• Journal of Information Processing Systems
• /
• 제13권4호
• /
• pp.863-875
• /
• 2017

The traditional text similarity measurement methods based on word frequency vector ignore the semantic relationships between words, which has become the obstacle to text similarity calculation, together with the high-dimensionality and sparsity of document vector. To address the problems, the improved singular value decomposition is used to reduce dimensionality and remove noises of the text representation model. The optimal number of singular values is analyzed and the semantic relevance between words can be calculated in constructed semantic space. An inverted index construction algorithm and the similarity definitions between vectors are proposed to calculate the similarity between two documents on the semantic level. The experimental results on benchmark corpus demonstrate that the proposed method promotes the evaluation metrics of F-measure.

• 말소리와 음성과학
• /
• 제7권4호
• /
• pp.49-55
• /
• 2015

It is argued in this paper that, in determining semantic similarity, Korean words should be recategorized with a focus on the semantic relation to ontology in light of cross-linguistic morphological variations. It is proposed, in particular, that Korean semantic similarity should be measured on three tracks, human judgements track, relatedness track, and cross-part-of-speech relations track. As demonstrated in Yang et al. (2015), GloVe, the unsupervised learning machine on semantic similarity, is applicable to Korean with its performance being compared with human judgement results. Based on this compatability, it was further thought that the model's performance might most likely vary with different kinds of specific relations in different languages. An attempt was made to analyze them in terms of two major Korean-specific categories involved in their lexical and cross-POS-relations. It is concluded that languages must be analyzed by varying methods so that semantic components across languages may allow varying semantic distance in the vector space models.

• 한국지능시스템학회논문지
• /
• 제11권7호
• /
• pp.579-583
• /
• 2001

In the area of data clustering in high dimensional space, one of the difficulties is the time-consuming process for computing vector similarities. It becomes worse in the case of the agglomerative algorithm with the group-average link and mean centroid method, because the cluster similarity must be recomputed whenever the cluster center moves after the merging step. As a solution of this problem, we present an incremental method of similarity computation, which substitutes the scalar calculation for the time-consuming calculation of vector similarity with several measures such as the squared distance, inner product, cosine, and minimum variance. Experimental results show that it makes clustering speed significantly fast for very high dimensional data.

• The Journal of the Acoustical Society of Korea
• /
• 제27권2E호
• /
• pp.51-56
• /
• 2008

In this paper, we propose an effective method for music summarization which automatically extracts a representative part of the music by using signal processing technology. Proposed method uses a vector quantization technique to extract several segments which can be regarded as the most important contents in the music. In general, there is a repetitive pattern in music, and human usually recognizes the most important or catchy tune from the repetitive pattern. Thus the repetition which is extracted using segment similarity is considered to express a music summary. The segments extracted are again combined to generate a complete music summary. Experiments show the proposed method captures the main theme of the music more effectively than conventional methods. The experimental results also show that the proposed method could be used for real-time application since the processing time in generating music summary is much faster than other methods.

• 대한원격탐사학회지
• /
• 제36권1호
• /
• pp.55-65
• /
• 2020

Image classification needs the spectral similarity comparison between spectral features of each pixel and the representative spectral features of each class. The spectral similarity is obtained by computing the spectral feature vector distance between the pixel and the class. Each spectral feature contributes differently in the image classification depending on the class separability of the spectral feature, which is computed using a suitable vector distance measure such as the Bhattacharyya distance. We propose a method to determine the weight value of each spectral feature in the computation of feature vector distance for the similarity measurement. The weight value is determined by the ratio between each feature separability value to the total separability values of all the spectral features. We created ten spectral features consisting of seven bands of Landsat-8 OLI image and three indices, NDVI, NDWI and NDBI. For three experimental test sites, we obtained the overall accuracies between 95.0% and 97.5% and the kappa coefficients between 90.43% and 94.47%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권11호
• /
• pp.2824-2838
• /
• 2013

There has been a lot of attention paid recently to analyze dynamic human gestures that vary over time. Most attention to dynamic gestures concerns with spatio-temporal features, as compared to analyzing each frame of gestures separately. For accurate dynamic gesture recognition, motion feature extraction algorithms need to find representative features that uniquely identify time-varying gestures. This paper proposes a new feature-extraction algorithm using temporal self-similarity based on a hierarchical human model. Because a conventional temporal self-similarity method computes a whole movement among the continuous frames, the conventional temporal self-similarity method cannot recognize different gestures with the same amount of movement. The proposed model-based temporal self-similarity method groups body parts of a hierarchical model into several sets and calculates movements for each set. While recognition results can depend on how the sets are made, the best way to find optimal sets is to separate frequently used body parts from less-used body parts. Then, we apply a multiclass support vector machine whose optimization algorithm is based on structural support vector machines. In this paper, the effectiveness of the proposed feature extraction algorithm is demonstrated in an application for taebo gesture recognition. We show that the model-based temporal self-similarity method can overcome the shortcomings of the conventional temporal self-similarity method and the recognition results of the model-based method are superior to that of the conventional method.

• 한국측량학회지
• /
• 제30권6_2호
• /
• pp.665-672
• /
• 2012

Amid rapidly increasing imagery inputs and their volume in a remote sensing imagery database, Content-Based Image Retrieval (CBIR) is an effective tool to search for an image feature or image content of interest a user wants to retrieve. It seeks to capture salient features from a 'query' image, and then to locate other instances of image region having similar features elsewhere in the image database. For a CBIR approach that uses texture as a primary feature primitive, designing a texture descriptor to better represent image contents is a key to improve CBIR results. For this purpose, an extended feature vector combining the Gabor filter and co-occurrence histogram method is suggested and evaluated for quantitywise and qualitywise retrieval performance criterion. For the better CBIR performance, assessing similarity between high dimensional feature vectors is also a challenging issue. Therefore a number of distance metrics (i.e. L1 and L2 norm) is tried to measure closeness between two feature vectors, and its impact on retrieval result is analyzed. In this paper, experimental results are presented with several CBIR samples. The current results show that 1) the overall retrieval quantity and quality is improved by combining two types of feature vectors, 2) some feature is better retrieved by a specific feature vector, and 3) retrieval result quality (i.e. ranking of retrieved image tiles) is sensitive to an adopted similarity metric when the extended feature vector is employed.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1991년도 하계학술대회 논문집
• /
• pp.825-828
• /
• 1991

This paper addresses estimation of the relative shift vector from aerial image sequences. We perform similarity function tests and decide the most appropriate similarity function for the visual navigation system using aerial images. Finally, we propose the maximum variance reference line selection method for reducing the estimation error of the shift vector.

• Journal of Computing Science and Engineering
• /
• 제9권2호
• /
• pp.73-82
• /
• 2015

Understanding how the topic evolves is an important and challenging task. A topic usually consists of multiple related events, and the accurate identification of event evolution relationship plays an important role in topic evolution analysis. Existing research has used the traditional vector space model to represent the event, which cannot be used to accurately compute the semantic similarity between events. This has led to poor performance in identifying event evolution relationship. This paper suggests constructing a semantic aspect-based vector space model to represent the event: First, use hierarchical Dirichlet process to mine the semantic aspects. Then, construct a semantic aspect-based vector space model according to these aspects. Finally, represent each event as a point and measure the semantic relatedness between events in the space. According to our evaluation experiments, the performance of our proposed technique is promising and significantly outperforms the baseline methods.

• 말소리와 음성과학
• /
• 제7권4호
• /
• pp.41-47
• /
• 2015

This paper examines whether the Global Vector model is applicable to Korean data as a universal learning algorithm. The main purpose of this study is to compare the global vector model (GloVe) with the word2vec models such as a continuous bag-of-words (CBOW) model and a skip-gram (SG) model. For this purpose, we conducted an experiment by employing an evaluation corpus consisting of 70 target words and 819 pairs of Korean words for word similarities and analogies, respectively. Results of the word similarity task indicated that the Pearson correlation coefficients of 0.3133 as compared with the human judgement in GloVe, 0.2637 in CBOW and 0.2177 in SG. The word analogy task showed that the overall accuracy rate of 67% in semantic and syntactic relations was obtained in GloVe, 66% in CBOW and 57% in SG.