SCIDAR - A Digital Archive of the University of Kragujevac

In this paper, design of infinite impulse response lowpass differentiators that can be realized by parallel connection of two allpass filters whose orders differ by two, where one of the allpass branches is pure delay, is considered. As adopted structure of proposed lowpass differentiators allows formulation of their magnitude and phase responses as functions of allpass filter phase response, a set of nonlinear equations in unknown allpass filter coefficients is derived and iteratively solve...

The paper presents the GeNNsem (Genetic algorithm ANNs ensemble) software framework for the simultaneous optimization of individual neural networks and building their optimal ensemble. The proposed framework employs a genetic algorithm to search for suitable architectures and hyperparameters of the individual neural networks to maximize the weighted sum of accuracy and diversity in their predictions. The optimal ensemble consists of networks with low errors but diverse predictions, resulting ...

This paper presents a platform for nonlinear programmed learning, an innovative tool for individualized acquisition and practice of educational content. The platform allows students to learn and practice various procedures, especially in mathematics education, but also in other subjects, adapting to their needs and levels of knowledge. Nonlinear programmed learning involves generating subsequent tasks based on the student's current response. When solving tasks, students have access to t...

This research focuses on the detection of Structured Query Language (SQL) injection intrusion detection. This problem has gained significance due to the widespread use of SQL in different systems, as well as for the numerous versions of attacks that are performable by using this technique. This work aims to propose a robust solution for the detection of such attacks by applying artificial intelligence (AI). The data is preprocessed by a Bidirectional Encoder Representations from Transfor...

This work has a goal to test a deep-learning approach to the problem of aerial weed detection in crops. The issue of this type of detection lies in the nature of plants and their life cycles. Crops as well as weeds change their appearance and can be similar in physical appearance. The use of advanced models like the You Only Look Once v8 (YOLOv8) allows for fast and accurate predictions. In this work, five different sizes of the YOLOv8 are applied to the same dataset consisting of aeria...

Radiotherapy is crucial for treating tumors, but achieving effectiveness while minimizing damage to surrounding healthy tissue presents significant challenges. In this research, we present novel methods for automatically selecting a proper set of parameters to address these two opposing criteria: achieving maximum radiation homogeneity and minimizing exposure to organs-at-risk (OARs). Our research is based on the FOTELP-VOX program (author R.Ilić), a Monte Carlo technique that determines ...

The aim of the present study was to evaluate the effects of adding protease enzymes (Ronozyme ProAct, 0, 200 mg/kg and 300 mg/kg diet) while reducing the crude protein content (control group - standard diet, group E-I - 4 % less crude protein compared to the control group and group E-II, which received 6 % low-protein feed compared to the control group) in fast and medium-growing meat chickens on the weight and percentage of certain classes of meat. In the experiment, fast-growing Cobb 5...

In this paper are presented the results of research on the influence of traverse speed on cutting forces and machined surface in abrasive water jet machining. The results indicated that there is a strong connection between the dynamic character of the cutting force, that is, the appearance of peaks in the cutting force signal, with the appearance of irregularities and uncut parts on the machined surface. Also, the research showed that with the increase of the traverse speed, there is an inc...

This research paper presents a comprehensive investigation into the design, analysis, and optimization of Proportional-Integral (PI) controller methods for interacting systems, conducted through laboratory experimentation. The study aims to enhance the performance and stability of PI controllers by exploring various tuning methods and strategies tailored to address the intricacies of interacting systems. Through a series of experimental setups in the laboratory environment, different PI contr...