The digital world has been witnessing a fast progress in technology, which led to an enormous increase in using digital devices, such as cell phones, laptops, and digital cameras. Thus, photographs and videos function as the primary sources of legal proof in courtrooms concerning any incident or crime. It has become important to prove the trustworthiness of digital multimedia. Inter-frame video forgery one of common types of video manipulation performed in temporal domain. It deals with inter-frame video forgery detection that involves frame deletion, insertion, duplication, and shuffling. Deep Learning (DL) techniques have been proven effective in analysis and processing of visual media. Dealing with video data needs to handle the third dimension (the time dimension), which means extracting temporal features as well as spatial features. The proposed model is built based on the Three Dimension Convolution Neural Network (3D-CNN). Through pre-processing operation that introduced difference frames that pick up the difference in successive adjacent frames, which provide a large quantity of temporal information and lead to enhance the effectiveness of the proposed model. The model achieves high accuracy of 99%.
Research in the field of English language as a foreign language (EFL) has been consistently highlighted the need for communicative competence skills among students. Accompanied by the validated positive impact of technologies on students’ skills’, this study aims to explore the strategies used by EFL students in enhancing their communicative competence using digital platforms and identify the factors of developing communicative competence using digital platforms (linguistic factors, environmental factors, psychological factors, and university-related factors). The mixed-method research design was utilized to obtain data from Iraqi undergraduate EFL students. The study was conducted in the Iraqi University in Baghdad Iraq. EFL undergradu
... Show MoreCorrect grading of apple slices can help ensure quality and improve the marketability of the final product, which can impact the overall development of the apple slice industry post-harvest. The study intends to employ the convolutional neural network (CNN) architectures of ResNet-18 and DenseNet-201 and classical machine learning (ML) classifiers such as Wide Neural Networks (WNN), Naïve Bayes (NB), and two kernels of support vector machines (SVM) to classify apple slices into different hardness classes based on their RGB values. Our research data showed that the DenseNet-201 features classified by the SVM-Cubic kernel had the highest accuracy and lowest standard deviation (SD) among all the methods we tested, at 89.51 % 1.66 %. This
... Show MoreThe study area of Baghdad region and nearby areas lies within the central part of the Mesopotamia plain. It covers about 5700 Km2. The remote sensing techniques are used in order to produce possible Land Use – Land Cover (LULC) map for Baghdad region and nearby areas depending on Landsat TM satellite image 2007. The classification procedure which was developed by USGS used and followed with field checking in 2010. Land Use-land cover digital map is created depending on maximum likelihood classifications (ML) of TM image using ERDAS 9.2.The LULC raster image is converted to vector structure, using Arc GIS 9.3 Program in order to create a digital LULC map. This study showed it is possible to produce a digital map of LULC and it can be co
... Show MoreNecessary and sufficient conditions for the operator equation I AXAX n  ï€* , to have a real positive definite solution X are given. Based on these conditions, some properties of the operator A as well as relation between the solutions X andAare given.
This paper presents results about the existence of best approximations via nonexpansive type maps defined on modular spaces.
Nowadays, people's expression on the Internet is no longer limited to text, especially with the rise of the short video boom, leading to the emergence of a large number of modal data such as text, pictures, audio, and video. Compared to single mode data ,the multi-modal data always contains massive information. The mining process of multi-modal information can help computers to better understand human emotional characteristics. However, because the multi-modal data show obvious dynamic time series features, it is necessary to solve the dynamic correlation problem within a single mode and between different modes in the same application scene during the fusion process. To solve this problem, in this paper, a feature extraction framework of
... Show MoreThe aim of the research is to investigate potential effects of the finance industry and block-chain to general business of financing in particular, as well as its shortcomings and difficulties. To answer the research questions, the researcher used the objective narrative-analytical descriptive approach and included a qualitative analysis of Blockchain technology. The process of Blockchain technology based on their industries, the authors were selected based on their reputation in the Blockchain field. The research found that Blockchain can improve the efficiency of the banking industry's various sections. It has the ability to upgrade and transfer wages across borders, financial reporting and compliance, as well as trade finance
... Show MoreThe main objective of e-learning platforms is to offer a high quality instructing, training and educational services. This purpose would never be achieved without taking the students' motivation into consideration. Examining the voice, we can decide the emotional states of the learners after we apply the famous theory of psychologist SDT (Self Determination Theory). This article will investigate certain difficulties and challenges which face e-learner: the problem of leaving their courses and the student's isolation.
Utilizing Gussian blending model (GMM) so as to tackle and to solve the problems of classification, we can determine the learning abnormal status for e-learner. Our framework is going to increase the students’ moti
This paper discusses the method for determining the permeability values of Tertiary Reservoir in Ajeel field (Jeribe, dhiban, Euphrates) units and this study is very important to determine the permeability values that it is needed to detect the economic value of oil in Tertiary Formation. This study based on core data from nine wells and log data from twelve wells. The wells are AJ-1, AJ-4, AJ-6, AJ-7, AJ-10, AJ-12, AJ-13, AJ-14, AJ-15, AJ-22, AJ-25, and AJ-54, but we have chosen three wells (AJ4, AJ6, and AJ10) to study in this paper. Three methods are used for this work and this study indicates that one of the best way of obtaining permeability is the Neural network method because the values of permeability obtained be
... Show MorePredicting the network traffic of web pages is one of the areas that has increased focus in recent years. Modeling traffic helps find strategies for distributing network loads, identifying user behaviors and malicious traffic, and predicting future trends. Many statistical and intelligent methods have been studied to predict web traffic using time series of network traffic. In this paper, the use of machine learning algorithms to model Wikipedia traffic using Google's time series dataset is studied. Two data sets were used for time series, data generalization, building a set of machine learning models (XGboost, Logistic Regression, Linear Regression, and Random Forest), and comparing the performance of the models using (SMAPE) and
... Show More