Huamao Gu’s research while affiliated with Zhejiang Gongshang University and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (11)


A Preliminary Geometric Structure Simplification for Principal Component Analysis
  • Article

November 2018

·

10 Reads

·

1 Citation

Neurocomputing

Huamao Gu

·

·

Xun Wang

Real world data are commonly geometrically nonlinear and thus are not easy to be processed by the traditional linear methods. Many existing techniques for nonlinear dimensionality reduction need careful parameter tuning and cannot be applied to real data stably and consistently. In this article we propose an efficient data preprocessing algorithm, called Curve Straightening Transformation (CST), to flatten the nonlinear geometric structure of data. Then Principal Component Analysis (PCA) and other linear projection methods are adequate to perform the dimensionality reduction task in most cases. In this aspect, the proposed CST algorithm can be regarded as a geometric preprocessing step tailored for PCA. The comprehensive experiments on both artificial and real datasets demonstrate that the proposed preprocessing algorithm is able to simplify the nonlinear geometric structures, and the flattened data are suitable for further dimensionality reduction by linear methods such as PCA.


Manifold Learning by Curved Cosine Mapping

July 2017

·

39 Reads

·

5 Citations

IEEE Transactions on Knowledge and Data Engineering

Huamao Gu

·

Xun Wang

·

Xuewen Chen

·

[...]

·

Jinqin Shi

In the field of pattern recognition, data analysis and machine learning, data points are usually modeled as high-dimensional vectors. Due to the curse-of-dimensionality, it is non-trivial to efficiently process the orginal data directly. Given the unique properties of nonlinear dimensionality reduction techniques, nonlinear learning methods are widely adopted to reduce the dimension of data. However, existing nonlinear learning methods fail in many real applications because of the too-strict requirements (for real data) or the difficulty in parameters tuning. Therefore, in this paper, we investigate the manifold learning methods which belong to the family of nonlinear dimensionality reduction methods. Specifically, we proposed a new manifold learning principle for dimensionality reduction named Curved Cosine Mapping (CCM). Based on the law of cosines in Euclidean space, CCM applies a brand new mapping pattern to manifold learning. In CCM, the nonlinear geometric relationships are obtained by utlizing the law of cosines, and then quantified as the dimensionality-reduced features. Compared with the existing approaches, the model has weaker theoretical assumptions over the input data. Moreover, to further reduce the computation cost, an optimized version of CCM is developed. Finally, we conduct extensive experiments over both artificial and real-world datasets to demonstrate the performance of proposed techniques.


Deciding the SHOQ(D)-Satisfiability with a Fully Tiered Clause Group

February 2012

·

35 Reads

Journal of Software

SHOQ(D) is one of the fundamental theories In Description Logics due to its support to concrete datatypes and named individuals. At present, deciding the satisfiability of SHOQ(D)-concepts is mainly completed by enhancing Tableau algorithm with blocking. However, there is still much to be desired in performance as there are tremendous description overlaps in completion forest, thus causing great spatial waste as a result. To tackle this problem, this paper presented a new approach to check the satisfiability of acyclic SHOQ(D)-concepts——FTC(Fully Tiered Clauses) algorithm. This calculus can make a direct judgement on the satisfiability of acyclic SHOQ(D)-concept by translating its description into a fully tiered clause group whose satisfiability is directly available, and reusing clauses to block unnecessary extensions. FTC algorithm eliminates description overlaps to the largest extent as it works on concept description directly. Therefore, FTC algorithm has notably better performance than Tableau by saving a lot of spatial costs.


The Differential Degree Test: a Novel Methodology for Electronic Tongue Applications

January 2012

·

48 Reads

·

2 Citations

Sensors and Materials

A novel methodology for electronic tongue applications based on the differential degree test was proposed in this study. Five basic tastes, namely, sour, sweet, bitter, salty, and umami, were detected by a novel voltammetric electronic tongue. Results proved that the differential degree test is applicable to intelligent instruments, and the Dd (differential degree) value was confirmed to be the most useful to distinguish the differences between samples quantitatively. At the same time, the theoretical foundation for electronic tongue applications was advanced. The Dd value is proportional to the logarithm of concentration (r > 0.98), and the sensors' responses to the stimulus were similar to Fechner's law in the field of psychophysics. On the basis of these results, the Dd value was applied for the quantitative distinction of Chinese rice wine of different ages (1, 3, 5, and 8 years); the Dd value increased with age. In addition, the changing quality of an orange juice beverage was indicated by the D d value; the electronic tongue proved useful in quality control.


Determining the SHOIN(D)-Satisfiability with a Complete Disjunctive Normal Form Group

August 2010

·

26 Reads

Journal of Software

This paper presents an approach to check the satisfiability of acyclic SHOIN(D)-concepts-CDNF (complete disjunctive normal form) algorithm. This calculus can make a direct judgment on the satisfiability of acyclic SHOIN(D)-concept by restructuring it into a hierarchical disjunctive normal form group on concept descriptions which is satisfiability self-telling, and reusing description clauses to block unnecessary extensions. CDNF algorithm eliminates description overlaps to the largest extent for it works on concept description directly. Therefore, CDNF algorithm has much better performance than Tableau as it saves a lot of spatial and temporal costs. © by Institute of Software, the Chinese Academy of Sciences. All rights reserved.


Automated Negotiation Decision Model Based on Machine Learning

October 2009

·

14 Reads

·

6 Citations

Journal of Software

The proposed model labels the negotiation history data automatically by making full use of the implicit information in negotiation history. Then, the labeled data become the training samples of least-squares support vector machine that outputs the estimation of opponent's utility function. After that, the self's utility function and the estimation of opponent's utility function constitute a constraint optimization problem that will be further figured out by genetic algorithm. The optimal solution is the counter-offer of oneself. Experimental results show that the proposed model is effective and efficient in environments where information is private and the prior knowledge is not available. © by Institute of Software, the Chinese Academy of Sciences. All rights reserved.


An Ontology-Based Development Framework for Edutainments

December 2008

·

5 Reads

·

2 Citations

Although there are many edutainments in market yet, they are still not popular among school teaching due to the game developers’ lack of teaching experience. This paper proposed a concept of “made by teacher” in game development, and presented an Ontology-based Edutainment Development Framework (OEDF) that assists teachers to design easily educational games at their wills. In OEDF, Ontology is employed to structure the sharable knowledge of game industries and the knowledge in textbooks. Moreover, this framework has been implemented in ParaEngine, a simple yet comprehensive and distributed 3D online game engine. Besides, the developing procedure for educational game under the OEDF framework is also provided. At the same time, a segment of an educational game has been developed based on the OEDF framework.


Negotiation decision model based on learning of opponent's attitudes

October 2008

·

13 Reads

·

7 Citations

Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science Edition

A support vector machine (SVM) based method was proposed to learn opponent's attitudes to solve the problem of bilateral automated negotiation in agent mediated application. The procedure of negotiation was viewed as a proposals' sequence which can be transformed to multiple negotiation tracks-one negotiation track for each negotiation issue-by mapping them to a new feature space. Then the opponent's attitude of each issue can be got by learning the negotiation tracks. A negotiation decision making model was constructed by utilizing the opponent's attitude. The model can make effective trade offs between opponent's attitudes and self's preferences. If the model's function constraints to some condition, the convergence and monotonic of model can be promised. Experimental results show that the model can decrease negotiation time and increase the total utility of negotiation participants.


Task Oriented Web Service Requirement Framework

November 2007

·

17 Reads

·

1 Citation

Aiming to overcome the mismatch between coarse grain of Web service's functions and fine grain of current Web service requirements with inputs and outputs as functional requirements, a three layer task oriented Web service requirement framework is proposed. The top the is task layer which defines the tasks and their relationships, the middle is the method layer which represents multiple implementations of the primitive task, and the low is the operation layer which represents the abstract features of typical operations that a method owns. The task oriented Web service requirement framework proposed well matches the coarse grain feature of Web service's functions and provides a more natural way to express the service requirements.


Fig. 1: A FCR relation between concepts A and B with a membership degree of md. Circles designate concepts, while squares denote individuals. Dotted lines mean associations between individuals with a same membership degree md.  
Towards a General Fuzzy Ontology and Its Construction
  • Article
  • Full-text available

October 2007

·

119 Reads

·

10 Citations

International Journal of Computational Intelligence Systems

Most of the current fuzzy ontologies are too domain-specific and don't support reasoning on fuzzy descriptions. By investigating the uncertainty information in the real world, we discover three widely existing general fuzzy relations. Based on such investigation and motivated by the desire to support reasoning and guide fuzzy ontology construction, we propose a reasoning-enabled general fuzzy ontology including these general fuzzy relations. To support such ontology in theory, we introduce a fuzzy description logic ef-SHIN, and define its syntax and semantics. Besides, a reference process for guiding the construction of fuzzy concept base relations in fuzzy ontology is also presented.

Download

Citations (8)


... The precision of hyperspectral inversion for the soil Cu content is influenced not only by the spectral preprocessing but also by dimensionality reduction method [56][57][58][59][60][61][62]. A suitable combination of spectral preprocessing and dimensionality reduction can improve the accuracy and performance of the inversion model. ...

Reference:

On Optimizing Hyperspectral Inversion of Soil Copper Content by Kernel Principal Component Analysis
A Preliminary Geometric Structure Simplification for Principal Component Analysis
  • Citing Article
  • November 2018

Neurocomputing

... For data with nonlinear structures, non-linear subspace learning algorithms are required, such as manifold learning methods [7,13] or kernel based subspace learning algorithms [8,14]. Manifold learning methods assume that the highdimensional data lie on a low-dimensional manifold, and explore the local or global data manifold structure information by manifold assumption Kernel based subspace learning methods [5,6] map high-dimensional data to a Reproducing Kernel Hilbert Space (RKHS) through kernel function to reduce the nonlinearity of data, and learning a linear subspace learning in RKHS. ...

Manifold Learning by Curved Cosine Mapping
  • Citing Article
  • July 2017

IEEE Transactions on Knowledge and Data Engineering

... Furthermore, how to learn fuzzy datatypes is not addressed, and fuzzy axioms are not allowed. Gu et al. pointed out the need to build a fuzzy matrix with the degrees of truth of the relationships between pairs of concepts (for example, fuzzy subclass axioms), but do not detail how to compute the degrees (Gu et al., 2007). ...

Towards a General Fuzzy Ontology and Its Construction

International Journal of Computational Intelligence Systems

... Therefore, agents only know their negotiation information, which is impossible to make a win-win counter-proposal. There is a lot of literature on promoting negotiation [5][6][7][8][9][10][11]. Zheng [6] propose a tri-training based algorithm to learn the opponent's negotiation preference. ...

Negotiation decision model based on learning of opponent's attitudes
  • Citing Article
  • October 2008

Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science Edition

... Therefore, agents only know their negotiation information, which is impossible to make a win-win counter-proposal. There is a lot of literature on promoting negotiation [5][6][7][8][9][10][11]. Zheng [6] propose a tri-training based algorithm to learn the opponent's negotiation preference. ...

Automated Negotiation Decision Model Based on Machine Learning
  • Citing Article
  • October 2009

Journal of Software

... In this case, the design as well as the balance of gameplay and education are vital in order to keep the players motivated for playing and learning. In order to make full use of edutainment, learning and gaming should be blended harmoniously [72]. On the one hand, this means to involve teachers in the design of educational games. ...

An Ontology-Based Development Framework for Edutainments
  • Citing Article
  • December 2008

... In the general information domain, Chaolin et al. (2005) presented a method for distributing and managing tasks in the environment of the grid computing, and the task is the practical computing mission there. Others' work have investigated the separation of tasks and Web Services (Gorton and Reiff- Marganiec, 2006; Cardoso et al., 2004; Yu et al., 2007), in which business goals are achieved using tasks, and tasks are executed Table 1 Services involved in the flood example. ...

Task Oriented Web Service Requirement Framework
  • Citing Conference Paper
  • November 2007