31 October 2023 in Facta Universitatis, Series: Mechanical Engineering
The paper defines the methodology for the selection of standards and tools that system analysts use for the purposes of analyzing the computer infrastructure of organizations. The goal of system analyst analysis is primarily to increase: the speed of processing information, the efficiency of data processing and data exchange. A large number of standards and tools complicates an adequate choice, and on the other hand system analysts are not the only ones who influence the choice. In the analysis of the choice of standards and tools, in the second chapter an algorithm for determining the weight coefficients for the criteria selected by the company and the ranking of the standards for selection is presented through an example. In order to choose the best standard, the choice was made between four standards described in the third chapter. The chapter defines the criteria that cover IT activities for the selection of standards according to selected criteria and defined weight coefficients in the observed company. Finally, on the assumption that the company together with the analyst chose “k” criteria, where the methodology (LBWA) for the selection of weight coefficients for the criteria was proposed, a new model for calculating the ranking of standards was presented, i.e. the choice of the best. The conclusion of the paper is that the presented procedure for choosing standards is not complicated, that it is very successful, and that in this way the proposals were more easily accepted and implemented in the fastest way.
27 October 2025 in Applied Soft Computing
10 August 2024 in Complex & Intelligent Systems
Electroencephalography (EEG) serves as a crucial neurodiagnostic tool by recording the electrical brain activity via attached electrodes on the patient’s head. While artificial intelligence (AI) exhibited considerable promise in medical diagnostics, its potential in the realm of neurodiagnostics remains underexplored. This research addresses this gap by proposing an innovative approach employing time-series classification of EEG data, leveraging long-short-term memory (LSTM) neural networks for the identification of abnormal brain activity, particularly seizures. To enhance the performance of the proposed model, metaheuristic algorithms were employed for optimizing hyperparameter collection. Additionally, a tailored modification of the variable neighborhood search (VNS) is introduced, specifically tailored for this neurodiagnostic application. The effectiveness of this methodology is evaluated using a carefully curated dataset comprising real-world EEG recordings from both healthy individuals and those affected by epilepsy. This software-based approach demonstrates noteworthy results, showcasing its efficacy in anomaly and seizure detection, even when working with relatively modest sample sizes. This research contributes to the field by illuminating the potential of AI in neurodiagnostics, presenting a methodology that enhances accuracy in identifying abnormal brain activities, with implications for improved patient care and diagnostic precision.