allows an efficient flood risk management by considering various conditions in flood inundation mapping because an uncertainty source under different conditions may propagate in different ways. The objectives of this study are (1) to perform sensitivity analysis of uncertainty sources by different conditions on flood inundation map using the FOA method and (2) to find a major contributor to a propagated uncertainty in the flood inundation map in Flatrock at Columbus, U.S.A. Result of this study illustrates that an uncertainty in a variable is differently propagated to flood inundation map by combination with other uncertainty sources. Moreover, elevation error was found to be the most sensitive to uncertainty in the flood inundation map of the study reach.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.42 no.5 s.305
• /
• pp.27-34
• /
• 2005

Ventricular fibrillation(VF) is generally caused by chaotic behavior of electrical propagation in heart and may result in sudden cardiac death. In this study, we proposed a ventricular fibrillation detection algorithm based on support vector machine classifier, which could offer benefits to reduce the teaming costs as well as good classification performance. Before the extraction of input features, raw ECG signal was applied to preprocessing procedures, as like wavelet transform based bandpass filtering, R peak detection and segment assignment for feature extraction. We selected input features which of some are related to the rhythm information and of others are related to wavelet coefficients that could describe the morphology of ventricular fibrillation well. Parameters for SVM classifier, C and ${\alpha}$, were chosen as 10 and 1 respectively by trial and error experiments. Each average performance for normal sinus rhythm ventricular tachycardia and VF, was 98.39%, 96.92% and 99.88%. And, when the VF detection performance of SVM classifier was compared to that of multi-layer perceptron and fuzzy inference methods, it showed similar or higher values. Consequently, we could find that the proposed input features and SVM classifier would one of the most useful algorithm for VF detection.

• Journal of radiological science and technology
• /
• v.26 no.1
• /
• pp.71-82
• /
• 2003

In this paper, I proposed a classifier of liver cirrhotic step using T1-weighted MRI(magnetic resonance imaging) and hierarchical neural network. The data sets for classification of each stage, which were normal, 1type, 2type and 3type, were obtained in Pusan National University Hospital from June 2001 to december 2001. And the number of data was 46. We extracted liver region and nodule region from T1-weighted MR liver image. Then objective interpretation classifier of liver cirrhotic steps in T1-weighted MR liver images. Liver cirrhosis classifier implemented using hierarchical neural network which gray-level analysis and texture feature descriptors to distinguish normal liver and 3 types of liver cirrhosis. Then proposed Neural network classifier teamed through error back-propagation algorithm. A classifying result shows that recognition rate of normal is 100%, 1type is 82.3%, 2type is 86.7%, 3type is 83.7%. The recognition ratio very high, when compared between the result of obtained quantified data to that of doctors decision data and neural network classifier value. If enough data is offered and other parameter is considered, this paper according to we expected that neural network as well as human experts and could be useful as clinical decision support tool for liver cirrhosis patients.