• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권11호
• /
• pp.2690-2701
• /
• 2013

Humans are able to recognize small number of people they know well by the way they walk. This ability represents basic motivation for using human gait as the means for biometric identification. Such biometric can be captured at public places from a distance without subject's collaboration, awareness or even consent. Although current approaches give encouraging results, we are still far from effective use in practical applications. In general, methods set various constraints to circumvent the influence factors like changes of view, walking speed, capture environment, clothing, footwear, object carrying, that have negative impact on recognition results. In this paper we investigate the influence of walking speed variation to different visual based gait recognition approaches and propose normalization based on geometric transformations, which mitigates its influence on recognition results. With the evaluation on MoBo gait dataset we demonstrate the benefits of using such normalization in combination with different types of gait recognition approaches.

• 대한산업공학회지
• /
• 제25권1호
• /
• pp.111-124
• /
• 1999

This evapaper is toluate the forecasting performance of three neural network(NN) approaches against ARIMA model using the famous time series analysis competition data. The first NN approach is to analyze the second Makridakis (M2) Competition Data using Multilayer Perceptron (MLP) that has been the most popular NN model in time series analysis. Since it is recently known that MLP suffers from bias/variance dilemma, two approaches are suggested in this study. The second approach adopts Cascade Correlation Network (CCN) that was suggested by Fahlman & Lebiere as an alternative to MLP. In the third approach, a time series is separated into two series using Noise Filtering Network (NFN) that utilizes autoassociative memory function of neural network. The forecasts in the decomposition analysis are the sum of two prediction values obtained from modeling each decomposed series, respectively. Among the three NN approaches, Decomposition Analysis shows the best forecasting performance on the M2 Competition Data, and is expected to be a promising tool in analyzing socio-economic time series data because it reduces the effect of noise or outliers that is an impediment to modeling the time series generating process.

• 산업공학
• /
• 제9권2호
• /
• pp.191-202
• /
• 1996

A variety of approaches on performance evaluation modeling have appeared in the technical literature for flexible manufacturing systems(FMS) which can be evaluated only through computer simulation. This study represents a comparative approach for FMS performance evaluation modeling based on reliability, availability and maintainability, and life cycle cost. The methodology proposed in this research includes the following three-step generative approaches. First, a static model to find the initial system configuration is considered under the assumption that the system availability is given as one (failure and maintenance are not considered), and in second step, a stochastic simulation is proposed to serve as a performance evaluation model for FMS with stochastic failure and repair time. In the last step, we developed a simulation modeling using a simulator, FACTOR/AIM to consider a variety of performance factors and dynamic behavior of FMS. Also the applicability and validity of the proposed approaches has been tested and compared through the results of a sample problem using computer programs and procedures developed in each step.

• 한국정보보호학회:학술대회논문집
• /
• 한국정보보호학회 2006년도 하계학술대회
• /
• pp.241-245
• /
• 2006

Recent studies show that fingerprint recognition technology is confronted with spoofing of artificial fingers. In order to overcome this problem, the fingerprint recognition system needs to distinguish a fake finger from a live finger. This paper examines existing software-based approaches for fingerprint liveness detection through experiments. Implemented and tested in this paper are the approaches based on deformation, wavelet, and perspiration. These approaches will be analyzed and compared based on experimental results.

• 품질경영학회지
• /
• 제22권1호
• /
• pp.33-53
• /
• 1994

Recently, from the viewpoint of TQM, the criticism and new approaches toward Japanese TQC have made much progress in Japan. It shows that these new approaches to quality are what are needed these days. In this connection, this paper aims at the study of a reform of Japanese TQC. This paper consists of the following two steps. First, several success factors of TQM in Japanese companies were selected through the study of literature. Second, actual approaches to or recognition of TQM in those companies were examined through the AHP analysis. The results of this paper are as follows: First, quality improvement and cost-down efforts within a factory have been emphasized. On the other hand, the development of strategic quality management is weak. Second, the development of creativity by individual autonomous teamwork is more needed than the development of creativity by group consciousness in companies. Third, the reform of upper-class management must be carried out by powerful leadership of top management.

• 한국항공운항학회지
• /
• 제22권2호
• /
• pp.53-59
• /
• 2014

Simultaneous parallel approaches in all weather conditions should be applied to manage efficiently increasing volume of air traffic flow and solve the problem of delayed arrivals. But All of the airports which have closely-spaced parallel-runways in Korea don't meet the interval-standards for IFR parallel approaches. In that regard, more accurate and safer System should be applied for the Korean airports. GNSS was adopted as an international standard of the next-generation navigation system and many studies and master plans have been activated by stages in Korea. In this paper, the current state of the domestic airports will be analyzed focusing on the interval of parallel runways and future specification of both flight operation system and air-side management will be recommended.

• 한국항공운항학회지
• /
• 제22권2호
• /
• pp.9-15
• /
• 2014

'Visual segment surface' means a surface that extends from the missed approach point of non precision approaches (or the decision altitude location for approaches with vertical guidance and precision approaches) to the threshold to facilitate the identification of and protection from obstacles in this visual segment of the approach. Validation is the necessary final quality assurance step in the procedure design process, prior to publication. The purpose of validation is the verification of all obstacle and navigation data, and assessment of flyability of the procedure. This paper shows how to apply the protection for the visual segment of the approach procedure, and the results of the validation for visual segment surface conducted at an airport.

• 한국시스템다이내믹스연구
• /
• 제16권1호
• /
• pp.75-91
• /
• 2015

The price-volume in land by land categories is evaluated with dynamic approaches in the era of aging society This research tries to investigate in the respect of major factors such as real estate, macro-economics, and population that is simulated by land categories. The system dynamics approaches on price-volume in land are forecasted until 2020 using the data in the period of 2000-2014. In regard to methodologies, this research adopted system dynamics to evaluate the relationships between price-volume in land and aging society. The meaningful results have been found during the last over 10 year's analysis as the dynamic relations with major factors. Regarding land categories, this research tries to overcome former research limitations. As an implication from the price-volume in land, it confirmed that the multifaceted aspects show that system dynamics approach effectively simulated them by price-volume in land with the population of aging society.

• Industrial Engineering and Management Systems
• /
• 제13권4호
• /
• pp.421-431
• /
• 2014

The market basket data in the form of a binary user-item matrix or a binary item-user matrix can be modelled as a binary classification problem. The binary logistic regression approach tackles the binary classification problem, where principal components are predictor variables. If users or items are sparse in the training data, the binary classification problem can be considered as a cold-start problem. The binary logistic regression approach may not function appropriately if the principal components are inefficient for the cold-start problem. Assuming that the market basket data can also be considered as a special regression problem whose response is either 0 or 1, we propose three supervised learning approaches: random forest regression, random forest classification, and elastic net to tackle the cold-start problem, comparing the performance in a variety of experimental settings. The experimental results show that the proposed supervised learning approaches outperform the conventional approaches.

• Structural Engineering and Mechanics
• /
• 제37권5호
• /
• pp.543-560
• /
• 2011

In structural engineering there are randomness inherently exist on determination of the loads, strength, geometry, and so on, and the manufacturing of the structural members, workmanship etc. Thus, objective and constraint functions of the optimization problem are functions that depend on those randomly natured components. The constraints being the function of the random variables are evaluated by using reliability index or performance measure approaches in the optimization process. In this study, the minimum weight of a space truss is obtained under the uncertainties on the load, material and cross-section areas with harmony search using reliability index and performance measure approaches. Consequently, optimization algorithm produces the same result when both the approaches converge. Performance measure approach, however, is more efficient compare to reliability index approach in terms of the convergence rate and iterations needed.