Wyniki wyszukiwania - BazTech

1

Education Quality Detection Method Based on the Probabilistic Neural Network Algorithm

Wu Changdong, Jiang Hua, Wang Ping

Diagnostyka

|

2020

|

Vol. 21, No. 4

79--86

EN

The traditional education quality detection method is too single and unreasonable, which is not suitable to evaluate students' ability comprehensively. In this paper, the probabilistic neural network (PNN) algorithm is used to detect the education quality by considering the important impact between the various achievements of students. PNN algorithm originates from Bayesian decision rule, and it uses the non-linear Gaussian Parzen window as the probability density function. As PNN model has the virtues of strong nonlinear and anti-interfering ability, it is fit to detect the education quality by classifying the students' achievements. Besides, the influences of different evaluation models on classification accuracy and efficiency are also discussed in this paper. Furthermore, the effect of spread value on PNN model is also discussed. Finally, the actual data are used to detect the education quality. Experimental results show that the detection accuracy can reach 95%, and the detection time is only 0.0156s based on the proposed method. That is to say, the method is a very practical detection algorithm with high accuracy and efficiency. Moreover, it also provides a reference for how to further improve the teaching quality.

2

Complex lithology prediction using mean impact value, particle swarm optimization, and probabilistic neural network techniques

Gu Yufeng, Zhang Zhongmin, Zhang Demin, Zhu Yixuan, Bao Zhidong, Zhang Daoyong

Acta Geophysica

|

2020

|

Vol. 68, no. 6

1727--1752

EN

Lithology prediction is a fundamental problem because the outcome of lithology prediction is the critical underlying data for some basic geological work, e.g., establishing stratigraphic framework or analyzing distribution of sedimentary facies. As the geological formation generally consists of many diferent lithologies, the lithology prediction is always viewed as a tough work by geologists. Probabilistic neural network (PNN) shows high efciency when solving pattern recognition problem since learning data do not need to do any pre-training of learning data and calculation results are universally reliable, and then, this model could be considered as an efective solution. However, there are two factors that seriously limit the PNN’s performance: One is existence of the interference variables of learning samples, and the other is selection of the window length of probability density distribution. In view of adverse impact of those two factors, two techniques, mean impact value (MIV) and particle swarm optimization (PSO), are introduced to improve the PNN’s calculation capability. Thus, a new prediction method referred as MIV–PSO–PNN is proposed in this paper. The proposed method is validated by three well-designed experiments, and the corresponding experiment data are recorded by two cored wells of the LULA oilfeld. For the three experiments, prediction accuracies of the results provided by the proposed method are 81.67%, 73.34% and 88.34%, respectively, all of which are higher than those provided by other comparative approaches including backpropagation (BP), PNN, and MIV-PNN. The experiment results strongly demonstrate that the proposed method is capable to predict complex lithology.

3

Determination of the best microstructure and titanium alloy powders properties using neural network

Duriagina Z. A., Tkachenko R. O., Trostianchyn A. M., Lemishka I. A., Kovalchuk A. M., Kulyk V. V., Kovbasyuk T. M.

Journal of Achievements in Materials and Manufacturing Engineering

|

2018

|

Vol. 87, nr 1

25--31

EN

Purpose: Create a software product using a probabilistic neural network (PNN) and database based on experimental research of titanium alloys to definition of the best microstructure and properties of aerospace components. Design/methodology/approach: The database creation process for artificial neural network training was preceded by the investigation of the granulometric composition of the titanium powder alloys, study of microstructure, phase composition and evaluation of micromechanical properties of these alloys by the method of material plasticity estimation in the conditions of hard pyramidal indenters application. A granulometric analysis was done using a special complex of materials science for the images analysis ImageJ. Metallographic investigations of the powder structure morphology were carried out on the scanning electron microscope EVO 40XVP. Specimens for micromechanical testing were obtained by overlaying the titanium alloy powders on the substrate made of the material close to chemical composition. Substrates were prepared by pressing the powder mixture under the load of 400 MPa and following sintering at 1300°C for 1 hour. Overlaying was performed by an electron gun ELA-6 (beam current – 16 mA). Findings: According to the modelling results, a threshold of the PNN accuracy was established to be over 80%. A high level of experimental data reproduction allows us a full or partial replacement of a number of experimental investigations by neural network modelling, noticeably decreasing, in this case, the cost of the material creation possessing the preset properties with preserved quality. It is expected that this software can be used for solving other problems in materials science too. Research limitations/implications: The accuracy of the PNN algorithm depends on the number of input parameters obtained experimentally and forms a database for the training of the system. For our case, the amount of input data is limited. Practical implications: Previously trained system based on the PNN algorithm will reduce the number of experiments that significantly reduce costs and time to study. Originality/value: A software product on the basis of the PNN network was developed. The training sample was built based on a series of laboratory studies granulometric composition of the titanium powder alloys, study of microstructure, phase composition and evaluation of micromechanical properties of powder materials. The proposed approach allows us to determine the best properties of the investigated material for the design of aerospace components.

4

Glossokinetic potential based tongue–machine interface for 1-D extraction using neural networks

Gorur K., Bozkurt M. R., Bascil M. S., Temurtas F.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 3

745--759

EN

Tongue machine interface (TMI) is a tongue-operated assistive technology enabling people with severe disabilities to control their environments using their tongue motion. In many disorders such as amyotrophic lateral sclerosis or stroke, people can communicate with the external world in a limited degree. However, they may be disabled, while their mind is still intact. Various tongue–machine interface techniques has been developed to support these people by providing additional communication pathway. In this study, we aimed to develop a tongue–machine interface approach by investigating pattern of glossokinetic potential (GKP) signals using neural networks via simple right/left tongue touchings to the buccal walls for 1-D control and communication, named as GKP-based TMI. As can be known in the literature, the tongue is connected to the brain via hypoglossal cranial nerve. Therefore, it generally escapes from the severe damages, in spinal cord injuries and was slowly affected than limbs of persons suffering from many neuromuscular degenerative disorders. In this work, 8 male and 2 female naive healthy subjects, aged 22 to 34 years, participated. Multilayer neural network and probabilistic neural network were employed as classification algorithms with root-mean-square and power spectral density feature extraction operations. Then the greatest success rate achieved was 97.25%. This study may serve disabled people to control assistive devices in natural, unobtrusive, speedy and reliable manner. Moreover, it is expected that GKP-based TMI could be a collaboration channel for traditional electroencephalography (EEG)-based brain computer interfaces which have significant inadequacies arisen from the EEG signals.

5

Wykorzystanie probabilistycznych sieci neuronowych do wyznaczania ryzyka powstania szkód w budynkach poddanych wstrząsom górniczym

Witkowski M., Rusek J.

Przegląd Górniczy

|

2017

|

T. 73, nr 1

44--47

PL

W pracy przedstawiono metodykę pozwalającą na wyznaczenie ryzyka powstania szkód górniczych w budynkach o tradycyjnej konstrukcji murowanej w przypadku silnych wstrząsów górniczych. Podstawą do analiz była baza danych o zgłoszeniach uszkodzeń, jakie wystąpiły po wstrząsach z 20.02.2002 r., 16.05.2004 r. oraz 21.05.2006 r. (LGOM Polkowice) W oparciu o te dane utworzono model klasyfikacyjny w postaci probabilistycznej sieci neuronowej (PNN - Probabilistic Neural Network). Bazując na wynikach wcześniejszych prac, w modelu ujęto konstrukcyjne i geometryczne cechy budynków oraz ich zabezpieczenia przeciwko wstrząsom górniczym. Powstały klasyfikator pozwala na wskazanie prawdopodobieństwa powstania szkody przy zadanym zestawie zmiennych wejściowych. Probabilistyczna notacja modelu daje możliwość efektywnego szacowania prawdopodobieństwa wystąpienia szkody w analizie dużych grup obiektów budowlanych zlokalizowanych w obszarze oddziaływań parasejsmicznych. Pozwolić to może z kolei na oszacowanie, z odpowiednim prawdopodobieństwem, nakładów finansowych, które zakład górniczy powinien zabezpieczyć na usunięcie spodziewanych szkód górniczych.

EN

This paper presents a methodology that allows to determine the risk of mining damage in buildings of conventional brickwork in the case of strong mining tremors. The basis for the analysis was the database on notifications of damage occurring after the upheavals of 20 February 2002, 16 May 2004 and 21 May 2006 (LGOM – Polkowice). Based on these data classification a model in the form of a probabilistic neural network (PNN) was developed. Basing on the results of the previous papers, the model includes structural and geometric characteristics of the buildings and their protection against mining tremors. The probability of damage at a given set of input variables can be indicated owing to the obtained classifier. An efficient way to estimate the probability of damage in the analysis of large groups of buildings located in the area of paraseismic interaction can be obtained by the use of a probabilistic notation model. Due to PNN the financing costs of removing the anticipated mining damage can be estimated with an appropriate probability.

6

Pattern Classification of Fabric Defects Using a Probabilistic Neural Network and Its Hardware Implementation using the Field Programmable Gate Array System

Hasnat A., Ghosh A., Khatun A., Halder S.

Fibres & Textiles in Eastern Europe

|

2017

|

Vol. 25, no. 1 (121)

42--48

EN

This study proposes a fabric defect classification system using a Probabilistic Neural Network (PNN) and its hardware implementation using a Field Programmable Gate Arrays (FPGA) based system. The PNN classifier achieves an accuracy of 98 ± 2% for the test data set, whereas the FPGA based hardware system of the PNN classifier realises about 94±2% testing accuracy. The FPGA system operates as fast as 50.777 MHz, corresponding to a clock period of 19.694 ns.

PL

W pracy zaprezentowano system klasyfikacji wad tkanin przy użyciu probabilistycznej sieci neuronowej (PNN) i przy zastosowaniu systemu Field Programmable Gate Array (FPGA). PNN pozwala na osiągnięcie dokładności 98 ± 2% dla zbioru danych testowych, podczas gdy system FPGA pozwala na osiągnięcie dokładności około 94 ± 2%. System FPGA pracuje przy częstotliwości 50,777 MHz, co odpowiada 19,694 ns.

7

Developing an Intelligent Model for the Construction a Hip Shape Recognition System Based on 3D Body Measurement

Jin J.-F., Yang Y.-C., Zou F.-Y.

Fibres & Textiles in Eastern Europe

|

2016

|

Vol. 24, no. 5 (119)

110--118

EN

The purpose of this paper was to develop an intelligent recognition system consisting of a feature reduction method combining cluster and correlation analyses, and a probabilistic neural network (PNN) classifier to identify different types of hip shape from 3D measurement for each person. Firstly 28 items reflecting lower body part information of 300 female university students aging from 20 to 24 years were selected. The feature reduction method was employed to extract typical indices. Secondly hip shapes were subdivided into five types by a K-means cluster and analysis of variance (ANOVA). Finally the PNN was then trained to serve as a classifier for identifying five different hip shape types. The average classification accuracy of the scheme proposed was 97.37%, and its effectiveness was successfully validated by comparing with the BP and Support Vector Machine (SVM) scheme. Thus an intelligent recognition system was developed to make hip shape type classification of high-precision and time saving.

PL

Model łączy analizę skupień i korelacji oraz probabilistyczną sztuczną sieć neuronową dla identyfikacji różnych typów kształtów bioder opartą o pomiary 3D poszczególnych osób. Wyselekcjonowano 28 przypadków odzwierciedlających dolną część sylwetki 300 studentek w wieku od 20 do 24 lat. Zastosowano metodę redukcji poszczególnych właściwości dla wybrania typowych wskaźników. Następnie kształt bioder podzielono na 5 typów za pomocą algorytmu klastrowego i systemu ANOVA (analiza wariancji). Następnie przeprowadzono trening sieci neuronowej aby mogła posłużyć jako klasyfikator identyfikacji 5 różnych kształtów bioder. Przeciętna dokładność klasyfikacji proponowanego systemu wynosiła 97,37%, a efektywność była sukcesywnie sprawdzana przez porównanie schematów BP i SVM. W ten sposób stworzono inteligentny system rozpoznania typu kształtu bioder o dużej precyzji, pozwalający na oszczędność czasu.

8

Dimensionality Reduction for Probabilistic Neural Network in Medical Data Classification Problems

Kusy M.

International Journal of Electronics and Telecommunications

|

2015

|

Vol. 61, No. 3

289–300

EN

This article presents the study regarding the problem of dimensionality reduction in training data sets used for classification tasks performed by the probabilistic neural network (PNN). Two methods for this purpose are proposed. The first solution is based on the feature selection approach where a single decision tree and a random forest algorithm are adopted to select data features. The second solution relies on applying the feature extraction procedure which utilizes the principal component analysis algorithm. Depending on the form of the smoothing parameter, different types of PNN models are explored. The prediction ability of PNNs trained on original and reduced data sets is determined with the use of a 10-fold cross validation procedure.

9

Statistical testing of segment homogeneity in classification of piecewise-regular objects

Savchenko A. V., Belova N. S.

International Journal of Applied Mathematics and Computer Science

|

2015

|

Vol. 25, no. 4

915--925

EN

The paper is focused on the problem of multi-class classification of composite (piecewise-regular) objects (e.g., speech signals, complex images, etc.). We propose a mathematical model of composite object representation as a sequence of independent segments. Each segment is represented as a random sample of independent identically distributed feature vectors. Based on this model and a statistical approach, we reduce the task to a problem of composite hypothesis testing of segment homogeneity. Several nearest-neighbor criteria are implemented, and for some of them the well-known special cases (e.g., the Kullback–Leibler minimum information discrimination principle, the probabilistic neural network) are highlighted. It is experimentally shown that the proposed approach improves the accuracy when compared with contemporary classifiers.

10

Wykorzystanie probabilistycznych sieci neuronowych i sygnałów drganiowych do diagnozowania uszkodzeń wtryskiwaczy silnika ZS

Czech P.

Zeszyty Naukowe. Transport / Politechnika Śląska

|

2013

|

z. 81

25--30

PL

W przeprowadzonych badaniach podjęto próbę określenia występującego uszkodzenia wtryskiwaczy w silniku spalinowym samochodu. Za obiekt badań posłużył samochód Ford Mondeo, napędzany silnikiem ZS o pojemności 2,0 [dm3]. Do diagnozowania uszkodzenia wykorzystano sygnały drganiowe, generowane przez silnik – wstępnie przetworzone przy wykorzystaniu dyskretnej transformaty falkowej, oraz probabilistyczne sieci neuronowe. W artykule zaproponowano wykorzystanie analizy DWT oraz energii lub entropii, będących podstawą systemu diagnozującego.

EN

Conducted tests attempted to determine the occurring damage of fuel injectors in car combustion engine. Test object was Ford Mondeo car powered by diesel engine with capacity of 2.0 [dm3]. In order to diagnose the damage the vibration signals generated by the engine were used – initially processed with the use of discrete wavelet transform and probabilistic neural networks. In this article is proposed using DWT analysis and energy or entropy which are a base for diagnostic system.

11

Image processing and database architecture for Intelligent Transportation Systems

Anagnostopoulos C., Anagnostopoulos J., Kayafas E., Loumos V.

Image Processing & Communications

|

2002

|

Vol. 8, no 2

93-103

EN

This paper presents in detail all the relevant components required for the design of a real-time traffic Intelligent Transportation System (ITS). Specifically, the paper addresses analytically hardware and software issues such as the image acquisition module, the image processing routines, the OCR engine using Artificial Neural Network (ANN) technology and the database management system (DBMS). The image-processing algorithm, which is the software core of the system, works in different natural backgrounds, angles of vision and a wide range of illumination conditions and additionally it is plate-format independent. Following image processing, the OCR engine presented high level of accuracy and the total performance of the identification system is 92,5% on the basis of ITS standards. The benefits of such systems and their potential applications are discussed in the final section, where situations in which non-trivial problems can be solved by using such an artificial vision system are highlighted.