Determining the face of wearing a mask from not wearing a mask from visual data such as video and still, images have been a fascinating research topic in recent decades due to the spread of the Corona pandemic, which has changed the features of the entire world and forced people to wear a mask as a way to prevent the pandemic that has calmed the entire world, and it has played an important role. Intelligent development based on artificial intelligence and computers has a very important role in the issue of safety from the pandemic, as the Topic of face recognition and identifying people who wear the mask or not in the introduction and deep education was the most prominent in this topic. Using deep learning techniques and the YOLO (”You only look once”) neural network algorithm, which is an efficient real-time object identification algorithm, an intelligent system was developed in this thesis to distinguish which faces are wearing a mask and who is not wearing a wrong mask. The proposed system was developed based on data preparation, preprocessing, and adding a multi-layer neural network, followed by extracting the detection algorithm to improve the accuracy of the system. Two global data sets were used to train and test the proposed system and worked on it in three models, where the first contains the AIZOO data set, the second contains the MoLa RGB CovSurv data set, and the third model contains a combined data set for the two in order to provide cases that are difficult to identify and the accuracy results that were obtained. obtained from the merging datasets showed that the face mask (0.953) and the face recognition system were the most accurate in detecting them (0.916).
The multi-focus image fusion method can fuse more than one focused image to generate a single image with more accurate description. The purpose of image fusion is to generate one image by combining information from many source images of the same scene. In this paper, a multi-focus image fusion method is proposed with a hybrid pixel level obtained in the spatial and transform domains. The proposed method is implemented on multi-focus source images in YCbCr color space. As the first step two-level stationary wavelet transform was applied on the Y channel of two source images. The fused Y channel is implemented by using many fusion rule techniques. The Cb and Cr channels of the source images are fused using principal component analysis (PCA).
... Show More
(1)
(3)
The performance of sewage pumps stations affected by many factors through its work time which produce undesired transportation efficiency. This paper is focus on the use of artificial neural network and multiple linear regression (MLR) models for prediction the major sewage pump station in Baghdad city. The data used in this work were obtained from Al-Habibia sewage pump station during specified records- three years in Al-Karkh district, Baghdad. Pumping capability of the stations was recognized by considering the influent input importance of discharge, total suspended solids (TSS) and biological oxygen demand (BOD). In addition, the chemical oxygen demands (COD), pH and chloride (Cl). The proposed model performanc
... Show More
(7)
Aerial manipulation of objects has a number of advantages as it is not limited by the morphology of the terrain. One of the main problems of the aerial payload process is the lack of real-time prediction of the interaction between the gripper of the aerial robot and the payload. This paper introduces a digital twin (DT) approach based on impedance control of the aerial payload transmission process. The impedance control technique is implemented to develop the target impedance based on emerging the mass of the payload and the model of the gripper fingers. Tracking the position of the interactional point between the fingers of gripper and payload, inside the impedance control, is achieved using model predictive control (MPD) approach.
... Show More
(4)
(3)
The secure data transmission over internet is achieved using Steganography. It is the art and science of concealing information in unremarkable cover media so as not to arouse an observer’s suspicion. In this paper the color cover image is divided into equally four parts, for each part select one channel from each part( Red, or Green, or Blue), choosing one of these channel depending on the high color ratio in that part. The chosen part is decomposing into four parts {LL, HL, LH, HH} by using discrete wavelet transform. The hiding image is divided into four part n*n then apply DCT on each part. Finally the four DCT coefficient parts embedding in four high frequency sub-bands {HH} in
... Show More
(4)
In this paper, a national grid-connected photovoltaic (PV) system is proposed. It extracts the maximum power point (MPP) using three-incremental-steps perturb and observe (TISP&O) maximum power point tracking (MPPT) method. It improves the classic P&O by using three incremental duty ratio (ΔD) instead of a single one in the conventional P and O MPPT method. Therefore, the system's performance is improved to a higher speed and less power fluctuation around the MPP. The Boost converter controls the MPPT and then is connected to a three-phase voltage source inverter (VSI). This type of inverter needs a high and constant input voltage. A second-order low pass (LC) filter is connected to the output of VSI to reduce t
... Show More
(3)
Digital Elevation Model (DEM) is one of the developed techniques for relief representation. The definition of a DEM construction is the modeling technique of earth surface from existing data. DEM plays a role as one of the fundamental information requirement that has been generally utilized in GIS data structures. The main aim of this research is to present a methodology for assessing DEMs generation methods. The DEMs data will be extracted from open source data e.g. Google Earth. The tested data will be compared with data produced from formal institutions such as General Directorate of Surveying. The study area has been chosen in south of Iraq (Al-Gharraf / Dhi Qar governorate. The methods of DEMs creation are kriging, IDW (inver
... Show More
(1)
Data steganography is a technique used to hide data, secret message, within another data, cover carrier. It is considered as a part of information security. Audio steganography is a type of data steganography, where the secret message is hidden in audio carrier. This paper proposes an efficient audio steganography method that uses LSB technique. The proposed method enhances steganography performance by exploiting all carrier samples and balancing between hiding capacity and distortion ratio. It suggests an adaptive number of hiding bits for each audio sample depending on the secret message size, the cover carrier size, and the signal to noise ratio (SNR). Comparison results show that the proposed method outperforms state of the art methods
... Show MoreIn modern era, which requires the use of networks in the transmission of data across distances, the transport or storage of such data is required to be safe. The protection methods are developed to ensure data security. New schemes are proposed that merge crypto graphical principles with other systems to enhance information security. Chaos maps are one of interesting systems which are merged with cryptography for better encryption performance. Biometrics is considered an effective element in many access security systems. In this paper, two systems which are fingerprint biometrics and chaos logistic map are combined in the encryption of a text message to produce strong cipher that can withstand many types of attacks. The histogram analysis o
... Show More