• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.3
• /
• pp.329-337
• /
• 2017

This paper proposes a search method that explores parameters C and σ values of support vector machines (SVM) to improve performance while maintaining search accuracy. A traditional grid search method requires tremendous computational times because it searches all available combinations of C and σ values to find optimal combinations which provide the best performance of SVM. To address this issue, this paper proposes a deep search method that reduces computational time. In the first stage, it divides C-σ- accurate metrics into four regions, searches a median value of each region, and then selects a point of the highest accurate value as a start point. In the second stage, the selected start points are re-divided into four regions, and then the highest accurate point is assigned as a new search point. In the third stage, after eight points near the search point. are explored and the highest accurate value is assigned as a new search point, corresponding points are divided into four parts and it calculates an accurate value. In the last stage, it is continued until an accurate metric value is the highest compared to the neighborhood point values. If it is not satisfied, it is repeated from the second stage with the input level value. Experimental results using normal and defect bearings show that the proposed deep search algorithm outperforms the conventional algorithms in terms of performance and search time.

• Korean Management Science Review
• /
• v.13 no.2
• /
• pp.147-161
• /
• 1996

Due-date is an important factor in Flexible Manufacturing System scheduling. Even though most of researchers have focused part selection and loading problem using fixed due-date assignment rules, FMSs consist of multi-function machines which facilitate alternative processes. This research investigates interactions of three dispatching mechanisms, three NSS (Next Station Selection) rules and four due-date assignment rules using simulation. Both cost-based and time-based performance measures are considered in this research.

• The Journal of the Acoustical Society of Korea
• /
• v.10 no.2
• /
• pp.13-22
• /
• 1991

The presence of an unbalanced mass is originated the common source of vibration in machines with rotating rotor. In this study, the unbalanced rigid rotor mounted on an overhang shaft is balanced using the static balancing procedure, and the compensation mass is estimated by the phase angle method and four run method. Also, the reduction of vibration level before and after balancing is examined. In the experimental results, it is shown that the vibration due to the unbalanced mass is decreased by eliminating the effect of the unbalance. Above all, the four run method is proved more effective on the ability of vibration reduction, in small unbalanced mass, the phase angle method.

• Fashion & Textile Research Journal
• /
• v.20 no.1
• /
• pp.83-92
• /
• 2018

This paper investigated garment formability and fabric mechanical properties of one-way and two-way stretch fabrics according to the thermal treatment methods. One-way and two-way stretch fabrics were woven using 75d and 150d PET/spandex covering yarns and then these were wet thermal treated with four kinds of finishing machines. The fabric mechanical properties of these stretch fabrics specimens were measured and compared with the regular PET fabrics. The stretch ratio of one-way stretch fabric was ranged 12 to 26 percentage, 15 to 45 percentage for 2-way stretch fabrics and 4 to 10 percentage for regular fabrics. Garment formability of stretch fabric was superior than that of regular fabrics, in addition, 2-way stretch fabric was better than one-way. The garment formability of the stretch fabrics treated with CPB and Lava wet thermal machines showed the highest values, and the stretch ratio of these 2-way stretch fabrics was also the highest, which was ranged 20 to 45 percentage. This phenomenon was assumed to be due to high extensibility and bending rigidity with low shear modulus of the 2-way stretch fabric treated with CPB and Lava wet thermal machines. It was shown that the garment formability of stretch fabrics treated without dry thermal treatment was higher than that of dry thermal treated fabrics. It revealed that high stretch fabric was available under the condition of low process tension in the wet and dry thermal treatments of the finishing process, which makes high garment formability.

• Journal of Biosystems Engineering
• /
• v.7 no.2
• /
• pp.36-44
• /
• 1983

Farm population was rapidly decreasing due to shift of the people from farm sector to the non-farm sector caused by the economic growth of the country. Especially, a great shortage of farm labor in busy farming period in June and October is becoming a serious problem in maintaining or promoting land productivity. The peak of labor requirement in summer is caused by rice transplanting and barley harvesting. In order to reduce the restrictions imposed on farm management by the concurrence of labor requirement and the lack of labor, the experimental study for mechanization of barley harvesting has been carried out in the fields. 1. The machines for barley harvesting were knap-sack type reapers, windrow reaper (power tiller attachment), binder and combine. The order of higher efficiency of machine for barley harvesting was combine, binder, windrow reaper (WR), knapsack type reaper 1(KSTR1), and knap sack type reaper 2(KSTR2; mist and duster attachment). 2. The ratio of grain loss for the manual, binder, and combine plot was about four percent of total field yield. 3. The total yield of barley in 35 days and 40 days harvesting after heading were 514 kg and 507kg per 10 ares respectively. The yield of 35 days-plot was higher than other experimental plots. 4. The lowest yield was recorded in 30 days-plot due to the large quantity of immatured grains and having lighter 1000-grain weight. The ratio of immatured grains was 2.66 percent and 1000-grain weight was 29.4 grams. 5. The total harvesting cost of the windrow reaper was 10,178 won per 10 ares. It was the lowest value compared to other machines. The next were combine, binder, KSTR1, KSTR2, and manual in sequence. As a result, the optimum time of barley harvesting for mechanization was 35-40 days after heading. Combine, binder, and windrow reaper were recommended as the suitable machines for barley harvesting in the work efficiency. However, in total harvesting cost, the windrow reaper was the most promising machine for barley harvesting.

• Journal of KIISE:Software and Applications
• /
• v.35 no.1
• /
• pp.41-49
• /
• 2008

Fingerprint classification is useful to reduce the matching time of a huge fingerprint identification system by categorizing fingerprints into predefined classes according to their global features. Although global features are distributed diversly because of the uniqueness of a fingerprint, previous fingerprint classification methods extract global features non-adaptively from the fixed region for every fingerprint. We propose an novel method that extracts features adaptively for each fingerprint in order to classify various fingerprints effectively. It extracts ridge directional values as feature vectors from the region after searching the feature region by calculating variations of ridge directions, and classifies them using support vector machines. Experimental results with NIST4 database show that we have achieved a classification accuracy of 90.3% for the five-class problem and 93.7% for the four-class problem, and proved the validity of the proposed adaptive method by comparison with non-adaptively extracted feature vectors.

• Journal of KIISE:Software and Applications
• /
• v.32 no.11
• /
• pp.1136-1146
• /
• 2005

Fingerprint classification is useful in an automated fingerprint identification system (AFIS) to reduce the matching time by categorizing fingerprints. Based on Henry system that classifies fingerprints into S classes, various techniques such as neural networks and support vector machines (SVMs) have been widely used to classify fingerprints. Especially, SVMs of high classification performance have been actively investigated. Since the SVM is binary classifier, we propose a novel classifier-combination model, multiple decision templates (MuDTs), to classily fingerprints. The method extracts several clusters of different characteristics from samples of a class and constructs a suitable combination model to overcome the restriction of the single model, which may be subject to the ambiguous images. With the experimental results of the proposed on the FingerCodes extracted from NIST Database4 for the five-class and four-class problems, we have achieved a classification accuracy of $90.4\%\;and\;94.9\%\;with\;1.8\%$ rejection, respectively.

• The Research Journal of the Costume Culture
• /
• v.21 no.4
• /
• pp.494-510
• /
• 2013

The purpose of this study was to develop unique men's pullovers using the patterns of Baekje tile, brick, and gilt-bronze shoes. As the method of the study, it was reviewed of the literature about Baekje traditional patterns and the knitting techniques. The development of pullover design was used TexPro design CAD program. The manufacture of pullover were knitted by Shima Seiki computerized knitting machines and Brother manual knitting machines. The results of study were as follows. First, the patterns of Baekje tile, brick and gilt-bronze shoes were suited to develop as motif for men's pullover. Second, men's pullover using Baekje traditional patterns were able to maintain the identity of Korean traditional culture and express the originality of design. Third, pullover was chosen three styles and was developed four design. Each pullover design was applied four colorway. Forth, pullover products were made by wool 100% yarn or cotton 47%/acrylic 53% mixed yarn. The patterns were expressed by knitting techniques of floating jacquard and birds-eye jacquard. Luxurious knit fashions were produced. Consequently, through the men's pullover development utilizing Baekje traditional patterns was showed the superiority of the local traditional culture, which is further emphasized by the current globalization. It also confirmed the possibility of the development of high value-added knitted fashion products to meet the needs of modern people to pursue individuality.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2006.11a
• /
• pp.411-416
• /
• 2006

Fault detection and diagnosis is the most important technology in condition-based maintenance(CBM) system that usually begins from collecting signatures of running machines using multiple sensors for subsequent accurate analysis. With the quick development in industry, there is an increasing requirement of selecting special sensors that are cheap, robust, and easy-installation. This paper experimentally investigated performances of four types of sensors used in induction motors faults diagnosis, which are vibration, current, voltage and flux. In addition, diagnostic effects of five popular classifiers also were evaluated. First, the raw signals from the four types of sensors are collected at the same time. Then the features are calculated from collected signals. Next, these features are classified through five classifiers using artificial intelligence techniques. Finally, conclusions are given based on the experiment results.

• Journal of Electrical Engineering and Technology
• /
• v.3 no.1
• /
• pp.68-78
• /
• 2008

This paper introduces a complete package for SRM drive on Power System Computer-Aided Design/Electromagnetic Transients (PSCAD/EMTDC). A three-phase SRM drive is modeled and simulated on PSCAD. The motor is modeled using an accurate nonlinear analytical model that takes into consideration the machine nonlinearities. A current control algorithm is applied for torque ripple minimization to achieve a smooth output torque which is necessary for high performance applications. The motor drive is tested for four-quadrant operations. The modeled SRM is capable of operating as a motor or generator during clockwise and counterclockwise motions. The proposed package helps in understanding the operational principles of switched reluctance motors, investigating the dynamic characteristics of SRM drives, and achieving a high performance dynamic control task.