One study whose importance has significantly grown in recent years is lip-reading, particularly with the widespread of using deep learning techniques. Lip reading is essential for speech recognition in noisy environments or for those with hearing impairments. It refers to recognizing spoken sentences using visual information acquired from lip movements. Also, the lip area, especially for males, suffers from several problems, such as the mouth area containing the mustache and beard, which may cover the lip area. This paper proposes an automatic lip-reading system to recognize and classify short English sentences spoken by speakers using deep learning networks. The input video extracts frames and each frame is passed to the Viola-Jones to detect the face area. Then 68 landmarks of the facial area are determined, and the landmarks from 48 to 68 represent the lip area extracted based on building a binary mask. Then, the contrast is enhanced to improve the quality of the lip image by applying contrast adjustment. Finally, sentences are classified using two deep learning models, the first is AlexNet, and the second is VGG-16 Net. The database consists of 39 participants (32 males and 7 females). Each participant repeats the short sentences five times. The outcomes demonstrate the accuracy rate of AlexNet is 90.00%, whereas the accuracy rate for VGG-16 Net is 82.34%. We concluded that AlexNet performs better for classifying short sentences than VGG-16 Net.
We propose a novel strategy to optimize the test suite required for testing both hardware and software in a production line. Here, the strategy is based on two processes: Quality Signing Process and Quality Verification Process, respectively. Unlike earlier work, the proposed strategy is based on integration of black box and white box techniques in order to derive an optimum test suite during the Quality Signing Process. In this case, the generated optimal test suite significantly improves the Quality Verification Process. Considering both processes, the novelty of the proposed strategy is the fact that the optimization and reduction of test suite is performed by selecting only mutant killing test cases from cumulating t-way test ca
... Show MoreThe steel jetty selected for strengthening is in Baghdad city, over Tigris River, consists of 55 short spans, each of approximately 4 meters and one naviga-tional opening of 12 m. The bridge is 224 meters length and 8 meters in width. The strengthening system was designed to remove overstresses that occurred when the bridge was subjected to abnormal loads of 380 tons. A strengthening system which installed in spring 2008 was used where the main concept is to depend on added side supporting elements which impose reversal forces on the bridge to counteract most of the loads expected from the abnormal heavy loads. The bridge was load tested before and after the strengthening system was activated. The load test results indicate that the strengt
... Show MoreThis research aims to identify the impact of the reciprocal reading strategy on developing the innovative reading skills of fifth-grade secondary school students/ scientific branch. To achieve the goal of the research, an achievement test to measure the academic achievement of fifth-grade secondary school students in Arabic language grammar was prepared, a sample of (60) female students from the secondary school of Al- Bawaba Al-Sharkey for Girls in Baghdad were chosen for the academic year (2019-2020). For the purpose of applying the experiment, the test was applied on a pilot sample consisting of (30) students from the same research community. The researcher herself had taught the three
... Show MoreCorruption, in all its categories and forms, is regarded as the nowadays virus which has greatly spread in most institutes and society, a matter that cause a great waste of resources.
According to the reports of international transparency Institute, Iraq is regarded as one of the greatest countries in corruption.
Regardless of the reasons and forms of corruption, the retreat in work – values and ethics are the main reasons behind that.
Being the main source of providing qualified staff "educators" for the working market, the high education institutes face great challenges in standing against corruption inside and outside
... Show MoreRA Ali, LK Abood, Int J Sci Res, 2017 - Cited by 2
This research aims at calculating the optimum cutting condition for various types of machining methods, assisted by computers, (the computer program in this research is designed to solve linear programs; the program is written in v. basic language). The program obtains the results automatically, this occur through entering the preliminary information about the work piece and the operating condition, the program makes the calculation actually by solving a group of experimental relations, depending on the type of machining method (turning, milling, drilling). The program was transferred to package and group of windows to facilitate the use; it will automatically print the initial input and optimal solution, and thus reduce the effort and t
... Show MoreThis paper demonstrates the design of an algorithm to represent the design stages of fixturing system that serve in increasing the flexibility and automation of fixturing system planning for uniform polyhedral part. This system requires building a manufacturing feature recognition algorithm to present or describe inputs such as (configuration of workpiece) and built database system to represents (production plan and fixturing system exiting) to this algorithm. Also knowledge – base system was building or developed to find the best fixturing analysis (workpiece setup, constraints of workpiece and arrangement the contact on this workpiece) to workpiece.
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 More