Filters
total: 965
filtered: 769
-
Catalog
- Publications 769 available results
- Journals 4 available results
- People 43 available results
- Projects 3 available results
- Research Teams 1 available results
- Research Equipment 4 available results
- e-Learning Courses 15 available results
- Events 2 available results
- Open Research Data 124 available results
Chosen catalog filters
Search results for: KNN CLASSIFIER
-
Mine counter vehicles for Baltic navy. W: [CD-ROM] Conference proceedings. UDT EUROPE 2002. Undersea Defence Technology Conference and Exhibition. La Spezia, Italy, 18-20 June 2002. Classified Conference, La Spezia, Italy, 21 June 2002 [B.m.w.]**2002 [6 s. 3 rys.]. Pojazdy przeciwminowe dla marynarki dzialającej na Bałtyku.
PublicationW opracowaniu omówiono przeciwminowe systemy opracowane przez PolitechnikęGdańską dla potrzeb Marynarki Wojennej RP. Przedstawiono podstawowe wymaga-nia rozwiązań konstrukcyjnych i zasady użycia.
-
Modelowanie elektrowni wiatrowych. Elektrownie i sieci- zagadnienia wybrane: generacja rozproszona i odnawialne źródła energii,urządzenia i sieci nN - SN, problemy wybrane.
PublicationPrzedstawiono typy komercyjnych elektrowni wiatrowych oraz sposoby ich modelowania pod kątem analizy ich pracy w systemie elektroenergetycznym. Zaprezentowano model matematyczny elektrowni wiatrowej. przedstawiono wyniki symulacji stanów pracy wybranego typu elektrowni wiatrowej.
-
Detection of anomalies in bee colony using transitioning state and contrastive autoencoders
PublicationHoneybees plays vital role for the environmental sustainability and overall agricultural economy. Assisting bee colonies within their proper functioning brings the attention of researchers around the world. Electronics systems and machine learning algorithms are being developed for classifying specific undesirable bee behaviors in order to alert about upcoming substantial losses. However, classifiers could be impaired when used...
-
Verification of the Parameterization Methods in the Context of Automatic Recognition of Sounds Related to Danger
PublicationW artykule opisano aplikację, która automatycznie wykrywa zdarzenia dźwiękowe takie jak: rozbita szyba, wystrzał, wybuch i krzyk. Opisany system składa się z bloku parametryzacji i klasyfikatora. W artykule dokonano porównania parametrów dedykowanych dla tego zastosowania oraz standardowych deskryptorów MPEG-7. Porównano też dwa klasyfikatory: Jeden oparty o Percetron (sieci neuronowe) i drugi oparty o Maszynę wektorów wspierających....
-
The passive operating mode of the linear optical gesture sensor
PublicationThe study evaluates the influence of natural light conditions on the effectiveness of the linear optical gesture sensor, working in the presence of ambient light only (passive mode). The orientations of the device in reference to the light source were modified in order to verify the sensitivity of the sensor. A criterion for the differentiation between two states - "possible gesture" and "no gesture" - was proposed. Additionally,...
-
Automatic labeling of traffic sound recordings using autoencoder-derived features
PublicationAn approach to detection of events occurring in road traffic using autoencoders is presented. Extensions of existing algorithms of acoustic road events detection employing Mel Frequency Cepstral Coefficients combined with classifiers based on k nearest neighbors, Support Vector Machines, and random forests are used. In our research, the acoustic signal gathered from the microphone placed near the road is split into frames and converted...
-
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...
-
Application of autoencoder to traffic noise analysis
PublicationThe aim of an autoencoder neural network is to transform the input data into a lower-dimensional code and then to reconstruct the output from this code representation. Applications of autoencoders to classifying sound events in the road traffic have not been found in the literature. The presented research aims to determine whether such an unsupervised learning method may be used for deploying classification algorithms applied to...
-
Sperm segmentation and abnormalities detection during the ICSI procedure using machine learning algorithms
Publication(1) About 15-20% of couples struggle with the problem of infertility. 30 to 40% of these cases are caused by abnormalities in the structure and motility of sperm. Sometimes the only possibility for such people is to use the procedure of artificial insemination. CASA systems are used to increase the efficiency of this procedure by selecting the appropriate sperm cell. (2) This paper presents an approach to the sperm classification...
-
Evaluation of sound event detection, classification and localization in the presence of background noise for acoustic surveillance of hazardous situations
PublicationAn evaluation of the sound event detection, classification and localization of hazardous acoustic events in the presence of background noise of different types and changing intensities is presented. The methods for separating foreground events from the acoustic background are introduced. The classifier, based on a Support Vector Machine algorithm, is described. The set of features and samples used for the training of the classifier...
-
Investigation of Air Quality beside a Municipal Landfill: The Fate of Malodour Compounds as a Model VOC
PublicationThis paper presents the results of an investigation on ambient air odour quality in the vicinity of a municipal landfill. The investigations were carried out during the spring–winter and the spring seasons using two types of the electronic nose instrument. The field olfactometers were employed to determine the mean odour concentration, which was from 2.1 to 32.2 ou/m3 depending on the measurement site and season of the year. In...
-
Układy regulacji grupowej w węzłach wytwórczych. Elektrownie i sieci - zagadnienia wybrane: generacja rozproszona i odnawialne źródła energii, urządzenia i sieci nN - SN, problemy wybrane,
PublicationW węzłach wytwórczych i przesyłowych w celu zapewnienia prawidłowego procesu regulacji napięć i sterowania rozpływem mocy biernej w systemie należy dążyć do zastosowania układów regulacji grupowej napięcia i mocy biernej. Układy regulacji grupowej powinny swoim sterowaniem (nadrzędnym) obejmować wszystkie układy regulacji biorące udział w procesie regulacji U i Q w danym węźle. W referacie przedstawiono wymagania dla układów...
-
Applying artificial neural networks for modelling ship speed and fuel consumption
PublicationThis paper deals with modelling ship speed and fuel consumption using artificial neural network (ANN) techniques. These tools allowed us to develop ANN models that can be used for predicting both the fuel consumption and the travel time to the destination for commanded outputs (the ship driveline shaft speed and the propeller pitch) selected by the ship operator. In these cases, due to variable environmental conditions, making...
-
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 impact of the AC922 Architecture on Performance of Deep Neural Network Training
PublicationPractical deep learning applications require more and more computing power. New computing architectures emerge, specifically designed for the artificial intelligence applications, including the IBM Power System AC922. In this paper we confront an AC922 (8335-GTG) server equipped with 4 NVIDIA Volta V100 GPUs with selected deep neural network training applications, including four convolutional and one recurrent model. We report...
-
Detection, classification and localization of acoustic events in the presence of background noise for acoustic surveillance of hazardous situations
PublicationEvaluation of sound event detection, classification and localization of hazardous acoustic events in the presence of background noise of different types and changing intensities is presented. The methods for discerning between the events being in focus and the acoustic background are introduced. The classifier, based on a Support Vector Machine algorithm, is described. The set of features and samples used for the training of the...
-
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’...
-
Optimized Deep Learning Model for Flood Detection Using Satellite Images
PublicationThe increasing amount of rain produces a number of issues in Kerala, particularly in urban regions where the drainage system is frequently unable to handle a significant amount of water in such a short duration. Meanwhile, standard flood detection results are inaccurate for complex phenomena and cannot handle enormous quantities of data. In order to overcome those drawbacks and enhance the outcomes of conventional flood detection...
-
An Intelligent Approach to Short-Term Wind Power Prediction Using Deep Neural Networks
PublicationIn this paper, an intelligent approach to the Short-Term Wind Power Prediction (STWPP) problem is considered, with the use of various types of Deep Neural Networks (DNNs). The impact of the prediction time horizon length on accuracy, and the influence of temperature on prediction effectiveness have been analyzed. Three types of DNNs have been implemented and tested, including: CNN (Convolutional Neural Networks), GRU (Gated Recurrent...
-
Artificial Neural Networks in Microwave Components and Circuits Modeling
PublicationArtykuł dotyczy wykorzystania sztucznych sieci neuronowych (SNN) w projektowaniu i optymalizacji układów mikrofalowych.Zaprezentowano podstawowe zasady i założenia modelowania z użyciem SNN. Możliwości opisywanej metody opisano wykorzystując przykładowyprojekt anteny łatowej. Przedstawiono różne strategie modelowania układów, które wykorzystują możliwości opisywanej metody w połączeniu zwiedzą mikrofalową. Porównano również dokładność...
-
DEEP CONVOLUTIONAL NEURAL NETWORKS AS A DECISION SUPPORT TOOL IN MEDICAL PROBLEMS – MALIGNANT MELANOMA CASE STUDY
PublicationThe paper presents utilization of one of the latest tool from the group of Machine learning techniques, namely Deep Convolutional Neural Networks (CNN), in process of decision making in selected medical problems. After the survey of the most successful applications of CNN in solving medical problems, the paper focuses on the very difficult problem of automatic analyses of the skin lesions. The authors propose the CNN structure...
-
Strategie treningu neuronowego estymatora częstotliwości tonu krtaniowego z użyciem generatora syntetycznych samogłosek
PublicationW wielu zastosowaniach telekomunikacyjnych pojawia się problem przetwarzania lub analizy sygnału mowy, w ramach którego, często w obszarze podstawowych algorytmów, stosuje się estymator częstotliwości tonu krtaniowego. Estymator rozpatrywany w tej pracy bazuje na neuronowym klasyfikatorze podejmującym decyzje na podstawie częstotliwości oraz mocy chwilowej wyznaczanych w podpasmach analizowanego sygnału mowy. W pracy rozważamy...
-
Artificial intelligence support for disease detection in wireless capsule endoscopy images of human large bowel
PublicationIn the work the chosen algorithms of disease recognition in endoscopy images were described and compared for theirs efficiency. The algorithms were estimated with regard to utility for application in computer system's support for digestive system's diagnostics. Estimations were achieved in an advanced testing environment, which was built with use of the large collection of endoscopy movies received from Medical University in Gdańsk....
-
Lessons learned during SRAD hybrid motor development
PublicationStudent Researched and Developed (SRAD) hybrid rocket motor H-15 with total impulse of 15 $kNs$ was built. First version of the engine has average thrust of 3 $kN$, the second, improved one is prepared with an aim to have average thrust of 5 $kN$. Engine development was started from scratch and went through phases of: definition of design assumptions and constraints, numerical modelling to predict engine performance, CAD and CAM...
-
When Neural Networks Meet Decisional DNA: A Promising New Perspective for Knowledge Representation and Sharing
PublicationABSTRACT In this article, we introduce a novel concept combining neural network technology and Decisional DNA for knowledge representation and sharing. Instead of using traditional machine learning and knowledge discovery methods, this approach explores the way of knowledge extraction through deep learning processes based on a domain’s past decisional events captured by Decisional DNA. We compare our approach with kNN (k-nearest...
-
Audio Feature Analysis for Precise Vocalic Segments Classification in English
PublicationAn approach to identifying the most meaningful Mel-Frequency Cepstral Coefficients representing selected allophones and vocalic segments for their classification is presented in the paper. For this purpose, experiments were carried out using algorithms such as Principal Component Analysis, Feature Importance, and Recursive Parameter Elimination. The data used were recordings made within the ALOFON corpus containing audio signal...
-
Influence of stirrups in a concrete shell on strengthening reinforced concrete column
PublicationTwelve concrete columns, with a 150x150mm square section and three columns with a circular section (d=200mm), are tested to investigate the effect of strengthening by RC jacket. Based on a confined concrete model for axial static loading, an analytical methods, reported in the literature are proposed to predict the behavior of columns with RC jacket. The results support the conception that the effect of strengthening depends...
-
USING ARTIFICIAL NEURAL NETWORKS FOR PREDICTING SHIP FUEL CONSUMPTION
PublicationIn marine vessel operations, fuel costs are major operating costs which affect the overall profitability of the maritime transport industry. The effective enhancement of using ship fuel will increase ship operation efficiency. Since ship fuel consumption depends on different factors, such as weather, cruising condition, cargo load, and engine condition, it is difficult to assess the fuel consumption pattern for various types...
-
Segmentation-Based BI-RADS ensemble classification of breast tumours in ultrasound images
PublicationBackground: The development of computer-aided diagnosis systems in breast cancer imaging is exponential. Since 2016, 81 papers have described the automated segmentation of breast lesions in ultrasound images using arti- ficial intelligence. However, only two papers have dealt with complex BI-RADS classifications. Purpose: This study addresses the automatic classification of breast lesions into binary classes (benign vs. ma- lignant)...
-
The Development of a Combined Method to Quickly Assess Ship Speed and Fuel Consumption at Different Powertrain Load and Sea Conditions
PublicationDecision support systems (DSS) recently have been increasingly in use during ships operation. They require realistic input data regarding different aspects of navigation. To address the optimal weather routing of a ship, which is one of the most promising field of DSS application, it is necessary to accurately predict an actually attainable speed of a ship and corresponding fuel consumption at given loading conditions and predicted...
-
Monitoring of odour nuisance on the adjacent areas to the landfill using fast GC and sensory analysis
PublicationThe paper shows the results of investigation on classification of the atmospheric air samples collected in a vicinity of the landfill during August and September period have been presented. The studies was conducted by the use of Fast GC HERACLES II from AlphaMOS company and sensory analysis. About 86% of the atmospheric air samples ollected were classified correctly using PCA and LDA. Based on a classification of the atmospheric...
-
Stock Markets’ Reactions to the Announcement of the Hosts. An Event Study in the Analysis of Large Sporting Events in the Years 1976–2032
PublicationThis study attempts to estimate the impact of the announcements of hosts of large sporting events on domestic stock markets. The research problem is to establish a connection between the uniqueness of a sporting event and investors’ beliefs through stock price behavior. Using appropriate estimation windows, 13 different sporting events classified as large, including mega and major events, were tested. The obtained results show...
-
Artificial neural network prophecy of ion exchange process for Cu (II) eradication from acid mine drainage
PublicationThe removal of heavy metal ions from wastewater was found to be significant when the cation exchange procedure was used effectively. The model of the cation exchange process was built using an artificial neural network (ANN). The acid mine drainage waste’s Cu(II) ion was removed using Indion 730 cation exchange resin. Experimental data from 252 cycles were recorded. In a column study, 252 experimental observations validated the...
-
O wyszukiwaniu niepoprawnych pomiarów w systemach DCS obiektów energetycznych = On search for incorrect measurement results in distributed control systems (DCS) of power objects
PublicationPrzedyskutowano problem rozpoznawania degradacji mierników pomiarowych w systemach DCS dużych obiektów energetycznych, przy równoczesnym występowaniu degradacji eksploatacyjnej urządzeń składowych tych obiektów. Zastosowano sieć neuronową (SNN) o skokowych funkcjach przejścia. Zastosowana SNN wykazała wysoką jakość. Sprawdzono możliwości rozpoznawania obu typów degradacji występującej w zastosowaniu do tzw. degradacji dwukrotnych.
-
Mathematical modeling and prediction of pit to crack transition under cyclic thermal load using artificial neural network
PublicationThe formation of pitting is a major problem in most metals, which is caused by extremely localized corrosion that creates small holes in metal and subsequently, it changes into cracks under mechanical load, thermo-mechanical stress, and corrosion process factors. This research aims to study pit to crack transition phenomenon of steel boiler heat tubes under cyclic thermal load, and mathematical modeling...
-
Metoda i algorytmy sterowania procesami miksowania dźwięku za pomocą gestów w oparciu o analizę obrazu wizyjnego
PublicationGłównym celem rozprawy było opracowanie systemu miksowania dźwięku za pomocą gestów rąk wykonywanych w powietrzu oraz zbadanie możliwości oferowanych przez takie rozwiązanie w porównaniu ze współczesną metodą miksowania sygnałów fonicznych, wykorzystującą środowisko komputera. Opracowany system rozpoznaje zarówno dynamiczne jak i statyczne gesty rąk. Rozpoznawanie gestów dynamicznych zrealizowano w oparciu o metody logiki rozmytej...
-
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,...
-
Estimation of the Ultimate Strength of FRP Strips-to-Masonry Substrates Bond
PublicationFiber-Reinforced Polymers (FRP) were developed as a new method over the past decades due to their many beneficial mechanical properties, and they are commonly applied to strengthen masonry structures. In this paper, the Artificial Neural Network (ANN), K-fold Cross-Validation (KFCV) technique, Multivariate Adaptive Regression Spline (MARS) method, and M5 Model Tree (M5MT) method were utilized to predict the ultimate strength of...
-
Emotion Recognition from Physiological Channels Using Graph Neural Network
PublicationIn recent years, a number of new research papers have emerged on the application of neural networks in affective computing. One of the newest trends observed is the utilization of graph neural networks (GNNs) to recognize emotions. The study presented in the paper follows this trend. Within the work, GraphSleepNet (a GNN for classifying the stages of sleep) was adjusted for emotion recognition and validated for this purpose. The...
-
TOXIC GASES IDENTIFICATION USING SINGLE ELECTROCATALYTIC SENSOR RESPONSES AND ARTIFICIAL NEURAL NETWORK
PublicationThe need for precise detection of toxic gases drives development of new gas sensors structures and methods of processing the output signals from the sensors. In literature, artificial neural networks are considered as one of the most effective tool for the analysis of gas sensors or sensors arrays responses. In this paper a method of toxic gas components identification using a electrocatalytic gas sensor as a detector and an artificial...
-
Rough Set-Based Classification of EEG Signals Related to Real and Imagery Motion
PublicationA rough set-based approach to classification of EEG signals registered while subjects were performing real and imagery motions is presented in the paper. The appropriate subset of EEG channels is selected, the recordings are segmented, and features are extracted, based on time-frequency decomposition of the signal. Rough set classifier is trained in several scenarios, comparing accuracy of classification for real and imagery motion....
-
Wpływ wybranych zakłóceń w układzie prostownika trakcyjnego na elektroenergetyczną sieć zasilającą. Elektrownie i sieci - zagadnienia wybrane: generacja rozproszona i odnawialne źródła energii, urządzenia i sieci nN - SN, problemy wybrane.
PublicationW artykule przedstawiono wyniki symulacji komputerowych wybranych zakłóceń w układzie prostownika trakcyjnego wykonanych w programie PSPICE. Zaprezentowano przykładowe przebiegi napięć i prądów w stanach ustalonych i przejściowych w elektroenergetycznej sieci zasilającej. Przeanalizowano wyniki badań symulacyjnych wybranych zakłóceń w układzie prostownika oraz stanów pracy bezawaryjnej w celu oceny ich wpływu na kształt napięć...
-
Evaluation of the separation algorithm performance employing ANNs
PublicationCelem niniejszego rozdziału jest przedstawienie metodyki separacji dźwięków muzycznych bez informacji a priori o dźwiękach zawartych w muzycznym miksie. W pracy pokazano, że prawidłowo wytrenowana sztuczna sieć neuronowa (SNN)jest w stanie w sposób automatyczny poprawnie sklasyfikować dźwięki zawarte w zmiksowanym sygnale. Skuteczność klasyfikacji SNN jest porównywalna z oceną subiektywną ekspertów.
-
Music Data Processing and Mining in Large Databases for Active Media
PublicationThe aim of this paper was to investigate the problem of music data processing and mining in large databases. Tests were performed on a large data-base that included approximately 30000 audio files divided into 11 classes cor-responding to music genres with different cardinalities. Every audio file was de-scribed by a 173-element feature vector. To reduce the dimensionality of data the Principal Component Analysis (PCA) with variable...
-
Usuwanie tła w video nagraniach pochodzących z monitorowania basenu pływackiego
PublicationAutomatyczna obróbka obrazu w czasie rzeczywistym jest kluczowa dla wielu rozwiązań monitoringu wykorzystywanych m.in. w celach bezpieczeństwa. Często jednym z ważniejszych etapów obróbki jest oddzielenie tła od obiektów na pierwszym planie, tak aby wykluczyć wszystkie nieistotne informacje z obrazu. Celem niniejszej pracy jest podsumowanie doświadczenia zdobytego podczas śledzenia pływaków oraz pokazanie możliwości skutecznego...
-
Adaptive CAD-Model Construction Schemes
PublicationTwo advanced surrogate model construction techniques are discussed in this paper. The models employ radial basis function (RBF)interpolation scheme or artificial neural networks (ANN) with a new training algorithm. Adaptive sampling technique is applied withrespect to all variables. Histograms showing the quality of the models are presented. While the quality of RBF models is satisfactory, theperformance of the ANN models obtained...
-
Wikipedia Articles Representation with Matrix'u
PublicationIn the article we evaluate different text representation methods used for a task of Wikipedia articles categorization. We present the Matrix’u application used for creating computational datasets ofWikipedia articles. The representations have been evaluated with SVM classifiers used for reconstruction human made categories.
-
Enhanced oxygen mobility by doping Yb in BaGd1-xYbxMn2O5+δ double perovskite-structured oxygen storage materials
Publication -
Ti-doped Sr2Fe1.4-xTixMo0.6O6-δ double perovskites with improved stability as anode materials for Solid Oxide Fuel Cells
Publication