Association rules mining is an important research topic in data mining area, which is successfully applied to commercial domains. For this reason, many approaches are proposed to mine association rules, but little wor...
详细信息
Association rules mining is an important research topic in data mining area, which is successfully applied to commercial domains. For this reason, many approaches are proposed to mine association rules, but little work was done on their maintenance. This paper puts forward an incremental updating algorithm on the basis of FP-tree. Firstly the concept of support function is introduced. Then an incremental updating model is presented, which contains the construction of IFP-tree and IFP-tree growth algorithm. The model considers not only adding new data into the database but also reducing old data from the database. Furthermore, it can predigest five cases to three cases. Finally, some nontrivial experiments are conducted. The results show that IFP-growth algorithm is powerful and efficient, suitable for mining association rules, as well as for some other purposes. Additionally, a small example is presented to illustrate how to define the support function Z and how to develop IFP-tree.
Gnutella protocol simply uses flooding algorithm to route peer's querying, so it has the poor scalability problem. For not using down-layer's routing information of Internet, it also has the common problem tha...
详细信息
Gnutella protocol simply uses flooding algorithm to route peer's querying, so it has the poor scalability problem. For not using down-layer's routing information of Internet, it also has the common problem that its querying routing is just implemented on application layer, and its efficiency is low. The distributions of topology nodes in Gnutella and Internet are reviewed, and they not only exhibit power law and small world properties, but also have the near power-coefficient t. A new distributed peer-to-peer network model based on active network technology (active distributed peer-to-peer network, ADP2PN) is proposed, and its prototype system is implemented. Simulation results about ADP2PN's prototype architecture and querying routing algorithm show that it could effectively resolve the above problems, so the model is reasonable and valid.
We examined several popular indexes of cluster validity and showed the laws that they must obey. A group of new indexes of cluster validity was presented to calculate the lower and upper bound of real cluster number i...
详细信息
We examined several popular indexes of cluster validity and showed the laws that they must obey. A group of new indexes of cluster validity was presented to calculate the lower and upper bound of real cluster number in dataset. The group of indexes of cluster validity can be performed efficiently in dataset with arbitrary-shaped and density-skewed clusters. Two experiments were used to verify the effectiveness of the design in this paper.
Wavelet domain hidden Markov tree (HMT) model can well capture the statistical characteristics of wavelet coefficients, but the comp.tational comp.exity of its training algorithm is high. We presented a new training a...
详细信息
Wavelet domain hidden Markov tree (HMT) model can well capture the statistical characteristics of wavelet coefficients, but the comp.tational comp.exity of its training algorithm is high. We presented a new training algorithm-HMT-based raw segmentation training algorithm for image denoising. By training different HMT models for different types of textures independently, the wavelet coefficient trees are separated into different types according to the textures' HMTs using a maximum likelihood classifier (raw segmentation). By this means, all trees of one type are modeled by one HMT which is initialized by the parameters of the raw segmentation HMT corresponding to the type of texture. For images containing comp.icated scenes or textures, we also presented a simple block-variance-based raw segmentation algorithm which classifies the wavelet coefficient trees according to their corresponding block variance in the original image. Simulations on natural images and SAR (synthetic aperture radar) images indicate that the algorithm performs better than the existing HMT-based algorithms in that its mean square error is smaller and its comp.tational overhead is less.
A kind of brief fuzzy proportional-integral-derivative (PID) control system was developed on the basis of the general fuzzy controller and PID controller. This system was designed on the T-S model. It also overcomes s...
详细信息
A kind of brief fuzzy proportional-integral-derivative (PID) control system was developed on the basis of the general fuzzy controller and PID controller. This system was designed on the T-S model. It also overcomes some difficult problems in nonlinear design and applies the linear system theory to solve the difficult problems in the design of nonlinear system. The design of the fuzzy PID control system was simplified by substituting two planar fuzzy controllers adding integral for three-dimensional fuzzy PID control system. Simulation tests prove that the fuzzy PID control system has a few rules, high stability and brief structure.
The genetic algorithm is an efficient optimization tool for its independence of problems, intrinsic parallelism and inherent learning capacity;however, it has some disadvantages such as slow convergence and prematurit...
详细信息
The genetic algorithm is an efficient optimization tool for its independence of problems, intrinsic parallelism and inherent learning capacity;however, it has some disadvantages such as slow convergence and prematurity. A quantum genetic algorithm (QGA), is proposed based on the combination of the quantum theory with the evolutionary theory. By adopting the qubit chromosome as a representation, QGA can represent a linear superposition of solutions due to its probabilistic representation. The random observation simulating the quantum collapse can bring diverse individuals, and the evolution of quantum chromosome can pilot the evolution. So it has better diversity than the classical genetic algorithm. Rapid convergence and good global search capacity characterize the performance of QGA. The paper proves the global convergence of the QGA, and some simulation experiments show its superiority over other algorithms.
Gather-and-Sift based on DIXON resultant is an effective algorithm for solving nonlinear algebraic equation system. This algorithm is not applied widely because it requires interacting of the expert. The author studie...
详细信息
Gather-and-Sift based on DIXON resultant is an effective algorithm for solving nonlinear algebraic equation system. This algorithm is not applied widely because it requires interacting of the expert. The author studied this algorithm and made two improvements on programming skills in order to solve the problem of lower efficiency when the middle results of DPS are not satisfied. The author developed an automatic software, GAS, by applying the skills. GAS has higher efficiency in solving nonlinear algebraic equation system without any interacting in the whole processing and can be used in real engineering comp.ting.
Based on the optical orthogonal codes, a method for constructing irregular LDPC (low-density parity check) codes was presented. These LDPC codes are quasi-cyclic codes and can be encoded with low comp.exity with a lin...
详细信息
Based on the optical orthogonal codes, a method for constructing irregular LDPC (low-density parity check) codes was presented. These LDPC codes are quasi-cyclic codes and can be encoded with low comp.exity with a linear relationship to code length. These codes have Tanner graphs free of 4-cycles. They perform well with the sum-product iterative decoding. comp.red with random codes and regular LDPC codes based on the optical orthogonal codes with similar parameters, they have decoding performance gains respectively about 0.3 and 0.15 dB when bit error rate is 10-5.
The recent results of research in the field of statistical theory were applied to potential analysis of enhanced oil recovery (EOR). The applications of group method of data handling (GMDH), improved error back propag...
详细信息
The recent results of research in the field of statistical theory were applied to potential analysis of enhanced oil recovery (EOR). The applications of group method of data handling (GMDH), improved error back propagation (BP) artificial neutral network and support vector machine (SVM) to enhanced oil recovery were discussed. The comp.rison of the three methods indicates that SVM has both the universality and the extendibility of a model when the samples are very limited. A small error from an effective training set can guarantee a small error for the corresponding independent testing set. SVM shows a good prospect of its application.
Wireless networks are inherently limited by the bandwidth constraint. MAC protocols for Wireless Local Area Networks (WLANs) play the important role of arbitrating and statistically multiplexing the transmission reque...
详细信息
Wireless networks are inherently limited by the bandwidth constraint. MAC protocols for Wireless Local Area Networks (WLANs) play the important role of arbitrating and statistically multiplexing the transmission requests of various stations contending to access the channel. The performance of IEEE 802.11 degrades in Ad hoc networks because of the presence of hidden and exposed terminals. To counter these problems, we propose a new MAC protocol called Interleaved Carrier Sense Multiple Access (ICSMA) Protocol for Ad hoc wireless networks. The performance of ICSMA was comp.red with single channel 802.11 MAC protocol and with 802.11 MAC protocol over two channels with half the bandwidth through extensive simulation studies. Results show that ICSMA performs better with respect to throughput, access delay, throughput fairness, and delay fairness when comp.red with IEEE 802.11.
暂无评论