• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제8권11호
• /
• pp.449-456
• /
• 2019

본 논문은 진공을 이용한 흡착방식과 바퀴형 이동방식을 사용하는 벽면 이동로봇의 구성과 이러한 임베디드 환경에 적합하고 기계학습에 기반한 벽면 균열 자동 검출 알고리즘의 성능 비교에 관한 연구이다. 임베디드 시스템 환경에서 객체 학습을 위해 YOLO 등 최근에 시도된 학습 방법들을 적용하여 성능을 비교, 검토하였으며 기존의 에지 검출 알고리즘들과도 성능을 비교하였다. 결국, 본 연구에서는 균열검출을 잘하며 임베디드 환경에도 적합한 최적의 기계학습방법을 선택하고 기존 방법과 성능을 비교하여 우수성을 제시하였다. 또한, 검출된 균열의 영상을 저장하고 위치 정보를 추정하여 균열에 대한 정보를 관리자 기기로 전송하는 지능적인 문제해결 기능을 구축하였다.

• 정보처리학회논문지B
• /
• 제12B권3호
• /
• pp.343-348
• /
• 2005

본 연구에서는 신경망 학습의 일반화 성능과 학습속도를 개선시키기 위한 인자들의 결합 효과를 살펴본다. 신경망 학습에서 중요한 평가 척도로서 여기서 고려하는 인자들에는 초기 가중값의 범위와 학습률 그리고 계수조정 등이 있다. 특히 초기 가중값과 학습률을 고정시킨 후 새롭게 조정된 계수들을 단계적으로 변화시키는 새로운 인자 결합방법을 이용한다. 이를 통하여 신경망 학습량과 학습속도를 비교해 보고, 계수조정을 통한 개선된 학습 영향을 살펴본다. 그리고 비선형의 단순한 예제를 이용한 실증분석을 통하여 신경망 모형의 일반화 성능과 학습 속도 개선을 위한 각 인자들의 개별 효과와 결합 효과를 살펴보고 그 개선 방안을 논의한다.

• 전자공학회논문지C
• /
• 제34C권7호
• /
• pp.82-91
• /
• 1997

In this paper, we analyze the dynamics of langevine competitive learning neural network based on its fokker-plank equation. From the viewpont of the stochastic differential equation (SDE), langevine competitive learning equation is one of langevine stochastic differential equation and has the diffusin equation on the topological space (.ohm., F, P) with probability measure. We derive the fokker-plank equation from the proposed algorithm and prove by introducing a infinitestimal operator for markov semigroups, that the weight vector in the particular simplex can converge to the globally optimal point under the condition of some convex or pseudo-convex performance measure function. Experimental resutls for pattern recognition of the remote sensing data indicate the superiority of langevine competitive learning neural network in comparison to the conventional competitive learning neural network.

• International Journal of Computer Science & Network Security
• /
• 제21권1호
• /
• pp.1-5
• /
• 2021

Cyberbullying is a problem that is faced in many cultures. Due to their popularity and interactive nature, social media platforms have also been affected by cyberbullying. Social media users from Arab countries have also reported being a target of cyberbullying. Machine learning techniques have been a prominent approach used by scientists to detect and battle this phenomenon. In this paper, we compare different machine learning algorithms for their performance in cyberbullying detection based on a labeled dataset of Arabic YouTube comments. Three machine learning models are considered, namely: Multinomial Naïve Bayes (MNB), Complement Naïve Bayes (CNB), and Linear Regression (LR). In addition, we experiment with two feature extraction methods, namely: Count Vectorizer and Tfidf Vectorizer. Our results show that, using count vectroizer feature extraction, the Logistic Regression model can outperform both Multinomial and Complement Naïve Bayes models. However, when using Tfidf vectorizer feature extraction, Complement Naive Bayes model can outperform the other two models.

• International Journal of Computer Science & Network Security
• /
• 제24권6호
• /
• pp.1-7
• /
• 2024

Comparing text features involves evaluating the "similarity" between texts. It is crucial to use appropriate similarity measures when comparing similarities. This study utilized various techniques to assess the similarities between newspaper articles, including deep learning and a previously proposed method: a combination of Pointwise Mutual Information (PMI) and Word Pair Matching (WPM), denoted as PMI+WPM. For performance comparison, law data from medical research in Japan were utilized as validation data in evaluating the PMI+WPM method. The distribution of similarities in text data varies depending on the evaluation technique and genre, as revealed by the comparative analysis. For newspaper data, non-deep learning methods demonstrated better similarity evaluation accuracy than deep learning methods. Additionally, evaluating similarities in law data is more challenging than in newspaper articles. Despite deep learning being the prevalent method for evaluating textual similarities, this study demonstrates that non-deep learning methods can be effective regarding Japanese-based texts.

• 전자공학회논문지CI
• /
• 제45권6호
• /
• pp.179-186
• /
• 2008

본 논문에서는 베이지안 알고리즘이 불균형 데이터의 학습 시 나타나는 현상을 분석하고 성능 평가 방법을 비교하였다. 사전 데이터 분포를 가정하고 불균형 데이터 비율과 분류 복잡도에 따라 발생된 분류 문제에 대해 베이지안 학습을 수행하였다. 실험 결과는 ROC(Receiver Operator Characteristic)와 PR(Precision-Recall) 평가 방법의 AUC(Area Under the Curve)를 계사하여 불균형 데이터 비율과 분류 복잡도에 따라 분석되었다. 비교 분석에서 불균형 비율은 기 수행된 연구 결과와 같이 베이지안 학습에 영향을 주었으며, 높은 분류 복잡도로부터 나타나는 데이터 중복은 학습 성능을 방해하는 요인으로 확인되었다. PR 평가의 AUC는 높은 분류 복잡도와 높은 불균형 데이터 비율에서 ROC 평가의 AUC보다 학습 성능의 차이가 크게 나타났다. 그러나 낮은 분류 복잡도와 낮은 불균형 데이터 비율의 문제에서 두 측정 방법의 학습 성능의 차이는 미비하거나 비슷하였다. 이러한 결과로부터 PR 평가의 AUC는 클래스 불균형 문제의 학습 모델의 설계와 오분류 비용을 고려한 최적의 학습기를 결정하는데 도움을 줄 수 있다.

• Journal of Positioning, Navigation, and Timing
• /
• 제11권3호
• /
• pp.163-172
• /
• 2022

Typical anti-jamming technologies based on array antennas, Space Time Adaptive Process (STAP) & Space Frequency Adaptive Process (SFAP), are very effective algorithms to perform nulling and beamforming. However, it does not perform equally well for all types of jamming signals. If the anti-jamming algorithm is not optimized for each signal type, anti-jamming performance deteriorates and the operation stability of the system become worse by unnecessary computation. Therefore, jamming classification technique is required to obtain optimal anti-jamming performance. Machine learning, which has recently been in the spotlight, can be considered to classify jamming signal. In general, performing supervised learning for classification requires a huge amount of data and new learning for unfamiliar signal. In the case of jamming signal classification, it is difficult to obtain large amount of data because outdoor jamming signal reception environment is difficult to configure and the signal type of attacker is unknown. Therefore, this paper proposes few-shot jamming signal classification technique using meta-learning and transfer-learning to train the model using a small amount of data. A training dataset is constructed by anti-jamming algorithm input data within the GNSS receiver when jamming signals are applied. For meta-learning, Model-Agnostic Meta-Learning (MAML) algorithm with a general Convolution Neural Networks (CNN) model is used, and the same CNN model is used for transfer-learning. They are trained through episodic training using training datasets on developed our Python-based simulator. The results show both algorithms can be trained with less data and immediately respond to new signal types. Also, the performances of two algorithms are compared to determine which algorithm is more suitable for classifying jamming signals.

• 기술혁신연구
• /
• 제12권2호
• /
• pp.21-46
• /
• 2004

Focusing on a product, this paper reconstructs the concept of technological systems first introduced by Carlsson and Stankiewicz (1991). Based on the model and our earlier works, we compare the salient features of technological systems for computer numerically controlled (CNC) machine tools in Korea, Sweden, and the United States.. We also try to measure the performance of the systems in an international comparison. Major findings are as follows: (1) The length of 'learning period' for local (national) technological system is substantial, even though it is a catching-up case. (2) The key success factor of the technological system appears to be the connectivity among various actors or infrastructures, rather than just the existence or formation of those. (3) In three countries' experience, the government played an important role in the formation of each own technological system. (4) The performance of Korea's technological system for CNC machine tools during the past two decades(1981-97) seems to be better than that of Sweden and the U.S. Lastly, many policy implication are presented.

• 한국컴퓨터정보학회논문지
• /
• 제24권8호
• /
• pp.87-93
• /
• 2019

These days, as interest in the recommendation system with deep learning is increasing, a number of related studies to develop a performance for collaborative filtering through autoencoder, a state-of-the-art deep learning neural network architecture has advanced considerably. The purpose of this study is to propose autoencoder which is used by the recommendation system to predict ratings, and we added more hidden layers to the original architecture of autoencoder so that we implemented deep autoencoder with 3 to 5 hidden layers for much deeper architecture. In this paper, therefore we make a comparison between the performance of them. In this research, we use 2-dimensional arrays and 3-dimensional tensor as the input dataset. As a result, we found a correlation between matrix entry of the 3-dimensional dataset such as item-time and user-time and also figured out that deep autoencoder with extra hidden layers generalized even better performance than autoencoder.

• 인터넷정보학회논문지
• /
• 제24권4호
• /
• pp.85-92
• /
• 2023

X-ray, Computed Tomography (CT), Magnetic Resonance Imaging (MRI)과 같은 의료데이터에서 딥러닝을 활용해 질병 유무 판별 태스크와 같은 문제를 해결하려는 시도가 활발하다. 대부분의 데이터 기반 딥러닝 문제들은 높은 정확도 달성과 정답과 비교하는 성능평가의 활용을 위해 지도학습기법을 사용해야 한다. 지도학습에는 다량의 이미지와 레이블 세트가 필요하지만, 학습에 충분한 양의 의료 이미지 데이터를 얻기는 어렵다. 다양한 데이터 증강 기법을 통해 적은 양의 의료이미지와 레이블 세트로 지도학습 기반 모델의 과소적합 문제를 극복할 수 있다. 본 연구는 딥러닝 기반 갈비뼈 골절 세그멘테이션 모델의 성능 향상과 효과적인 좌우 반전, 회전, 스케일링 등의 데이터 증강 기법을 탐색한다. 좌우 반전과 30° 회전, 60° 회전으로 증강한 데이터셋은 모델 성능 향상에 기여하지만, 90° 회전 및 ⨯0.5 스케일링은 모델 성능을 저하한다. 이는 데이터셋 및 태스크에 따라 적절한 데이터 증강 기법의 사용이 필요함을 나타낸다.