Yazar "Ibrahim, Abdullahi A." seçeneğine göre listele
Listeleniyor 1 - 4 / 4
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A novel miniaturized reconfigurable microstrip antenna based printed metamaterial circuitries for 5G applications(2022) Al-Khaylani, Hayder H.; Elwi, Taha A.; Ibrahim, Abdullahi A.A novel reconfigurable sub-6 GHz microstrip patch antenna operating at three resonant frequencies 3.6, 3.9, and 4.9 GHz is designed for 5G applications. The proposed antenna is constructed from metamaterial (MTM) array with a matching circuit printed around a printed strip line. The antenna is excited with a coplanar waveguide to achieve an excellent matching over a wide frequency band. The proposed antenna shows excellent performance in terms of S11, gain, and radiation pattern that are controlled well with two photo resistance. The proposed antenna shows different operating frequencies and radiation patterns after changing the of photo resistance status. The main antenna novelty is achieved by splitting the main lobe that tracks more than one user at same resonant frequency. Nevertheless, the main radiation lobe can be steered to the desired location by controlling the surface current motion using two varactor diodes on a matching circuit.Öğe Brain Tumor Detection and Classifiaction Using CNN Algorithm and Deep Learning Techniques(Institute of Electrical and Electronics Engineers Inc., 2020) Fayyadh, Sultan B.; Ibrahim, Abdullahi A.Detection of brain tumors through image processing is done by using an integrated approach. This work was planned to present a system to classify and detect brain tumors using the CNN algorithm and deep learning techniques from MRI images to the most popular tumors in the world. This work was performed using an MRI image dataset as input, Preprocessing and segmentation were performed to enhance the images. Our neural network design is simpler to train and it's possible to run it on another computer because the designed algorithm requires fewer resources. The dataset was used contains 3064 images related to different tumors meningioma (708 slices), glioma (1426 slices), and pituitary tumor (930 slices), the convolution neural network (CNN) was used through which the brain tumor is classified according to a special structure of this algorithm consisting of several layers, The implementation of the neural network consist blocks each block include many types of layer, first, the input layer then followed by convolution layer, then the activation function that used was Rectified Linear Units (ReLU), normalization layer, and pooling layer. Also, it contains the classification layer fully connected and softmax layer the overall accuracy rate obtained from the proposed approach was (98,029%) in the testing stage and (98.29%) in the training stage for the data set were used. © 2020 IEEE.Öğe Forest fire detection techniques based on IoT technology: review(Institute of Electrical and Electronics Engineers Inc., 2023) Radhi, Ahmed A.; Ibrahim, Abdullahi A.Protecting forests from fires is very important, as they are vast areas that contain many resources that serve life on Earth, as well as their impact on the climate. Despite all the strenuous attempts to reduce wildfires, they still persist and cause environmental disasters. In recent years, researchers have been interested in the early detection of forest fires by using different technologies, such as using satellite images and drones, in addition to using sensors and network systems (wireless sensor networks), and after the development of networks and the emergence of the Internet of Things technology, which has become the focus of researchers' attention, By linking it to other technologies. This article discusses the types of forest fires, their causes, and their effects on the environment, as well as a literature review of some researchers interested in detecting forest fires, in addition to some statistics on forest fires. Some of the techniques used to detect forest fires have been explained, as well as the methodologies used by these techniques to detect wildfires, in addition to a comparison between them. A comparison discussion of the techniques used in detecting forest fires showed that the Internet of Things technology is the best in the early detection of fires and at the lowest costs, with the improvement of the sensor nodes localization, as well as the improvement routing of data transmission over the network by using optimization algorithms.Öğe Novel semi-supervised learning approach for descriptor generation using artificial neural networks(Springer, 2022) Alwindawi, Alla Fikrat; Uçan, Osman Nuri; Ibrahim, Abdullahi A.; Yusuf, AminuThe rise of machine learning and neural networks has opened many doors for making various arduous real-life tasks far more accessible, in addition to their ability to analyze vast amounts of data that are considered to be impossible for humans to process. Neural networks are an essential topic as they can be applied in many real-life applications, such as image, video and sound matching, making them a very attractive research area. Numerous methods and approaches are available for training neural networks, but this paper is concerned with only the semi-supervised training approach, for which a new ‘‘enhanced semi-supervised’’ learning method is proposed. Semi-supervised learning means that machines, such as computers, can learn in the presence of datasets that are both labeled and unlabeled. In contrast, the supervised learning approach can be applicable with labeled data only. A novel semi-supervised learning approach for descriptor generation using artificial neural networks is proposed to control the values that are output by the neural network. However, no interaction with the assignment of these values to each input group occurs, nor is the space where the output values belong utilized. Thus, this method seeks to provide a more efficient learning approach with a more even distribution of the output throughout the output field of space, resulting in a more effective learning approach. The handwritten digit experiment showed an accuracy of 85.27%, while Alzheimer’s detection experiment recorded an accuracy of 99.27%. The results after applying the proposed method to two sets of experimental data revealed a significant improvement in accuracy compared with the use of Siamese neural networks in different applications.
