• 한국지능시스템학회논문지
• /
• 제10권3호
• /
• pp.203-210
• /
• 2000

본 논문에서는 패턴분류문제를 해결하기 위한 새로운 무감독학습 신경망 및 경쟁학습 알고리즘을 제한한다. 제아하는 신경망은 입력 데이터의 군집을 분류하기 위한 거리측도로서 군집들 상호간의 상대유사도(relative similarity)를 기반으로 하고 있다. 이러한 까닭에 제안하는 신경망과 알고리즘을 상대유사 신경망 (relative similarity network; RSN)및 학습 알고리즘이라 이름한다. 상대유사도를 정의하고 가중벡터 학습 규칙을 구성함으로써, RSN의 구조를 설계하고 학습알고리즘을 구현하기 의한 의사코드를 기술한다. 일반적인 패턴분류에 RSN을 적용한 결과, 초기 학습률이 없음에도 불구하고 기존이 경쟁학습 신경망인 WTAdlsk SOM고 동등한 성능을 나타내었다. 반면 기존 경쟁학습 신경망의 분류성능이 저하되었던 군집이 경걔가 불분명한 패턴, 그리고 군집이 밀집도와 군집의 크기가 다른 패턴들에 대한 실험에서는 기존의 경쟁학습망보다 효과적인 분류결과를 나타내었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권6호
• /
• pp.2527-2545
• /
• 2016

Measuring the similarity of given samples is a key problem of recognition, clustering, retrieval and related applications. A number of works, e.g. kernel method and metric learning, have been contributed to this problem. The challenge of similarity learning is to find a similarity robust to intra-class variance and simultaneously selective to inter-class characteristic. We observed that, the similarity measure can be improved if the data distribution and hidden semantic information are exploited in a more sophisticated way. In this paper, we propose a similarity learning approach for retrieval and recognition. The approach, termed as LDA-FEK, derives free energy kernel (FEK) from Latent Dirichlet Allocation (LDA). First, it trains LDA and constructs kernel using the parameters and variables of the trained model. Then, the unknown kernel parameters are learned by a discriminative learning approach. The main contributions of the proposed method are twofold: (1) the method is computationally efficient and scalable since the parameters in kernel are determined in a staged way; (2) the method exploits data distribution and semantic level hidden information by means of LDA. To evaluate the performance of LDA-FEK, we apply it for image retrieval over two data sets and for text categorization on four popular data sets. The results show the competitive performance of our method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권3호
• /
• pp.522-538
• /
• 2013

Content based image retrieval has become an increasingly important research topic for its wide application. It is highly challenging when facing to large-scale database with large variance. The retrieval systems rely on a key component, the predefined or learned similarity measures over images. We note that, the similarity measures can be potential improved if the data distribution information is exploited using a more sophisticated way. In this paper, we propose a similarity measure learning approach for image retrieval. The similarity measure, so called Fisher kernel, is derived from the probabilistic distribution of images and is the function over observed data, hidden variable and model parameters, where the hidden variables encode high level information which are powerful in discrimination and are failed to be exploited in previous methods. We further propose a discriminative learning method for the similarity measure, i.e., encouraging the learned similarity to take a large value for a pair of images with the same label and to take a small value for a pair of images with distinct labels. The learned similarity measure, fully exploiting the data distribution, is well adapted to dataset and would improve the retrieval system. We evaluate the proposed method on Corel-1000, Corel5k, Caltech101 and MIRFlickr 25,000 databases. The results show the competitive performance of the proposed method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권8호
• /
• pp.2895-2912
• /
• 2014

Content-based image retrieval has been the most important technique for managing huge amount of images. The fundamental yet highly challenging problem in this field is how to measure the content-level similarity based on the low-level image features. The primary difficulties lie in the great variance within images, e.g. background, illumination, viewpoint and pose. Intuitively, an ideal similarity measure should be able to adapt the data distribution, discover and highlight the content-level information, and be robust to those variances. Motivated by these observations, we in this paper propose a probabilistic similarity learning approach. We first model the distribution of low-level image features and derive the free energy kernel (FEK), i.e., similarity measure, based on the distribution. Then, we propose a learning approach for the derived kernel, under the criterion that the kernel outputs high similarity for those images sharing the same class labels and output low similarity for those without the same label. The advantages of the proposed approach, in comparison with previous approaches, are threefold. (1) With the ability inherited from probabilistic models, the similarity measure can well adapt to data distribution. (2) Benefitting from the content-level hidden variables within the probabilistic models, the similarity measure is able to capture content-level cues. (3) It fully exploits class label in the supervised learning procedure. The proposed approach is extensively evaluated on two well-known databases. It achieves highly competitive performance on most experiments, which validates its advantages.

• International Journal of Computer Science & Network Security
• /
• 제22권4호
• /
• pp.111-118
• /
• 2022

This research article presents the work that is related to the application of different machine learning based similarity techniques on religious text for identifying similarities and differences among its various translations. The dataset includes 10 different English translations of verses (Arabic: Ayah) of two Surahs (chapters) namely, Al-Humazah and An-Nasr. The quantitative similarity values for different translations for the same verse were calculated by using the cosine similarity and semantic similarity. The corpus went through two series of experiments: before pre-processing and after pre-processing. In order to determine the performance of machine learning based similarities, human annotated similarities between translations of two Surahs (chapters) namely Al-Humazah and An-Nasr were recorded to construct the ground truth. The average difference between the human annotated similarity and the cosine similarity for Surah (chapter) Al-Humazah was found to be 1.38 per verse (ayah) per pair of translation. After pre-processing, the average difference increased to 2.24. Moreover, the average difference between human annotated similarity and semantic similarity for Surah (chapter) Al-Humazah was found to be 0.09 per verse (Ayah) per pair of translation. After pre-processing, it increased to 0.78. For the Surah (chapter) An-Nasr, before preprocessing, the average difference between human annotated similarity and cosine similarity was found to be 1.93 per verse (Ayah), per pair of translation. And. After pre-processing, the average difference further increased to 2.47. The average difference between the human annotated similarity and the semantic similarity for Surah An-Nasr before preprocessing was found to be 0.93 and after pre-processing, it was reduced to 0.87 per verse (ayah) per pair of translation. The results showed that as expected, the semantic similarity was proven to be better measurement indicator for calculation of the word meaning.

• Journal of the Korean Data and Information Science Society
• /
• 제22권1호
• /
• pp.99-105
• /
• 2011

We propose a semi-supervised learning algorithm based on a form of regularization that incorporates similarity and dissimilarity penalty terms. Our approach uses a graph-based encoding of similarity and dissimilarity. We also present a model-selection method which employs cross-validation techniques to choose hyperparameters which affect the performance of the proposed method. Simulations using two types of dat sets demonstrate that the proposed method is promising.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권5호
• /
• pp.1252-1271
• /
• 2013

Automatic image annotation has become an increasingly important research topic owing to its key role in image retrieval. Simultaneously, it is highly challenging when facing to large-scale dataset with large variance. Practical approaches generally rely on similarity measures defined over images and multi-label prediction methods. More specifically, those approaches usually 1) leverage similarity measures predefined or learned by optimizing for ranking or annotation, which might be not adaptive enough to datasets; and 2) predict labels separately without taking the correlation of labels into account. In this paper, we propose a method for image annotation through collaborative similarity metric learning from dataset and modeling the label correlation of the dataset. The similarity metric is learned by simultaneously optimizing the 1) image ranking using structural SVM (SSVM), and 2) image annotation using correlated label propagation, with respect to the similarity metric. The learned similarity metric, fully exploiting the available information of datasets, would improve the two collaborative components, ranking and annotation, and sequentially the retrieval system itself. We evaluated the proposed method on Corel5k, Corel30k and EspGame databases. The results for annotation and retrieval show the competitive performance of the proposed method.

• 한국인터넷방송통신학회논문지
• /
• 제22권5호
• /
• pp.171-176
• /
• 2022

최근 딥러닝 기술의 발전과 함께 추천 시스템의 영역도 다양해졌다. 본 논문은 학습률 향상을 위한 알고리즘을 연구하였으며 Word2Vec 모델의 성능 특징과 비교를 통해 단어에 따른 유의어 결과를 연구하였다. 문제 추천 알고리즘은 Word2Vec 모델의 특징인 텍스트 간 의미 반영 및 유사성 테스트를 통해 표현된 값으로 구현됐다. Word2Vec 의 학습 결과를 통해 텍스트 유사도 값을 이용해 문제 추천을 진행하였으며 유사도가 높은 문제를 추천할 수 있다. 실험 과정에서 정량적인 데이터양으로는 정확성이 낮아지는 결과를 보았으며 데이터 셋의 데이터양이 방대할수록 정확성을 높일 수 있음을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권4호
• /
• pp.1424-1440
• /
• 2015

It is a challenging problem to search the intended images from a large number of candidates. Content based image retrieval (CBIR) is the most promising way to tackle this problem, where the most important topic is to measure the similarity of images so as to cover the variance of shape, color, pose, illumination etc. While previous works made significant progresses, their adaption ability to dataset is not fully explored. In this paper, we propose a similarity learning method on the basis of probabilistic generative model, i.e., probabilistic latent semantic analysis (PLSA). It first derives Fisher kernel, a function over the parameters and variables, based on PLSA. Then, the parameters are determined through simultaneously maximizing the log likelihood function of PLSA and the retrieval performance over the training dataset. The main advantages of this work are twofold: (1) deriving similarity measure based on PLSA which fully exploits the data distribution and Bayes inference; (2) learning model parameters by maximizing the fitting of model to data and the retrieval performance simultaneously. The proposed method (PLSA-FK) is empirically evaluated over three datasets, and the results exhibit promising performance.

• 한국컴퓨터정보학회논문지
• /
• 제28권1호
• /
• pp.39-47
• /
• 2023

본 논문에서는 골프 동영상 속 스윙 자세 사이의 유사도를 측정할 수 있는 방법을 제안한다. 딥러닝 기반 인공지능 기술이 컴퓨터 비전 분야에 효과적인 것이 알려지면서 동영상을 기반으로 한 스포츠 데이터 분석에 인공지능을 활용하기 위한 시도가 증가하고 있다. 본 연구에서는 딥러닝 기반의 자세 추정 모델을 사용하여 골프 스윙 동영상 속 사람의 관절 좌표를 획득하였고, 이를 바탕으로 각 스윙 구간별 유사도를 측정하였다. 제안한 방법의 평가를 위해 GolfDB 데이터셋의 Driver 스윙 동영상을 활용하였다. 총 36명의 선수에 대해 스윙 동영상들을 두 개씩 짝지어 스윙 유사도를 측정한 결과, 본인의 또 다른 스윙이 가장 유사하다고 평가한 경우가 26명이었으며, 이때의 유사도 평균 순위는 약 5위로 확인되었다. 이로부터 비슷한 동작을 수행하고 있는 경우에도 면밀히 유사도를 측정하는 것이 가능함을 확인할 수 있었다.