Yazar "Alyassri, Salam" seçeneğine göre listele

Listeleniyor 1 - 7 / 7
  • [ X ]
    Öğe
    Deep transfer learning methods for classification colorectal cancer based on histology images
    (Institute of Electrical and Electronics Engineers Inc., 2022) Alhanaf, Ahmed Sami; Al-Jumaili, Saif; Bilgin, Gökhan; Duru, Adil Deniz; Alyassri, Salam; Balık, Hasan Hüseyin
    Deep transfer learning is one of the common techniques used to classify different types of cancer. The goal of this research is to focus on and adopt a fast, accurate, suitable, and reliable for classification of colorectal cancer. Digital histology images are adjustable to the application of convolutional neural networks (CNNs) for analysis and classification, due to the sheer size of pixel data present in them. Which can provide a lot of information about colorectal cancer. We used ten different types of pr-trained models with two type method of classification techniques namely (normal classification and k-fold crosse validation) to classify the tumor tissue, we used two different kinds of datasets were these datasets consisting of three classes (normal, low tumors, and high tumors). Among all these eight models of deep transfer learning, the highest accuracy achieved was 96.6% with Darknet53 for 5-Fold and for normal classification the highest results obtained was 98.7% for ResNet50. Moreover, we compared our result with many other papers in stat-of-the-art, the results obtained show clearly the proposed method was outperformed the other papers.
  • [ X ]
    Öğe
    Novel partial overlapped gaussian pulse multi-access system aided by data analysis
    (2022) Alyassri, Salam; Ilyas, Muhammad; Marhoon, Ali; Bayat, Oğuz
    Orthogonal frequency-division multi-access (OFDMA) systems have limited flexibility to improve efficiency due to their dependency on subcarrier orthogonality. As a result of this restriction, attention has shifted to a new multi-access communication method. The popularity of non-orthogonal multi-access (NOMA) systems is growing. Because the NOMA systems may broadcast and receive signals at various power levels, more complicated reception devices are required. Partially overlapped subcarriers or a non-orthogonal multi-access system are presented in this study. Instead of relying on the power level of sending signals, as is the case in present NOMA systems, the proposal relies on the benefit of modifying the shape of subcarriers to build a more efficient system. The authors propose Gaussian-pulse signals as an alternative to sites of concern for nature conservation (SINC) (SINC is the shape of subcarriers in OFDM). In this paper, there are several algorithms designed for this work. These algorithms control the distribution of frames on the transmitting subcarriers. They also calculate the width of the subcarriers as well as the spacing between the subcarriers to produce the lowest possible data error rate. The similarity values between the frames that will be sent will influence the values generated by these algorithms. So, these algorithms are to reduce the computational complexity of the system and obtain efficient channel capacity. The proposed model presents encouraging results for the bit error rate (BER) compared with OFDMA and ordinary NOMA systems. Also, Gaussian pulses with data analysis, as in the proposed schema, can achieve a reduction value in spectrum requirements by up to 13.8%. Besides, there is a decrease in out-of-band compared to OFDMA, which increases the spectrum efficiency. Finally, as compared to OFDMA, an improvement in BER with multipath fading and a Doppler frequency shifting environment was discovered in this research.
  • Küçük Resim
    Öğe
    Polygon number algorithm for peak-to-average ratio reduction of massive 5G systems using modified partial transmit sequence scheme
    (Wiley, 2021) Alkatrani, Hayder; İlyas, Muhammad; Alyassri, Salam; Nahar, Ali; Al-Turjman, Fadi; Rasheed, Jawad; Alshahrani, Ali; Al-Kasasbeh, Basil
    The high peak-to-average power ratio (PAPR) of the transmit signal is a major shortcoming of OFDM systems, which results in band radiation and distortion due to the nonlinearity of the high-power amplifier (H.P). To resolve the traditional OFDM highPAPR issue, where the transmit sequence is designed to avoid similar data from being sent in the same order to reduce PAPR, there are numerous conventional ways for lowering the PAPR for OFDM system, such as selective mapping, tone reservation, block coding, filtering, clipping, and partial transmit sequence (PTS). This study proposes a new method called polygon number algorithm (PN) with conventional partial transmit sequence (C-PTS). This method (PN-PTS) processes the entered data before sending it, taking advantage of the number nonsimilarity according to the geometry of the number to prevent direct sending of similar data via PTS, and thus, this improved the level of PAPR rise in the proposed system. The amount of reduction that can be achieved in PAPR is up to 8 dB by different techniques. The best result obtained was the amount of reduction between the conventional method and the proposed method is 4.5683 where N = 64. Besides this, there is no transmission of side information (SI), which improves transmission efficiency. Finally, this method is easy in the calculation process and the ciphering and deciphering of data, which adds a few calculations.
  • [ X ]
    Öğe
    Recent advances on convolutional architectures in medical applications: classical or quantum
    (Institute of Electrical and Electronics Engineers Inc., 2022) Al-Jumaili, Saif; Al-Jumaili, Ahmed; Alyassri, Salam; Duru, Adil Deniz; Uçan, Osman Nuri
    Deep learning is one of the most significant advances in AI (AI). It is used in a variety of fields due to it has the ability to solve problems that cannot be handled by traditional technologies. The optimization of deep learning relevant to medical images is one of the most important recent advances in image analysis. Several developments have been done on Convolutional Neural Networks to achieve optimal accuracy and increase the learning speed. However, in this paper, we discuss the most recent innovations in convolutional neural networks within Classical method and Quantum method. We briefly provide a snapshot about the architecture, improvements, and principles of both (Classical and Quantum).
  • [ X ]
    Öğe
    Reduction of packet error rate in V2V communication based on machine learning
    (IEEE, 2021) Alyassri, Salam; Ilyas, Mohammad; Marhoon, Ali; Bayat, Oğuz
    Reducing the accidents that resulted from traffic is a highly concerning issue. Automating cars or emergency communication are attempting the decrease these accidents. So improving the conditions of communication between vehicles under research. One of the improvements comes by standardizing transmitting packets, which is best executed by the 802.11p protocol. 802.11p encompasses a field that has the size value of the transmitted packet.. So this work centering on developing a powerfully adaptable packet size framework, which depends on the value of the signal-to-noise ratio (SNR). There is neural network (NN) controls to the framework, which prepared by candidate values of packet size come from an equation derived practically by testing it numerous times the connection between packet error ratios (PERs) and packet size values. The usage of the proposed framework comes about in a noteworthy diminishment in PER, and the comes about were appeared by practice the proposed framework and two other frameworks, one of them is satisfied without channel tracking whereas the moment had channel tracking. The comparison for band 10MHz appears there's a 46.6 percent and 36.88 percent average decrease in PER values compared to not tracking the channel and tracking the channel, separately. Comes about average improving the PER values for band 20MHz were 18 percent for the without-channeltracking and 66.91 percent for the with-channel-tracking frameworks. As a result, the inspiration to utilize NN, which is one field of machine learning (ML), was figured out. Besides, this work persuades more researches that got to be done applying the ML into the vehicle to vehicle (V2V) communication.
  • [ X ]
    Öğe
    Survey of general communication based on using deep learning autoencoder
    (Institute of Electrical and Electronics Engineers Inc., 2022) Mohammed, Mohaimen; Çevik, Mesut; Alyassri, Salam
    The growth of artificial intelligence opened several horizons and fields that made researchers more curious about the progress in this field, especially the growth of deep learning and its entry into the world of communications such as autoencoder, and this is likely due to its ability to bypass the impact of the noise that the signal suffered by denoising feature. In this field, there are many research papers, most of which are mentioned in this review, to produce a research paper that can be considered as a reference for researchers who wish to know the most prominent research findings included in this topic. The results were categorized based on (Challenges trying solved, type of system, channel types, system parameters, and findings) and it was found that there was a difference in the variables used in the mentioned research.
  • [ X ]
    Öğe
    Unique MIMO system using Gaussian signals and the advantage of these signals in sensing CSI and multipath fading
    (John Wiley and Sons Ltd, 2025) Alyassri, Salam; Ilyas, Muhammad; Aljumaily, Mustafa S.; Al-jumaili, Saif; Duru, Adil Deniz
    To improve communication network efficiency, researchers must look at all aspects of transmission and the mechanisms that regulate their evolution as a whole. These features include solutions for dealing with the channel's noise and interference. To decrease interference and increase spectrum efficiency, orthogonal frequency division multiple access (OFDMA) systems employ orthogonal signals. While transmitting and receiving signals, noise and numerous feeds can be done in diverse ways. It has become increasingly common to use 256 quadratic modulation (QAM), which is more vulnerable to noise and has a higher bit error rate (BER). BERs in OFDM systems were high when multiple feeds and noise were present, as demonstrated in this article. Starting with the transmission and reception of Gaussian subband signals, an improved system has been designed that includes numerous stages of development. Thus, the need for “orthogonally” of transmitted signals to increase spectrum efficiency has been eliminated, as has the effect of surrounding channels. We have created a header for every frame that has been transmitted. Several transmitters and numerous receivers send these frames in parallel so that the channel state information (CSI) attributes may be evaluated using parallel processing. Using the identical transmission conditions for both OFDM systems and the proposed system, the simulation results reveal a significant reduction in BER values. This results in BER values of fewer than 10−1 when there are two tabs and 10−1 when there are three tabs for multiple feeding in the OFDM system. This corresponds to BER values of 10−11 in a suggested system when there are three tabs. Some improvements have been made to the proposed design to make it distinctive and qualified to be regarded as a multiaccess system in today's contemporary communication infrastructures.