• Journal of Computing Science and Engineering
• /
• v.9 no.4
• /
• pp.204-213
• /
• 2015

Under the conditional independence assumption among local features, the Naive Bayes Nearest Neighbor (NBNN) classifier has been recently proposed and performs classification without any training or quantization phases. While the original NBNN shows high classification accuracy without adopting an explicit training phase, the conditional independence among local features is against the compositionality of objects indicating that different, but related parts of an object appear together. As a result, the assumption of the conditional independence weakens the accuracy of classification techniques based on NBNN. In this work, we look into this issue, and propose a novel Bayesian network for an NBNN based classification to consider the conditional dependence among features. To achieve our goal, we extract a high-level feature and its corresponding, multiple low-level features for each image patch. We then represent them based on a simple, two-level layered Bayesian network, and design its classification function considering our Bayesian network. To achieve low memory requirement and fast query-time performance, we further optimize our representation and classification function, named relation-based Bayesian network, by considering and representing the relationship between a high-level feature and its low-level features into a compact relation vector, whose dimensionality is the same as the number of low-level features, e.g., four elements in our tests. We have demonstrated the benefits of our method over the original NBNN and its recent improvement, and local NBNN in two different benchmarks. Our method shows improved accuracy, up to 27% against the tested methods. This high accuracy is mainly due to consideration of the conditional dependences between high-level and its corresponding low-level features.

• Asian-Australasian Journal of Animal Sciences
• /
• v.24 no.2
• /
• pp.162-172
• /
• 2011

In this paper, simulation was used to determine accuracies of genomic breeding values for polygenic traits associated with many thousands of markers obtained from high density genome scans. The statistical approach was based upon stochastically simulating a pedigree with a specified base population and a specified set of population parameters including the effective and noneffective marker distances and generation time. For this population, marker and quantitative trait locus (QTL) genotypes were generated using either a single linkage group or multiple linkage group model. Single nucleotide polymorphism (SNP) was simulated for an entire bovine genome (except for the sex chromosome, n = 29) including linkage and recombination. Individuals drawn from the simulated population with specified marker and QTL genotypes were randomly mated to establish appropriate levels of linkage disequilibrium for ten generations. Phenotype and genomic SNP data sets were obtained from individuals starting after two generations. Genetic prediction was accomplished by statistically modeling the genomic relationship matrix and standard BLUP methods. The effect of the number of linkage groups was also investigated to determine its influence on the accuracy of breeding values for genomic selection. When using high density scan data (0.08 cM marker distance), accuracies of breeding values on juveniles were obtained of 0.60 and 0.82, for a low heritable trait (0.10) and high heritable trait (0.50), respectively, in the single linkage group model. Estimates of 0.38 and 0.60 were obtained for the same cases in the multiple linkage group models. Unexpectedly, use of BLUP regression methods across many chromosomes was found to give rise to reduced accuracy in breeding value determination. The reasons for this remain a target for further research, but the role of Mendelian sampling may play a fundamental role in producing this effect.

• Journal of the Korean Society for Precision Engineering
• /
• v.12 no.7
• /
• pp.138-147
• /
• 1995

The conventional PWM method, which was used in controlling the on-off valve, such as high-speed solenoid valve, was modulating the width of the pulse applied to the valve, by selecting arbitrary sampling time and modulating the duty-ratio in proportion to the error. However, in this method, a selection of long sampling time was inevitable and it was unable to get a high accuracy and a quick response. This study is for designing an appropriate controller for high-speed solenoid valve by proposing an improved duty-ratio modulation method using the Saw-toothed Carrier Wave which enables a short sampling time selection, high accuracy of control, and a quick response. Test which was carried out in the laboratory shows that transient and steady state response could be improved by PID controller.

• International Journal of Precision Engineering and Manufacturing
• /
• v.7 no.3
• /
• pp.47-50
• /
• 2006

High-speed machining is a very useful tool and one of the most effective rapid manufacturing processes. This study sought to produce various high-speed machining materials with excellent quality and dimensional accuracy. However, high-speed machining is not suitable for microscale thin-walled structures because the structure stiffness lacks the ability to resist the cutting force. This paper proposes a new method that is able to rapidly produce very thin-walled structures. This method consists of high-speed machining followed by filling. A strong work-holding force results from the solidification of the filling materials. Low-melting point metal alloys are used to minimize the thermal effects during phase changes and to hold the arbitrarily shaped thin-walled structures quickly during the high-speed machining. We demonstrate some applications, such as thin-walled cylinders and hemispherical shells, to verify the usefulness of this method and compare the analyzed dimensional accuracy of typical parts of the structures.

• Journal of the Korean Society for Precision Engineering
• /
• v.18 no.10
• /
• pp.208-213
• /
• 2001

High speed milling(HSM) is one of the emerging cutting process having tremendous potential not only in increased metal removal rates but also in improved surface finish, burr free edge, dimensional accuracy and a virtually stress free component after machining. The High efficiency and accuracy in machining of die/mold materials can be obtained in high speed machining, so it is necessary to analytic the mechanism of high speed cutting process : cutting force, acoustic emission signal.

• Journal of KSNVE
• /
• v.9 no.6
• /
• pp.1227-1233
• /
• 1999

Modern technology depends on the reliability of extremely high technology equipments. In the production of semiconductor wafer, optical and electron microscopes, ion-beam, laser device must maintain their alignments within a nanometer. This equipment requires a vibration free environment to provide its proper function. Especially, lithography and inspection devices, which have sub-nanometer class high accuracy and resolution, have come to necessity for producing more improved giga and tera class semiconductor wafers. This high technology equipments require very strict environmental vibration standard, vibration criteria, in proportion to the accuracy of the manufacturing, inspecting devices. This paper deals with the structural dynamic design in high class semiconductor factory in order to be satisfied more strict vibration criteria for high sensitive equipment.

• Journal of the Korean Society for Precision Engineering
• /
• v.10 no.2
• /
• pp.190-196
• /
• 1993

Internal high speed grinding under several high grinding wheel speed condition has been performed in this study for the effects have analyzed and compared with the grinding power, grinding tangential force and accuracy of surface with the carbon tool steel(SK3). The following results have been obtained: (1) Under the workpiece speed constant condition, increasing the grinding speed, the tangential force is decreased, and on the contrary, accuracy of surface is improved. (2) Under the speed ratio (V$_{w}$/V$_{s}$) contant condition it is possible to increase the high machining efficiency constraint to tangential grinding force constant.ant.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.667-670
• /
• 1998

Novel bipolar transresistance amplifier(TRA) for high-accuracy current-mode signal processing is described. The TRA consists of two current follower for the current inputs, a current summer for curent-differential, and a voltage follower for the voltage output. The simulation results show that the impedence of the current input and the voltage output is 0.5 $\Omega$ and the 3-dB cutoff frequency when used as a current to voltage converter extends beyond 40 MHz.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1991.11a
• /
• pp.101-104
• /
• 1991

Bal1 screw systems has been used for positioning elements of machine tools. In order to maintain high rigidity and accuracy, preload is applied between nut and screw. However, large amount of preload increases frictional heat. Temperature rises remarkably at high speed notion, Thermal expansion degrades positioning accuracy, In this paper, finite differance method is applied to compute temperature distributions and thermal expansions of ball screw systems according to preload condition and rotational steed. Some simulation results show that the developed methodology is good to study thermal expansion of ball screw systems.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.04b
• /
• pp.371-376
• /
• 1995

Computer vision is applicated to measure the position and orientation of the SMD on 8mm Camcoder PCB and advanced image processing algorithms for high accuracy and real time processing are proposed. Illumination conditions are optimized for the best image formation and a set of LEDs is used as economic illuminator, which is regarded as a summation of many point sources. Conctete optical system is constructed and the performance of the proposed algorithm is verified by several experiments.