Filtry
wszystkich: 1157
-
Katalog
wyświetlamy 1000 najlepszych wyników Pomoc
Wyniki wyszukiwania dla: NEURONAL OSCILLATIONS
-
Jednofazowy falownik napięcia z aktywnym obwodem odsprzęgającym
PublikacjaZnanym zagadnieniem w jednofazowych falownikach napięcia jest pobieranie ze źródła napięcia stałego składowej przemiennej o częstotliwości dwukrotnie większej od częstotliwości generowanej przez falownik. Jednym z rozwiązań problemu jest stosowanie dużej baterii kondensatorów elektrolitycznych, lecz lepszym sposobem z punktu widzenia niezawodności i gęstości mocy przekształtnika jest stosowanie aktywnych układów odsprzęgania mocy....
-
Wpływ sposobu odwzorowania pojazdu szynowego na odpowiedź dynamiczną przęsła mostowego
PublikacjaW pracy przedstawiono rezultaty analiz numerycznych oraz badań eksploatacyjnych dwóch przęseł mostowych wymuszonych ruchomym pojazdem szynowym. Pojazd odwzorowano za pomocą czterech modeli uproszczonych: strumienia sił skupionych, strumienia mas skupionych oraz strumieni oscylatorów jedno- i dwumasowych. Analizy numeryczne wykonano przy wykorzystaniu MES. Potrzebne parametry dynamiczne wyznaczono na podstawie wyników identyfikacji...
-
Machine Learning Applied to Aspirated and Non-Aspirated Allophone Classification—An Approach Based on Audio "Fingerprinting"
PublikacjaThe 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...
-
Towards Knowledge Sharing Oriented Adaptive Control
PublikacjaIn 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...
-
Minimizing Distribution and Data Loading Overheads in Parallel Training of DNN Acoustic Models with Frequent Parameter Averaging
PublikacjaIn 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...
-
Analysis of 2D Feature Spaces for Deep Learning-based Speech Recognition
Publikacjaconvolutional 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...
-
A high-accuracy complex-phase method of simulating X-ray propagation through a multi-lens system
PublikacjaThe propagation of X-ray waves through an optical system consisting of many X-ray refractive lenses is considered. For solving the problem for an electromagnetic wave, a finite-difference method is applied. The error of simulation is analytically estimated and investigated. It was found that a very detailed difference grid is required for reliable and accurate calculations of the propagation of X-ray waves through a multi-lens...
-
Starter for Voltage Boost Converter to Harvest Thermoelectric Energy for Body-Worn Sensors
PublikacjaThis paper examines the suitability of selected configurations of ultra-low voltage (ULV) oscilla-tors as starters for a voltage boost converter to harvest energy from a thermoelectric generator (TEG). Important properties of particularly promising configurations, suitable for on-chip imple-mentation are compared. On this basis, an improved oscillator with a low startup voltage and a high output voltage swing is proposed. The applicability...
-
Optymalizacja treningu i wnioskowania sieci neuronowych
PublikacjaSieci 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,...
-
Hybrid System for Ship-Aided Design Automation
PublikacjaA 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.
-
Zdzisław Kowalczuk prof. dr hab. inż.
OsobyW 1978 ukończył studia w zakresie automatyki i informatyki na Wydziale Elektroniki Politechniki Gdańskiej, następnie rozpoczął pracę na macierzystej uczelni. W 1986 obronił pracę doktorską, w 1993 habilitował się na Politechnice Śląskiej na podstawie pracy Dyskretne modele w projektowaniu układów sterowania. W 1996 mianowany profesorem nadzwyczajnym, w 2003 otrzymał tytuł profesora nauk technicznych. W 2006 założył i od tego czasu...
-
Deep Learning: A Case Study for Image Recognition Using Transfer Learning
PublikacjaDeep 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
PublikacjaDeep 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,...
-
Breast MRI segmentation by deep learning: key gaps and challenges
PublikacjaBreast MRI segmentation plays a vital role in early diagnosis and treatment planning of breast anomalies. Convolutional neural networks with deep learning have indicated promise in automating this process, but significant gaps and challenges remain to address. This PubMed-based review provides a comprehensive literature overview of the latest deep learning models used for breast segmentation. The article categorizes the literature...
-
Assessment of Failure Occurrence Rate for Concrete Machine Foundations Used in Gas and Oil Industry by Machine Learning
PublikacjaConcrete machine foundations are structures that transfer loads from machines in operation to the ground. The design of such foundations requires a careful analysis of the static and dynamic effects caused by machine exploitation. There are also other substantial differences between ordinary concrete foundations and machine foundations, of which the main one is that machine foundations are separated from the building structure....
-
WARUNKI REZONANSOWE W WĘŹLE Z KOMPENSATOREM SVC
PublikacjaInstalowanie kompensatorów statycznych w sieciach rozdzielczych i przesyłowych służy poprawie profili napięciowych. Kompensatory jako źródła mocy biernej zwiększają stabilność napięciową systemu. Pozwalają także na szybszą odbudowę systemu w przypadku awarii napięciowej. W artykule zaprezentowano wpływ struktury i wysterowania układu SVC na zmianę impedancji w układzie zasilania. Ma to bezpośredni wpływ na częstotliwości, przy...
-
Badania eksperymentalne i symulacyjne dynamiki modelowego odcinka sieci trakcyjnej
PublikacjaW pracy przedstawiono główne założenia i strukturę opracowanego modelu matematycznego odcinka kolejowej górnej sieci trakcyjnej, opartego na metodzie energetycznej Lagrange’a. W celu wyznaczenia wybranych parametrów modelu, jak również dla oceny stopnia zgodności odwzorowania przez utworzony program symulacyjny stanów statycznych i dynamicznych sieci zbudowano laboratoryjny model odcinka sieci jezdnej z użyciem rzeczywistych jej...
-
Importance of sign conventions on analytical solutions to the wave-induced cyclic response of a poro-elastic seabed
PublikacjaThis paper discusses the influence of different sign conventions for strains and stresses, i.e. the solid mechanics sign convention and the soil mechanics sign convention, on the form of governing partial differential equations (the static equilibrium equations and the continuity equation) used to describe the wave-induced cyclic response of a poro-elastic seabed due to propagation of a sinusoidal surface water-wave. Some selected...
-
Efficient Calibration of Cost-Efficient Particulate Matter Sensors Using Machine Learning and Time-Series Alignment
PublikacjaAtmospheric particulate matter (PM) poses a significant threat to human health, infiltrating the lungs and brain and leading to severe issues such as heart and lung diseases, cancer, and premature death. The main sources of PM pollution are vehicular and industrial emissions, construction and agricultural activities, and natural phenomena such as wildfires. Research underscores the absence of a safe threshold for particulate exposure,...
-
Deep Learning Optimization for Edge Devices: Analysis of Training Quantization Parameters
PublikacjaThis paper focuses on convolution neural network quantization problem. The quantization has a distinct stage of data conversion from floating-point into integer-point numbers. In general, the process of quantization is associated with the reduction of the matrix dimension via limited precision of the numbers. However, the training and inference stages of deep learning neural network are limited by the space of the memory and a...
-
Direct electrical brain stimulation of human memory: lessons learnt and future perspectives
PublikacjaModulation of cognitive functions supporting human declarative memory is one of the grand challenges of neuroscience, and of vast importance for a variety of neuropsychiatric, neurodegenerative and neurodevelopmental diseases. Despite a recent surge of successful attempts at improving performance in a range of memory tasks, the optimal approaches and parameters for memory enhancement have yet to be determined. On a more fundamental...
-
Interrelationship between total volatile organic compounds emissions, structure and properties of natural rubber/polycaprolactone bio-blends cross-linked with peroxides
PublikacjaNatural rubber/polycaprolactone (NR/PCL) bio-based blends with different organic peroxides were prepared using an internal batch mixer and subsequently cross-linked at 170°C. Two types of commonly used organic peroxides, dicumyl peroxide and di(tert-butylperoxyisopropyl)benzene peroxide, were applied as free-radical initiator. Cross-linking efficiency of NR/PCL blends were investigated using oscillating disc rheometer measurements,...
-
Processing, physico-mechanical and thermal properties of reclaimed GTR and NBR/reclaimed GTR blends as function of various additives
PublikacjaIn this work, ground tire rubber (GTR) was mechano-chemically reclaimed in the presence of bitumen and various additives. During studies three types of processing and curing additives: (i) peptizer P300; (ii) vulcanization accelerator tetramethylthiuram disulfide (TMTD) and (iii) organic peroxide di(2-tert-butyl-peroxyisopropyl)benzene (BIB1) were applied to enhance reclaiming of GTR. Reclaiming process was evaluated by oscillating...
-
Language Models in Speech Recognition
PublikacjaThis chapter describes language models used in speech recognition, It starts by indicating the role and the place of language models in speech recognition. Mesures used to compare language models follow. An overview of n-gram, syntactic, semantic, and neural models is given. It is accompanied by a list of popular software.
-
Problems of modelling toxic compounds emitted by a marine internal combustion engine in unsteady states
PublikacjaContemporary engine tests are performed based on the theory of experiment. The available versions of programmes used for analysing experimental data make frequent use of the multiple regression model, which enables examining effects and interactions between input model parameters and a single output variable. The use of multi-equation models provides more freedom in analysing the measured results, as those models enable simultaneous...
-
Detection of Lexical Stress Errors in Non-Native (L2) English with Data Augmentation and Attention
PublikacjaThis paper describes two novel complementary techniques that improve the detection of lexical stress errors in non-native (L2) English speech: attention-based feature extraction and data augmentation based on Neural Text-To-Speech (TTS). In a classical approach, audio features are usually extracted from fixed regions of speech such as the syllable nucleus. We propose an attention-based deep learning model that automatically de...
-
Simulating Power Generation from Photovoltaics in the Polish Power System Based on Ground Meteorological Measurements—First Tests Based on Transmission System Operator Data
PublikacjaThe Polish power system is undergoing a slow process of transformation from coal to one that is renewables dominated. Although coal will remain a fundamental fuel in the coming years, the recent upsurge in installed capacity of photovoltaic (PV) systems should draw significant attention. Owning to the fact that the Polish Transmission System Operator recently published the PV hourly generation time series in this article, we aim...
-
Poprawa jakości klasyfikacji głębokich sieci neuronowych poprzez optymalizację ich struktury i dwuetapowy proces uczenia
PublikacjaW pracy doktorskiej podjęto problem realizacji algorytmów głębokiego uczenia w warunkach deficytu danych uczących. Głównym celem było opracowanie podejścia optymalizującego strukturę sieci neuronowej oraz zastosowanie uczeniu dwuetapowym, w celu uzyskania mniejszych struktur, zachowując przy tym dokładności. Proponowane rozwiązania poddano testom na zadaniu klasyfikacji znamion skórnych na znamiona złośliwe i łagodne. W pierwszym...
-
WYKORZYSTANIE SIECI NEURONOWYCH DO SYNTEZY MOWY WYRAŻAJĄCEJ EMOCJE
PublikacjaW niniejszym artykule przedstawiono analizę rozwiązań do rozpoznawania emocji opartych na mowie i możliwości ich wykorzystania w syntezie mowy z emocjami, wykorzystując do tego celu sieci neuronowe. Przedstawiono aktualne rozwiązania dotyczące rozpoznawania emocji w mowie i metod syntezy mowy za pomocą sieci neuronowych. Obecnie obserwuje się znaczny wzrost zainteresowania i wykorzystania uczenia głębokiego w aplikacjach związanych...
-
Spatiotemporal Assessment of Satellite Image Time Series for Land Cover Classification Using Deep Learning Techniques: A Case Study of Reunion Island, France
PublikacjaCurrent Earth observation systems generate massive amounts of satellite image time series to keep track of geographical areas over time to monitor and identify environmental and climate change. Efficiently analyzing such data remains an unresolved issue in remote sensing. In classifying land cover, utilizing SITS rather than one image might benefit differentiating across classes because of their varied temporal patterns. The aim...
-
Methods of Artificial Intelligence for Prediction and Prevention Crisis Situations in Banking Systems
PublikacjaIn this paper, a support vector machine has been studied due to prediction of bank crisis. To prevent outcomes of crisis situations, artificial neural networks have been characterized as applied to stock market investments, as well as to test the credibility of the bank's customers. Finally, some numerical experiments have been presented.
-
THE ROLE OF INFERENCE IN MOBILE MEDICAL APPLICATION DESIGN
PublikacjaIn the early 21st century, artificial intelligence began to be used to process medical information. However, before this happened, predictive models used in healthcare could only consider a limited number of variables, and only in properly structured and organised medical data. Today, advanced tools based on machine learning techniques - which, using artificial neural networks, can explore extremely complex relationships - and...
-
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...
-
User Orientation Detection in Relation to Antenna Geometry in Ultra-Wideband Wireless Body Area Networks Using Deep Learning
PublikacjaIn this paper, the issue of detecting a user’s position in relation to the antenna geometry in ultra-wideband (UWB) off-body wireless body area network (WBAN) communication using deep learning methods is presented. To measure the impulse response of the channel, a measurement stand consisting of EVB1000 devices and DW1000 radio modules was developed and indoor static measurement scenarios were performed. It was proven that for...
-
Swapping Space for Time: An Alternative to Time-Domain Interferometry
PublikacjaYoung's double-slit experiment [1] requires two waves produced simultaneously at two different points in space. In quantum mechanics the waves correspond to a single quantum object, even as complex as a big molecule. An interference is present as long as one cannot tell for sure which slit is chosen by the object. The more we know about the path, the worse the interference. In the paper we show that quantum mechanics allows for...
-
Preparation and characterization of natural rubber composites highly filled with brewers' spent grain/ground tire rubber hybrid reinforcement
PublikacjaBrewers' spent grain (BSG) and ground tire rubber (GTR) were applied as low-cost hybrid reinforcement natural rubber (NR). The impact of BSG/GTR ratio (in range: 100/0, 75/25, 50/50, 25/75 and 0/100 phr) on processing and performance properties of highly filled natural rubber composites was evaluated by oscillating disc rheometer, Fourier-transform infrared spectroscopy, thermogravimetric analysis, scanning electron microscopy,...
-
Tagged images with LEGO bricks - Bricks Sloped
Dane BadawczeThe set contains images of LEGO bricks (from Bricks Sloped category). The images were prepared for training neural network for recognition and labeling of LEGO bricks. The images contain one brick each. The images were taken from different sides by handheld camera hovering over the bricks lying on a white, non reflective surface.
-
Tagged images with LEGO bricks - Tiles
Dane BadawczeThe set contains images of LEGO bricks (from Tiles category). The images were prepared for training neural network for recognition and labeling of LEGO bricks. The images contain one brick each. The images were taken from different sides by handheld camera hovering over the bricks lying on a white, non reflective surface.
-
Tagged images with LEGO bricks - Windscreens and Fuselage
Dane BadawczeThe set contains images of LEGO bricks (from Windscreens and Fuselage category). The images were prepared for training neural network for recognition and labeling of LEGO bricks. The images contain one brick each. The images were taken from different sides by handheld camera hovering over the bricks lying on a white, non reflective surface.
-
Tagged images with LEGO bricks - Bricks Special
Dane BadawczeThe set contains images of LEGO bricks (from Bricks Special category). The images were prepared for training neural network for recognition and labeling of LEGO bricks. The images contain one brick each. The images were taken from different sides by handheld camera hovering over the bricks lying on a white, non reflective surface.
-
Tagged images with LEGO bricks - Bricks
Dane BadawczeThe set contains images of LEGO bricks (from Bricks category). The images were prepared for training neural network for recognition and labeling of LEGO bricks. The images contain one brick each. The images were taken from different sides by handheld camera hovering over the bricks lying on a white, non reflective surface.
-
Tagged images with LEGO bricks - Technic Beams
Dane BadawczeThe set contains images of LEGO bricks (from Technic Beams category). The images were prepared for training neural network for recognition and labeling of LEGO bricks. The images contain one brick each. The images were taken from different sides by handheld camera hovering over the bricks lying on a white, non reflective surface.
-
Tagged images with LEGO bricks - Technic Pins
Dane BadawczeThe set contains images of LEGO bricks (from Technic Pins category). The images were prepared for training neural network for recognition and labeling of LEGO bricks. The images contain one brick each. The images were taken from different sides by handheld camera hovering over the bricks lying on a white, non reflective surface.
-
Tagged images with LEGO bricks - Minifig Accessories
Dane BadawczeThe set contains images of LEGO bricks (from Minifig Accessories category). The images were prepared for training neural network for recognition and labeling of LEGO bricks. The images contain one brick each. The images were taken from different sides by handheld camera hovering over the bricks lying on a white, non reflective surface.
-
Tagged images with LEGO bricks - Plates
Dane BadawczeThe set contains images of LEGO bricks (from Plates category). The images were prepared for training neural network for recognition and labeling of LEGO bricks. The images contain one brick each. The images were taken from different sides by handheld camera hovering over the bricks lying on a white, non reflective surface.
-
Tagged images with LEGO bricks - Technic Panels
Dane BadawczeThe set contains images of LEGO bricks (from Technic Panels category). The images were prepared for training neural network for recognition and labeling of LEGO bricks. The images contain one brick each. The images were taken from different sides by handheld camera hovering over the bricks lying on a white, non reflective surface.
-
Tagged images with LEGO bricks - Pneumatics
Dane BadawczeThe set contains images of LEGO bricks (from Pneumatics category). The images were prepared for training neural network for recognition and labeling of LEGO bricks. The images contain one brick each. The images were taken from different sides by handheld camera hovering over the bricks lying on a white, non reflective surface.
-
Tagged images with LEGO bricks - Technic Bricks
Dane BadawczeThe set contains images of LEGO bricks (from Technic Bricks category). The images were prepared for training neural network for recognition and labeling of LEGO bricks. The images contain one brick each. The images were taken from different sides by handheld camera hovering over the bricks lying on a white, non reflective surface.
-
Tagged images with LEGO bricks - Technic Gears
Dane BadawczeThe set contains images of LEGO bricks (from Technic Gears category). The images were prepared for training neural network for recognition and labeling of LEGO bricks. The images contain one brick each. The images were taken from different sides by handheld camera hovering over the bricks lying on a white, non reflective surface.
-
Tagged images with LEGO bricks - Panels
Dane BadawczeThe set contains images of LEGO bricks (from Panels category). The images were prepared for training neural network for recognition and labeling of LEGO bricks. The images contain one brick each. The images were taken from different sides by handheld camera hovering over the bricks lying on a white, non reflective surface.