**Author details**

**5. Conclusion**

**Table 3.**

**100**

**Dataset** *hci***(***t***)** *h*<sup>0</sup>

*Sustainability in Urban Planning and Design*

This chapter proposes the parameter for adjustment of the Gaussian symmetric neighborhood function. Our parameter adjusting method can reduce both *QE* and *TE* of the feature map. However, the value of parameter must be determined individually for each specific dataset. The improved Gaussian function is better than the original Gaussian function and some other neighborhood functions like

*ci***(***t***) Bubble function Asymmetric neighborhood function**

XOR 0.1890 0.1585 0.2572 0.1808

Aggregation 5.9702 2.9340 7.3092 4.9466

Flame 2.1839 1.1822 2.6352 2.1916

Pathbased 4.5859 2.4779 5.524 5.3888

Spiral 4.7595 3.4675 5.6515 4.3775

Jain 5.2745 2.3559 6.3026 5.4962

Compound 4.4205 3.7595 5.5663 3.5529

R15 2.2226 1.4606 2.5017 1.8911

D31 4.7676 2.4569 5.6095 5.958

Iris 0.7709 0.6430 1.001 0.9284

Vowel 2.7459 2.3755 3.1022 2.8808

Zoo 1.5841 1.0912 1.7182 1.7179

0.0318 0.0223 0.2708 0.4635

0.0549 0.0245 0.1794 0.4476

0.0700 0.0393 0.1642 0.6828

0.0561 0.0315 0.1981 0.2715

0.0543 0.0284 0.1502 0.6306

0.0513 0.0269 0.2024 0.3172

0.0624 0.0299 0.2199 0.4349

0.0722 0.0274 0.1384 0.6337

0.0479 0.0207 0.2054 0.3506

0.0739 0.0548 0.2312 0.2610

0.0537 0.0412 0.1872 0.3965

0.0343 0.0104 0.2182 0.2210

Bubble function, asymmetric neighborhood function.

*Compares measures QE, TE of some neighborhood functions.*

Le Anh Tu Halong University, Vietnam

\*Address all correspondence to: anhtucntt@gmail.com

© 2019 The Author(s). Licensee IntechOpen. This chapter is distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/ by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
