• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.1
• /
• pp.99-107
• /
• 2022

In the current technological society, where various technologies are converged into one and being transformed into new technologies, new cyber attacks are being made just as they keep pace with the changes in society. In particular, due to the convergence of various attacks into one, it is difficult to protect the system with only the existing security system. A lot of information is being generated to respond to such cyber attacks. However, recklessly generated vulnerability information can induce confusion by providing unnecessary information to administrators. Therefore, this paper proposes a mechanism to assist in the analysis of emerging cyberattack convergence technologies by providing differentiated vulnerability information to managers by learning documents using deep learning-based language learning models, extracting vulnerability information and classifying them according to the MITRE ATT&CK framework.

• Journal of IKEEE
• /
• v.26 no.4
• /
• pp.568-576
• /
• 2022

Automatic modulation classification(AMC) is a core technique in Software Defined Radio(SDR) platform that enables smart and flexible spectrum sensing and access in a wide frequency band. In this study, we propose a simple yet accurate deep learning-based method that allows AMC for variable-size radio signals. To this end, we design a classification architecture consisting of two Convolutional Neural Network(CNN)-based models, namely main and small models, which were trained on radio signal datasets with two different signal sizes, respectively. Then, for a received signal input with an arbitrary length, modulation classification is performed by augmenting the input samples using a self-replicating padding technique to fit the input layer size of our model. Experiments using the RadioML 2018.01A dataset demonstrated that the proposed method provides higher accuracy than the existing methods in all signal-to-noise ratio(SNR) domains with less computation overhead.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.12
• /
• pp.561-568
• /
• 2021

In recent years, autonomous driving technologies have become a high-value-added technology that attracts attention in the fields of science and industry. For smooth Self-driving, it is necessary to accurately detect an object and estimate its movement speed in real time. CNN-based deep learning algorithms and conventional dense optical flows have a large consumption time, making it difficult to detect objects and estimate its movement speed in real time. In this paper, using a single camera image, fast object detection was performed using the YOLOv5 algorithm, a deep learning algorithm, and fast estimation of the speed of the object was performed by using a local dense optical flow modified from the existing dense optical flow based on the detected object. Based on this algorithm, we present a system that can predict the collision time and probability, and through this system, we intend to contribute to prevent tram accidents.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.650-652
• /
• 2022

Frame rate up-conversion (FRUC) algorithm is an image interpolation technology that improves the frame rate of moving pictures. This solves problems such as screen shake or blurry motion caused by low frame rate video in high-definition digital video systems, and provides viewers with a more free and smooth visual experience. In this paper, we propose a video compression technique using deep learning-based FRUC algorithm. The proposed method compresses and transmits after excluding some images from the original video, and uses a deep learning-based interpolation method in the decoding process to restore the excluded images, thereby compressing them with high efficiency. In the experiment, the compression performance was evaluated using the decoded image and the image restored by the FRUC algorithm after encoding the video by skipping 1 or 3 pages. When 1 and 3 sheets were excluded, the average BD-rate decreased by 81.22% and 27.80%. The reason that excluding three images has lower encoding efficiency than excluding one is because the PSNR of the image reconstructed by the FRUC method is low.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.150-159
• /
• 2022

This paper presents an implementation of detecting whether a helmet is worn and there is a fall accident through individual image analysis in real-time from extracting the image objects of several workers active in the industrial field. In order to detect image objects of workers, YOLO, a deep learning-based computer vision model, was used, and for whether a helmet is worn or not, the extracted images with 5,000 different helmet learning data images were applied. For whether a fall accident occurred, the position of the head was checked using the Pose real-time body tracking algorithm of Mediapipe, and the movement speed was calculated to determine whether the person fell. In addition, to give reliability to the result of a falling accident, a method to infer the posture of an object by obtaining the size of YOLO's bounding box was proposed and implemented. Finally, Telegram API Bot and Firebase DB server were implemented for notification service to administrators.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.115-127
• /
• 2023

Video stabilization is one of the camera technologies that the importance is gradually increasing as the personal media market has recently become huge. For deep learning-based video stabilization, existing methods collect pairs of video datas before and after stabilization, but it takes a lot of time and effort to create synchronized datas. Recently, to solve this problem, unsupervised learning method using only unstable video data has been proposed. In this paper, we propose a network structure that learns the stabilized trajectory only with the unstable video image without the pair of unstable and stable video pair using the Convolutional Auto Encoder structure, one of the unsupervised learning methods. Optical flow data is used as network input and output, and optical flow data was mapped into grid units to simplify the network and minimize noise. In addition, to generate a stabilized trajectory with an unsupervised learning method, we define the loss function that smoothing the input optical flow data. And through comparison of the results, we confirmed that the network is learned as intended by the loss function.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.72-76
• /
• 2021

판례는 일반인 또는 법률 전문가가 사건에 참조하기 위해 가장 먼저 참고할 수 있는 재판의 선례이다. 하지만 이러한 판례의 유용성에도 불구하고 현 대법원 판례 검색 시스템은 판례 검색에 용이하지 않다. 왜냐하면 법률 전문 지식이 없는 일반인은 검색 의도에 부합하는 검색 결과를 정확히 도출하는 데 어려움이 있으며, 법률 전문가는 검색에 많은 시간과 비용이 들게 되기 때문이다. 이미 해외에서는 유사 케이스 매칭 데이터셋을 구축하여 일반인과 전문가로 하여금 유사 판례 검색을 용이하게 할 뿐만 아니라 여러 자연어 처리 태스크에도 활용하고 있다. 하지만 국내에는 법률 AI와 관련하여 오직 법률과 관련한 세부 태스크 수행에 초점을 맞춘 연구가 많으며, 리소스로서의 유사 케이스 매칭 데이터셋은 구축되어 있지 않다. 이에 본 논문에서는 리소스로서의 판례 데이터셋을 위해 딥러닝 알고리즘 중 문서의 의미를 반영할 수 있는 Doc2Vec 임베딩 모델과 SBERT 임베딩 모델을 적용하여 판례 문서 간 유사도를 측정·비교하였다. 그 결과 SBERT 모델을 통해 도출된 유사 판례가 문서 간 내용적 유사성이 높게 나타났으며, 이를 통해 SBERT 모델을 이용하여 유사 판례 매칭 기초 데이터셋을 구축하였다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.86-86
• /
• 2021

온천천은 부산광역시 금정구, 동래구, 연제구를 흐르는 도심 하천으로 부산 시민들의 도심 속 산책길, 자전거 길 등으로 활용되는 도시하천이다. 그러나 온천천 양안의 동래 곡저 평야가 시가지화 되고 온천천 발원지인 금정산 주변에서 무허가 상수도를 사용하고 각종 쓰레기와 하수의 유입으로 인해 하천 전체가 하수관으로 변해왔다. 이에 따라 부산광역시는 온천천 정비 계획을 시행하여 하천 정비와 함께 자동측정망을 설치하여 하천의 DO (dissolved oxygen), 탁도, TDS농도 등 자료를 수집하고 있다. 그러나 자동측정망으로 쌓여가는 데이터를 활용하여 DO농도 예측은 거의 이뤄지지 않고 있다. DO는 하천의 수질 오염 정도를 판단하는 수질인자로 역사적으로 하천 연구의 주요 연구 대상이 되어 왔다. 본 연구에서는 일 자료 뿐만 아니라 시 자료를 기반으로 RNN-LSTM 알고리즘을 활용한 DO예측을 시도하였다. RNN-LSTM은 시계열 학습에 뛰어난 알고리즘으로 인공신경망의 발전된 형태인 순환신경망이다. 연구에 앞서 부산광역시 보건환경정보 공개시스템으로부터 받은 자료 중에서 교정, 보수 중, 비사용, 장비전원단절 등으로 인해 누락데이터를 2014년 1월 1일부터 2018년 12월 31일의 데이터 전수조사 후 이상데이터를 확인하여 선형 보간하여 데이터를 사용하였다. 연구에서는 Google에서 개발한 딥러닝 오픈소스 라이브러리인 텐서플로우를 활용하여 부산광역시 금정구 부곡동에 위치한 부곡교 관측소의 DO농도를 시간 또는 일 예측을 하였다. 일 예측 학습에는 2014년~ 2018년의 기상자료(기온, 상대습도, 풍속, 강수량), DO농도 자료를 사용하였고, 시 예측 학습에는 연속된 자료가 가장 많은 2015년 3월 ~ 12월까지의 데이터를 활용하여 연구를 진행하였다. 모형의 검증을 위해 결정계수(R square)를 이용하여 통계분석을 실시하였다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1103-1108
• /
• 2023

In this paper, we propose a new algorithm for attenuating the background noises in acoustic signal. This algorithm improves the noise attenuation performance by using the FNN(: Full-connected Neural Network) deep learning algorithm instead of the existing adaptive filter after wavelet transform. After wavelet transforming the input signal for each short-time period, noise is removed from a single input audio signal containing noise by using a 1024-1024-512-neuron FNN deep learning model. This transforms the time-domain voice signal into the time-frequency domain so that the noise characteristics are well expressed, and effectively predicts voice in a noisy environment through supervised learning using the conversion parameter of the pure voice signal for the conversion parameter. In order to verify the performance of the noise reduction system proposed in this study, a simulation program using Tensorflow and Keras libraries was written and a simulation was performed. As a result of the experiment, the proposed deep learning algorithm improved Mean Square Error (MSE) by 30% compared to the case of using the existing adaptive filter and by 20% compared to the case of using the STFT(: Short-Time Fourier Transform) transform effect was obtained.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.4
• /
• pp.685-692
• /
• 2024

In this paper, we propose a new CNN model to improve the recognition performance of command voice signals. This method obtains a spectrogram image after performing a short-time Fourier transform (STFT) of the input signal and improves command recognition performance through supervised learning using a CNN model. After Fourier transforming the input signal for each short-time section, a spectrogram image is obtained and multi-classification learning is performed using a CNN deep learning model. This effectively classifies commands by converting the time domain voice signal to the frequency domain to express the characteristics well and performing deep learning training using the spectrogram image for the conversion parameters. To verify the performance of the speech recognition system proposed in this study, a simulation program using Tensorflow and Keras libraries was created and a simulation experiment was performed. As a result of the experiment, it was confirmed that an accuracy of 92.5% could be obtained using the proposed deep learning algorithm.