Search results for: approximation methods, fractional calculus, modeling, neural networks, recurrent neural networks
-
Neurocontrolled Car Speed System
PublicationThe features of the synthesis of neural controllers for the car speed control system are considered in this article. The task of synthesis is to determine the weight coefficients of neural networks that provide the implementation of proportional and proportional-integralderivative control laws. The synthesis of controllers is based on an approach that uses a reversed model of the standard. A model of the car speed control system with...
-
Spatiotemporal Assessment of Satellite Image Time Series for Land Cover Classification Using Deep Learning Techniques: A Case Study of Reunion Island, France
PublicationCurrent 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...
-
International Conference on Artificial Neural Networks and Genetic Algorithms
Conferences -
International Work-Conference on Artificial and Natural Neural Networks
Conferences -
IEEE International Workshop on Neural Networks for Signal Processing
Conferences -
Experience-Based Cognition for Driving Behavioral Fingerprint Extraction
PublicationABSTRACT With the rapid progress of information technologies, cars have been made increasingly intelligent. This allows cars to act as cognitive agents, i.e., to acquire knowledge and understanding of the driving habits and behavioral characteristics of drivers (i.e., driving behavioral fingerprint) through experience. Such knowledge can be then reused to facilitate the interaction between a car and its driver, and to develop better and...
-
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...
-
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...
-
Computational intelligence methods in production management
PublicationThis chapter presents a survey of selected computational intelligence methods used in production management. This group of methods includes, among others, approaches based on the artificial neural networks, the evolutionary algorithms, the fuzzy logic systems and the particle swarm optimization mechanisms. From the abovementioned methods particularly noteworthy are the evolutionary and the particle swarm algorithms, which are successfully...
-
OBTAINING FLUID FLOW PATTERN FOR TURBINE STAGE WITH NEURAL MODEL.
PublicationIn the paper possibility of applying neural model to obtaining patterns of proper operation for fluid flow in turbine stage for fluid-flow diagnostics is discussed. Main differences between Computational Fluid Dynamics (CFD) solvers and neural model is given, also limitations and advantages of both are considered. Time of calculations of both methods was given, also possibilities of shortening that time with preserving the accuracy...
-
Neural Network Subgraphs Correlation with Trained Model Accuracy
PublicationNeural Architecture Search (NAS) is a computationally demanding process of finding optimal neural network architecture for a given task. Conceptually, NAS comprises applying a search strategy on a predefined search space accompanied by a performance evaluation method. The design of search space alone is expected to substantially impact NAS efficiency. We consider neural networks as graphs and find a correlation between the presence...
-
Evaluating Performance and Accuracy Improvements for Attention-OCR
PublicationIn this paper we evaluated a set of potential improvements to the successful Attention-OCR architecture, designed to predict multiline text from unconstrained scenes in real-world images. We investigated the impact of several optimizations on model’s accuracy, including employing dynamic RNNs (Recurrent Neural Networks), scheduled sampling, BiLSTM (Bidirectional Long Short-Term Memory) and a modified attention model. BiLSTM was...
-
Shape Optimisation of Kaplan Turbine Blades Using Genetic Algorithms
PublicationThis monograph is a comprehensive guide to a method of blade profile optimisation for Kaplan-type turbines. This method is based on modelling the interaction between rotor and stator blades. Additionally, the shape of the draft tube is investigated. The influence of the periodic boundary condition vs. full geometry is also discussed. Evolutionary algorithms (EA) are used as an optimisation method together with artificial neural...
-
A Method for Optimising the Blade Profile in Kaplan Turbine
PublicationThis paper introduces a method of blade profile optimisation for Kaplan-type turbines, based on modelling the interaction between rotor and stator blades. Rotor and stator blade geometry is described mathematically by means of a midline curve and thickness distribution. Genetic algorithms are then used to find a global optimum that minimises the loss coefficient. This allows for variety of possible blade shapes and configurations....
-
Selection of an artificial pre-training neural network for the classification of inland vessels based on their images
PublicationArtificial neural networks (ANN) are the most commonly used algorithms for image classification problems. An image classifier takes an image or video as input and classifies it into one of the possible categories that it was trained to identify. They are applied in various areas such as security, defense, healthcare, biology, forensics, communication, etc. There is no need to create one’s own ANN because there are several pre-trained...
-
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...
-
Fractional Order Dynamic Positioning Controller
PublicationImproving the performance of Dynamic Positioning System in such applications as station keeping, position mooring and slow speed references tracking requires improving the position and heading control precision. These goals can be achieved through the improvement of the ship control system. Fractional-order calculus is a very useful tool which extends classical, integer-order calculus and is used in contemporary modeling and control...
-
Marek Biziuk prof. dr hab. inż.
PeopleCURRICULUM VITAE Marek BIZIUK Born 1947 MSc 1969 GUT PhD 1977 GUT DSc 1994 GUT Professor 2001 Membership of scientific society - Gdansk Scientific Society - Romanian Society of Analytical Chemistry - Engineers and Techniques of...
-
A Novel IoT-Perceptive Human Activity Recognition (HAR) Approach Using Multi-Head Convolutional Attention
PublicationTogether with fast advancement of the Internet of Things (IoT), smart healthcare applications and systems are equipped with increasingly more wearable sensors and mobile devices. These sensors are used not only to collect data, but also, and more importantly, to assist in daily activity tracking and analyzing of their users. Various human activity recognition (HAR) approaches are used to enhance such tracking. Most of the existing...
-
User Orientation Detection in Relation to Antenna Geometry in Ultra-Wideband Wireless Body Area Networks Using Deep Learning
PublicationIn 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...
-
Towards neural knowledge DNA
PublicationIn this paper, we propose the Neural Knowledge DNA, a framework that tailors the ideas underlying the success of neural networks to the scope of knowledge representation. Knowledge representation is a fundamental field that dedicates to representing information about the world in a form that computer systems can utilize to solve complex tasks. The proposed Neural Knowledge DNA is designed to support discovering, storing, reusing,...
-
Neural Network-Based Sequential Global Sensitivity Analysis Algorithm
PublicationPerforming global sensitivity analysis (GSA) can be challenging due to the combined effect of the high computational cost, but it is also essential for engineering decision making. To reduce this cost, surrogate modeling such as neural networks (NNs) are used to replace the expensive simulation model in the GSA process, which introduces the additional challenge of finding the minimum number of training data samples required to...
-
Dagmara Nikulin dr
PeopleBio: Dagmara Nikulin Dagmara Nikulin has been employed at the Faculty of Management and Economics as a research and teaching assistant professor since 2014. Initially, she worked at the Department of Economic Sciences, and now at the Department of Statistics and Econometrics. She is a graduate of the Faculty of Economics at the Poznań University of Economics (2009) and the Faculty of Social Sciences of the Adam Mickiewicz University...
-
New Two-center Ellipsoidal Basis Function Neural Network for Fault Diagnosis of Analog Electronic Circuits
PublicationIn the paper a new fault diagnosis-oriented neural network and a diagnostic method for localization of parametric faults in Analog Electronic Circuits (AECs) with tolerances is presented. The method belongs to the class of dictionary Simulation Before Test (SBT) methods. It utilizes dictionary fault signatures as a family of identification curves dispersed around nominal positions by component tolerances of the Circuit Under Test...
-
Underground Water Level Prediction in Remote Sensing Images Using Improved Hydro Index Value with Ensemble Classifier
PublicationThe economic sustainability of aquifers across the world relies on accurate and rapid estimates of groundwater storage changes, but this becomes difficult due to the absence of insitu groundwater surveys in most areas. By closing the water balance, hydrologic remote sensing measures offer a possible method for quantifying changes in groundwater storage. However, it is uncertain to what extent remote sensing data can provide an...
-
Machine Learning Algorithm-Based Tool and Digital Framework for Substituting Daylight Simulations In Early- Stage Architectural Design Evaluation
PublicationThe aim of this paper is to examine the new method of obtaining the simulation-based results using backpropagation of errors artificial neural networks. The primary motivation to conduct the research was to determine an alternative, more efficient and less timeconsuming method which would serve to achieve the results of daylight simulations. Three daylight metrics: Daylight Factor, Daylight Autonomy and Daylight Glare Probability have...
-
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...
-
Neural network training with limited precision and asymmetric exponent
PublicationAlong with an extremely increasing number of mobile devices, sensors and other smart utilities, an unprecedented growth of data can be observed in today’s world. In order to address multiple challenges facing the big data domain, machine learning techniques are often leveraged for data analysis, filtering and classification. Wide usage of artificial intelligence with large amounts of data creates growing demand not only for storage...
-
Workshop on Approximation and Randomization Algorithms in Communication Networks
Conferences -
Neural network simulator's application to reference performance determination of turbine blading in the heat-flow diagnostics.
PublicationIn the paper, the possibility of application of artificial neural networks to perform the fluid flow calculations through both damaged and undamaged turbine blading was investigated. Preliminary results are presented and show the potentiality of further development of the method for the purpose of heat-flow diagnostics.
-
Speech Analytics Based on Machine Learning
PublicationIn this chapter, the process of speech data preparation for machine learning is discussed in detail. Examples of speech analytics methods applied to phonemes and allophones are shown. Further, an approach to automatic phoneme recognition involving optimized parametrization and a classifier belonging to machine learning algorithms is discussed. Feature vectors are built on the basis of descriptors coming from the music information...
-
DIAGNOSIS OF MALIGNANT MELANOMA BY NEURAL NETWORK ENSEMBLE-BASED SYSTEM UTILISING HAND-CRAFTED SKIN LESION FEATURES
PublicationMalignant melanomas are the most deadly type of skin cancer but detected early have high chances for successful treatment. In the last twenty years, the interest of automated melanoma recognition detection and classification dynamically increased partially because of public datasets appearing with dermatoscopic images of skin lesions. Automated computer-aided skin cancer detection in dermatoscopic images is a very challenging task...
-
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,...
-
Breast MRI segmentation by deep learning: key gaps and challenges
PublicationBreast 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...
-
General concept of reduction process for big data obtained by interferometric methods
PublicationInterferometric sonar systems apply the phase content of the sonar signal to measure the angle of a wave front returned from the seafloor or from a target. It collect a big data – datasets that are so large or complex that traditional data processing application software is inadequate to deal with them. The recording a large number of data is associated with the difficulty of their efficient use. So data have to be reduced. The main...
-
Chemometrics for Selection, Prediction, and Classification of Sustainable Solutions for Green Chemistry—A Review
PublicationIn this review, we present the applications of chemometric techniques for green and sustainable chemistry. The techniques, such as cluster analysis, principal component analysis, artificial neural networks, and multivariate ranking techniques, are applied for dealing with missing data, grouping or classification purposes, selection of green material, or processes. The areas of application are mainly finding sustainable solutions...
-
Deep neural network architecture search using network morphism
PublicationThe paper presents the results of the research on neural architecture search (NAS) algorithm. We utilized the hill climbing algorithm to search for well-performing structures of deep convolutional neural network. Moreover, we used the function preserving transformations which enabled the effective operation of the algorithm in a short period of time. The network obtained with the advantage of NAS was validated on skin lesion classification...
-
Deep Learning Optimization for Edge Devices: Analysis of Training Quantization Parameters
PublicationThis 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...
-
Selection of Features for Multimodal Vocalic Segments Classification
PublicationEnglish speech recognition experiments are presented employing both: audio signal and Facial Motion Capture (FMC) recordings. The principal aim of the study was to evaluate the influence of feature vector dimension reduction for the accuracy of vocalic segments classification employing neural networks. Several parameter reduction strategies were adopted, namely: Extremely Randomized Trees, Principal Component Analysis and Recursive...
-
BIG DATA SIGNIFICANCE IN REMOTE MEDICAL DIAGNOSTICS BASED ON DEEP LEARNING TECHNIQUES
PublicationIn this paper we discuss the evaluation of neural networks in accordance with medical image classification and analysis. We also summarize the existing databases with images which could be used for training deep models that can be later utilized in remote home-based health care systems. In particular, we propose methods for remote video-based estimation of patient vital signs and other health-related parameters. Additionally, potential...
-
Modelowanie przepływu pary przez okołodźwiękowe wieńce turbinowe z użyciem sztucznych sieci neuronoych
PublicationNiniejszy artykuł stanowi opis modelu przepływu pary przez okołodźwiękowe stopnie turbinowe, stworzonego w oparciu o sztuczne sieci neuronowe (SSN). Przedstawiony model neuronowy pozwala na wyznaczenie rozkładu wybranych parametrów w analizowanym przekroju kanału przepływowego turbiny dla rozpatrywanego zakresu wartości ciśnienia wlotowego.
-
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...
-
Analyzing the Effectiveness of the Brain–Computer Interface for Task Discerning Based on Machine Learning
PublicationThe aim of the study is to compare electroencephalographic (EEG) signal feature extraction methods in the context of the effectiveness of the classification of brain activities. For classification, electroencephalographic signals were obtained using an EEG device from 17 subjects in three mental states (relaxation, excitation, and solving logical task). Blind source separation employing independent component analysis (ICA) was...
-
An Improved Convolutional Neural Network for Steganalysis in the Scenario of Reuse of the Stego-Key
PublicationThe topic of this paper is the use of deep learning techniques, more specifically convolutional neural networks, for steganalysis of digital images. The steganalysis scenario of the repeated use of the stego-key is considered. Firstly, a study of the influence of the depth and width of the convolution layers on the effectiveness of classification was conducted. Next, a study on the influence of depth and width of fully connected...
-
Comparison of selected electroencephalographic signal classification methods
PublicationA variety of methods exists for electroencephalographic (EEG) signals classification. In this paper, we briefly review selected methods developed for such a purpose. First, a short description of the EEG signal characteristics is shown. Then, a comparison between the selected EEG signal classification methods, based on the overview of research studies on this topic, is presented. Examples of methods included in the study are: Artificial...
-
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,...
-
Training of Deep Learning Models Using Synthetic Datasets
PublicationIn order to solve increasingly complex problems, the complexity of Deep Neural Networks also needs to be constantly increased, and therefore training such networks requires more and more data. Unfortunately, obtaining such massive real world training data to optimize neural networks parameters is a challenging and time-consuming task. To solve this problem, we propose an easy-touse and general approach to training deep learning...
-
Methods of Artificial Intelligence for Prediction and Prevention Crisis Situations in Banking Systems
PublicationIn 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.
-
A Novel Method for the Deblurring of Photogrammetric Images Using Conditional Generative Adversarial Networks
PublicationThe visual data acquisition from small unmanned aerial vehicles (UAVs) may encounter a situation in which blur appears on the images. Image blurring caused by camera motion during exposure significantly impacts the images interpretation quality and consequently the quality of photogrammetric products. On blurred images, it is difficult to visually locate ground control points, and the number of identified feature points decreases...