• The Journal of Information Systems
• /
• v.30 no.2
• /
• pp.105-126
• /
• 2021

Purpose The purpose of this study is to implement a optimal machine learning model about the cancellation prediction performance in car sales business. It is to apply the data set of accumulated contract, cancellation, and sales information in sales support system(SFA) which is commonly used for sales, customers and inventory management by imported car dealers, to several machine learning models and predict performance of cancellation. Design/methodology/approach This study extracts 29,073 contracts, cancellations, and sales data from 2015 to 2020 accumulated in the sales support system(SFA) for imported car dealers and uses the analysis program Python Jupiter notebook in order to perform data pre-processing, verification, and modeling that is applying and learning to Machine learning model after then the final result was predicted using new data. Findings This study confirmed that cancellation prediction is possible by applying car purchase contract information to machine learning models. It proved the possibility of developing and utilizing a generalized predictive model by using data of imported car sales system with machine learning technology. It can reduce and prevent the sales failure as caring the potential lost customer intensively and it lead to increase sales revenue by predicting the cancellation possibility of individual customers.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.18 no.11
• /
• pp.1192-1198
• /
• 2008

In this paper, the vibration and shock of an HDD car-holder are reduced through vibration analysis and a structural modification. In order to identify the exciting frequency components of vibration and shock, vibration signals are measured and analyzed from the wind shield or dashboard. In addition, the modal test for the current HDD car-holder is performed to investigate the dynamic characteristics of the car-holder. From these experiments, it is found that the exciting frequencies coincide to the natural frequencies of the car-holder. For the purpose of avoiding resonance, some FEM simulations are carried out and then structural modifications are made for the car-holder. Based on the results of simulations, a prototype of new car-holder are manufactured and tested to demonstrate the reduction of vibration and shock. It is verified by the test that a considerable amount of vibration and shock are reduced.

• Knowledge Management Research
• /
• v.18 no.3
• /
• pp.1-35
• /
• 2017

This study conducted comparative study on autonomous car's industry policy and corporate strategy of US, China, Germany, Japan and Korea. By analyzing core technologies and industry paradigm shifts of autonomous car industry, I was able to figure out autonomous car has high potential to be dominant transportation in the future and it is important to construct core competency in technology area. The meaningful findings by analyzing various primary and secondary data are as followings: First, in case of US, Google was leading autonomous car industry by developing its own OS and Platform. US government has been actively supporting and interacting with private firms and Universities for stimulating industry/technology convergence and establishing standard. Second, in case of Germany, autonomous car development was leading by several auto makers such as Mercedes, BMW in Hardware and manufacturing area, and German government was focusing on deregulations for private company. Third, in case of Japan which quite similar with German situation, they were both independently developing technology and expanding alliances with MNCs. And Japanese government was supporting triple helix system construction between local companies and universities. Fourth, in case of China, autonomous car industry was leading by IT companies, and various cooperations between IT companies and automakers were established. Chinese government was regulating foreign companies and supporting domestic companies both in market and technologies Last, in Korean case, the active and extensive alliances were lacking in Korean companies while strategic and strong government supports were missing in public sector. For competing with other countries and players, more active collaboration between different countries and strong policy supports are needed in Korean auto industry.

• The Journal of the Korea Contents Association
• /
• v.13 no.7
• /
• pp.141-149
• /
• 2013

Recently, the time in which children moves by car become frequent, they stay longer in the car because leisure life including camping and etc. increased. Children whose physical activities are active were subject to restriction because of the limited car boarding visual space and on security. Because of limited space in cars, domestic and foreign automotive companies show the different glass roof applied in cars that exhibited wide clear view in order to remove tedious and stuffy of children while they stay for a long time inside the car. In addition, the potential probability in which the Smart Car that the IT technology is grafted research and research that it utilizes the door window glass as the display is progressed and which the glass roof can be used as the screen can be sufficient. In this study, the in-vehicle display application case and Smart Devices constellation application were benchmarked. The car glass roof application method of the constellation studying content which performed the user survey for the child by the car with the parents whose movement is frequent and considers the child and fundamental interaction way tried to be drawn and we try to propose.

• Science of Emotion and Sensibility
• /
• v.17 no.1
• /
• pp.29-38
• /
• 2014

In recent days, according as ergonomics and aesthetic engineering are important factors in the product market, there is a demand to develop automobile seat and interior designs which are focused on sensitive elements such as aesthetic and comfort features in order to satisfy the sensitive needs of consumers. To meet such demands, car seats are turning into functional and sensitive products that reflect elements of function and entertainment. According to such trends, this research is aimed to develop the illuminating car seat fabric that serve such functions as recognizing and reacting to car environments, which includes sensing over-speed, open doors, and unfastened safety belts through the illuminating car seat fabrics by optical fiber. For this purpose, basic physical properties of optical fiber are analyzed, appropriate weaving and etching technologies are applied, and the woven fabric of optical fiber for car seats are illuminating depend upon car environments. Moreover, the applicable woven fabric of optical fiber is deduced after evaluating the physical properties (such as tensile strength, heatproof, anti-fouling, washable and combustible traits) for the appropriateness of applying the woven fabric of optical fiber to car seats. For this purpose, the woven fabric of optical fiber is covered according to car seat processes; the optical fiber applied to seats is composed that it may be connected to one end of the connector linked to a LED so that it may perform functions like sensing over-speed, open doors, and unfastened safety belts; the sensed signals are transmitted to the control part, and luminescent signals are transmitted to LED.

• Journal of Information Technology Services
• /
• v.18 no.1
• /
• pp.201-217
• /
• 2019

Cars have become a necessity in modern life. It is widely used to transport people or products to a destination conveniently. However, the addition of a navigation service that provides route information and more makes driving more convenient and safer. Recent developments in the mobile app ecosystem encourages people to adopt not only an installation-type car navigation, but also a mobile app navigation, supporting connected car concepts. It should be noted that mobile apps with mobile Internet can be a significant linkage between information acquired online and offline business. This study demonstrates the impact of the app use experience for a driver in the context of applying artificial intelligence service. As a result, the introduction of artificial intelligence services has a statistically significant moderating effect on the use of mobile navigation apps. This seminal research is valuable as it evaluates the role of artificial intelligence applied to mobile navigation apps.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.9
• /
• pp.105-111
• /
• 2015

This paper suggests O(n) linear-time algorithm for car sequencing problem (CSP) that has been classified as NP-complete because of the polynomial-time algorithm to solve the solution has been unknown yet. This algorithm applies maximum options-equiped car type first production rule to decide the car sequencing of n meet the r:s constraint. This paper verifies thirteen experimental data with the six data are infeasible. For thirteen experimental data, the proposed algorithm can be get the solution for in all cases. And to conclude, This algorithm shows that the CSP is not NP-complete but the P-problem. Also, this algorithm proposes the solving method to the known infeasible cases. Therefore, the proposed algorithm will stand car industrial area in good stead when it comes to finding a car sequencing plan.

• Proceedings of the KSR Conference
• /
• 2008.11b
• /
• pp.1642-1645
• /
• 2008

It is said that the effect in wheels of freight car varies with the type of freight, the condition of operation, the braking device, and the type of bogie. The hardness of open wagon, gondola car, propylene car, covered freight car, container car and hopper car has been measured according to the mileage through this research. As a result, the wheel with more mileages after shaving off the wheel tread has a higher hardness than the others in the case of same type of car.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.8 no.5
• /
• pp.249-254
• /
• 2013

In this paper we propose nonlinear control system for automatic unmanned vehicle using a RC (Radio Controlled) car which is usually controlled by a remote controller. In the proposed system, a RC car is dissembled and reassembled with several parts enabling it to be controlled by an android mobile platform with Bluetooth communication. In our system, an android mobile smartphone is mounted on the RC car and plays an important role as an eye of the car. The proposed system automatically controls the RC car to follow a lane that we draw on the floor of our laboratory. Also, the proposed RC car system can also be controlled manually using the accelerometer sensor of a smartphone through a Bluetooth module. Our proposed system that has both manual mode and automatic mode consists of several components; a microprocessor unit, a Bluetooth serial interface module, a smartphone, a dual motor controller and a RC toy car. We are now in the development of a group driving system in which one car follows the front car that tracks a lane automatically.

• Journal of Service Research and Studies
• /
• v.13 no.3
• /
• pp.105-126
• /
• 2023

The domestic used car market continues to grow along with the used car online platform service. The used car online platform service discloses vehicle specifications, accident history, inspection history, and detailed options to service consumers. Most of the preceding studies were predictions of used car prices using vehicle specifications and some options for vehicles. As a result of the study, it was confirmed that there was a nonlinear relationship between used car prices and some specification variables. Accordingly, the researchers tried to solve the nonlinear problem by executing a Machine Learning model. In common, the Regression based Machine Learning model had the advantage of knowing the actual influence and direction of variables, but there was a disadvantage of low Cost Function figures compared to the Decision Tree based Machine Learning model. This study attempted to predict used car prices of six domestic brands by utilizing both vehicle specifications and vehicle options. Through this, we tried to collect the advantages of the two types of Machine Learning models. To this end, we sequentially conducted a regression based Machine Learning model and a decision tree based Machine Learning model. As a result of the analysis, the practical influence and direction of each brand variable, and the best tree based Machine Learning model were selected. The implications of this study are as follows. It will help buyers and sellers who use used car online platform services to predict approximate used car prices. And it is hoped that it will help solve the problem caused by information inequality among users of the used car online platform service.