Principal Component Analysis Neural Network Research Articles

NEURAL NETWORK APPROACHES FOR INTRUSION DETECTION AND RECOGNITION

Most current Intrusion Detection Systems (IDS) examine all data features to detect intrusion. Also existing intrusion detection approaches have some limitations, namely impossibility to process large number of audit data for real-time operation, low detection and recognition accuracy. To overcome these limitations, we apply modular neural network models to detect and recognize attacks in computer networks. It is based on combination of principal component analysis (PCA) neural networks and multilayer perceptrons (MLP). PCA networks are employed for important data extraction and to reduce high dimensional data vectors. We present two PCA neural networks for feature extraction: linear PCA (LPCA) and nonlinear PCA (NPCA). MLP is employed to detect and recognize attacks using feature-extracted data instead of original data. The proposed approaches are tested using KDD-99 dataset. The experimental results demonstrate that the designed models are promising in terms of accuracy and computational time for real world intrusion detection.

Prediction of the Level of Air Pollution Using Principal Component Analysis and Artificial Neural Network Techniques: a Case Study in Malaysia

This study focused on the pattern recognition of Malaysian air quality based on the data obtained from the Malaysian Department of Environment (DOE). Eight air quality parameters in ten monitoring stations in Malaysia for 7 years (2005–2011) were gathered. Principal component analysis (PCA) in the environmetric approach was used to identify the sources of pollution in the study locations. The combination of PCA and artificial neural networks (ANN) was developed to determine its predictive ability for the air pollutant index (API). The PCA has identified that CH4, NmHC, THC, O3, and PM10 are the most significant parameters. The PCA-ANN showed better predictive ability in the determination of API with fewer variables, with R 2 and root mean square error (RMSE) values of 0.618 and 10.017, respectively. The work has demonstrated the importance of historical data in sampling plan strategies to achieve desired research objectives, as well as to highlight the possibility of determining the optimum number of sampling parameters, which in turn will reduce costs and time of sampling.

Use of Hyperspectral Imaging to Discriminate the Variety and Quality of Rice

This paper investigated the use of hyperspectral imaging (HSI) to discriminate the variety and quality of rice. Hyperspectral images (400–1,000 nm) of paddy rice samples were acquired to extract both spectral and image information. Dimension reduction was carried out on the region of interest (ROI) of the images by principal component analysis (PCA). The first principal components (PCs) explained over 98 % of variances of all spectral bands. Chalkiness degree and shape feature (‘MajorAxisLength’, ‘MinorAxisLength’, length-width ratio, ‘Perimeter’ and ‘Eccentricity’) were further extracted and used for subsequent rice variety discrimination by PCA and back propagation neural network (BPNN). An integration of spectral and image data was used for BPNN classification. The BPNN model based on spectral data (seven optimal wavelengths) achieved better results than PCA based on spectral data (seven optimal wavelengths) in variety discrimination with classification accuracy of 89.18 and 89.91 % for PCA and BPNN model, respectively. The BPNN model based on data fusion achieved the best results (94.45 %), which was superior to the results based on spectral data (89.91 %) or image data (88.09 %) alone. Finally, the resulting classification maps were able to visualize different rice varieties. The results demonstrated that discrimination of rice variety and quality with HSI technology was feasible and could be utilized for quality control purposes and/or for innovative sorting of rice.

UNSUPERVISED CLASSIFICATION OF CHROMATOGRAPHIC COLUMNS IN MICELLAR AND CONVENTIONAL REVERSED-PHASE HIGH-PERFORMANCE LIQUID CHROMATOGRAPHY

The classification of chromatographic columns with bonded octadecyl groups in conventional reversed-phase high-performance liquid chromatography (RP-HPLC) and in micellar liquid chromatography (MLC) was completed using unsupervised pattern recognition methods: principal component analysis, cluster analysis, and self-organized Kohonen neural networks (KNN). KNN provided an unbiased classification of the chromatographic columns and can be used as a powerful tool for columns selection in routine analysis. Despite the covering of C18 bonded silica surface of stationary phase with surfactant monomers in MLC, which strongly affect the compounds retention, the selectivity of the test compounds separation in MLC as well as in conventional RP-HPLC is affected by the sorbent properties. Thus, elucidation of columns similarity in both HPLC modes is of primary importance for developing robust analytical methods and selection of the analogous sorbents.

Classification and identification of soot source with principal component analysis and back-propagation neural network

Identification of soot sources is significant in fire investigation and forensic science. In this paper, principal component analysis (PCA) and a back-propagation (BP) neural network model have been used to classify and identify the soot samples from three different kinds of combustible material. Diesel, polystyrene and acrylonitrile butadiene styrene were burnt under the controlled combustion conditions in small-scale burn tests. Based on the matrix data from the GC-MS analysis data, two principal components have been obtained from PCA analysis with the cumulative energy content of 90.21%. Three different kinds of soot sample can be classified with 100% accuracy. A BP neural network model for predicting and identifying the soot source has been further developed. Accurate identification of the unknown samples has been achieved with this trained BP model. This pilot study indicates that PCA and BP neural network methods have potential in the analysis of soot to identify its principle pre-combustion source material.

The Design of New Soft Sensors Based on PCA and a Neural Network for Parameters Estimation of a Petroleum Reservoir

A new set of soft sensors is presented based on principal component analysis (PCA) and artificial neural network (ANN) methodologies for parameters estimation of a petroleum reservoir. The crude diagrams of reservoir parameters provide valuable evaluation for petrophysical parameters. These parameters, however, are usually difficult to measure due to limitations on cost reliability considerations, inappropriate instrument maintenance, and sensor failures. PCA is utilized to develop new soft sensors to incorporate reliability and prediction capabilities of ANN. For this purpose, a PCA model is derived to reconstruct a parameter from other reservoir parameters using their redundancy relations. The developed soft sensors are applied to reconstruct parameters of Marun reservoir located in Ahwaz, Iran, by utilizing the available geophysical well log data. The experimental results demonstrate that the proposed hybrid PCA-NN algorithm is able to reveal a better performance than the PCA and the conventional back propagation–based NNs.

Power Transformer Differential Protection Based on Neural Network Principal Component Analysis, Harmonic Restraint and Park's Plots

This paper describes a new approach for power transformer differential protection which is based on the wave-shape recognition technique. An algorithm based on neural network principal component analysis (NNPCA) with back-propagation learning is proposed for digital differential protection of power transformer. The principal component analysis is used to preprocess the data from power system in order to eliminate redundant information and enhance hidden pattern of differential current to discriminate between internal faults from inrush and overexcitation conditions. This algorithm has been developed by considering optimal number of neurons in hidden layer and optimal number of neurons at output layer. The proposed algorithm makes use of ratio of voltage to frequency and amplitude of differential current for transformer operating condition detection. This paper presents a comparative study of power transformer differential protection algorithms based on harmonic restraint method, NNPCA, feed forward back propagation neural network (FFBPNN), space vector analysis of the differential signal, and their time characteristic shapes in Park’s plane. The algorithms are compared as to their speed of response, computational burden, and the capability to distinguish between a magnetizing inrush and power transformer internal fault. The mathematical basis for each algorithm is briefly described. All the algorithms are evaluated using simulation performed with PSCAD/EMTDC and MATLAB.

Forecasting postage traffic using principal component analysis and artificial neural network

Predicting postage traffic and enhancing factors which affect postage traffic are some of the main concerns in postal services. In this paper, we present a combined approach based on principal component analysis (PCA) and artificial neural networks (ANN) for forecasting postage traffic. Due to the large available data set size, PCA is used to reduce the dimension and the required principal components (PCs) are selected based on the given rules. These PCs are then treated as inputs of an ANN to make forecasts for the postage traffic. Real data of Islamic Republic of Iran Postal Company is used to compare the results of the proposed model with that of the traditional regression model. Key words: Forecasting, artificial neural networks, principal component analysis.

Neural network model for transient ischemic attacks diagnostics

In this paper the neural network model for transient ischemic attacks (TIA) recognition is described. The proposed approach is based on integration of nonlinear principal component analysis (NPCA) neural network and multilayer perceptron (MLP). The data set from clinic was used for experiments performing. At combining the two different neural networks (NPCA and MLP) it is possible to produce efficient performance in terms of transient ischemic attacks detection and recognition. The main advantages of using the neural network techniques are the ability to recognize "novel" TIA instances, quickness and ability to assist a doctor in making decision.

Measuring Reflectance Spectra of Textile Fabrics by Scanner

This study presents a practical approach for estimation reflectance spectra by means of scanner. New methods were based on polynomial regression, neural network, neuro-fuzzy and principal component analysis techniques. Obtained results indicate that the recovery error decreases with increase number of principal component and number of terms in a polynomial. Also, application of principal component increase accuracy of reflectance measurement. The best estimation is obtained by principal component analysis and artificial neural network (PCA- ANNET) with 0.0297 RMS and 6.14 ?E*ab error.

Pharmacophore-based database mining for probing fragmental drug-likeness of diketo acid analogues

A number of the structurally diverse chemical compounds with functional diketo acid (DKA) subunit(s) have been revealed by combined online and MoStBiodat 3D pharmacophore-guided ZINC and PubChem database screening. We used the structural data available from such screening to analyse the similarities of the compounds containing the DKA fragment. Generally, the analysis by principal component analysis and self-organizing neural network approaches reveals four families of compounds complying with the chemical constitution (aromatic, aliphatic) of the compounds. From a practical point of view, similar studies may reveal potential bioisosteres of known drugs, e.g. raltegravir/elvitegravir. In this context, it seems that mono-halogenated aryl substructures with para group show the closest similarity to these compounds, in contrast to structures where the aromatic ring is halogenated in both ortho- and para-locations.

Structure-activity relationship analysis of 4'-bromo-[1,1'-biphenyl]-4-yl 4-X-phenyl methanone derivatives and activity against Mycobacterium tuberculosis.

Principal Component Analysis (PCA) and Artificial Neural Network (ANN) were used to analyze the relationship between the structure and the activities of a series of nine biphenyl-phenyl methanone derivatives against Mycobacterium tuberculosis in vitro. Both PCA and ANN were able to classify these derivatives in two categories: low active and highly active compounds. Empirical and theoretical descriptors were used in the classification process. The descriptors selected by PCA indicated that the reactivity plays an important role in the determination of antimycobacterial activity of biphenylphenyl methanone derivatives (BPM). The BPM showed a moderate activity against the M. tuberculosis strain tested with the exception of chloride-, bromide- and nitroderivatives (when X = Cl, Br, NO2) which were the most actives against M. tuberculosis in vitro among all the methanones studied.

Detection of XinyangMaojian Green Tea Quality and Age by Electronic Nose

In this work, the capacity of an electronic nose (E-nose, PEN2) to classify tea quality grades is investigated. Three tea groups with different quality grades were harvested at different times. Principal component analysis (PCA) and artificial neural network (ANN) were applied to identify the different tea samples. PCA provided perfect classification of tea quality grades. In the analysis of age, six groups of XinyangMaojian green tea were distinguished completely by PCA. The results of ANN analysis gave a high percentage of correct discrimination of green tea samples. The correct identification rates of the training and testing data were 98.6% and 83%, respectively, for three grades of green tea samples harvested in 2009. The correct identification rates of the training and testing data were 100% and 87.8%, respectively, for three grades of green tea samples harvested in 2010. In the analysis of age, the correct discrimination percentages for six groups of XinyangMaojian green tea were 99.4% and 88.9% for training and testing data, respectively. These results indicate that the electronic nose could be successfully used for the detection of teas of different quality grades and ages.

Research on Selecting Real Estate Project Based on PCA and RBF Neural Network

A new method based on the integration of principal component analysis (PCA) and radial basic function (RBF) neural network is put forward for selecting the real estate project. Firstly, principal component analysis (PCA) is used to reduce the evaluation index dimensions. And then, radial basic function (RBF) neural network is used to evaluate the real estate projects. In order to grasp this method better, finally, the paper provides a case to demonstrate the application of this method in selecting the real estate project. The case has shown that the method applied to select the real estate project is feasible and reliable.

Research on Selecting Public Investment Project Based on a Decision Support System

The paper presents a decision support system for selecting public investment project. Based on principal component analysis（PCA）and BP (Back Propagation, BP) neural network, and, with the help of software R, A decision support system for selecting public investment project is developed in this study. A case is used to demonstrate the application of this system.

Software Quality Prediction Method with Hybrid Applying Principal Components Analysis and Wavelet Neural Network and Genetic Algorithm

The principal components analysis method is used to select the training and testing data from software metrics to eliminate the multicollinearitiy in the original data and reduce the dimensions of the data, the genetic algorithm is applied to optimize the parameters of the constructed wavelet neural network, and then a novel software quality prediction model is proposed and its performance is evaluated. The experimental results with six error parameters show that the presented model combining principal components analysis with wavelet neural network and genetic algorithm can obtain better prediction accuracy than the models using the neural network of back propagation and generalized regression neural network.

Gas Mixture Recognition Method with New Hybrid Architecture

The quantification accuracy of the gas mixture recognizing is greatly dependent on the gas sensor array signal processing method. The paper reports the new hybrid architecture with two main stages for gas mixture recognition. The first stage combine the principal component analysis (PCA) and back propagation neural network (BPNN) to qualitative identify the gas mixture, and the second stage composed of the independent component analysis (ICA) and BP sub networks to quantify the gas concentrations. The hybrid architecture and three other commonly used methods of PCA+BPNN, ICA+BPNN, and ICA+BP sub networks were respectively applied in binary gas mixture quantification based on the same gas sensor array, and results show that the hybrid architecture has the lowest quantitative recognition errors and fast converge speed comparing with the other methods.

Adaptive multiple minor directions extraction in parallel using a PCA neural network

A principal component analysis (PCA) neural network is developed for online extraction of the multiple minor directions of an input signal. The neural network can extract the multiple minor directions in parallel by computing the principal directions of the transformed input signal so that the stability-speed problem of directly computing the minor directions can be avoided to a certain extent. On the other hand, the learning algorithms for updating the net weights use constant learning rates. This overcomes the shortcoming of the learning rates approaching zero. In addition, the proposed algorithms are globally convergent so that it is very simple to choose the initial values of the learning parameters. This paper presents the convergence analysis of the proposed algorithms by studying the corresponding deterministic discrete time (DDT) equations. Rigorous mathematical proof is given to prove the global convergence. The theoretical results are further confirmed via simulations.

A mixture neural methodology for computing rice consumptive water requirements in Fada N’Gourma Region, Eastern Burkina Faso

Crop consumptive water requirement (Crop-ET) is a key variable for developing management plans to optimize the efficiency of water use for crop production particularly in semiarid zone. In Burkina Faso, the unfavorable climatic conditions characterized by the low and unevenly distribution of rainfall have pushed water resources management to the forefront of the crop production issue. Crop-ET is extremely required in rainwater effective management for mitigating the impact of water deficit on the crops. Basically, Crop-ET determination involves reference evapotranspiration (ETo) and crop coefficient (Kc) which required complete climatic data and specific site crop information, respectively. ETo estimation with the recommended FAO56 Penman–Monteith (PM) equation is limited in Burkina Faso due to the numerous meteorological data required which are not always available in many production sites. In such circumstances, research to compute directly Crop-ET as an alternative to the two-step approach of calculating ETo and determining site specific Kc, seems desirable. Therefore, this study aims to evaluate the performance of a mixture principal component analysis neural network (PCANN) model for computing rice Crop-ET directly from temperatures data in Fada N’Gourma region located in Eastern Burkina Faso, Africa. From the statistical results, rice Crop-ET can be successfully computed by using PCANN methodology, when only temperatures data are available in this African semiarid environment. Thus, in poor data situation, Crop-ET direct computation can be rapidly addressed through PCANN model for agricultural water management in African semiarid regions.

A Family of Fuzzy Learning Algorithms for Robust Principal Component Analysis Neural Networks

In this paper, we analyze Xu and Yuille's robust principal component analysis (RPCA) learning algorithms by means of the distance measurement in space. Based on the analysis, a family of fuzzy RPCA learning algorithms is proposed, which is robust against outliers. These algorithms can explicitly be understood from the viewpoint of fuzzy set theory, though Xu and Yuille's algorithms were proposed based on a statistical physics approach. In the proposed algorithms, an adaptive learning procedure overcomes the difficulty of selection of learning parameters in Xu and Yuille's algorithms. Furthermore, the robustness of proposed algorithms is investigated by using the theory of influence functions. Simulations are carried out to illustrate the robustness of these algorithms.