-view object recognition. In: Computer Vision and Pattern Recognition , CVPR 2008, Conference on IEEE.
 Davis, K. H., Biddulph, R. and Balashek, S., 1952. AutomaticRecognition of Spoken Digits. In: Acoustical Society of America.
 Dudek, A., Patalas-Maliszewska, J., 2016. IT tool for knowledge management support in the service department in the manufacturing company – a case study . In: R. Knosala, ed. Innovation in Management and Production Engineering . Oficyna Wydawnicza Polskiego Towarzystwa Zarządzania Produkcją, Vol 2, pp.35-46.
This paper proposes a new Matlab-developed algorithm for automatic recognition of digital modulations using the constellation of states. Using this technique the automatic distinction between four digital modulation schemes (8-QAM, 16-QAM, 32-QAM and 64-QAM) was made. It has been seen that the efficiency of the algorithm is influenced by the type of modulation, the value of the signal-to-noise ratio and the number of samples. In the case of an AWGN noise channel the simulation results indicated that the value of SNR (signal-to-noise ratio) has a small influence on the recognition rate for lower-order QAM (8-QAM and 16-QAM). The length of the signal may change essentially the recognition rate of this algorithm especially for modulations with a high number of bits per symbol. Consequently, for the 64-QAM modulation in a case of 25dB signal-to-noise ratio the recognition rate is doubled if the sample rate is incresed from 5400 to 80640.
Róbert Sabo, Peter Krammer, Ján Mojžiš and Marcel Kvassay
We propose a text classification method for the purpose of creating a language model for automatic recognition of spontaneous spoken speech. Transcripts from our departmental speech database served as spontaneous spoken texts. Using supervised machine learning methods, we have created multiple classification models (including neural networks), that were able to distinguish them from written texts with high accuracy. We subsequently verified the accuracy of our trained models on a database of texts containing direct speech extracted from newspaper articles.
The article presents the classification software according to the international product description standard ETIM. The software has been designed for Polish manufacturers or wholesalers who want to implement this standard in their companies. Classification is done in Polish language, on the basis of information contained in the company’s product files. Application features several mechanisms to facilitate the creation of product description, like suggestion of the appropriate class or automatic recognition of values of the required parameters. With this application, the tedious and time consuming job of classification becomes easier and can be done much quicker.
Part of speech transitions represent an interesting issue in terms of Automatic Morphological Analysis (AMA). In these cases, two parts of speech have to be considered: initial and final. However, their automatic recognition is complicated by the same form. This article presents the results of a corpus study aimed at mapping nominalized adjectives tagging with a focus on detecting candidates for nominalization among frequent adjectives. Analysis of the data obtained from the ČNK SYN v5 corpus shows different reasons for incorrect tagging. Taking into account these reasons, we propose three solutions for the improvement nominalized adjectives tagging.
This paper presents a method of automatic recognition of thiarubrine canals in images obtained with Optical Coherence Tomography technique. The plant material was the Ri-transformed root culture of South American herb Schkuhria pinnata. The series of highresolution OCT B-scans for the study were collected using custom made experimental system operating light of 800 nm central wavelength. The method reduces significant artefacts and uses region growing approach adapted to specific features of OCT images. Results of the identification have been compared with data obtained by specialist for selected B-scans. The algorithm accuracy was also verified using a simple numeric phantom.
The paper presents the importance of analysis isotopes on anonymous readers’ comments as an important part of deep interpretation of texts. Furthermore, we describe a classification methodology of the anonymous readers’ comments on online articles, through the overlapping of isotopes, which completed the traditional analytical methods. Automatic recognition of isotopes is an important topic in Natural Language Processing (NLP), especially in the semantic disambiguation. The aim of this article is the automatic comparative analysis of the identified isotopes in articles and comments, which reveals an important part of online behavior. Moreover, we present a new tool that classifies the online commentators based on existing resources, open-source or freely available for research purposes. This study is intend to help direct beneficiaries (journalists, business, education, managers, PR specialists), but also specialists and researchers in the field of natural language processing, linguists, psychologists, etc.
Angela-Aida K. Runyoro, Irina Zlotnikova and Jesuk Ko
Traffic congestion problem has been noticed to have a serious impact on the economy of the country in terms of time wastage, energy consumption costs, human loss and environmental effects. Different strategies have been used so far all over the world as shown in the literature review. Intelligent Transportation System (ITS) is a multi-technology approach that can help to handle the issues and create a complete congestion reduction framework. This paper presents a case study for implementing automated road management system using networks in Tanzania, where three cities highly affected by traffic congestion have been studied. Study results show that these cities have not yet implemented new technologies in road traffic management; instead the traffic is controlled using traffic police officers and traffic lights only. The traffic lights use an old technology that cannot manage traffic in relation to the real-time situations. This study proposes components for a framework, which will assist automation in road traffic management. From the review of various existing ITS of which Advanced Traffic Management System (ATMS) and Advanced Travel Information System (ATIS) are subsystems, we have identified the possibility to integrate the two sub-systems within the framework. Three-phase traffic theory has been referred, FOTO and ASDA models are applied to the automatic recognition and tracking of congested spatiotemporal traffic patterns on roads.
Andrzej Szelmanowski, Andrzej Pazur, Tomasz Prusik and Alicja Malanowicz
The article presents selected results of the analytical works, carried out in the Air Force Institute of Technology, in the field of possibilities to support the pilot’s work in the cabin of the modern multi-task aircraft or military helicopter with the use of the computer voice communication assistant, with automatic recognition of the pilot’s voice and speech, which operates in conditions of the lack of time. There are presented the voice systems warning the pilot of the occurrence of an emergency state, as the so-called voice guides, P-591-04 type, used in the MiG-29 multi-purpose aircraft and RI-65 type, used in the Mi-17 and Mi-24 helicopters. As an example of implementation of the concept of a new system supporting the pilot’s work, there was selected the voice communication system, constructed in the Air Force Institute of Technology for the W-3PL multi-purpose helicopter with the ZSA integrated avionics system. The main research problems related to the construction of integrated avionics systems, verbally supporting the pilot’s work, were discussed, and the specialized tools and research stations used in the Air Force Institute of Technology for the phonoscopic speech and voice studies, were presented. Furthermore, an example of the functional diagram and the system architecture of the pilot’s work verbal supporting for a selected emergency situation on the aircraft board were demonstrated, as well as the expected range of that system’s applications.
1. Saidi, M. N., B. Hoeltzener, A. Toumi, A. Khecnhaf. AutomaticRecognition of ISAR Images: Target Shapes Features Extraction. - In: Proc. of ICTTA, 2008, pp. 1-6.
2. Pastina, D., C. Spina. Multi-Feature Based AutomaticRecognition of Ship Targets in ISAR. - IET Radar, Sonar & Navig., Vol. 3, 2009, No 4, pp. 406-423.
3. Martorella, M., E. Giusti, L. Demi, Z. Zhou, A. Cacciamano, F. Berizzi, B. Bates. Automatic Target Recognition by Means of Polarimetric ISAR Images: A Model Matching Based Algorithm