Alzheimer’s disease (AD) is a deadly cognitive condition in which people develop severe dementia symptoms. Neurologists commonly use a series of physical and mental tests to diagnose AD that may not always be effective. Damage to brain cells is the most significant physical change in AD. Proper analysis of brain images may assist in the identification of crucial bio-markers for the disease. Because the development of brain cells is so intricate, traditional image processing algorithms sometimes fail to perceive important bio-markers. The deep neural network (DNN) is a machine learning technique that helps specialists in making appropriate decisions. In this work, we used brain magnetic resonance scans to implement some commonly used DNN models for AD classification. According to the classification results, where the average of multiple metrics is observed, which includes accuracy, precision, recall, and an F1 score, it is found that the DenseNet-121 model achieved the best performance (86.55%). Since DenseNet-121 is a computationally expensive model, we proposed a hybrid technique incorporating LeNet and AlexNet that is light weight and also capable of outperforming DenseNet. To extract important features, we replaced the traditional convolution Layers with three parallel small filters ($1\times 1,3\times 3$, and $5\times 5$). The model functions effectively, with an overall performance rate of 93.58%. Mathematically, it is observed that the proposed model generates significantly fewer convolutional parameters, resulting in a lightweight model that is computationally effective.

Load Flow Analysis in Power System Network Incorporating STATCOM: A Comparison of the Direct and Indirect Algorithm of the Newton-Raphson Method

Standard EN 50160 ED. 3 was released in 2011 and despite the fact that this is the third edition of this standard, it still does not limit values for all parameters at all voltage levels. This article examines the various methods of evaluation variables with two levels and then presents some recommendations for amendments undefined parameters vvn network in EN 50160 ED. 3rd.

In the power company CEZ in the North Moravia Region (the Czech Republic) the monitoring of a number of selected parameters of the quality of electrical energy (harmonics, flicker and unbalance) is being carried out in cooperation with research laboratories of the Faculty of Electrical Engineering and Computer Science, VSB - Technical University of Ostrava. The monitoring is being carried out in a complex manner in 59 feeding points 400 V, always within one week intervals, and at the same time on all voltage levels (HV, MV and LV). The whole cycle lasted for 3 years, and currently the fourth cycle of monitoring is performed. 3 full cycles enable comparing of the status after twice three years. In the paper, the results of the first, second, third and part of fourth cycle of the complex monitoring will be summarized together with the comparison of the changes of parameters after three years. In the second cycle of monitoring, there were measured currents in the neutral conductor. The results of monitoring of harmonic components of current in the neutral conductor will be presented in the paper.

High-quality supply of electricity is one of the most important part of the transmission of electricity to customers. For the supply of electricity distribution companies are responsible to face any complaints about the quality of electrical energy. All such complaints must examine the distribution companies and then determine what type of claim it is. Verifying the legitimacy of claims to power quality monitoring is carried out parameters of power quality according to ČSN EN 50160th. For justification of the complaint on the quality of electricity distribution companies must take measures that would remove the cause of the complaint on power quality.

In the power company CEZ in the North Moravia Region (the Czech Republic) the monitoring of a number of selected parameters of the quality of electrical energy (harmonics, flicker and unbalance) is being carried out in cooperation with research laboratories of the Faculty of Electrical Engineering and Computer Science, VSB - Technical University of Ostrava. The monitoring is being carried out in a complex manner in 59 feeding points 400 V, always within one week intervals, and at the same time on all voltage levels (HV, MV and LV). In the paper, the results of the complex monitoring during 12 years will be summarized together with the comparison of the changes of parameters after three years. In addition the results of annual continual monitoring for one selected locality on MV level will be presented in the paper. In addition the possibility of utilization of intelligent electrometers for monitoring of some quality parameters will be referred.