• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.766-771
• /
• 2006

현재 많은 신경망의 하드웨어 구현은 부동 소수점 연산에 비해서 적은 면적과 빠른 수행시간을 가지는 고정소수점 연산을 많이 사용하지만, 소프트웨어에서는 일반적으로 높은 정확도를 가지는 부동소수점 연산을 사용한다. 신경망의 하드웨어 구현에서 많이 사용하는 고정소수점 연산은 부동소수점 연산에 비해서 빠른 처리속도와 적은 면적으로써 쉽게 하드웨어 구현에 용이하지만, 부동소수점 연산에 비해서 낮은 정확도와 기존의 부동소수점 연산을 사용하는 소프트웨어 신경망을 쉽게 적용할 수 없는 단점을 가진다. 본 논문에서는 부동소수점 연산을 사용하여 문자 추출 MLP의 데이터 변환 없이 적용할 수 있는 전체 파이프라이닝 설계 구조를 제안한다. 제안된 설계방법은 신경망의 전체 구조를 입력층과 은닉층을 링크 병렬화 방법과 은닉층과 출력층을 뉴런 병렬화 방법을 개선하여 쉽게 파이프라이닝 구조로 설계함으로써 신경망 처리는 은닉층 뉴런수와 동일한 주기로 처리되며, 기존의 문자추출 소프트웨어 신경망을 제안된 하드웨어 설계방법으로 구현하였을 때 11배의 빠른 성능을 나타낸다.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.1056-1059
• /
• 1996

In this paper, we analyzed the effect of the change of the rotor time constant on the performance of the indirect vector control system. By employing indirect field orientation technique, we have also suggested an optimal control algorithm that allows an induction motor to maintain the maximum torque under the changing environment of rotor time constant. A computer simulation on the transient response of the output torque was demonstrated. To verify the validity of the method that has been proposed in this paper, an experiment has been performed utilizing TMS32OC31(40MHz) DSP chip which is capable of performing floating-point arithmetic in real time.

• 제어로봇시스템학회:학술대회논문집
• /
• 1988.10a
• /
• pp.16-20
• /
• 1988

This paper presents a new algorithm for solving the inverse kinematics in real-time applications. The end-tip movement of each link can be resolved into the basic resolution unit, .DELTA.l, which depends on link length, reduction ratio and resolution of the incremental encoder attached to the joint. When x- and y-axis projection of the end-tip movement are expressed in .DELTA.l unit, projectional increments .DELTA.x and .DELTA.y become -1, 0 or I by truncation. By using the incremental computation with these ternary value and some simple logic rules, a coordinate transformation can be realized. Through this approach, it should be noted that the floating-point arithmetic and the manipulation of trigonometric functions are completely eliminated. This paper demonstrates the proposed method in a parallelogram linkage type, two-link arm.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1394-1397
• /
• 1993

A Fuzzy Microprocessor(FMP) is presented, which is suitable for real-time control applications. The features include high speed inference of maximum 114K FLIPS at 20MHz system clocks, capability of up to 128-rule construction, and handing of 8 input variables with 8-bit resolution. In order to realize these features, the fuzzifier circuit and the processing element(PE) are well optimized for LSI implementation. The chip fabricated in 1.2$\mu\textrm{m}$ CMOS technology contains 71K transistors in 82.8 $\textrm{mm}^2$ die size and is packaged in 100-pin plastic QFP.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.40 no.9
• /
• pp.724-733
• /
• 2003

Generally, dividers have been designed to use iteration, but recently the research on the pipelined divider is underway. It is a difficult point in the known pipelined division unit that a large lookup table is required. In this paper, the cost-effective pipelined divider is proposed, that needs a lookup table smaller than that of the other pipelined divider. The latency of the proposed divider is 3 cycles. We obtain a 30% reduced area than that of P. Hung.

• The KIPS Transactions:PartA
• /
• v.16A no.3
• /
• pp.159-168
• /
• 2009

In this paper, we present an efficient way of implementing OpenGL ES 1.1 standard for the environments with hardware-supported OpenGL API, such as desktop PCs. Although OpenGL ES was started from the existing OpenGL features, it becomes a new three-dimensional graphics library customized for embedded systems through introducing fixed-point arithmetic operations, buffer management with fixed-point data type supports, completely new texture mapping functionalities and others. Currently, it is the official three dimensional graphics library for Google Android, Apple iPhone, PlayStation3, etc. In this paper, we achieved improvements on the arithmetic operations for the fixed-point number representation, which is the most characteristic data type for OpenGL ES. For the conversion of fixed-point data types to the floating-point number representations for the underlying OpenGL, we show the way of efficient conversion processes even with satisfying OpenGL ES standard requirements. We also introduced a simple memory management scheme to mange the converted data for the buffer containing fixed-point numbers. In the case of texture processing, the requirements in both standards are quite different and thus we used completely new software-implementations. Our final implementation result of OpenGL ES library provides all of over than 200 functions in OpenGL ES 1.1 standard and completely passed its conformance test, to show its compliance with the standard. From the efficiency viewpoint, we measured its execution times for several OpenGL ES-specific application programs and achieved at most 33.147 times improvements, to become the fastest one among the OpenGL ES implementations in the same category.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.05a
• /
• pp.140-142
• /
• 2011

In this paper, special purpose arithmetic unit for mobile graphics accelerator is designed. The designed processor supports six operations, such as $1/{\chi}$, $\frac{1}{{\sqrt{x}}$, $log_2x$, $2^x$, $sin(x)$, $cos(x)$. The processor adopts 2nd-order polynomial minimax approximation scheme based on IEEE floating point data format to satisfy accuracy conditions and has 5-stage pipeline structure to meet high operational rates. The SFAU processor consists of 23,000 gates and its estimated operating frequency is about 400 Mhz at operating condition of 65nm CMOS technology. Because the processor can execute all operations with 5-stage pipeline scheme, it has about 400 MOPS(million operations per second) execution rate. Thus, it can be applicable to the 3D mobile graphics processors.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.4
• /
• pp.373-378
• /
• 2002

In fuzzy inferencing, most of conventional fuzzy controllers have problems of speed down in floating point operations of fuzzy membership functions in (0,1) as compared with integer operations. Therefore, in this paper, we propose a high-speed fuzzy controller with only integer operations. In this, for fast fuzzy computations, we use a scan line conversion algorithm to convert lines of each fuzzy linguistic term to the set of the closest integer pixels. We also implement a GUI (Graphic User Interface) application program for the convenient environments to modify and input fuzzy membership functions.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.6
• /
• pp.1150-1158
• /
• 2010

In this paper, a new reliable portable activity monitoring device implemented with the buddhist-style bowing activity and walking step detection algorithm, is presented. In order to monitor the bowing and walking activities, miniaturized 3-axis accelerometer sensor with the sensitivity of 800 mV/g was used. After initial signal conditioning, vector magnitude of accelerometer signals was calculated. Syntactic peak detection method was used in order to feature points. All signal processing algorithms were implemented in ultra-low power microcontroller MSP430 with double precision floating point arithmetic. For evaluation, 19 young man($24.22\pm5.22$ yrs) and woman($22.28\pm2.72$ yrs) were involved. The accuracy of the proposed algorithms were 98.91 %($\pm0.011$) for walking step detection and 98.25 %($\pm0.023$) for buddhist-style bowing activity. Comparing to the commercialized pedometer accuracy, 87.1 %($\pm0.058$), the proposed walking step detection algorithms show more reliable accuracy.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.895-898
• /
• 2005

This paper describes a design of LNS-based divider and square-root circuits which are key arithmetic units in graphic processor and digital signal processor. To achive area-efficient and low-power that is an essential consideration for mobile environment, a fixed-point format of 16.16 is adopted instead of conventional floating-point format. The designed divider and square-root units consist of binary-to-logarithm converter, subtractor, logarithm-to-binary converter. The binary to logarithm converter is designed using combinational logic based on six regions approximation method. As a result, gate count reduction is obtained when compared with conventional lookup approack. The designed units is 3,130 gate count and 1,280 gate count. To minimize average percent error 3.8% and 4.2%. error compensation method is employed.