Healthiness of the insulation system of any power apparatus plays vital criteria for its effective performance in power system. Minor flaws in insulation system such as blow-holes, cavities, imperfection on the surfac...
详细信息
ISBN:
(纸本)9781601321480
Healthiness of the insulation system of any power apparatus plays vital criteria for its effective performance in power system. Minor flaws in insulation system such as blow-holes, cavities, imperfection on the surface etc are inevitable even during manufacturing stage leading to discharges called Partial Discharge (PD) eventually leading to degradation of dielectric material usually caused by erosion mechanism (tracking and treeing). PD initiated treeing of insulation system has been receiving wide attention by researchers very recently since this mechanism is categorized as a severe case of insulation degradation by electrical utilities. This phenomenon may lead to mal operation of power apparatus. Further exhaustive literature survey carried out in this field has clearly delineated on the close relationship between physics related to the degradation mechanism and nature of flaw (void, cavity etc). Further, since the time between PD initiated treeing and breakdown is much shorter than the time to tree initiation, recognition of such complex and stochastic pattern of PD becomes challenging task even for experts. Standard laboratory models simulating various types of PD initiated treeing is fabricated. An accelerated ageing test method is carried out in testing the laboratory models. PD initiated discharge patterns and treeing patterns are acquired from the direct testing circuits as proposed by IEC 60270:2000. The morphology of the treeing patterns is visually correlated to comprehend the nature of discharge. In addition PD signatures acquired from the PD measurement and acquisition system is trained and tested with neural networks to discriminate tree and PD initiated discharge fingerprints.
The research is based on 10-node autonomous, distributed wireless monitoring system placed in various locations throughout Historical Center of Mexico City to take permanent measurements of the noise levels and stream...
详细信息
ISBN:
(纸本)9789604742509
The research is based on 10-node autonomous, distributed wireless monitoring system placed in various locations throughout Historical Center of Mexico City to take permanent measurements of the noise levels and stream the data back to the main monitoring station every five minutes and the measurements of signals of the noise produced during the takeoff in a location of the international Airport of Mexico City. As first stage, this paper presents a novel computational model that allows aircrafts identification based on generated noise. This model also helps to foresee potential effects to health caused by this kind of noise during the aircraft takeoff, which is when the greatest impact are generated due to the sonorous levels that are reached. The data acquisition is made at 25 KHz at 24 bits. The identification of the aircraft noise is done through two parallel neural networks combined with a weighted addition. In order to generate the inputs to the neural networks, parameters that were obtained from the auto-regressive model and the 1/12 octave analysis are used. This system has 13 categories of aircrafts and it has an identification level of 80% in real environments.
Over the recent years, a great deal of effort has been made to age estimation from face images. It has been reported that age can be accurately estimated under controlled environment such as frontal faces, no expressi...
详细信息
ISBN:
(纸本)9781424475421
Over the recent years, a great deal of effort has been made to age estimation from face images. It has been reported that age can be accurately estimated under controlled environment such as frontal faces, no expression, and static lighting conditions. However, it is not straightforward to achieve the same accuracy level in real-world environment because of considerable variations in camera settings, facial poses, and illumination conditions. In this paper, we apply a recently-proposed machine learning technique called covariate shift adaptation to alleviating lighting condition change between laboratory and practical environment. Through real-world age estimation experiments, we demonstrate the usefulness of our proposed method.
Feature extraction is an important issue in graphics retrieval. Local feature based descriptors are currently the predominate method used in image retrieval and object recognition. Inspired by the success of Haar feat...
详细信息
Feature extraction is an important issue in graphics retrieval. Local feature based descriptors are currently the predominate method used in image retrieval and object recognition. Inspired by the success of Haar feature and Local Binary pattern (LBP), a novel feature named structured local binary Haar pattern (SLBHP) is proposed for graphics retrieval in this paper. SLBHP encodes the polarity instead of the magnitude of the difference between accumulated gray values of adjacent rectangles. Experimental results on graphics retrieval show that the discriminative power of SLBHP is better than those of using edge points (EP), Haar feature, and LBP even in noisy condition.
This paper presents a biometric recognition system based on the iris of a human eye using embedded zerotree wavelet coding. The proposed system consists of three modules: image pre-processing, feature extraction, and ...
详细信息
This paper presents a biometric recognition system based on the iris of a human eye using embedded zerotree wavelet coding. The proposed system consists of three modules: image pre-processing, feature extraction, and recognition modules. Image pre-processing module uses some image processing algorithms to localize and cut the region of iris out of the input image. The feature extraction module adopts a modified embedded zerotree wavelet coding to discriminate texture features. The system encodes the features to generate its iris feature codes. Finally, the recognition module uses these feature codes for iris matching. The experimental results show that the system has an encouraging performance on the UBIRIS iris image database. The recognition rates up to 100.00% can be achieved.
This paper proposes a new method for feature extraction and recognition, namely, the fuzzy bidirectional maximum margin criterion (FBMMC) based on the maximum margin criterion and fuzzy set theory. In FBMMC, a members...
详细信息
This paper proposes a new method for feature extraction and recognition, namely, the fuzzy bidirectional maximum margin criterion (FBMMC) based on the maximum margin criterion and fuzzy set theory. In FBMMC, a membership grade matrix is calculated by the FKNN algorithm, and then the membership grades are incorporated into the formulation of the scatter matrices to formulate the row and column directional fuzzy scatter matrices. Using the fuzzy scatter matrix, FBMMC performs fuzzy image MMC in the row and column directions simultaneously. Experiments on the ORL and Yale face databases show the effectiveness of the proposed FBMMC based feature extraction method.
Recent research has shown that cognitive radio (CR) is an attractive technology to enhance the spectrum utilization and the fractional Fourier transform (FRFT) is widely used for its advantages in dealing with the tim...
详细信息
Recent research has shown that cognitive radio (CR) is an attractive technology to enhance the spectrum utilization and the fractional Fourier transform (FRFT) is widely used for its advantages in dealing with the time-varying degradations and non-stationary processes. In this paper, a novel interference suppression approach using the CR-FRFT is proposed for the spread spectrum systems. This approach firstly carries out the patternrecognition by spectrum sensing, and then chooses an optimal transform order for the recognized interference to make the FRFT-based transform domain excision. Theoretical analysis and experimental results show that the proposed CR-FRFT technique is more pertinent than the conventional techniques and can achieve a significant performance for the broadband interference. As the FRFT has a fast digital algorithm, it is conveniently to make a software package of the proposed CR-FRFT technique and be embedded in the existed spread spectrum systems for interference excision applications.
Wavelet has important apply in image processing and patternrecognition. In 2008, the wavelet technology was applied to Beijing Olympic traffic guidance transmission successfully, by locating and identifying all kinds...
详细信息
Wavelet has important apply in image processing and patternrecognition. In 2008, the wavelet technology was applied to Beijing Olympic traffic guidance transmission successfully, by locating and identifying all kinds of vehicles. This paper carries on research about the construction of binary wavelet from the practical need of signal processing and analysis and provides two types of binary wavelet construction methods: one is symmetrical binary wavelet with zero as centre of symmetry; the other is dissymmetrical binary wavelet with zero as centre of dissymmetry. These results complete the binary wavelet theory and lay a strong foundation for the application of binary wavelet in signal processing and analysis. Meanwhile, this paper also shows the key arithmetic of image denoising with binary wavelet and arithmetic in edge detection.
Aiming at the current structured P2P system's locality of physical location and accessing resources, in the context of P4P technology, this paper takes the Pastry and P4P-Pastry algorithms as foundation, proposes ...
详细信息
Aiming at the current structured P2P system's locality of physical location and accessing resources, in the context of P4P technology, this paper takes the Pastry and P4P-Pastry algorithms as foundation, proposes a enhanced P4P routing algorithm, in which peers performed clustering to the same resources and the proximity of physical location of nodes. When routing, the node routes to the nodes which are physical adjacent to it and have the lowest cost of communication. Theory analysis and the experimental results show that the algorithm proposed in this paper has realized localization download and greatly raised the data transfer rate, reduced the load in backbone network and enhanced the network performance.
In contemporary digital world, image digitization benefits the patternrecognition based on the computational methods. By the nature of associative memory, which is a practical usage of discrete Hopfield neural networ...
详细信息
In contemporary digital world, image digitization benefits the patternrecognition based on the computational methods. By the nature of associative memory, which is a practical usage of discrete Hopfield neural network, it can be adopted for the patternrecognition application. This paper proposes the design and the prototype implementation of patternrecognition through associative memory. Our approach is semantics oriented through figure contour extracted by edge detection. Experimental results show that our approach can recover the polluted or fragmentary image on a high confidence level.
暂无评论