• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3330-3344
• /
• 2023

This paper proposes an antenna performance prediction model in the autonomous driving radar manufacturing process. Our research work is based upon a challenge dataset, Driving Radar Manufacturing Process Dataset, and a typical AutoML machine learning workflow engine, Pycaret open-source Python library. Note that the dataset contains the total 70 data-items, out of which 54 used as input features and 16 used as output features, and the dataset is properly built into resolving the multi-output regression problem. During the data regression analysis and preprocessing phase, we identified several input features having similar correlations and so detached some of those input features, which may become a serious cause of the multicollinearity problem that affect the overall model performance. In the training phase, we train each of output-feature regression models by using the AutoML approach. Next, we selected the top 5 models showing the higher performances in the AutoML result reports and applied the ensemble method so as for the selected models' performances to be improved. In performing the experimental performance evaluation of the regression prediction model, we particularly used two metrics, MAE and RMSE, and the results of which were 0.6928 and 1.2065, respectively. Additionally, we carried out a series of experiments to verify the proposed model's performance by comparing with other existing models' performances. In conclusion, we enhance accuracy for safer autonomous vehicles, reduces manufacturing costs through AutoML-Pycaret and machine learning ensembled model, and prevents the production of faulty radar systems, conserving resources. Ultimately, the proposed model holds significant promise not only for antenna performance but also for improving manufacturing quality and advancing radar systems in autonomous vehicles.

• Journal of Power Electronics
• /
• v.18 no.4
• /
• pp.975-984
• /
• 2018

This work presents a high efficiency phase shifted full bridge (PSFB) DC-DC converter for use in the second stage of a battery charger for neighborhood electrical vehicle (EV) applications. In the design of the converter, Lithium-ion battery cells are preferred due to their high voltage and current rates, which provide a high power density. This requires wide range output voltage regulation for PSFB converter operation. In addition, the battery charger works with a light load when the battery charge voltage reaches its maximum value. The soft switching of the PSFB converter depends on the dead time optimization and load condition. As a result, the converter has to work with soft switching at a wide range output voltage and under light conditions to reach high efficiency. The operation principles of the PSFB converter for the continuous current mode (CCM) and the discontinuous current mode (DCM) are defined. The performance of the PSFB converter is analyzed in detail based on wide range output voltage and load conditions in terms of high efficiency. In order to validate performance analysis, a prototype is built with 42-54 V / 15 A output values at a 200 kHz switching frequency. The measured maximum efficiency values are obtained as 94.4% and 76.6% at full and at 2% load conditions, respectively.

• Proceedings of the KIEE Conference
• /
• 2006.10c
• /
• pp.391-393
• /
• 2006

In this paper, we develop a portable game device with uncompressed HD video and high quality sound output. Portable game devices support not only game function but also various complex functions recently. It especially supports TV-Out port to play realistic game, connecting a large screen display device. But the video and audio output signals of conventional TV-out port have the low performance and these signals are analog output. So, it is difficult that the users enjoy realistic game with benefit of high resolution digital TV. We propose the game device output with uncompressed digital signal, which has no delay of video/audio signal, also has strong immunity to external noise. Since it supports a high resolution video and high quality sound, users can playa realistic game. First, we implement the HDMI to the game device and we test reliability with the various resolutions video inputs and audio inputs. The proposed method can be applied multimedia devices requiring high performance output function as well as portable devices.

• Proceedings of the KIEE Conference
• /
• 2004.04a
• /
• pp.133-135
• /
• 2004

As a result of the recent advances in magnetic materials, the Magnetic Amplifier(Magamp) technique is one of the reliable and cost-effective postregulation method for multiple-output power supply. This is true for high-current postregulated output since at highter output current the efficiency of linear postregulation is unacceptably low, while the complexity of more efficient switch mode postregulator is associated with a significant cost. Magamp have some advantages of higher power density, simple control circuit, good regulation, high frequency and high performance. In this paper, Operation principle of proposed approach and a performance of magamp control circuit with TL431 is described. The comparative analysis of magamp circuit and buck regulator circuit with 20W load condition is conducted. Experimental verifications on multi-output flyback converter are conducted. Simulations and experimental results show that the proposed approach is efficiency and voltage regulation of the auxiliary output is excellent.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.9C
• /
• pp.734-742
• /
• 2008

In spatially multiplexed MIMO systems that enable high data rate transmission over wireless communication channels, the spatial demultiplexing at the receiver is a challenging task and various demultiplexing methods have been developed. Among the previous methods, maximum likelihood detection with QR decomposition and M-algorithm (QRM-MLD), sphere decoding (SD), QOC, and MOC schemes have been reported to achieve a (near) maximum likelihood (ML) hard decision performance. In general, however, the reliability of soft output of these schemes is not satisfactory. In this paper, we propose a method which enhances the reliability of soft output. By computer simulations, we demonstrate the improved performance by the proposed method.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.28 no.6
• /
• pp.248-255
• /
• 2016

In this study, the degree of performance changes between the guaranteed performance and the performance after a certain operating start time is calculated by using the performance test of gas turbine CHP. The reason of the performance degradation will then be analysed. For some results of the CHP plant performance tests the comprehensive electric power output was 8,380 kW lower than the guaranteed performance, and the gas turbine's output was reduced to about 250 kW whenever ambient temperatures rose to $1^{\circ}C$. Also, causes of the performance degradation of gas turbines are ambient temperature rise, temperature aging and air compressor's efficiency drop.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.12
• /
• pp.403-410
• /
• 2020

In addition to the research on noise removal and super-resolution using the data restoration (Output result) function of Autoencoder, research on the performance improvement of clustering using the dimension reduction function of autoencoder are actively being conducted. The clustering function and data restoration function using Autoencoder have common points that both improve performance through the same learning. Based on these characteristics, this study conducted an experiment to see if the autoencoder model designed to have excellent data recovery performance is superior in clustering performance. Skip connection technique was used to design autoencoder with excellent data recovery performance. The output result performance and clustering performance of both autoencoder model with Skip connection and model without Skip connection were shown as graph and visual extract. The output result performance was increased, but the clustering performance was decreased. This result indicates that the neural network models such as autoencoders are not sure that each layer has learned the characteristics of the data well if the output result is good. Lastly, the performance degradation of clustering was compensated by using both latent code and skip connection. This study is a prior study to solve the Hanja Unicode problem by clustering.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.8
• /
• pp.1537-1546
• /
• 2011

The photovoltaic(PV) generation system have recently become widely used to solve the environmental problems and running out of fossil fuels. However, the study on maintenance is inadequate for PV system. This paper proposes the novel diagnosis method of output power decline to maintain the normal output performance of PV array. The diagnosis method used the proportional relation of irradiation-output current(S-I) of PV array at maximum power point(MPP). And, first order polynomial using the relation is proposed to easily apply PV system. To estimate the relation in case of separation of PV array producer and diagnosis system producer. Kalman Filter algorithm is also proposed at 30.2kW grid-connected PV system. Then, the performance of diagnosis method is evaluated using the hardware tests as well as the simulation.

• Proceedings of the KIEE Conference
• /
• 2000.11d
• /
• pp.694-696
• /
• 2000

In this paper, the Direct Learning Control is applied to robot's trajectory tracking control to solve the problem that lies in the existing Iterative Learning Control(ILC) and the tracking Performance is analyzed and the better approach is searched using computer simulation and experiments. It is assumed that the Direct Learning Control(DLC) is saved onto memory basically after obtaining control input Profiles for several Periodic output trajectories using the ILC. In case the new output trajectory has special relations with the previous output trajectories, there is an advantage that the desired control input profile can be obtained without iterative executions only using the DLC. The robot's tracking control system is comprised of DSP chip. A/D converter, D/A converter and high-speed pulse counter included in the control board and the performance is examined by carrying out the tracking control for the given output trajectory.

• Journal of Institute of Control, Robotics and Systems
• /
• v.3 no.5
• /
• pp.443-449
• /
• 1997

LQ-servo design procedure introduced by Athans is a method using a partial states feedback and an output feedback in order to improve the poor performance robustness of the LQR as well as to maintain its stability robustness. Although the method guarantees good stability robustness, it is not effective in performance robustness as it does not match the singular value at low or high frequencies of the transfer matrix obtained by breaking at the plant output. This paper intends propose of a new method, using the limited behaviour of the control gain introduced by Kwakernaak and Sivan, in order to improve it does it refer to controlga introduced by kwakernaak or the new metho Anblguouls.