Today due to the importance and necessity of implementing security systems in homes and other buildings, systems with higher certainty, lower cost and with sensor fusion methods are more attractive, as an applicable a...
详细信息
Today due to the importance and necessity of implementing security systems in homes and other buildings, systems with higher certainty, lower cost and with sensor fusion methods are more attractive, as an applicable and high performance methods for the researchers. In this paper, the application of Dempster-Shafer evidential theory and also the newer, more general one Dezert-Smarandache theory for implementing as a home security system and also using sensor data fusion have been considered. The benefits of multisensor fusion with direct connection to the control unit, in comparison with the traditional single sensor systems, have been shown.
A method for detecting spikes and slow burst in photic evoked electroencephalogram (EEG) was proposed. The spikes were detected by combining methods of the morphological filter and the similarity coefficient in the ti...
详细信息
A method for detecting spikes and slow burst in photic evoked electroencephalogram (EEG) was proposed. The spikes were detected by combining methods of the morphological filter and the similarity coefficient in the time domain. The slow burst was detected by using pole of AR model in the frequency domain. The proposed method was applied for the photic evoked EEG data containing spikes and slow burst, and brought satisfactory coincidence with the results interpreted by a qualified electroencephalographer.
Efficiency and fairness are two crucial issues to be considered for resource alloca- tion in multi-user wireless networks. Based on the joint optimization of physical layer and data link layer, an optimization model i...
详细信息
Efficiency and fairness are two crucial issues to be considered for resource alloca- tion in multi-user wireless networks. Based on the joint optimization of physical layer and data link layer, an optimization model is derived to achieve efficient and fair downlink data scheduling in multi-user OFDM wireless networks by maximizing the total utility function with respect to the average waiting time of user queue. A dynamic sub-carrier allocation algorithm （DSAA） based on the optimization model is proposed in order to obtain the maximization of the total scheduling utility. Effi- ciency is improved by combining DSAA with time scale interference predictor （TSIP） which at large time scales predict ON/OFF period of user data with temporal corre- lation structure across multiple time scales in multi-user interference environment. Simulation results verify the efficiency and fairness of the scheme.
Fisher discriminant analysis (FDA) is a popular method for supervised dimensionality reduction. FDA seeks for an embedding transformation such that the ratio of the between-class scatter to the within-class scatter is...
详细信息
Fisher discriminant analysis (FDA) is a popular method for supervised dimensionality reduction. FDA seeks for an embedding transformation such that the ratio of the between-class scatter to the within-class scatter is maximized. Labeled data, however, often consume much time and are expensive to obtain, as they require the efforts of human annotators. In order to cope with the problem of effectively combining unlabeled data with labeled data to find the embedding transformation, we propose a novel method, called subspace semi-supervised Fisher discriminant analysis (SSFDA), for semi-supervised dimensionality reduction. SSFDA aims to find an embedding transformation that respects the discriminant structure inferred from the labeled data and the intrinsic geometrical structure inferred from both the labeled and unlabeled data. We also show that SSFDA can be extended to nonlinear dimensionality reduction scenarios by applying the kernel trick. The experimental results on face recognition demonstrate the effectiveness of our proposed algorithm.
According to the rules of UIC515-3, the service loads of the axles are defined, which include some different loads cases as follows： the static loads; the impact loads resulted from running through the rail joints an...
详细信息
According to the rules of UIC515-3, the service loads of the axles are defined, which include some different loads cases as follows： the static loads; the impact loads resulted from running through the rail joints and unevenness rails; the loads through curves and from braking. Through the calculating and analysis, the stress distribution of the hollow axles is obtained for 200 km/h high speed motor trains used in China. At the same time, the fatigue crack growth of hollow axles is studied, and the initial surface cracks of 2 mm depth caused by hard objects strike or the other causes are discussed. On the basis of the linear elastic fracture mechanics theory, the stress intensity factor of the crack of the geometry transition outside the wheel seat is also studied. Associated with fatigue crack propagation equation and the corresponding crack propagation threshold, the crack propagation characteristics under different shapes are calculated. Then the running distances are educed with different shapes propagating to the critical length, and the estimation of the residual lives about hollow axles which are the reference values of examine and repair limit of the hollow axle is given.
Automatic Target Recognition (ATR) is increasingly important in a wide range of video and image applications, such as machine vision and security monitoring. In order to reduce the complexity and time lag in Unmanned ...
详细信息
This paper introduces the fundamental of cross-section measurement system based on Electrical Resistance Tomography (ERT). The measured data of four flow regimes of the gas/liquid two-phase flow in horizontal pipe flo...
This paper introduces the fundamental of cross-section measurement system based on Electrical Resistance Tomography (ERT). The measured data of four flow regimes of the gas/liquid two-phase flow in horizontal pipe flow are obtained by an ERT system. For the measured data, five entropies are extracted to analyze the experimental data according to the different flow regimes, and the analysis method is examined and compared in three different perspectives. The results indicate that three different perspectives of entropy-based feature extraction are sensitive to the flow pattern transition in gas/liquid two-phase flow. By analyzing the results of three different perspectives with the changes of gas/liquid two-phase flow parameters, the dynamic structures of gas/liquid two-phase flow is obtained, and they also provide an efficient supplementary to reveal the flow pattern transition mechanism of gas/liquid two-phase flow. Comparison of the three different methods of feature extraction shows that the appropriate entropy should be used for the identification and prediction of flow regimes.
A new approach for decreasing the amplitude characteristic deviation of Guassian filter in surface roughness measurements is presented in this paper. According to Central Limit Theorem, many different Guassian approxi...
详细信息
This paper presents a new clustering algorithm to solve the blind identification problem of digital communication signal modulation types. the algorithm utilized the instantaneous frequency and instantaneous phase of ...
详细信息
A new method is presented in order to solve the problem of randomness of the initial selection for nearest neighbor clustering algorithm and redundant nodes introduced by subtractive clustering algorithm,namely, the a...
详细信息
A new method is presented in order to solve the problem of randomness of the initial selection for nearest neighbor clustering algorithm and redundant nodes introduced by subtractive clustering algorithm,namely, the algorithm that contain pruning technique of subtractive clustering algorithm and nearest neighbor clustering algorithm combine together,and accomplish the learnimg of training samples. The simulation results show that the effectiveness of the new algorithm.
暂无评论