• Journal of the Korean Society of Costume
• /
• v.54 no.3
• /
• pp.99-112
• /
• 2004

The purpose of this research is to examine the relation between the cyber environment and the contemporary fashion design by studying the formative feature characteristics of cyber character's fashion in the on-line game from the point of the contemporary fashion design. The research method is to understand the general concept of the cyber-space and characters and then is to contemplate characteristics and formative features of game character's fashion of the cyber-space mainly with cyber characters that were closely linked with features of the contemporary fashion design. As a result, the formative feature of game character's fashion of the cyber-space was to be classified into four categories; reactionism, mechanism, futurism, sensualism. First, reactionism takes traditional elements with symbolical and compromising form. Second, mechanism has a tendency of deconstruction due to its vitality and sense of velocity for objects through employing geometrical forms and new materials. Third, futurism deviates from the established framework. It makes use of high-tech materials and has surrealistic and futuristic features. Fourth, sensualism does emphasize sensual parts of the body and intends to convey aesthetic atmosphere through association of ideas. Character's fashion of the cyber on-line game is unnatural and artificial in its forms and wear for the lack of knowledge for costume's structure, and it shows just simplified design that accept extremely partial fragment of features in the contemporary fashion design.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.8
• /
• pp.105-113
• /
• 1996

In this paper, a new korean digita speech recognition technique was proposed using muktolayer perceptron (MLP). In spite of its weakness in dynamic signal recognition, MLP was adapted for this model, cecause korean syllable could give static features. It is so simle in its structure and fast in its computing that MLP was used to the suggested system. MLP's input vectors was transformed using karhunen-loeve transformation (KLT), which compress signal successfully without losin gits separateness, but its physical properties is changed. Because the suggested technique could extract static features while it is not affected from the changes of syllable lengths, it is effectively useful for korean numeric recognition system. Without decreasing classification rates, we can save the time and memory size for computation using KLT. The proposed feature extraction technique extracts same size of features form the tow same parts, front and end of a syllable. This technique makes frames, where features are extracted, using unique size of windows. It could be applied for continuous speech recognition that was not easy for the normal neural network recognition system.

• Journal of Computing Science and Engineering
• /
• v.9 no.4
• /
• pp.204-213
• /
• 2015

Under the conditional independence assumption among local features, the Naive Bayes Nearest Neighbor (NBNN) classifier has been recently proposed and performs classification without any training or quantization phases. While the original NBNN shows high classification accuracy without adopting an explicit training phase, the conditional independence among local features is against the compositionality of objects indicating that different, but related parts of an object appear together. As a result, the assumption of the conditional independence weakens the accuracy of classification techniques based on NBNN. In this work, we look into this issue, and propose a novel Bayesian network for an NBNN based classification to consider the conditional dependence among features. To achieve our goal, we extract a high-level feature and its corresponding, multiple low-level features for each image patch. We then represent them based on a simple, two-level layered Bayesian network, and design its classification function considering our Bayesian network. To achieve low memory requirement and fast query-time performance, we further optimize our representation and classification function, named relation-based Bayesian network, by considering and representing the relationship between a high-level feature and its low-level features into a compact relation vector, whose dimensionality is the same as the number of low-level features, e.g., four elements in our tests. We have demonstrated the benefits of our method over the original NBNN and its recent improvement, and local NBNN in two different benchmarks. Our method shows improved accuracy, up to 27% against the tested methods. This high accuracy is mainly due to consideration of the conditional dependences between high-level and its corresponding low-level features.

• Journal of Advanced Navigation Technology
• /
• v.28 no.2
• /
• pp.163-171
• /
• 2024

In the existing air traffic management (ATM) system, various types of safety alert features are provided based on trajectory data to ensure the safety of aircraft operations, along with aircraft position and detailed flight information. The urban air traffic management (UATM) system for urban air mobility (UAM) should also provide safety alert features to ensure the safety of UAM operations. Considering the operational environment of UAM, it is necessary that the safety alert features provided at least match or exceed those available in the existing ATM system. This study aims to present the safety alert features of the new UATM system that differ from those provided by the existing ATM system before introduction and commercialization of UAM. The study was conducted focusing on the safety alert features that should be provided in the event of a deviation from the UAM's path, and the establishment of the safety alert features was carried out in two parts: approach path monitor (APM), which is applied during the approach phase, and route adherence monitoring (RAM), which is applied during the cruise phase.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.3
• /
• pp.209-218
• /
• 2013

Early researches in human action recognition have focused on tracking and classifying articulated body motions. Such methods required accurate segmentation of body parts, which is a sticky task, particularly under realistic imaging conditions. Recent trends of work have become popular towards the use of more and low-level appearance features such as spatio-temporal interest points. Given the great progress in pose estimation over the past few years, redefined views about pose-based approach are needed. This paper addresses the issues of whether it is sufficient to train a classifier only on low-level appearance features in appearance approach and proposes effective pose-based approach with pose estimation for emotional action recognition. In order for these questions to be solved, we compare the performance of pose-based, appearance-based and its combination-based features respectively with respect to scenario of various emotional action recognition. The experiment results show that pose-based features outperform low-level appearance-based approach of features, even when heavily spoiled by noise, suggesting that pose-based approach with pose estimation is beneficial for the emotional action recognition.

• The KIPS Transactions:PartA
• /
• v.12A no.1 s.91
• /
• pp.13-22
• /
• 2005

Similarly to the edges defined in a 2D image, we can define the geometric features representing the boundary of the distinctive parts appearing on 3D meshes. The geometric features have been used as basic primitives in several applications such as mesh simplification, mesh deformation, and mesh editing. In this paper, we propose geometric livewire and geometric livelane for extracting geometric features in a 3D mesh, which are the extentions of livewire and livelane methods in images. In these methods, approximate curvatures are adopted to represent the geometric features in a 3D mesh and the 3D mesh itself is represented as a weighted directed graph in which cost functions are defined for the weights of edges. Using a well-known shortest path finding algorithm in the weighted directed graph, we extracted geometric features in the 3D mesh among points selected by a user. In this paper, we also visualize the results obtained from applying the techniques to extracting geometric features in the general meshes modeled after human faces, cows, shoes, and single teeth.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2004.10a
• /
• pp.329-332
• /
• 2004

Cast-forging process has a lot of advantages in terms of saving materials along with enhancement of mechanical properties. Therefore, this process has been taken as one of candidate process to manufacturing automotive suspension parts. Since most of cast-forging parts are made with using Al-Si alloys of high castability, the mechanical properties largely depends on the primary ${\alpha}$ and eutectic Si particles. During hot forging step these microstructural features evolve with strain increment. In the present study, the mechanical property evolution was investigated in terms of microstructual evolution with strain. Specially, fracture behavior of A356 alloy was studied to find out how to improve the mechanical properties.

• Proceedings of the KSR Conference
• /
• 2004.10a
• /
• pp.1278-1284
• /
• 2004

Platform screen dorr (PSD) is equipment composed of screens and doors on the platform of subways or light trains, separating the platform from the railroad. The equipment is opened and closed in connection to the doors of carriages. In order to operate the system safely, it is important to understand the characteristics of key parts. There are many parts and environmental factors such as voltage, current and temperature change but the present study measured the change rate of torque and energy changes according to the temperature of the driving motor and analyzed the characteristics of the changes and examined the features of a motor required for stable PDS and the conformability of control programs.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.12 no.4
• /
• pp.1-8
• /
• 2003

It is well known that design cost is only about 5% of final product cost but over 70% of it is determined during design stage. Earlier in the product design and development cycle the design changes occur, more economic they become. Therefore, it is recommended that the manufacturing time and cost of product are considered in steps involved in designing and manufacturing a product as early as possible. In this study, it is proposed a possible way that cm be available for estimating manufacturing time of parts, which are manufactured by conventional material removal processes (e.g. turning, milling and drilling). For it to be useful in the early design stage, the minimum number of informations on dimension shape, and design features of part will be used in this method.

• Journal of the Korean Society for Precision Engineering
• /
• v.24 no.1 s.190
• /
• pp.47-56
• /
• 2007

Recently, demands on mechanical micro machining technology have been increased in manufacturing of micro-scale precision shapes and parts. The main purpose of this research is to verify the accuracy and cost efficiency of the mechanical micro machining. In order to measure the precision and feasibility of mechanical micro machining, various micro features were machined. Aluminum molds were machined by a 3-axis micro stage in order to fabricate microchips with $200{\mu}m$ wide channel for capillary electrophoresis, then the same geometry of microchip was made by injection molding. To evaluate the cost efficiency of various micro manufacturing processes, cost estimation for mechanical micro machining was conducted, and actual costs of microchips fabricated by mechanical micro machining, injection molding, and MEMS (Micro electro mechanical system) were compared.