Ograniczanie wyników
Czasopisma help
Autorzy help
Lata help
Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 304

Liczba wyników na stronie
first rewind previous Strona / 16 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  sztuczna sieć neuronowa
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 16 next fast forward last
EN
Installations and the detection of their faults has become a major challenge. In order to develop a reliable approach for monitoring and diagnosis faults of these components, a test rig was mounted. In this article, a Multi Layer Perceptron (MLP) Artificial Neural Network (ANN) has been structured and optimized for online monitoring of induction motors. The input layer of our ANN used eight indicators calculated from the collected time signals and which represent the different states of the motor (Healthy, broken rotor bars, bearing fault and Misalignment) and the output layer used a codified matrix. However, based on L27 Taguchi design, the architecture for the hidden layers of our network is chosen, with the use of the LevenbergMarquardt learning algorithm. Garson's algorithm and connection weight approach showed that there's a great sensitivity of the crest factor, the kurtosis and the variance on the effectiveness of our diagnostic system. Consequently, the obtained results are capable of detecting faults in the induction motor under different operating conditions.
EN
This paper presents a method of automatic recognition of fingerprint diffraction images of motor vehicle users. The proposed method is based on the basic physical properties of the Fourier transform. It creates the possibility of reducing the problem of recognition to the Fourier transform of the image function, extraction of characteristic features vector and classification of input images.
PL
Praca prezentuje metodę automatycznego rozpoznawania obrazów dyfrakcyjnych odcisków palców użytkowników pojazdów mechanicznych. Proponowana metoda, bazuje na podstawowych właściwościach fizycznych transformaty Fouriera. Stwarza możliwość sprowadzenia problemu rozpoznawania do transformaty Fouriera funkcji obrazowej, ekstrakcji wektora cech charakterystycznych i klasyfikacji obrazów wejściowych.
EN
The article contains a review of selected classification methods of dermatoscopic images with human skin lesions, taking into account various stages of dermatological disease. The described algorithms are widely used in the diagnosis of skin lesions, such as artificial neural networks (CNN, DCNN), random forests, SVM, kNN classifier, AdaBoost MC and their modifications. The effectiveness, specificity and accuracy of classifications based on the same data sets were also compared and analyzed.
PL
Artykuł zawiera przegląd wybranych metod klasyfikacji obrazów dermatoskopowych zmian skórnych człowieka z uwzględnieniem różnych etapów choroby dermatologicznej. Opisane algorytmy są szeroko wykorzystywane w diagnostyce zmian skórnych, takie jak sztuczne sieci neuronowe (CNN, DCNN), random forests, SVM, klasyfikator kNN, AdaBoost MC i ich modyfikacje. Porównana i przeanalizowana została również skuteczność, specyficznośc i dokładność klasyfikatów w oparciu o te same zestawy danych.
EN
Diabetes mellitus (DM) is a multifactorial disease characterized by hyperglycemia. The type 1 and type 2 DM are two different conditions with insulin deficiency and insulin resistance, respectively. It may cause atherosclerosis, stroke, myocardial infarction and other relevant complications. It also features neurological degeneration with autonomic dysfunction to meet metabolic demand. The autonomic balance controls the physiological variables that exhibit nonlinear dynamics. Thus, in current work, nonlinear heart rate variability (HRV) parameters in prognosis of diabetes using artificial neural network (ANN) and support vector machine (SVM) have been demonstrated. The digital lead-I electrocardiogram (ECG) was recorded from male Wister rats of 10–12 week of age and 200 ± 20 gm of weight from control (n = 5) as well as from Streptozotocin induced diabetic rats (n = 5). A total of 526 datasets were computed from the recorded ECG data for evaluating thirteen nonlinear HRV parameters and used for training and testing of ANN. Using these parameters as inputs, the classification accuracy of 86.3% was obtained with an ANN architecture (13:7:1) at learning rate of 0.01. While relatively better accuracy of 90.5% was observed with SVM to differentiate the diabetic and control subjects. The obtained results suggested that nonlinear HRV parameters show distinct changes due to diabetes and hence along with machine learning tools, these can be used for development of noninvasive low-cost real-time prognostic system in predicting diabetes using machine learning techniques.
EN
Epilepsy is a widely spread neurological disorder caused due to the abnormal excessive neural activity which can be diagnosed by inspecting the electroencephalography (EEG) signals visually. The manual inspection of EEG signals is subjected to human error and is a tedious process. Further, an accurate diagnosis of generalized and focal epileptic seizures from normal EEG signals is vital for the supervision of pertinent treatment, life advancement of the subjects, and reduction in cost for the subjects. Hence the development of automatic detection of generalized and focal epileptic seizures from normal EEG signals is important. An approach based on tunable-Q wavelet transform (TQWT), entropies, Particle Swarm Optimization (PSO) and Artificial Neural Network (ANN) is proposed in this work for detection of epileptic seizures and its types. Two EEG databases namely, Karunya Institute of Technology and Sciences (KITS) EEG database and Temple University Hospital (TUH) database consisting of normal, generalized and focal EEG signals is used in this work to analyze the performance of the proposed approach. Initially, the EEG signals are decomposed into sub-bands using TQWT and the non-linear features like log energy entropy, Shannon entropy and Stein's unbiased risk estimate (SURE) entropy is computed from each sub-band. The informative features from the computed feature vectors are selected using PSO and fed into ANN for the classification of EEG signals. The proposed algorithm for KITS database achieved a maximum accuracy of 100% for four experimental cases namely, (i) normal-focal, (ii) normal-generalised, (iii) normal-focal + generalised and (iv) normal-focal-generalised. The TUH database achieved an accuracy of 95.1%, 97.4%, 96.2% and 88.8% for the four experimental cases. The proposed approach is promising and able to discriminate the epileptic seizure types with satisfactory classification performance.
EN
Purpose: This article uses soft computing-based techniques to elaborate a study on the prediction of the friction angle of clay. Design/methodology/approach: A total of 30 data points were collected from the literature to predict the friction angle of the clay. To achieve the friction angle, the independent parameters sand content, silt content, plastic limit and liquid limit were used in the soft computing techniques such as artificial neural networks, M5P model tree and multi regression analysis. Findings: The major findings from this study are that the artificial neural networks are predicting the friction angle of the clay accurately than the M5P model and multi regression analysis. The sensitivity analysis reveals that the clay content is the major influencing independent parameter to predict the friction angle of the clay followed by sand content, liquid limit and plastic limit. Research limitations/implications: The proposed expressions can used to predict the friction angle of the clay accurately but can be further improved using large data for a wider range of applications. Practical implications: The proposed equations can be used to calculate the friction angle of the clay based on sand content, silt content, plastic limit and liquid limit. Originality/value: There is no such expression available in the literature based on soft computing techniques to calculate the friction angle of the clay.
EN
Purpose: To evaluate and compare the capability of ANFIS (Adaptive Neuro-Fuzzy-Inference System), ANN (Artificial Neural Network), and MNLR (Multiple Non-linear Regression) techniques in the estimation and formulation of Discharge Correction Factor (Cd) of modified Parshall flumes as based on linear relations and errors between input and output data. Design/methodology/approach: Acknowledging the necessity of further research in this field, experiments were conducted in the Hydraulics Laboratory of Civil Engineering Department, National Institute of Technology, Kurukshetra, India. The Parshall flume characteristics, associated longitudinal slopes and the discharge passing through the flume were varied. Consequent water depths at specific points in Parshall flumes were noted and the values of Cd were computed. In this manner, a data set of 128 observations was acquired. This was bifurcated arbitrarily into a training dataset consisting of 88 observations and a testing dataset consisting of 40 observations. Models developed using the training dataset were checked on the testing dataset for comparison of the performance of each predictive model. Further, an empirical relationship was formulated establishing Cd as a function of flume characteristics, longitudinal slope, and water depth at specific points using the MNLR technique. Moreover, Cd was estimated using soft computing tools; ANFIS and ANN. Finally, a sensitivity analysis was done to find out the flume variable having the greatest influence on the estimation of Cd. Findings: The predictive accuracy of the ANN-based model was found to be better than the model developed using ANFIS, followed by the model developed using the MNLR technique. Further, sensitivity analysis results indicated that primary depth reading (Ha) as input parameter has the greatest influence on the prediction capability of the developed model. Research limitations/implications: Since the soft computing models are data based learning, hence the prediction capability of these models may dwindle if data is selected beyond the current data range, which is based on the experiments conducted under specific conditions. Further, since the present study has faced time and facility constraints, hence there is still a huge scope of research in this field. Different lateral slopes, combined lateral- longitudinal slopes, and more modified Parshall flume models of larger sizes can be added to increase the versatility of the current research. Practical implications: Cd of modified Parshall flumes can be predicted using the ANN- based prediction model more accurately as compared to other considered techniques. Originality/value: The comparative analysis of prediction models, as well as the formulation of relation, has been conducted in this study. In all the previous works, little to no soft computing techniques have been applied for the analysis of Parshall flumes. Even the regression techniques have been applied only on Parshall flumes of standard sizes. However, this paper includes not only Parshall flume of standard size but also a modified Parshall flume in its pursuit of predicting Cd with the help of ANN and ANFIS based prediction models along with MNLR technique.
EN
Inaccurate estimation in highway projects represents a major problem facing planners and estimators, especially when data and information about the projects are not available, and therefore the need to use modern technologies that addresses the problem of inaccuracy of estimation arises. The current methods and techniques used to estimate earned value indexes in Iraq are weak and inefficient. In addition, there is a need to adopt new and advanced technologies to estimate earned value indexes that are fast, accurate and flexible to use. The main objective of this research is to use an advanced method known as artificial neural networks to estimate the TSPI of highway buildings. The application of artificial neural networks as a new digital technology in the construction industrial in Republic of Iraq is absolutely necessary to ensure successful project management. One model built to predict the TCSPI of highway projects. In this current study, artificial neural network model were used to model the process of estimating earned value indexes, and several cases related to the construction of artificial neural networks have been studied, including network architecture and internal factors and the extent of their impact on the performance of artificial neural network models. Easy equation was developed to calculate that TSPI. It was found that these networks have the ability to predict the TSPI of highway projects with a very outstanding saucepan of reliability (97.00%), and the accounting coefficients (R) (95.43%).
EN
The study areas are located in Turkey (Kastamonu, Bartın, Karabük, Sivas) and contain very diferent rock types, various mining and agricultural activity opportunities. So, the areas have groundwaters that have diferent chemical compositions and electrical conductivity (EC) values. The EC can be measured using EC meter, and it must be measured in situ. But, the measurement of EC in situ is laborious, time-consuming, expensive, and difcult in arduous terrain environments. In recent years, machine learning models have been a primary focus of interest for a lot of study by providing often highly accurate forecast for solutions of such problems. The aim of the study is to forecast EC of groundwater using artifcial neural networks (ANN) and multiple linear regressions (MLR). Twelve diferent hydrochemical parameters, which afect the EC, such as major/minor ions and trace elements, were used in the analysis. Multilayer feed-forward ANN trained with backpropagation in Python machine learning libraries was used in this study. In order to obtain the most appropriate ANN architecture, trialand-error procedure was used and diferent numbers of hidden layers, neurons, activation functions, optimizers, and test sizes were constructed. This study also tests the usability of input parameters in EC prediction studies. As a result, comparisons between the measured and predicted values indicated that the machine learning models could be successfully applied and provide high accuracy and reliability for EC and similar parameters forecasting.
EN
The continuous shift of shoreline boundaries due to natural or anthropogenic events has created the necessity to monitor the shoreline boundaries regularly. This study investigates the perspective of implementing artifcial intelligence techniques to model and predict the realignment in shoreline along the eastern Indian coast of Orissa (now called Odisha). The modeling consists of analyzing the satellite images and corresponding reanalysis data of the coastline. The satellite images (Landsat imagery) of the Orissa coastline were analyzed using edge detection flters, mainly Sobel and Canny. Sobel and canny flters use edge detection techniques to extract essential information from satellite images. Edge detection reduces the volume of data and flters out worthless information while securing signifcant structural features of satellite images. The image diferencing technique is used to determine the shoreline shift from GIS images (Landsat imagery). The shoreline shift dataset obtained from the GIS image is used together with the metrological dataset extracted from Modern-Era Retrospective analysis for Research and Applications, Version 2, and tide and wave parameter obtained from the European Centre for Medium-Range Weather Forecast for the period 1985–2015, as input parameter in machine learning (ML) algorithms to predict the shoreline shift. Artifcial neural network (ANN), k-nearest neighbors (KNN), and support vector machine (SVM) algorithm are used as a ML model in the present study. The ML model contains weights that are multiplied with relevant inputs/features to obtain a better prediction. The analysis shows wind speed and wave height are the most prominent features in shoreline shift prediction. The model’s performance was compared, and the observed result suggests that the ANN model outperforms the KNN and SVM model with an accuracy of 86.2%.
11
PL
W badaniach podjęto próbę wykorzystania ultrasłabej emisji fotonowej do oceny jakości wybranych surowców biologicznych. Sprawdzono poziom wtórnej luminescencji z trzech rodzajów czekolad: gorzkiej, mlecznej oraz białej. Do przeprowadzenia pomiarów użyto stanowiska wyposażonego w fotopowielacz, służący do identyfikacji pojedynczych fotonów. Odnotowano znaczne zróżnicowanie w poziomie emisyjności fotonów z wybranych produktów. Dokonano analizy wyników porównując je z zawartością poszczególnych składników odżywczych. Zastosowano sztuczne sieci neuronowe do określenia zależności pomiędzy poszczególnymi zmiennymi oraz do klasyfikacji rodzaju czekolady na podstawie liczby emitowanych przez nią fotonów.
EN
The research attempts to use ultra-low photonic emission to assess the quality of selected biological raw materials. The level of secondary luminescence from three kinds of chocolate: dark, milk and white. A station equipped with a photomultiplier used to identify individual photons was used to do the measurements. There was a appreciable difference in the emissivity level of photons from selected products. The results were compared comparing them with the content of various nutrients. Artificial neural networks were used to check the relationships between individual variables and to classify chocolate based on the number of photons it emits.
EN
А method for load distribution in the network 0,4/0,23 kV using artificial neural networks is proposed. Types of artificial neural networks are analyzed and a solution to this task based on neural network multilayer perception is proposed. A neural network structure is built which makes recommendations for the uniform distribution of loads in the network based on statistical information. On the basis of the neural network, software for the uniform distribution of loads between phases of the network is created.
PL
W pracy zaproponowano metodę rozkładu obciążeń w sieci 0,4/0,23 kV za pomocą sztucznej sieci neuronowej. Przeanalizowano typy sztucznych sieci neuronowych oraz zaproponowano rozwiązanie wymienionego zadania na podstawie wielostrefowego perceptronu. Opracowano strukturę sieci neuronowej, która daje polecenia, co do równomiernego rozkładu obciążeń w sieci, wychodząc z informacji statystycznej. Dzięki sieci neuronowej tworzone jest oprogramowanie do równomiernego rozkładu obciążeń między fazami sieci.
EN
The main purpose of this study is the multicriterion optimization in a dynamic context of the operation of an industrial electrostatic separation process with rotating electrode. A study of the operation of this process, performed by using an artificial neural network (ANN), has shown the complexity of adjusting the control variables for use in the industrial field. In this context, a multifactorial control approach has been proposed using meta-heuristics based on artificial intelligence.
PL
W artykule zaprezentowano multikryterialną optymalizację przemysłowego separatora elektrostatycznego z ruchomymi elektrodami. Do optymalizacji wykorzystano sztuczne sieci neuronowe.
14
Content available remote Industrial processes control with the use of a neural tomographic algorithm
EN
This paper presents the original Electrical Impedance Tomography (EIT) imaging algorithm in relation to physic-chemical processes of crystallization. Thanks to the developed method based on artificial neural networks (ANN), it was possible to develop an algorithm that could allow effective detection of crystals and other inclusions inside the reactor filled with non-Newtonian fluid. The neural controller contains a structure of independent neural networks. The number of ANNs corresponds to the resolution of the output image mesh.
PL
W artykule przedstawiono oryginalny algorytm obrazowania z wykorzystaniem elektrycznej impedancji tomograficznej (EIT) w odniesieniu do fizykochemicznych procesów krystalizacji. Dzięki opracowanej metodzie opartej na sztucznych sieciach neuronowych (SSN) możliwe było opracowanie algorytmu, który umożliwiłby skuteczne wykrywanie kryształów i innych wtrąceń wewnątrz reaktora wypełnionego płynem nienewtonowskim. Sterownik neuronowy składa się z systemu niezależnych sieci neuronowych. Liczba SSN odpowiada rozdzielczości siatki obrazu wyjściowego.
PL
Dla potrzeb takiej identyfikacji osób przebywających w pomieszczeniach budynu, opracowany został algorytm profilowania i identyfikacji osobowej z zastosowaniem sztucznych sieci neuronowych – neuronową identyfikacją organicznego profilu osobowego (NIOPO – ang. Neural identification of an organic personal profile NIOPP). Identyfikacja neuronowa, wykorzystuje pomiary koncentracji gazów, których proporcje oraz skład są cechą indywidualną dla każdego człowieka.
EN
For the purpose of such identification of people staying in the building's premises, a profiling and personal identification algorithm was developed with the use of artificial neural networks - neural identification of the organic personal profile (NIOPP). Neural identification, uses measurements of gas concentrations whose proportions and composition are an individual feature for every human being.
EN
Multiphase flow meters are used to measure the water-liquid ratio (WLR) and void fraction in a multiphase fluid stream pipeline. In the present study, a system of multiphase flow measurement has been designed by application of three thallium-doped sodium iodide scintillators and a radioactive source of 133Ba simulated by Monte Carlo N-particle (MCNP) transport code. In order to capture radiations passing across the pipe, two direct detectors have been installed on opposite sides of the radioactive source. Another detector has been placed perpendicular to the transmission beam emitted from the 133Ba source to receive radiations scattered from the fluid flow. Simulation was done by the MCNP code for different volumetric fractions of water, oil, and gas phases for two types of flow regimes, namely, homogeneous and annular; training and validation data have been provided for the artificial neural network (ANN) to develop a computation model for pattern recognition. Depending on applications of the neural system, several structures of ANNs are used in the current paper to model the flow measurement relations, while the detector outputs are considered as the input parameters of the neural networks. The first, second, and third structures benefit from two, three, and five multilayer perceptron neural networks, respectively. Increasing the number of ANNs makes the system more complicated and decreases the available data; however, it increases the accuracy of estimation of WLR and gas void fraction. According to the results, the maximum relative difference was observed in the scattering detector. It was clear that transmission detectors would demonstrate the difference between the flow regimes as well. It is necessary to note that the error calculated by the MCNP simulator is <0.5% for the direct detectors (TR1 and TR2). Due to the difference between the data of the two flow regimes and the errors of data in the simulation codes of the MCNP, it was possible to separate these flow regimes. The effect of changing WLR on the efficiency for a constant void fraction confi rms a considerable variance in the results of annular and homogeneous flow s occurring in the scattering detector. There is a similar trend for the void fraction; hence, one can easily distinguish changes in efficiency due to the WLR. Analysis of the simulation results revealed that in the proposed structure of the multiphase flow meter and the computation model used for simulation, the two flow regimes are simply distinguishable.
EN
This work is aimed at developing relations between the pertinent variables that affect drilling process of stainless steel using artificial neural network. The experiments were conducted on vertical CNC machining centre. The parameters used were spindle speed and feed rate. The effect of machining parameters on entry burr height, exit burr height and surface roughnesswas experimentally evaluated for different spindle speeds and feed rates. A model was established between the drilling parameters and experimentally obtained data using ANN. The predicted values and measured values are fairly close, which indicates that the developed model can be effectively used to predict the burr height and surface roughness in drilling of stainless steel. Genetic algorithm (GA) technique was used in this work to identify the optimized drilling parameters. Confirmation test was conducted with the optimized parameters and it was found that confirmation test results were similar to that of GA-predicted output values.
EN
In this research study, a combination of lower and upper bound finite element limit analysis (FELA) and artificial neural network (ANN) has been adopted in order to forecast critical seismic coefficients (kc) of homogeneous earth dams (HED) subjected to pseudo-static seismic loading. To achieve this, the results of kc obtained by OptumG2 software were used in the development of the ANN and MR models. The ANN models have shown higher prediction performance than the MR models based on the performance indices. The most appropriate architecture was found 8-14-1, as this gave the best kc predict with the minimum statistical measures of error and the high determination coefficient (> 99%). Consequently, the ANN model can be used to easily and accurately predict kc value of the HED as the best substitute for the conventional methods.
EN
Automatic classification methods, such as artificial neural networks (ANNs), the k-nearest neighbor (kNN) and self-organizing 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’ and phonology experts’ speech was selected for analyses. For the purpose of the present study, a sub-list of 103 words containing the English alveolar lateral phoneme /l/ was compiled. The list includes ‘dark’ (velarized) allophonic realizations (which occur before a consonant or at the end of the word before silence) and 52 ‘clear’ allophonic realizations (which occur before a vowel), as well as voicing variants. The recorded signals were segmented into allophones and parametrized using a set of descriptors, originating from the MPEG 7 standard, plus dedicated time-based parameters as well as modified MFCC features proposed by the authors. Classification methods such as ANNs, the kNN and the SOM were employed to automatically detect the two types of allophones. Various sets of features were tested to achieve the best performance of the automatic methods. In the final experiment, a selected set of features was used for automatic evaluation of the pronunciation of dark /l/ by non-native speakers.
20
EN
The paper describes the selected methods of adaptive control of the pulverized coal combustion process overview with various types of prognostic models. It was proposed to use a class of control methods that are relatively well established in industrial practice. The presented approach distinguishes the use of an additional source of information in the form of signals from an optical diagnostic system and models based on selected deep structures of recurrent networks. The research aim is to increase the efficiency of the combustion process in the power boiler, taking into account the EU emission standards, leading in consequence to sustainable energy and sustainable environmental engineering.
PL
W artykule opisano wybrane metody adaptacyjnego sterowania przeglądem procesu spalania pyłu węglowego z wykorzystaniem określonych modeli prognostycznych. Zaproponowano użycie metod, które są stosunkowo dobrze znane w praktyce przemysłowej. Przedstawione podejście wyróżnia wykorzystanie dodatkowego źródła informacji w postaci sygnałów z optycznego systemu diagnostycznego i modeli opartych na strukturach sieci głębokich. Badania mają na celu zwiększenia efektywności procesu spalania w kotle energetycznym, z uwzględnieniem norm emisji UE, prowadząc w konsekwencji do zrównoważonej energii i zrównoważonej inżynierii środowiska.
first rewind previous Strona / 16 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.