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.
Given the importance of increasing economic openness transport companies’ face various issues arising at present time, this required importing different types of goods with different means of transport. Therefore, these companies pay great attention to reducing total costs of transporting commodities by using numbers means of transport methods from their sources to the destinations. The majority of private companies do not acquire the knowledge of using operations research methods, especially transport models, through which the total costs can be reduced, resulting in the importance and need to solve such a problem. This research presents a proposed method for the sum of Total Costs (Tc) of rows and columns, in order to arrive at the init
... Show MoreIn this paper, we investigate the behavior of the bayes estimators, for the scale parameter of the Gompertz distribution under two different loss functions such as, the squared error loss function, the exponential loss function (proposed), based different double prior distributions represented as erlang with inverse levy prior, erlang with non-informative prior, inverse levy with non-informative prior and erlang with chi-square prior.
The simulation method was fulfilled to obtain the results, including the estimated values and the mean square error (MSE) for the scale parameter of the Gompertz distribution, for different cases for the scale parameter of the Gompertz distr
... Show MoreThis paper aims to evaluate the reliability analysis for steel beam which represented by the probability of Failure and reliability index. Monte Carlo Simulation Method (MCSM) and First Order Reliability Method (FORM) will be used to achieve this issue. These methods need two samples for each behavior that want to study; the first sample for resistance (carrying capacity R), and second for load effect (Q) which are parameters for a limit state function. Monte Carlo method has been adopted to generate these samples dependent on the randomness and uncertainties in variables. The variables that consider are beam cross-section dimensions, material property, beam length, yield stress, and applied loads. Matlab software has be
... Show MoreUndesirable behaviors among students are consider one of the danger problems threating societies and educational and scientific institutions of countries because its one of the way to express aggression , so the instructors consider one of the most important people could be trust their evaluation and logical view , therefore the present research aimed to :
- Recognize undesirable behavior in students of University by the view of their instructors
- Measure the level of undesirable behavior in students of university by the view of their instructors
- Recognize more common undesirable behavior in students of University by the view o
Functional dyspepsia is one of the most common gastrointestinal symptoms and attributed to various causes including Helicobacter pylori infection. AIM OF THE STUDY: To correlate Helicobacter pylori infection to functional dyspepsia and to identify the possible risk factors for this infection. PATIENTS AND METHODS: Fifty patients who were referred to the endoscopy unit for dyspepsia symptoms, secondary gastric causes of dyspepsia were excluded during endoscopy, gastric biopsies were taken for histopathological study and for bedside urease test for detection of Helicobacter pylori infection. RESULTS: 62% of non-ulcer dyspeptic patients were infected with Helicobacter pylori, 74.2% of the patients were above 30 years old, female gender patient
... Show MoreIraqi kaolin was used for the preparation and characterization of NaY zeolite for biodiesel production via esterification reaction. Oleic acid was used usually as a typical simulated feedstock of high acid number for the esterification reaction.
The chemical composition for the prepared Nay zeolite is as following: (Ca2.6Na1.K0.1)(Al6.3Si17.7)O48.16H2O, the silica to alumina ratio in the prepared catalyst was found equal to 2.6 and Na2O content was 12.26 wt. %, with relative crystallinity equal to 147.4 % obtained by the X-ray diffraction. The surface area result shows that the prepared catalyst has 330 m2
... Show MoreAdvances in gamma imaging technology mean that is now technologically feasible to conduct stereoscopic gamma imaging in a hand-held unit. This paper derives an analytical model for stereoscopic pinhole imaging which can be used to predict performance for a wide range of camera configurations. Investigation of this concept through Monte Carlo and benchtop studies, for an example configuration, shows camera-source distance measurements with a mean deviation between calculated and actual distances of <5 mm for imaging distances of 50–250 mm. By combining this technique with stereoscopic optical imaging, we are then able to calculate the depth of a radioisotope source beneath a surfa
The Adaptive Optics technique has been developed to obtain the correction of atmospheric seeing. The purpose of this study is to use the MATLAB program to investigate the performance of an AO system with the most recent AO simulation tools, Objected-Oriented Matlab Adaptive Optics (OOMAO). This was achieved by studying the variables that impact image quality correction, such as observation wavelength bands, atmospheric parameters, telescope parameters, deformable mirror parameters, wavefront sensor parameters, and noise parameters. The results presented a detailed analysis of the factors that influence the image correction process as well as the impact of the AO components on that process