Milan Navratil

Classification of audio sources using neural network applicable in security or military industry

In this paper, classification of audio sources is presented to supplement current work on existing system for localization of audio sources. The question of achieving the audio classification lies in the convenient discrimination of the feature vector in the feature vector space. Characteristics based on frequency analysis were chosen and used as feature vector. Artificial neural network was applied in order to classify different audio classes especially from security and military areas, such as different shots and explosions. The information about specific type of a sound can trigger localization process of given audio source. Moreover, it can improve situation when guards get ready for the alert state. This classification method is currently developed as an additional part of the system for audio source hyperbolic localization; the paper also gives some basic structure of that system. Its utilization can be found for additional securing of larger objects like squares or military basis, for instance.

Utilization of audio source localization in security systems

Paper deals with utilization of audio source localization in security systems especially dedicated for additional securing of larger objects like squares or military basis for instance. Proposed detection system supposes that intruder makes uniquely determinable noise which can be picked up by microphone array. On the basis of real-time signal analysis from each microphone unit direction to acoustic source can be determined. In this paper is presented time-delay estimation method of the direction of arrival of the sound wave which is used in many other practical applications. Experimental part proposes design of the evaluation system consisting of microphone sensory system and standard personal computer equipped with Advantech PCI-1716 multifunction data acquisition card.

The effect of tip speed in AFM scratching

In this study, we investigated the effect of tip speed in AFM scratching. Three testing patterns were engraved on polycarbonate substrate at different scratching parameters. The subsequent characterization of fabricated structures was performed using the identical atomic force microscope. It was found that the depth and width depend only weakly on tip speed.

The effect of scratching direction in AFM nanolithography

In this paper, we investigated the effect of scratching direction in AFM scratching. The understanding of this effect is one of the key factors in the patterning process. In our experiment, several testing grooves were engraved in all four basic directions (forward, backward, right and left) on polycarbonate substrate using Si probe. Both the fabrication and subsequent characterization were performed using the identical atomic force microscope. Our results were compared to previous reports. It was found that scratching in the backward direction is the most suitable for the common usage.

Nano-steganography using atomic force microscopy

This paper presents physical nano-steganography for secret data transmission. The experimental code was engraved into the base polycarbonate plastic layer of a compact disc by atomic force microscopy nanolithography. The advantage is that such information cannot be found using optical microscopes and it is very problematic to find it even by the most of electron microscopes due to the subtle variations in height.

Scanning System for Ballistic Analysis

This paper presents hardware and software solution of the scanning system designed for ballistic analysis of cartridge cases which were deformed by firing pin after shooting for identification process of firing weapon. The system is based on resistivity measurement between the scanning tip and a sample and three axis servomotor positioning controlled by application created in MATLAB programming environment. Output of the application is matrix of coordinates for 3D visualization of deformed cartridges for firearm identification process. Measured example results are included.

Quality control in microelectronics using scanning probe microscopy

In this paper, atomic force microscopy and its variation scanning microwave microscopy were used for the characterization of microelectronics (PNP bipolar transistors on a chip and epitaxial layers with different properties on a silicon substrate). The capabilities of these methods in the quality control process are presented.

Nanoscale characterization of ultra-thin tungsten films deposited by radio-frequency magnetron sputtering

In this article, atomic force microscopy was used for nanoscale characterization of ultra-thin tungsten films which were deposited on silicon substrate. Radio-frequency magnetron sputtering was used for tungsten deposition on the surface.

Device design based on automatic colour measurement used for polymer waste recycling

This paper deals with design and development of a device used for measurement of colour changes of granulate polymer material which is produced by recycling technology. Individual parts of design from the point of hardware and software are described. Description of user application in MATLAB programming environment is introduced. Relative measurement of reference sample set is also presented.