Michal Kelnar

A ROBUST APPROACH FOR ACOUSTIC NOISE SUPPRESSION IN SPEECH USING ANFIS

Abstract The authors of this article deals with the implementation of a combination of techniques of the fuzzy system and artificial intelligence in the application area of non-linear noise and interference suppression. This structure used is called an Adaptive Neuro Fuzzy Inference System (ANFIS). This system finds practical use mainly in audio telephone (mobile) communication in a noisy environment (transport, production halls, sports matches, etc). Experimental methods based on the two-input adaptive noise cancellation concept was clearly outlined. Within the experiments carried out, the authors created, based on the ANFIS structure, a comprehensive system for adaptive suppression of unwanted background interference that occurs in audio communication and degrades the audio signal. The system designed has been tested on real voice signals. This article presents the investigation and comparison amongst three distinct approaches to noise cancellation in speech; they are LMS (least mean squares) and RLS (recursive least squares) adaptive filtering and ANFIS. A careful review of literatures indicated the importance of non-linear adaptive algorithms over linear ones in noise cancellation. It was concluded that the ANFIS approach had the overall best performance as it efficiently cancelled noise even in highly noise-degraded speech. Results were drawn from the successful experimentation, subjective-based tests were used to analyse their comparative performance while objective tests were used to validate them. Implementation of algorithms was experimentally carried out in Matlab to justify the claims and determine their relative performances.

Realization of Prototype of a Low-Cost Bidirectional Communication System Through Fibreless Optics

The article deals with the design and realization of a prototype of an efficient Low-Cost, Low-Power, Low Complexity—hereinafter (L-CPC) bidirectional communication system for reading and configuration of inbuilt devices (e.g. devices for reading of water meters, power meters, gas meters, identification of property and other specific applications), which will comply with the requirements of no radio waves, reuses already existing components (NRW-RAEC). The goal of the authors was to realize a fibreless optical communication system that would be capable of efficiently replacing current systems (Wi-Fi, Bluetooth, ZigBee, IrDa etc.) at a fraction of their initial cost with an emphasis on L-CPC and NRW-RAEC. Within the development of the prototype, the authors were responsible for the hardware, firmware (ASM, C) and software components (C#) of the prototype. The functionality of the technical solution of the prototype was verified in a real-life application (reading of water meters). The original contribution of the presented article is the realization of a functional prototype including a patented technical solution and design of an intuitive UI. Real-life experiments have shown that the functional prototype designed by the authors can fully replace current systems at a fraction of their initial cost within the scope of the required parameters.

Advanced Waste Rock Exploring by Mobile Robot

The goal of the work is construction and testing of the mobile robot for waste rock exploring. It is descripted concept of mobile service device with ability to explore waste rock, detect toxic gases and monitors that area. The area of waste rock is dangerous for human, because surface of waste rock is inconsistent and it might be very unstable for human walking. Furthermore dangerous gases can occur in these places. Some of the gases are undetectable by human. Another problem is temperature on the surface. Due these properties on the whole is proper to use mobile robot to explore these places.

Adaptive noise suppression in voice communication using a neuro-fuzzy inference system

This paper describes the implementation of a combination of techniques of the fuzzy system and artificial intelligence in the application area of non-linear suppression of noise and interference. The structure used is called ANFIS (Adaptive Neuro Fuzzy Inference System). This system finds practical use mainly in audio telephone (mobile) communication in a noisy environment (transport, production halls, sports matches, etc.). Within the experiments carried out, the authors created, based on the ANFIS structure, a comprehensive system for the adaptive suppression of unwanted background interference that occurs in audio communication and which degrades the audio signal. The system designed has been tested on real voice signals. Noise cancellation performance of the algorithms has been compared by means of SSNR (Segmental Signal to Noise Ratio) and DTW (Dynamic Time Warping). Also processing durations of the algorithms are determined for evaluating the possibility of real time implementation. The results imply that a system using ANFIS has better experimental results than conventional systems built on adaptive algorithms of the LMS (Least Mean Squares) and RLS (Recursive Least Squares) families.

Modelling of Fetal Hypoxic Conditions Based on Virtual Instrumentation

This article is dedicated to the design and implementation of a software simulator of the fetal ECG signal (fECG). Primarily, it aims at modelling the influence of physiological and pathological changes. Fetal electrocardiogram is a valuable carrier of information and its potential can be utilized in the diagnosis of hypoxic conditions. Analysis of real records and study of methods intended for obtaining the ECG signal in clinical practice resulted in creating a simulator of fECG waveforms based on virtual instrumentation. In a suitable user environment, the signal formed in this manner can be combined with physiological and pathological parameters that modify the signal. The respective changes can be observed and analysed with the help of graphical output elements of the user interface. The generator allows the user to model the transvaginal monitoring method (invasive), transabdominal monitoring method (non-invasive) and cardiotocograph (CTG) with ST analyser (STAN). Due to their morphology, the simulation results correlate with the established theoretical assumptions and approximate to real records.

Small-scale wind power in off-grid and its controlling by variable load

This article solves problem of small-scale wind power in off-grid. Article offers solution for controlling load by prototype. Prototype manages the load so that the induction generator is still in his optimum. The article focuses on controlling by prototype. The whole design of prototype, suitable value of capacitors and load is also discussed in this paper. Prototype is created from MOSFETs and microcontroller structure it allows really low price of whole prototype. The prototype is designed so that it can be used for different powers of induction generator and different weather conditions. The prototype has got self education program for learning of optimum of induction generator. Article shows waveforms from measurements, where the prototype operates in education mode and where the prototype operates in full educated mode.

Using of microcontroller with small-scale wind power in off-grid coupled with induction generator

This article solves problem of small-scale wind power in off-grid. We have developed prototype for control induction generator. Prototype manages the load so that the induction generator is still in his optimum. The whole design of prototype, suitable value of capacitors and load is also discussed in this paper. Prototype is created from MOSFETs and microcontroller structure it allows really low price of whole prototype. The prototype is designed so that it can be used for different powers of induction generator and different weather conditions. The prototype has got self education program for learning of optimum of induction generator.