Yazar "Ahmed, Saadaldeen Rashid Ahmed" seçeneğine göre listele

Listeleniyor 1 - 6 / 6
  • [ X ]
    Öğe
    Brest cancer detection and image evaluation using amugented deep convolutional neural network
    (Altınbaş Üniversitesi, Lisansüstü Eğitim Enstitüsü, 2019) Ahmed, Saadaldeen Rashid Ahmed; Uçan, Osman Nuri; Duru, Adil Deniz
    Meme kanseri, dünyada insan ölümüne sebep olan başlıca hastalıklardan biridir.Erken teşhis, doğru tedavinin geliştirilmesini ve sağ kalma olasılığını arttırır, ancak bu süreç belirsizdir ve düzenli olarak patologlar arasında bir çelişki yaratır. bilgisayar destekli sonuç sistemlerinin, görüntü kesinliğini arttırmada belirli potansiyele sahip olduğu belirtilir.Bu çalışmada, göğüste kötü huylu büyüme histolojisi resim karakterizasyonu için artırılmış derin evrişimsel sinir sistemlerine bağlı olan hesaplama metodolojisini geliştiriyoruz. Metodolojimiz birkaç derin sinir sistemi yapısı kullanır ve meyilli sinir ağı sınıflandırılmasına yardımcı olur.3 sınıf gruplandırma, İyi huylu, kötü huylu ve normal / istilacı olarak tanımlanır.Yüksek güvenilirlik çalışma noktasında% 88,3 kesinlik ve% 86,2 kabul edilebilirlik rapor ediyoruz.Herhangi biri söz konusu olduğunda, bu metodoloji bilgisayarlı görüntü gruplamadaki diğer temel teknikleri uygular.Farklı ağ mimarilerini ve eğitim yapılandırmalarını test ettikten sonra, evrişimselağların meme kanseri lezyonlarını umut verici sonuçlarla bölümlere ayırabildiğini gösterdik. Ayrıca, bu performans sadece daha zengin veri setleri mevcut olduğunda artacaktır.Bu yönde araştırmaları destekliyoruz. Farklı ağ mimarilerini ve eğitim yapılandırmalarını test ettikten sonra, derin evrimsel ağların meme kanseri lezyonlarını ümit verici sonuçlarla bölümlere ayırabildiğini gösterdik. Ayrıca, bu performans sadece daha zengin veri setleri mevcut olduğunda artacaktır.Bu yönde araştırmaları teşvik ediyoruz.Bu çalışmada kullandığımız teknikler çığır açıcıdır ve sonuçlarımız stratejiyi temelden değiştirmeden daha fazla hesaplamaya dayalı değerler uygulayarak kullanılan yöntemlerle geliştirilebilir.İşbu yazıda, kanserli tümörlerin tespiti ve sınıflandırılması için çok az hazırlık yapılarak yeniden renklendirilmiş olarak göğüste kötü huylu histolojikbüyüme görüntülerinin düzenlenmesi için basit ve güçlü bir strateji öneriyoruz.
  • Küçük Resim
    Öğe
    Clustering algorithms subjected to K-mean and gaussian mixture model on multidimensional data set
    (International University of Sarajevo, 2019) Ahmed, Saadaldeen Rashid Ahmed; Al-Barazanchi, Israa; Jaaz, Zahraa; Abdulshaheed, Haider Rasheed
    This paper explored the method of clustering. Two main categories of algorithms will be used, namely k-means and Gaussian Mixture Model clustering. We will look at algorithms within thesis categories and what types of problems they solve, as well as what methods could be used to determine the number of clusters. Finally, we will test the algorithms out using sparse multidimensional data acquired from the usage of a video games sales all around the world, we categories the sales in three main standards of high sales, medium sales and low sales, showing that a simple implementation can achieve nontrivial results. The result will be presented in the form of an evaluation of there is potential for online clustering of video games sales. We will also discuss some task specific improvements and which approach is most suitable. © 2019 International University of Sarajevo.
  • Küçük Resim
    Öğe
    Detection of vehicle with Infrared images in road traffic using YOLO computational mechanism
    (IOP Publishing Ltd, 2020) Mahmood, Mohammed Thakir; Ahmed, Saadaldeen Rashid Ahmed; Ahmed, Mohammad Rashid Ahmed
    Vehicle counting is an important process in the estimation of road traffic density to evaluate the traffic conditions in intelligent transportation systems. With increased use of cameras in urban centers and transportation systems, surveillance videos have become central sources of data. Vehicle detection is one of the essential uses of object detection in intelligent transport systems. Object detection aims at extracting certain vehicle-related information from videos and pictures containing vehicles. This form of information collection in intelligent systems is faced with low detection accuracy, inaccuracy in vehicle type detection, slow processing speeds. In this research, we propose a vehicle detection system from infrared images using YOLO (You Look Only Once) computational mechanism. The YOLO mechanism can apply different machine or deep learning algorithms for accurate vehicle type detection. In this study we propose an infrared based technique to combine with YOLO for vehicle detection in traffic. This method will be compared with a machine learning technique of K-means++ clustering algorithm, a deep learning mechanism of multitarget detection and infrared imagery using convolutional neutral network © Published under licence by IOP Publishing Ltd.
  • Küçük Resim
    Öğe
    Lung cancer classification using data mining and supervised learning algorithms on multi-dimensional data set
    (International University of Sarajevo, 2019) Ahmed, Saadaldeen Rashid Ahmed; Al-Barazanchi, Israa; Mhana, Ammar; Abdulshaheed, Haider Rasheed
    These With recent developments in machine learning, data mining and computer vision, there is great potential for improvements in early detection of lung cancer using scans and data available. This paper details the methods and techniques used in our project, where the objective is to develop algorithms to determine whether a patient has or is likely to develop lung cancer using dataset images using data mining and machine learning for the classification and examination. We explore approaches to address the problem. Cancer is the most important cause of death globally. The disease diagnosis is a major process to treat the patients who are affected by cancer disease. The diagnosis process is more difficult comparatively known about the cancer disease detection. Developing a proposed data mining model is useful to diagnose the cancer disease once the cancer detection is accomplished using data mining for the examination and classification of machine learning supervised algorithms. © 2019 International University of Sarajevo.
  • [ 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.
  • Küçük Resim
    Öğe
    Real time sleep onset detection from single channel EEG signal using block sample entropy
    (IOP Publishing Ltd, 2020) Zobaed, Talha; Ahmed, Saadaldeen Rashid Ahmed; Miah, Abu Saleh Musa; Binta, Salma Masuda; Ahmed, Mohammed Rashid Ahmed; Rashid, Mamunur
    In recent years, driver's temporary state has been one in each of the foremost causes of road accidents and would possibly lead to severe physical damaging, mortality and necessary and noticeable economic losses. Maximum road accidents possible to avoided, if possible, to properly monitored driver's drowsiness and a system are given warnings. In this work, a simple and inexpensive method has been offered to detect driver's drowsiness or sleep onset detection with single channel EEG signal analysis. The key novelty of this work is to identify the sleep onset detection from a publicly available graph signal dataset by exploitation only one feature, simply implementable filter in any microcontroller device or smartphone and a threshold based mostly classification. Since, threshold-based classification techniques don't need to train the classifier, hence, new subject adaptation is comparatively easier and real time implementation is more feasible. This novel approach can be easily implemented in smartphone to design and expand a drowsiness detection and alarming system for vehicle's driver. On a variety of subjects, the experimental results show 95.68% accuracy. © 2020 Published under licence by IOP Publishing Ltd.