Piotr Artiemjew

We propose a new design for a feedforward neural network model that can be used to find numerical solutions to various linear Volterra integral equations of the second kind. The developed architecture has a solid theoretical basis in the theory of fuzzy transforms and thus contributes to the important area of explainable neural network design.

In this paper, we present the results of a study on the development of a system to support medical diagnoses based on voice-based medical interviews. The main objective is to develop a tool that improves the process of collecting information from patients, using natural language analysis to identify key diagnostic information. The system processes the collected data to create information vectors for a selected group of diseases, allowing for an initial assessment of possible disease entities. An analysis of data mining and selected machine learning methods was carried out to develop an effective diagnosis algorithm. The system is designed to optimise patient care by automating the initial phase of the medical interview, which can lead to a reduction in errors due to subjective assessments and reduce the workload on doctors. The solution presented in this paper is part of a broader research project to develop a Medical Interview system, and this paper is the first article in a series that describes the experiences and challenges of implementing this system. Further work is planned to develop the model into advanced medical decision support techniques and validate it in a clinical setting.

Path planning is one of the most important problems in mobile robotics. Particularly challenging in...

Despite the number of successful applications of the Extreme Learning Machine (ELM), we show that its underlying foundational principles do not have a rigorous mathematical justification. Specifically, we refute the proofs of two main statements, and we also create a dataset that provides a counterexample to the ELM learning algorithm and explain its design, which leads to many such counterexamples. Finally, we provide alternative statements of the foundations, which justify the efficiency of ELM in some theoretical cases.

In this paper, we present an innovative technique for the path planning of flying robots in a 3D environment in Rough Mereology terms. The main goal was to construct the algorithm that would generate the mereological potential fields in 3-dimensional space. To avoid falling into the local minimum, we assist with a weighted Euclidean distance. Moreover, a searching path from the start point to the target, with respect to avoiding the obstacles was applied. The environment was created by connecting two cameras working in real-time. To determine the gate and elements of the world inside the map was responsible the Python Library OpenCV [1] which recognized shapes and colors. The main purpose of this paper is to apply the given results to drones.