Improving the Input of Classified Neural Networks Through Feature Construction

A general classification algorithm of neural networks is unable to obtain satisfied results because of the uncertain problems existing among the features in moot classification programs, such as interaction. With new features constructed by optimizing decision trees of examples, the input of neural networks is improved and an optimized classification algorithm based on neural networks is presented. A concept of dispersion of a classification program is also introduced too in this paper. At the end of the paper, an analysis is made with an example.

Smart Grid Construction with Chinese Features

The construction of smart grids has started in China. In early October 2009, the editorial department of Electricity carried out an exclusive interview with Mr. Wang Yimin, Director of the Department of Smart Grid, SGCC, about this program.

Enlightenment from the Construction of American Botanic Gardens:A Case Study of The Morton Arboretum

Starting from reviewing the current development of botanic gardens in China,the shortcomings of current research on botanical gardens in China are summarized:the research and construction concepts of the botanical gardens lack professional characteristics;the education and science popularization system is extensive;and the investment and construction model and operation and management method are relatively rigid.Through combing the development history of The Morton Arboretum and introducing its construction features,such as the long-term garden-establishing idea with a high starting point,continuously building and improving for a long time to actively adapt to changes in social needs,a refi ned education and science popularization system for various groups,and a strong self-hematopoietic function,the successful construction experience of The Morton Arboretum is elaborated and the enlightenment from The Morton Arboretum to the construction of botanic gardens China are put forward,so as to provide a reference for the construction and development of botanic gardens in China in the new period.

Subdivision surface modeling system based on arbitrary topological curves network and combined subdivision

Arbitrary topological curve network has no restriction in topology structure,so it has more powerful representing ability in defining complex surfaces.A complex surface modeling system is presented based on arbitrary topological curve network and the improved combined subdivision method,its functions including creating and editing curve network,and generating and modifying curve network＇s interpolated surface.This modeling system can be used to the process of products＇concept design,and its applications is also significant to the development of subdivision method.

Synthesis and Microstructure Analysis of Autoclaved Aerated Concrete with Carbide Slag Addition

Synthesis of autoclaved aerated concrete （AAC） has been carried out with carbide slag addition, and the carbide slag could be used as a main material to produce the AAC with the compressive strength about 2 MPa and the density below 0.6 g.cm-3. In this study, quartz sand acted as frame structure phase in the matrix, and quartz addition also influenced the Si/Ca of starting material. Tobermorite and CSH gel were formed readily at 62%, which seemed to enhance the compressive strength of samples. Curing time seemed to affect the morphology of phase produced, and specimen with the plate-like tobermorite formed at 10 h appeared to have a better compressive strength development than the fiber-like one at 18 h. The higher curing temperature seemed to favor the tobermorite and CSH gel formation, which also exerted a significant effect on the strength development of the samples. On the micro-scale, the formed CSH gel was filled in the interface of the matrix, and the tobermorite appeared to grow in internal-surface of the pores and interstices. The tobermorite or/and CSH formation seemed to densify the matrix, and therefore enhanced the strength of the samples.

Research on synchronous gear pump

Based on a comprehensive analysis of the structure and existing problems ofthe gear pump, provided a structure principle of a synchronous gear pump.The discussionsfocused on the working principle, construction features and finite element analysis ofthe hydraulic gear.The research indicates that the new pump has such advantages aslower noise, better distributed flow and a high work pressure, and it can be widely used inhydraulic systems.

Jiangsu Issues Action Plan for Featured Countryside Construction of Jiangsu Province

To promote the level of rural construction,the provincial party committee and the provincial government of Jiangsu officially issued the Action Plan for Featured Countryside Construction of Jiangsu Province on Jun.20,2017.The Plan proposed that,by sticking to the principles of innovation,coordination,green,open,and sharing,and in line

A New Road Extraction Method from Satellite Images Using Genetic Programming

Extracting roads from satellite images is an important task in thefield of computer vision with a wide range of applications.However,efficient road extraction from satellite images remains a complex challenge due to issues such as data labeling and the diversity of road features.Existing methods often struggle to balance accuracy,robustness,and interpretability.Genetic programming(GP)is based on aflexible and interpretable structure that is robust and does not require a large amount of data support.We position the road extraction problem as a binary semantic segmentation task and introduce GP algorithms.First,an approach for extracting pixel neighborhood features is proposed,and features from multiple images in the DeepGlobe road extraction dataset are extracted.Then,an advanced feature construction method based on GP is employed.Finally,these advanced features are utilized for training classifier and classi-fication to achieve road extraction.We have validated the effectiveness of the approach on the DeepGlobe road extraction dataset.The results demonstrated that the proposed approach exhibits superior performance compared to traditional classification methods and multilayer perceptron(MLP)in terms of accuracy,generalization,and interpretability.This study provides a valuable reference for the integration of GP into the domain of road extraction from satellite images,showcasing their potential to enhance the accuracy and efficiency.