A joint generalized exemplar method for classification of massive datasets

Tağluk, M. Emin; Ertuğrul, Ömer Faruk

doi:10.1016/j.asoc.2015.07.044

Cited by 4 publications

(4 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Since samples belonging to these datasets were randomly generated based on the distributions, a fair comparison cannot be made between the achieved accuracies in this study and reported accuracies in the literature. However, similar accuracies were reported with synthetic datasets [26]. The Pima Indian Diabetes dataset was employed in many papers as a benchmark dataset and accuracies reported with ANNs trained by ELM, SVM, NB, and generalized behavioral learning methods were 77.57% [31], 76.50% [50], 64.60% [51], and 65.23% [52], respectively.…”

Section: Batch Datasetsmentioning

confidence: 65%

“…In order to confirm the traditional condensing by clustering approach, synthetic datasets, which have different statistical distributions [26] (as seen in Figure 1), were generated by prtools [27] and employed in experiments. In addition to these synthetic datasets, to increase the cogency some real benchmark datasets were also employed and the properties of all employed batch datasets are summarized in Table 1.…”

Section: Batch Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

A novel approach for extracting ideal exemplars by clustering for massivetime-ordered datasets

Ertuğrul¹

2017

Turk J Elec Eng & Comp Sci

Self Cite

View full text Add to dashboard Cite

Abstract:The number and length of massive datasets have increased day by day and this yields more complex machine learning stages due to the high computational costs. To decrease the computational cost many methods were proposed in the literature such as data condensing, feature selection, and filtering. Although clustering methods are generally employed to divide samples into groups, another way of data condensing is by determining ideal exemplars (or prototypes), which can be used instead of the whole dataset. In this study, first the efficiency of traditional data condensing by clustering approach was confirmed according to obtained accuracies and condensing ratios in 9 different synthetic or real batch datasets. This approach was then improved to be employed in time-ordered datasets. In order to validate the proposed approach, 23 different real time-ordered datasets were used in experiments. Achieved mean RMSEs were 0.27 and 0.29 by employing the condensed (mean condensed ratio was 97.17%) and the whole datasets, respectively. Obtained results showed that higher accuracy rates and condensing ratios were achieved by the proposed approach.

show abstract

Section: Batch Datasetsmentioning

confidence: 65%

Section: Batch Datasetsmentioning

confidence: 99%

A novel approach for extracting ideal exemplars by clustering for massivetime-ordered datasets

Ertuğrul¹

2017

Turk J Elec Eng & Comp Sci

Self Cite

View full text Add to dashboard Cite

show abstract

“…Dünyada ve ülkemizde akıllı şebeke ve mikro şebeke kullanılarak YEK aracılığıyla enerji verimliliğine katkı sağlayacak birçok çalışma yapılmaktadır [20,21]. Bu amaçla güneş enerjisinden maksimum düzeyde faydalanmak amacıyla yenilenebilir enerji kaynaklarının sanayi tesislerinde kullanımına yönelik araştırmalar artmaktadır [22][23][24]. Özellikle sanayi tesislerinde filtreleme yöntemleriyle ve motor, pompa, kompresör gibi tüketimi yüksek olan cihazların tasarruflu kullanımı için yapılmış birçok çalışmada yeni verimlilik önerilerine yer verilmektedir.…”

Section: Türkiye Ve Güneşten Elektrik üRetim Teşvikleriunclassified

Termal Güneş Enerjisi Kullanımı ve CSP Sistemlerin Verimlilik Analizi

Cengiz¹,

Mamiş²

2016

Bitlis Eren Üniversitesi Fen Bilimleri Dergisi

View full text Add to dashboard Cite

ÖzetTüm dünyada olduğu gibi ülkemizde de enerji önemli bir sorundur. Ülkemiz fosil enerji kaynakları bakımından yetersiz rezervlere sahip olduğundan enerjide dışa bağımlıdır. Ancak güneş enerjisi (GE) açısından ülkemiz zengin kaynaklara sahiptir. Avrupa Birliği (AB) ülkeleri, tüketicileri için güneşten elektrik enerjisi üretiminde bilinçlendirme çalışmaları yaparak teşvikler aracılığıyla GE kullanımını yaygınlaştırmaya çalışmaktadır. Ülkemizde ise bilinçlendirme ve teşvik çalışmalarına gerektiği kadar önem verilmemektedir. Bu çalışmada ülkemiz ve Dünya ülkelerinin GE potansiyeli karşılaştırılarak kısa vadede yapılabilecek GE yatırımları, kamu tarafından verilebilecek teşvikler ve ekonomik anlamda ülkeye sağlayacağı katkılar incelenmiştir. Avrupa'da son 10 yılda CSP sistemleriyle ısı kaynaklı GE'den faydalanarak atılım yapan ve bu alanda Dünya 4.'sü olan İspanya örneğinin Türkiye için model olabileceğine dair değerlendirmelere yer verilmiştir. Sonuç olarak CSP sistemlerinden bireysel elektrik enerjisi üretimi ve kullanımına uygun olan Stirling Motorlu Güneş Takip Sistemlerinin (SMGTS) ülkemizde yaygınlaştırılmasının gerekliliğine dair analiz ve değerlendirmeler yapılmıştır.Anahtar Kelimeler: Konsantre güneş enerji sistemleri, termal güneş enerjisi, güneş potansiyeli Thermal Solar Energy Use and Efficiency Analysis of CSP Systems AbstractEnergy is an important problem in Turkey as well as the whole world. Since Turkey has insufficient sources in terms of fossil energy sources, it is dependent on foreign. However, Turkey has rich resources in terms of solar energy (SE). The European Union countries (EU) try to generalize solar energy through promotions performing studies for raising awareness for generation of electricity from the sun. In Turkey, required importance is not given to the studies to raise the awareness and promotions. In this study, the SE investments that will be made in the long turn, the promotions that can be given by the public and the economic contributions made to the country are examined by comparing the SE potential of the world countries. Assessments on the fact that Spain, as a sample, which has made a move benefitting from heat source SE with CSP systems in the last decade and which ranks the 4th in this field in the world can be a model for Turkey is included. As a result, analysis and assessments have been made on that Stirling Engine Solar Tracking Systems that are appropriate for using and generating electricity individually among CSP systems should be generalized in Turkey.

show abstract

“…To comparatively evaluate the proposed approach, FM and WM were performed on real world data sets of different specifications [23][24][25][26][27][28][29][30], and were analyzed in terms of both accuracy and computational cost. The motivation behind the use of WM was the success of the best accuracy [17].…”

Section: Employed Proceduresmentioning

confidence: 99%

A fast feature selection approach based on extreme learning machine and coefficient of variation

Ertuğrul¹,

Tağluk²

2017

Turk J Elec Eng & Comp Sci

Self Cite

View full text Add to dashboard Cite

Abstract:Feature selection is the method of reducing the size of data without degrading their accuracy. In this study, we propose a novel feature selection approach, based on extreme learning machines (ELMs) and the coefficient of variation (CV). In the proposed approach, the most relevant features are identified by ranking each feature with the coefficient obtained through ELM divided by CV. The achieved accuracies and computational costs, obtained with the use of features selected via the proposed approach in 9 classification and 26 regression benchmark data sets, were compared to those obtained with all features, as well as those obtained with the features selected by a wrapper and a filtering method. The achieved accuracy values obtained with the proposed approach were generally higher than when using all features. Furthermore, high feature reduction ratios were obtained with the proposed approach, including the achieved feature reduction ratios in epilepsy, liver, EMG, shuttle, and abalone. Stock data sets were 90.48%, 90%, 70.59%, 66.67%, 75%, and 77.78%, respectively. This approach is an extremely fast process that is independent of the employed machine-learning methods.

show abstract

A joint generalized exemplar method for classification of massive datasets

Cited by 4 publications

References 38 publications

A novel approach for extracting ideal exemplars by clustering for massivetime-ordered datasets

A novel approach for extracting ideal exemplars by clustering for massivetime-ordered datasets

Termal Güneş Enerjisi Kullanımı ve CSP Sistemlerin Verimlilik Analizi

A fast feature selection approach based on extreme learning machine and coefficient of variation

Contact Info

Product

Resources

About