• Journal of Broadcast Engineering
• /
• v.23 no.6
• /
• pp.855-865
• /
• 2018

Sound event detection is one of the research areas to model human auditory cognitive characteristics by recognizing events in an environment with multiple acoustic events and determining the onset and offset time for each event. DCASE, a research group on acoustic scene classification and sound event detection, is proceeding challenges to encourage participation of researchers and to activate sound event detection research. However, the size of the dataset provided by the DCASE Challenge is relatively small compared to ImageNet, which is a representative dataset for visual object recognition, and there are not many open sources for the acoustic dataset. In this study, the sound events that can occur in indoor and outdoor are collected on a larger scale and annotated for dataset construction. Furthermore, to improve the performance of the sound event detection task, we developed a dual CNN structured sound event detection system by adding a supplementary neural network to a convolutional neural network to determine the presence of sound events. Finally, we conducted a comparative experiment with both baseline systems of the DCASE 2016 and 2017.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.1031-1033
• /
• 2013

Radiation protection, as well as finding the location of the radiation source, such as the Fukushima radiation leak accident, it is important for the early and safe disposal of nuclear accident. The three-dimensional position of the radiation source detection distance of the radiation source can provide additional information to the existing radiation detectors radiation of a two-dimensional position detection function and then it can play a decisive role in the radiation contaminant removal and decontamination work. In this research, three-dimensional semiconductor sensor based on dual radiation detectors radiation source device visible part of the research and development of efficient radiation sensor unit on the design of the shielding structure.The lightweight, high-efficiency radiation source locator implementation was attempted for the structure and thickness of the shielding and collimator to perform the simulation of the radiation shielding for the various parameters of the shape model through design the optimal structure of the MCNP-based heavy-duty tungsten shielding, lead shielding The results of this study, is a compact, lightweight three-dimensional radiation source detection and future of silicon - based sensors will be used in the study.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.2
• /
• pp.193-199
• /
• 2008

In this paper, it is proposed the implementation of face authentication system based on real-time image processing. We described the process implementing the two steps for real-time face authentication system. At first face detection steps, we describe the face detection by using feature of wavelet transform, LoG operator and hausdorff distance matching. In the second step we describe the new dual-line principal component analysis(PCA) for real-time face recognition. It is combines horizontal line to vertical line so as to accept local changes of PCA. The proposed system is affected a little by the video size and resolution. And then simulation results confirm the effectiveness of out system and demonstrate its superiority to other conventional algorithm. Finally, the possibility of performance evaluation and real-time processing was confirmed through the implementation of face authentication system.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.3
• /
• pp.266-274
• /
• 2003

This paper considers an incremental support vector learning for the abnormality detection problems. One of the most well-known support vector learning methods for abnormality detection is the so-called SVDD(support vector data description), which seeks the strategy of utilizing balls defined on the kernel feature space in order to distinguish a set of normal data from all other possible abnormal objects. The major concern of this paper is to modify the SVDD into the direction of utilizing the relation between the optimal solution and incrementally given training data. After a thorough review about the original SVDD method, this paper establishes an incremental method for finding the optimal solution based on certain observations on the Lagrange dual problems. The applicability of the presented incremental method is illustrated via a design example.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.10
• /
• pp.1481-1487
• /
• 2017

This paper proposes a sensorless speed control algorithm for parallel-connected dual Surface-mounted Permanent Magnet Synchronous Motors fed by a single inverter. For stable parallel operation of synchronous motors with a single inverter, each motor has to be constantly kept in the synchronization state regardless of load torque. If the master motor with the larger load is controlled, the synchronous state will be maintained. Therefore, detection of the master motor is essential. Conventionally, the master motor is determined by comparing the rotor position error from the relation between the back-EMF for torque angle and the flux position. consequently, the position sensor is deemed essential for finding the rotor position. In this paper, we proposed a method that decides the magnitude of the load from the power angle of two motors due to the load variation and selects the motor to control through the sign function for the sensorless speed control without the position sensor. The results of simulation and experiment conducted verify the efficacy of the proposed method.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.27 no.6
• /
• pp.531-538
• /
• 2016

In this paper, we design and fabricate a short range FMCW radar which detects and tracks a moving target in a two-dimensional domain using dual transceiver modules. For the short range radar, we propose a scheme for alternate extraction of the two-dimensional positions using one-dimensional range information from time division transceiver modules, and successfully apply the scheme to the two-dimensional short range radar. Measured results of the targets at 10 m and 30 m are presented as performance demonstration of each transceiver module. Also the performance of the two-dimensional radar is demonstrated using a two-dimensional target map, which uses the range bin corresponding to the frequency resolution, and the effectiveness of the proposed scheme is validated.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.3
• /
• pp.1048-1057
• /
• 2015

This paper proposes a sensorless speed control algorithm for parallel-connected dual Surface-mounted Permanent Magnet Synchronous Motors (SPMSMs) fed by a single inverter. For stable parallel operation of synchronous motors with a single inverter, each motor has to be constantly kept in the synchronization state regardless of load torque. If the master motor with the larger load is controlled, the synchronous state will be maintained. Therefore, detection of the master motor is essential. Conventionally, the master motor is determined by comparing the rotor position error from the relation between the back-EMF for torque angle and the flux position; consequently, the position sensor is deemed essential for finding the rotor position. The parallel sensorless speed control method proposed in this paper uses no position sensor, instead it compares the flux-axis current from the connection between the back-EMF for torque angle and current in unbalanced load conditions. The results of simulation and experiment conducted verify the efficacy of the proposed method.

• Journal of information and communication convergence engineering
• /
• v.7 no.3
• /
• pp.366-371
• /
• 2009

A realization for an accurate position detecting system of a moving target in two dimensional plane using dual line CCDs and photometric interpolation is presented. The system is realized that the infrared LEDs are utilized for lighting source, a target size is recognized by the scanned data from CCD owing to blocking the radiated light path by placing the target between CCD and lighting source, a coordinate on the plane is found by plane trigonometry formed by the moving target and two CCD sensors, and the former scan data is used for the coordinate iteratively and the photometric interpolation is applied to sub-pixel of scanned image. The experimental results show that the experiment results in a success rate about 3 different size targets, 3, 5 and 7mmm on the test plane $210{\times}373mm$. The moving target positioning detected success rate is 93% in 3mm target, 5mm is 95.3%, and 7mm is 95.8% respectively. The photometric interpolation is enhanced to 1.5% in comparison to be unused.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.37 no.12
• /
• pp.1225-1231
• /
• 2009

One reaction wheel cluster of satellite usually has four reaction wheels. Each wheel is not arranged parallel to the attitude axis of satellite. Therefore, if one reaction wheel is broken, it is very hard to isolate the fault except using the sensors of wheel itself. In this paper, the isolator of satellite reaction wheel cluster is designed. Using a dual filter, FDP(Fault Detection Parameter) is made to detect fault, and using a multi-hypothesis extended Kalman filter, fault isolation of wheel cluster is done. We verify the improvement of isolation performance of wheel cluster by simulation with 4-reaction wheel cluster.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.50 no.10
• /
• pp.479-485
• /
• 2001

In this paper, we introduce a charge pump phase-locked loop (PLL) architecture which employs a precharge phase frequency detector (PFD) and a sequential PFD to achieve a high frequency operation and a fast acquisition. Operation frequency is increased by using the precharge PFD when the phase difference is within $-{\pi}{\sim}{\pi}$ and acquisition time is shortened by using the sequential PFD and the increased charge pump current when the phase difference is larger than ${\pm}{\pi}$. So error detection range of the proposed PLL structure is not limited to $-{\pi}{\sim}{\pi}$ and a high frequency operation and a higher speed lock-up time can be achieved. The proposed PLL was designed using 1.5 ${\mu}m$ CMOS technology with 5V supply voltage to verify the lock in process. The proposed PLL shows successful acquisition for 200 MHz input frequency. On the other hand, the conventional PLL with the sequential PFD cannot operate at up to 160MHz. Moreover, the lock-up time is drastically reduced from 7.0 ${\mu}s\;to\;2.0\;{\mu}s$ only if the loop bandwidth to input frequency ratio is regulated by the divide-by-4 counter during the acquisition process. By virtue of this dual PFDs, the proposed PLL structure can improve the trade-off between acquisition behavior and locked behavior.