• International Journal of Advanced Culture Technology
• /
• v.5 no.2
• /
• pp.82-89
• /
• 2017

The range of problems that can be handled by the activation of big data and the development of hardware has been rapidly expanded and machine learning such as deep learning has become a very versatile technology. In this paper, mnist data set is used as experimental data, and the Cross Entropy function is used as a loss model for evaluating the efficiency of machine learning, and the value of the loss function in the steepest descent method is We applied the GradientDescentOptimize algorithm to minimize and updated weight and bias via backpropagation. In this way we analyze optimal reliability value corresponding to the number of exercises and optimal reliability value without overfitting. And comparing the overfitting time according to the number of data changes based on the number of training times, when the training frequency was 1110 times, we obtained the result of 92%, which is the optimal reliability value without overfitting.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.205-206
• /
• 2018

본 논문에서는 IoT 환경의 무선 센서 네트워크 시스템 상의 효율적인 패킷 전달을 위해 큐러닝(Q-learning)에 기반한 다중 대기열 동적 스케쥴링 기법을 제안한다. 이 정책은 다중 대기열(Multiple queue)의 각 큐가 요구하는 딜레이 조건에 맞춰 최대한 패킷 처리를 미룸으로써 효율적으로 CPU자원을 분배한다. 또한 각 노드들의 상태를 큐러닝(Q-learning)을 통해 지속적으로 상태를 파악하여 기아상태(Starvation)를 방지한다. 제안하는 기법은 무선 센서 네트워크 상의 가변적이고 예측 불가능한 환경에 대한 사전지식이 없이도 요구하는 서비스의 질(Quality of service)를 만족할 수 있도록 한다. 본 논문에서는 모의실험을 통해 기존의 학습 기반 패킷 스케쥴링 알고리즘과 비교하여 제안하는 스케쥴링 기법이 복잡한 요구조건에 따라 유연하고 공정한 서비스를 제공함에 있어 우수함을 증명하였다.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.4
• /
• pp.202-208
• /
• 2015

In this study, we propose a new inference algorithm for a multiclass Gaussian process classification model using a variational EM framework and the Laplace approximation (LA) technique. This is performed in two steps, called expectation and maximization. First, in the expectation step (E-step), using Bayes' theorem and the LA technique, we derive the approximate posterior distribution of the latent function, indicating the possibility that each observation belongs to a certain class in the Gaussian process classification model. In the maximization step, we compute the maximum likelihood estimators for hyper-parameters of a covariance matrix necessary to define the prior distribution of the latent function by using the posterior distribution derived in the E-step. These steps iteratively repeat until a convergence condition is satisfied. Moreover, we conducted the experiments by using synthetic data and Iris data in order to verify the performance of the proposed algorithm. Experimental results reveal that the proposed algorithm shows good performance on these datasets.

• Journal of Information Processing Systems
• /
• v.17 no.4
• /
• pp.818-833
• /
• 2021

To address the problems of low precision rate, insufficient feature extraction, and poor contextual ability in existing text sentiment analysis methods, a mixed model account of a CNN-BiLSTM-TE (convolutional neural network, bidirectional long short-term memory, and topic extraction) model was proposed. First, Chinese text data was converted into vectors through the method of transfer learning by Word2Vec. Second, local features were extracted by the CNN model. Then, contextual information was extracted by the BiLSTM neural network and the emotional tendency was obtained using softmax. Finally, topics were extracted by the term frequency-inverse document frequency and K-means. Compared with the CNN, BiLSTM, and gate recurrent unit (GRU) models, the CNN-BiLSTM-TE model's F1-score was higher than other models by 0.0147, 0.006, and 0.0052, respectively. Then compared with CNN-LSTM, LSTM-CNN, and BiLSTM-CNN models, the F1-score was higher by 0.0071, 0.0038, and 0.0049, respectively. Experimental results showed that the CNN-BiLSTM-TE model can effectively improve various indicators in application. Lastly, performed scalability verification through a takeaway dataset, which has great value in practical applications.

• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1380-1390
• /
• 2021

The video face recognition (FR) is one of the most popular researches in the field of computer vision due to a variety of applications. In particular, research using the attention mechanism is being actively conducted. In video face recognition, attention represents where to focus on by using the input value of the whole or a specific region, or which frame to focus on when there are many frames. In this paper, we propose a novel attention based deep learning method. Main novelties of our method are (1) the use of combining two loss functions, namely weighted Softmax loss function and a Triplet loss function and (2) the feasibility of end-to-end learning which includes the feature embedding network and attention weight computation. The feature embedding network has a positive effect on the attention weight computation by using combined loss function and end-to-end learning. To demonstrate the effectiveness of our proposed method, extensive and comparative experiments have been carried out to evaluate our method on IJB-A dataset with their standard evaluation protocols. Our proposed method represented better or comparable recognition rate compared to other state-of-the-art video FR methods.

• International Journal of Computer Science & Network Security
• /
• v.23 no.9
• /
• pp.47-54
• /
• 2023

For Bengali music emotion classification, deep learning models, particularly CNN and RNN are frequently used. But previous researches had the flaws of low accuracy and overfitting problem. In this research, attention-based Conv1D and BiGRU model is designed for music emotion classification and comparative experimentation shows that the proposed model is classifying emotions more accurate. We have proposed a Conv1D and Bi-GRU with the attention-based model for emotion classification of our Bengali music dataset. The model integrates attention-based. Wav preprocessing makes use of MFCCs. To reduce the dimensionality of the feature space, contextual features were extracted from two Conv1D layers. In order to solve the overfitting problems, dropouts are utilized. Two bidirectional GRUs networks are used to update previous and future emotion representation of the output from the Conv1D layers. Two BiGRU layers are conntected to an attention mechanism to give various MFCC feature vectors more attention. Moreover, the attention mechanism has increased the accuracy of the proposed classification model. The vector is finally classified into four emotion classes: Angry, Happy, Relax, Sad; using a dense, fully connected layer with softmax activation. The proposed Conv1D+BiGRU+Attention model is efficient at classifying emotions in the Bengali music dataset than baseline methods. For our Bengali music dataset, the performance of our proposed model is 95%.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.971-974
• /
• 2020

Infants express their physical and emotional needs to the outside world mainly through crying. However, most of parents find it challenging to understand the reason behind their babies' cries. Failure to correctly understand the cause of a baby' cry and take appropriate actions can affect the cognitive and motor development of newborns undergoing rapid brain development. In this paper, we propose an infant cry recognition system based on deep transfer learning to help parents identify crying babies' needs the same way a specialist would. The proposed system works by transforming the waveform of the cry signal into log-mel spectrogram, then uses the VGGish model pre-trained on AudioSet to extract a 128-dimensional feature vector from the spectrogram. Finally, a softmax function is used to classify the extracted feature vector and recognize the corresponding type of cry. The experimental results show that our method achieves a good performance exceeding 0.96 in precision and recall, and f1-score.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.217-218
• /
• 2021

본 논문에서는 다층 퍼셉트론을 활용하여 League of Legends 게임의 승패를 예측하는 Deep Neural Network 프로그램을 설계하는 방법을 제안한다. 연구 방법으로 한국 서버의 챌린저 리그에서 행해진 약 26000 경기 데이터 셋을 분석하여, 경기 도중 15분 데이터 중 드래곤 처치 수, 챔피언 레벨, 정령, 타워 처치 수가 게임 결과에 유의미한 영향을 끼치는 것을 확인하였다. 모델 설계는 softmax 함수보다 sigmoid 함수를 사용했을 때 더 높은 정확도를 얻을 수 있었다. 실제 LOL의 프로 게임 16경기를 예측한 결과 93.75%의 정확도를 도출했다. 게임 평균시간이 34분인 것을 고려하였을 때, 게임 중반 정도에 게임의 승패를 예측할 수 있음이 증명되었다. 본 논문에서 설계한 이 프로그램은 전 세계 E-sports 프로리그의 승패예측과 프로팀의 유용한 훈련지표로 활용 가능하다고 사료된다.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.184-187
• /
• 2020

다중 지문 기계독해는 질문과 여러 개의 지문을 입력받고 입력된 지문들에서 추출된 정답 중에 하나의 정답을 출력하는 문제이다. 다중 지문 기계독해에서는 정답이 있을 단락을 선택하는 순위화 방법에 따라서 성능이 크게 달라질 수 있다. 본 논문에서는 단락 안에 정답이 있을 확률을 예측하는 단락 재순위화 모델과 선택된 단락에서 서술형 정답을 위한 세부적인 정답의 경계를 예측하는 세부 단락 선별 기법을 제안한다. 단락 순위화 모델 학습의 경우 모델 학습을 위해 각 단락의 출력에 softmax와 cross-entroy를 이용한 손실 값과 sigmoid와 평균 제곱 오차의 손실 값을 함께 학습하고 키워드 매칭을 함께 적용했을 때 KorQuAD 2.0의 개발셋에서 상위 1개 단락, 3개 단락, 5개 단락에서 각각 82.3%, 94.5%, 97.0%의 재현율을 보였다. 세부 단락 선별 모델의 경우 입력된 두 단락을 비교하는 duoBERT를 이용했을 때 KorQuAD 2.0의 개발셋에서 F1 83.0%의 성능을 보였다.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.91-96
• /
• 2021

조기 위험 검출은 실시간으로 들어오는 텍스트를 순차적으로 처리하면서 해당 대화에 위험이 있는지 조기에 분류하는 작업으로, 정확도 저하를 최소화하는 동시에 가능한 한 빨리 대화를 분류하는 것을 목적으로 한다. 이러한, 조기 위험 검출은 온라인 그루밍 검출, 보이스 피싱 검출과 같은 다양한 영역에 활용될 수 있다. 이에, 본 논문에서는 조기 위험 검출 문제를 정의하고, 이를 평가할 수 있는 데이터 셋과 Latency F1 평가 지표를 소개한다. 또한, 점진적 문장 분류 모듈과 위험 검출 결정 모듈로 구성된 점진적 조기 텍스트 분류 시스템을 제안한다. 점진적 문장 분류 모듈은 이전 문장들에 대한 메모리 벡터와 현재 문장 벡터를 통해 현재까지의 대화를 분류한다. 위험 검출 결정 모듈은 softmax 분류 점수와 강화학습을 기반으로 하여 Read 또는 Stop 판단을 내린다. 결정 모듈이 Stop 판단을 내리면, 현재까지의 대화에 대한 분류 결과를 전체 대화의 분류 결과로 간주하고 작업을 종료한다. 해당 시스템은 micro F1과 Latency F1 지표 각각에서 0.9684와 0.8918로 높은 검출 정확성 및 검출 신속성을 달성하였다.