• Journal of IKEEE
• /
• v.27 no.3
• /
• pp.350-354
• /
• 2023

This paper describes ISO/IEC TR 24029-1, an international standard to evaluate the performance of artificial intelligence systems. ISO/IEC TR 24029-1 defines the performance measures of artificial intelligence systems in two categories, i.e. interpolation and classificiation. Performance measures in the interpolation categories mean how much the predicted values of the artificial intelligence system is close to the real values. Performance measures in the classification categories mean how much the predicted classes of the artificial intelligence system is equal to the real classes. Based on these performance measures, performance of artificial intelligence systems can be evaluated and performance of different artificial intelligence systems can be compared.

• Proceedings of the ESK Conference
• /
• 1997.10a
• /
• pp.376-380
• /
• 1997

This paper describes usability evaluation techniques for the human interface of consumer electronic products. The techniques include measures for evaluating the user performance and emotion/impression on the product. Evaluation method for collecting the measures were also surveyed and summarized. Finally, this paper describes a systematic way of finding appropriate methods for collecting a specific measures.

• Journal of Korean Society of Forest Science
• /
• v.95 no.5
• /
• pp.569-579
• /
• 2006

This study focuses on the application of multi-criteria performance measures based on the concept of equifinality to the calibration of the rainfall-runoff model TOPMODEL in a small deciduous forest catchment. The performance of each parameter set was evaluated by six performance measures, individually, and each set was identified as a behavioral or non-behavioral parameter set by a given behavioral acceptance threshold. Many behavioral parameter sets were scattered throughout the parameter space, and the range of model behavior and the sensitivity for each parameter varied considerably between the different performance measures. Sensitivity was very high in some parameters, and varied depending on the kind of performance measure as well. Compatibilities of behavioral parameter sets between different performance measures also varied, and very few parameter sets were selected to be used in making god predictions for all performance measures. Since different behavioral parameter sets with different likelihood weights were obtained for each performance measure, the decision on which performance measure to be used may be very important to achieve the goal of study. Therefore, one or more suitable performance measures should be selected depending on the environment and the goal of a study, and this may lead to decrease model uncertainty.

• Korean Journal of Environmental Agriculture
• /
• v.24 no.3
• /
• pp.303-313
• /
• 2005

Agricultural environmental indicators (AEIs) are useful tool for evaluating environmental performance induced by agri-environmental policy measures. General and specific criteria have been set to assess the linkages between policy measures and environmental states. In addition, a number of specific AEIs such as nutrient balance indicators and farm management indicators have been posit to review environmental performance associated with agri-environmental policy measures. The proposed environmental subjects encompass soil quality, qualities of underground and surface water, water resource preservation, species and genetic diversity, diversity for wildlife habitats, and agricultural landscapes. The developed AEIs may contribute to establishment or adjustment of environmental targets and ex-ante or ex-post evaluation for environmental performance associated with policy measures. In addition, the AEIs may be useful to consider introduction of new agri-environmental measures and enhance policy efficiency by assessing environmental performance, considering specific locality, and harmonizing support measures.

• Sleep Medicine and Psychophysiology
• /
• v.10 no.1
• /
• pp.12-19
• /
• 2003

Sleepiness, or hypersomnia, is a relatively common complaint and one of the main problems of modern society. Accurate evaluation and diagnosis of sleepiness are important. The methods used for evaluating sleepiness are subjective measures or self-evaluations, performance decrease measures, sleep propensity measures, and arousal decrease measures. A clear and detailed history is important in differential diagnosis of sleepiness because symptoms of sleepiness may be expressed in terms of 'tiredness' or 'fatigue' that do not directly denote sleepiness. Comprehensive diagnostic evaluation is also invaluable because these symptoms may result from a variety of causes ranging from medical disorders to insufficient nocturnal sleep.

• Journal of Technology Innovation
• /
• v.13 no.1
• /
• pp.265-293
• /
• 2005

This research examines the relationship between the characteristics of Government S&T Research Institutes (GRI) and their institutional performance evaluation system. First, based on Kaplan & Norton (1992) Balanced Scorecard Model, six perspectives suitable to Korean GRI are derived. Second, personnel who works on evaluation job classified current performance measures into the six perspectives. Analyzing comparative weights of individual perspectives, the characteristics of performance evaluation systems among institutes are derived and compared with their missions. The results are as follows: First, GRI evaluation systems put most weight on the customer perspective and least weight on the financial perspective. This result complies with Korean GRI's missions and strategies as well as findings of foreign cases. Second, Basic-technology GRI group relatively more priotizes long-term customer perspective, while Applied-technology GRI Group relatively more priotizes short-term customer perspective. Public-technology GRI Group is located in the middle in terms of priority of customer perspectives. Third, for three yews (2000-2002), performance measure weights of Basic-technology Group are changed much less than those of the other two groups. Further research are needed for reasons of drastic changes for Applied-technology and Public-technology groups and some abnormally high and low measure weights.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.16 no.4
• /
• pp.431-439
• /
• 2018

Less mature nuclear reactor technologies are characterized by a greater uncertainty due to insufficient detailed design information, operational data, cost information, etc., but the expected performance characteristics of less mature options are usually more attractive in comparison with more mature ones. The greater uncertainty is, the higher economic risks associated with the project realization will be. Within a comparative evaluation of less and more mature nuclear reactor technologies, it is necessary to apply economic risk measures to balance judgments regarding the economic performance of less and more mature options. Assessments of any risk metrics involve calculating different characteristics of probability distributions of associated economic performance indicators and applying the Monte-Carlo method. This paper considers the applicability of statistical risk measures for different economic performance indicators within a trial case study on a comparative evaluation of less and more mature unspecified LWRs. The presented case study demonstrates the main trends associated with the incorporation of economic risk metrics into a comparative evaluation of less and more mature nuclear reactor technologies.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.1
• /
• pp.9-16
• /
• 2016

In this paper, we present a performance evaluation agent based on fuzzy cluster analysis and validity measures. The proposed agent is consists of three modules, fuzzy cluster analyzer, performance evaluation measures, and feature ranking algorithm for feature selection step in CAD system. Feature selection is an important step commonly used to create more accurate system to help human experts. Through this agent, we get the feature ranking on the dataset of mass and calcification lesions extracted from the public real world mammogram database DDSM. Also we design a CAD system incorporating the agent and apply five different feature combinations to the system. Experimental results proposed approach has higher classification accuracy and shows the feasibility as a diagnosis supporting tool.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.52 no.2
• /
• pp.85-92
• /
• 2003

In this paper, we propose a method to evaluate performances of mobile personal robots. A set of performance measures is proposed and the corresponding evaluation methods are developed. Different from industrial manipulators, personal robots need to be evaluated with its mobility, navigation, task and intelligent performance in environments where human beings exist. The proposed performance measures are composed of measures for mobility including vibration, repeatability, path accuracy and so on, as well as measures for navigation performance including wall following, overcoming doorsill, obstacle avoidance and localization. But task and intelligent behavior performances such as cleaning capability and high-level decision-making are not considered in this paper. To measure the proposed performances through a series of tests, we designed a test environment and developed measurement systems including a 3D Laser tracking system, a vision monitoring system and a vibration measurement system. We measured the proposed performances with a mobile robot to show the result as an example. The developed systems, which are installed at Korea Agency for Technology and Standards, are going to be used for many robot companies in Korea.

• Journal of the Ergonomics Society of Korea
• /
• v.20 no.3
• /
• pp.47-60
• /
• 2001

The purpose of this paper is propose an analytical method for evaluating user satisfaction of Internet website and identifying casual relationships between user satisfaction of Internet website and performance measures as like revisit intention and complaints using the structural equation model (SEM). This paper is intended to identify critical evaluation factors of user satisfaction for Internet website to determine criteria for evaluating the website. and use the criteria to develop a SEM model for quantitatively evaluation of each factors effects of user preference. The SEM model used 5 latent variables for the evaluation factors of website user satisfaction and 2 latent variables for performance evaluation. 2 portal sites were evaluated to construct the SEM model. and 74 subjects participated the website evaluation using the walk-through and face-to face survey method. Analysis results showed that the SEM model was statistically significant for all the 2 websites evaluated.