Journal of Artificial Intelligence in Electrical Engineering
Volume:11 Issue: 44, Winter 2023

With the emergence of smart cities vision, its large distributed applications such as intelligent transportation systems demand scalable low-latency trusted data exchange architecture with high storage and computational resources for storing the high-volume of IoT data and providing real-time services. In recent years, blockchain technology has gained extensive attention to fulfil the requirements of such highly distributed large systems. However, there are a number of technical challenges in the integration of blockchain and IoT applications. Firstly, Bitcoin blockchain with low scalability and throughput is not able to provide fast services. Secondly, there are limitations like constrained spaces for establishing big blockchain nodes storing a massive volume of data generated by numerous smart IoT devices or sensors inside the streets of cities. This paper argues that solving both issues in one large blockchain network is infeasible. Therefore, we prioritize this two weakness of blockchain in relation to such systems and propose two separate level of blockchain networks cooperating with each other asynchronously to address them. One network called Fast BlockChain (FBC) composed of multiple scalable sub-blockchain networks responsible for fast services. Another network, CityBC, supports the networks of FBC through the long-term storing of their data and providing their smart manager with knowledge for dynamic autonomous partitioning of them in order to decrease network-to-network communications and avoid wasting storage resources and network bandwidth. Furthermore, this paper evaluates the ideal size of sub-blockchain and then proposes a novel idea for an initial partitioning technique before using collected data by blockchain nodes for dynamic partition of network.

One of the most important symptoms of epilepsy is convulsions, whose detailed analysis is performed by electroencephalography (EEG) signal. Electroencephalogram, as a clinical tool to illustrate the electrical activities of the brain accurately, provides an appropriate method for diagnosing epilepsy disorders, which plays an important role in identifying this disease, especially seizures. Seizures resulting from epilepsy may have negative physical, psychological, and social consequences such as loss of consciousness and sudden death. With timely and correct identification of epilepsy, its effect can be treated with medicine or surgery. In this thesis, a brief review of the methods of identifying epilepsy using EEG signal analysis along with the separation of epileptic signals from healthy and normal signals has been done. Methods based on EEG analysis, from non-linear methods of signal processing, provide much better results due to the properties of signal dynamics

According to the report of the World Health Organization, corona disease is the most dangerous and contagious disease in the world. Currently, the most common method used to diagnose corona disease is the polymer chain reaction laboratory technique of reverse transcription, but since this method requires time to confirm the presence of the virus in the laboratory and also due to the unavailability of diagnostic kits and its high costs, Suspected corona virus patients cannot be identified and treated in time; This, in turn, can increase the likelihood of spreading the disease.Another diagnostic method is the use of X-ray chest imaging technique as well as chest computed tomography scan. Also, the use of deep learning methods can be very important for faster and more accurate diagnosis of the lung problems of the corona virus.In this study, using optimized deep convolutional networks based on X-ray images, patients with corona virus were diagnosed.In this article, using the optimized convolutional neural network of healthy people and those with corona, with 10-Fold cross-validation, average accuracy of 98.9% and average sensitivity of 96.5% were obtained.According to the obtained results, it can be said that the proposed method has the ability to separate healthy and unhealthy signals with acceptable accuracy.

In this paper we study the acquisition of fundamental TE mode reflection in rectangular cavities from a tilted face (end mirror) of superluminescent light emitting diodes (SLD). When its width is 3 micrometers and the inclination of the mirror is 3 ̊, the result will be a reduction of nearly 20 dB of reflection. While if the width is 6 micrometers, the inclination of the mirror 2 ̊ will cause an excess reflection loss of 20 dB. The results obtained in our paper for small tilt angles are the Gaussian approximation of the guided state. While our results differ greatly from the Gaussian approximation for larger angles and larger reflection losses.

A sliding motion can be divided into two phases: reaching phase and sliding phase. One of the features of sliding mode control is that it is robust to parameter uncertainties and external disturbances in the sliding phase. But in the reaching phase, SMC may be sensitive to parameter uncertainty and external disturbance. The moving sliding surface proposed by Choi et al can minimize or eliminate the reaching phase. In this article, the sliding mode fuzzy controller design method with a moving sliding surface is presented. The simulation results show the superiority of SMFC over classical SMC and PID controller in the presence of external disturbances.

Hybrid connections (bolts, glue) and perforated plates are one of the most important topics in various industries, including aerospace. This type of process occurs due to the growth of small cracks in the metal structure as a result of cyclic or intermittent loading. Since failures occur suddenly, terrible accidents such as plane crashes, shipwrecks, bridge collapses, and toxic radioactive fallout can occur. To prevent these incidents, fatigue tests are performed on a sample of parts that is similar to the real part, so that the fatigue life can be obtained through this method. However, because fatigue tests are time-consuming and expensive, artificial intelligence methods have been used in this research to estimate the fatigue life of hybrid joints and perforated plates. In the experimental part of this research, plates made of aluminum alloy 2024-T3, which is one of the widely used materials in aerospace, the used materials are screws made of Hex head M5 and a special adhesive made of Loctite 3421 (Henkel ltd). Fatigue tests are extracted as input and output data from the related article. Out of a total of 71 fatigue tests, 35 tests were performed for perforated plates, 18 tests for hybrid joints, and 18 tests for bolted joints. Also, according to the number of data, the best result was when 80% of the data was considered for training the network and 20% was used as test data to evaluate the performance of the network. Finally, the predicted output was compared with the actual output and it was seen that the best performance of the neural network was after normalizing the data, that the error value was close to zero.