Yazar "Ahmed, S.R." seçeneğine göre listele

Listeleniyor 1 - 7 / 7
  • Küçük Resim Yok
    Öğe
    Analysis Survey on Deepfake detection and Recognition with Convolutional Neural Networks
    (Institute of Electrical and Electronics Engineers Inc., 2022) Ahmed, S.R.; Sonuc, E.; Ahmed, M.R.; Duru, A.D.
    Deep Learning (DL) is the most efficient technique to handle a wide range of challenging problems such as data analytics, diagnosing diseases, detecting anomalies, etc. The development of DL has raised some privacy, justice, and national security issues. Deepfake is a DL-based application that has been very popular in recent years and is one of the reasons for these problems. Deepfake technology can create fake images and videos that are difficult for humans to recognize as real or not. Therefore, it needs to be proposed some automated methods for devices to detect and evaluate threats. In another word, digital and visual media must maintain their integrity. A set of rules used for Deepfake and some methods to detect the content created by Deepfake have been proposed in the literature. This paper summarizes what we have in the critical discussion about the problems, opportunities, and prospects of Deepfake technology. We aim for this work to be an alternative guide to getting knowledge of Deepfake detection methods. First, we cover Deepfake history and Deepfake techniques. Then, we present how a better and more robust Deepfake detection method can be designed to deal with fake content. © 2022 IEEE.
  • Küçük Resim Yok
    Öğe
    A Descriptive Statistical Analysis of Overweight and Obesity Using Big Data
    (Institute of Electrical and Electronics Engineers Inc., 2022) Ali, S.A.G.; Al-Fayyadh, H.R.D.; Mohammed, S.H.; Ahmed, S.R.
    In this paper, we have obtained the dataset from an open-source repository for obese people by focused on a descriptive statistical analysis of overweight and obesity using big data. We performed the statistical analysis on large scale streaming data for obesity prediction. We have classified the obesity with all categories on the scale of Body Mass Index (BMI) is being calculated i.e., underweight, normal weight, overweight, obese, very obese, and extremely obese using MapReduce technique with the help of Apache Spark and Apache Hadoop engine in pydoop python programming. The MapReduce technique in-volves the updating of cluster centers after arrival of new batch in the stream of data. The streaming of data is produced by the sensors which are classified into six different BMI categories, which are stored and processed through big data tools connected to the statistical analysis system. The Apache spark produces the latency values in accessing the data from dataset. We analyzed any obesity in the people from the normal latency value using the Apache spark and Hadoop which are well known in big data. The methods and techniques by which we can predict obesity efficiently from the large-scale streaming data has been per-formed using python programming. This is applied with the help of Apache Spark and Hadoop. In order to validate the efficiency of MapReduce technique. We have tested it both on single and distributed environment for obesity prediction using the built-in Pydoop package in python. © 2022 IEEE.
  • Küçük Resim Yok
    Öğe
    Design and fabrication of UWB microstrip Antenna on different substrates for wireless Communication system
    (Institute of Electrical and Electronics Engineers Inc., 2022) Ahmed, O.; Thaher, R.H.; Ahmed, S.R.
    A new shape of microstrip antenna is proposed that operates in the 5G Sub band with size 26times 30times 1-6)mm3 ' and the effect of changing the suberate on the performance of the antenna was Investigated; the antenna is Installed using the Roger 8850 Substrata with relative dielectric Constant in_mathrmr=2,2 and loss tangent tan partial=0.009 The Effect of Changing the Substrate t_0in_r=4.3, in_r=6,15) is studied, it is found that these substrates affect the return loss (S11), gain, and group delay. It is found that in_r=2,2 provides better return loss and group delay, whereas the Substrate with in r=6,15 gives better gain; therefore, the Substrate selection depends on the required performance factor. The antennas were fabricated using Rogers Substrata with a relative dielectric constant of in_r=2,2 and tested using the Vector Network Analyzer; it was found that the Simulation and experimental results are in reasonable agreement. © 2022 IEEE.
  • Küçük Resim Yok
    Öğe
    A New Approach to Study the Challenges of E-Learning Advantages and Disadvantage
    (IOP Publishing Ltd, 2021) Alkaragole, M.; Karim, S.M.; Ahmed, S.R.
    In this paper, we have a tendency to tried to explore the challenges in implication of E-Learning and its benefits and downsides. There are some problems for not implementing E-Learning as there's some lacking's of understanding concerning E-Learning to the teacher additionally the scholars and have some issue that bothers to just accept E-Learning instead of ancient learning surroundings, and our main target is to seek out the explanation behind at purpose there's some opinion concerning the challenges for not implementing E-Learning. E-Learning surroundings is principally an online bases platform in academic section mistreatment technology, the aspects of E-Learning surroundings is mistreatment digital tools in courses of study, it presents the ways, tasks, and therefore the connections between a course structure and introduced new assessment in numerous stages. The aim of this study is to spot what challenges or that factors are the explanation for not applying E-Learning normally additionally it'll concentrate on what challenges lecturers and what issues students suffers in learning through virtual policy separately by this it'll helps to seek out the views of E-Learning of lecturers and student each. currently a day's E-Learning is known in academic sites. E-Learning surroundings is principally student targeted. It's essentially virtual resource area, wherever student should get to be liable for their own work, because it may be a self-format study therefore student should have privy to their responsibility. I attempted to explore the challenges in implication E-Learning, because the outcome is affirmative there are some problems for not implementing E-Learning as there's some lacking's of understanding concerning E-Learning to the teacher additionally the scholars and have some issue that bothers to just accept E-Learning instead of ancient learning surroundings, and my main target is to seek out the explanation behind at purpose there's some opinion concerning the challenges for not implementing E-Learning. © Published under licence by IOP Publishing Ltd.
  • Küçük Resim Yok
    Öğe
    A Photovoltaic Electric Vehicle Automatic Charging and Monitoring System
    (Institute of Electrical and Electronics Engineers Inc., 2022) Niu, Y.; Habeeb, F.A.; Mansoor, M.S.G.; Gheni, H.M.; Ahmed, S.R.; Radhi, A.D.
    This paper researches and designs an automatic charging control and monitoring system for PV electric vehicle batteries, which can automatically charge the low-voltage and high-voltage batteries by obtaining the operation mode of PV electric vehicles, avoiding battery maintenance to the maximum extent, preventing damage to the battery cell caused by over-discharge, and increasing the range of the whole vehicle. Suppose the PV EV is in parking mode. In that case, it will obtain the power of the low-voltage battery in real-Time and charge the low-voltage battery according to the request, and then it will obtain the power of the high-voltage battery and send a power-up request to charge the high-voltage battery according to the request; if the PV EV is in driving mode, it will obtain the power of the low-voltage battery in real-Time and generate a power-up request according to the power-up request. When the PV electric vehicle is in driving mode, it will obtain the low voltage battery power condition in real-Time and send a request to recharge the low voltage battery. © 2022 IEEE.
  • Küçük Resim Yok
    Öğe
    SPEAKER IDENTIFICATION MODEL BASED ON DEEP NURAL NETWOKS
    (College of Education, Al-Iraqia University, 2022) Ahmed, S.R.; Abbood, Z.A.; Farhan, H.M.; Yasen, B.T.; Ahmed, M.R.; Duru, A.D.
    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.
  • Küçük Resim Yok
    Öğe
    Survey On Recognition Hand Gesture By Using Data Mining Algorithms
    (Institute of Electrical and Electronics Engineers Inc., 2022) Khalaf, L.I.; Aswad, S.A.; Ahmed, S.R.; Makki, B.; Ahmed, M.R.
    We investigated the usage of hand motion recognition using data mining approaches. In gesture detection applications, I've discovered that employing data mining to recognize hand motions has several advantages. To begin, we employ data mining to recognize bandwidth hand motions. Second, we have a high temporal resolution, which is great for data mining. A short-range, close-pulse broadcast signal is required in most cases. The frequency components of the data mining for hand gesture recognition are the same as the pulse, but the phase components are different. Our vision must be strong enough to differentiate a far hand from distant things. Data mining is equal to recognizing hand motions by heart rate divided by length in these categorized articles. Obtaining significant power for a brief period. © 2022 IEEE.