Journal of Artificial Intelligence in Electrical Engineering
Volume:10 Issue: 37, Spring 2021

One of the most time-consuming parts of video encoding is motion estimation. Motion estimation is an important part of video encoding that improves the amount and accuracy of compression by exploiting the temporal similarity between successive frames. This action is the main cause of maximum compression in the video, which imposes the minimum quality loss on the video. In order to be able to compensate the movement, it is necessary to first find the value of the movement direction, which is called movement estimation.By doing motion estimation, instead of sending repeated information at consecutive times, the difference between consecutive frames is encoded and sent in different ways. Generally, a motion estimator in video encoding includes fractional pixel motion estimation (FME) and integer pixel motion estimation (IME). The FME method provides better performance with the cost of computational complexity and estimation time on the encryption process.

Nowadays, accuracy, speed and flexibility in making decision and the ability to predict the future have an important role , All organizations and institutions make a competitive advantage by accessing to significant information at the moment and making accurate and rapid decision . one of the bridges to reach that goal is to recognize and use artificial intelligence in organizations and institutions . artificial intelligence is one of the sciences that has made remarkable progress in science in the past decades . It is clear that this progress isn’t limited to a particular science, but also includes all the sciences, even the humanities. Artificial Intelligence (AI) is a way to intelligent computers , generally ,in fact creating the ability of human insight and understanding in machines , is one the targets of this newborn phenomenon is that there is a long distance to reach , make a machine with thought and human understanding power .About the influence and application of artificial intelligence in project management , every construction project is associated with risks and uncertainties , These include risks related to work allocation, project costs, and construction management. Machine learning is a section of artificial intelligence that has many applications in project management. Including the first category of problems in the project process, reducing project time, monitoring of structural safety, monitoring of project safety and workforce, structural analysis and prevention of earthquake crises, concrete and soil laboratory estimates are including artificial intelligence applications in project management. in this article we will concentrate on introduction to artificial intelligence and the impact and applications of artificial intelligence in project management.

Three-phase induction motors as widely used electric drives in industry, automation, transportation and electric vehicles are mainly controlled by two conventional methods, vector control (VC) and direct torque control (DTC). The vector control method has a suitable steady state response, but in terms of dynamics and time to reach the steady state, it provides a relatively slower response. In contrast, the direct torque control method works almost the opposite way and provides a better dynamic response. Therefore, providing a control strategy that combines the advantages of the two mentioned methods as much as possible improves the driving performance of the induction motor. This paper presents a hybrid control method based on the optimal keying table to select the appropriate keying modes for the induction motor drive converter to improve the output dynamic response. To reduce current and torque ripples in different operational states, the space vector modulation technique has been used in the proposed drive system. The efficiency of the drive system presented with the hybrid control strategy has been compared with the conventional DTC and VC control methods, and the results illustrate a faster dynamic response of the proposed drive system with less steady-state ripples than the two conventional methods. Modeling and implementation of the proposed drive system have been performed in MATLAB/Simulink software.

This paper introduces a new application of the Rotor based-current MRAS observer (RCMO) method for Doubly fed induction generator (DFIG) sensorless control in the condition of network voltage drop. DFIG control is Field oriented control (FOC) vector and Model reference adaptive system (MRAS) observer is used instead of speed and position sensor based on rotor current. It is possible to estimate the speed and position of the rotor. Simulation and analysis have been done based on 10% balanced voltage drop in the wind power plant terminal. The results of the simulation show the estimated speed (ω̂r), accurate and appropriate sequence of speed has real (ωr). Also, the graph of the machine variables in the state of balanced three-phase voltage drop in the state sensored is obtained and compared with the state sensorless, which shows the lack of influence of the estimated speed fault on the simulation results and the acceptability of using the RCMO method in estimating the speed in the condition of balanced voltage drop. Finally, the effect of various voltage drops on the estimated speed fault has been investigated.

A new feature extraction technique for Content based retina biomedical image retrieval is proposed. This method is based on spectral correlation that provides description in the frequency domain. The image is partitioned into non-overlapping tiles. The features drawn from transferred image with proposed new features Spectral correlation using moments between the image tiles, serve as local descriptors. Shape information is captured in terms of edge images computed using combined moments. The combination of the texture features between image and the shape features provide a robust feature set for biomedical retina image retrieval. The experimental results show the efficacy of the method. For matching the biomedical retina images an integrated matching, based on similar highest is provided. The experimental results are compared and found to be encouraging.

today and regarding the increase of social media platforms and the people welcoming these networks has led to share different data throughout the world without the confirmation by the platforms. This has increased the incorrect data frequency and has had great effects on political, economic, and social fields. such incorrect data are called fake news. This has changed into one of the topical issues in today’s society. Through the proposal of an appropriate solution and first through analyzing the news resources in the dataset called BuzzfeedNews, we have concluded that websites with better fames propagate less fake news. We changed the data into vector using Word2vec and investigated the similarity of the taught data and the tagged data in the dataset and got the least precision amounting to 0.60 and the highest precision amounting to 0.94 out of 1 and the results showed that our algorithm has been very helpful in discovering the qualified news.