• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권9호
• /
• pp.4317-4335
• /
• 2018

Semi-supervised multi-view latent space learning is gaining considerable popularity recently in many machine learning applications due to the high cost and difficulty to obtain the large amount of label information of data. Although some semi-supervised multi-view latent space learning methods have been presented, there is still much space for improvement: 1) How to learn latent discriminant intact feature representations by employing data of multiple views; 2) How to exploit the manifold structure of both labeled and unlabeled point in the learned latent intact space effectively. To address the above issues, we propose an approach called semi-supervised multi-view manifold discriminant intact space learning ($SM^2DIS$) for image classification in this paper. $SM^2DIS$ aims to seek a manifold discriminant intact space for data of different views by making use of both the discriminant information of labeled data and the manifold structure of both labeled and unlabeled data. Experimental results on MNIST, COIL-20, Multi-PIE, and Caltech-101 databases demonstrate the effectiveness and robustness of our proposed approach.

• Genomics & Informatics
• /
• 제17권2호
• /
• pp.20.1-20.5
• /
• 2019

Entity normalization, or entity linking in the general domain, is an information extraction task that aims to annotate/bind multiple words/expressions in raw text with semantic references, such as concepts of an ontology. An ontology consists minimally of a formally organized vocabulary or hierarchy of terms, which captures knowledge of a domain. Presently, machine-learning methods, often coupled with distributional representations, achieve good performance. However, these require large training datasets, which are not always available, especially for tasks in specialized domains. CONTES (CONcept-TErm System) is a supervised method that addresses entity normalization with ontology concepts using small training datasets. CONTES has some limitations, such as it does not scale well with very large ontologies, it tends to overgeneralize predictions, and it lacks valid representations for the out-of-vocabulary words. Here, we propose to assess different methods to reduce the dimensionality in the representation of the ontology. We also propose to calibrate parameters in order to make the predictions more accurate, and to address the problem of out-of-vocabulary words, with a specific method.

• 대한수학회보
• /
• 제60권3호
• /
• pp.575-591
• /
• 2023

Motivated by several generalizations of the Pochhammer symbol and their associated families of hypergeometric functions and hypergeometric polynomials, by choosing to use a very generalized Pochhammer symbol, we aim to introduce certain extensions of the generalized Lauricella function F⁽ⁿ⁾_A and the Humbert's confluent hypergeometric function Ψ⁽ⁿ⁾ of n variables with, as their respective particular cases, the second Appell hypergeometric function F₂ and the generalized Humbert's confluent hypergeometric functions Ψ₂ and investigate their several properties including, for example, various integral representations, finite summation formulas with an s-fold sum and integral representations involving the Laguerre polynomials, the incomplete gamma functions, and the Bessel and modified Bessel functions. Also, pertinent links between the major identities discussed in this article and different (existing or novel) findings are revealed.

• 대한수학교육학회지:수학교육학연구
• /
• 제8권1호
• /
• pp.59-71
• /
• 1998

Recently, most classrooms in Korea are fully equipped with multimedia environments such as a powerful pentium pc, a 43″large sized TV, and so on through the third renovation of classroom environments. However, there is not much software teachers can use directly in their teaching. Even with existing software such as GSP, and Mathematica, it turns out that it doesn####t fit well in a large number of students in classrooms and with all written in English. The study is to analyze the characteristics of problem-solving process and to develop a computer program which integrates the instruction of problem solving into a regular math program in areas of quadratic functions and ellipses. Problem Solving in this study included two sessions: 1) Learning of basic facts, concepts, and principles; 2) problem solving with problem contexts. In the former, the program was constructed based on the definitions of concepts so that students can explore, conjecture, and discover such mathematical ideas as basic facts, concepts, and principles. In the latter, the Polya#s 4 phases of problem-solving process contributed to designing of the program. In understanding of a problem, the program enhanced students#### understanding with multiple, dynamic representations of the problem using visualization. The strategies used in making a plan were collecting data, using pictures, inductive, and deductive reasoning, and creative reasoning to develop abstract thinking. In carrying out the plan, students can solve the problem according to their strategies they planned in the previous phase. In looking back, the program is very useful to provide students an opportunity to reflect problem-solving process, generalize their solution and create a new in-depth problem. This program was well matched with the dynamic and oscillation Polya#s problem-solving process. Moreover, students can facilitate their motivation to solve a problem with dynamic, multiple representations of the problem and become a powerful problem solve with confidence within an interactive computer environment. As a follow-up study, it is recommended to research the effect of the program in classrooms.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2016년도 춘계학술발표대회
• /
• pp.633-635
• /
• 2016

Convolutional Networks (ConvNets) are powerful models that learn hierarchies of visual features, which could also be used to obtain image representations for transfer learning. The basic pipeline for transfer learning is to first train a ConvNet on a large dataset (source task) and then use feed-forward units activation of the trained ConvNet as image representation for smaller datasets (target task). Our key contribution is to demonstrate superior performance of multiple ConvNet layer features over single ConvNet layer features. Combining multiple ConvNet layer features will result in more complex feature space with some features being repetitive. This requires some form of feature selection. We use AdaBoost with single stumps to implicitly select only distinct features that are useful towards classification from concatenated ConvNet features. Experimental results show that using multiple ConvNet layer activation features instead of single ConvNet layer features consistently will produce superior performance. Improvements becomes significant as we increase the distance between source task and the target task.

• 한국문헌정보학회지
• /
• 제31권3호
• /
• pp.135-146
• /
• 1997

일반적으로 주어진 정보 요구에 대하여 서로 다른 사용자는 서로 다른 질의를 생성할 수 있으며, 또는 한명의 사용자가 통제어의 사용 여부에 따라 서로 다른 질의를 생성할 수 있다. 최근 정보 검색 분야의 연구들은 이러한 서로 다른 질의 표현은 서로 다른 문서 집합을 검색함을 보여준다. 본 논문에서는 하나의 사용자 질의에 대하여 다양한 적합성 피드백 방법을 적용함으로써 다중의 질의들을 자동으로 생성한 후, 생성된 다중 질의들을 다시 하나의 질의로 결합하는 방법을 제안한다. 또한 실험을 통하여 자동으로 생성된 다중의 질의들을 결합함으로써 보다 높은 검색 효과를 얻을 수 있음을 입증한다.

• 한국멀티미디어학회논문지
• /
• 제20권5호
• /
• pp.758-768
• /
• 2017

In this paper, we present a novel method to extract face representation based on multi-resolution spatial pyramid. In our method, a face is subdivided into increasingly finer sub-regions (local regions) and represented at multiple levels of histogram representations. To cope with misaligned problem, patch-based local descriptor extraction has been also developed in a novel way. To preserve multiple levels of detail in local characteristics and also encode holistic spatial configuration, histograms from all levels of spatial pyramid are integrated by using dimensionality reduction and feature combination, leading to our spatial-pyramid face feature representation. We incorporate our proposed face features into general face recognition pipeline and achieve state-of-the-art results on challenging face recognition problems.

• 한국멀티미디어학회논문지
• /
• 제20권8호
• /
• pp.1175-1186
• /
• 2017

Human emotion recognition is one of the promising applications in the era of artificial super intelligence. Thus far, facial expression traits are considered to be the most widely used information cues for realizing automated emotion recognition. This paper proposes a novel facial expression recognition (FER) method that works well for recognizing emotion from image sequences. To this end, we develop the so-called weighted soft voting classification (WSVC) algorithm. In the proposed WSVC, a number of classifiers are first constructed using different and multiple feature representations. In next, multiple classifiers are used for generating the recognition result (namely, soft voting) of each face image within a face sequence, yielding multiple soft voting outputs. Finally, these soft voting outputs are combined through using a weighted combination to decide the emotion class (e.g., anger) of a given face sequence. The weights for combination are effectively determined by measuring the quality of each face image, namely "peak expression intensity" and "frontal-pose degree". To test the proposed WSVC, CK+ FER database was used to perform extensive and comparative experimentations. The feasibility of our WSVC algorithm has been successfully demonstrated by comparing recently developed FER algorithms.

• 감성과학
• /
• 제26권1호
• /
• pp.43-54
• /
• 2023

본 연구는 참가자 간 상관(Intersubject correlation: ISC)기법을 통해 정서 유발 자극에 대한 한 참가자의 반응과 그 참가자를 제외한 나머지 참가자들의 반응 간 일치성이 각 정서표상 범주(지배가, 각성가, 정서가)와 다양한 감각양상(청각, 시각, 촉각)에서 어떠한 차이가 있는지 밝히고자 하였다. 참가자 간 상관을 계산하기 위해 사용된 데이터는 참가자들의 청각, 시각, 촉각 자극에 대한 생리 측정치와 정서 평정치로 구성되었으며, 한 참가자의 데이터 세트와 나머지 참가자들의 데이터 세트의 평균으로 구분한 뒤 가능한 모든 자극 쌍에 대해 상관을 구하는 방식으로 참가자 간 상관을 계산하였다. 연구 결과, 지배가를 기준으로 재정렬한 데이터 세트에 대한 참가자들의 반응 일치성은 청각 감각양상 조건보다 시각 감각양상 조건에서 높은 ISC 값을 얻었다. 다음으로 각성가로 재정렬한 데이터 세트의 경우 시각 감각양상과 청각 감각양상에서 차이가 있음은 같았지만, 지배가 기준으로 재정렬한 데이터 세트와 결과가 상반되었다. 마지막으로, 정서가를 기준으로 재정렬된 데이터 세트는 모든 감각양상에서 부정적인 데이터 세트들이 긍정적인 데이터 세트보다 참가자들의 반응 일치성이 더 높았다. 모든 데이터 세트에서 정서표상 범주의 높고 낮음과 상관없이 촉각 감각양상에서 높은 ISC 값을 얻었다. 본 연구의 결과는 참가자 간 상관의 다양한 감각양상과 정서표상에 대한 반응의 일치성이 의미하는 바에 대한 해석을 제시하며, ISC 분석 방법이 참가자 반응의 차이에 대한 패턴을 측정하는 유용한 도구가 될 가능성을 제시하였다.

• Journal of Multimedia Information System
• /
• 제4권4호
• /
• pp.233-238
• /
• 2017

Automatic identification of disease in plants from their leaves is one of the most challenging task to researchers. Diseases among plants degrade their performance and results into a huge reduction of agricultural products. Therefore, early and accurate diagnosis of such disease is of the utmost importance. The advancement in deep Convolutional Neural Network (CNN) has change the way of processing images as compared to traditional image processing techniques. Deep learning architectures are composed of multiple processing layers that learn the representations of data with multiple levels of abstraction. Therefore, proved highly effective in comparison to many state-of-the-art works. In this paper, we present a plant disease identification methodology from their leaves using deep CNNs. For this, we have adopted GoogLeNet that is considered a powerful architecture of deep learning to identify the disease types. Transfer learning has been used to fine tune the pre-trained model. An accuracy of 85.04% has been recorded in the identification of four disease class in Apple plant leaves. Finally, a comparison with other models has been performed to show the effectiveness of the approach.