• The Journal of Information Systems
• /
• v.29 no.2
• /
• pp.287-306
• /
• 2020

Purpose Youth unemployment is a social problem that continues to emerge in Korea. In this study, we create a model that predicts the employment of college graduates using decision tree, random forest and artificial neural network among machine learning techniques and compare the performance between each model through prediction results. Design/methodology/approach In this study, the data processing was performed, including the acquisition of the college graduates' vocational path survey data first, then the selection of independent variables and setting up dependent variables. We use R to create decision tree, random forest, and artificial neural network models and predicted whether college graduates were employed through each model. And at the end, the performance of each model was compared and evaluated. Findings The results showed that the random forest model had the highest performance, and the artificial neural network model had a narrow difference in performance than the decision tree model. In the decision-making tree model, key nodes were selected as to whether they receive economic support from their families, major affiliates, the route of obtaining information for jobs at universities, the importance of working income when choosing jobs and the location of graduation universities. Identifying the importance of variables in the random forest model, whether they receive economic support from their families as important variables, majors, the route to obtaining job information, the degree of irritating feelings for a month, and the location of the graduating university were selected.

• Magazine of the Korea Concrete Institute
• /
• v.8 no.6
• /
• pp.235-243
• /
• 1996

The mechanical behavior ot concrete is strongly influenced by various scenarios of crack initiation and crack propagation. Recently. the study of the interface fracture and cracking in interfacial regions is emerged as an important field, in the context of the developement of high performance concrete composites. The crack path criterion for elastically homogeneous materials is not valid when the crack advances at an interface because. in this case, the consideration of the relative magnitudes of the fracture toughnesses between the constituent materials and the interface are involved. In this paper, a numerical method is presented to obtain the values of two interfacial fracture parameters such as the energy release rate and the phase angle at the tip of an existing interface crack. Criteria based on energy release rate concepts are suggested for the prediction of crack growth at the interfaces and an hybrid experimental-numerical study is presented on the two-phase beam composite models containing interface cracks to investigate the cracking scenarios in interfacial regions. In general, good agreement between the experimental results and the prediction from the criteria is obtained.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.11
• /
• pp.1011-1022
• /
• 2014

Currently, the wireless network environment of air node is constructed mainly of ground relay station. However, as the Korean Peninsula is composed of 70% mountainous region, there are multiple shadow zones. This is calling for effective measures to prevent aircraft from losing communication link during low-mid altitude missions. In this article we propose the utilization of Bezier Curve for estimation of aircraft flight path and control method for entering shadow zone. This method successfully estimated aircraft track, and analyzed the existence, disseminated the warning, and took measures to avoid the shadow zone before entering. This article, suggested after simulated experiments, proves that the method enables seamless communication during air operations.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.9 no.5
• /
• pp.131-138
• /
• 2009

In this paper, a dynamic warning system to forecast inland flooding associated with typhoons and storms is described. The system is used operationally during the typhoon season to anticipate the potential impact such as inland flooding on the coastal zone of interest. The system has been developed for the use of the public and emergency management officials. Simple typhoon models for quick prediction of wind fields are implemented in a user-friendly way by using a Graphical User Interface (GUI) of MATLAB. The main program for simulating tides, depth-averaged tidal currents, wind-driven surges and currents was also vectorized for the fast performance by MATLAB. By pushing buttons and clicking the typhoon paths, the user is able to obtain real-time water level fluctuation of specific points and the flooding zone. This system would guide local officials to make systematic use of threat information possible. However, the model results are sensitive to typhoon path, and it is yet difficult to provide accurate information to local emergency managers.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.14 no.1
• /
• pp.3-22
• /
• 2012

Control independence has been put forward as a significant new source of instruction-level parallelism for superscalar processors. In branch prediction mechanisms, all instructions after a mispredicted branch have to be squashed and then instructions of a correct path have to be re-fetched and re-executed. This paper presents a new branch misprediction recovery mechanism to reduce the number of instructions squashed on a misprediction. Detection of control independent instructions is accomplished with the help of the static method using a profiling and the dynamic method using a control flow of program sequences. We show that the suggested branch misprediction recovery mechanism improves the performance by 2~7% on a 4-issue processor, by 4~15% on an 8-issue processor and by 8~28% on a 16-issue processor.

• Journal of the Korean Geosynthetics Society
• /
• v.23 no.1
• /
• pp.17-25
• /
• 2024

The Voids in the Mineral Aggregate (VMA) within asphalt mixtures play a crucial role in defining the mixture's structural integrity, durability, and resistance to environmental factors. Accurate prediction and optimization of VMA are essential for enhancing the performance and longevity of asphalt pavements, particularly in varying climatic and environmental conditions. This study introduces a novel machine learning framework leveraging ensemble machine learning model for predicting VMA in asphalt mixtures. By analyzing a comprehensive set of variables, including aggregate size distribution, binder content, and compaction levels, our framework offers a more precise prediction of VMA than traditional single-model approaches. The use of advanced machine learning techniques not only surpasses the accuracy of conventional empirical methods but also significantly reduces the reliance on extensive laboratory testing. Our findings highlight the effectiveness of a data-driven approach in the field of asphalt mixture design, showcasing a path toward more efficient and sustainable pavement engineering practices. This research contributes to the advancement of predictive modeling in construction materials, offering valuable insights for the design and optimization of asphalt mixtures with optimal void characteristics.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.11
• /
• pp.256-264
• /
• 2020

Industrial Wireless Sensor Networks (IWSNs) is exploited to achieve various objectives such as improving productivity and reducing cost in the diversity of industrial application, and it has requirements such as low-delay and high reliability packet transmission. To accomplish the requirement, the network manager performs graph construction and resource allocation about network topology, and determines the transmission cycle and path of each node in advance. However, this network management scheme cannot treat mobile devices that cause continuous topology changes because graph reconstruction and resource reallocation should be performed as network topology changes. That is, despite the growing need of mobile devices in many industries, existing scheme cannot adequately respond to path failure caused by movement of mobile device and packet loss in the process of path recovery. To solve this problem, a network management scheme is required to prevent packet loss caused by mobile devices. Thus, we analyse the location and movement cycle of mobile devices over time using machine learning for predicting the mobility pattern. In the proposed scheme, the network manager could prevent the problems caused by mobile devices through performing graph construction and resource allocation for the predicted network topology based on the movement pattern. Performance evaluation results show a prediction rate of about 86% compared with actual movement pattern, and a higher packet delivery ratio and a lower resource share compared to existing scheme.

• ETRI Journal
• /
• v.34 no.6
• /
• pp.911-921
• /
• 2012

In high-speed wireless communications, an analysis of the propagation characteristics is an important process. Information on the propagation characteristics suitable for each environment significantly helps in the design of mobile communications. This paper presents the analysis results of radio propagation characteristics in outdoor environments for a new mobile wireless system at 781 MHz. To avoid the interference of Korean DTV broadcasting, we measure the channel characteristics in urban, suburban, and rural areas on Jeju Island, Republic of Korea, using a channel sounder and $4{\times}4$ antenna. The path loss (PL) measurement results differ from those of existing propagation models by more than 10 dB. To analyze the frequency characteristics for Korean propagation environments, we derive various propagation characteristic parameters: PL, delay spread, angular spread, and K-factor. Finally, we verify the validity of the measurement results by comparing them with the actual measurement results and 3D ray-tracing simulation results.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.22 no.8
• /
• pp.720-728
• /
• 2012

It is important for identification of noise and vibration problem of tire to consider influence of interaction between road and tire. A quantification of road noise is a challenging issue in vehicle NVH due to extremely complicated transfer paths of road noise as well as the difficulty in an experimental identification of input force from tire-road interaction. A noise caused by tire is divided into road noise(structure-borne noise) and pattern noise(air-borne noise). Pattern noise is caused by pattern shape of tire, which has larger than 500 Hz, but road noise is generated by the interactions between a tire and a vehicle body. In this paper, we define the quantitative analysis for road noise caused by interactions between tire and road parameters. For the identification of road noise, the chassis dynamometer that is equipped $10mm{\times}10mm $ square cleat in the semi-anechoic chamber is used, and the tire spindle forces are measured by load cell. The vibro-acoustic transfer function between ear position and wheel center was measured by the vibro-acoustic reciprocity method. In this study three tires with different type of mechanical are used for the experiment work.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.23 no.4
• /
• pp.315-323
• /
• 2013

Tire noise is divided into a road noise(structure-borne noise) and a pattern noise(air-borne noise). Whilst the road noise is caused by the structural vibration of the components on the transfer path from tire to car body, the pattern noise is generated by the air-pumping between tire and road. In this paper, a practical method to estimate the pattern noise inside a passenger car is proposed. The method is developed based on the sound intensity and airborne source quantification. Sound intensity is used for identifying the noise sources of tire. Airborne source quantification is used for estimating the sound pressure level generated by each noise source of a tire. In order to apply the airborne source quantification to the estimation of the sound pressure, the volume velocity of each source should be obtained. It is obtained by using metrics inverse method. The proposed method is successfully applied to the evaluation of the interior noises generated by four types of tires with different pattern each other.