• Journal of information and communication convergence engineering
• /
• 제16권2호
• /
• pp.106-113
• /
• 2018

Although deep learning methods of convolutional neural networks (CNNs) and long-/short-term memory (LSTM) are widely used for text categorization, they still have certain shortcomings. CNNs require that the text retain some order, that the pooling lengths be identical, and that collateral analysis is impossible; In case of LSTM, it requires the unidirectional operation and the inputs/outputs are very complex. Against these problems, we thus improved these traditional deep learning methods in the following ways: We created collateral CNNs accepting disorder and variable-length pooling, and we removed the input/output gates when creating bidirectional LSTMs. We have used four benchmark datasets for topic and sentiment classification using the new methods that we propose. The best results were obtained by combining LTSM regional embeddings with data convolution. Our method is better than all previous methods (including deep learning methods) in terms of topic and sentiment classification.

• Communications for Statistical Applications and Methods
• /
• 제31권1호
• /
• pp.105-127
• /
• 2024

We propose recurrent neural network (RNN) methods for forecasting realized volatility (RV). The data are RVs of ten major stock price indices, four from the US, and six from the EU. Forecasts are made for relative ratio of adjacent RVs instead of the RV itself in order to avoid the out-of-scale issue. Forecasts of RV ratios distribution are first constructed from which those of RVs are computed which are shown to be better than forecasts constructed directly from RV. The apparent asymmetry of RV ratio is addressed by the Piecewise Min-max (PM) normalization. The serial dependence of the ratio data renders us to consider two architectures, long short-term memory (LSTM) and gated recurrent unit (GRU). The hyperparameters of LSTM and GRU are tuned by the nested cross validation. The RNN forecast with the PM normalization and ratio transformation is shown to outperform other forecasts by other RNN models and by benchmarking models of the AR model, the support vector machine (SVM), the deep neural network (DNN), and the convolutional neural network (CNN).

• 전기학회논문지
• /
• 제68권1호
• /
• pp.153-158
• /
• 2019

In this paper, we analyze the infrared feature for the small coast targets according to the surrounding environment for autonomous flight device equipped with an infrared imaging sensor and we propose Cross Duality of Neural Network (CR-DuNN) method which can classify the target and clutter in coastal environment. In coastal environment, there are various property according to diverse change of air temperature, sea temperature, deferent seasons. And small coast target have various infrared feature according to diverse change of environment. In this various environment, it is very important thing that we analyze and classify targets from the clutters to improve target detection accuracy. Thus, we propose infrared feature learning algorithm through LSTM neural network and also propose CR-DuNN algorithm that integrate LSTM prediction network with Du-CNN classification network to classify targets from the clutters.

• 신재생에너지
• /
• 제18권2호
• /
• pp.18-25
• /
• 2022

In this study, we propose a wind power generation prediction system that applies machine learning and data mining to predict wind power generation. This system increases the utilization rate of new and renewable energy sources. For time-series data, the data set was established by measuring wind speed, wind generation, and environmental factors influencing the wind speed. The data set was pre-processed so that it could be applied appropriately to the model. The prediction system applied the CNN (Convolutional Neural Network) to the data mining process and then used the LSTM (Long Short-Term Memory) to learn and make predictions. The preciseness of the proposed system is verified by comparing the prediction data with the actual data, according to the presence or absence of data mining in the model of the prediction system.

• International Journal of Computer Science & Network Security
• /
• 제21권7호
• /
• pp.159-168
• /
• 2021

Detecting cyber-attacks using machine learning or deep learning is being studied and applied widely in network intrusion detection systems. We noticed that the application of deep learning algorithms yielded many good results. However, because each deep learning model has different architecture and characteristics with certain advantages and disadvantages, so those deep learning models are only suitable for specific datasets or features. In this paper, in order to optimize the process of detecting cyber-attacks, we propose the idea of building a new deep learning network model based on the association and combination of individual deep learning models. In particular, based on the architecture of 2 deep learning models: Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM), we combine them into a combined deep learning network for detecting cyber-attacks based on network traffic. The experimental results in Section IV.D have demonstrated that our proposal using the CNN-LSTM deep learning model for detecting cyber-attacks based on network traffic is completely correct because the results of this model are much better than some individual deep learning models on all measures.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2021년도 추계학술대회
• /
• pp.91-94
• /
• 2021

As deep learning technologies becoming developed, realistic fake videos synthesized by deep learning models called "Deepfake" videos became even more difficult to distinguish from original videos. As fake news or Deepfake blackmailing are causing confusion and serious problems, this paper suggests a novel model detecting Deepfake videos. We chose Residual Convolutional Neural Network (Resnet50) as an extraction model and Long Short-Term Memory (LSTM) which is a form of Recurrent Neural Network (RNN) as a classification model. We adopted cosine similarity with hinge loss to train our extraction model in embedding the features of Deepfake and original video. The result in this paper demonstrates that temporal features in the videos are essential for detecting Deepfake videos.

• Smart Structures and Systems
• /
• 제33권4호
• /
• pp.301-311
• /
• 2024

This paper proposes a deep convolutional long short-term memory (ConvLSTM)-based crack growth prediction technique for predictive maintenance of structures. Since cracks are one of the critical damage types in a structure, their regular inspection has been mandatory for structural safety and serviceability. To effectively establish the structural maintenance plan using the inspection results, crack propagation or growth prediction is essential. However, conventional crack prediction techniques based on mathematical models are not typically suitable for tracking complex nonlinear crack propagation mechanism on civil structures under harsh environmental conditions. To address the technical issue, a field data-driven crack growth prediction technique using ConvLSTM is newly proposed in this study. The proposed technique consists of the four steps: (1) time-series crack image acquisition, (2) target image stabilization, (3) deep learning-based crack detection and quantification and (4) crack growth prediction. The performance of the proposed technique is experimentally validated using a concrete mock-up specimen by applying step-wise bending loads to generate crack growth. The validation test results reveal the prediction accuracy of 94% on average compared with the ground truth obtained by field measurement.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2020년도 춘계학술발표대회
• /
• pp.540-543
• /
• 2020

본 논문에서는 대표적인 이미지 분류 모델인 CNN(Convolutional Neural Network)과 시간에 따른 이미지의 변화를 학습할 수 있는 LSTM(Long Short-Term Memory) 기반의 온라인 서명인식 모델을 제안한다. 실제로는 위조서명을 미리 구하기 어렵다는 사실을 고려해 서명검증 대상자가 아닌 타인의 진서명과 대상자의 일반 필기 데이터를 음의 데이터로서 학습에 사용하였다. 실험 결과, 전체 이미지 중 서명 부분의 비율에 따라 좋은 성능을 보이는 검증 모델이 다르며 Accuracy 성능지표를 통해 이 비율이 높거나 낮을 경우 CNN-LSTM 이, 중간일 경우 CNN 이 적합하다는 것을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권6호
• /
• pp.2128-2147
• /
• 2021

Cognitive radio systems are being implemented recently to tackle spectrum underutilization problems and aid efficient data traffic. Spectrum sensing is the crucial step in cognitive applications in which cognitive user detects the presence of primary user (PU) in a particular channel thereby switching to another channel for continuous transmission. In cognitive radio systems, the capacity to precisely identify the primary user's signal is essential to secondary user so as to use idle licensed spectrum. Based on the inherent capability, a new spectrum sensing technique is proposed in this paper to identify all types of primary user signals in a cognitive radio condition. Hence, a spectrum sensing algorithm using improved convolutional neural network and long short-term memory (CNN-LSTM) is presented. The principle used in our approach is simulated annealing that discovers reasonable number of neurons for each layer of a completely associated deep neural network to tackle the streamlining issue. The probability of detection is considered as the determining parameter to find the efficiency of the proposed algorithm. Experiments are carried under different signal to noise ratio to indicate better performance of the proposed algorithm. The PU signal will have an associated modulation format and hence identifying the presence of a modulation format itself establishes the presence of PU signal.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 춘계학술발표대회
• /
• pp.641-642
• /
• 2022

단일 데이터로부터의 이동 객체에 대한 행동 인식 연구는 데이터 수집 과정에서 발생하는 노이즈의 영향을 크게 받는다. 본 논문은 영상 데이터와 센서 데이터를 이용하여 다중 융합 네트워크 기반 이동 객체 행동 인식 방법을 제안한다. 영상으로부터 객체가 감지된 영역의 추출과 센서 데이터의 이상치 제거 및 결측치 보간을 통해 전처리된 데이터들을 융합하여 시퀀스를 생성한다. 생성된 시퀀스는 CNN(Convolutional Neural Networks)과 LSTM(Long Short Term Memory)기반 다중 융합 네트워크 모델을 통해 시계열에 따른 행동 특징들을 추출하고, 깊은 FC(Fully Connected) 계층을 통해 특징들을 융합하여 행동을 예측한다. 본 연구에서 제시된 방법은 사람을 포함한 동물, 로봇 등의 다양한 객체에 적용될 수 있다.