• IEMEK Journal of Embedded Systems and Applications
• /
• v.9 no.1
• /
• pp.17-24
• /
• 2014

In this paper, we implement and evaluate the performance of a vector-based rasterization algorithm for 3D graphics by using a SIMD (single instruction multiple data) many-core processor architecture. In addition, we evaluate the impact of a data-per-processing elements (DPE) ratio that is defined as the amount of data directly mapped to each processing element (PE) within many-core in terms of performance, energy efficiency, and area efficiency. For the experiment, we utilize seven different PE configurations by varying the DPE ratio (or the number PEs), which are implemented in the same 130 nm CMOS technology with a 500 MHz clock frequency. Experimental results indicate that the optimal PE configuration is achieved as the DPE ratio is in the range from 16,384 to 256 (or the number of PEs is in the range from 16 and 1,024), which meets the requirements of mobile devices in terms of the optimal performance and efficiency.

• Proceedings of the KIEE Conference
• /
• 1997.11a
• /
• pp.479-483
• /
• 1997

In general, motor parameters can be divided into mechanical/electrical parameters and harmonic parameters. Mechanical/electrical parameters identification of motor have been studying systematically for a long time. But, systematical study on harmonic parameters analysis for efficient motor drive system are very poor. The goal of this paper is to propose analyzing method of harmonic parameters for motor drive system with various experimental graphic screens and numerical results and to develope harmonic parameters analyzer. A developed analyzer is made up 586-PC and DSP (digital signal processor) board, motor drive system, power and harmonic parameters analyzing software for windows. Harmonic parameters are analyzed using correlation signal processing techniques based on the correlation between voltage and current waveforms. Analysis results are visualized by 3-D current coordinates, and it is compared and evaluated with conventional time/frequency domain. To verify the validity of the proposed system, 1/4HP capacitor run type single phase induction motor and thyristor speed controller is used for analyzing. Harmonic parameters of motor drive system is analyzed and verified, with varying fire angle of thyristor speed controller, and the proposed approach is to confirm validity.

• The KIPS Transactions:PartB
• /
• v.18B no.4
• /
• pp.173-180
• /
• 2011

This paper shows an approach for real-time object segmentation on GPU (Graphics Processing Unit) using CUDA (Compute Unified Device Architecture). Recently, many applications that is monitoring system, motion analysis, object tracking or etc require real-time processing. It is not suitable for object segmentation to procedure real-time in CPU. NVIDIA provide CUDA platform for Parallel Processing for General Computation to upgrade limit of Hardware Graphic. In this paper, we use adaptive Gaussian Mixture Background Modeling in the step of object extraction and CCL(Connected Component Labeling) for classification. The speed of GPU and CPU is compared and evaluated with implementation in Core2 Quad processor with 2.4GHz.The GPU version achieved a speedup of 3x-4x over the CPU version.

• Proceedings of the KOSOMBE Conference
• /
• v.1996 no.05
• /
• pp.320-324
• /
• 1996

Digital fetal monitoring system based on the personal computer combined with the digital signal processing board was implemented. The DSP board acquires and digitally processes ultrasound fetal Doppler signal for digital rectification, FIR filtering, autocorrelation function calculation, its peak detection and MEDIAN filtering. The personal computer interfaced with the DSP board is in charge of graphic display, hardcopy, data transmission and on-line analysis of fetal heart rate change including and variability. I used a recursive technique for autocorrelation function computation method and MEDIAN filter which can greatly reduce the amount of calculation and accuracy. I also implemented analysis algorithm of fetal heart rate change based on normal fetal sample data in order to exact diagnosis.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.3
• /
• pp.547-554
• /
• 2008

In this paper, two-stage pipelined floating-point multiplier (FP-MUL) is designed. The FP-MUL processor supports single precision multiplication for 3D graphic APIs, such as OpenGL and Direct3D and has area-efficient and low-latency architecture via saturated arithmetic, area-efficient sticky-bit generator, and flagged prefix adder. The FP-MUL has about 4-ns delay time under $0.13{\mu}m$ CMOS standard cell library and consists of about 7,500 gates. Because its maximum performance is about 250 MFLOPS, it can be applicable to mobile 3D graphics application.

• Korean Journal of Radiology
• /
• v.24 no.7
• /
• pp.698-714
• /
• 2023

In recent years, artificial intelligence, especially object detection-based deep learning in computer vision, has made significant advancements, driven by the development of computing power and the widespread use of graphic processor units. Object detection-based deep learning techniques have been applied in various fields, including the medical imaging domain, where remarkable achievements have been reported in disease detection. However, the application of deep learning does not always guarantee satisfactory performance, and researchers have been employing trial-and-error to identify the factors contributing to performance degradation and enhance their models. Moreover, due to the black-box problem, the intermediate processes of a deep learning network cannot be comprehended by humans; as a result, identifying problems in a deep learning model that exhibits poor performance can be challenging. This article highlights potential issues that may cause performance degradation at each deep learning step in the medical imaging domain and discusses factors that must be considered to improve the performance of deep learning models. Researchers who wish to begin deep learning research can reduce the required amount of trial-and-error by understanding the issues discussed in this study.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.05a
• /
• pp.641-644
• /
• 2008

This paper describes the GUI implementation of an intelligent embedded system which can be used for a personal information platform and an industrial mobile application system. It shows the architecture and the necessary structure and components of X Window graphic system. The embedded system used in this paper has low power and high performance processor, and has a large memory size with a nand-flash memory device. We configured the linux kernel with a TIT-LCD and touch screen device for the operation of X Window system. And we used GTK+2 for running application softwares on the platform embedded system. The GUI library of GTK+2 is useful for providing the same graphics programming environment with host Linux PC. We have developed in this paper the X Window system and the GUI environment for GTK+2 in a new embedded system, and verified the full operation of X Window system and application softwares using GTK+2. The embedded system with large memory size can be used in X Window application softwares for providing a personal information service with a mobile embedded system.

• Journal of Broadcast Engineering
• /
• v.16 no.4
• /
• pp.596-601
• /
• 2011

In this paper, we propose a fast depth-image-based rendering method to generate a virtual view image in real-time using a graphic processor unit (GPU) for a 3D broadcasting system. Before the transmission, we encode the input 2D+depth video using the H.264 coding standard. At the receiver, we decode the received bitstream and generate a stereo video using a GPU which can compute in parallel. In this paper, we apply a simple and efficient hole filling method to reduce the decoder complexity and reduce hole filling errors. Besides, we design a vertical parallel structure for a forward mapping process to take advantage of the single instruction multiple thread structure of GPU. We also utilize high speed GPU memories to boost the computation speed. As a result, we can generate virtual view images 15 times faster than the case of CPU-based processing.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.435-438
• /
• 2003

The MS card data transfer system using blue-tooth protocol ran communicate the MS card data wirelessly and does not take an extra communication expense which is a weakness point of existing wireless communication system. This Blue-tooth system, which has excellent security and no extra communication expense, can efficiently communicate data of the place ,where can be solved with small scale wireless network, such as the theme-park or gasoline-station. Existing wireless communication system compose network using wireless-LAN protocol which has extra communication expense, or with RF protocol which has poor security. But this system suitable for LAN because it has not extra communication expense and it has excellent security cause frequency-hopping of Blue-tooth protocol. The MS card data transfer system using blue-tooth protocol has low power, high performance RISC processor and large scale 16-gray graphic LCD which is suitable for portable unit. The MS card data transfer system can efficiently control depot for a long time because it has low power, excellent security and no extra communication expense.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.2
• /
• pp.117-124
• /
• 2004

In this paper, we have been implemented the QPSK-based underwater transmission systems using DSP in order to transmit the underwater image data. We have adopted a BDPA (Block Data Parallel Architecture) to control multiple DSPs used in the transmitter and receiver in order to transmit the image data in real-time. We also have developed GUI software in order to drive and to debug the implemanted system in real-time. We have executed open sea tests in order to analyze the performance of the implemented system at East Sea near Kosung in Kangwon-Do. As a result of these experiments, it has been demonstrated that 10 kbps image data can be received without errors at 30m and 80m depth points, while the distance between the transmitter and the receiver is up to 20m.