• Journal of Mechanical Science and Technology
• /
• v.14 no.6
• /
• pp.655-665
• /
• 2000

We propose an efficient algorithm for the purpose of satisfying a wide range of design constraints represented with equality and inequality equations as well as production rules. The algorithm employs simulated-annealing and a production rule inference engine and works on design constraints represented with networks. The algorithm fulfills equality constraints through constraint satisfaction processes like variable elimination while taking into account inequality constraints and inferring production rules. It can also reduce the load of the optimization procedure if necessary. We demonstrate the implementation of the algorithm with the result on machine tool design.

• Journal of Multimedia Information System
• /
• v.7 no.3
• /
• pp.205-214
• /
• 2020

Crime has become one of the major problems in modern society. Even though visual surveillances through closed-circuit television (CCTV) is extensively used for solving crime, the number of crimes has not decreased. This is because there is insufficient workforce for performing 24-hour surveillance. In addition, CCTV surveillance by humans is not efficient for detecting dangerous situations owing to accuracy issues. In this paper, we propose the autonomous detection of dangerous situations in CCTV scenes using a deep learning model with relational inference. The main feature of the proposed method is that it can simultaneously perform object detection and relational inference to determine the danger of the situations captured by CCTV. This enables us to efficiently classify dangerous situations by inferring the relationship between detected objects (i.e., distance and position). Experimental results demonstrate that the proposed method outperforms existing methods in terms of the accuracy of image classification and the false alarm rate even when object detection accuracy is low.

• The Bulletin of The Korean Astronomical Society
• /
• v.41 no.2
• /
• pp.58.3-58.3
• /
• 2016

The Kepler space mission provides quantitative and qualitative photometric time series of oscillating stars. It is possible to examine statistical study with seismic properties of solar-like stars. Global seismic properties - large frequency separation (${\Delta}{\nu}$), frequency of maximum power (${\nu}_{max}$) and amplitude of Gaussian envelope (A) widely have been used to determine empirical scaling relations for inferring the stellar physical quantities - mass, age and temperature. We aim to confirm whether width of Gaussian envelope on power excess (${\delta}{\nu}_{env}$) can be used with parameter of scaling relation before redgiant phase using Kepler data. Therefore we analyze the characteristics of ${\delta}{\nu}_{env}$ of 129 solar-like stars from main-sequence to subgiant. We have demonstrated that ${\delta}{\nu}_{env}$ has highly correlations with global parameters - ${\Delta}{\nu}$ and ${\nu}max$. We have also found the break of ${\delta}{\nu}_{env}-{\Delta}{\nu}$ and ${\nu}_{max}$ relations.

• Journal of Ocean Engineering and Technology
• /
• v.12 no.3 s.29
• /
• pp.96-102
• /
• 1998

This paper presents to create a SAC(Sectional Area Curve) using an ANFIS(Adaptive-Network-based Fuzzy Inference System). First, it defines SACs of parent ships by using a B-spline approximation and a genetic algorithm and accumulates a database about SAC's control points. Second, it learns an ANFIS from parent ship data, which are related with principal dimensions and SAC's control points. This process is to model an ANFIS for SAC inferreice. When an ANFIS modeling is completed, we can determine a SAC through an ANFIS inferring.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.10a
• /
• pp.115-120
• /
• 1997

System identification is the task of inferring a mathematical description of a dynamic system from a series of measurements of the system. There are several motives for establishing mathematical descriptions of dynamic systems. Typical applications encompass simulation, prediction, fault diagnostics, and control system design. The paper demonstrates that neural networks can be used effective for the identification of nonlinear dynamical systems. The content of this paper concerns dynamic neural network models, where not all inputs to and outputs from the networks are measurable. Only one model type is treated, the well-known Innovation State Space model(Kalman Predictor). The identification is based only on input/output measurements, so in fact a non-linear Extended Kalman Filter problem is solved. Even for linear models this is a non-linear problem without any assurance of convergence, and in spite of this fact an attempt is made to apply the principles from linear models, an extend them to non-linear models. Computer simulation results reveal that the identification scheme suggested are practically feasible.

• Journal of The Korean Association For Science Education
• /
• v.15 no.4
• /
• pp.452-458
• /
• 1995

Science textbooks are very important materials in order to know elementary science learning in Japan and Korea. In this research the 5th grade science textbooks in Japan and Korea are analyzed by an analyzing category. The analyzing category is consisted of knowledge and scientific inquiry. Knowledge is divided by fact, concept, and rule. Scientific inquiry is divided by problem cognition, variable control, experiment planning, observing, measuring, categorizing, inferring, data transformation, predicting, correlation, cause and effect, result, communication, which are 13 subcategories. Analyzing methods are counting the frequency of each subcategory and tabulating the data. The results of this study are: 1. The frequency of scientific inquiry appeared in Korean 5th grade science textbooks is three times more than that in Japanese textbooks. 2. In scientific inquiry category, Japanese science textbooks emphasized observing, predicting, measuring and problem cognition; Korean science textbooks emphasized experiment planning, observing and problem cognition. 3. In knowledge category, fact subcategory is mostly emphasized in both countries.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.9
• /
• pp.84-101
• /
• 1997

Inferring and recognizing 3D objects form a 2D occuluded image has been an important research area of computer vision. The octree model, a hierarchical volume description of 3D objects, may be utilized to generate projected images from arbitrary viewing directions, thereby providing an efficient means of the data base for 3D object recognition. We present a fast algorithm of finding the 4 pairs of feature points to estimate the viewing direction. The method is based on matching the object contour to the reference occuluded shapes of 49 viewing directions. The initially best matched viewing direction is calibrated by searching for the 4 pairs of feature points between the input image and the image projected along the estimated viewing direction. Then the input shape is recognized by matching to the projectd shape. The computational complexity of the proposed method is shown to be O(n$^{2}$) in the worst case, and that of the simple combinatorial method is O(m$^{4}$.n$^{4}$) where m and n denote the number of feature points of the 3D model object and the 2D object respectively.

• Journal of Korea Game Society
• /
• v.11 no.3
• /
• pp.21-30
• /
• 2011

The form of web-based MMORTS game has changed the way users recognize games. This paper focuses fact that users' semiosis in MMORTS game shows different aspects from MMORPG game and to analyze it through theory of Charles Sanders Peirce. Users in MMORTS make a semiotic process in a wide range of ways including keeping avatars at a distance, reading index mark, and inferring through symbol marks. It leads to call a user in web-based MMORTS an administrator, symbol interpreter, and strategist.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.6
• /
• pp.954-962
• /
• 1990

Experties of recognizing an object despite of every possible occlusions among objects is difficult to be provided directly to a system. In this paper, we propose a method for inferring inherent shape-characteirstics of an object from training views provided. The method learns rules incrementally by alternating the rule induction process from limited number of training views and the rule verification process from the following taining views. The learned rules are represented using logical expressions to enhance the readability. Thr proposed method is tested by simulating occlusions on 2-dimensional objects to examine the learning process and to show improvement of recognition rate. Thr result shows that it can be applied to a practical system for 3-dimensional object recognition.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2003.11a
• /
• pp.370-378
• /
• 2003

Continuous seismic refraction, reflection and echo-sounder surveys conducted at Koyna Project site provided geotechnical information which helped in choosing the alignment for Head race tunnel and in designing and choosing the site for Lake Tap. Seismic refraction survey both on land and in shallow water determined depths to bedrock and helped in inferring the bedrock quality. Seismic reflection survey mapped the subsurface stratigraphy with high resolution. Reservoir-bed and bedrock contours drawn from the results of the survey helped in choosing the tunnel alignment and the lake tap position cost effectively. It was inferred from the results of the survey that the geology and the quality of rock do not change unexpectedly around the site for extension of Head race tunnel and the lake tapping. The bedrock levels evaluated by seismic survey agreed remarkably well with those inferred in boreholes having Rock Quality Designation 90 percent or more.