• Journal of Information Processing Systems
• /
• 제14권4호
• /
• pp.807-823
• /
• 2018

Speaker verification system performance depends on the utterance of each speaker. To verify the speaker, important information has to be captured from the utterance. Nowadays under the constraints of limited data, speaker verification has become a challenging task. The testing and training data are in terms of few seconds in limited data. The feature vectors extracted from single frame size and rate (SFSR) analysis is not sufficient for training and testing speakers in speaker verification. This leads to poor speaker modeling during training and may not provide good decision during testing. The problem is to be resolved by increasing feature vectors of training and testing data to the same duration. For that we are using multiple frame size (MFS), multiple frame rate (MFR), and multiple frame size and rate (MFSR) analysis techniques for speaker verification under limited data condition. These analysis techniques relatively extract more feature vector during training and testing and develop improved modeling and testing for limited data. To demonstrate this we have used mel-frequency cepstral coefficients (MFCC) and linear prediction cepstral coefficients (LPCC) as feature. Gaussian mixture model (GMM) and GMM-universal background model (GMM-UBM) are used for modeling the speaker. The database used is NIST-2003. The experimental results indicate that, improved performance of MFS, MFR, and MFSR analysis radically better compared with SFSR analysis. The experimental results show that LPCC based MFSR analysis perform better compared to other analysis techniques and feature extraction techniques.

• 한국빅데이터학회지
• /
• 제8권1호
• /
• pp.35-47
• /
• 2023

It is crucial to develop effective and efficient big data analytics methods for problem-solving in the field of business in order to improve the performance of data analytics and reduce costs and risks in the analysis of customer data. In this study, a big data-driven data analysis system using artificial intelligence techniques is designed to increase the accuracy of big data analytics along with the rapid growth of the field of data science. We present a key direction for big data analysis systems through missing value imputation, outlier detection, feature extraction, utilization of explainable artificial intelligence techniques, and exploratory data analysis. Our objective is not only to develop big data analysis techniques with complex structures of business data but also to bridge the gap between the theoretical ideas in artificial intelligence methods and the analysis of real-world data in the field of business.

• 한국국방경영분석학회지
• /
• 제6권2호
• /
• pp.89-127
• /
• 1980

The multivariate analysis techniques of cluster analysis are examined in this article. The theory and applications of the techniques and computer software concerning these techniques are discussed and sample jobs are included. A hierarchical cluster analysis algorithm, available in the IMSL software package, is applied to a set of data extracted from a group of subjects for the purpose of partitioning a collection of 26 attributes of a weapon system into six clusters of superattributes. A nonhierarchical clustering procedure were applied to a collection of data of tanks considering of twenty-four observations of ten attributes of tanks. The cluster analysis shows that the tanks cluster somewhat naturally by nationality. The principal componant analysis and the discriminant analysis show that tank weight is the single most important discriminator among nationality although they are not shown in this article because of the space restriction. This is a part of thesis for master's degree in operations research.

• 한국의상디자인학회지
• /
• 제25권2호
• /
• pp.123-134
• /
• 2023

Fashion design, CAD production, and the use of digital software can shorten the time and production processes in the fashion industry, but there are still many limitations in how to similarly express textile textures. Having this awareness, how to implement the visual effects of textile texture similar to that of the real world in the virtual world is one of the major exploration tasks in the fashion industry. Therefore, this study aims to analyze examples of embroidery techniques in Christian Dior collections and explore how embroidery techniques in 3D CLO fashion design can express the texture of real clothes more similarly by creating virtual works through 3D samples and 3D CLO software. First, the analysis criteria and theoretical basis of this study were derived through a literature review on fashion textile embroidery techniques, identifying types and characteristics of embroidery techniques, and classifying them into 12 types. Second, photos of the Dior 2017-2023 SS/FW Ready-to-Wear collections were collected and analyzed through the case analysis VOGUE site. Third, it presents the production of 3D CLO works by deriving a method of implementing embroidery techniques through the design of sample textile embroidery techniques using substances 3D sample software. The study's has some limitations. First, in 3D CLO fashion design, the needle gap for embroidery must be widened to see the thread pattern. Second, by reducing the number of needles, it is necessary to imitate the actual embroidery effect. Third, it is judged that it will be effective to lengthen the thread and adjust the thickness of the thread. Fourth, the thickness of the entire embroidery pattern must be increased to enable a three-dimensional texture.

• Journal of Advanced Marine Engineering and Technology
• /
• 제40권8호
• /
• pp.726-732
• /
• 2016

Clustering analysis is widely used in data mining to classify data into categories on the basis of their similarity. Through the decades, many clustering techniques have been developed, including hierarchical and non-hierarchical algorithms. In gene profiling problems, because of the large number of genes and the complexity of biological networks, dimensionality reduction techniques are critical exploratory tools for clustering analysis of gene expression data. Recently, clustering analysis of applying dimensionality reduction techniques was also proposed. PCA (principal component analysis) is a popular methd of dimensionality reduction techniques for clustering problems. However, previous studies analyzed the performance of PCA for only full data sets. In this paper, to specifically and robustly evaluate the performance of PCA for clustering analysis, we exploit an improved FCBF (fast correlation-based filter) of feature selection methods for supervised clustering data sets, and employ two well-known clustering algorithms: k-means and k-medoids. Computational results from supervised data sets show that the performance of PCA is very poor for large-scale features.

• 한국환경과학회지
• /
• 제7권6호
• /
• pp.793-801
• /
• 1998

In this study, the Dilution Method is used to measure river discharge through the hydraulic model test. the dilution method is divided into Constant-Rate-Infection Method and Slug-Injection Method in the river discharge measurement techniques. When the dilution method is applied in the hydraulic model flume, it is analyzed that the estimated error of constant-rate-injection method is less than that of the slug-in-jection method, and the result shows that floodflow analysis is more efficient than lowflow analysis as compared observed discharge with calculated discharge. The result of statistical error analysis shows that the constant-rate-injection method is appropriate technique for the measurement of the river discharge. Therefore, the dilution method among the river discharge measurement techniques can be applied for the river basin which can't be measured with current meter or unsteady-flow regime in the urban-small drainage or hydraulic structure equipment area and can be obtained more exact results than any other discharge measurement techniques.

• Spatial Information Research
• /
• 제17권1호
• /
• pp.25-37
• /
• 2009

최근 인명과 재산을 보호할 수 있는 중요한 분야인 안전 운전 서비스를 위해 GIS 및 텔레매틱스 기술에 USN을 활용하는 연구가 증가하고 있다. 본 논문에서는 이러한 안전 운전 서비스를 위한 연구의 하나로, USN을 활용하여 굴곡 도로에서 발생할 수 있는 위험을 분석하고 사고를 예방하기 위한 기술을 제안한다. 위험 분석 기술은 크게 모델링과 알고리즘으로 구성된다. 모델링으로는 굴곡 도로, 도로 방향, 센서, 차량, 위험에 대한 모델을 제안하고, 알고리즘으로는 위험을 분석하고 경고할 수 있는 다중 레벨 위험 분석 알고리즘을 제안한다. 그리고, 제안한 모델링과 알고리즘에 대한 시뮬레이션 응용 프로그램을 구현한다.

• 한국유기농업학회지
• /
• 제20권4호
• /
• pp.519-533
• /
• 2012

In this study, of currently being implemented organic cultivation in rice, the economic effects of snail agriculture, natural circulation agriculture, stevia agriculture and art nature agriculture were compared and analyzed. Analysis results showed that the economic effects of selling price per 10a, gross margin and agricultural income were increased, compared to those of previous agricultural techniques. In addition, the comparison results of economic effects by agricultural techniques showed that the agricultural income per 10a of organic cultivation were increased from the national average, compared to that of conventional cultivation. These economic effects analysis by agricultural techniques can help in the decisionmaking of farmers for the adoption of agricultural techniques in the future.

• 한국국방경영분석학회지
• /
• 제22권1호
• /
• pp.67-80
• /
• 1996

Artificial Intelligence(AI) techniques and Object-Oriented(OO) techniques contribute to the simulation modeling of the complex systems. AI techniques are suitable to model human reasoning in the simulation. While OO techniques have advantages of re-usability, maintainability and extendability of the software. Thus, in this paper, we design a knowledge-based object-oriented simulation model, particularly for the logistics analysis of military armor vehicles. The simulation model consists of three modules i.e., scenario, simulation mechanism, and inference engine. The model is designed within the OO paradigm and implemented by using the C++ language. An example case of using the model for the logistic analysis is included.

• Asian-Australasian Journal of Animal Sciences
• /
• 제20권2호
• /
• pp.283-294
• /
• 2007

Conventional culture-based methods of enumerating rumen microorganisms (bacteria, archaea, protozoa, and fungi) are being rapidly replaced by nucleic acid-based techniques which can be used to characterise complex microbial communities without incubation. The foundation of these techniques is 16S/18S rDNA sequence analysis which has provided a phylogenetically based classification scheme for enumeration and identification of microbial community members. While these analyses are very informative for determining the composition of the microbial community and monitoring changes in population size, they can only infer function based on these observations. The next step in functional analysis of the ecosystem is to measure how specific and, or, predominant members of the ecosystem are operating and interacting with other groups. It is also apparent that techniques which optimise the analysis of complex microbial communities rather than the detection of single organisms will need to address the issues of high throughput analysis using many primers/probes in a single sample. Nearly all the molecular ecological techniques are dependant upon the efficient extraction of high quality DNA/RNA representing the diversity of ruminal microbial communities. Recent reviews and technical manuals written on the subject of molecular microbial ecology of animals provide a broad perspective of the variety of techniques available and their potential application in the field of animal science which is beyond the scope of this treatise. This paper will focus on nucleic acid based molecular methods which have recently been developed for studying major functional groups (cellulolytic bacteria, protozoa, fungi and methanogens) of microorganisms that are important in nutritional studies, as well as, novel methods for studying microbial diversity and function from a genomics perspective.