• ETRI Journal
• /
• 제36권1호
• /
• pp.99-105
• /
• 2014

This paper presents a new locomotion mode recognition method based on a transformed correlation feature analysis using an electromyography (EMG) pattern. Each movement is recognized using six weighted subcorrelation filters, which are applied to the correlation feature analysis through the use of six time-domain features. The proposed method has a high recognition rate because it reflects the importance of the different features according to the movements and thereby enables one to recognize real-time EMG patterns, owing to the rapid execution of the correlation feature analysis. The experiment results show that the discriminating power of the proposed method is 85.89% (${\pm}2.5$) when walking on a level surface, 96.47% (${\pm}0.9$) when going up stairs, and 96.37% (${\pm}1.3$) when going down stairs for given normal movement data. This makes its accuracy and stability better than that found for the principal component analysis and linear discriminant analysis methods.

• 한국멀티미디어학회논문지
• /
• 제18권3호
• /
• pp.323-329
• /
• 2015

In this paper we applied pattern recognition approach to detect audio forgery. Classification of the microphone types and models can help determining the authenticity of the recordings. Canonical correlation analysis was applied to extract feature for microphone classification. We utilized the linear dependence between two near-silence regions. To utilize the advantage of multi-feature based canonical correlation analysis, we selected three commonly used features to capture the temporal and spectral characteristics. Using three different microphones, we tested the usefulness of multi-feature based characteristics of canonical correlation analysis and compared the results with single feature based method. The performance of classification rate was carried out using the backpropagation neural network. Experimental results show the promise of canonical correlation features for microphone classification.

• 말소리와 음성과학
• /
• 제9권4호
• /
• pp.91-97
• /
• 2017

This study categorizes several voice characteristics by subjective listening assessment, and investigates correlation between voice characteristics and speech feature parameters. A model was developed to classify voice characteristics into the defined categories using SVM algorithm. To do this, we extracted various speech feature parameters from speech database for men in their 20s, and derived statistically significant parameters correlated with voice characteristics through ANOVA analysis. Then, these derived parameters were applied to the proposed SVM model. The experimental results showed that it is possible to obtain some speech feature parameters significantly correlated with the voice characteristics, and that the proposed model achieves the classification accuracies of 88.5% on average.

• 한국컴퓨터정보학회논문지
• /
• 제21권4호
• /
• pp.63-71
• /
• 2016

This paper is about applying efficient data mining method which improves the score calculation and proper building performance of credit ranking score system. The main idea of this data mining technique is accomplishing such objectives by applying Correlation based Feature Selection which could also be used to verify the properness of existing rank scores quickly. This study selected 2047 manufacturing companies on KOSPI market during the period of 2009 to 2013, which have their own credit rank scores given by NICE information service agency. Regarding the relevant financial variables, total 80 variables were collected from KIS-Value and DART (Data Analysis, Retrieval and Transfer System). If correlation based feature selection could select more important variables, then required information and cost would be reduced significantly. Through analysis, this study show that the proposed correlation based feature selection method improves selection and classification process of credit rank system so that the accuracy and credibility would be increased while the cost for building system would be decreased.

• 대한산업공학회지
• /
• 제42권6호
• /
• pp.370-376
• /
• 2016

Manufacturing data analysis and its applications are getting a huge popularity in various industries. In spite of the fast advancement in the big data analysis technology, however, the manufacturing quality data monitored from the automated inspection system sometimes is not reliable enough due to the complex patterns of product quality. In this study, thus, we aim to define the level of trusty of an automated quality inspection system and improve the reliability of the quality inspection data. By correlation analysis and feature selection, this paper presents a method of improving the inspection accuracy and efficiency in an SVM-based automatic product quality inspection system using thermal image data in an auto part manufacturing case. The proposed method is implemented in the sealer dispensing process of the automobile manufacturing and verified by the analysis of the optimal feature selection from the quality analysis results.

• 한국멀티미디어학회논문지
• /
• 제19권5호
• /
• pp.848-855
• /
• 2016

Face recognition has received a great deal of attention for the wide range of applications in real-world scenario. In this scenario, mismatches (so called heterogeneity) in terms of resolution and illumination between gallery and test face images are inevitable due to the different capturing conditions. In order to deal with the mismatch problem, we propose a local feature learning method using deep canonical correlation analysis (DCCA) for heterogeneous face recognition. By the DCCA, we can effectively reduce the mismatch between the gallery and the test face images. Furthermore, the proposed local feature learned by the DCCA is able to enhance the discriminative power by using facial local structure information. Through the experiments on two different scenarios (i.e., matching near-infrared to visible face images and matching low-resolution to high-resolution face images), we could validate the effectiveness of the proposed method in terms of recognition accuracy using publicly available databases.

• 한국정보통신학회논문지
• /
• 제16권9호
• /
• pp.1878-1883
• /
• 2012

일반적으로 수중표적 인식에서는 표적의 형상/재질에 따른 수신 표적신호의 공간적인 정보를 특징인자로 추출하여 식별하고자 하는 특징을 추출하였다. 또한, 표적신호의 수신 위치에 덜 민감한 특징파라미터 추출을 위해 다양한 신호처리 기법을 적용하는 연구가 수행되어 왔다. 본 논문에서는 표적신호의 수신위치에 상대적으로 민감하지 않은 정준상관분석(Canonical correlation Analysis; CCA)을 사용하여 합성된 수중물체의 특징을 분석하였다. 다중각도 환경에서 특징추출을 위해 정준산관분석기법이 적용되었으며, 각각 다른 각도에서 수중물체에 반사되어 되돌아오는 연속적인 두개의 소나신호를 대상으로 정준상관분석을 수행하여 두 신호의 상관성을 분석하였다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권3호
• /
• pp.79-84
• /
• 2021

고차원의 데이터를 처리하기 위해서는 데이터의 성질을 유지하면서 특징을 잘 반영할 수 있는 특징 추출 방법이 필요하다. 주성분분석 방법은 고차원 데이터에 포함된 정보를 저차원의 데이터로 변환하여 원래 데이터의 변수 수보다 적은 수의 변수로 고차원 데이터를 표현 할 수 있는 방법으로서 데이터의 특징 추출을 위한 대표적인 방법이다. 본 연구에서는 데이터가 고차원인 경우 데이터 특징 추출을 위한 주성분 분석에 있어서 주성분 변수 선정 시 적응적 상관도를 기반으로 한 주성분 분석 방법을 제안한다. 제안하는 방법은 입력 데이터간의 상관 관계를 기반으로 상관도를 적응적으로 반영하여 데이터의 주성분을 분석함으로써 다른 여러 변수에 중복적으로 상관도가 높은 변수와 주성분을 유도하는데 연관성이 적은 변수를 주성분 변수 후보 대상에서 제외시키고자 한다. 고유벡터 계수 값에 의한 주성분 위계를 분석하고 위계가 낮은 주성분이 변수로 선정이 되는 것을 막고 또한 상관 분석을 통하여 데이터의 중복 발생이 데이터 편향을 유도하는 것을 최소화하 하고자 한다. 이를 통하여 주성분 변수 선정 시 데이터 편향성의 영향을 줄임으로써 실제 데이터의 특징을 잘 나타내는 주성분 변수를 선정하는 방법을 제안하고자 한다.

• Journal of Multimedia Information System
• /
• 제9권3호
• /
• pp.177-182
• /
• 2022

A deep neural network (DNN) includes variables whose values keep on changing with the training process until it reaches the final point of convergence. These variables are the co-efficient of a polynomial expression to relate to the feature extraction process. In general, DNNs work in multiple 'dimensions' depending upon the number of channels and batches accounted for training. However, after the execution of feature extraction and before entering the SoftMax or other classifier, there is a conversion of features from multiple N-dimensions to a single vector form, where 'N' represents the number of activation channels. This usually happens in a Fully connected layer (FCL) or a dense layer. This reduced 2D feature is the subject of study for our analysis. For this, we have used the FCL, so the trained weights of this FCL will be used for the weight-class correlation analysis. The popular DNN models selected for our study are ResNet-101, VGG-19, and GoogleNet. These models' weights are directly used for fine-tuning (with all trained weights initially transferred) and scratch trained (with no weights transferred). Then the comparison is done by plotting the graph of feature distribution and the final FCL weights.

• 한국물환경학회지
• /
• 제35권5호
• /
• pp.425-431
• /
• 2019

Recently, people have been attracting attention to the good quality of water resources as well as water welfare. to improve the quality of life. This study is a papers on the prediction of benthic macroinvertebrate index (BMI), which is a aquatic ecological health, using the machine learning based CFS (Correlation-based Feature Selection) method and the random forest model to compare the measured and predicted values of the BMI. The data collected from the Han River's branch for 10 years are extracted and utilized in 1312 data. Through the utilized data, Pearson correlation analysis showed a lack of correlation between single factor and BMI. The CFS method for multiple regression analysis was introduced. This study calculated 10 factors(water temperature, DO, electrical conductivity, turbidity, BOD, $NH_3-N$, T-N, $PO_4-P$, T-P, Average flow rate) that are considered to be related to the BMI. The random forest model was used based on the ten factors. In order to prove the validity of the model, $R^2$, %Difference, NSE (Nash-Sutcliffe Efficiency) and RMSE (Root Mean Square Error) were used. Each factor was 0.9438, -0.997, and 0,992, and accuracy rate was 71.6% level. As a result, These results can suggest the future direction of water resource management and Pre-review function for water ecological prediction.