ملخص البحث :

Generally, the things that have the great role in facilitating the emergence of internet-connected sensory devices can be embodied in the developments that happen in the sphere of software, hardware, and communication technologies. The internet-connected sensory devices present perceptions and measurements of data from the real world. It is suggested that nearly through 2020, the total use of internet-connected devices may reach to 25 to 50 billion. Actually, the relation between technologies and the volume of data being published is kept in one line. That is, if there is growth in the technologies, the volume of the data will be increased. Such technology, ie internet-connected devices, can be called as Internet of Things (IoT). Its role is to connect the real world with the cyber one. Furthermore, generating great data with velocity as its main characteristic will help in increasing the volume of IoT. To develop smart IoT applications, one can use such intelligent processing and analyzing such big data. In this paper, we tend to study the impact of implementing machine learning (ML) algorithms and methods and their efficiency in the IoT domain. As well as explore how these algorithms help in founding efficient backbone solutions to analyze and estimate the huge amounts of data that are expected to arise in the coming few years due to the rapid growth on demands for IoT based applications.

ملخص البحث :

Given the importance of agriculture, food supply, and food security, as well as population growth, the use of state-of-the-art technologies to increase agricultural productivity and mechanization with the least amount of loss and damage to crops and human beings has been highly prioritized. A great body of research has been conducted on and many solutions have been adopted for agricultural mechanization and reduced and optimized consumption of the available herbicides. Using convolutional neural networks and deep learning, this study sought to increase the accuracy of detecting grapes in the vineyard and of weeds in fields. For this purpose, the VGG16 Standard was utilized. The results indicated a 99% learning accuracy in the learning section for grape and weed detection. The validation and the final accuracy of detection for the machine designed was 63% for grapes detection and 95% for weeds. It was also demonstrated that the proposed method outperformed the KNN, decision tree, and random forest algorithms compared to the other algorithms and methods.

ملخص البحث :

The growth and development of universities, just as other organizations, depend on their abilities to strategically plan and implement development blueprints which are in line with their vision and mission statements. The actualizations of these statements, which are often designed into goals and sub-goals and linked to their respective actors are better measured by defining key performance indicators (KPIs) of the university. The proposes ReGADaK, which is an extended the GRAnD approach highlights the facts, dimensions, attributes, measures and KPIs of the organization. The measures from the goal analysis of this unit serve as the basis of developing the related university’s KPIs. The proposed data warehouse schema is evaluated through expert review, prototyping and usability evaluation. The findings from the evaluation processes suggest that the proposed data warehouse schema is suitable for monitoring the University’s KPIs.

ملخص البحث :

Cancer is one of the most common causes of mortality today. This disease's complications impose many costs on the human community's health, care, and well-being sectors. Solving complex biological problems requires advanced computational methods, and bioinformatics was created to solve such complex problems with the active interaction of several fields of science. Bioinformatics is an interdisciplinary science combining biological sciences, computers, mathematics, and statistics. The issue investigated in this research deals with one of the challenging issues in bioinformatics, namely candidate gene prioritization in breast cancer. Gene prioritization means sorting genes based on their relevance to a specific disease, such as breast cancer. Finally, the genes are checked according to their importance in performing costly experiments. The proposed approach in this research is to present a method based on graph mining for prioritizing genes. The study conducted with ENDEAOUR and DIR methods was compared and evaluated. The evaluation results show that the designed method is more efficient than other compared methods.

ملخص البحث :

DeepFake is a concern for celebrities and everyone because it is simple to create. DeepFake images, especially high-quality ones, are difficult to detect using people, local descriptors, and current approaches. On the other hand, video manipulation detection is more accessible than an image, which many state-of-the-art systems offer. Moreover, the detection of video manipulation depends entirely on its detection through images. Many worked on DeepFake detection in images, but they had complex mathematical calculations in preprocessing steps, and many limitations, including that the face must be in front, the eyes have to be open, and the mouth should be open with the appearance of teeth, etc. Also, the accuracy of their counterfeit detection in all previous studies was less than what this paper achieved, especially with the benchmark Flickr faces high-quality dataset (FFHQ). This study proposed, a new, simple, but powerful method called image Re-representation by combining the local binary pattern of multiple-channel (IR-CLBP-MC) color space as an image re-representation technique improved DeepFake detection accuracy. The IRCLBP- MC is produced using the fundamental concept of the multiple-channel of the local binary pattern (MCLBP), an extension of the original LBP. The primary distinction is that in our method, the LBP decimal value is calculated in each local patch channel, merging them to re-represent the image and producing a new image with three color channels. A pretrained convolutional neural network (CNN) was utilized to extract the deep textural features from twelve sets of a dataset of IR-CLBP-MC images made from different color spaces: RGB, XYZ, HLS, HSV, YCbCr, and LAB. Other than that, the experimental results by applying the overlap and non-overlap techniques showed that the first technique was better with the IR-CLBP-MC, and the YCbCr image color space is the most accurate when used with the model and for both datasets. Extensive experimentation is done, and the high accuracy obtained are 99.4% in the FFHQ and 99.8% in the CelebFaces Attributes dataset (Celeb-A).

ملخص البحث :

Deepfake is a type of artificial intelligence used to create convincing images, audio, and video hoaxes and it concerns celebrities and everyone because they are easy to manufacture. Deepfake are hard to recognize by people and current approaches, especially high-quality ones. As a defense against Deepfake techniques, various methods to detect Deepfake in images have been suggested. Most of them had limitations, like only working with one face in an image. The face has to be facing forward, with both eyes and the mouth open, depending on what part of the face they worked on. Other than that, a few focus on the impact of pre-processing steps on the detection accuracy of the models. This paper introduces a framework design focused on this aspect of the Deepfake detection task and proposes pre-processing steps to improve accuracy and close the gap between training and validation results with simple operations. Additionally, it differed from others by dealing with the positions of the face in various directions within the image, distinguishing the concerned face in an image containing multiple faces, and segmentation the face using facial landmarks points. All these were done using face detection, face box attributes, facial landmarks, and key points from the MediaPipe tool with the pre-trained model (DenseNet121). Lastly, the proposed model was evaluated using Deepfake Detection Challenge datasets, and after training for a few epochs, it achieved an accuracy of 97% in detecting the Deepfake.