This paper presents a novel parallel neural network clustering approach based Particle Swarm Optimisation (PSO) for the large spatial database suitable in data mining. A large number of pieces of evidence are clustere...
详细信息
In wireless sensor network, in-network data aggregation can eliminate redundancy, improve data accuracy and thus prolong the lifetime of network. However, most of data aggregation technologies assumed that the aggrega...
In wireless sensor network, in-network data aggregation can eliminate redundancy, improve data accuracy and thus prolong the lifetime of network. However, most of data aggregation technologies assumed that the aggregator node has been receiving all the data when it performers the aggregation operation, these methods give larger latency to the transmission of network's data and affect the accuracy of network. Therefore, this paper presents a new data aggregation technology, conjiguring carefilly the aggregator node's timeouts through making use of a new aggregation timing control scheme, which is to achieve a good trade-off between energy efficiency and data accuracy.
Evaluating the combat effectiveness of electronic equipment is an important research task. Due to the incomplete information, the data which is used for effectiveness evaluation is regarded as the uncertain grey numbe...
详细信息
The paper addresses the problem of scheduling tasks represented by a directed acyclic graph (DAG) on distributed environments. Due to the task, communication and resource constraints, the resource matching and task sc...
详细信息
According to the characteristics of spiral mining head for deep seabed cobalt-rich crust, the kinematic model, cutting loads model, quantity of cutting picks model of mining head, granularity distribution model and en...
详细信息
According to the characteristics of spiral mining head for deep seabed cobalt-rich crust, the kinematic model, cutting loads model, quantity of cutting picks model of mining head, granularity distribution model and energy consumption model were constructed. Based on these models, computer simulation program of cutting loads was developed with VB software. The mechanical parameters of mining head were obtained in the cutting depth range of 5160 mm. Making use of the simulation results, the effect of cutting depth of spiral mining head on the mining process was studied. The results show that the maximum force of single pick is 4.7051kN, the maximum force and torque of spiral drum of mining head are respectively 34.1668kN and 3.8795kN·m at the cutting depth of 160mm.
This paper proposes a prediction approach that combines grey prediction model with three-layer computing architecture in Web environment. It presents a refined prediction formula to enhance the scalability and usage s...
This paper proposes a prediction approach that combines grey prediction model with three-layer computing architecture in Web environment. It presents a refined prediction formula to enhance the scalability and usage scope of the Web prediction systems. It layouts a three layer architecture for the Web prediction system to reduce the network traffic and maintain load balance. A traffic decision support system is presented to illustrate the proposed approach.
Fault detection and diagnosis (FDD) are increasingly important for wheeled mobile robots (WMRs), especially those in unknown environments such as planetary exploration. There are many kinds of fault diagnosis methods ...
详细信息
Data mining as a novel approach has been widely applied to intrusion detection, selecting an appropriate representation to extract the most significant feature is very important, and the algorithm of pattern classific...
详细信息
Data mining as a novel approach has been widely applied to intrusion detection, selecting an appropriate representation to extract the most significant feature is very important, and the algorithm of pattern classification is also crucial. This paper describes a new support vector machine (SVM) for anomaly intrusion detection idea based on latent semantic indexing (LSI). The proposed method can generate features in LSI method by singular value decomposition (SVD). SVD as preprocessing step can reduce the dimensionality and remove the noise in the raw data matrix. The computation complexity is also greatly degraded. SVM has been proved that have a good performance for classification. We performed SVM on the new feature space obtained by SVD, the redial basis function (RBF) is chosen as our kernel function. Our experiments performed on PARPA'98 BSM data set show that our approach can lead to a higher detection rate and a lower false positive rate, it is an effective and efficient methods. In particular, LSI technique can lead to a greatly reduction of the computation complexity and CPU-time
A new conception of full digital control and amplifier system for magnetic levitating bearing is described. It needs good performances such as high control precision, fast response, low noise and high stability, so ma...
详细信息
A new conception of full digital control and amplifier system for magnetic levitating bearing is described. It needs good performances such as high control precision, fast response, low noise and high stability, so magnetic levitating bearing control and amplifier system is a real time multi-spots harmonious intellectualized system. In this paper, a switching strategy is described for the magnetic levitating bearing mode of operation. A control strategy is then proposed which introduces a multiple parameters PI and PID arithmetic in the control law. The arithmetic is smart in the sense that it is a function of the rotor states, and varies in a manner that reduces the system power losses and avoids control singularities. The experimental result shows that the DSP-based system features very well
In this paper, a structure health monitor (SHM) system for the bridge is introduced, of which wireless communication and embedding techniques are deployed. After summing up the wireless communication techniques and ti...
详细信息
In this paper, a structure health monitor (SHM) system for the bridge is introduced, of which wireless communication and embedding techniques are deployed. After summing up the wireless communication techniques and time synchronization requirements in practical application, a data transfer protocol based on clock synchronization and reliability in wireless sensor networks is proposed, and then its time synchronization error analysis are discussed. All of the related work contributes to the development of a commercial, cost-effective, and reliable SHM system
暂无评论