• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.16 no.3
• /
• pp.115-127
• /
• 2006

The purpose of this paper is evaluation of various normalization methods and fusion algorithms in addition to pattern classification algorithms for multi-biometric systems. Experiments are performed using various normalization functions, fusion algorithms and pattern classification algorithms based on Biometric Scores Set-Releasel(BSSR1) provided by NIST. The performance results are presented by Half Total Error Rate (WTER). This study gives base data for the study on performance enhancement of multiple-biometric system by showing performance results using single database and metrics.

• Journal of Wetlands Research
• /
• v.25 no.1
• /
• pp.64-73
• /
• 2023

Before 2022, there was a lot of confusion in the process of planning and implementing the projects for ecological restoration of the stream due to dualization the principal agent of stream management. Because the Ministry of Environment took charge of the project in 2022, securing the health of aquatic ecosystem of stream became an essential factor in the project. Therefore, in this study, the streams that require the project for ecological restoration was selected in Han River estuary, where it is essential to secure the health of the stream aquatic ecosystem as blackish water zone and Ramsar wetland are located. Physical, chemical, spatial/humanistic, health of aquatic ecosystems evaluation indexes were calculated based on the detailed facts and figures of the project for ecological restoration of the stream in the beginning. Ranking, re-scaling, z-score, and t-score normalization methods were applied to the calculated evaluation index, and the values were compared and analyzed. After that, the entropy weight method was applied to each evaluation index. Through this process, the streams(Mokgamcheon, Anyangcheon etc.) that require the project for ecological restoration were selected for the purpose of securing the health of the aquatic ecosystem in Han River estuary. The result of this study can be used as basic research data in the process of selecting the priority determination of the projects for ecological restoration of the stream.

• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.5
• /
• pp.163-172
• /
• 2007

ESC has been used as a tool for evaluating overall performance of firms. ESC focuses mainly on building a balanced viewpoint comprising perspectives and their metrics. It is, therefore, difficult to value overall strategic achievements of a company derived by consolidating various perspectives and metrics. Because of the absence of a method for consolidating ESC metrics and computing total score based on these metrics, it is difficult to evaluate whole strategic performance and find core obstacle parts of performance. In this paper, we suggest a method of normalizing a numerical value of metrics with different units, and calculating the total score of ESC metrics. We conduct a case study of evaluating the effectiveness of CRM to illustrate the applicability and feasibility of the suggested method.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.3E
• /
• pp.19-23
• /
• 1997

The goal of postprocessing in automatic speech recognition is to improve recognition performance by utterance verification at the output of recognition stage. It is focused on the effective rejection of out-of vocabulary words based on the confidence score of hypothesized candidate word. We present two methods for computing confidence scores. Both methods are based on the distance between each observation vector and the representative code vector, which is defined by the most likely code vector at each state. While the first method employs simple time normalization, the second one uses a normalization technique based on the concept of on-line garbage mode[1]. According to the speaker independent isolated words recognition experiment with discrete density HMM, the second method outperforms both the first one and conventional likelihood ratio scoring method[2].

• Journal of the Korea Convergence Society
• /
• v.10 no.10
• /
• pp.7-13
• /
• 2019

The natural gas (NG), mostly methane leaks into the air, it is a big problem for the climate. detected NG leaks under U.S. city streets and collected data. In this paper, we introduced a Deep Neural Network (DNN) classification of prediction for a level of NS leak. The proposed method is OrdinalEncoder(OE) based K-means clustering and Multilayer Perceptron(MLP) for predicting NG leak. The 15 features are the input neurons and the using backpropagation. In this paper, we propose the OE method for labeling target data using k-means clustering and compared normalization methods performance for NG leak prediction. There five normalization methods used. We have shown that our proposed OE based MLP method is accuracy 97.7%, F1-score 96.4%, which is relatively higher than the other methods. The system has implemented SPSS and Python, including its performance, is tested on real open data.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.14 no.4
• /
• pp.332-339
• /
• 2014

Face classification has wide applications in security and surveillance. However, this technique presents various challenges caused by pose, illumination, and expression changes. Face recognition with long-distance images involves additional challenges, owing to focusing problems and motion blurring. Multiple frames under varying spatial or temporal settings can acquire additional information, which can be used to achieve improved classification performance. This study investigates the effectiveness of multi-frame decision-level fusion with photon-counting linear discriminant analysis. Multiple frames generate multiple scores for each class. The fusion process comprises three stages: score normalization, score validation, and score combination. Candidate scores are selected during the score validation process, after the scores are normalized. The score validation process removes bad scores that can degrade the final output. The selected candidate scores are combined using one of the following fusion rules: maximum, averaging, and majority voting. Degraded facial images are employed to demonstrate the robustness of multi-frame decision-level fusion in harsh environments. Out-of-focus and motion blurring point-spread functions are applied to the test images, to simulate long-distance acquisition. Experimental results with three facial data sets indicate the efficiency of the proposed decision-level fusion scheme.

• Korean Journal of Construction Engineering and Management
• /
• v.16 no.4
• /
• pp.98-106
• /
• 2015

VE aims at reduction in a budget, improvement of function, structural safety and quality security for public construction projects. However, there is possibility for the structural safety and quality security review to be insufficient because related regulations are mostly composed of analysis on economic efficiency of design. In addition, due to the misconception about VE as a cost saving methodology, an alternative is being presented which still focuses mainly on cost saving, but with no objective evaluation of function related to cost. In order to improve this, the government adopted the reduction of life cycle cost and proposal of value improvement, and let people specify the cost and function of the original plan versus the alternative plan, and the value changes between them. However, it is written mainly into practical convenience rather than theoretical basis since a specific way is not suggested. The current method sets a different starting point by applying the attributional difference of function and cost. Furthermore, an evaluation standard for correlating is an important element in rational decision making for assessing and choosing an alternative. This paper analyzes the process and method of function & cost scoring when performing VE and suggests a mathematical normalization model in order to support rational decision making when selecting an optimum plan.

• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.1
• /
• pp.8-14
• /
• 2002

In this paper, we realized a real-time text-independent speaker recognition system using gaussian mixture model, and applied frame level likelihood normalization method which shows its effects in verification system. The system has three parts as front-end, training, recognition. In front-end part, cepstral mean normalization and silence removal method were applied to consider speaker's speaking variations. In training, gaussian mixture model was used for speaker's acoustic feature modeling, and maximum likelihood estimation was used for GMM parameter optimization. In recognition, likelihood score was calculated with speaker models and test data at frame level. As test sentences, we used text-independent sentences. ETRI 445 and KLE 452 database were used for training and test, and cepstrum coefficient and regressive coefficient were used as feature parameters. The experiment results show that the frame-level likelihood method's recognition result is higher than conventional method's, independently the number of registered speakers.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.663-667
• /
• 1999

In this paper, we review the conventional speaker verification algorithm and present the text-dependent speaker verification system for application over telephone lines and its result of experiments. We apply blind-segmentation algorithm which segments speech into sub-word unit without linguistic information to the speaker verification system for training speaker model effectively with limited enrollment data. And the World-mode] that is created from PBW DB for score normalization is used. The experiments are presented in implemented system using database, which were constructed to simulate field test, and are shown 3.3% EER.

• Journal of Wetlands Research
• /
• v.13 no.3
• /
• pp.411-426
• /
• 2011

The construction of composite indicators should be normalized and weighted to render them comparable and evaluable variables in the field, which undergoes absence of a distinct methodology and where the application of universally popular method is common. Constructing of indices does not compare and analyze applying various normalizing and weighting, but constructer generally use chosen method and develops indicators and indices in most research. In this study, indices are applied various normalization and weighting methods, thereby analyzing how much impact the index and identifying individual characteristics derive a more reasonable way to help other research in the future. 5 different methods of normalization and 4 different types of weights were compared and analyzed. There are different results depending applied normalized methods and Z-score method best reflects the characteristics of the variables. According to weighting methods, the calculated results show little difference, but the ranking results of indices did not changed significantly. It might be better to provide constructors with a set of normalization and weighting methods to reflect their characteristics in order to build flood indices through the result of this study.