Filters
total: 941
filtered: 645
Search results for: FACIAL EXPRESSIONS RECOGNITION
-
Enabling Deeper Linguistic-based Text Analytics – Construct Development for the Criticality of Negative Service Experience
PublicationSignificant progress has been made in linguistic-based text analytics particularly with the increasing availability of data and deep learning computational models for more accurate opinion analysis and domain-specific entity recognition. In understanding customer service experience from texts, analysis of sentiments associated with different stages of the service lifecycle is a useful starting point. However, when richer insights...
-
On the derivatives $\partial^{2}P_{\nu}(z)/\partial\nu^{2}$ and $\partial Q_{\nu}(z)/\partial\nu$ of the Legendre functions with respect to their degrees
PublicationWe provide closed-form expressions for the degree-derivatives $[\partial^{2}P_{\nu}(z)/\partial\nu^{2}]_{\nu=n}$ and $[\partial Q_{\nu}(z)/\partial\nu]_{\nu=n}$, with $z\in\mathbb{C}$ and $n\in\mathbb{N}_{0}$, where $P_{\nu}(z)$ and $Q_{\nu}(z)$ are the Legendre functions of the first and the second kind, respectively. For $[\partial^{2}P_{\nu}(z)/\partial\nu^{2}]_{\nu=n}$, we find that % \begin{displaymath} \frac{\partial^{2}P_{\nu}(z)}{\partial\nu^{2}}\bigg|_{\nu=n} =-2P_{n}(z)\Li_{2}\frac{1-z}{2}+B_{n}(z)\ln\frac{z+1}{2}+C_{n}(z), \end{displaymath} % where...
-
Determining an Architectural Character for Durban Residential Streetscapes
PublicationIn the current global context and in consideration of the Sustainable Development Goals, there is a strong need for urban densification. However, this development is also driven by processes linked to the idea of capitalism and 'economic growth'. Such development often leads to the loss of the 'genius loci' of a place and sometimes even overlooks the fact that the quality of the built environment greatly influences the health and...
-
Structural insights, biocatalytic characteristics, and application prospects of lignin-modifying enzymes for sustainable biotechnology
PublicationLignin modifying enzymes (LMEs) have gained widespread recognition in depolymerization of lignin polymers by oxidative cleavage. LMEs are a robust class of biocatalysts that include lignin peroxidase (LiP), manganese peroxidase (MnP), versatile peroxidase (VP), laccase (LAC), and dye-decolorizing peroxidase (DyP). Members of the LMEs family act on phenolic, non-phenolic substrates and have been widely researched for valorization...
-
Facilitating free travel in the Schengen area—A position paper by the European Association for Biometrics
PublicationDue to migration, terror-threats and the viral pandemic, various EU member states have re-established internal border control or even closed their borders. European Association for Biometrics (EAB), a non-profit organisation, solicited the views of its members on ways which biometric technologies and services may be used to help with re-establishing open borders within the Schengen area while at the same time mitigating any adverse...
-
Creating a Realible Music Discovery and Recomendation System
PublicationThe aim of this paper is to show problems related to creating a reliable music dis-covery system. The SYNAT database that contains audio files is used for the purpose of experiments. The files are divided into 22 classes corresponding to music genres with different cardinality. Of utmost importance for a reliable music recommendation system are the assignment of audio files to their appropriate gen-res and optimum parameterization...
-
Problems of modelling toxic compounds emitted by a marine internal combustion engine for the evaluation of its structure parameters
PublicationThe paper presents the possibility of using an analytical study of the engine exhaust ignition to evaluate the technical condition of the selected components. Software tools available for the analysis of experimental data commonly use multiple regression model that allows the study of the effects and iterations between model input quantities and one output variable. The use of multi-equation models gives a lot of freedom in the...
-
Minimizing Distribution and Data Loading Overheads in Parallel Training of DNN Acoustic Models with Frequent Parameter Averaging
PublicationIn the paper we investigate the performance of parallel deep neural network training with parameter averaging for acoustic modeling in Kaldi, a popular automatic speech recognition toolkit. We describe experiments based on training a recurrent neural network with 4 layers of 800 LSTM hidden states on a 100-hour corpora of annotated Polish speech data. We propose a MPI-based modification of the training program which minimizes the...
-
The role of EMG module in hybrid interface of prosthetic arm
PublicationNearly 10% of all upper limb amputations concern the whole arm. It affects the mobility and reduces the productivity of such a person. These two factors can be restored by using prosthetics. However, the complexity of human arm makes restoring its basic functions quite difficult. When the osseointegration and/or targeted muscle reinnervation (TMR) are not possible, different modalities can be used to control the prosthesis. In...
-
Optical Sensor Based Gestures Inference Using Recurrent Neural Network in Mobile Conditions
PublicationIn this paper the implementation of recurrent neural network models for hand gesture recognition on edge devices was performed. The models were trained with 27 hand gestures recorded with the use of a linear optical sensor consisting of 8 photodiodes and 4 LEDs. Different models, trained off-line, were tested in terms of different network topologies (different number of neurons and layers) and different effective sampling frequency...
-
Semantic URL Analytics to Support Efficient Annotation of Large Scale Web Archives
PublicationLong-term Web archives comprise Web documents gathered over longer time periods and can easily reach hundreds of terabytes in size. Semantic annotations such as named entities can facilitate intelligent access to the Web archive data. However, the annotation of the entire archive content on this scale is often infeasible. The most efficient way to access the documents within Web archives is provided through their URLs, which are...
-
Comparison of Classification Methods for EEG Signals of Real and Imaginary Motion
PublicationThe classification of EEG signals provides an important element of brain-computer interface (BCI) applications, underlying an efficient interaction between a human and a computer application. The BCI applications can be especially useful for people with disabilities. Numerous experiments aim at recognition of motion intent of left or right hand being useful for locked-in-state or paralyzed subjects in controlling computer applications....
-
Structural and dynamic insights on the EmrE protein with TPP+ and related substrates through molecular dynamics simulations
PublicationEmrE is a bacterial transporter protein that forms an anti-parallel homodimer with four transmembrane helices in each monomer. EmrE transports positively charged aromatic compounds, such as TPP+ and its derivatives. We performed molecular dynamics (MD) simulations of EmrE in complex with TPP+, MeTPP+, and MBTPP+ embedded in a membrane. The detailed molecular properties and interactions were analysed for all EmrE-ligand complexes....
-
ROAD SAFETY FOR CYCLISTS BASED ON THE CALORIES NEEDED
PublicationCyclists are a vulnerable group of road users, especially when no separate infrastructure for cyclists is provided. Then, road factors such as distance and altitude differences can indirectly affect cyclists' safety. Therefore, the authors proposed a procedure based on the geometric characteristics of the road that can determine riding difficulties for cyclists. The proposed procedure can be used both by the public authorities who...
-
A novel in vivo approach to assess strains of the human abdominal wall under known intraabdominal pressure
PublicationThe study concerns mechanical behaviour of a living human abdominal wall. A better mechanical understanding of a human abdominal wall and recognition of its material properties is required to find mechanically compatible surgical meshes to significantly improve the treatment of ventral hernias. A non-invasive methodology, based on in vivo optical measurements is proposed to determine strains of abdominal wall corresponding to...
-
THE STUDY OF WATER POLLUTION OF THE LOWER VISTULA RIVER BY PLASTIC PARTICLES
PublicationSince the beginning of widespread use of plastic its consumption and production has been constantly increasing. As a result of human activity part of waste ends up in our environment and is deposited in each of the elements of the biosphere. These impurities can be in the form of large elements, small particles fragmented to macroscopic level (pellets, facial scrub grains) and the microparticles visible under a microscope. Particularly...
-
Representation of magnetic hysteresis in a circuit model of a single-phase transformer
PublicationThe paper presents a mathematical model for the hysteresis phenomenon in a multi-winding single-phase core type transformer. The set of loop differential equations was developed for K-th winding transformer model where the flux linkages of each winding includes a flux common Φ to all windings as function of magneto motive force Θ of all windings. The first purpose of this paper is to determine a hysteresis nonlinearity involved...
-
Design and construction of an industrial robot controlled by the ROS environment
PublicationThis engineering thesis focuses on the recognition of modern budgetary solutions of roboticarms and on the design and implementation of one of them. Historical solutions are discussedusing the example of the IRB6 robot and the modern approach - the Omron Viper 850. Thepaper includes a description of the design thought of the different parts. Mechanical, electrical andsoftware aspects are presented. In...
-
CNN-CLFFA: Support Mobile Edge Computing in Transportation Cyber Physical System
PublicationIn the present scenario, the transportation Cyber Physical System (CPS) improves the reliability and efficiency of the transportation systems by enhancing the interactions between the physical and cyber systems. With the provision of better storage ability and enhanced computing, cloud computing extends transportation CPS in Mobile Edge Computing (MEC). By inspecting the existing literatures, the cloud computing cannot fulfill...
-
Identification of Emotional States Using Phantom Miro M310 Camera
PublicationThe purpose of this paper is to present the possibilities associated with the use of remote sensing methods in identifying human emotional states, and to present the results of the research conducted by the authors in this field. The studies presented involved the use of advanced image analysis to identify areas on the human face that change their activity along with emotional expression. Most of the research carried out in laboratories...
-
Modernization and adaptation of historical interiors
PublicationModernization of the historical building's interior entails the need to take many decisions, often conflicting. Operational requirements, protection of the architectural heritage, fire-safety recommendations, construction regulations, all these aspects involve a whole set of problems that require a rational solution, respecting ambient architectural and historical value, as well as the needs arising from the planned transformation....
-
Network oscillations modulate interictal epileptiform spike rate during human memory
PublicationEleven patients being evaluated with intracranial electroencephalography for medically resistant temporal lobe epilepsy participated in a visual recognition memory task. Interictal epileptiform spikes were manually marked and their rate of occurrence compared between baseline and three 2 s periods spanning a 6 s viewing period. During successful, but not unsuccessful, encoding of the images there was a significant reduction in...
-
Selected Technical Issues of Deep Neural Networks for Image Classification Purposes
PublicationIn recent years, deep learning and especially Deep Neural Networks (DNN) have obtained amazing performance on a variety of problems, in particular in classification or pattern recognition. Among many kinds of DNNs, the Convolutional Neural Networks (CNN) are most commonly used. However, due to their complexity, there are many problems related but not limited to optimizing network parameters, avoiding overfitting and ensuring good...
-
Nonlocal Vibration of Carbon/Boron-Nitride Nano-hetero-structure in Thermal and Magnetic Fields by means of Nonlinear Finite Element Method
PublicationHybrid nanotubes composed of carbon and boron-nitride nanotubes have manifested as innovative building blocks to exploit the exceptional features of both structures simultaneously. On the other hand, by mixing with other types of materials, the fabrication of relatively large nanotubes would be feasible in the case of macroscale applications. In the current article, a nonlinear finite element formulation is employed to deal with...
-
Towards evaluation of the Second Generation Intact Stability Criteria - examination of a fishing vessel vulnerability to surf-riding, based on historical capsizing
PublicationThe Second Generation Intact Stability Criteria (SGISC) are the latest achievements in the field of intact ship stability assessment. The criteria are the result of massive international cooperative efforts and extensive research that lasted more than 15 years. Even though they are based on a solid scientific foundation, the trial period has commenced to collect user experience and further validation. One of possible approaches...
-
Crystal structures of aminotransferases Aro8 and Aro9 from Candida albicans and structural insights into their properties
PublicationAminotransferases catalyze reversibly the transamination reaction by a ping-pong bi-bi mechanism with pyridoxal 5′-phosphate (PLP) as a cofactor. Various aminotransferases acting on a range of substrates have been reported. Aromatic transaminases are able to catalyze the transamination reaction with both aromatic and acidic substrates. Two aminotransferases from C. albicans, Aro8p and Aro9p, have been identified recently, exhibiting...
-
Conservation and diversity of MutS proteins
PublicationThe homologues of MutS, mismatch repair protein, exist in all prokaryotes, with the exception of Actinobacteria, Mollicutes and part of the Archaea. Multiple alignments of 316 MutS amino acid sequences from 169 species revealed conserved residues and sequence motifs distinguishing MutS homologues. All MutS homologues show high conservation within the ATPase domain. MutS1, the homologue responsible for DNA mismatch recognition,...
-
In vitro affinity of Deinococcus radiodurans MutS towards mismatched DNA exceeds that of its orthologues from Escherichia coli and Thermus thermophilus
PublicationThe mismatch binding protein MutS is responsible for the recognition of mispaired and unpaired bases, which is the initial step in DNA repair. Among the MutS proteins most extensively studied in vitro are those derived from Thermus thermophilus, Thermus aquaticus and Escherichia coli. Here, we present the first report on the in vitro examination of DNA mismatch binding activity of MutS protein from Deinococcus radiodurans and confront...
-
Thermal Image Processing for Respiratory Estimation from Cubical Data with Expandable Depth
PublicationAs healthcare costs continue to rise, finding affordable and non-invasive ways to monitor vital signs is increasingly important. One of the key metrics for assessing overall health and identifying potential issues early on is respiratory rate (RR). Most of the existing methods require multiple steps that consist of image and signal processing. This might be difficult to deploy on edge devices that often do not have specialized...
-
Activation of Metabotropic Glutamate Receptor (mGlu2) and Muscarinic Receptors (M1, M4, and M5), Alone or in Combination, and Its Impact on the Acquisition and Retention of Learning in the Morris Water Maze, NMDA Expression and cGMP Synthesis
PublicationThe Morris water maze (MWM) is regarded as one of the most popular tests for detecting spatial memory in rodents. Long-term potentiation and cGMP synthesis seem to be among the crucial factors involved in this type of learning. Muscarinic (M1, M4, and M5 receptors) and metabotropic glutamate (mGlu) receptors are important targets in the search for antipsychotic drugs with the potency to treat cognitive disabilities associated with...
-
Molecularly imprinted polymers for the detection of volatile biomarkers
PublicationIn the field of cancer detection, the development of affordable, quick, and user-friendly sensors capable of detecting various cancer biomarkers, including those for lung cancer (LC), holds utmost significance. Sensors are expected to play a crucial role in the early-stage diagnosis of various diseases. Among the range of options, sensors emerge as particularly appealing for the diagnosis of various diseases, owing to their cost-effectiveness,...
-
Psychological and physical components in forming preferences on urban greenery management – The case of trees
PublicationPublic opinion is increasingly important in managing urban greenery. In this regard, this study demonstrates the importance of sociological (environmental worldviews), psychological (place attachment, perceived benefits of trees), and physical factors (type of building people live in, and urban greenery) in forming residents’ opinions on whether the municipality or landowners should decide about tree removal on private land. Logistic...
-
Recent advancements in molecularly imprinted polymers for the removal of heavy metal ions and dyes
PublicationContamination set off by highly toxic metal ions and dyes is a big threat to the environment and living beings. Various industries like metal plating, mining, pesticides, battery manufacturing, and dyeing release metal ions and toxic dyes directly into the water. It is necessary to remove these toxic substances from the environment. Molecular imprinting technology (MIT) got a lot of attention in the last two decades because of...
-
Myrosinase activity in different plant samples; optimisation of measurement conditions for spectrophotometric and pH-stat methods
PublicationMyrosinase found in Brassicaceae plants, is the enzyme responsible for hydrolysis of glucosinolates. As a result a variety of biologically active metabolites are liberated, whose importance in crop protection and especially in cancer chemoprevention is rapidly gaining recognition. The growing practical application of glucosinolate degradation products requires that sensitive and reliable methods of myrosinase activity determination...
-
“Shadow” vs. “Phase 3D” method within endoscopic examinations of marine engines
PublicationA visual investigation of surfaces creating internal, working spaces of marine combustion engines by means of specialized view-finders so called endoscopes is at present almost a basic method of technical diag-nostics. The surface structure of constructional material is visible during investigations like through the magnifying glass (usually with a precisely determined magnification), which makes possible a detection, recognition...
-
The optimisation of analytical parameters for routine profiling of antioxidants in complex mixture by HPLC coupled post-column derivatisation
PublicationIntroduction: The wide application of natural and artificial antioxidants in food, cosmetic and pharmaceutical industry as well as the recognition of the importance of food antioxidants for supporting human health created demand for reliable and industrially applicable methods of determining antioxidative activity. This requirement can be fullfilled with the recently proposed HPLC-post-column derivatisation approach enabling the...
-
Information retrieval with semantic memory model
PublicationPsycholinguistic theories of semantic memory form the basis of understanding of natural language concepts. These theories are used here as an inspiration for implementing a computational model of semantic memory in the form of semantic network. Combining this network with a vector-based object-relation-feature value representation of concepts that includes also weights for confidence and support, allows for recognition of concepts...
-
Visual Features for Endoscopic Bleeding Detection
PublicationAims: To define a set of high-level visual features of endoscopic bleeding and evaluate their capabilities for potential use in automatic bleeding detection. Study Design: Experimental study. Place and Duration of Study: Department of Computer Architecture, Faculty of Electronics, Telecommunications and Informatics, Gdansk University of Technology, between March 2014 and May 2014. Methodology: The features have...
-
The Bridge to Knowledge – Open Access to Scientific Research Results on Multidisciplinary Open System Transferring Knowledge Platform
PublicationThe European policy of Open Access to scientific research is now one of the key issues discussed in public debates on the future development of scientific communication. The implementation of Open Access tools has significant impact on scientific and economic growth. On the one hand, Open Access accelerates disseminating new research findings and facilitates recognition of authors on a more global scale. On the other hand, Open...
-
Deep CNN based decision support system for detection and assessing the stage of diabetic retinopathy
PublicationThe diabetic retinopathy is a disease caused by long-standing diabetes. Lack of effective treatment can lead to vision impairment and even irreversible blindness. The disease can be diagnosed by examining digital color fundus photographs of retina. In this paper we propose deep learning approach to automated diabetic retinopathy screening. Deep convolutional neural networks (CNN) - the most popular kind of deep learning algorithms...
-
Genetic programming extension to APF-based monocular human body pose estimation
PublicationNew method of the human body pose estimation based on a single camera 2D observation is presented, aimed at smart surveillance related video analysis and action recognition. It employs 3D model of the human body, and genetic algorithm combined with annealed particle filter for searching the global optimum of model state, best matching the object's 2D observation. Additionally, new motion cost metric is employed, considering current...
-
Progressing Pollutant Elution from Snowpack and Evolution of its Physicochemical Properties During Melting Period— a Case Study From the Sudetes, Poland
PublicationMain aim of the work assumed recognition of physicochemical changes in snowpack occurring during the melting period. Properties of snow cover had been identified at two sites in Western Sudetes mountains (860 and 1228 m asl) in SW Poland since the end of January, and monitored until the disappearance of snow in late Spring. Snow pit measurements and sample collection at both sites were made followed by chemical analyses with the...
-
Determination of long-chain aldehydes using a novel quartz crystal microbalance sensor based on a biomimetic peptide
PublicationThere is an increasingly popular trend aimed at improvement of fundamental metrological parameters of sensors via implementation of materials mimicking biological olfactory systems. This study presents investigation on usefulness of the peptide mimicking HarmOBP7 region as a receptor element of the piezoelectric sensor for selective analysis of long-chain aldehydes. Identification of odorant binding proteins creates new possibilities...
-
A framework for Air Quality Management Zones - Useful GIS-based tool for urban planning: Case studies in Antwerp and Gdańsk
PublicationThere is a growing recognition of the importance of proper urban design in the improvement of air flow and pollution dispersion and in reducing human exposure to air pollution. However, a limited number of studies have been published so far focusing on the development of standard procedures which could be applied by urban planners to effectively evaluate urban conditions with respect to air quality. To fill this gap, a new approach...
-
Highly selective impedimetric determination of Haemophilus influenzae protein D using maze-like boron-doped carbon nanowall electrodes
PublicationThis study reports a novel impedimetric immunosensor for protein D detection in purified and bacterial (Haemophilus influenzae, Hi) samples. The detection was based on antigen recognition by anti-protein D antibodies (apD) immobilised at the maze-like boron-doped carbon nanowall electrodes (B:CNW). The B:CNW electrodes were synthesised, and their surface was characterised by scanning electron microscopy (SEM) and X-ray photoelectron...
-
Convolutional Neural Networks for C. Elegans Muscle Age Classification Using Only Self-Learned Features
PublicationNematodes Caenorhabditis elegans (C. elegans) have been used as model organisms in a wide variety of biological studies, especially those intended to obtain a better understanding of aging and age-associated diseases. This paper focuses on automating the analysis of C. elegans imagery to classify the muscle age of nematodes based on the known and well established IICBU dataset. Unlike many modern classification methods, the proposed...
-
Interdisciplinary research as a form of monument protection and preparation for the investment process on the example of the former Gdańsk Shipyard complex
PublicationThe multi-layered heritage of many industrial plants operating until the end of the 20th century creates a particular challenge for conservators, designers and investors. In the process of protecting its values, displaying qualities and managing the property, it is necessary to recognize a wider transformation of technology of the entire plant and the individual functions of its buildings, as well as the context of intangible...
-
Chemical hazard in glacial melt? The glacial system as a secondary source of POPs (in the Northern Hemisphere). A systematic review
PublicationToxicity of compounds belonging to persistent organic pollutants (POPs) iswidely known, and their re-emission from glaciers has been conclusively demonstrated. However, the harmful effects associated with such secondary emissions have yet to be thoroughly understood, especially in the spatial and temporal context, as the existing literature has a clear sampling biaswith the best recognition of sites in the European Alps. In this...
-
Using Convolutional Neural Networks for Corneal Arcus Detection Towards Familial Hypercholesterolemia Screening
PublicationFamilial hypercholesterolemia (FH) is a highly undiagnosed disease. Among FH patients, the onset of premature coronary artery disease is 13 times higher than in the general population. Early diagnosis and treatment is essential to prevent cardiovascular diseases and their complications, and to prolong life. One of the clinical criteria of FH is the occurrence of a corneal arcus (CA) among patients, especially those under 45 years...
-
Potentiometric sensor containing set of ion selective electrodes with lipid modified membranes for quality assessment of tested non-alcoholic beverages
PublicationPotentiometric sensors may be a good tool for fast quality control of commercial drinks. In this work, such a sensor, containing a set of ion-selective electrodes with lipid-modified membranes (benzylhexadecyldimethylammonium chloride monohydrate, hexadecylamine, 1-dodecanol, elaidic acid, cholesterol) was used for discrimination and quality control of non-alcoholic beverages, mainly composed of sugar and citric acid. It was found...