The proliferation of many editing programs based on artificial intelligence techniques has contributed to the emergence of deepfake technology. Deepfakes are committed to fabricating and falsifying facts by making a person do actions or say words that he never did or said. So that developing an algorithm for deepfakes detection is very important to discriminate real from fake media. Convolutional neural networks (CNNs) are among the most complex classifiers, but choosing the nature of the data fed to these networks is extremely important. For this reason, we capture fine texture details of input data frames using 16 Gabor filters indifferent directions and then feed them to a binary CNN classifier instead of using the red-green-blue

Monaural source separation is a challenging issue due to the fact that there is only a single channel available; however, there is an unlimited range of possible solutions. In this paper, a monaural source separation model based hybrid deep learning model, which consists of convolution neural network (CNN), dense neural network (DNN) and recurrent neural network (RNN), will be presented. A trial and error method will be used to optimize the number of layers in the proposed model. Moreover, the effects of the learning rate, optimization algorithms, and the number of epochs on the separation performance will be explored. Our model was evaluated using the MIR-1K dataset for singing voice separation. Moreover, the proposed approach achi

In this work, the possibility of utilizing osmosis phenomenon to produce energy as a type of the renewable energy using Thin Film Composite Ultra Low Pressure membrane TFC-ULP was studied. Where by forward osmosis water passes through the membrane toward the concentrated brine solution, this will lead to raise the head of the high brine solution. This developed static head may be used to produce energy. The aim of the present work is to study the static head developed and the flux on the high brine water solution side when using forward and reverse osmosis membranes for an initial concentration range from 35-300 g/l for each type of membrane used at room temperature and pressure conditions, and finally calculating the maximum possible po

In this work Laser wireless video communication system using intensity modualtion direct
detection IM/DD over a 1 km range between transmitter and receiver is experimentally investigated and
demonstrated. Beam expander and beam collimeter were implemented to collimete laser beam at the
transmitter and focus this beam at the receiver respectively. The results show that IM/DD communication
sysatem using laser diode is quite attractive for transmitting video signal. In this work signal to noise
ratio (S/N) higher than 20 dB is achieved in this work.

The software-defined network (SDN) is a new technology that separates the control plane from data ‎plane for the network devices. One of the most significant issues in the video ‎surveillance system is the link failure. When the path failure occurs, the monitoring center cannot receive the ‎video from the cameras. In this paper, two methods are proposed to solve this problem.  The first ‎method uses the Dijkstra algorithm to re-find the path at the source node switch. The second method ‎uses the Dijkstra algorithm to re-find the path at the ingress node switch (or failed link).

  A.R. Ammons's  Garbage is a unique poem in all measures, starting from the title to the subject matter of the poem.  Though it discusses the ecological repercussion of waste management, the long poem is written to shed light on the correlation between language\poetry and garbage. The paper argues that in his examination of language\poetry and garbage as both reflectors of human life and experience, Ammons claims that redemption is possible through both language and garbage by scrutinizing human experience whether low or high, mundane or sacred. This paper tries to examine Ammons's  efforts to use the farfetched metaphor of garbage to discuss language and poetry-writing.  

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

Trip generation is the first phase in the travel forecasting process. It involves the estimation of the
total number of trips entering or leaving a parcel of land per time period (usually on a daily basis);
as a function of the socioeconomic, locational, and land-use characteristics of the parcel.
The objective of this study is to develop statistical models to predict trips production volumes for a
proper target year. Non-motorized trips are considered in the modeling process. Traditional method
to forecast the trip generation volume according to trip rate, based on family type is proposed in
this study. Families are classified by three characteristics of population social class, income, and
number of vehicle ownersh