• The Mathematical Education
• /
• v.45 no.1 s.112
• /
• pp.123-138
• /
• 2006

In this paper, we confirm through surveys and interviews that it helps students in solving a problem counting the number of combinations to find a structural isomorphism between the given problem and a typical problem with the same mathematical structure. Then we suggest that a problem of distributing balls into boxes might be a good candidate for a typical problem. This approach is coherent to the viewpoint given by English(2004) that it is educationally important to see the connection and relationship between problems with different context but with similar mathematical structure.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.665-666
• /
• 2022

반려동물의 이상행동 탐지를 위한 센서 데이터를 수집하는 과정에서 발생하는 시간과 비용의 문제로 인해 데이터 증강이 요구되고 있다. 본 논문에서는 통계적 변형과 GAN 기반의 데이터 증강을 통해 반려동물의 정상행동과 이상행동으로 분류하는 방법을 제안한다. 통계적 변형은 회전, 순열, 조합 등을 이용하며, GAN을 통해 원본 데이터에 노이즈가 포함된 유사한 데이터를 생성한다. 증강된 모든 데이터는 원본 데이터와 함께 학습 데이터로 사용한다. 최종적으로, LSTM의 단점을 보완한 Convolutional LSTM 모델을 통해 반려동물의 정상행동 인식의 범주를 넓혀 보다 정확한 이상행동을 인식하고자 한다.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.536-543
• /
• 2023

Speaker diarization, which labels for "who spoken when?" in speech with multiple speakers, has been studied on a deep neural network-based end-to-end method for labeling on speech overlap and optimization of speaker diarization models. Most deep neural network-based end-to-end speaker diarization systems perform multi-label classification problem that predicts the labels of all speakers spoken in each frame of speech. However, the performance of the multi-label-based model varies greatly depending on what the threshold is set to. In this paper, it is studied a speaker diarization system using single-label classification so that speaker diarization can be performed without thresholds. The proposed model estimate labels from the output of the model by converting speaker labels into a single label. To consider speaker label permutations in the training, the proposed model is used a combination of Permutation Invariant Training (PIT) loss and cross-entropy loss. In addition, how to add the residual connection structures to model is studied for effective learning of speaker diarization models with deep structures. The experiment used the Librispech database to generate and use simulated noise data for two speakers. When compared with the proposed method and baseline model using the Diarization Error Rate (DER) performance the proposed method can be labeling without threshold, and it has improved performance by about 20.7 %.