{"title":"Tests of selected emotional states recognition","authors":"Krystian Kapala, Dawid Krawczyk, S. Brachmański","doi":"10.1109/SPA.2016.7763628","DOIUrl":"https://doi.org/10.1109/SPA.2016.7763628","url":null,"abstract":"The matters regarding speech signal processing and analyzing in terms of emotional states recognition were presented in the paper. Issues concerning both speech signal samples acquisition and selection were discussed. An attempt was made to develop a tool used for determining the emotional state in recorded statement.","PeriodicalId":413894,"journal":{"name":"2016 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131431944","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Majkowski, M. Kołodziej, R. Rak, Robert Korczyeski
{"title":"Classification of emotions from speech signal","authors":"A. Majkowski, M. Kołodziej, R. Rak, Robert Korczyeski","doi":"10.1109/SPA.2016.7763627","DOIUrl":"https://doi.org/10.1109/SPA.2016.7763627","url":null,"abstract":"The article presents an analysis of the possibility of recognizing speaker's emotions from speech signal in Polish language. In order to perform experiments a database containing speech recordings with emotional content was created. On its basis, extraction of features from the speech signals was performed. The most important step was to determine which of the previously extracted features were the most suitable to distinguish emotions and with what accuracy the emotions could be classified. Two feature selection methods — Sequential Forward Search (SFS) and t-statistics were examined. Emotion classification was implemented using k — Nearest Neighbor (k-NN), Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM) classifiers. Classification was carried out for pairs of emotions. The best results were obtained for classifying neutral and fear (91.9%) and neutral and joy emotions (89.6%).","PeriodicalId":413894,"journal":{"name":"2016 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130409783","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Agnieszka Stankiewicz, T. Marciniak, A. Dabrowski, M. Stopa, Elzbieta Marciniak, A. Michalski
{"title":"Matching 3D OCT retina images into super-resolution dataset","authors":"Agnieszka Stankiewicz, T. Marciniak, A. Dabrowski, M. Stopa, Elzbieta Marciniak, A. Michalski","doi":"10.1109/SPA.2016.7763600","DOIUrl":"https://doi.org/10.1109/SPA.2016.7763600","url":null,"abstract":"Optical coherence tomography (OCT) is the current very fast and accurate modality for noninvasive assessment of 3D retinal structure. Due to large amount of data acquired with this technique the resolution of 3D scans is limited. In this paper we present a new method for improving resolution of 3D macula scans while maintaining short acquisition time and robustness with respect to motion artifacts. Our approach is based on multiframe super-resolution method applied to several 3D standard resolution OCT scans. Presented experiments where performed on volumetric data acquired from adult patients with the use of Avanti RTvue device. Each OCT cross-section (B-scan) was subjected to image denoising and retinal layers segmentation. The generated 3D super-resolution scans have significantly improved quality of the vertical cross-sections.","PeriodicalId":413894,"journal":{"name":"2016 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131082829","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Statistical analysis of Polish language corpus for speech recognition application","authors":"P. Kłosowski","doi":"10.1109/SPA.2016.7763632","DOIUrl":"https://doi.org/10.1109/SPA.2016.7763632","url":null,"abstract":"This article presents the original results of statistical analysis of Polish language, based on orthographic and phonemic language corpus, preformed by the author. The phonemic language corpus for Polish was developed, by automatic grapheme-to-phoneme conversion of source orthographic language corpus. Phonemic language corpus contains the most frequently used Polish words written with the use of phonemic notation. Performed statistical analysis of Polish language based on phonemic language corpus, includes frequency of occurrence calculation of the orthographic and phonemic language components and their sequence. The statistical language data obtained as a result of performed statistical analysis enable to develop statistical word-based and subword-based language models for Polish language. The development of statistical methods of speech recognition may be very useful in research on improving automatic speech recognition in Polish, based on statistical language models.","PeriodicalId":413894,"journal":{"name":"2016 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130247161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
K. Sieczkowski, T. Sondej, A. Dobrowolski, R. Olszewski
{"title":"Autocorrelation algorithm for determining a pulse wave delay","authors":"K. Sieczkowski, T. Sondej, A. Dobrowolski, R. Olszewski","doi":"10.1109/SPA.2016.7763635","DOIUrl":"https://doi.org/10.1109/SPA.2016.7763635","url":null,"abstract":"This article concerns an autocorrelation algorithm for determining a pulse wave delay. The pulse wave delay is defined as difference between the characteristic points i.e. the difference between the R wave in the electrocardiogram signal (ECG) and distinctive point in the photoplethysmogram (PPG) waveform. Obtaining values of the characteristic points (time stamps) are realized by correlation function. The known values of the time stamps can be used to estimate change of blood pressure. In the proposed algorithm using the autocorrelation function is calculated signal pattern. Then, this pattern is used for further correlation calculations. In the algorithm all the time is analysed the quality of the measured signal. In the next part of article was described method of measurement and the results calculated the time of the characteristic points to determine the pulse wave delay.","PeriodicalId":413894,"journal":{"name":"2016 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114690238","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"HDR tonal mapping algorithm for mobile devices","authors":"A. Konieczka, Karol Piniarski, J. Balcerek","doi":"10.1109/SPA.2016.7763621","DOIUrl":"https://doi.org/10.1109/SPA.2016.7763621","url":null,"abstract":"In this paper the application for generation of HDR image based on two consecutive images (underexposed and overexposed) for Android mobile operating system is presented. The implemented software preserves a lot of image details and maintains a low execution time. These features are particularly important for pictures taken using mobile devices in emergency situations. Such photos may constitute evidence that a threat occurred, was properly recognized, or someone committed a crime. HDR images can be also used in mobile systems for supporting pedestrians or drivers. Obtained results indicate on a high effectiveness of the presented solution.","PeriodicalId":413894,"journal":{"name":"2016 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"151 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116082171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Automatic tuning of hyperparameters for NMF-based face recognition system","authors":"S. Drgas, R. Zdunek","doi":"10.1109/SPA.2016.7763584","DOIUrl":"https://doi.org/10.1109/SPA.2016.7763584","url":null,"abstract":"In the paper, the NMF-based (non-negative matrix factorization) face recognition system is considered. An error rate made by such a system depends on the hyperparameters (for example, sparsity, a number of NMF components) which are usually determined experimentally. Typically, a large number of combinations of the hyperparameters is evaluated. Each evaluation involves substantial computational time. Recently, automatic procedures for tuning the hyperparameters have achieved a considerable success. They give a possibility to reduce a number of the system evaluations. In our study, we applied this approach to the NMF-based face recognition system. The results show that such tools can substantially reduce an overall computational complexity in comparison to random grid searching. They can also provide reliable information about the importance of the hyperparameters and their interactions.","PeriodicalId":413894,"journal":{"name":"2016 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"266 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122138062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Automatic detection of SSVEP using independent component analysis","authors":"M. Kołodziej, A. Majkowski, R. Rak","doi":"10.1109/SPA.2016.7763612","DOIUrl":"https://doi.org/10.1109/SPA.2016.7763612","url":null,"abstract":"A new method of automatic SSVEP detection in the EEG signal based on Independent Components Analysis (A-ICA) is described in the article. For the presented method reduction of artifacts in EEG signal is not required. Besides, the method has low computational complexity. In order to select the best ICA decomposition, we conducted a comparative study of known ICA algorithms for the use in SSVEP detection. For feature extraction from ICA components, time-frequency analysis (STFT) was used. The algorithm was tested on real EEG signals recorded from 5 users, for 4 stimuli frequencies. The achieved SSVEP classification accuracy was in the range of 53–89%, for different users. The proposed algorithm can be successfully used in SSVEP based brain-computer interfaces.","PeriodicalId":413894,"journal":{"name":"2016 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125114374","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Exploiting features of symmetric polynomials for improved comb filter design","authors":"G. Jovanovic-Dolecek, L. Dolecek","doi":"10.1109/SPA.2016.7763581","DOIUrl":"https://doi.org/10.1109/SPA.2016.7763581","url":null,"abstract":"This paper presents a simple method to increase alias rejection in comb decimation filters. The method is based on exploiting the properties of the system function of the convolution of a comb filter with itself. Specifically, we take advantage of the fact that this system function is a symmetric polynomial, with a special relation between its coefficients and the position of its zeros on the unit circle in complex z-plane. By appropriately choosing the centermost coefficient of this polynomial, we can separate the double zeros of the polynomial and thus increase the width of the folding bands of the derived structure. The resulting structure is multiplierless; we contrast it with some existing methods and demonstrate the benefits of the proposed design technique.","PeriodicalId":413894,"journal":{"name":"2016 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125150110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Increasing disregard for excellence in circuits and systems theory and related mathematics","authors":"A. Borys","doi":"10.1109/SPA.2016.7763624","DOIUrl":"https://doi.org/10.1109/SPA.2016.7763624","url":null,"abstract":"The days of great interest in circuit theory seem to be over. Since O. Heaviside and Ch. Steinmetz till the recent decades, we have seen a continuous development of the circuits and systems theory. Recently, such very famous researchers like L. Chua, Ch. Desoer, S. Mitra, G. Moschytz, I. Sandberg, L. Zadeh and many others worked very actively in the above area. But, we do not see their successors. For example, character of present publications in IEEE Transactions on Circuits and Systems confirms this. A dominated position in this journal occupy now articles which are more contributions to the technology than to the circuits and systems theory. Admittedly, elements of the circuit theory are used in them, but in a limited scope. It happens that their usage is clumsy and not consistent. This will be illustrated here by some concrete examples taken from publications. They show unambiguously increasing disregard for excellence in circuits and systems theory and related mathematics. This is our thesis and it will be developed in this paper.","PeriodicalId":413894,"journal":{"name":"2016 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"392 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123359969","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}