• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.6
• /
• pp.319-325
• /
• 2023

In this study, we proposed a method for hyperparameter optimization in the building and training of a deep learning model designed to process point cloud data collected by a millimeter-wave radar system. The primary aim of this study is to facilitate the deployment of a baseline model in resource-constrained IoT devices. We evaluated a RadHAR baseline deep learning model trained on a public dataset composed of point clouds representing five distinct human activities. Additionally, we introduced a coarse-to-fine hyperparameter optimization procedure, showing substantial potential to enhance model efficiency without compromising predictive performance. Experimental results show the feasibility of significantly reducing model size without adversely impacting performance. Specifically, the optimized model demonstrated a 3.3% improvement in classification accuracy despite a 16.8% reduction in number of parameters compared th the baseline model. In conclusion, this research offers valuable insights for the development of deep learning models for resource-constrained IoT devices, underscoring the potential of hyperparameter optimization and model size reduction strategies. This work contributes to enhancing the practicality and usability of deep learning models in real-world environments, where high levels of accuracy and efficiency in data processing and classification tasks are required.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.27 no.10
• /
• pp.941-944
• /
• 2016

This paper proposes 24 GHz power amplifier for automotive collision avoidance and surveillance short range radar using Samsung 65-nm CMOS process. The proposed circuit has a 2-stage differential power amplifier which includes common source structure and transformer for single to differential conversion, impedance matching, and power combining. The measurement results show 15.5 dB maximum voltage gain and 3.6 GHz 3 dB bandwidth. The measured maximum output power is 13.1 dBm, input $P1_{dB}$ is -4.72 dBm, output $P1_{dB}$ is 9.78 dBm, and maximum power efficiency is 17.7 %. The power amplifier consumes 74 mW DC power from 1.2 V supply voltage.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.2
• /
• pp.23-29
• /
• 2014

The advanced traffic management system of intelligent transport systems automates the related traffic tasks such as vehicle speed, traffic volume and traffic incidents through the improved infrastructures like high definition cameras, high-performance radar sensors. For the safety of road users, especially, the automated incident detection and secondary accident prevention system is required. Normally, CCTV based image object detection and radar based object detection is used in this system. In this paper, we proposed the algorithm for real time highway incident detection system using multi surveillance cameras to mosaic video and track accurately the moving object that taken from different angles by background modeling. We confirmed through experiments that the video detection can supplement the short-range shaded area and the long-range detection limit of radar. In addition, the video detection has better classification features in daytime detection excluding the bad weather condition.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.23 no.1
• /
• pp.47-55
• /
• 2012

This paper describes the developed HILS and test equipment in order to test the performances of MMW(Millimeter-Wave) seeker which can detect and track a high speed of short-range ballistic missile and aircraft. This system is used to 141 horn antenna array, array switching, and gain and phase control algorithm to simulate various kind of targets and trajectory of high speed and maneuver moving target. In addition, it simulates not only velocity and range for these targets but also clutter and jamming environments. System configuration and implementation and the measurement results of major subsystems such as target motion simulator, simulation signal generator, high speed data aquisition unit, and central control unit are presented. These systems could verify the detection and tracking performance of MMW seeker through dynamic real-time test based on simulation flight scenario.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.17 no.3
• /
• pp.350-357
• /
• 2014

MRDS is a short range missile/rocket defense system which protects a main battle tank(MBT) from threats at a short range. It is composed of 2 radars, 2 infrared trackers(IRT)s, 1 fire control computer(FCC), 2 launchers and countermeasures. In this paper, the radar and the IRT models based on sensing errors, the FCC model based on filtering errors, the launcher model based on driving errors and the countermeasure model based on flying errors are proposed to analyze the defense performance with the approaching RPG-7 and the moving MBT. The simulation results are presented to evaluate and verify the effectiveness of the proposed method.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.15 no.1
• /
• pp.1-8
• /
• 2012

Obstacle detection is much studied by using sensors such as laser, vision, radar and ultrasonic in path planning for UGV(Unmanned Ground Vehicle), but not much reported about its characterization. In this paper not only an obstacle classification method using 2-dimensional LMS(Laser Measurement System) but also a decision making method whether to avoid or traverse the obstacle is proposed. The basic idea of decision making is to classify the characteristics by 2D laser scanned data and intensity data. Roughness features are obtained by range data using a simple linear regression model. The standard deviations of roughness and intensity data are used as measures for decision making by comparing with those of reference data. The obstacle classification and decision making for the UGV can facilitate a short path to the target position and the survivability of the robot.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.10
• /
• pp.1386-1391
• /
• 2018

The radar in the moving platform is interfered by the mainlobe clutter as well as the altitude clutter that is received from sidelobe. The altitude clutter is relatively short range compared to mainlobe clutter and therefore enters the radar with a strong signal. As these clutters are major reason making the probability of false alarm high, it is required to suppress both altitude clutter and mainlobe clutter. In this paper, It is proposed the clutter suppression method consisted of two pulse canceller to suppress the clutters being two frequency area in moving platform. It is analyzed the correlation of output signals according to the use of pulse canceller and provided the structure of staggered pulse canceller considered the correlation. Finally, it shows that altitude clutter and mainlobe clutter are suppressed by proposed staggered pulse canceller using the simulation.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.2
• /
• pp.133-138
• /
• 2016

This paper describes the track initiation and target-tracking filter for ship tracking in a marine environment by using Light Detection And Ranging (LiDAR). LiDAR with three-dimensional scanning capability is more useful for target tracking in the short to medium range compared to RADAR. LiDAR has rotating multi-beams that return point clouds reflected from targets. Through preprocessing the cluster of the point cloud, the center point can be obtained from the cloud. Target tracking is carried out by using the center points of targets. The track of the target is initiated by investigating the normalized distance between the center points and connecting the points. The regular track obtained from the track initiation can be maintained by the target-tracking filter, which is commonly used in radar target tracking. The target-tracking filter is constructed to track a maneuvering target in a cluttered environment. The target-tracking algorithm including track initiation is experimentally evaluated in a sea-trial test with several boats.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.45 no.11
• /
• pp.61-68
• /
• 2008

In this paper, we propose a RF front-end developments for vehicle UWB radar systems. UWB systems have a very narrow pulse width that is below 1ns. Therefore, UWB is designed to have broadband quality of low power several GHz and must coexist with the radio communication system. UWB's advantages include high channel capacity and data rate, because precise resolution for multi-path can easily position estimate and Rake receiver. Also, UWB has low interference because it displays broadband quality of low power. Positioning is made possible by short range accuracy, which can reduce the expense of system design. An RF front-end module is designed using the DCR(Direct ConveRsion) method and is composed in RF for vehicles at a low-cost.

• Proceedings of the KSRS Conference
• /
• v.1
• /
• pp.520-523
• /
• 2006

Whereas it is well known that the surface roughness parameters, the RMS height and the correlation length, of a natural soil surface are underestimated with a short surface profile, it is not clear how much the underestimated surface parameters affect the backscattering coefficients of the surface for various incidence angles and polarizations. The backscattering coefficients of simulated and measured surface profiles are computed using the integral equation method (IEM) and analyzed in this paper to answer this question. It is shown that the RMS error of the backscattering coefficients between 5-m- and 1-m-long measured surface profiles is 1.7 dB for vv-polarization and 0.5 dB for hh-polarization at a medium range of incidence angle ($15^{\circ}{\leq}{\theta}{\leq}70^{\circ}$), while the surface roughness parameters are significantly reduced; from 2.4 cm to 1.5 cm for the RMS height s and from 35.1 cm to 10.0 cm for the autocorrelation length l. This result is verified with numerous simulations with various roughness conditions and various wavelengths.