Yazar "Ahmed, Mohammed Rashid" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim
    Öğe
    Android application to retrieve car details from car plate numbers
    (IOP Publishing Ltd, 2020) Ahmed, Saadaldeen Rashid; Ahmed, Mohammed Rashid; Majeed, Doaa Abdulwahhab; Hammed, Azal Hazim; Daham, Asayel Salam; Hammed, Elaf Hazim
    Computer vision is a field in computer science that has had great success due to the increasing popularity of machine learning. Instead of having a human look at images and decide what they depict, we are able to teach computers to recognize patterns of previous images and see the resemblance in new images. In this paper we will get car all information from his number plates through an Android Application which use image preprocessing and YOLO (You only look once) technique to detect the plates and then optimal character recognition to read the plates and Arabic numbers of the cars in Iraq and we have trained it using darkflow. Every Car has its unique Licensed number plate which will be scanned and give the details about the car. Computer vision can also be used to read alphanumeric characters in images and turn them into text. We have implemented API to detect the text and number in the plates. The purpose of this project is to develop a system for our Government and Police So that If police need details about any car he would easily access it. We have achieved the accuracy of 92.23% which means out of 3500 number plates 3220 read correctly. © 2020 Published under licence by IOP Publishing Ltd.
  • [ X ]
    Öğe
    Motor-imagery BCI task classification using riemannian geometry and averaging with mean absolute deviation
    (Ieee, 2019) Miah, Abu Saleh Musa; Ahmed, Saadaldeen Rashid Ahmed; Ahmed, Mohammed Rashid; Bayat, Oguz; Duru, Adil Deniz; Molla, Md. Khademul Islam
    Brain Computer interface (BCI) is thought as a better way to link within brain and computer alternative machine. Many types of physiological signal will work BCI framework. Motor imagery (MI) has incontestable to be a excellent way to work a BCI system. Recent research concerning MI based mostly BCI framework, lower performance accuracy and intense of time have common issues. Main focuses of this paper is select the appropriate central point of tangent space in Tangent Space Linear Discriminant analysis-based Motor-Imagery Brain-Computer interfacing. Method name tangent space mapping LDA (TSMLDA) analysis takes its moves from the observations that normally, the EEG signal embodies outliers, so the centrality as a geometric mean of tangent space might not be the simplest alternative. We tend to propose the employment of strong estimators of variance matrices average. Specifically, Median Absolute Deviation(MAD) going to be planned and mentioned. Associate in Nursing experimental analysis can show the advance of Tangent house Linear Discriminant Analysis corresponding to the planned strong estimators. Experimental results show that our proposed method performs 3% better than the recently developed algorithms.
  • [ X ]
    Öğe
    SPEAKER IDENTIFICATION MODEL BASED ON DEEP NURAL NETWOKS
    (College of Education, Al-Iraqia University, 2022) Ahmed, Saadaldeen Rashid; Abbood, Zainab Ali; Farhan, hameed Mutlag; Yasen, Baraa Taha; Ahmed, Mohammed Rashid; Duru, Adil Deniz
    This study aims is to establish a small system of text-independent recognition of speakers for a relatively small group of speakers at a sound stage. The fascinating justification for the International Space Station (ISS) to detect if the astronauts are speaking at a specific time has influenced the difficulty. In this work, we employed Machine Learning Applications. Accordingly, we used the Direct Deep Neural Network (DNN)-based approach, in which the posterior opportunities of the output layer are utilized to determine the speaker's presence. In line with the small footprint design objective, a simple DNN model with only sufficient hidden units or sufficient hidden units per layer was designed, thereby reducing the cost of parameters through intentional preparation to avoid the normal overfitting problem and optimize the algorithmic aspects, such as context-based training, activation functions, validation, and learning rate. Two commercially available databases, namely, TIMIT clean speech and HTIMIT multihandset communication database and TIMIT noise-added data framework, were tested for this reference model that we developed using four sound categories at three distinct signal-to-noise ratios. Briefly, we used a dynamic pruning method in which the conditions of all layers are simultaneously pruned, and the pruning mechanism is reassigned. The usefulness of this approach was evaluated on all the above contact databases. © 2022 Iraqi Journal for Computer Science and Mathematics. All rights reserved.