• Journal of the Korean Data and Information Science Society
• /
• v.12 no.2
• /
• pp.113-124
• /
• 2001

CHAID, logistic regression, bagging trees, and bagging trees are compared on SAS artificial data set as HMEQ in terms of classification accuracy and training time. In error rates, bagging trees is at the top, although its run time is slower than those of others. The run time of logistic regression is best among given models, but there is no uniformly efficient model satisfied in both criteria.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.12a
• /
• pp.275-278
• /
• 2002

Vapnik이 제안한 Support Vector Machine은 두 개의 부류를 갖는 데이터에 대한 분류에는 매우 좋은 성능을 보인다는 점은 이미 잘 알려져 있다. 하지만 부류의 개수가 3개 이상인 다중 패턴을 갖는 데이터에 대한 분류에는 SVM을 적용하기가 쉽지 않다. Support Vector Machine의 이러한 문제점을 해결하기 위하여 Zhu는 3개 이상의 부류를 갖는 데이터의 패턴 분류를 위하여 Import Vector Machine을 제안하였다. 이 모형은 Support Vector Machine을 이용하여 해결하기 어려운 다중 패턴 분류를 가능케 한다. Import Vector Machine은 커널 로지스틱 기반의 함수만을 사용하지만 본 논문에서는 다수의 커널 함수를 적용하여 가장 성능이 우수한 커널 함수를 찾아내어 최종 분류를 수행하게되는 bagging 기법을 적용하였다 제안하는 방법이 기존의 방법에 비해, 더욱 정확한 분류를 수행함을 실험 결과를 통해 확인한다.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.97-102
• /
• 2022

Network intrusion detection is becoming an increasing necessity for both organizations and individuals alike. Detecting intrusions is one of the major components that aims to prevent information compromise. Automated systems have been put to use due to the voluminous nature of the domain. The major challenge for automated models is the noise and data imbalance components contained in the network transactions. This work proposes an ensemble model, Attribute Subset Selector Bagging (ASUB) that can be used to effectively handle noise and data imbalance. The proposed model performs attribute subset based bag creation, leading to reduction of the influence of the noise factor. The constructed bagging model is heterogeneous in nature, hence leading to effective imbalance handling. Experiments were conducted on the standard intrusion detection datasets KDD CUP 99, Koyoto 2006 and NSL KDD. Results show effective performances, showing the high performance of the model.

• Journal of Life Science
• /
• v.7 no.4
• /
• pp.342-346
• /
• 1997

This experiment was carried out to clarify the effects of gibberellin(GA) aplication and bagging on repeening and quality in 'Delaware' grape berries. Treatments are 4 plots(2X2 factorial experiment); GA, GA+bagging, bagging and control. The clusters were dipped twice in 100 ppm GA with GA treatment : 10 days before and after the full bloom. The results obtained as follows: 1. GA treatment made the seedless grape berry reduced in the fresh weight but it hastened the ripening period about 2 weeks. 2. Total soluble solid(TSS), viscosity and pH value of berry juice increased with maturation. The concentration of TSS and viscosity were higher in GA treatment plot than GA non-treatment. 3. Berry-hardness, titratable acidity and alcohol inslouble solid(AIS) decreased with maturation. Expically berry-hardness and AIS decreased more greatly in GA non-treatment than GA treatment. 4. The concentration of anthocyanin increased with ripening but pectic substance didn't fluctuate nearly. These of anthocyanin and pectin were higher in GA non-treatment plot than GA treatment. 5. By analysis of factorial experiment GA treatment was highly significant with the $^{o}$Brix/Acidity ratio, juice viscosity and AIS, but high negatively, significant with berry-hardness and berry fresh weight. And it was significant with T S S and negatively, titratable acidity. Bagging was significant with $^{o}$Brix/Acidity ratio and AIS content, but negatively, titratable acidity. 6. Qualitative characters were high correlated with the $^{o}$Brix/Acidity ratio in simple correlation but direct effect by the path-coefficient analysis didn't coincide with simple correlation. The direct effect of pH was large and juice viscosity, the next. And that of berry-hardness was negligible but, AIS, small negatively.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.32 no.1
• /
• pp.33-41
• /
• 1996

In order to obtain the most favourable classification system for fishing gears, the problems in the existing systems were investigated and a new system in which the fishing method was adopted as the criterion of classification and the kinds of fishing gears were obtained by exchanging the word method into gear in the fishing methods classified newly for eliminating the problems was established. The new system to which the actual gears are arranged is as follows ; (1)Harvesting gear \circled1Plucking gears : Clamp, Tong, Wrench, etc. \circled2Sweeping gears : Push net, Coral sweep net, etc. \circled3Dredging gears : Hand dredge net, Boat dredge net, etc. (2)Sticking gears \circled1Shot sticking gears : Spear, Sharp plummet, Harpoon, etc. \circled2Pulled sticking gears : Gaff, Comb, Rake, Hook harrow, Jerking hook, etc. \circled3Left sticking gears : Rip - hook set line. (3)Angling gears \circled1Jerky angling gears (a)Single - jerky angling gears : Hand line, Pole line, etc. (b)Multiple - jerky angling gears : squid hook. \circled2Idly angling gears (a)Set angling gears : Set long line. (b)Drifted angling gears : Drift long line, Drift vertical line, etc. \circled3Dragged angling gears : Troll line. (4)Shelter gears : Eel tube, Webfoot - octopus pot, Octopus pot, etc. (5)Attracting gears : Fishing basket. (6)Cutoff gears : Wall, Screen net, Window net, etc. (7)Guiding gears \circled1Horizontally guiding gears : Triangular set net, Elliptic set net, Rectangular set net, Fish weir, etc. \circled2Vertically guiding gears : Pound net. \circled3Deeply guiding gears : Funnel net. (8)Receiving gears \circled1Jumping - fish receiving gears : Fish - receiving scoop net, Fish - receiving raft, etc. \circled2Drifting - fish receiving gears (a)Set drifting - fish receiving gears : Bamboo screen, Pillar stow net, Long stow net, etc. (b)Movable drifting - fish receiving gears : Stow net. (9)Bagging gears \circled1Drag - bagging gears (a)Bottom - drag bagging gears : Bottom otter trawl, Bottom beam trawl, Bottom pair trawl, etc. (b)Midwater - drag gagging gears : Midwater otter trawl, Midwater pair trawl, etc. (c)Surface - drag gagging gears : Anchovy drag net. \circled2Seine - bagging gears (a)Beach - seine bagging gears : Skimming scoop net, Beach seine, etc. (b)Boat - seine bagging gears : Boat seine, Danish seine, etc. \circled3Drive - bagging gears : Drive - in dustpan net, Inner drive - in net, etc. (10)Surrounding gears \circled1Incomplete surrounding gears : Lampara net, Ring net, etc. \circled2Complete surrounding gears : Purse seine, Round haul net, etc. (11)Covering gears \circled1Drop - type covering gears : Wooden cover, Lantern net, etc. \circled2Spread - type covering gears : Cast net. (12)Lifting gears \circled1Wait - lifting gears : Scoop net, Scrape net, etc. \circled2Gatherable lifting gears : Saury lift net, Anchovy lift net, etc. (13)Adherent gears \circled1Gilling gears (a)Set gilling gears : Bottom gill net, Floating gill net. (b)Drifted gilling gears : Drift gill net. (c)Encircled gilling gears : Encircled gill net. (d)Seine - gilling gears : Seining gill net. (e)Dragged gilling gears : Dragged gill net. \circled2Tangling gears (a)Set tangling gears : Double trammel net, Triple trammel net, etc. (b)Encircled tangling gears : Encircled tangle net. (c)Dragged tangling gears : Dragged tangle net. \circled3Restrainting gears (a)Drifted restrainting gears : Pocket net(Gen - type net). (b)Dragged restrainting gears : Dragged pocket net. (14)Sucking gears : Fish pumps.

• Journal of Korean Society of Forest Science
• /
• v.98 no.6
• /
• pp.696-702
• /
• 2009

Yellow poplar (Liriodendron tulipifera L.) is an insect-pollinated tree species with large, perfect flower, and its seed sets average only about 10 percent naturally. In its controlled pollination, pollination bags are usually taken to prevent unwanted pollination, but bagging is an expensive and time-consuming process. Therefore, this study was conducted to determine the need of pollination bag by estimating how much unintended pollination would occur when different cross methods were applied. Five different pollination methods were applied as follows: 1) natural open pollination (i.e. insect pollination) as a reference, 2) self-pollination; no removing reproductive organs with bagging, 3) open pollination; emasculated(removing sepal, petal and stamen) without bagging, 4) controlled pollination; emasculated with bagging and 5) controlled pollination; emasculated without bagging. Very low value of full seed rate (0.2%) was observed in method 3, it was suggested that removing stamen and petal restrict the activity of pollen vectors like bee. Difference in the full seed rate between method 4 and method 5 was not significant (27.9% versus 24.0%, respectively). Consequently, controlled pollination without bagging might be an alternative method for extensive breeding and mass production of seeds in yellow poplar.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.11
• /
• pp.5427-5445
• /
• 2019

While deep neural networks have achieved remarkable performance in representation learning, a huge amount of labeled training data are usually required by supervised deep models such as convolutional neural networks. In this paper, we propose a new representation learning method, namely generative adversarial networks (GAN) based bagging deep convolutional autoencoders (GAN-BDCAE), which can map data to diverse hierarchical representations in an unsupervised fashion. To boost the size of training data, to train deep model and to aggregate diverse learning machines are the three principal avenues towards increasing the capabilities of representation learning of neural networks. We focus on combining those three techniques. To this aim, we adopt GAN for realistic unlabeled sample generation and bagging deep convolutional autoencoders (BDCAE) for robust feature learning. The proposed method improves the discriminative ability of learned feature embedding for solving subsequent pattern recognition problems. We evaluate our approach on three standard benchmarks and demonstrate the superiority of the proposed method compared to traditional unsupervised learning methods.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.492-494
• /
• 2021

The decision tree technique is used as a classification technique in machine learning. However, the decision tree has a problem of consuming a lot of speed or resources due to the problem of overfitting. To solve this problem, there are bagging and boosting techniques. Bagging creates multiple samplings and models them using them, and boosting models the sampled data and adjusts weights to reduce overfitting. In addition, recently, techniques Xgboost have been introduced to improve performance. Therefore, in this paper, we collect wifi signal data for indoor positioning, apply it to the existing method and Xgboost, and perform performance evaluation through it.

• The Korean Journal of Applied Statistics
• /
• v.18 no.2
• /
• pp.343-354
• /
• 2005

The goal of this paper is to compare classification performances and to find a better classifier based on the characteristics of data. The compared methods are CART with two ensemble algorithms, bagging or boosting and SVM. In the empirical study of twenty-eight data sets, we found that SVM has smaller error rate than the other methods in most of data sets. When comparing bagging, boosting and SVM based on the characteristics of data, SVM algorithm is suitable to the data with small numbers of observation and no missing values. On the other hand, boosting algorithm is suitable to the data with number of observation and bagging algorithm is suitable to the data with missing values.

• Journal of Internet Computing and Services
• /
• v.17 no.2
• /
• pp.49-57
• /
• 2016

Ensemble classification involves combining multiple classifiers to obtain more accurate predictions than those obtained using individual models. Ensemble learning techniques are known to be very useful for improving prediction accuracy. Bagging is one of the most popular ensemble learning techniques. Bagging has been known to be successful in increasing the accuracy of prediction of the individual classifiers. Bagging draws bootstrap samples from the training sample, applies the classifier to each bootstrap sample, and then combines the predictions of these classifiers to get the final classification result. Bootstrap samples are simple random samples selected from the original training data, so not all bootstrap samples are equally informative, due to the randomness. In this study, we proposed a new method for improving the performance of the standard bagging ensemble by optimizing bootstrap samples. A genetic algorithm is used to optimize bootstrap samples of the ensemble for improving prediction accuracy of the ensemble model. The proposed model is applied to a bankruptcy prediction problem using a real dataset from Korean companies. The experimental results showed the effectiveness of the proposed model.