• 한국멀티미디어학회논문지
• /
• 제14권6호
• /
• pp.711-718
• /
• 2011

얼굴인식과 같이 클래스의 수가 변하는 분류 문제에는 학습이 필요하지 않은 k-최근접이웃 분류기가 적합하다. 최근 학습 데이터의 분포를 반영하여 거리 척도를 학습하는 방법은 k 최근접이웃 분류기의 획기적 성능향상을 보고하였다. 거리척도학습 방법은 적용 분야에 따라 성능 개선 정도가 다르다. 본 논문에서는 얼굴인식에 대하여 주요 거리척도학습 방법의 성능을 비교한다. 공개 얼굴 데이터베이스에 대한 실험 결과는 성능 및 계산시간 측면에서 주성분 분석 기반의 마하라노비스 거리척도가 얼굴인식 문제에서는 여전히 좋은 선택이 될 수 있음을 보여준다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.3798-3814
• /
• 2022

Social recommendation algorithm can alleviate data sparsity and cold start problems in recommendation system by integrated social information. Among them, matrix-based decomposition algorithms are the most widely used and studied. Such algorithms use dot product operations to calculate the similarity between users and items, which ignores user's potential preferences, reduces algorithms' recommendation accuracy. This deficiency can be avoided by a metric learning-based social recommendation algorithm, which learns the distance between user embedding vectors and item embedding vectors instead of vector dot-product operations. However, previous works provide no theoretical explanation for its plausibility. Moreover, most works focus on the indirect impact of social friends on user's preferences, ignoring the direct impact on user's rating preferences, which is the influence of user rating preferences. To solve these problems, this study proposes a user bias drift social recommendation algorithm based on metric learning (BDML). The main work of this paper is as follows: (1) the process of introducing metric learning in the social recommendation scenario is introduced in the form of equations, and explained the reason why metric learning can replace the click operation; (2) a new user bias is constructed to simultaneously model the impact of social relationships on user's ratings preferences and user's preferences; Experimental results on two datasets show that the BDML algorithm proposed in this study has better recommendation accuracy compared with other comparison algorithms, and will be able to guarantee the recommendation effect in a more sparse dataset.

• 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.

• Human Ecology Research
• /
• 제55권5호
• /
• pp.527-538
• /
• 2017

This study examines the effects of university students' types of self-determination and academic emotions on their learning community participant competence. The subjects were 234 early-childhood preservice teachers attending a university or college in the Kyonggi and Incheon area of Korea. The first metric created by Bak et al. (2005) measured early-childhood preservice teachers' types of self-determination. The second metric developed by Kim & Kim (2016) measured their levels of learning community participant competence. The thirds metric, originally developed by Kim (2012) and So (2010), was modified by Chung (2015) to measure the academic emotions of subjects. The test results were analyzed by correlation and multi-regression techniques using SPSS 21 for Windows. The findings were as follows. First, there were significant relationships between the subjects' types of self-determination and the levels of learning community participant competence. Second, there were significant relationships between the subjects' academic positive and negative emotions and the levels of learning community participant competence. Third, the subjects' levels of learning community participant competence were perceived differently according to their academic emotions. Based on these results, implications pertaining to academic emotions on learning community participant competence are suggested.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권2호
• /
• pp.742-762
• /
• 2015

In this study, we propose a distance metric learning approach called discriminant metric learning (DML) for face verification, which addresses a binary-class problem for classifying whether or not two input images are of the same subject. The critical issue for solving this problem is determining the method to be used for measuring the distance between two images. Among various methods, the large margin nearest neighbor (LMNN) method is a state-of-the-art algorithm. However, to compensate the LMNN's entangled data distribution due to high levels of appearance variations in unconstrained environments, DML's goal is to penalize violations of the negative pair distance relationship, i.e., the images with different labels, while being integrated with LMNN to model the distance relation between positive pairs, i.e., the images with the same label. The likelihoods of the input images, estimated using DML and LMNN metrics, are then weighted and combined for further analysis. Additionally, rather than using the k-nearest neighbor (k-NN) classification mechanism, we propose a verification mechanism that measures the correlation of the class label distribution of neighbors to reduce the false negative rate of positive pairs. From the experimental results, we see that DML can modify the relation of negative pairs in the original LMNN space and compensate for LMNN's performance on faces with large variances, such as pose and expression.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권4호
• /
• pp.819-833
• /
• 2013

Computing global features based on local features using a bio-inspired framework has shown promising performance. However, for some tough applications with large intra-class variances, a single local feature is inadequate to represent all the attributes of the images. To integrate the complementary abilities of multiple local features, in this paper we have extended the efficacy of the bio-inspired framework, HMAX, to adapt heterogeneous features for global feature extraction. Given multiple global features, we propose an approach, designated as parameterized metric learning, for high dimensional feature fusion. The fusion parameters are solved by maximizing the canonical correlation with respect to the parameters. Experimental results show that our method achieves significant improvements over the benchmark bio-inspired framework, HMAX, and other related methods on the Caltech dataset, under varying numbers of training samples and feature elements.

• Journal of Information Processing Systems
• /
• 제16권5호
• /
• pp.1105-1112
• /
• 2020

Gait recognition, as a promising biometric, can be used in video-based surveillance and other security systems. However, due to the complexity of leg movement and the difference of external sampling conditions, gait recognition still faces many problems to be addressed. In this paper, an improved convolutional neural network (CNN) based on Gabor filter is therefore proposed to achieve gait recognition. Firstly, a gait feature extraction layer based on Gabor filter is inserted into the traditional CNNs, which is used to extract gait features from gait silhouette images. Then, in the process of gait classification, using the output of CNN as input, we utilize metric learning techniques to calculate distance between two gaits and achieve gait classification by k-nearest neighbors classifiers. Finally, several experiments are conducted on two open-accessed gait datasets and demonstrate that our method reaches state-of-the-art performances in terms of correct recognition rate on the OULP and CASIA-B datasets.

• Journal of Information Technology Applications and Management
• /
• 제27권6호
• /
• pp.141-151
• /
• 2020

The job mismatch between job seekers and SMEs is becoming more and more intensifying with the serious difficulties in youth employment. In this study, a bi-directional content-based metric learning model is proposed to recommend suitable jobs for job seekers and suitable job seekers for SMEs, respectively. The proposed model not only enables bi-directional recommendation, but also enables HR matching without relearning for new job seekers and new job offers. As a result of the experiment, the proposed model showed superior performance in terms of precision, recall, and f1 than the existing collaborative filtering model named NCF+GMF. The proposed model is also confirmed that it is an evolutionary model that improves performance as training data increases.

• 한국통신학회논문지
• /
• 제29권12A호
• /
• pp.1333-1339
• /
• 2004

IS-95와 IMT-2000 시스템에서 사용되고 있는 여러 종류의 길쌈 부호기를 부호율 1/2, 구속장 3인 길쌈 부호기로 한정하여, neural network의 LVQ(Learning Vector Quantization)과 PVSL(Prototype Vector Selecting Logic)을 적용하여 비터비 복호기에서 사용되는 PM(Path Metric)과 BM(Branch Metric) 메모리 수와 산술$.$비교 연산량을 줄임으로써 시스템의 단순화와 순방향 복호를 가능하게 한다. 구속장의 확장성 여부와 관계없이 간단한 응용으로 기존의비터비 복호기에 적용할 수 있는 새로운 비터비 복호기의 구조와 적용 알고리즘을 제시하고, 제시된 비터비 복호기의 합리성을 VHDL 시뮬레이션으로 검증 후, 기존의 복호기와의 성능을 비교 분석한다.

• 한국방사선학회논문지
• /
• 제16권5호
• /
• pp.595-602
• /
• 2022

본 연구는 딥러닝을 이용한 흉부 X선 폐렴 영상에 대하여 정확하고 효율적인 의료영상의 자동진단을 위해서 가장 효율적인 학습률을 제시하고자 하였다. Inception V3 딥러닝 모델에 학습률을 0.1, 0.01, 0.001, 0.0001로 각각 설정한 후 3회 딥러닝 모델링을 수행하였다. 그리고 검증 모델링의 평균 정확도 및 손실 함수 값, Test 모델링의 Metric을 성능평가 지표로 설정하여 딥러닝 모델링의 수행 결과로 획득한 결과값의 3회 평균값으로 성능을 비교 평가하였다. 딥러닝 검증 모델링 성능평가 및 Test 모델링 Metric에 대한 성능평가의 결과, 학습률 0.001을 적용한 모델링이 가장 높은 정확도와 우수한 성능을 나타내었다. 이러한 이유로 본 논문에서는 딥러닝 모델을 이용한 흉부 X선 영상에 대한 폐렴 유무 분류 시 학습률을 0.001로 적용할 것을 권고한다. 그리고 본 논문에서 제시하는 학습률의 적용을 통한 딥러닝 모델링 시 흉부 X선 영상에 대한 폐렴 유무 분류에 대한 인력의 보조적인 역할을 수행할 수 있을 거라고 판단하였다. 향후 딥러닝을 이용한 폐렴 유무 진단 분류 연구가 계속해서 진행될 시, 본 논문의 논문 연구 내용은 기초자료로 활용될 수 있다고 여겨지며 나아가 인공지능을 활용한 의료영상 분류에 있어 효율적인 학습률 선택에 도움이 될 것으로 기대된다.