• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• 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.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.617-621
• /
• 2021

의미역 결정은 문장 속에서 서술어와 그 논항의 관계를 파악하며, '누가, 무엇을, 어떻게, 왜' 등과 같은 의미역 관계를 찾아내는 자연어 처리 기법이다. 최근 수행되고 있는 의미역 결정 연구는 주로 말뭉치를 활용하여 딥러닝 학습을 하는 방식으로 연구가 이루어지고 있다. 최근 구글에서 개발한 사전 훈련된 Bidirectional Encoder Representations from Transformers (BERT) 모델이 다양한 자연어 처리 분야에서 상당히 높은 성능을 보이고 있다. 본 논문에서는 한국어 의미역 결정 성능 향상을 위해 한국어의 언어적 특징을 고려하며 사전 학습된 SNU KR-BERT를 사용하면서 한국어 의미역 결정 모델의 성능을 살펴보였다. 또한, 본 논문에서는 BERT 모델에서 과연 어떤 히든 레이어(hidden layer)에서 한국어 의미역 결정을 더 잘 수행하는지 알아보고자 하였다. 실험 결과 마지막 히든 레이어 임베딩을 활용하였을 때, 언어 모델의 성능은 66.4% 였다. 히든 레이어 별 언어 모델 성능을 비교한 결과, 마지막 4개의 히든 레이어를 이었을 때(concatenated), 언어 모델의 성능은 67.9% 이였으며, 11번째 히든 레이어를 사용했을 때는 68.1% 이였다. 즉, 마지막 히든 레이어를 선택했을 때보다 더 성능이 좋았다는 것을 알 수 있었다. 하지만 각 언어 모델 별 히트맵을 그려보았을 때는 마지막 히든 레이어 임베딩을 활용한 언어 모델이 더 정확히 의미역 판단을 한다는 것을 알 수 있었다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.387-387
• /
• 2022

기존 홍수기시 댐 운영은 예측 강우와 실시간 관측 강우를 이용하여 댐 운영 모형을 수행하며, 예측 결과에 따라 의사결정 및 댐 운영을 실시하게 된다. 하지만 이 과정에서 반복적인 분석이 필요하며, 댐 운영 모형 수행자의 경험에 따라 예측 결과가 달라져서 반복작업에 대한 자동화, 모형 수행자에 따라 달라지지 않는 예측 결과의 일반화가 필요한 상황이다. 이에 댐 운영 모형에 AI 기법을 적용하여, 다양한 강우 상황에 따른 자동 예측 및 모형 결과의 일반화를 구현하고자 하였다. 이를 위해 수자원 분야에 적용된 국내외 129개 연구논문에서 사용된 딥러닝 기법의 활용성을 분석하였으며, 다양한 수자원 분야 AI 적용 사례 중에서 댐 운영 예측 모형에 적용한 사례는 없었지만 유사한 분야로는 장기 저수지 운영 예측과 댐 상·하류 수위, 유량 예측이 있었다. 수자원의 시계열 자료 활용을 위해서는 Long-Short Term Memory(LSTM) 기법의 적용 활용성이 높은 것으로 분석되었다. 댐 운영 모형에서 AI 적용은 2개 분야에서 진행하였다. 기존 강우관측소의 관측 강우를 활용하여 강우의 패턴분석을 수행하는 과정과, 강우에서 댐 유입량 산정시 매개변수 최적화 분야에 적용하였다. 강우 패턴분석에서는 유사한 표본끼리 묶음을 생성하는 K-means 클러스터링 알고리즘과 시계열 데이터의 유사도 분석 방법인 Dynamic Time Warping을 결합하여 적용하였다. 강우 패턴분석을 통해서 지점별로 월별, 태풍 및 장마기간에 가장 많이 관측되었던 강우 패턴을 제시하며, 이를 모형에서 직접적으로 활용할 수 있도록 구성하였다. 강우에서 댐 유입량을 산정시 활용되는 매개변수 최적화를 위해서는 3층의 Multi-Layer LSTM 기법과 경사하강법을 적용하였다. 매개변수 최적화에 적용되는 매개변수는 중권역별 8개이며, 매개변수 최적화 과정을 통해 산정되는 결과물은 실측값과 오차가 제일 적은 유량(유입량)이 된다. 댐 운영 모형에 AI 기법을 적용한 결과 기존 반복작업에 대한 자동화는 이뤘으며, 댐 운영에 따른 상·하류 제약사항 표출 기능을 추가하여 의사결정에 소요되는 시간도 많이 줄일 수 있었다. 하지만, 매개변수 최적화 부분에서 기존 댐운영 모형에 적용되어 있는 고전적인 매개변수 추정기법보다 추정시간이 오래 소요되며, 매개변수 추정결과의 일반화가 이뤄지지 않아 이 부분에 대한 추가적인 연구가 필요하다.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.

• Journal of Korean Society for Quality Management
• /
• v.50 no.4
• /
• pp.701-716
• /
• 2022

Purpose: This study aims to predict the dry cargo transportation market economy. The subject of this study is the BDI (Baltic Dry Index) time-series, an index representing the dry cargo transport market. Methods: In order to increase the accuracy of the BDI time-series, we have pre-processed the original time-series via time-series decomposition and data augmentation techniques and have used them for ANN learning. The ANN algorithms used are Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) to compare and analyze the case of learning and predicting by applying time-series decomposition and data augmentation techniques. The forecast period aims to make short-term predictions at the time of t+1. The period to be studied is from '22. 01. 07 to '22. 08. 26. Results: Only for the case of the MAPE (Mean Absolute Percentage Error) indicator, all ANN models used in the research has resulted in higher accuracy (1.422% on average) in multivariate prediction. Although it is not a remarkable improvement in prediction accuracy compared to uni-variate prediction results, it can be said that the improvement in ANN prediction performance has been achieved by utilizing time-series decomposition and data augmentation techniques that were significant and targeted throughout this study. Conclusion: Nevertheless, due to the nature of ANN, additional performance improvements can be expected according to the adjustment of the hyper-parameter. Therefore, it is necessary to try various applications of multiple learning algorithms and ANN optimization techniques. Such an approach would help solve problems with a small number of available data, such as the rapidly changing business environment or the current shipping market.