• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권3호
• /
• pp.1243-1263
• /
• 2018

The two-stage linear discrimination analysis (TSLDA) is a feature extraction technique to solve the small size sample problem in the field of image recognition. The TSLDA has retained all subspace information of the between-class scatter and within-class scatter. However, the feature information in the four subspaces may not be entirely beneficial for classification, and the regularization procedure for eliminating singular metrics in TSLDA has higher time complexity. In order to address these drawbacks, this paper proposes an improved two-stage linear discriminant analysis (Improved TSLDA). The Improved TSLDA proposes a selection and compression method to extract superior feature information from the four subspaces to constitute optimal projection space, where it defines a single Fisher criterion to measure the importance of single feature vector. Meanwhile, Improved TSLDA also applies an approximation matrix method to eliminate the singular matrices and reduce its time complexity. This paper presents comparative experiments on five face databases and one handwritten digit database to validate the effectiveness of the Improved TSLDA.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2002년도 춘계종합학술대회
• /
• pp.177-180
• /
• 2002

본 논문에서는 이진영상 데이터의 저작권 보호를 위한 디지털 워터마킹 방법을 제안하였다. 제안 방법은 먼저 이진영상을 기하학적 특징이 포함된 특징영역과 그 외의 일반영역으로 분리한다. 그리고 기하학적 특징이 포함된 이진영상의 특징영역을 보존하면서 인증을 위한 워터마크를 일반영역에만 삽입, 검출하는 효과적인 워터마킹 방법을 연구하였다. 특징영역은 특수런을 사용한 런길이부호화를 이용하여 일반영역과 분리하였다. 워터마크의 비가시성을 위해 워터마크는 일반영역 중에서 화소변화에 대한 민감도를 고려하여 삽입하였다. 제안 방법을 문사, 서명, 도장, 지문영상에 적용하여 성능을 평가하였다. 실험 결과 제안 방법은 원 영상의 중요한 특징영역을 보존하고, 또한 워터마킹된 영상의 비가시성이 높음을 알 수 있었다.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.369-384
• /
• 2021

In a personalized product recommendation system, when the amount of log data is large or sparse, the accuracy of model recommendation will be greatly affected. To solve this problem, a personalized product recommendation method using deep factorization machine (DeepFM) to analyze user behavior is proposed. Firstly, the K-means clustering algorithm is used to cluster the original log data from the perspective of similarity to reduce the data dimension. Then, through the DeepFM parameter sharing strategy, the relationship between low- and high-order feature combinations is learned from log data, and the click rate prediction model is constructed. Finally, based on the predicted click-through rate, products are recommended to users in sequence and fed back. The area under the curve (AUC) and Logloss of the proposed method are 0.8834 and 0.0253, respectively, on the Criteo dataset, and 0.7836 and 0.0348 on the KDD2012 Cup dataset, respectively. Compared with other newer recommendation methods, the proposed method can achieve better recommendation effect.

• 대한전자공학회논문지SP
• /
• 제42권3호
• /
• pp.115-120
• /
• 2005

본 논문에서는 multi-feature clustering(MFC) 방법을 이용한 강인한 내용 기반 음악 장르 분류 알고리즘을 제안한다. 기존 연구와 비교하여 본 논문에서는 입력 질의 패턴(또는 구간)과 입력 질의 길이의 변화에 따라 나타나는 불안정한 시스템 성능을 개선하는데 노력하였고, k-means clustering 기법에 기반한 multi-feature clustering(MFC)이라는 새로운 알고리즘을 제안하였다. 제안된 시스템의 성능을 검증하기 위해 질의 음악 파일의 서로 다른 여러 구간에서 질의 길이를 다변화하여 음악 특징 계수를 추출하였고, MFC 방법을 사용한 시스템과 MFC 방법을 사용하지 않은 시스템에 대한 장르 분류 성공률을 비교하여 제안 알고리즘의 성능을 비교${\cdot}$분석하였다. 모의실험 결과 MFC 방법을 사용한 시스템의 장르 분류 성공률이 높게 나타났고, 시스템의 안정성 역시 높게 나타났다.

• 한국정보시스템학회지:정보시스템연구
• /
• 제26권3호
• /
• pp.63-90
• /
• 2017

Purpose This study proposes a novel system trading model using case-based reasoning (CBR) based on absolute similarity threshold. The proposed model is designed to optimize the absolute similarity threshold, feature selection, and instance selection of CBR by using genetic algorithm (GA). With these mechanisms, it enables us to yield higher returns from stock market trading. Design/Methodology/Approach The proposed CBR model uses the absolute similarity threshold varying from 0 to 1, which serves as a criterion for selecting appropriate neighbors in the nearest neighbor (NN) algorithm. Since it determines the nearest neighbors on an absolute basis, it fails to select the appropriate neighbors from time to time. In system trading, it is interpreted as the signal of 'hold'. That is, the system trading model proposed in this study makes trading decisions such as 'buy' or 'sell' only if the model produces a clear signal for stock market prediction. Also, in order to improve the prediction accuracy and the rate of return, the proposed model adopts optimal feature selection and instance selection, which are known to be very effective in enhancing the performance of CBR. To validate the usefulness of the proposed model, we applied it to the index trading of KOSPI200 from 2009 to 2016. Findings Experimental results showed that the proposed model with optimal feature or instance selection could yield higher returns compared to the benchmark as well as the various comparison models (including logistic regression, multiple discriminant analysis, artificial neural network, support vector machine, and traditional CBR). In particular, the proposed model with optimal instance selection showed the best rate of return among all the models. This implies that the application of CBR with the absolute similarity threshold as well as the optimal instance selection may be effective in system trading from the perspective of returns.

• Advances in materials Research
• /
• 제8권4호
• /
• pp.313-335
• /
• 2019

The objective of the present paper is to investigate the bending and free vibration behavior of functionally graded material (FGM) sandwich rectangular plates using an efficient and simple higher order shear deformation theory. Unlike other theories, there are only four unknown functions involved, as compared to five in other shear deformation theories. The most interesting feature of this theory is that it does not require the shear correction factor. Two common types of FGM sandwich plates are considered, namely, the sandwich with the FGM facesheet and the homogeneous core and the sandwich with the homogeneous facesheet and the FGM core. The equation of motion for the FGM sandwich plates is obtained based on Hamilton's principle. The closed form solutions are obtained by using the Navier technique. A static and free vibration frequency is given for different material properties. The accuracy of the present solutions is verified by comparing the obtained results with the existing solutions.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 1997년도 춘계학술대회논문집; 경주코오롱호텔; 22-23 May 1997
• /
• pp.110-115
• /
• 1997

In this work, the constant average acceleration, which is a fundamental feature of the trapezoidal rule, is investigated and generalized. Using the generalization of average acceleration concept, a higher order accurate and unconditionally stable time-integration method is developed. The linear approximate of the present methods is exactly the same as the famous trapezoidal rule. To observe the accuracy and stability of the method, several numerical tests are performed and the results are compared with the results from the trapezoidal rule and the exact solution. From the numerical tests, it has been known that the present method has a higher order accuracy and unconditional stability.

• 한국음향학회지
• /
• 제13권2호
• /
• pp.50-59
• /
• 1994

본 논문에서는 3차 Cumulant를 이용하여 음성의 특징벡타를 추출하고, 이것을 신경회로망의 입력으로 사용하는 음성 인식 방법을 제시한다. 3차 이상의 고차 cumulant를 이용하면 Gaussian 잡음과 음성 신호의 분리가 가능하며, 충분히 많은 데이타를 사용할 경우 음성 데이타를 AR 모델링한 계수값을 bias 없이 추출할 수 있다. 또한 기존의 2차 statistics를 이용한 특징 벡타 추출 방법과 비교할 때 잡음이 큰 경우에도 분산은 크지만 bias가 작아 보다 잡음에 강한 특징벡타를 추출할 수 있다. 한국어 단모음에 대한 모의실험을 통하여 유색 잡음 환경에서 SNR이 커질수록 3차 cumulant를 이용한 방법이 기존의 2차 statistics를 이용한 방법보다 높은 인식율을 나타냄을 보인다.

• ETRI Journal
• /
• 제28권6호
• /
• pp.807-810
• /
• 2006

This letter presents a prediction model for sentence-final intonations for Korean conversational-style text-to-speech systems in which we introduce the linguistic feature of 'modality' as a new parameter. Based on their function and meaning, we classify tonal forms in speech data into tone types meaningful for speech synthesis and use the result of this classification to build our prediction model using a tree structured classification algorithm. In order to show that modality is more effective for the prediction model than features such as sentence type or speech act, an experiment is performed on a test set of 970 utterances with a training set of 3,883 utterances. The results show that modality makes a higher contribution to the determination of sentence-final intonation than sentence type or speech act, and that prediction accuracy improves up to 25% when the feature of modality is introduced.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1998년도 제15회 음성통신 및 신호처리 워크샵(KSCSP 98 15권1호)
• /
• pp.250-253
• /
• 1998

In digital communicatioin networks, speech recognition systems conventionally reconstruct speech followed by extracting feature [parameters. In this paper, we consider a useful approach by incorporating speech coding parameters into the speech recognizer. Most speech coders employed in the networks represent line spectral pairs as spectral parameters. In order to improve the recognition performance of the LSP-based speech recognizer, we introduce two different ways: one is to devise weighed distance measures of LSPs and the other is to transform LSPs into a new feature set, named a pseudo-cepstrum. Experiments on speaker-independent connected-digit recognition showed that the weighted distance measures significantly improved the recognition accuracy than the unweighted one of LSPs. Especially we could obtain more improved performance by using PCEP. Compared to the conventional methods employing mel-frequency cepstral coefficients, the proposed methods achieved higher performance in recognition accuracies.