• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권3호
• /
• pp.1348-1375
• /
• 2018

Support Vector Machine (SVM) is a well-known machine learning classification algorithm, which has been widely applied to many data mining problems, with good accuracy. However, SVM classification speed decreases with increase in dataset size. Some applications, like video surveillance and intrusion detection, requires a classifier to be trained very quickly, and on large datasets. Hence, this paper introduces two filter-based instance selection techniques for optimizing SVM training speed. Fast classification is often achieved at the expense of classification accuracy, and some applications, such as phishing and spam email classifiers, are very sensitive to slight drop in classification accuracy. Hence, this paper also introduces two wrapper-based instance selection techniques for improving SVM predictive accuracy and training speed. The wrapper and filter based techniques are inspired by Cuckoo Search Algorithm and Bat Algorithm. The proposed techniques are validated on three popular e-fraud types: credit card fraud, spam email and phishing email. In addition, the proposed techniques are validated on 20 other datasets provided by UCI data repository. Moreover, statistical analysis is performed and experimental results reveals that the filter-based and wrapper-based techniques significantly improved SVM classification speed. Also, results reveal that the wrapper-based techniques improved SVM predictive accuracy in most cases.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.919-920
• /
• 2008

In this paper, we present early processing techniques for visual inspection of metallic parts. Since metallic surfaces give rise to specular reflections, it is difficult to extract object boundaries using elementary segmentation techniques such as edge detection or binary thresholding. In this paper, we present two techniques for finding object boundaries on micro bit images. First, we explain a technique for detecting blade boundaries using a directional correlation mask. Second, a line and angle extraction technique based on Harris corner detector and Hough transform is described. These techniques have been effective for detecting blade boundaries, and a number of experimental results are presented using real images.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2001년도 춘계종합학술대회
• /
• pp.629-632
• /
• 2001

본 논문은 최근 급격히 대두되어지고 있는 디지털 영상에 대한 워터마킹(Watermarking) 기법들중에서 웨이블릿 기반의 여러 가지 기법들에 대한 장/단점을 비교하였다. 워터마킹은 소유권을 주장하기 위하여 '워터마크'라는 디지털 신호를 영상에 첨가하는 것이다. 본 연구에서는 다양한 워터마킹 기법들 중에서 웨이블릿 기법을 이용한 워터마킹에 대해서 국 내/외에서 주장되어진 여러 가지 예들을 가지고 비교함으로써, 보다 실용적인 워터마킹 기법을 제시하고자 한다. 실험 결과 제안된 여러 가지 기법들 중에서 보다 우수한 화질과 강인한 특성을 가지는 워터마킹 기법에 대해서 알 수 있었다.

• PNF and Movement
• /
• 제18권2호
• /
• pp.245-254
• /
• 2020

Purpose: The study investigated the effects of extracorporeal shock wave therapy with myofascial release techniques (ESWT+MFR) on pain, movement, and function in patients with myofascial pain syndrome. Methods: Forty participants with upper trapezius trigger points were recruited and randomly allocated to two groups: an experimental group (n = 20) and a control group (n = 20). The experimental group performed the ESWT+MFR, and the control group performed only myofascial release techniques. Each group was treated for 15 minutes, twice a week for four weeks. Pain was assessed using a visual analogue scale and a pressure pain threshold measure. Movement was assessed by cervical range of motion, and cervical and shoulder function were assessed on the Constant-Murley Scale and the Neck Disability Index before and after treatment. Results: The results indicate statistically significant improvements in the two groups on all parameters after intervention as compared to baseline (p < 0.05). As compared to the control group, the experimental group showed statistically significant improvements on the visual analogue scale and pressure pain threshold, cervical range of motion (except rotation), and on the Neck Disability Index (p < 0.05). Conclusion: The ESWT+MFR is more effective than myofascial release techniques for pain, movement, and function in patients with myofascial pain syndrome and would be clinically useful for physical therapists treating myofascial pain syndrome.

• 한국기계연구소 소보
• /
• 제4권2호
• /
• pp.115-118
• /
• 1982

• International Journal of Naval Architecture and Ocean Engineering
• /
• 제2권1호
• /
• pp.24-33
• /
• 2010

Design of a Pump Jet Propulsor (PJP) was undertaken for an underwater body with axisymmetric configuration using axial/low compressor design techniques supported by Computational Fluid Dynamics (CFD) analysis for performance prediction. Experimental evaluation of the PJP was earned out through experiments in a Wind Tunnel Facility (WTF) using momentum defect principle for propulsive performance prior to proceeding with extensive experimental evaluation in towing tank and cavitation tunnel. Experiments were particularly conducted with respect to Self Propulsion Point (SPP), residual torque and thrust characteristics over a range of vehicle advance ratio in order to ascertain whether sufficient thrust is developed at the design condition with least possible imbalance torque left out due to residual swirl in the slip stream. Pumpjet and body models were developed for the propulsion tests using Aluminum alloy forged material. Tests were conducted from 0 m/s to 30 m/s at four rotational speeds of the PJP. SPP was determined confirming the thrust development capability of PJP. Estimation of residual torque was carried out at SPP corresponding to speeds of 15, 20 and 25 m/s to examine the effectiveness of the stator. Estimation of thrust and residual torque was also carried out at wind speeds 0 and 6 m/s for PJP RPMs corresponding to self propulsion tests to study the propulsion characteristics during the launch of the vehicle m water where advance ratios are close to Zero. These results are essential to assess the thrust performance at very low advance ratios to accelerate the body and to control the body during initial stages. This technique has turned out to be very useful and economical method for quick assessment of overall performance of the propulsor and generation of exhaustive fluid dynamic data to validate CFD techniques employed.

• 한국환경복원기술학회지
• /
• 제3권1호
• /
• pp.38-51
• /
• 2000

This study seeks to present creation techniques increasing biodiversity while excluding techniques that avoid rooftop as a place for revegetation or techniques that are standardized and ecologically undesirable. To this end, a theoretical study was conducted including the identification of issues that need to be considered in introducing biotope creation techniques at a rooftop space using eco-pond or eco-park creation techniques. Based on the result, a creation process and techniques were presented for the rooftop of Kyungdong Energy Company building located in Bundang, Sungnam city. The conclusions reached in this study are as follows. First, when structural problems such as load or leakage are resolved and when it is planned as a habitat within a range of carrying load, a rooftop may be habitats for various organisms. Second, same creation techniques for eco-ponds or eco-parks may be applied to create biotope in a rooftop. In fact, the introduction of a wetland ecosystem on a rooftop may contribute significantly in increasing biodiversity. In addition, it would be desirable to approach traditional rooftop revegetation methods in an ecological aspect and to introduce indigenous plants and to offer habitats to insects and birds. Third, in order to create rooftop biotope, there should be enough studies and experiments on resolving structural problems and on techniques or technologies to create habitats. Since the Kyongdong Energy Company rooftop biotope described in this study is the first experimental site in Korea, it requires a series of process to identify problems and to improve them by monitoring the site in the future. Through such studies and experiments, efficient rooftop biotope creation techniques should be developed and disseminated.

• Bulletin of the Korean Chemical Society
• /
• 제25권7호
• /
• pp.1046-1050
• /
• 2004

Six physical properties (enthalpy, density, decomposition temperature, solubility in water, pKa values, and hydronium potential) were examined by molecular modeling techniques. The molecular connectivity index, Wiener distance index, and Ad hoc descriptor are employed as structural parameters to encode information about branching, size, cyclization, unsaturation, heteroatom content, and polarizability. This paper examines the correlation of the molecular modeling techniques parameters and the physicochemical properties of amino acids. As a results, calculated values were in agreement with experimental data in the above six physical properties of amino acids and the molecular connectivity index was superior to the other indices in fitting the calculated data.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.459-462
• /
• 2003

Selectivity estimation of queries not only provides useful information to the query processing optimization but also may give users with a preview of processing results. In this paper, we investigate the problem of selectivity estimation in the context of a spatial dataset. Although several techniques have been proposed in the literature to estimate spatial query result sizes, most of those techniques still have some drawback in the case that a large amount of memory is required to retain accurate selectivity. To eliminate the drawback of estimation techniques in previous works, we propose a new method called MW Histogram. Our method is based on two techniques: (a) MinSkew partitioning algorithm that processes skewed spatial datasets efficiently (b) Wavelet transformation which compression effect is proven. We evaluate our method via real datasets. With the experimental result, we prove that the MW Histogram has the ability of providing estimates with low relative error and retaining the similar estimates even if memory space is small.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2006년도 춘계학술발표회 논문집
• /
• pp.243-248
• /
• 2006

In this paper, we propose the unsupervised change detection algorithm that apply the similarity measure techniques to the hyperspectral image. The general similarity measures including euclidean distance and spectral angle were compared. The spectral similarity scale algorithm for reducing the problems of those techniques was studied and tested with Hyperion data. The thresholds for detecting the change area were estimated through EM(Expectation-Maximization) algorithm. The experimental result shows that the similarity measure techniques and EM algorithm can be applied effectively for the unsupervised change detection of the hyperspectral data.