Deep learning convolution neural network has been widely used to recognize or classify voice. Various techniques have been used together with convolution neural network to prepare voice data before the training process in developing the classification model. However, not all model can produce good classification accuracy as there are many types of voice or speech. Classification of Arabic alphabet pronunciation is a one of the types of voice and accurate pronunciation is required in the learning of the Qur’an reading. Thus, the technique to process the pronunciation and training of the processed data requires specific approach. To overcome this issue, a method based on padding and deep learning convolution neural network is proposed to evaluate the pronunciation of the Arabic alphabet. Voice data from six school children are recorded and used to test the performance of the proposed method. The padding technique has been used to augment the voice data before feeding the data to the CNN structure to developed the classification model. In addition, three other feature extraction techniques have been introduced to enable the comparison of the proposed method which employs padding technique. The performance of the proposed method with padding technique is at par with the spectrogram but better than mel-spectrogram and mel-frequency cepstral coefficients. Results also show that the proposed method was able to distinguish the Arabic alphabets that are difficult to pronounce. The proposed method with padding technique may be extended to address other voice pronunciation ability other than the Arabic alphabets.
In recent years, observed focus greatly on gold nanoparticles synthesis due to its unique properties and tremendous applicability. In most of these researches, the citrate reduction method has been adopted. The aim of this study was to prepare and optimize monodisperse ultrafine particles by addition of reducing agent to gold salt, as a result of seed mediated growth mechanism. In this research, gold nanoparticles suspension (G) was prepared by traditional standard Turkevich method and optimized by studying different variables such as reactants concentrations, preparation temperature and stirring rate on controlling size and uniformity of nanoparticles through preparing twenty formulas (G1-G20). Subsequently, the selected formula that pr
... Show MoreThe Assignment model is a mathematical model that aims to express a real problem facing factories and companies which is characterized by the guarantee of its activity in order to make the appropriate decision to get the best allocation of machines or jobs or workers on machines in order to increase efficiency or profits to the highest possible level or reduce costs or time To the extent possible, and in this research has been using the method of labeling to solve the problem of the fuzzy assignment of real data has been approved by the tire factory Diwaniya, where the data included two factors are the factors of efficiency and cost, and was solved manually by a number of iterations until reaching the optimization solution,
... Show MoreThis study investigated the effect of using brainstorming as a teaching technique on the students’ performance in writing different kinds of essays and self regulation among the secondary students. The total population of this study, consisted of (51) female students of the 5th Secondary grade in Al –kawarzmi School in Erbil during the academic year 2015-2016. The chosen sample consisted of 40 female students, has been divided into two groups. Each one consists of (20) students to represent the experimental group and the control one. Brainstorming technique is used to teach the experimental group, and the conventional method is used to teach the control group. The study inst
... Show MoreThe feature extraction step plays major role for proper object classification and recognition, this step depends mainly on correct object detection in the given scene, the object detection algorithms may result with some noises that affect the final object shape, a novel approach is introduced in this paper for filling the holes in that object for better object detection and for correct feature extraction, this method is based on the hole definition which is the black pixel surrounded by a connected boundary region, and hence trying to find a connected contour region that surrounds the background pixel using roadmap racing algorithm, the method shows a good results in 2D space objects.
Keywords: object filling, object detection, objec
The Arabic calligraphy, in the early days of Islam, was used for the purpose of decorating the walls of mosques from inside and outside. Hence, this decorative art must be actively involved in enriching the designs of Islamic fabrics and costumes because it has a highly qualified and aesthetically pleasing look and expresses the originality of the Arab spirit. The research is divided into two section: the first section included the following topics: First "A historical overview of the art of decoration in Islamic Arab thought". Second "linear formations of decorative designs, and the subject of intellectual aesthetic taste of the art of decorating. This section tackles two subsections: first "the beauty of thought between the function an
... Show MoreGenerally, statistical methods are used in various fields of science, especially in the research field, in which Statistical analysis is carried out by adopting several techniques, according to the nature of the study and its objectives. One of these techniques is building statistical models, which is done through regression models. This technique is considered one of the most important statistical methods for studying the relationship between a dependent variable, also called (the response variable) and the other variables, called covariate variables. This research describes the estimation of the partial linear regression model, as well as the estimation of the “missing at random” values (MAR). Regarding the
... Show MoreThis research describes a new model inspired by Mobilenetv2 that was trained on a very diverse dataset. The goal is to enable fire detection in open areas to replace physical sensor-based fire detectors and reduce false alarms of fires, to achieve the lowest losses in open areas via deep learning. A diverse fire dataset was created that combines images and videos from several sources. In addition, another self-made data set was taken from the farms of the holy shrine of Al-Hussainiya in the city of Karbala. After that, the model was trained with the collected dataset. The test accuracy of the fire dataset that was trained with the new model reached 98.87%.
In recent decades, the identification of faces with and without masks from visual data, such as video and still images, has become a captivating research subject. This is primarily due to the global spread of the Corona pandemic, which has altered the appearance of the world and necessitated the use of masks as a vital measure for epidemic prevention. Intellectual development based on artificial intelligence and computers plays a decisive role in the issue of epidemic safety, as the topic of facial recognition and identifying individuals who wear masks or not was most prominent in the introduction and in-depth education. This research proposes the creation of an advanced system capable of accurately identifying faces, both with and
... Show More