In this paper, a fusion of K models of full-rank weighted nonnegative tensor factor two-dimensional deconvolution (K-wNTF2D) is proposed to separate the acoustic sources that have been mixed in an underdetermined reverberant environment. The model is adapted in an unsupervised manner under the hybrid framework of the generalized expectation maximization and multiplicative update algorithms. The derivation of the algorithm and the development of proposed full-rank K-wNTF2D will be shown. The algorithm also encodes a set of variable sparsity parameters derived from Gibbs distribution into the K-wNTF2D model. This optimizes each sub-model in K-wNTF2D with the required sparsity to model the time-varying variances of the sources in the spectrogram. In addition, an initialization method is proposed to initialize the parameters in the K-wNTF2D. Experimental results on the underdetermined reverberant mixing environment have shown that the proposed algorithm is effective at separating the mixture with an average signal-to-distortion ratio of 3 dB.
In this paper solar radiation was studied over a region of Baghdad (Latitude 33.3o and longitude 44.4o). The two parts of global solar radiation: diffuse and direct solar radiation were estimated depending on the clearance index of measured data (Average Monthly mean global solar radiation). Metrological data of measured (average monthly mean diffuse and direct solar radiation) were used to comparison the results and show the agreement between them. Results are determined by applying Liu and Jordan two models (1960). Excel 2007program is used in calculation, graphics and comparison the results.
The crude enzyme Nattokinase produced by Bacillus subtilis was used in ripening cheddar cheese by adding three concentration of enzyme 80, 160 and 320mg/Kg beside the control treatment without enzyme, the product was checked for three months to determine humidity, protein, fat, non-protein nitrogen, soluble nitrogen and pH, sensory evaluation was conducted, it was noticed that the variety in protein percentages and the soluble nitrogen percentage during second month of ripening for T2, T3 and T4 treatments were (11.2, 15.54 and 18.48) respectively, in comparison with control which was 7.6%, while in the third month it was (17.37, 20.67 and 22.26) respectively, in comparison with control which was only 10%, on the other hand, non-protein
... Show MoreThe origin of this technique lies in the analysis of François Kenai (1694-1774), the leader of the School of Naturalists, presented in Tableau Economique. This method was developed by Karl Marx in his analysis of the Departmental Relationships and the nature of these relations in the models of " "He said. The current picture of this type of economic analysis is credited to the Russian economist Vasily Leontif. This analytical model is commonly used in developing economic plans in developing countries (p. 1, p. 86). There are several types of input and output models, such as static model, mobile model, regional models, and so on. However, this research will be confined to the open-ended model, which found areas in practical application.
... Show MoreWater/oil emulsion is considered as the most refractory mixture to separate because of the interference of the two immiscible liquids, water and oil. This research presents a study of dewatering of water / kerosene emulsion using hydrocyclone. The effects of factors such as: feed flow rate (3, 5, 7, 9, and 11 L/min), inlet water concentration of the emulsion (5%, 7.5%, 10%, 12.5%, and 15% by volume), and split ratio (0.1, 0.3, 0.5, 0.7, and 0.9) on the separation efficiency and pressure drop were studied. Dimensional analysis using Pi theorem was applied for the first time to model the hydrocyclone based on the experimental data. It was shown that the maximum separation efficiency; at split ratio 0.1, was 94.3% at 10% co
... Show MoreCompressing the speech reduces the data storage requirements, leading to reducing the time of transmitting the digitized speech over long-haul links like internet. To obtain best performance in speech compression, wavelet transforms require filters that combine a number of desirable properties, such as orthogonality and symmetry.The MCT bases functions are derived from GHM bases function using 2D linear convolution .The fast computation algorithm methods introduced here added desirable features to the current transform. We further assess the performance of the MCT in speech compression application. This paper discusses the effect of using DWT and MCT (one and two dimension) on speech compression. DWT and MCT performances in terms of comp
... Show MoreEye Detection is used in many applications like pattern recognition, biometric, surveillance system and many other systems. In this paper, a new method is presented to detect and extract the overall shape of one eye from image depending on two principles Helmholtz & Gestalt. According to the principle of perception by Helmholz, any observed geometric shape is perceptually "meaningful" if its repetition number is very small in image with random distribution. To achieve this goal, Gestalt Principle states that humans see things either through grouping its similar elements or recognize patterns. In general, according to Gestalt Principle, humans see things through genera
... Show MoreAs we live in the era of the fourth technological revolution, it has become necessary to use artificial intelligence to generate electric power through sustainable solar energy, especially in Iraq and what it has gone through in terms of crises and what it suffers from a severe shortage of electric power because of the wars and calamities it went through. During that period of time, its impact is still evident in all aspects of daily life experienced by Iraqis because of the remnants of wars, siege, terrorism, wrong policies ruling before and later, regional interventions and their consequences, such as the destruction of electric power stations and the population increase, which must be followed by an increase in electric power stations,
... Show MoreNeural cryptography deals with the problem of “key exchange” between two neural networks by using the mutual learning concept. The two networks exchange their outputs (in bits) and the key between two communicating parties ar eventually represented in the final learned weights, when the two networks are said to be synchronized. Security of neural synchronization is put at risk if an attacker is capable of synchronizing with any of the two parties during the training process.
Diabetes is one of the increasing chronic diseases, affecting millions of people around the earth. Diabetes diagnosis, its prediction, proper cure, and management are compulsory. Machine learning-based prediction techniques for diabetes data analysis can help in the early detection and prediction of the disease and its consequences such as hypo/hyperglycemia. In this paper, we explored the diabetes dataset collected from the medical records of one thousand Iraqi patients. We applied three classifiers, the multilayer perceptron, the KNN and the Random Forest. We involved two experiments: the first experiment used all 12 features of the dataset. The Random Forest outperforms others with 98.8% accuracy. The second experiment used only five att
... Show MoreShadow detection and removal is an important task when dealing with color outdoor images. Shadows are generated by a local and relative absence of light. Shadows are, first of all, a local decrease in the amount of light that reaches a surface. Secondly, they are a local change in the amount of light rejected by a surface toward the observer. Most shadow detection and segmentation methods are based on image analysis. However, some factors will affect the detection result due to the complexity of the circumstances. In this paper a method of segmentation test present to detect shadows from an image and a function concept is used to remove the shadow from an image.