Huaping Dai

A rough set based clustering algorithm and the information theoretical approach to refine clusters

In many clustering processes, the presence of more information does not usually generate a corresponding increase in the performance of clustering. The presence of irrelevant information decreases the effectiveness of the clustering algorithm. We propose a solution to improve the quality of clustering that is an attribute-weighted clustering algorithm based on rough set theory and the information theoretical refinement process. Firstly, we give every attribute the same weight value, and use rough set based clustering algorithm to get the initial classes. Then we weigh every attribute by Shannons Entropy Theory, substitute mutual entropy values for the weight of every attribute, and compute with attribute-weighted rough set clustering algorithm again to refine and improve the clustering result. We have tested our algorithm on data sets from UCI repository. The experimental results show that our algorithm can obtain better results in classification rate and purity of classes than other traditional clustering methods.

An algebraic model for performance evaluation of a class of continuous Petri nets

Continuous event graphs (CEGs) are a class of continuous Petri nets. As limiting cases of timed event graphs, CEGs can not only approximately model for the discrete events, but also describe the continuous processes. A set of min-plus linear algebraic equations is inferred as a novel method to study CEGs without input, if treated the cumulated mark consumed by transitions as state-variables. Moreover, the explicit solution of the equations is given. A practical method for CEGs with input is to convert them to a CEG without input via feedback. In the last, a simple example is given to illustrate the feedback control of CEGs with input.

A System Level Low Power Static Real-Time Scheduling Algorithm of Mixed Tasks and Its Application to FTU

FTU (feeder terminal unit) is an important device of distribution automation system, always working in bad environment. Its power dissipation and related thermal issues affect the lifetime of circuit component. When blackout in power grid comes forth, FTU will be working normally powered by the battery. Reducing the power of FTU can increase the normally working time and then increase the power grids reliability. Traditionally, studies on energy reduction techniques of FTU have been conducted in the circuit design. Based on these previous studies, a system level low power static real-time scheduling algorithm of mixed tasks is proposed for FTU in this paper. The simulation experiment shows that this algorithm can decrease the FTU power consumption effectively

A Mathematical Model for Energy-Efficient Coverage and Detection in Wireless Sensor Networks

The tradeoff between system lifetime and system reliability is a paramount design consideration for wireless sensor networks. In order to prolong the system lifetime, random sleep scheme can be adopted without coordinating with its neighboring nodes. Based on the random sleep scheme, an accurate mathematical model for expected coverage ratio and point event detection quality is put forward in this paper. Furthermore, the model also takes the border effects into account and thus improves the accuracy of performance and quality analysis. Our model is flexible enough to capture the interaction among the essential system parameters. Therefore, this model could provide beneficial guidelines for optimal sensor network deployment satisfying both the lifetime and reliability requirements. Additional simulation results confirm the correctness and effectiveness of our analysis.

Studies on the minimum initial marking of a class of hybrid timed petri nets

For the minimum initial marking (MIM) problem is one of minimum resource allocation problems, it is significant to study the MIM problem for a class of hybrid timed Petri nets, called a hybrid timed event graph (HTEG). An HTEG has additional continuous places and continuous transitions than a timed event graph (TEG). By the construction of a new dioid endowed with the pointwise minimum as addition and the composition of functions as multiplication, a linear min-plus algebraic model of HTEG was derived. Based on the min-plus algebra and its properties, the MIM problem for HTEG was studied in the text.

On the evolvement of extended continuous event graphs

Extended Continuous Event Graphs (ECEG) are a special class of Continuous Petri Nets. As the limiting form of Extended Timed Event Graphs (ETEG), ECEGs can be used not only to describe the discrete events approximately, but also to describe the continuous processes. In this note, we obtain some of the global properties of ECEGs. In the end, a simple example is given to illustrate the feedback control of CEGs with input.

Develop multi-hierarchy classification model: rough set based feature decomposition method

Model development on high dimension database is very difficult. This paper presents a new rough set based machine learning method, named feature decomposition method, to discover concept hierarchies and develop a multi-hierarchy model of database. For the databases which we are familiar with, the feature group can be selected by experience of expert. When dealing with the databases without any background knowledge, a new criterion based on rough set is presented to select the features to form a feature group. According to some measures of rough set theory, the objects defined on the proposed feature group are labeled by a new intermediate concept. The concept hierarchies of the database have specific meaning, which increased the transparency of data mining process and enhance the comprehensibility of the model. Each feature group and the corresponding intermediate concept compose the structure of the database. Finally rule induction can be processed on the intermediate concepts. The algorithm presented is verified by datasets from UCI. The results show that the multi-hierarchy model established by feature decomposition method can get high classification accuracy and have better comprehensibility.

A novel feature decomposition method to develop multi-hierarchy model

The comprehensibility of a model is very important since the results should be ultimately be interpreted by a human. This paper presents a new machine learning method, named feature decomposition method based on rough set theory, to discover concept hierarchies and develop a multi-hierarchy model of database. First the features with more relations are selected into a feature group. Then some measures by rough set theory are presented in this paper. According to these measures, the objects defined on the proposed feature group are labeled to discover a new concept. The new concept hierarchies of the database usually have specific meaning, which increase the transparency of data mining process. Finally the rule induction can process on the concept hierarchies of the database to develop a new multi-hierarchy model. The idea presented is illustrated with examples and datasets from UCI machine learning repository. The results show that the multi-hierarchy model established by feature decomposition method can get high classification accuracy and have better comprehensibility.

Application of multivariable feedback linearization for paper machine pressurized head box control

This paper investigates application of a multivariable control technique to the multi-input multi-output (MIMO) nonlinear model of the paper machine pressurized head box. The proposed controller design is based on a feedback linearization and LQ optimization method. The method can stabilize the system at operating point. In the last, we simulated the performance of pressurized head boxes with the new controller.

A novel approach to analyzing and designing time problems of sequential circuits

Sequential circuit design technology is the base of digital circuit design such as programmable logic device and micro-controller interface. The sequential circuit design includes two basic problems: logic synthesis and time problems. Usually the digital circuit text introduces logic synthesis, but until now there is no systemic theory to study time problems. The following text would put forward a max-plus algebra based analyzing and designing method for time problems. This is a novel systemic theory to compute the time parameters of sequential circuit. In the end, a simple example would show the design process of the new method.