In this paper, we design a content-based image retrieval system where multiple query examples can be used to indicate the need to retrieve not only images similar to the individual examples, but also those images which actually represent a combination of the content of query images. We propose a scheme for representing content of an image as a combination of features from multiple examples. This scheme is exploited for developing a multiple example-based retrieval engine. We have explored the use of machine learning techniques for generating the most appropriate feature combination scheme for a given class of images. The combination scheme can be used for developing purposive query engines for specialized image databases. Here, we have considered facial image databases. The effectiveness of the image retrieval system is experimentally demonstrated on different databases. 相似文献
The deformation behavior of several single- and two-phase coarse microstructures has been examined using microhardness measurements.
It has been found that the strength response of a coarse phase in isolation is distinctly different from its response when
it exists in a two-phase system. The second phase alters the mechanical state of the first one andvice versa even in the plastically undeformed condition. This phenomenon is explained in terms of the existence of an appreciable amount
of residual stresses in two-phase coarse microstructures. These stresses primarily arise due to the difference in thermal
expansion coefficients of the phases. The in- fluence of elastic stress field on microhardness response is shown with a new
type of experiment to support the proposed explanation. The present results question the existing expressions for deformation
modeling of multiphase materials because of the uncertainties in the estimation of the average strength of the phases in a
two-phase system. 相似文献
The purpose of this paper is two folded. Firstly, the concept of mean potentiality approach (MPA) has been developed and an algorithm based on this new approach has been proposed to get a balanced solution of a fuzzy soft set based decision making problem. Secondly, a parameter reduction procedure based on relational algebra with the help of the balanced algorithm of mean potentiality approach has been used to reduce the choice parameter set in the parlance of fuzzy soft set theory and it is justified to the problems of diagnosis of a disease from the myriad of symptoms from medical science. Moreover the feasibility of this proposed method is demonstrated by comparing with Analytical Hierarchy Process (AHP), Naive Bayes classification method and Feng's method. 相似文献
A temperature sensor based on photonic crystal structures with two- and three-dimensional geometries is proposed, and its measurement performance is estimated using a machine learning technique. The temperature characteristics of the photonic crystal structures are studied by mathematical modeling. The physics of the structure is investigated based on the effective electrical permittivity of the substrate (silicon) and column (air) materials for a signal at 1200 nm, whereas the mathematical principle of its operation is studied using the plane-wave expansion method. Moreover, the intrinsic characteristics are investigated based on the absorption and reflection losses as frequently considered for such photonic structures. The output signal (transmitted energy) passing through the structures determines the magnitude of the corresponding temperature variation. Furthermore, the numerical interpretation indicates that the output signal varies nonlinearly with temperature for both the two- and three-dimensional photonic structures. The relation between the transmitted energy and the temperature is found through polynomial-regression-based machine learning techniques. Moreover, rigorous mathematical computations indicate that a second-order polynomial regression could be an appropriate candidate to establish this relation. Polynomial regression is implemented using the Numpy and Scikit-learn library on the Google Colab platform.
The oxy-CO2 methane reforming reaction (OCRM) has been investigated over CoOx supported on a MgO precoated highly macroporous silica–alumina catalyst carrier (SA-5205) at different reaction temperatures (700–900 °C), O2/CH4 ratios (0.3–0.45) and space velocites (20,000–100,000 cc/g/h). The reaction temperature had a profound influence on the OCRM performance over the CoO/MgO/SA-5205 catalyst; the methane conversion, CO2 conversion and H2 selectivity increased while the H2/CO ratio decreased markedly with increasing reaction temperature. While the O2/CH4 ratio did not strongly affect the CH4 and CO2 conversion and H2 selectivity, it had an intense influence on the H2/CO ratio. The CH4 and CO2 conversion and the H2 selectivity decreased while the H2/CO increased with increasing space velocity. The O2/CH4 ratio and the reaction temperature could be used to manipulate the heat of the reaction for the OCRM process. Depending on the O2/CH4 ratio and temperature the OCRM process could be operated in a mildly exothermic, thermal neutral or mildly endothermic mode. The OCRM reaction became almost thermoneutral at an OCRM reaction temperature of 850 °C, O2/CH4 ratio of 0.45 and space velocity of 46,000 cc/g/h. The CH4 conversion and H2 selectivity over the CoO/MgO/SA-5205 catalyst corresponding to thermoneutral conditions were excellent: 95% and 97%, respectively with a H2/CO ratio of 1.8. 相似文献
Nanocrystalline La0.9Sr0.1Al0.85Co0.05Mg0.1O3 oxide powder was synthesized by a citrate–nitrate auto-ignition process and characterized by thermal analysis, X-ray diffraction, and impedance spectroscopy measurements. Nanocrystalline (50–100 nm) powder with perovskite structure could be produced at 900°C by this process. The powder could be sintered to a density more than 96% of the theoretical density at 1550°C. Impedance measurements on the sintered samples unequivocally established the potential of this process in developing nanostructured lanthanum aluminate-based oxides. The sintered La0.9Sr0.1Al0.85Co0.05Mg0.1O3 sample exhibited a conductivity of 2.40 × 10−2 S/cm in air at 1000°C compared with 4.9 × 10−3 S/cm exhibited by La0.9Sr0.1Al0.85Mg0.15O3. 相似文献
In this paper, an approach has been made to produce a compressed audio without losing any information. The proposed scheme is fabricated with the help of dynamic cluster quantization followed by Burrows Wheeler Transform (BWT) and Huffman coding. The encoding algorithm has been designed in two phases, i.e., dynamic cluster selection (of sampled audio) followed by dynamic bit selection for determining quantization level of individual cluster. Quantization level of each cluster is selected dynamically based on mean square quantization error (MSQE). Bit stream is further compressed by applying Burrows Wheeler Transform (BWT) and Huffman code respectively. Experimental results are supported with current state-of-the-art in audio quality analysis (like statistical parameters (compression ratio, space savings, SNR, PSNR) along with other parameters (encoding time, decoding time, Mean Opinion Score (MOS) and entropy) and compared with other existing techniques.