This abstract has been withdrawn

By the characteristics of its origin, appearance of certain elements of valley relief, as well as by its basic shape and geographical position, the Neretva valley is the unique morphological phenomenon in the central Dinarids. Seasonal phytocenological tests have been performed on several sites in Blagaj using Blaun-Blanquet method. During the field visits we have established that there is a large number of various plant species (86) in this area, belonging to different systematic categories, especially to autochthonic therapeutic, edible, aromatic and endemic plant species. On the basis of bioindicator values of the vascular flora in regard to the vegetation and eco-system degradation level (primary P, secundary S, and tertiary T bioindicators), it has been established that the vegetation in Blagaj area is endangered due to numerous problems caused by human activities. Most of the human activities lead towards rapid extinction of rare and ecologically specialized species as well as towards the fragmentation of their habitats. The level of manifestation of such activities brings into question the very survival of these interesting habitats. This paper offers data about the present condition of eco-system in Blagaj area along with proposals for measures to preserve and manage it sustainably.

In network development problems can be encountered considering plans and projects that will provide satisfying QoS for different circumstances, different types of users, and different traffic flow profiles. It is necessary to develop satisfying mathematical model which will provide connections between QoS and network parameters. In this paper we will look into traffic with variable intensity which can effectively be described using Markov Modular Poisson Processes (MMPP). We will offer new analytical model, and using graphs we will show losses function depending on network parameters.

In this paper, a wavelet packet-based method is used for detection of abnormal respiratory sounds. The sound signal is divided into segments, and a feature vector for classification is formed using the results of the search for the best wavelet packet decomposition. The segments are classified as containing crackles, wheezes or normal lung sounds, using Learning Vector Quantization. The method is tested using a small set of real patient data which was also analysed by an expert observer. The preliminary results are promising, although not yet good enough for clinical use.

Respiratory sounds are composed of various events: normal and so-called adventitious sounds. These phenomena present a wide range of characteristics which make difficult their analysis with a single technique. Adapted time-frequency and time-scale techniques allow to fit best, under constraints, the accuracy of analysis of a time segmentation and, by the way, make feasible the study of complex signals. We present here new approaches based only on the wavelet packet decomposition to segment respiratory sounds.