Filtry
wszystkich: 946
-
Katalog
Wyniki wyszukiwania dla: MULTIMODAL EMOTION RECOGNITION
-
Interactions with recognized objects
PublikacjaImplicit interaction combined with object recognition techniques opens a new possibility for gathering data and analyzing user behavior for activity and context recognition. The electronic eyewear platform, eGlasses, is being developed, as an integrated and autonomous system to provide interactions with smart environment. In this paper we present a method for the interactions with the recognized objects that can be used for electronic...
-
The Innovative Faculty for Innovative Technologies
PublikacjaA leaflet describing Faculty of Electronics, Telecommunications and Informatics, Gdańsk University of Technology. Multimedia Systems Department described laboratories and prototypes of: Auditory-visual attention stimulator, Automatic video event detection, Object re-identification application for multi-camera surveillance systems, Object Tracking and Automatic Master-Slave PTZ Camera Positioning System, Passive Acoustic Radar,...
-
Effect of some organic solvent - water mixtures composion on precipitated calcium carbonate in carbonation process
PublikacjaPrecipitated calcium carbonate particles were obtained during carbonation of calcium hydroxide slurry with carbon dioxide. Aqueous solutions of isopropyl alcohol, n-butanol and glycerol were used as solvents. Concentration of organic additives in the reactive mixture was from 0 to 20 % (vol.). Precipitation process were performed in a stirred tank reactor equipped with gas distributor. Multimodal courses of particles size distribution...
-
Once in a season – the pragmatic function of fuck in “BoJack Horseman” TV Show
PublikacjaThis article investigates the use and pragmatic functions of the swear word fuck in the “BoJack Horseman” produced by Netflix and bridges the gap in the linguistic research on this particular TVshow. Incorporating corpus linguistics tools, the BoJack Horseman Corpus was compiled and thelemma fuck has been investigated and analysed from the multimodal perspective....
-
Virtual immersive environments
PublikacjaYet a higher level of active systems may be achieved when users are fully immersed in an interface which is a 3D computer generated virtual world and can interact with surrounding objects of that world as they were in a real one. This is the issue covered by Chapter 7. Interaction in such a world is both multidimensional and multimodal, with the possibility of free movement of the user in any direction and the simultaneous stimulation...
-
The Impact of Foreign Accents on the Performance of Whisper Family Models Using Medical Speech in Polish
PublikacjaThe article presents preliminary experiments investigating the impact of accent on the performance of the Whisper automatic speech recognition (ASR) system, specifically for the Polish language and medical data. The literature review revealed a scarcity of studies on the influence of accents on speech recognition systems in Polish, especially concerning medical terminology. The experiments involved voice cloning of selected individuals...
-
MODALITY corpus - SPEAKER 17 - SEQUENCE S1
Dane BadawczeThe MODALITY corpus is one of the multimodal database of word recordings in English. It consists of over 30 hours of multimodal recordings. The database contains high-resolution, high-framerate stereoscopic video streams and audio signals obtained from a microphone array and a laptop microphone. The corpus can be employed to develop an AVSR system,...
-
MODALITY corpus - SPEAKER 17 - SEQUENCE S4
Dane BadawczeThe MODALITY corpus is one of the multimodal database of word recordings in English. It consists of over 30 hours of multimodal recordings. The database contains high-resolution, high-framerate stereoscopic video streams and audio signals obtained from a microphone array and a laptop microphone. The corpus can be employed to develop an AVSR system,...
-
MODALITY corpus - SPEAKER 17 - SEQUENCE S2
Dane BadawczeThe MODALITY corpus is one of the multimodal database of word recordings in English. It consists of over 30 hours of multimodal recordings. The database contains high-resolution, high-framerate stereoscopic video streams and audio signals obtained from a microphone array and a laptop microphone. The corpus can be employed to develop an AVSR system,...
-
MODALITY corpus - SPEAKER 17 - SEQUENCE S5
Dane BadawczeThe MODALITY corpus is one of the multimodal database of word recordings in English. It consists of over 30 hours of multimodal recordings. The database contains high-resolution, high-framerate stereoscopic video streams and audio signals obtained from a microphone array and a laptop microphone. The corpus can be employed to develop an AVSR system,...
-
MODALITY corpus - SPEAKER 17 - SEQUENCE S3
Dane BadawczeThe MODALITY corpus is one of the multimodal database of word recordings in English. It consists of over 30 hours of multimodal recordings. The database contains high-resolution, high-framerate stereoscopic video streams and audio signals obtained from a microphone array and a laptop microphone. The corpus can be employed to develop an AVSR system,...
-
MODALITY corpus - SPEAKER 17 - SEQUENCE S6
Dane BadawczeThe MODALITY corpus is one of the multimodal database of word recordings in English. It consists of over 30 hours of multimodal recordings. The database contains high-resolution, high-framerate stereoscopic video streams and audio signals obtained from a microphone array and a laptop microphone. The corpus can be employed to develop an AVSR system,...
-
Gesture-based computer control system applied to the interactive whiteboard
PublikacjaIn the paper the gesture-based computer control system coupled with the dedicated touchless interactive whiteboard is presented. The system engineered enables a user to control any top-most computer application by using one or both hands gestures. First, a review of gesture recognition applications with a focus on methods and algorithms applied is given. Hardware and software solution of the system consisting of a PC, camera, multimedia...
-
Gesture-based computer control system applied to the interactive whiteboard
PublikacjaIn the paper the gesture-based computer control system coupled with the dedicated touchless interactive whiteboard is presented. The system engineered enables a user to control any top-most computer application by using one or both hands gestures. First, a review of gesture recognition applications with a focus on methods and algorithms applied is given. Hardware and software solution of the system consisting of a PC, camera, multimedia...
-
Quality of graphical markers for the needs of eyewear devices
Publikacjain this paper we propose to cast the problem of identification of people, objects or places into an application for smart glasses that decodes information from graphical markers. We focus on analyzing different factors that can have influence on the processes of the automatic recognition of information from a code. The research we present aims at reviewing recognition performances in function of: size of a marker, distance from/to...
-
Is it too late now to say we’re sorry? Examining anxiety contagion and crisis communication strategies using machine learning
PublikacjaIn this paper, we explore the role of perceived emotions and crisis communication strategies via organizational computer-mediated communication in predicting public anxiety, the default crisis emotion. We use a machine-learning approach to detect and predict anxiety scores in organizational crisis announcements on social media and the public’s responses to these posts. We also control for emotional and language tones in organizational...
-
Zastosowanie metod eksploracji danych do analizy odpowiedzi czujników gazu
PublikacjaZagadnienia poruszane w niniejszej rozprawie dotyczą zastosowania metod eksploracji danych do analizy odpowiedzi czujników gazu, umożliwiających poprawną identyfikację składu mieszaniny gazowej w elektronicznych systemach rozpoznawania gazu. Elektroniczne systemy rozpoznawania gazu to urządzenia wykorzystujące czujniki gazu oraz odpowiednio dobrane metody analizy danych pomiarowych, zdolne do określenia składu mierzonej mieszaniny...
-
Features extraction from the electrocatalytic gas sensor responses
PublikacjaOne of the types of gas sensors used for detection and identification of toxic-air pollutant is an electrocatalytic gas sensor. The electrocatalytic sensors are working in cyclic voltammetry mode, enable detection of various gases. Their response are in the form of I-V curves which contain information about the type and the concentration of measured volatile compound. However,...
-
Trustworthy Applications of ML Algorithms in Medicine - Discussion and Preliminary Results for a Problem of Small Vessels Disease Diagnosis.
PublikacjaML algorithms are very effective tools for medical data analyzing, especially at image recognition. Although they cannot be considered as a stand-alone diagnostic tool, because it is a black-box, it can certainly be a medical support that minimize negative effect of human-factors. In high-risk domains, not only the correct diagnosis is important, but also the reasoning behind it. Therefore, it is important to focus on trustworthiness...
-
''Computing with words'' concept applied to musical instrument recognition. W: [CD-ROM] International Symposium of Musical Acoustics. ISMA MEXICO CITY. Mexico City, 9-13 December 2002. Mexico City: Escuela Nacional de Musica UNAM**2002, 8 s. 3 rys. 3 tab. bibliogr. 25 poz. Automatyczne rozpoznawanie klas instrumentów muzycznych w oparciu o wyraże- nia opisujące barwę dźwięku.
PublikacjaW referacie przedstawiono nowy sposób automatycznego przetwarzania danychmuzycznych w oparciu o paradygmat zaproponowany przez L. Zadeha. Pozwala tona automatyczne rozpoznawanie klas instrumentów muzycznych wykorzystując o-pis słowny barwy dźwięku. Przedstawiono system realizujący automatyczną kla-syfikację instrumentów muzycznych oparty o metodę zbiorów przybliżonych ilogikę rozmytą.
-
Eye Blink Based Detection of Liveness in Biometric Authentication Systems Using Conditional Random Fields
PublikacjaThe goal of this paper was to verify whether the conditional random fields are suitable and enough efficient for eye blink detection in user authentication systems based on face recognition with a standard web camera. To evaluate this approach several experiments were carried on using a specially developed test application and video database.
-
Adrian Kastrau mgr inż.
Osoby -
Robust unsupervised georeferencing algorithm for aerial and satellite imagery
PublikacjaIn order to eliminate a human factor and fully automate the process of embedding the spatial localization information in a remote sensed image the integrated georeferencing method was proposed. The paper presents this unsupervised and robust approach which is comprised of pattern recognition, using SIFT-based detector, and RANSAC based outlier removal with matching algorithm.
-
Virtual Whiteboard: A gesture-controlled pen-free tool emulating school whiteboard
PublikacjaIn the paper the so-called Virtual Whiteboard is presented which may be an alternative solution for modern electronic whiteboards based on electronic pens and sensors. The presented tool enables the user to write, draw and handle whiteboard contents using his/her hands only. An additional equipment such as infrared diodes, infrared cameras or cyber gloves is not needed. The user's interaction with the Virtual Whiteboard computer...
-
Automation of the Road Gate Operations Process at the Container Terminal—A Case Study of DCT Gdańsk SA
PublikacjaThe future increased terminal capacity will result in more container movement through the road complex and rail siding, which are one of the most critical areas (potential bottlenecks) in the container terminal. Truck turnaround time is one of the major factors that customers take into account while deciding how many container volumes they will handle through the container terminal. To enable to optimize increased traffic with...
-
Potential and Use of the Googlenet Ann for the Purposes of Inland Water Ships Classification
PublikacjaThis article presents an analysis of the possibilities of using the pre-degraded GoogLeNet artificial neural network to classify inland vessels. Inland water authorities monitor the intensity of the vessels via CCTV. Such classification seems to be an improvement in their statutory tasks. The automatic classification of the inland vessels from video recording is a one of the main objectives of the Automatic Ship Recognition and...
-
Molecular Imaging and Nanotechnology—Emerging Tools in Diagnostics and Therapy
PublikacjaPersonalized medicine is emerging as a new goal in the diagnosis and treatment of diseases. This approach aims to establish differences between patients suffering from the same disease, which allows to choose the most effective treatment. Molecular imaging (MI) enables advanced insight into molecule interactions and disease pathology, improving the process of diagnosis and therapy and, for that reason, plays a crucial role in personalized...
-
On Facial Expressions and Emotions RGB-D Database
PublikacjaThe goal of this paper is to present the idea of creating reference database of RGB-D video recordings for recognition of facial expressions and emotions. Two different formats of the recordings used for creation of two versions of the database are described and compared using different criteria. Examples of first applications using databases are also presented to evaluate their usefulness.
-
State of the art electronic nose technology and future trends
PublikacjaThis chapter briefly reviews the progress in field of artificial olfaction and demonstrates future trends in electronic nose technology. The discussion about e-nose concern also a big challenge for the pattern recognition (PARC) systems due to several particular problems they involve. Finally, the application of e-nose in different areas of life is given.
-
Deep neural networks for data analysis
Kursy OnlineThe aim of the course is to familiarize students with the methods of deep learning for advanced data analysis. Typical areas of application of these types of methods include: image classification, speech recognition and natural language understanding. Celem przedmiotu jest zapoznanie studentów z metodami głębokiego uczenia maszynowego na potrzeby zaawansowanej analizy danych. Do typowych obszarów zastosowań tego typu metod należą:...
-
Emotions in Human-Computer Interaction Research Group (EMORG)
Zespoły Badawcze* rozpoznawanie emocji użytkownika (ang. emotion elicitation) * reprezentację informacji o emocjach użytkownika (ang. emotion representation/ affect modelling) i zarządzanie nimi * ekspresję emocji lub reakcję na emocje przez programy np. przez wirtualne postaci (ang. affect expression) * wybrane zastosowania to badanie użyteczności oprogramowania rozszerzone o aspekty emocjonalne * badania wzorców behawioralnych w połączeniu...
-
An electronic nose based on the semiconducting and electrochemical gas sensors
PublikacjaThe practical application of human nose for fragrance recognition is severely limited by the fact that our sense of smell is subjective and gets tired easily. Consequently, there is a significant need for an instrument that can be a substitution of the human sense of smell. Development of an electronic nose devices is an active area of research starting from pioneering research of Dodd and Persuad in the mid-1980s. Such systems...
-
Further developments of parameterization methods of audio stream analysis for secuirty purposes
PublikacjaThe paper presents an automatic sound recognition algorithm intended for application in an audiovisual security monitoring system. A distributed character of security systems does not allow for simultaneous observation of multiple multimedia streams, thus an automatic recognition algorithm must be introduced. In the paper, a module for the parameterization and automatic detection of audio events is described. The spectral analyses...
-
Jan Cudzik dr inż. arch.
OsobyJan Cudzik (dr inż. arch.) jest adiunktem w Katedrze Architektury Miejskiej i Przestrzeni Nadwodnych na Wydziale Architektury Politechniki Gdańskiej oraz kierownikiem Laboratorium Cyfrowych Technologii i Materiałów Przyszłości. Prowadzi badania nad architekturą kinetyczną, technikami cyfrowymi w projektowaniu architektonicznym, fabrykacją cyfrową oraz formami sztucznej inteligencji w architekturze i sztuce. Jego badania nad automatyzacją...
-
Combined analysis of whole human blood parameters by Raman spectroscopy and spectral-domain low-coherence interferometry
PublikacjaIn this article the simultaneous investigation of blood parameters by complementary optical methods, Raman spectroscopy and spectral-domain low-coherence interferometry, is presented. Thus, the mutual relationship between chemical and physical properties may be investigated, because low-coherence interferometry measures optical properties of the investigated object, while Raman spectroscopy gives information about its molecular...
-
UPDRS tests for diagnosis of Parkinson's disease employing virtual-touchpad
PublikacjaThis paper presents a new approach to diagnosing Parkinson's disease. The progression of the disease can be measured by the UPDRS (Unified Parkinson Disease Rating Scale) scale which is used to evaluate motor and behavioral symptoms of Parkinson's disease. Hitherto the evaluation of the advancement of the disease in the UPDRS scale was made by a specialist through medical observation. The authors suggest a partial automation of...
-
Database of speech and facial expressions recorded with optimized face motion capture settings
PublikacjaThe broad objective of the present research is the analysis of spoken English employing a multiplicity of modalities. An important stage of this process, discussed in the paper, is creating a database of speech accompanied with facial expressions. Recordings of speakers were made using an advanced system for capturing facial muscle motion. A brief historical outline, current applications, limitations and the ways of capturing face...
-
Magdalena Szuflita-Żurawska
OsobyMagdalena Szuflita-Żurawska jest kierownikiem Sekcji Informacji Naukowo-Technicznej na Politechnice Gdańskiej oraz Liderem Centrum Kompetencji Otwartej Nauki przy Bibliotece Politechniki Gdańskiej. Jej główne zainteresowania badawcze koncentrują się w obszarze komunikacji naukowej oraz otwartych danych badawczych, a także motywacji i produktywności naukowej. Jest odpowiedzialna między innymi za prowadzenie szkoleń dla pracowników...
-
Julita Wasilczuk dr hab.
OsobyUrodzona 5 kwietnia 1965 roku w Gdańsku. W latach 1987–1991 odbyła studia na Wydziale Ekonomiki Transportu Uniwersytetu Gdańskiego (obecnie Wydział Ekonomii). Od 1993 roku zatrudniona na nowo utworzonym Wydziale Zarządzania i Ekonomii, Politechniki Gdańskiej, na stanowisku asystenta. W 1997 roku uzyskała stopień doktora nauk ekonomicznych na WZiE, a w 2006 doktora habilitowanego nauk ekonomicznych w dyscyplinie nauki o zarządzaniu,...
-
Distributed Representations Based on Geometric Algebra: the Continuous Model
PublikacjaAuthors revise the concept of a distributed representation of data as well as two previously developed models: Holographic Reduced Representation (HRR) and Binary Spatter Codes (BSC). A Geometric Analogue (GAc - ''c'' stands for continuous as opposed to its discrete version) of HRR is introduced - it employs role-filler binding based on geometric products. Atomic objects are real-valued vectors in n-dimensional Euclidean space...
-
Improving the Accuracy in Sentiment Classification in the Light of Modelling the Latent Semantic Relations
PublikacjaThe research presents the methodology of improving the accuracy in sentiment classification in the light of modelling the latent semantic relations (LSR). The objective of this methodology is to find ways of eliminating the limitations of the discriminant and probabilistic methods for LSR revealing and customizing the sentiment classification process (SCP) to the more accurate recognition of text tonality. This objective was achieved...
-
Comparison of Methods for Real and Imaginary Motion Classification from EEG Signals
PublikacjaA method for feature extraction and results of classification of EEG signals obtained from performed and imagined motion are presented. A set of 615 features was obtained to serve for the recognition of type and laterality of motion using 8 different classifications approaches. A comparison of achieved classifiers accuracy is presented in the paper, and then conclusions and discussion are provided. Among applied algorithms the...
-
Molecularly targeted nanoparticles: an emerging tool for evaluation of expression of the receptor for advanced glycation end products in a murine model of peripheral artery disease
PublikacjaAbstract Background: Molecular imaging with molecularly targeted probes is a powerful tool for studying the spatio-temporal interactions between complex biological processes. The pivotal role of the receptor for advanced glycation end products (RAGE) in numerous pathological processes, aroused the demand for RAGE targeted imaging in various diseases. In the study, we evaluated the use of a diagnostic imaging agent for RAGE quantification...
-
Activated Sludge Process Development
PublikacjaThis paper summarizes the most significant steps in the activated sludge process development and recognizes key contributors. Recognition of the roles of oxygen and living organisms was the first step (1882-1914). Ardern and Lockett (1914) named the accumulated olids "activated sludge". The process was rapidly accepted and applied in the period 1914-1930. The most dramatic changes in the activated sludge process understanding and...
-
AUGMENTATION OF THE CRITICAL HEAT FLUX IN WATER-Al2O3, WATER-TiO2 AND WATER-Cu NANOFLUIDS
PublikacjaThe main aim of the proposed study is therefore recognition of the phenomena accompanying nucleate boiling crisis of selected nanofluids during boiling on horizontal tubes of various outside diameters. Of particular interest is impact of contact angle and tube diameter on the value of critical heat flux. The results obtained should give more light on the nature of nucleate boiling crisis and will serve as a basis for future theoretical...
-
Biometryczna kontrola dostępu
PublikacjaOpisano szczegółowo algorytm detekcji oraz identyfikacji człowieka na podstawie punktów nodalnych twarzy. Zdefiniowano pojęcia: biometria, proces pomiaru biometrycznego, metody biometrycznej identyfikacji oraz kontrola dostępu. Przedstawiono opis opracowanego systemu biometrycznej identyfikacji wykorzystującego sztuczne sieci neuronowe. Podano wyniki badań oraz przeprowadzono ich wnikliwą dyskusję.Biometrics is the study of automated...
-
Stress Detection of Children with Autism using Physiological Signals in Kaspar Robot-Based Intervention Studies
PublikacjaThis study aims to develop a stress detection system using the blood volume pulse (BVP) signals of children with Autism Spectrum Disorder (ASD) during robot-based interven- tion. This study presents the heart rate variability (HRV) analysis method to detect the stress, where HRV features are extracted from raw BVP signals recorded from an E4 wristband during interaction studies with the social robot Kaspar. Low frequency power...
-
Noise profiling for speech enhancement employing machine learning models
PublikacjaThis paper aims to propose a noise profiling method that can be performed in near real-time based on machine learning (ML). To address challenges related to noise profiling effectively, we start with a critical review of the literature background. Then, we outline the experiment performed consisting of two parts. The first part concerns the noise recognition model built upon several baseline classifiers and noise signal features...
-
Robust Object Detection with Multi-input Multi-output Faster R-CNN
PublikacjaRecent years have seen impressive progress in visual recognition on many benchmarks, however, generalization to the out-of-distribution setting remains a significant challenge. A state-of-the-art method for robust visual recognition is model ensembling. However, recently it was shown that similarly competitive results could be achieved with a much smaller cost, by using multi-input multi-output architecture (MIMO). In this work,...
-
Robust Object Detection with Multi-input Multi-output Faster R-CNN
PublikacjaRecent years have seen impressive progress in visual recognition on many benchmarks, however, generalization to the out-of-distribution setting remains a significant challenge. A state-of-the-art method for robust visual recognition is model ensembling. However, recently it was shown that similarly competitive results could be achieved with a much smaller cost, by using multi-input multi-output architecture (MIMO). In this work,...