In Defense of Online Kmeans for Prototype Generation and Instance Reduction

Minimizing of foaming in digesters by pre-treatment of the surplus-sludge

Water Science & Technology ◽

10.2166/wst.2000.0215 ◽

2000 ◽

Vol 42 (9) ◽

pp. 235-241 ◽

Cited By ~ 31

Author(s):

M. Barjenbruch ◽

H. Hoffmann ◽

O. Kopplow ◽

J. Tränckner

Keyword(s):

High Pressure ◽

Activated Sludge ◽

Treatment Methods ◽

Foaming Agents ◽

Instance Reduction ◽

Filamentous Microorganisms ◽

Hydrophobic Substances ◽

Pre Treatment ◽

Heating Up ◽

The Impact

Several reasons can lead to the emergence of foam in digesting tanks, for instance overloading or the impact of hydrophobic substances. Furthermore, the foaming is in regular periods going together with the emergence of filamentous microorganisms. Up to now, several strategies to avoid foaming have been tested out (for instance reduction of the sludge load in the activated sludge stage, lowering of the sludge level in the digestion tank, dosage of anti foaming agents), but these have been done relatively unsystematically and with more or less success. For our contribution, laboratory-scale digestion tests were run to analyse mechanical and thermal pre-treatment methods for the destruction of the surplus sludge. Whereas the disintegration by a high pressure homogeniser did only achieve a low reduction of the foam phase, the thermal pre-treatment at 121°C made for an effective subduing of the foam emergence. Both methods allowed for a cutting up of the filaments, but only the heating up effected the reduction of the hydrophobic substances; thus, the foaming is possibly caused by them.

Download Full-text

Family of Instance Reduction Algorithms Versus Other Approaches

Advances in Soft Computing - Intelligent Information Processing and Web Mining ◽

10.1007/3-540-32392-9_3 ◽

2006 ◽

pp. 23-30 ◽

Cited By ~ 2

Author(s):

Ireneusz Czarnowski ◽

Piotr Jędrzejowicz

Keyword(s):

Instance Reduction

Download Full-text

Instance Reduction for Time Series Classification by Exploiting Representative Characteristics using k-means

Lecture Notes in Computer Science - Integrated Uncertainty in Knowledge Modelling and Decision Making ◽

10.1007/978-3-319-49046-5_19 ◽

2016 ◽

pp. 217-229

Author(s):

Vo Thanh Vinh ◽

Hien T. Nguyen ◽

Tin T. Tran

Keyword(s):

Time Series ◽

Time Series Classification ◽

Instance Reduction

Download Full-text

Natural Neighbor Reduction Algorithm for Instance-based Learning

International Journal of Cognitive Informatics and Natural Intelligence ◽

10.4018/ijcini.2016100103 ◽

2016 ◽

Vol 10 (4) ◽

pp. 59-73 ◽

Cited By ~ 2

Author(s):

Lijun Yang ◽

Qingsheng Zhu ◽

Jinlong Huang ◽

Dongdong Cheng ◽

Cheng Zhang

Keyword(s):

Classification Accuracy ◽

Hybrid Approach ◽

Reduction Algorithm ◽

Storage Space ◽

Computational Costs ◽

Condensation Method ◽

Instance Reduction ◽

Instance Based Learning ◽

Natural Neighbor ◽

Competitive Algorithms

Instance reduction is aimed at reducing prohibitive computational costs and the storage space for instance-based learning. The most frequently used methods include the condensation and edition approaches. Condensation method removes the patterns far from the decision boundary and do not contribute to better classification accuracy, while edition method removes noisy patterns to improve the classification accuracy. In this paper, a new hybrid algorithm called instance reduction algorithm based on natural neighbor and nearest enemy is presented. At first, an edition algorithm is proposed to filter noisy patterns and smooth the class boundaries by using natural neighbor. The main advantage of the algorithm is that it does not require any user-defined parameters. Then, using a new condensation method based on nearest enemy to reduce instances far from decision line. Through this algorithm, interior instances are discarded. Experiments show that the hybrid approach effectively reduces the number of instances while achieves higher classification accuracy along with competitive algorithms.

Download Full-text