• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.341-343
• /
• 2019

As the generation of high concentration particulate matter increases, much attention is focused on the prediction of particulate matter. Particulate matter refers to particulate matter less than $10{\mu}m$ diameter in the atmosphere and is affected by weather changes such as temperature, relative humidity and wind speed. Therefore, various studies have been conducted to analyze the correlation with weather information for particulate matter prediction. However, the nonlinear time series distribution of particulate matter increases the complexity of the prediction model and can lead to inaccurate predictions. In this paper, we try to mitigate the nonlinear characteristics of particulate matter by using cluster algorithm and classification algorithm of machine learning. The machine learning algorithms used are agglomerative clustering, density-based spatial clustering of applications with noise(DBSCAN).

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.10
• /
• pp.1275-1281
• /
• 2019

The automatic modulation recognition of a radio signal is a major task of an intelligent receiver, with various civilian and military applications. In this paper, we propose a method to recognize the modulation of radio signals in wireless communication based on the deep neural network. We classify the modulation pattern of radio signal by using the LSTM model, which can catch the long-term pattern for the sequential data as the input data of the deep neural network. The amplitude and phase of the modulated signal, the in-phase carrier, and the quadrature-phase carrier are used as input data in the LSTM model. In order to verify the performance of the proposed learning method, we use a large dataset for training and test, including the ten types of modulation signal under various signal-to-noise ratios.

• Journal of the Korea Society for Simulation
• /
• v.29 no.4
• /
• pp.21-31
• /
• 2020

NCTR(Non-Cooperative Target Recognition) refers to the function of radar to identify target on its own without support from other systems such as ELINT(ELectronic INTelligence). ISAR(Inverse Synthetic Aperture Radar) image is one of the representative methods of NCTR, but it is difficult to automatically classify the target without an identification database due to the significant changes in the image depending on the target's maneuver and location. In this study, we discuss how to build an identification database using simulation and deep-learning technique even when actual images are insufficient. To simulate ISAR images changing with various radar operating environment, A model that generates and learns images through the process named 'Perfect scattering image,' 'Lost scattering image' and 'JEM noise added image' is proposed. And the learning outcomes of this model show that not only simulation images of similar shapes but also actual ISAR images that were first entered can be classified.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1589-1605
• /
• 2022

Phase unwrapping is an essential procedure for interferometric synthetic aperture radar techniques. Accordingly, a lot of phase unwrapping methods have been developed. Deep-learning-based unwrapping methods have recently been proposed. In this paper, we reviewed state-of-the-art deep-learning-based unwrapping approaches in terms of 1) the approaches to predicting unwrapped phases, 2) deep learning model structures for phase unwrapping, and 3) training data generation. The research trend of the approaches to predicting unwrapped phases was introduced by categorizing wrap count segmentation, phase jump classification, phase regression, and deep-learning-assisted method. We introduced the case studies of deep learning model structure for phase unwrapping, and model structure optimization to relate the overall phase information. In addition, we summarized the research trend of the training data generation approaches in the views of phase gradient and noise in the main. And the future direction in deep-learning-based phase unwrapping was presented. It is expected that this paper is used as guideline for exploring future direction of deep-learning-based phase unwrapping research in Korea.

• Analytical Science and Technology
• /
• v.35 no.2
• /
• pp.69-81
• /
• 2022

The method of measuring and classifying the energy category of neutrons directly using raw data acquired through a CZT detector is not satisfactory, in terms of accuracy and efficiency, because of its poor energy resolution and low measurement efficiency. Moreover, this method of measuring and analyzing the characteristics of low-energy or low-activity gamma-ray sources might be not accurate and efficient in the case of neutrons because of various factors, such as the noise of the CZT detector itself and the influence of environmental radiation. We have therefore developed an efficient method of analyzing radiation characteristics using a neutron and gamma-ray analysis algorithm for the rapid and clear identification of the type, energy, and radioactivity of gamma-ray sources as well as the detection and classification of the energy category (fast or thermal neutrons) of neutron sources, employing raw data acquired through a CZT detector. The neutron analysis algorithm is based on the fact that in the energy-spectrum channel of 558.6 keV emitted in the nuclear reaction ¹¹³Cd + ¹n → ¹¹⁴Cd + in the CZT detector, there is a notable difference in detection information between a CZT detector without a PE modulator and a CZT detector with a PE modulator, but there is no significant difference between the two detectors in other energy-spectrum channels. In addition, the gamma-ray analysis algorithm uses the difference in the detection information of the CZT detector between the unique characteristic energy-spectrum channel of a gamma-ray source and other channels. This efficient method of analyzing radiation characteristics is expected to be useful for the rapid radiation detection and accurate information collection on radiation sources, which are required to minimize radiation damage and manage accidents in national disaster situations, such as large-scale radioactivity leak accidents at nuclear power plants or nuclear material handling facilities.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.905-910
• /
• 2022

Drowsy driving requires a lot of social attention because it increases the incidence of traffic accidents and leads to fatal accidents. The number of accidents caused by drowsy driving is increasing every year. Therefore, in order to solve this problem all over the world, research for measuring various biosignals is being conducted. Among them, this paper focuses on non-contact biosignal analysis. Various noises such as engine, tire, and body vibrations are generated in a running vehicle. To measure the driver's heart rate and respiration rate in a driving vehicle with a piezoelectric sensor, a sensor plate that can cushion vehicle vibrations was designed and noise generated from the vehicle was reduced. In addition, we developed a system for classifying whether the driver is sleeping or not by extracting the model using the CNN-LSTM ensemble learning technique based on the signal of the piezoelectric sensor. In order to learn the sleep state, the subject's biosignals were acquired every 30 seconds, and 797 pieces of data were comparatively analyzed.

• Journal of Biomedical Engineering Research
• /
• v.43 no.4
• /
• pp.185-192
• /
• 2022

Early detection of mild cognitive impairment can help prevent the progression of dementia. The purpose of this study was to design and validate a machine learning model that automatically differential diagnosed patients with mild cognitive impairment and identified cognitive decline characteristics compared to a control group with normal cognition using resting-state quantitative electroencephalogram (qEEG) with eyes closed. In the first step, a rectified signal was obtained through a preprocessing process that receives a quantitative EEG signal as an input and removes noise through a filter and independent component analysis (ICA). Frequency analysis and non-linear features were extracted from the rectified signal, and the 3067 extracted features were used as input of a linear support vector machine (SVM), a representative algorithm among machine learning algorithms, and classified into mild cognitive impairment patients and normal cognitive adults. As a result of classification analysis of 58 normal cognitive group and 80 patients in mild cognitive impairment, the accuracy of SVM was 86.2%. In patients with mild cognitive impairment, alpha band power was decreased in the frontal lobe, and high beta band power was increased in the frontal lobe compared to the normal cognitive group. Also, the gamma band power of the occipital-parietal lobe was decreased in mild cognitive impairment. These results represented that quantitative EEG can be used as a meaningful biomarker to discriminate cognitive decline.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.2
• /
• pp.210-217
• /
• 2022

Passive source depth estimation has been studied for decades since the source depth can be used for target classification, target tracking, etc. The purpose of this paper is to solve the problem of ambiguity in the previous paper [S.-il. Cho et al. (in Korean), J. Acoust. Soc. Kr. 38, 120-127 (2019)] that source depth is estimated in two points. The patterns of phase shift of Channel Impulse Response(CIR) reflected in ocean surface and bottom is used for removing ambiguity of the source depth estimation, and after removing ambiguity, source depth is estimated at one point through the intersection of CIR. In order to extract CIR in case of unknown source signal and continuous signal or noise, Ray-based blind deconvolution is used. The proposed algorithm is demonstrated through numerical simulation in ocean waveguide.

• Journal of Information Processing Systems
• /
• v.19 no.3
• /
• pp.289-301
• /
• 2023

Due to the development and dissemination of modern technology, anyone can easily communicate using services such as social network service (SNS) through a personal computer (PC) or smartphone. The development of these technologies has caused many beneficial effects. At the same time, bad effects also occurred, one of which was the spam problem. Spam refers to unwanted or rejected information received by unspecified users. The continuous exposure of such information to service users creates inconvenience in the user's use of the service, and if filtering is not performed correctly, the quality of service deteriorates. Recently, spammers are creating more malicious spam by distorting the image of spam text so that optical character recognition (OCR)-based spam filters cannot easily detect it. Fortunately, the level of transformation of image spam circulated on social media is not serious yet. However, in the mail system, spammers (the person who sends spam) showed various modifications to the spam image for neutralizing OCR, and therefore, the same situation can happen with spam images on social media. Spammers have been shown to interfere with OCR reading through geometric transformations such as image distortion, noise addition, and blurring. Various techniques have been studied to filter image spam, but at the same time, methods of interfering with image spam identification using obfuscated images are also continuously developing. In this paper, we propose a deep learning-based spam image detection model to improve the existing OCR-based spam image detection performance and compensate for vulnerabilities. The proposed model extracts text features and image features from the image using four sub-models. First, the OCR-based text model extracts the text-related features, whether the image contains spam words, and the word embedding vector from the input image. Then, the convolution neural network-based image model extracts image obfuscation and image feature vectors from the input image. The extracted feature is determined whether it is a spam image by the final spam image classifier. As a result of evaluating the F1-score of the proposed model, the performance was about 14 points higher than the OCR-based spam image detection performance.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.5
• /
• pp.441-446
• /
• 2009

This paper proposes an automatic indexing algorithm of golf video using audio information. In the proposed algorithm, the input audio stream is demultiplexed into the stream of video and audio. By means of Adaboost-cascade classifier, the continuous audio stream is classified into announcer's speech segment recorded in studio, music segment accompanied with players' names on TV screen, reaction segment of audience according to the play, reporter's speech segment with field background, filed noise segment like wind or waves. And golf swing sound including drive shot, iron shot, and putting shot is detected by the method of impulse onset detection and modulation spectrum verification. The detected swing and applause are used effectively to index action or highlight unit. Compared with video based semantic analysis, main advantage of the proposed system is its small computation requirement so that it facilitates to apply the technology to embedded consumer electronic devices for fast browsing.