Filters
total: 506
filtered: 425
-
Catalog
Chosen catalog filters
Search results for: GAS RECOGNITION
-
Multi-Stage Video Analysis Framework
PublicationThe chapter is organized as follows. Section 2 presents the general structure of the proposed framework and a method of data exchange between system elements. Section 3 is describing the low-level analysis modules for detection and tracking of moving objects. In Section 4 we present the object classification module. Sections 5 and 6 describe specialized modules for detection and recognition of faces and license plates, respectively....
-
Parallelization of video stream algorithms in kaskada platform
PublicationThe purpose of this work is to present different techniques of video stream algorithms parallelization provided by the Kaskada platform - a novel system working in a supercomputer environment designated for multimedia streams processing. Considered parallelization methods include frame-level concurrency, multithreading and pipeline processing. Execution performance was measured on four time-consuming image recognition algorithms,...
-
Comparison of Tracking Methods in Respect of Automation of Animal Behavioral Test
PublicationAutomation in experiments carried out on animals is getting more and more important in research. Computers take over laborious and time-consuming activities like recording and analysing images of experiment scene. The first step in an image analysis is finding and distinguishing between the observed animals, and then tracking all objects during the experiment. In this paper four tracking methods are presented. Quantitative and...
-
Student competitions as a socio-spatial tool for planning urban structures
PublicationThe aim of the article is to show the interdependencies between theory and practice based on the example of the student competitions at the Faculty of Architecture at the Gdańsk University of Technology. These competitions, on the one hand, broaden the spectrum of issues related to design and, on the other hand, contribute to the better recognition of problems related to tasks to be solved. Both the teaching and applicational aspects...
-
Evaluation of the Effectiveness of Methods for Delimitation of the Boundaries of Registered Parcels in the Process of Modernization of Land and Building Registration
PublicationIn the article, a comparative analysis of two methods for delimitation of the boundaries of registered parcels was carried out: the method of direct measurement in the field and the photogrammetric method. One of the analyzed factors was the attendance of parcels’ owners during the development of boundary recognition agreements. Research has shown that in this aspect the method of direct measurement...
-
On practical application of Shannon theory to character recognition and more
PublicationLet us consider an optical character recognition system, which in particular can be used for identifying objects that were assigned strings of some length. The system is not perfect, for example, it sometimes recognizes wrongly the characters "Y" and "V". What is the largest set of strings of given length for the system under consideration, which can be mutually correctly recognized, and the corresponding objects correctly identified?...
-
Neural Network Subgraphs Correlation with Trained Model Accuracy
PublicationNeural Architecture Search (NAS) is a computationally demanding process of finding optimal neural network architecture for a given task. Conceptually, NAS comprises applying a search strategy on a predefined search space accompanied by a performance evaluation method. The design of search space alone is expected to substantially impact NAS efficiency. We consider neural networks as graphs and find a correlation between the presence...
-
Septic safe interactions with smart glasses in health care
PublicationIn this paper, septic safe methods of interaction with smart glasses, due to the health care environment applications consideration, are presented. The main focus is on capabilities of an optical, proximity-based gesture sensor and eye-tracker input systems. The design of both interfaces is being adapted to the open smart glasses platform that is being developed under the eGlasses project. Preliminary results obtained from the...
-
Salicylaldimine-based receptor as a material for iron(III) selective optical sensing
Publicationα,α-Bis(salicylimino)-m-xylene (L) was prepared using both conventional and microwave-assisted procedure. The compound exhibits ability to colorimetric recognition of iron(III) ions in aqueous environment, what is shown by significant color change from yellow to purple. In DMSO : water (9:1 v/v) solvent system receptor creates with iron(III) cations complexes of 2:1 stoichiometry (L:Fe3+) with stability constant (log K) 7.54±0.21....
-
An Overview of the Development of a Real-Time System for Endoscopic Video Classification
PublicationThe article presents the results of improving endoscopic image classification algorithms in an effort towards applying them in a real-time diagnosis supporting system. Methods for the detection and removal of personal data are presented and discussed. The currently developed recognition algorithms have been improved in terms of accuracy and performance to make them suitable for a real-life implementation. Their test results are...
-
Emotion monitoring system for drivers
PublicationThis article describes a new approach to the issue of building a driver monitoring system. Actual systems focus, for example, on tracking eyelid and eyebrow movements that result from fatigue. We propose a different approach based on monitoring the state of emotions. Such a system assumes that by using the emotion model based on our own concept, referred to as the reverse Plutchik’s paraboloid of emotions, the recognition of emotions...
-
Molecular Recognition in Complexes of TRF Proteins with Telomeric DNA
PublicationTelomeres are specialized nucleoprotein assemblies that protect the ends of linear chromosomes. In humans and many other species, telomeres consist of tandem TTAGGG repeats bound by a protein complex known as shelterin that remodels telomeric DNA into a protective loop structure and regulates telomere homeostasis. Shelterin recognizes telomeric repeats through its two major components known as Telomere Repeat-Binding Factors, TRF1...
-
Remote Estimation of Video-Based Vital Signs in Emotion Invocation Studies
PublicationAbstract— The goal of this study is to examine the influence of various imitated and video invoked emotions on the vital signs (respiratory and pulse rates). We also perform an analysis of the possibility to extract signals from sequences acquired with cost-effective cameras. The preliminary results show that the respiratory rate allows for better separation of some emotions than the pulse rate, yet this relation highly depends...
-
Application of Electrochemical Impedance Spectroscopy to evaluate cathodically protected coated steel in seawater
PublicationTwo types of organic coated carbon steel (S235JR2 grade) electrodes were exposed to artificial seawater environment. One prepared type was defect free while the other one had an intentionally introduced φ0,5 cm coating defect. Both kinds of samples were polarized during the exposure to four potentials corresponding to four different cathodic protection levels. Evolution of their EIS spectra is presented in this paper. Results obtained...
-
Music Mood Visualization Using Self-Organizing Maps
PublicationDue to an increasing amount of music being made available in digital form in the Internet, an automatic organization of music is sought. The paper presents an approach to graphical representation of mood of songs based on Self-Organizing Maps. Parameters describing mood of music are proposed and calculated and then analyzed employing correlation with mood dimensions based on the Multidimensional Scaling. A map is created in which...
-
Interactions using passive optical proximity detector
PublicationIn this paper we evaluated the possible application of a passive, optical sensor as an interface for human-smart glasses interactions. The designed proximity sensor is composed of set of photodiodes and the appropriate hardware and software components. First, experiments were performed for the estimations of such parameters as distance to an object, its width and velocity. Achieved results were satisfactory. Therefore, next, a...
-
Affect-awareness framework for intelligent tutoring systems
PublicationThe paper proposes a framework for construction of Intelligent Tutoring Systems (ITS), that take into consideration student emotional states and make affective interventions. The paper provides definitions of `affect-aware systems' and `affective interventions' and describes the concept of the affect-awareness framework. The proposed framework separates emotion recognition from its definition, processing and making decisions on...
-
Affective computing and affective learning – methods, tools and prospects
PublicationEvery teacher knows that interest, active participation and motivation are important factors in the learning process. At the same time e-learning environments almost always address only the cognitive aspects of education. This paper provides a brief review of methods used for affect recognition, representation and processing as well as investigates how these methods may be used to address affective aspect of e-education. The paper...
-
A new division of bacterial UvrA homologues
PublicationThe UvrA protein is a DNA-binding and damage-recognition enzyme which participates in the prokaryotic type nucleotide excision repair (NER) pathway. It has recently been noted that some bacterial genomes comprise additional uvrA genes which encode five distinct types of UvrA homologue. We investigated the sequences of over 2400 bacterial genomes and found 130 examples of bacteria containing uvrA 2 genes. The sequence analyses conducted...
-
Parameters optimization in medicine supporting image recognition algorithms
PublicationIn this paper, a procedure of automatic set up of image recognition algorithms' parameters is proposed, for the purpose of reducing the time needed for algorithms' development. The procedure is presented on two medicine supporting algorithms, performing bleeding detection in endoscopic images. Since the algorithms contain multiple parameters which must be specified, empirical testing is usually required to optimise the algorithm's...
-
Integrating heterogeneous systems with high-dependability requirements by means of web services
PublicationWeb services are commonly used on boundaries of heterogeneous components in Service Oriented Architecture (SOA) as they provide a universal communication channel not bound to any particular programming language or run-time platform. This paper describes how web services can be used to integrate heterogeneous systems which serve purposes requiring high dependability, reliability and availability. Examples of such systems include...
-
Horizontally-split-drain MAGFET - a highly sensitive magnetic field sensor
PublicationWe propose a novel magnetic field sensitive semiconductor device, viz., Horizontally-Split-Drain Magnetic-Field Sensitive Field-Effect Transistor (HSDMAGFET) which can be used to measure or detect steady or variable magnetic fields. Operating principle of the transistor is based on one of the galvanomagnetic phenomena and a Gradual Channel Detachment Effect (GCDE) and is very similar to that of Popovic and Baltes's SDMAGFET. The...
-
Visual Detection of People Movement Rules Violation in Crowded Indoor Scenes
PublicationThe paper presents a camera-independent framework for detecting violations of two typical people movement rules that are in force in many public transit terminals: moving in the wrong direction or across designated lanes. Low-level image processing is based on object detection with Gaussian Mixture Models and employs Kalman filters with conflict resolving extensions for the object tracking. In order to allow an effective event...
-
Comparison of Acoustic and Visual Voice Activity Detection for Noisy Speech Recognition
PublicationThe problem of accurate differentiating between the speaker utterance and the noise parts in a speech signal is considered. The influence of utilizing a voice activity detection in speech signals on the accuracy of the automatic speech recognition (ASR) system is presented. The examined methods of voice activity detection are based on acoustic and visual modalities. The problem of detecting the voice activity in clean and noisy...
-
Analysis of the objects images on the sea using Dempster-Shafer Theory
PublicationThe paper presents the concept of using aerial and satellite imagery or images coming from the marine radar to identify and track vessels at sea. The acquired data were subjected to a highly advanced image analysis. The development of remote sensing techniques allows to gain a huge amount of data. These data are useful information source however usually we have to use different data mining methods to gain interested information....
-
Superresolution algorithm to video surveillance system
PublicationAn application of a multiframe SR (superresolution) algorithm applied to video monitoring is described. The video signal generated by various types of video cameras with different parameters and signal distortions which may be very problematic for superresolution algorithms. The paper focuses on disadvantages in video signal which occur in video surveillance systems. Especially motion estimation and its influence on superresolution...
-
Methodology of Selecting the Optimal Receptor to Create an Electrochemical Immunosensor for Equine Arteritis Virus Protein Detection
PublicationThe study reports a methodology of selecting the optimal receptor to create an electrochemical immunosensor for equine arteritis virus (EAV) protein detection. The detection was based on antigen recognition by antibodies immobilized on gold electrodes. Modification steps were controlled by electrochemical impedance spectroscopy and cyclic voltammetry measurements. In order to obtain the impedance immunosensor with the best parameters,...
-
Video content analysis in the urban area telemonitoring system
PublicationThe task of constant monitoring of video streams from a large number of cameras and reviewing the recordings in order to find a specified event requires a considerable amount of time and effort from the system operators and it is prone to errors. A solution to this problem is an automatic system for constant analysis of camera images being able to raise an alarm if a predefined event is detected. The chapter presents various aspects...
-
Development and tuning of irregular divide-and-conquer applications in DAMPVM/DAC
PublicationThis work presents implementations and tuning experiences with parallel irregular applications developed using the object oriented framework DAM-PVM/DAC. It is implemented on top of DAMPVM and provides automatic partitioning of irregular divide-and-conquer (DAC) applications at runtime and dynamic mapping to processors taking into account their speeds and even loads by other user processes. New implementations of parallel applications...
-
Application of molecularly imprinted polymers in analytical chiral separations and analysis
PublicationOver the last two decades the process of development and application of a new types of molecular imprinted polymer (MIP) sorbents in the field of analytical chemistry have been widely described in the literature. One of the new trends in analytical chemistry practice is the use of new types of MIP sorbents as specific sorption materials constituting the stationary phase in advanced separation techniques. The following review paper...
-
Deep Learning: A Case Study for Image Recognition Using Transfer Learning
PublicationDeep learning (DL) is a rising star of machine learning (ML) and artificial intelligence (AI) domains. Until 2006, many researchers had attempted to build deep neural networks (DNN), but most of them failed. In 2006, it was proven that deep neural networks are one of the most crucial inventions for the 21st century. Nowadays, DNN are being used as a key technology for many different domains: self-driven vehicles, smart cities,...
-
Mispronunciation Detection in Non-Native (L2) English with Uncertainty Modeling
PublicationA common approach to the automatic detection of mispronunciation in language learning is to recognize the phonemes produced by a student and compare it to the expected pronunciation of a native speaker. This approach makes two simplifying assumptions: a) phonemes can be recognized from speech with high accuracy, b) there is a single correct way for a sentence to be pronounced. These assumptions do not always hold, which can result...
-
Deep Learning
PublicationDeep learning (DL) is a rising star of machine learning (ML) and artificial intelligence (AI) domains. Until 2006, many researchers had attempted to build deep neural networks (DNN), but most of them failed. In 2006, it was proven that deep neural networks are one of the most crucial inventions for the 21st century. Nowadays, DNN are being used as a key technology for many different domains: self-driven vehicles, smart cities,...
-
Methodology of Selecting the Optimal Receptor to Create an Electrochemical Immunosensor for Equine Arteritis Virus Protein Detection
PublicationThe study reports a methodology of selecting the optimal receptor to create an electrochemical immunosensor for equine arteritis virus (EAV) protein detection. The detection was based on antigen recognition by antibodies immobilized on gold electrodes. Modification steps were controlled by electrochemical impedance spectroscopy and cyclic voltammetry measurements. In order to obtain the impedance immunosensor with the best parameters,...
-
Modern trends in solid phase extraction: New sorbent media
PublicationBased on the recently published literature, this review provides an update of the most important features and application of formats and devices employed in solid phase extraction (SPE). Special attention was paid on new trapping media proposed in SPE prior the chromatography analysis, based on the use of nanostructured materials, including carbon nanomaterials, electrospun nanofibers, dendrimes and magnetic nanoparticles, molecular...
-
Interaction Between Storm Water Conduit Flow and Overland Flow for Numerical Modelling of Urban Area Inundation
PublicationNowadays we can observe increasing frequency of inundations in cities. This makes accurate predicting of inundations more important than ever. Numerical modeling of this issue requires complex approach with simultaneous calculations of pipe flow and surface flow. In this paper, after a short review of known methods used for solving pipe and surface flow, we will try to answer the question if presented methods would be sufficiently...
-
Adjusting Game Difficulty by Recreating Behavioral Trees of Human Player Actions
PublicationThis paper presents a proposition of a method for adjusting game difficulty to the current level of player's skills in one-on-one games. The method is based on recognition of human player's actions and recording of those actions in the form of behavioral trees. Such trees are later used to drive behaviors of computer-controlled opponents so that human player has beat hit own strategy and improve on it, to win subsequent games....
-
Performance Analysis of Interaction between Smart Glasses and Smart Objects Using Image-Based Object Identification
PublicationWe propose the use of smart glasses to collaborate with smart objects in the Internet of Things environment. Particularly we are focusing on new interaction methods and the analysis of acceptable reaction times in the process of object recognition using smart glasses. We evaluated the proposed method using user studies and experiments with three different smart glasses: Google Glass, Epson Moverio, and the developed eGlasses platform....
-
Methodology of Affective Intervention Design for Intelligent Systems
PublicationThis paper concerns how intelligent systems should be designed to make adequate, valuable and natural affective interventions. The article proposes a process for choosing an affective intervention model for an intelligent system. The process consists of 10 activities that allow for step-by-step design of an affective feedback loop and takes into account the following factors: expected and desired emotional states, characteristics...
-
Semi complex navigation with an active optical gesture sensor
PublicationThis paper presents the methods of diversified touchless interactions between a user and a mobile platform utilizing the optical gesture sensor. The sensor uses 8 photodiodes to measure the reflected light in the active mode (using embedded LEDs) or it measures shadows caused by fingers in the passive mode. Several algorithms were implemented: automatic mode switching, adaptive illumination level compensation, resolution improvements...
-
1,3,4-Thiadiazole-based diamides: Synthesis and complexation properties
PublicationAromatic diamides, derivative of 2,6-pyridinedicarboxylic acid and isophthalic acid, bearing 1,3,4-thiadiazole residue were prepared with satisfactory yields in conventional procedures and microwave stimulated reactions. X-ray structure of N,N-bis (1,3,4-thiadiazol-2-yl)-2,6-pyridinedicarboxamide (2) DMSO solvate (2DMSO) was described. Selective zinc(II), lanthanum(III), terbium(III) and L-tyrosine recognition was found for N,N-bis(1,3,4-thiadiazol-2-yl)-2,6-pyridinedicarboxamide...
-
Poszukiwanie dobrych odpowiedzi na źle postawione pytania, rzecz o przedsiębiorczości kobiet
PublicationWomen entrepreneurship has been the subject of research for many years and its results are often compared against the men entrepreneurship results. The conducted research has often been aimed at identification/recognition of the differences between the entrepreneurs of opposite gender. The lack of satisfactory proof for the existence of the differences has been attributed by some determined researchers to inappropriate research...
-
From Linear Classifier to Convolutional Neural Network for Hand Pose Recognition
PublicationRecently gathered image datasets and the new capabilities of high-performance computing systems have allowed developing new artificial neural network models and training algorithms. Using the new machine learning models, computer vision tasks can be accomplished based on the raw values of image pixels instead of specific features. The principle of operation of deep neural networks resembles more and more what we believe to be happening...
-
Searching of the buried objects into the sea bottom by means of nonlinear acouctic methods
PublicationThe main goal of this paper is to introduce the methodology of preparing the area for investigations that will be carried out at the sea. As the first step there is recognition of the basic method both in the theory as well as experimental investigation. There were taken into account the nonlinear methods. These ones are very promising methods that have very interesting features, very convenient for examinations of the seabed structure....
-
Using Eye-tracking to get information on the skills acquisition by the radiology residents
PublicationThis paper describes the possibility of monitoring the progress of knowledge and skills acquisition by the students of radiology. It is achieved by an analysis of a visual attention distribution patterns during image-based tasks solving. The concept is to use the eye-tracking data to recognize the way how the radiographic images are read by recognized experts, radiography residents involved in the training program, and untrained...
-
The preparation and evaluation of core-shell magnetic dummy-template molecularly imprinted polymers for preliminary recognition of the low-mass polybrominated diphenyl ethers from aqueous solutions
PublicationThe design, preparation process, binding abilities, morphological characteristic and prospective field of application of dummy-template magnetic molecularly imprinted polymer (DMMIP) for preliminary recognition of the selected low-mass polybrominated diphenyl ethers (PBDE-47 and PBDE-99) from aquatic environment were investigated. The surface of iron oxide (Fe3O4) nanopowder (50-100 nm particles size) was modified with tetraethoxysilane...
-
Recognition of Emotions in Speech Using Convolutional Neural Networks on Different Datasets
PublicationArtificial Neural Network (ANN) models, specifically Convolutional Neural Networks (CNN), were applied to extract emotions based on spectrograms and mel-spectrograms. This study uses spectrograms and mel-spectrograms to investigate which feature extraction method better represents emotions and how big the differences in efficiency are in this context. The conducted studies demonstrated that mel-spectrograms are a better-suited...
-
Deep learning techniques for biometric security: A systematic review of presentation attack detection systems
PublicationBiometric technology, including finger vein, fingerprint, iris, and face recognition, is widely used to enhance security in various devices. In the past decade, significant progress has been made in improving biometric sys- tems, thanks to advancements in deep convolutional neural networks (DCNN) and computer vision (CV), along with large-scale training datasets. However, these systems have become targets of various attacks, with...
-
Performance Analysis of Developed Multimodal Biometric Identity Verification System
PublicationThe bank client identity verification system developed in the course of the IDENT project is presented. The total number of five biometric modalities including: dynamic handwritten signature proofing, voice recognition, face image verification, face contour extraction and hand blood vessels distribution comparison have been developed and studied. The experimental data were acquired employing multiple biometric sensors installed...
-
Bimodal classification of English allophones employing acoustic speech signal and facial motion capture
PublicationA method for automatic transcription of English speech into International Phonetic Alphabet (IPA) system is developed and studied. The principal objective of the study is to evaluate to what extent the visual data related to lip reading can enhance recognition accuracy of the transcription of English consonantal and vocalic allophones. To this end, motion capture markers were placed on the faces of seven speakers to obtain lip...