• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2000.04a
• /
• pp.213-217
• /
• 2000

The progressive die are multiple operations performed by means of a die having above two stages, on the each of stages performs a different operation as the sheet metal passes through the die hole. In the field of design and making tool for press working, the progressive die for sheet metal (STS 304, thickness : 0.5mm) is a specific division. in order to prevent the defects, the optimum design of the production part, strip layout, die design, die making and tryout etc. are necessary. They require analysis of many kinds of important factors, i.e. theory and practice of metal press working and its phenomena, die structure, machining condition for die making, die materials, heat treatment of die components, know-how and so on. In this study, we designed and constructed a progressive die of multi-stage and performed try out. Out of these processes the die development could be taken for advance. Especially the result of tryout and its analysis become the characteristics of this paper (part 1 and part 2) that nothing might be ever seen before such as this type of research method on all the processes. In the part 1 of this study we treated die design mostly.

• Journal of Korean Society of Transportation
• /
• v.24 no.2 s.88
• /
• pp.147-156
• /
• 2006

Metropolitan Subway, tke volume of station, distance between station is short. when the demand is concentrated during moving peak periods, the Headway that than Line Headway in which Station Headway is applied to Station Capacity computation be. The factors to determine the Station Headway have a fixing Price of the machine and the Dwell time. Other factors aye decided already or fixing price but the Dwell time that change according to demand cause the biggest effect at Station Headway. After analyze constituents that influence to Station Headway in this study calculated correct Station Capacity drawing estimating dwell time model that change according to demand.

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.931-941
• /
• 2020

As natural language processing technology using machine learning develops, a Smart Home Network Service (SHNS) is drawing attention again. However, it is difficult to apply a standardized authentication scheme for SHNS because of the diversity of components and the variability of users. Blockchain is proposed for data authentication in a distributed environment. But there is a limit to applying it to SHNS due to the computational overhead required when implementing a proof-of-work system. In this paper, a lightweight work proof system is proposed. The proposed lightweight proof-of-work system is proposed to manage block generation by controlling the work authority of the device. In addition, this paper proposes an access control scheme for SHNS.

• Journal of the Microelectronics and Packaging Society
• /
• v.29 no.3
• /
• pp.1-12
• /
• 2022

With the rapid development of artificial intelligence technology that gives existing sensors functions similar to human intelligence is drawing attention. Previously, researches were mainly focused on an improvement of fundamental performance indicators as sensors. However, recently, attempts to combine artificial intelligence such as classification and prediction with sensors have been explored. Based on this, intelligent sensor research has been actively reported in almost all kinds of sensing fields such as disease detection, motion detection, and gas sensor. In this paper, we introduce the basic concepts, types, and driving mechanisms of artificial intelligence and review some examples of its use.

• Structural Engineering and Mechanics
• /
• v.86 no.6
• /
• pp.765-778
• /
• 2023

This study investigates the free vibration and buckling analyses of isotropic curved plate structures fixed at all ends. The Kirchhoff-Love Plate Theory (KLPT) and Finite Element Method (FEM) are employed to model the curved structure. In order to perform the finite element analysis, a four-node quadrilateral element with 5 degrees of freedom (DOF) at each node is utilized. Additionally, the drilling effect (θ_z) is considered as minimal to satisfy the DOF of the structure. Lagrange's equation of motion is used in order to obtain the first ten natural frequencies and the critical buckling values of the structure. The effects of various radii of curvatures and aspect ratio on the natural frequency and critical buckling load values for the single-bay and two-bay curved frames are investigated within this scope. A computer code based on finite element analysis is developed to perform free vibration and buckling analysis of curved plate frames. The natural frequency and critical buckling load values of the present study are compared with ANSYS R18.2 results. It has been concluded that the results of the present study are in good agreement with ANSYS results for different radii of curvatures and aspect ratio values of both single-bay and two-bay structures.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.939-951
• /
• 2022

The most important factor in designing autonomous driving systems is to recognize the exact location of the vehicle within the surrounding environment. To date, various sensors and navigation systems have been used for autonomous driving systems; however, all have limitations. Therefore, the need for high-definition (HD) maps that provide high-precision infrastructure information for safe and convenient autonomous driving is increasing. HD maps are drawn using three-dimensional point cloud data acquired through a mobile mapping system (MMS). However, this process requires manual work due to the large numbers of points and drawing layers, increasing the cost and effort associated with HD mapping. The objective of this study was to improve the efficiency of HD mapping by segmenting semantic information in an MMS point cloud into six classes: roads, curbs, sidewalks, medians, lanes, and other elements. Segmentation was performed using various machine learning techniques including random forest (RF), support vector machine (SVM), k-nearest neighbor (KNN), and gradient-boosting machine (GBM), and 11 variables including geometry, color, intensity, and other road design features. MMS point cloud data for a 130-m section of a five-lane road near Minam Station in Busan, were used to evaluate the segmentation models; the average F1 scores of the models were 95.43% for RF, 92.1% for SVM, 91.05% for GBM, and 82.63% for KNN. The RF model showed the best segmentation performance, with F1 scores of 99.3%, 95.5%, 94.5%, 93.5%, and 90.1% for roads, sidewalks, curbs, medians, and lanes, respectively. The variable importance results of the RF model showed high mean decrease accuracy and mean decrease gini for XY dist. and Z dist. variables related to road design, respectively. Thus, variables related to road design contributed significantly to the segmentation of semantic information. The results of this study demonstrate the applicability of segmentation of MMS point cloud data based on machine learning, and will help to reduce the cost and effort associated with HD mapping.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.581-586
• /
• 2023

Recently a drama that features a lawyer with autism spectrum disorder has attracted a lot of attention, raising interest in the difficulties faced by people with autism spectrum disorders. If the Autism spectrum gets detected early and proper education and treatment, the prognosis can be improved, so the development of the treatment is urgently needed. Drugs currently used to treat autism spectrum often have side effects, so Digital Therapeutics that have no side effects and can be supplied in large quantities are drawing attention. In this paper, we introduce 'AEmotion', an application and a Digital Therapeutic that provides emotion and facial expression learning for toddlers with an autism spectrum disorder. This system is developed as an application for smartphones to increase interest in training autistic children and to test easily. Using machine learning, this system consists of three main stages: an 'emotion learning' step to learn emotions with facial expression cards, an 'emotion identification' step to check if the user understood emotions and facial expressions properly, and an 'expression training' step to make appropriate facial expressions. Through this system, it is expected that it will help autistic toddlers who have difficulties with social interactions by having problems recognizing facial expressions and emotions.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.21 no.1
• /
• pp.19-34
• /
• 1997

The goals of this study are to suggest the guidance for automated clothing manufacture by analysis the technology of the automated manufacturing facilities and to propose how improve the efficiency of the production planning and management for automated clothing manufacture In this study, the research about the automated clothing manufacturing machines and the analysis about the modules and functions of apparel information systems were performed. In order to understand the factory automation of the larger clothing firms, the case study method was used. The case study samples were 3 clothing firms. The results and suggestions are as follows: 1. An information technology for automated clothing manufacture has enabled the computer integrated manufacturing system to connect production planning and management part with each work station on the factory floor. 2. The apparel information system to integrate and manage manufacturing informations from each workstation and the apparel CAD system are used in the department of production planning. At the cutting room, there are automated manufacturing machines like an automatic spreading system and an automatic cutting system. Sewing room has the computer controlled unit production system and semi-automated sewing machines. In addition, in the finishing room, an automatic packing machine and a press system are used and besides a warehousing system has been developed. Considering these available technology, for better product efficiency, it is necessary to consider and utilize the specific character of these automatic manufacturing machines and computer system whether they proper to each product style. 3. Most of the clothing manufacturers are in the stage of semi-automated manufacture. In order to improve the manufacturing environment, it is needed to gradual procedure of manufacturing automation with considering the firm's financial condition, existing facilities and staffs operating machines. The case study sample firms are in the high degree of manufacturing automation. They can accomplish the flexible manufacturing system to link the information system with each work station menufacturing system by computerized control. For the case of the firm having already used the computer integrated manufacturing and managing system, it is necessary that the function to deal with drawing information is added to the retaining module of the apparel system.

• Polymer(Korea)
• /
• v.34 no.6
• /
• pp.579-587
• /
• 2010

To investigate the properties of PET films, PET films were extruded at various temperature above $T_m$ and quenched at $18^{\circ}C$ for amorphous sheet, and stretched along a direction defined as the machine direction (MD) with a transverse direction (TD) above $T_g$ at various stretching ratios and then annealed at various temperatures produced by SKC PET line. Thermal shrinkage of MD and TD increased with decreasing annealing temperature and extruding temperature, and increasing stretching ratio. The degree of crystallinity, density, heat of fusion (${\Delta}H$) and pre-melting point ($T_m'$) increased with increasing annealing temperature and extruding temperature. Number average molecular weight ($M_n$) and intrinsic viscosity decreased with increasing extruding temperature. Tensile strength and modulus increased with increasing stretching ratio, however decreased with increasing annealing temperature. Reflective index of both stretching and thickness direction increased with increasing stretching ratio and annealing temperature.

• Journal of KIISE
• /
• v.44 no.1
• /
• pp.51-56
• /
• 2017

The research area for solving question answering (QA) problems using artificial intelligence models is in a methodological transition period, and one such architecture, the dynamic memory network (DMN), is drawing attention for two key attributes: its attention mechanism defined by neural network operations and its modular architecture imitating cognition processes during QA of human. In this paper, we increased accuracy of the inferred answers, by adapting an automatic data augmentation method for lacking amount of training data, and by improving the ability of time perception. The experimental results showed that in the 1K-bAbI tasks, the modified DMN achieves 89.21% accuracy and passes twelve tasks which is 13.58% higher with passing four more tasks, as compared with one implementation of DMN. Additionally, DMN's word embedding vectors form strong clusters after training. Moreover, the number of episodic passes and that of supporting facts shows direct correlation, which affects the performance significantly.