Journal of Artificial Intelligence in Electrical Engineering
Volume:7 Issue: 26, Summer 2018

Communication protocols issues are one of the effective factors in communicated networks performance. One of challenging problem in CMT-SCTP which sends data by multipath concurrently is Receive Buffer Blocking. This problem has important role in data transmission speed in computer networks. In this paper, we propose a control method based on fuzzy logic so that can solve Receive Buffer Blocking problem in CMT-SCTP and has higher data transmission speed rather than other methods such as Buffer Splitting method. After proposed fuzzy logic designing by ANFIS logic and required data set, we evaluate our proposed method. Simulation result shows that our method improves data transmission speed compare to previous methods.

Ever-increasing energy demand has led to geographic expansion of transmission lines and their complexity. In addition, higher reliability is expected in the transmission systemsdue to their vital role in power systems. It is very difficult to realize this goal by conventional monitoring and control methods. Thus, phasor measurement units (PMUs) are used to measure system parameters. Although installation of PMUsincreases the observability and system reliability, high installation costs of these devices requireplacing them appropriately in proper positions. In this research, multi-objective placement of PMUs with the aims of improving investment and risk costs in power systems is performed along with observability constraint. Then, PMU placement problem is solved as an optimization problem using Non-dominated Sorting Genetic Algorithm-II (NSGA-II). Finally, the performance of the proposed method is tested on standard IEEE 24-bus test system and Roy Billiton IEEE 31-bus test system.

User interfaces are always one of the most important applied and study fields of information technology. The development and expansion of cognitive science studies and functionalization of its tools such as BCI1, as well as popularization of methods such as SSVEP2 to stimulate brain waves, have led to using these techniques every day, especially in appropriate solutions for physically and mentally handicapped people. Computer- brain interfaces enable users to communicate without involvement of their lateral muscles and nerves and since these interfaces are not dependent on muscular nervous control, they enable people with muscle neuromuscular control disorders (such as amyotrophic lateral sclerosis, brain stroke, cerebral palsy, etc.) to control and communicate. The main idea in this research is the implementation of a proposed system to provide the best options to the user due to the limitations of the simultaneous options in the SSVEP method and the specific user conditions for disabled people. To do this, we present a new implementation method based on extracting the wavelet feature and then dimension reduction by PCA3 and after the extraction step, the features are classified by the SVM4 and KNN5 classifiers. It has been observed in this project that99.3% accuracy can be achieved by KNN classifier.

Typically, the diagnosis of a tumor is done through surgical sampling, which is more precise with existing methods. The difference is that this is an aggressive, time consuming and expensive way. In the statistical method, due to the complexity of the brain tissues and the similarity between the cancerous cells and the natural tissues, even a radiologist or an expert physician may also be in error in his diagnosis. Tumor diagnosis is done automatically and various results are achieved. The steps involved in these algorithms can be divided into two sections of the feature discovery and the classification of the samples. The methods generally are that, firstly, the properties of the image are extracted. These characteristics usually include static properties such as entropy, skewness, mean, energy, torque, correlation, etc., or the properties of other algorithms (instant conversion, histogram, etc.). The information obtained at this stage is applied to the sample classification process for decision making. This section is done with an advanced neural network such as RVM. Possible neural networks have the ability to classify more than one class and a kind of radar disease to extract features from MRI images using histogram or satellite conversion techniques, and then selecting appropriate features and ultimately using the system. Fuzzy Neural Network Diagnostics The decision making system of the fuzzy system is a conclusion that trains with these features and in the output, multiple images are given at different levels. In this research, using image and image processing, we try to find out exactly where the brain is placed. For this purpose, it is initially performed using preventive techniques such as enhancement of contrast, marginalization and morphological functions, and then using the neural network to perform a careful separation of the cancerous parts of the brain health sectors.

Updating Optimal Coefficients and Selected Observations Affine Projection is an effective way to reduce the computational and power consumption of this algorithm in the application of adaptive filters. On the other hand, the calculation of this algorithm can be reduced by using subbands and applying the concept of filtering the Set-Membership in each subband. Considering these concepts, the first step is to apply an adaptive algorithm in the packet wavelet transform domain in this Article, and then using multiple decimate and independent filters instead of an adaptive filter in the corresponding packages of this structure is suggested. Then the EFI image algorithm is applied to the corresponding packages of this structure, and the three methods of data selector based on the Set-Membership filtering concept, the method for selecting the optimal coefficients for the update, and the observation selector method in the same time in all corresponding packets in the AFin algorithm apply. The simulation results show the efficiency of the proposed algorithm in terms of the convergence rate and the reduction of computational complexity.

One of the most important obstacles to using Internet banking is the lack of Stability of transactions and some misuse in the course of transactions it is financial. That is why preventing unauthorized access Crime detection is one of the major issues in financial institutions and banks. In this article, a system of intelligence has been designed that recognizes Suspicious and unusual behaviors for users in the Internet banking system. Because the behavior of different users is accompanied by ambiguity and uncertainty, this system is designed based on fuzzy logic to identify user behavior and categorize suspicious behaviors of varying severity. The system applies a diagnostic process based on KDD data. The results show that in all validation algorithms, 2 to 5 percent improvement in detection is provided.