Fuzzy relational classifier(FRC) is a recently proposed nonlinear classifier, in which the unsupervised clustering is performed to explore the underlying structure of the data distribution, and to construct the subseq...
详细信息
Fuzzy relational classifier(FRC) is a recently proposed nonlinear classifier, in which the unsupervised clustering is performed to explore the underlying structure of the data distribution, and to construct the subsequent classifier. Main advantage of FRC is the interpretable results of the classification prediction. However, the unsupervised FCM is highly sensitive to non-spherical data distribution and improper cluster numbers. In this paper, a new clustering method based on local discriminative information is proposed to group data based on both similarity and class labels, giving rise to that the constructed fuzzy relationship between the formed groups and the given classes is more reliable than unsupervised clustering method. During the classification period, neighbourhood information is incorporated into the classification mechanism to improve its performance. The experimental results on Routers-21578 text dataset and Fudan Chinese textset demonstrate that this new approach has overcome the above disadvantages of FRC and achieved prior robustness and classification performance in cost of small computational cost.
So far a lot of sensorless control methods have been proposed for permanent-magnet synchronous motors (PMSM). However, application which require the response at transition is limited in current methods, and the expans...
详细信息
So far a lot of sensorless control methods have been proposed for permanent-magnet synchronous motors (PMSM). However, application which require the response at transition is limited in current methods, and the expansion of coverage of sensorless control is requested. In this paper, an extended flux is defined and minimal order observer estimating it is proposed. Then, the poles of the minimal order observer are assigned, considering robustness to velocity estimation error and suppression of higher harmonic components. Assigning poles like this, this observer becomes robuster to velocity estimation error at transition than conventional method. By this characteristic, the improvement of the response can be expected. The performance of proposed method is shown by experiments.
The applicability of decomposable biopolymer (polylactide - PLA) as Printed Wiring Board (PWB) substrate was investigated. A novel approach for low temperature reflow soldering was applied. Different types of PLA boar...
详细信息
The applicability of decomposable biopolymer (polylactide - PLA) as Printed Wiring Board (PWB) substrate was investigated. A novel approach for low temperature reflow soldering was applied. Different types of PLA boards were prepared and each type was qualitatively characterized. The realized circuit was designed for the use of Surface Mounted (SM) components. The low maximum process temperature of PLA boards was a key aspect to set soldering temperatures. 58Bi42Sn solder alloy was chosen to match the lower soldering temperature range required by the PLA board material. Steps of reflow soldering technology (stencil printing, component placement, reflow soldering) were applied using 0603 discrete components and were inspected during the circuit assembling process. Hot soldering iron, IR radiation, hot gas method and Vapour Phase Soldering (VPS) were applied for heat transfer during the experiments. VPS was found the best for heat transfer to melt the low temperature (138 °C) solder alloy. The results verified the flexibility and usability of the VPS in the field of special applications. The quality of boards was examined with cross-section optical inspection; the solder joints were evaluated with shear force tests. Typical failures were also analyzed.
Classical logic has been used as a basis for knowledge representation and reasoning in many domains. Legal Knowledge Representation is interesting due to the natural occurrences of conflicts among law systems, individ...
详细信息
Classical logic has been used as a basis for knowledge representation and reasoning in many domains. Legal Knowledge Representation is interesting due to the natural occurrences of conflicts among law systems, individual laws and cases, usually taken as logical inconsistencies. Due to its inherently normative feature, coherence (consistency) in legal ontologies is more subtle than in other domains. An adequate intuitionistic semantics for negation in a legal domain comes to the fore when we consider laws as individuals instead of propositions. This paper presents a version of Intuitionistic Description logic designed for legal knowledge representation. The paper discusses a logical coherence analysis of ``Conflict of Laws in Space'', using our logic, and briefly compares this analysis to other logical approaches to Legal Reasoning.
In this paper we present three different methodologies of band selection for hyperspectral data sets applied to classification and regression tasks using Information Theory measures. In one of the cases, the bands wil...
详细信息
In this paper we present three different methodologies of band selection for hyperspectral data sets applied to classification and regression tasks using Information Theory measures. In one of the cases, the bands will be selected having information about the classification labels of the data points (supervised classification). In the second one, no information about the target labels is required (unsupervised classification). In the third problem, the target variables are of continuous nature and are also available (supervised regression).
A completely new teaching mode emerges encompassing Intensive Teaching and Independent Learning as a result of optimizing education resources with advanced education technology in info-net environment. The new teachin...
详细信息
In view of the problems of using traditional machine learning method to detect the network intrusions, a network intrusion detection model based on multi-class imbalanced learning is proposed. Based on the considerati...
详细信息
ISBN:
(纸本)9781424497621
In view of the problems of using traditional machine learning method to detect the network intrusions, a network intrusion detection model based on multi-class imbalanced learning is proposed. Based on the consideration that there is within-class imbalance in large data sets and multi-class data sets, every class of the training data is firstly clustered. Some minimum bounding hyperspheres are formed by Support Vector Date Description (SVDD) according to the clustering results. A test sample is assigned the label of hyperspheres if its distance to the sphere center is smaller than or equal to the radius. The model is testified by experiments on network security data sets.
Optimisation of the optical signal from the laser multi-spot beam generator employed in a photonic based real-time plant discrimination sensor for use in selective herbicide spraying systems is presented. The plant de...
详细信息
Optimisation of the optical signal from the laser multi-spot beam generator employed in a photonic based real-time plant discrimination sensor for use in selective herbicide spraying systems is presented. The plant detection sensor uses a three-wavelength laser diode module that sequentially emits identically-polarized laser light beams through a common aperture, along one optical path. Each laser beam enters a multi-spot beam generator which produces 15 parallel laser beams over a 240mm span. The intensity of the reflected light from each spot is detected by a high-speed line scan image sensor. Plant discrimination is based on calculating the slope of the spectral response between the 635nm to 685nm and 685nm to 785nm laser wavelengths. Further optimisation of the optical signal is achieved by minimising the effect of daylight background noise by implementing a custom designed optical band-pass filter. The effectiveness of this filter is experimentally demonstrated.
Being successful in semiconductor manufacturing of sub 50nm devices requires controlling variability of device leakage. Full wafer monitoring is essential to provide significant data. The Device Leakage Scribe Charact...
详细信息
Being successful in semiconductor manufacturing of sub 50nm devices requires controlling variability of device leakage. Full wafer monitoring is essential to provide significant data. The Device Leakage Scribe Characterization Vehicle (CV ® ) Test Chips presented here fit well within the scribe area constraints of product wafers. Their devices under test (DUT) are using product relevant layout pattern to support new product introduction. Those DUTs are passively connected into a Passive Leakage Array (PLA) to increase the signal to noise ratio of the device leakage measurements, which is essential to enable full wafer testing within existing test time restrictions on product wafers. Furthermore, the PLAs can be arranged inside a Multiplexed Leakage Array (MLA), which significantly increases the number of experiments within the precious scribe line area.
Research on the correlation of the sudden failure of aircraft with the human-machine-environment has important meaning to know the sudden failure mechanism of aircraft and reduce or eliminate the disaster accidents. I...
详细信息
Research on the correlation of the sudden failure of aircraft with the human-machine-environment has important meaning to know the sudden failure mechanism of aircraft and reduce or eliminate the disaster accidents. In this paper, the feature on sudden failure of aircraft, the forming reason of sudden failure, the spreading way of sudden failure and correlation on sudden failure of aircraft with human-machine environment are researched. At the same time, the relationship model on sudden failure of aircraft with human-machine environment is established, and monitoring module on aero engine in-flight shutdown is designed and it is simulated. Results show that sudden failure of aircraft is a synthetic action result on various factors with human-machine-environment, and it has an evolvement process from gradient to catastrophe and from slight to abrupt. If only the evolvement information of sudden failure can be caught in time and the correspondent measure can be adopted, the emergent fault may prevent and disastrous trouble may reduce.
暂无评论