Search
Filters
total: 4225
filtered: 2888
-
Catalog
- Publications 2888 available results
- Journals 256 available results
- Conferences 35 available results
- Publishing Houses 1 available results
- People 85 available results
- Projects 6 available results
- Laboratories 1 available results
- e-Learning Courses 47 available results
- Events 7 available results
- Open Research Data 899 available results
Chosen catalog filters
displaying 1000 best results Help
Search results for: NEURAL NETS
-
Evaluation of pollutant loading in the runoff waters from a major urban highway (Gdansk Beltway, Poland)
PublicationW artykule opisano wyniki badań dotyczących zawartości wybranych kationów i anionów w próbkach opadu otwartego, wód spływnych z ulic, wód spływnych z koron drzew oraz wody powierzchniowej, pobranych na terenie bedącym w zasiegu oddziaływania drogi szybkiego ruchu (Obwodnicy Trójmiejskiej). Wyniki zostały poddane analizie statystycznej. Zbadano m.in. korelacje pomiedzy zawartościami wybranych analitów w badanych próbkach wód a natężeniem...
-
Stable indirect adaptive control based on discrete-time T-S fuzzy model
PublicationThis paper presents an indirect adaptive fuzzy control scheme for uncertain nonlinear asymptotically stable plants.A discrete-time T-S fuzzy input-output model is employed to approximate the unknown plant dynamics. The T-S fuzzy model is fed with its own states, which are indeed its past outputs, rather than the measurements from the plants. Entirely based on this model, a feedback linearization control law is designed by using...
-
World's tower namely, how to build a 1200 metre tall house
Publication..
-
Analysis of the Application of Horizontal Directional Drilling
PublicationConstruction works are often considered to be very intrusive for the environment. Project designers assume deep excavations, or a complete replacement of the ground within the investment, which sometimes changes the initial conditions drastically. The problem started to appear in places, where the terrain is complicated and the excavation is burdensome. Some of state authorities...
-
Denitrifcation rate in the mainstream deammonification
PublicationThe conventional processes of biological nitrogen removal based on nitrification and denitrification does not fit properly into the concept of the circular economy. As the alternative one should consider the deammonification process, which is a combination of partial nitrification (nitritation) and Anammox processes. It consists of removing ammonium nitrogen from wastewater under anaerobic conditions by a group of autotrophic microorganisms....
-
Instrumental techniques used in the analysis of exhaled air
PublicationExhaled air composition changes depending on the health status of the patient, making it possible to use breath analysis for diagnosis and monitoring purposes. Despite the fact that it is not yet used in every day medical practice, it potential application could facilitate the diagnostics of various diseases such as metabolic disorders, respiratory tract and gastrointestinal diseases. Described in this paper are different application...
-
Two-dimensional gas chromatography – principles and application in fruits analysis
PublicationTwo-dimensional gas chromatography is a rapidly developing analytical technique. One of the major uses of this technique is its use for food analysis. The paper presents the principle of operation and history of this analytical technique. The specification of the two-dimensional gas chromatography technique has been discussed. The principles of separation of ingredients and application of the method, particularly in the analysis...
-
Application of gas chromatography to evaluate the quality of rapeseed oil
PublicationTwo-dimensional gas chromatography is an analytical technique, which is increasingly being used in food research. Through the analysis of volatile fraction, it is possible to determine the quality of food products. One of the reasons for the deterioration of food is thermal degradation. Products that are often subject to degradation reactions due to temperatures are edible oils. In the thesis, the results of edible oils with different...
-
KTaO3 a perovskite for water and air treatment
PublicationPerovskites are inorganic compounds that exhibit dielectric properties. These minerals belong to the crystal ceramics family. These compounds are described by the formula: ABX3 where, A and B are 2, 3 or 4 valuable metal ions, and X is an ion of oxygen or fluorine. An example of perovskite is the compound KTaO3. There are many methods for producing KTaO3, but the hydrothermal method is most commonly used. Perovskites can be characterized...
-
Protonic Ceramic Fuel Cells as novel electrochemical devices
PublicationProton ceramic conductors are novel materials which are interesting from the application point of view. For example, Protonic Ceramic Fuel Cells (PCFCs) is a type of a solid oxide fuel cell, which uses proton ceramic conductors as an electrolyte. Scientists are looking for the most efficient materials for these devices. In recent years main focus has been put on the search for new proton and mixed proton-electron conductors which...
-
Overall color parameter as a parameter determining the level of oxidation of olive oil
PublicationEdible fats are an important part of a human daily diet. They have a significant effect on the proper functioning of the human body. During frying, the oil is chemically modified and the fats consumed should have the highest oxidation stability. The subject of the study were samples of olive oil bought at local markets in Gdansk. Samples were heated at 20 °C, 60 °C, 100 °C, 140 °C and 180 °C. The aim of the study was to determine...
-
Analysis of volatile fraction selected hybrid fruits using chromatographic techniques
PublicationAt present, "healthy eating" is gaining in popularity. Many people associate this term with eating plenty of vegetables and fruits. The basic elements influencing the selection of fruit are their appearance and smell. Of course, their origin and impact on human health are also very important. In recent years, exotic fruits have become increasingly accessible, making them gaining popularity, even among Poles. You can also meet plants...
-
Fast GC as a useful tool for authenticity assessment of kiwifruit
PublicationKiwifruit is one of the healthiest fruits due to its high content of biologically active substances and nutrients. The most popular species of Actinidia (kiwifruit) are the Actinidia deliciosa fruits called kiwi and Actinidia chinensis commonly called golden kiwi, while the lesser known species is Actinidia arguta known as mini kiwi. Bioactivities and nutrients of Actinidia are influenced by species and cultivars. It is very important...
-
Integrating environmental issues with the practice of urban planning
PublicationEnvironmental protection of urban areas has become a common concern among academics, policy makers and urban planners. Therefore, environmental issues are often underlined and incorporated into many strategies for urban development. In the article a discussion about the development of the concept of sustainable development in the context of urban planning and international policies is presented, followed by a review of planning...
-
The application of environmental issues in designing urban structures – a framework for comprehensive local planning policies
PublicationThe implementation of environmental issues in planning and designing urban structures is becoming a novel approach and a common practice consistent with the paradigm of sustainable development. Maintaining environmental quality in urban areas, managing natural resources and understanding the complexity of urban systems is becoming increasingly challenging. Therefore, it is important to develop strategies for the integration of...
-
Determination of metal content in sewage sludge and sewage sludge ash to find opportunities to use them in the construction industry
PublicationSewage sludge management is becoming an increasing problem in developed and developing countries. Due to their physicochemical properties (mainly high content of heavy metals) a safe method of utilization is sought. Considering environmental protection, energy recycling, reduction in use of the raw materials and the possibility of immobilization hazardous substances, the use of ashes in building materials becomes a very good way...
-
Urine headspace analysis in medical diagnostics
PublicationThe analysis of the volatile organic compounds in the bodily fluids such as urine may provide useful information on the patients’ general health. The potential application of urine headspace analysis could facilitate the diagnostics of various diseases such as metabolic disorders, urinary tract diseases and gastrointestinal conditions. Described in this paper are the currently available techniques of urine sample analysis as well...
-
Open-Set Speaker Identification Using Closed-Set Pretrained Embeddings
PublicationThe paper proposes an approach for extending deep neural networks-based solutions to closed-set speaker identification toward the open-set problem. The idea is built on the characteristics of deep neural networks trained for the classification tasks, where there is a layer consisting of a set of deep features extracted from the analyzed inputs. By extracting this vector and performing anomaly detection against the set of known...
-
1D convolutional context-aware architectures for acoustic sensing and recognition of passing vehicle type
PublicationA network architecture that may be employed to sensing and recognition of a type of vehicle on the basis of audio recordings made in the proximity of a road is proposed in the paper. The analyzed road traffic consists of both passenger cars and heavier vehicles. Excerpts from recordings that do not contain vehicles passing sounds are also taken into account and marked as ones containing silence....
-
MACHINE LEARNING–BASED ANALYSIS OF ENGLISH LATERAL ALLOPHONES
PublicationAutomatic classification methods, such as artificial neural networks (ANNs), the k-nearest neighbor (kNN) and selforganizing maps (SOMs), are applied to allophone analysis based on recorded speech. A list of 650 words was created for that purpose, containing positionally and/or contextually conditioned allophones. For each word, a group of 16 native and non-native speakers were audio-video recorded, from which seven native speakers’...
-
DFT study of low-energy electron interaction with pyridine, pyrazine and their halo derivatives
PublicationIn this work, the density functional theory with B3LYP hybrid functional was employed to calculate quantities useful for estimating the behavior of pyridine, pyrazine and their derivatives monosubstituted with Cl or Br atom, when exposed to low-energy electron impact. Vertical electron affinities obtained in several Pople basis sets and in aug-cc-pVTZ basis set are reported. Although some of the investigated molecules do not form...
-
Znajomość własnego ciśnienia tętniczego i rozpowszechnienie nadciśnienia tętniczego w populacji wiejskiej - Program Kiełpino = The cognizance of patient's own blood pressure values and the hypertension prevalence among rural population - Kiełpino program
PublicationNadciśnienie tętnicze jest jedną z najczęstszych chorób przewlekłych występujących w Polsce. Nieleczone nadciśnienie tętnicze prowadzi do licznych powikłań, jest przyczyna przedwczesnej umieralności, wpływa na pogorszenie komfortu życia pacjenta i zwiększa koszty leczenia. Ocena znajomości własnego ciśnienia tętniczego krwi oraz rozpowszechnienia nadciśnienia tętniczego u pacjentów w wiejskiej praktyce lekarza rodzinnego - jest...
-
Does the carbon emissions trading system reduce carbon emissions by promoting two-way FDI in developing countries? Evidence from Chinese listed companies and cities
PublicationHow developing countries can effectively promote cities’ carbon emission reduction through the carbon emission trading system (ETS) is a topic worthy of attention in the global carbon reduction campaign. Policy changes in China's ETS provide a unique opportunity to measure whether ETS impacts carbon emissions through two-way FDI. Hence, this paper employs difference-in-differences (DID) method to test the causal impact of ETS...
-
Structural optimization of microjet array cooling system
PublicationThe single phase heat transfer from an upward facing, horizontal copper surface to arrays of impinging water jets was experimentally investigated. Experimental configuration allows for a free-surface unconfined jets flow. Square nozzles 50 × 100 μm arranged in four different geometries were used. Additionally, for the set of two jets array geometry was varied by adjusting the nozzle to nozzle distance. The area averaged heat transfer...
-
Gradient versus proper gradient homotopies
PublicationWe compare the sets of homotopy classes of gradient and proper gradient vector fields in the plane. Namely, we show that gradient and proper gradient homotopy classi cations are essentially different. We provide a complete description of the sets of homotopy classes of gradient maps from R^n to R^n and proper gradient maps from R^2 to R^2 with the Brouwer degree greater or equal to zero.
-
Detecting Lombard Speech Using Deep Learning Approach
PublicationRobust Lombard speech-in-noise detecting is challenging. This study proposes a strategy to detect Lombard speech using a machine learning approach for applications such as public address systems that work in near real time. The paper starts with the background concerning the Lombard effect. Then, assumptions of the work performed for Lombard speech detection are outlined. The framework proposed combines convolutional neural networks...
-
Trypsin inhibitor, antioxidant and antimicrobial activities as well as chemical composition of potato sprouts originating from yellow- and colored-fleshed varieties
Publication -
Efficiency of Artificial Intelligence Methods for Hearing Loss Type Classification: an Evaluation
PublicationThe evaluation of hearing loss is primarily conducted by pure tone audiometry testing, which is often regarded as golden standard for assessing auditory function. If the presence of hearing loss is determined, it is possible to differentiate between three types of hearing loss: sensorineural, conductive, and mixed. This study presents a comprehensive comparison of a variety of AI classification models, performed on 4007 pure tone...
-
Classifying Emotions in Film Music - A Deep Learning Approach
PublicationThe paper presents an application for automatically classifying emotions in film music. A model of emotions is proposed, which is also associated with colors. The model created has nine emotional states, to which colors are assigned according to the color theory in film. Subjective tests are carried out to check the correctness of the assumptions behind the adopted emotion model. For that purpose, a statistical analysis of the...
-
General Provisioning Strategy for Local Specialized Cloud Computing Environments
PublicationThe well-known management strategies in cloud computing based on SLA requirements are considered. A deterministic parallel provisioning algorithm has been prepared and used to show its behavior for three different requirements: load balancing, consolidation, and fault tolerance. The impact of these strategies on the total execution time of different sets of services is analyzed for randomly chosen sets of data. This makes it possible...
-
Hotspot of human verbal memory encoding in the left anterior prefrontal cortex
PublicationBackground: Treating memory and cognitive deficits requires knowledge about anatomical sites and neural activities to be targeted with particular therapies. Emerging technologies for local brain stimulation offer attractive therapeutic options but need to be applied to target specific neural activities, at distinct times, and in specific brain regions that are critical for memory formation. Methods: The areas that are critical...
-
Data augmentation for improving deep learning in image classification problem
PublicationThese days deep learning is the fastest-growing field in the field of Machine Learning (ML) and Deep Neural Networks (DNN). Among many of DNN structures, the Convolutional Neural Networks (CNN) are currently the main tool used for the image analysis and classification purposes. Although great achievements and perspectives, deep neural networks and accompanying learning algorithms have some relevant challenges to tackle. In this...
-
The ILs-assisted electrochemical synthesis of TiO2 nanotubes: The effect of ionic liquids on morphology and photoactivity
PublicationFacile and environmentally benign one-step titanium anodization method for TiO2 nanotubes (NTs) formation in a presence of ionic liquids (ILs) was proposed. Influence of the IL structure and its content in ethylene glycol electrolyte on morphology, surface properties and photoactivity of the TiO2 NTs was investigated. Possible interactions between IL and TiO2 NTs as well as the mechanism of NTs formation during anodic oxidation...
-
Experimental tests of steel double-type balcony connections
PublicationThe paper presents analysis and results of experimental tests of full scale prefabricated balcony sets with dimensions (width × length × height): 2.0 m × 2.78 m × 0.186 m (in slope to 0.17 m). The sets consists of reinforced concrete slabs (balcony and ceiling) connected with each other by double-type balcony connections. The paper analyses the impact of variable parameters on the load carry capacity of elements. Additionally...
-
Towards Knowledge Sharing Oriented Adaptive Control
PublicationIn this paper, we propose a knowledge sharing oriented approach to enable a robot to reuse other robots' knowledge by adapting itself to the inverse dynamics model of the knowledge-sharing robot. The purpose of this work is to remove the heavy fine-tuning procedure required before using a new robot for a task via reusing other robots' knowledge. We use the Neural Knowledge DNA (NK-DNA) to help robots gain empirical knowledge and...
-
Machine Learning Applied to Aspirated and Non-Aspirated Allophone Classification—An Approach Based on Audio "Fingerprinting"
PublicationThe purpose of this study is to involve both Convolutional Neural Networks and a typical learning algorithm in the allophone classification process. A list of words including aspirated and non-aspirated allophones pronounced by native and non-native English speakers is recorded and then edited and analyzed. Allophones extracted from English speakers’ recordings are presented in the form of two-dimensional spectrogram images and...
-
Extending touch-less interaction with smart glasses by implementing EMG module
PublicationIn this paper we propose to use temporal muscle contraction to perform certain actions. Method: The set of muscle contractions corresponding to one of three actions including “single-click”, “double-click” “click-n-hold” and “non-action” were recorded. After recording certain amount of signals, the set of five parameters was calculated. These parameters served as an input matrix for the neural network. Two-layer feedforward neural...
-
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...
-
Biopolymer-based composites for tissue engineering applications: A basis for future opportunities
PublicationBiomimetic scaffolds supporting tissue regeneration are complex materials with multifunctional characteristics. The unique biocompatibility and biodegradability of biopolymers make them excellent candidates for tissue engineering and regenerative medicine. Biopolymers, which have a wide range of properties, can be obtained from different natural sources. Depending on the target tissue, biopolymers can be engineered to meet a series...
-
Employing Subjective Tests and Deep Learning for Discovering the Relationship between Personality Types and Preferred Music Genres
PublicationThe purpose of this research is two-fold: (a) to explore the relationship between the listeners’ personality trait, i.e., extraverts and introverts and their preferred music genres, and (b) to predict the personality trait of potential listeners on the basis of a musical excerpt by employing several classification algorithms. We assume that this may help match songs according to the listener’s personality in social music networks....
-
Optymalizacja treningu i wnioskowania sieci neuronowych
PublicationSieci neuronowe są jedną z najpopularniejszych i najszybciej rozwijających się dziedzin sztucznej inteligencji. Ich praktyczne wykorzystanie umożliwiło szersze użycie komputerów w wielu obszarach komunikacji, przemysłu i transportu. Dowody tego są widoczne w elektronice użytkowej, medycynie, a nawet w zastosowaniach militarnych. Wykorzystanie sztucznej inteligencji w wielu przypadkach wymaga jednak znacznej mocy obliczeniowej,...
-
Organic pollutants photodegradation increment with use of TiO2 nanotubes decorated with transition metals after pulsed laser treatment
PublicationAmong various titanium(IV) oxide (TiO2, titania) structures, 1D nanotubes (TiO2 NTs) produced during the two-electrode anodization process, are extensively utilized in sensors or supercapacitors as well as in photo(electro)catalytic water splitting. However, due to wide bandgap and fast electron-hole recombination additional modifications, mostly concerned on materials surface, are required. According to the recent research, TiO2...
-
Analysis of 2D Feature Spaces for Deep Learning-based Speech Recognition
Publicationconvolutional neural network (CNN) which is a class of deep, feed-forward artificial neural network. We decided to analyze audio signal feature maps, namely spectrograms, linear and Mel-scale cepstrograms, and chromagrams. The choice was made upon the fact that CNN performs well in 2D data-oriented processing contexts. Feature maps were employed in the Lithuanian word recognition task. The spectral analysis led to the highest word...
-
MRI assessment of ectopic fat accumulation in pancreas, liver and skeletal muscle in patients with obesity, overweight and normal BMI in correlation with the presence of central obesity and metabolic syndrome
PublicationPurpose: Obesity, defined as a body mass index (BMI) exceeding 30 kg/m2, is a serious health problem, which can be called an epidemic on a global scale and is one of the most important causes of preventable death. The aim of this study was to assess ectopic fat accumulation in pancreas, liver and skeletal muscle in patients with obesity, overweight and normal BMI in correlation with metabolic syndrome (MetS). Patients and methods:...
-
Hybrid System for Ship-Aided Design Automation
PublicationA hybrid support system for ship design based on the methodology of CBR with some artificial intelligence tools such as expert system Exsys Developer along with fuzzy logic, relational Access database and artificial neural network with backward propagation of errors.
-
Knowledge representation of motor activity of patients with Parkinson’s disease
PublicationAn approach to the knowledge representation extraction from biomedical signals analysis concerning motor activity of Parkinson disease patients is proposed in this paper. This is done utilizing accelerometers attached to their body as well as exploiting video image of their hand movements. Experiments are carried out employing artificial neural networks and support vector machine to the recognition of characteristic motor activity...
-
Affine continuous cellular automata solving the fixed-length density classification problem
Publication -
Fuzzy regresion approach to road safety analysis at regional level
PublicationRoad safety modelling on regional level of NUTS 2 in the EU is the complex issue and authors of this article indicate this in previous publications. NUTS 2 are basic regions for the application of regional policies (0.8-3 m inhabitants). During multivariate models development they discovered that it is difficult to make regression model well described all regions, even if they are from one country. In the first step Poisson model...
-
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,...
-
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,...