• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.3
• /
• pp.967-976
• /
• 2012

This study presents a model to minimize vibration and noise of powertrain mount on a compact car which has the application of Stop & Go performance, in order to reduce CO2 and achieve better fuel-efficiency in accordance with the environmental regulations in automotive industries. In the first step, we analyze the powertrain mount system of the automobile "A" and present variables about rubber stiffness applied on powertrain mount using the Taguchi method. In the next step, we verify the optimization of vibration and noise which meet Stop & Go performance using the AHP(Analytic Hierarchy Process) method on the proto products for each variable. Using this validation system on the initial stage of the powertrain mount design, it is expected that we can grasp vibration and noise problems caused by engine movements and control them effectively without engineering know-how about powertrain mount rubber stiffness.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.41 no.10
• /
• pp.1005-1009
• /
• 2017

In this study, the shock resistance of a gas turbine package subjected to a shock load caused by non-contact underwater explosion was investigated using numerical analysis. To perform shock analysis, the time-history shock load was calculated according to BV-043 (German Navy Regulation). The direct transient response analysis in the time domain for the simplified Whole Engine Model (WEM) was performed using the calculated shock load. In addition, the structural integrity of a detailed model was evaluated by considering the shock load transferred to each component. As a result, it was confirmed that the safety factor was at least 1.0 as compared with the reference stress. Finally, the structural and functional integrity of the Engine Management System (EMS) of the gas turbine package was verified through an actual shock test.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.10
• /
• pp.2241-2246
• /
• 2015

Recently for efficient management, companies have collected and investigated information about customers' feedback by using a system that analyzes big data from social media. This paper proposes more accurate and efficient evaluation method of collecting and investigating customers' feedback using social big data for travel agency, which is representative company of hospitality industry. First, it designs service model and, as a test-bed, analyzes media channel, customer satisfaction, and brand-image etc. of big 5 travel agencies in Korea. In addition, we suggest an analysis result of evaluating preference with positive rate and negative rate by proposed evaluation method. It allows a travel agency to know which area should be improved corresponding to evaluation item; thus, suggested evaluation method is effective to manage customers even more efficiently.

• Korean Journal of Construction Engineering and Management
• /
• v.11 no.3
• /
• pp.3-12
• /
• 2010

Recently, workers on construction sites can hardly understand their tasks and the process of the tasks because the construction projects are becoming large and complex. Due to the complexity, workers need a tool that can help them understand their works and some paper-based manuals exist to support them. However, the existing paperbased manuals are not actively used by workers due to the low credibility of information on the manual. In particular, paper-based manual can not be updated frequently because those manuals have to be manually updated by experts. Thus, the credibility of information is decreased and the decrease let the users distrust information of the paper-based manual. Therefore, this research analyzed the feature of wiki-based system and suggested an wiki-based IETM(Interactive Electronic Technical Manual) system model that can be modified by users, and then conducted a survey through a prototype based on urban regeneration project. The result of the survey indicated that wikibased IETM can improve the stakeholder communication by reinforcing the process of creating knowledge as well as knowledge itself.

• Smart Media Journal
• /
• v.9 no.3
• /
• pp.25-30
• /
• 2020

The purpose of this paper is to implement a deep learning-based real-time video analysis algorithm that monitors safety of workers in industrial facilities. The worker's clothes were divided into six classes according to whether workers are wearing a helmet, safety vest, and safety belt, and a total of 5,307 images were used as learning data. The experiment was performed by comparing the mAP when weight was applied according to the number of learning iterations for 645 images, using YOLO v4. It was confirmed that the mAP was the highest with 60.13% when the number of learning iterations was 6,000, and the AP with the most test sets was the highest. In the future, we plan to improve accuracy and speed by optimizing datasets and object detection model.

• Archives of design research
• /
• v.16 no.1
• /
• pp.15-24
• /
• 2003

In the latest date, vehicles are offered to the drivers, not only the skill for shifting but the pleasure for driving vehicles that are existing today can be a social problem because the amount of vehicles that are increasing give difficulty for the traffic facilities and parking expansion. these day 80% of four wheeled vehicle carriers single or double person the reducing car scale is an important thing about the financial good use resources of energy and the storage of environment. A solution for these problem is a new general idea vehicle development for one or two person to ride. For the sake of these reasons, first, the information is collected and analyzed about existing foreign countries production. Car external design is intended by mathematical modeling, simulation and model testing about frame system of new concept specially we would like to show three wheeled vehicle that has active tilt control(ATC) system. This car tilts actively by the center rotation wheel and frame when the vehicle turns.

• Journal of the Institute of Convergence Signal Processing
• /
• v.10 no.3
• /
• pp.170-175
• /
• 2009

In this paper, we propose real time automatic speaker verification (ASV) system to protect personal information on personal digital assistant (PDA) device. Recently, the capacity of PDA has extended and been popular, especially for mobile environment such as mobile commerce (M-commerce). However, there still exist lots of difficulties for practical application of ASV utility to PDA device because it requires too much computational complexity. To solve this problem, we apply the method to relieve the computational burden by performing the preprocessing such as spectral subtraction and speech detection during the speech utterance. Also by applying the hidden Markov model (HMM) optimal state alignment and the sequential probability ratio test (SPRT), we can get much faster processing results. The whole system implementation is simple and compact enough to fit well with PDA device's limited memory and low CPU speed.

• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.3
• /
• pp.60-68
• /
• 2007

In this paper, we propose an automatic facial expressions recognition system to analyze facial expressions (happiness, disgust, surprise and neutral) using tree structures based on heuristic rules. The facial region is first obtained using skin-color model and connected-component analysis (CCs). Thereafter the origins of user's eyes are localized using neural network (NN)-based texture classifier, then the facial features using some heuristics are localized. After detection of facial features, the facial expression recognition are performed using decision tree. To assess the validity of the proposed system, we tested the proposed system using 180 facial image in the MMI, JAFFE, VAK DB. The results show that our system have the accuracy of 93%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.4
• /
• pp.791-797
• /
• 2001

In this paper, high-speed ,large-capacity ATM switching-chip is developed by MCM technology. MCM technology is suited for light-weight portable communications, mobile computing, high-frequency applications. For test of the developed MCM switching-chips, the simulating model is made by VHDL code of previously developed chip and input-output values of modeling pattern are obtained through the simulation. After the pattern values in chip-test machine are inserted , their results are compared with the simulation results. The design in this paper is simulated by synopsys design tool using SUN workstation and functions of chip is measured by TRILLIUM machine. Simulated and measured results have been compared, showing close agreement. Last, the MCM technique presented in this paper will provide useful insight into future designs.

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1141-1147
• /
• 2020

The hornet species are so similar in shape that they are difficult for non-experts to classify, and because the size of the objects is small and move fast, it is more difficult to detect and classify the species in real time. In this paper, we developed a system that classifies hornets species in real time based on a deep learning algorithm using a boundary box. In order to minimize the background area included in the bounding box when labeling the training image, we propose a method of selecting only the head and body of the hornet. It also experimentally compares existing boundary box-based object recognition algorithms to find the best algorithms that can detect wasps in real time and classify their species. As a result of the experiment, when the mish function was applied as the activation function of the convolution layer and the hornet images were tested using the YOLOv4 model with the Spatial Attention Module (SAM) applied before the object detection block, the average precision was 97.89% and the average recall was 98.69%.