Publications

Non-verbal vocal interaction (NVVI) is an interaction method in which sounds other than speech produced by a human are used, such as humming. NVVI complements traditional speech recognition systems with continuous control. In order to combine the two approaches (e.g. "volume up, mmm") it is necessary to perform a speech/NVVI segmentation of the input sound signal. This paper presents two novel methods of speech and humming segmentation. The first method is based on classification of MFCC and RMS parameters using a neural network (MFCC method), while the other method computes volume changes in the signal (IAC method). The two methods are compared using a corpus collected from 13 speakers. The results indicate that the MFCC method outperforms IAC in terms of accuracy, precision, and recall.

Information and communication technologies have already become an inseparable part of healthcare sector activities. In the chapter, the authors discuss the issues of standardization and interoperability that are crucial for correct interconnection of medical and other devices and information systems. Their previous work in the area has led to the conclusion that successful integration of partial solutions is strongly dependent on the issue of interoperability of medical devices and information systems. It comprises problems of standardization of data acquisition, communication, processing, and storage, and the connected problem: correct data mapping between different ICT applications. They present several examples of partial solutions of communication and data format definition in dedicated areas.

The objective of AAL and home care is a better care for frail individuals (elderly chronic and disabled patients) in a home care setting. In principle it means to allow the citizens to stay at home as long as possible, delaying the institutionalization of people, possibly avoiding it for a high percentage of them. Recent development in ICT shows that it is almost impossible to design and implement an AAL system as fixed to certain hardware, operating system, and infrastructure. Thus it is necessary to develop such architectures that will be easily extensible and modifiable. We will discuss such approaches in the chapter. We will also analyze the social, legal and ethical issues connected with the technology issues.

This paper describes experimental implementation of the cardiac output determination. The measurement is realized on the mechanical model of the cardiovascular system (CVS), which was developed for educational purposes. The CVS model is the system of tubes, the mechanical pump and many of hydraulic components. Inherently, it allows measuring the fluid-flow by several methods. This project is focused on determination of the cardiac output by the thermodilution. Correctness of the measured data is verified by using the accurate flowmeter which is implemented in the model. The aim of this project is to demonstrate means of the thermodilution cardiac output (CO) determination in the conventional way. This paper explains construction and function of the mechanical model of the CVS, structure of the measuring apparatus, data-processing and discussion about results.

This paper presents a modular development telemonitoring system. The system consists of wireless communication and biosignal acquisition modules. These modules are connected to a control unit via an extension board. The control unit is based on STM32 EVO Primer development kit. An integrated accelerometer is used for monitoring of subject's activity. The system features a signal processing and heart rate frequency computing algorithm. A memory card is used for saving the heart rate frequency. A heart arrhythmia alarm and an activity monitor are implemented in the system as well. The system has a simple alarm and a signal visualization program for PC. The modular solution is suitable for other biosignals acquisition and for miscellaneous means of wireless data transfer. The system provides raw signal data for further signal processing. This system was designed mainly for development, research and educational purposes in telemonitoring systems.

Information and communication technologies have already become inseparable part of healthcare sector activities. In the paper we discuss the issues of standardization and interoperability that are crucial for correct interconnection of medical and other devices and information systems. Our previous work in the area has led us to the conclusion that successful integration of partial solutions will be strongly dependent on the issue of interoperability of medical devices and information systems. It comprises problems of standardization of data acquisition, communication, processing, and storage; and connected problem: correct data mapping between different ICT applications. We present several examples of partial solutions of communication and data format definition in dedicated areas.

This paper deals with solving of the data synchronization problem during the data retrieval from independent devices. The data - oscillometry and photoplethysmography signals - are acquired using three independent measuring devices connected to PC via USB ports. The task is to obtain synchronized data. It means the problem is to sample signals in each device at the same time. The sampling of signals is triggered by internal counters independently in each device, the counters are commonly synchronized by general synchronization packets. The presented sampling method is robust and independent of the state of operating system on superordinate PC.

The paper presents telemonitoring system for distant monitoring of physiological signs. The system is designed as modular system content input modules for monitoring various vital signs like ECG, NIBP and oxygen saturation, control module and telecommunication modules for streaming data using various wireless technologies like Bluetooth, GSM and WiFi. The input and telecommunication modules are interchangeable. The system is able to preprocess acquired signals using filtration, parameterization etc. It allows stream both raw data and only aggregated data. The monitoring part is supplemented by PC based part for storing data in database, prospective processing of data and sharing data with other systems.

The objective of AAL and home care is a better care for frail individuals (elderly chronic and disabled patients) in a home care setting. To improve this kind of care means to allow the citizens to stay at home as long as possible, delaying the institutionalization of people, possibly avoiding it for a high percentage of them. Recent development in ICT shows that it is almost impossible to design and implement an AAL system as fixed to certain hardware, operating system, and infrastructure. Thus it is necessary to develop such architectures that will be easily extensible and modifiable. We will discuss such approaches in the paper.

The paper presents an analysis of EEG signal processing methods for studying correlations between human muscle and brain activity. The main task of this work is to design the methods of EEG signal processing and to verify them on artificial and real signals. The paper introduces methods of EEG processing in time and frequency domain.