Building a system to identify individuals through their speech recording can find its application in diverse areas, such as telephone shopping, voice mail and security control. However, building such systems is a tricky task because of the vast range of differences in the human voice. Thus, selecting strong features becomes very crucial for the recognition system. Therefore, a speaker recognition system based on new spin-image descriptors (SISR) is proposed in this paper. In the proposed system, circular windows (spins) are extracted from the frequency domain of the spectrogram image of the sound, and then a run length matrix is built for each spin, to work as a base for feature extraction tasks. Five different descriptors are generated from the run length matrix within each spin and the final feature vector is then used to populate a deep belief network for classification purpose. The proposed SISR system is evaluated using the English language Speech Database for Speaker Recognition (ELSDSR) database. The experimental results were achieved with 96.46 accuracy; showing that the proposed SISR system outperforms those reported in the related current research work in terms of recognition accuracy.
The extracting of personal sprite from the whole image faced many problems in separating the sprite edge from the unneeded parts, some image software try to automate this process, but usually they couldn't find the edge or have false result. In this paper, the authors have made an enhancement on the use of Canny edge detection to locate the sprite from the whole image by adding some enhancement steps by using MATLAB. Moreover, remove all the non-relevant information from the image by selecting only the sprite and place it in a transparent background. The results of comparing the Canny edge detection with the proposed method shows improvement in the edge detection.
Doses for most drugs are determined from population-level information, resulting in a standard ?one-size-fits-all’ dose range for all individuals. This review explores how doses can be personalised through the use of the individuals’ pharmacokinetic (PK)-pharmacodynamic (PD) profile, its particular application in children, and therapy areas where such approaches have made inroads.
The Bayesian forecasting approach, based on population PK/PD models that account for variability in exposure and response, is a potent method for personalising drug therapy. Its potential utility is eve
In this paper we prove a theorem about the existence and uniqueness common fixed point for two uncommenting self-mappings which defined on orbitally complete G-metric space. Where we use a general contraction condition.
Isthmus life and prepare for it
Objectives: To identify child or family related risk factors for
unintentional childhood poisoning in Sulaymaniyah, Iraq and to suggest
possible causes and preventive measures.
Methods: This is an epidemiological description and a case-control study. The study was undertaken in Sulaymani ,in 2004-2005. Cases were 200 children who were admitted to the hospital for treatment of poisoning. For every case two controls were selected. Al l parents of the children were interviewed by using a questionnaire that incl uded demographic and poisoning characteristic information.<
... Show MoreThe set of all (n×n) non-singular matrices over the field F. And this set forms a group under the operation of matrix multiplication. This group is called the general linear group of dimension over the field F, denoted by . The determinant of these matrices is a homomorphism from into F* and the kernel of this homomorphism was the special linear group and denoted by Thus is the subgroup of which contains all matrices of determinant one.
The rationally valued characters of the rational representations are written as a linear combination of the induced characters for the groups discussed in this paper. We find the Artin indicator for this group after studying the rationally valued characters of the rational
... Show MoreThis model is an extension to H.M.M.S and related developments models of a single product. These models will be converted to deal with Multiproduct for productive company. This model executed by computer programming technique to maximize profits
Electrocoagulation is an electrochemical process of treating polluted water where sacrificial anode corrodes to produce active coagulant (usually aluminum or iron cations) into solution. Accompanying electrolytic reactions evolve gas (usually as hydrogen bubbles). The present study investigates the removal of phenol from water by this method. A glass tank with 1 liter volume and two electrodes were used to perform the experiments. The electrode connected to a D.C. power supply. The effect of various factors on the removal of phenol (initial phenol concentration, electrode size, electrodes gab, current density, pH and treatment time) were studied. The results indicated that the removal efficiency decreased as initial phenol concentration
... Show MoreLet ℛ be a commutative ring with unity and let ℬ be a unitary R-module. Let ℵ be a proper submodule of ℬ, ℵ is called semisecond submodule if for any r∈ℛ, r≠0, n∈Z+, either rnℵ=0 or rnℵ=rℵ.
In this work, we introduce the concept of semisecond submodule and confer numerous properties concerning with this notion. Also we study semisecond modules as a popularization of second modules, where an ℛ-module ℬ is called semisecond, if ℬ is semisecond submodul of ℬ.