Principal Component Analysis Neural Network Research Articles

Geographical origin identification of Khao Dawk Mali 105 rice using combination of FT-NIR spectroscopy and machine learning algorithms

The mislabelled Khao Dawk Mali 105 rice coming from other geographical region outside the Thung Kula Rong Hai region is extremely profitable and difficult to detect; to prevent retail fraud (that adversely affects both the food industry and consumers), it is vital to identify geographical origin. Near infrared spectroscopy can be used to detect the specific content of organic moieties in agricultural and food products. The present study implemented the combinatorial method of FT-NIR spectroscopy with chemometrics to identify geographical origin of Khao Dawk Mali 105 rice. Rice samples were collected from 2 different region including the north and northeast of Thailand. NIR spectra data were collected in range of 12,500 – 4,000 cm−1 (800–2,500 nm). Five machine learning algorithms including linear discriminant analysis (LDA), partial least squares discriminant analysis (PLS-DA), C-support vector classification (C-SVC), backpropagation neural networks (BPNN), hybrid principal component analysis-neural network (PC-NN) and K-nearest neighbors (KNN) were employed to classify NIR data of rice samples with full wavelength and selected wavelength by Extremely Randomized Trees (Extra trees) algorithm. Based on the findings, geographical origin of rice could be specified quickly, cheaply, and reliably using combination of NIRS and machine learning. All models creating by full wavelength and selected wavelength exhibited accuracy between 65 and 100 % for identifying geographical region of rice. It was proven that NIR spectroscopy may be used for the quick and non-destructive identification of geographical origin of Khao Dawk Mali 105 rice.

Improved grey principal component analysis neural network based adaptive thermal comfort model: Application in the enclosed cabin with microclimatic conditions

Predicting the thermal comfort of operators in enclosed cabins under extreme operational conditions is crucial for the enhanced and optimal design of cabin air circulation systems. In this study, an improved supervised machine learning algorithm, namely a Grey Principal Component Analysis (G-PCA) was proposed to evaluate the operators’ thermal comfort. The comprehensive dataset was first attained and constructed from the proposed 32 indicators, which recorded each tested object’s EEG and physiological features, core body temperature, skin temperature, and subjective assessments. The accuracy of the proposed model was demonstrated by comparing it with the results predicted via existing indicator sets (PMV and 7-point skin temperature) and modelling algorithms (BP and PCA BP). The results showed that the prediction accuracy of the PMV model, 7-point skin temperature, the 32 indicators were found to be 79.4%, 82.8%, 96.1%, utilising the G-PCA WNN algorithm, and the prediction accuracy of BP, PCA BP, G-PCA WNN is 82.3%, 89.9%, 96.1%, based on the 32 indicators. A conclusion could be drawn that the proposed 32 indicators can incorporate a more comprehensive range of thermal comfort information, and the improved G-PCA WNN thermal comfort prediction model achieved the best prediction performance among the compared algorithms and models.

Evaluation of mine water quality based on the PCA–PSO–BP model

Abstract To enhance the mining area's overall use of mine water in the arid area of Western China and mitigate the current water scarcity problem, this paper introduces an intelligent optimization algorithm and neural network for mine water quality evaluation and proposes a principal component analysis (PCA)–particle swarm optimization (PSO)–back propagation (BP) mine water quality evaluation model. Firstly, the model uses PCA to identify the primary factors affecting mine water quality, then enhances the optimal weights and thresholds of the BP neural network based on the PSO algorithm, and the PCA–PSO–BP evaluation model with nine input layers, nine hidden layers, and one output layer is created. In addition, using the Shicaocun Mine as an example, the results demonstrate that the PCA–PSO–BP model has accurate mine water quality evaluation results, and the prediction accuracy reached 86.8255%. This exemplifies the PSO method's superiority to the BP neural network improvement. This study not only offers a novel theoretical framework for assessing and forecasting water quality in mining regions, but it also sets the stage for the possible broad use of state-of-the-art neural networks and optimization algorithms in the coal mining industry.

Data driven reduced modeling for fluidized bed with immersed tubes based on PCA and Bi-LSTM neural networks

The fast and accurate reduced-order modeling of fluidized beds is a challenging task in the field of fluid dynamics, owing to their high dimensionality and nonlinear dynamic behavior. In this study, a nonintrusive reduced order modeling method, the reduced order model based on principal component analysis and bidirectional long short-term memory networks (PBLSTM ROM), was developed to capture complex spatio-temporal dynamics of fluidized beds. By combining principal component analysis and Bidirectional long- short-term memory networks, the PBLSTM ROM effectively extracted dynamic evolution information without any prior knowledge of governing equations, enabling reduced-order modeling of unsteady flow fields. The PBLSTM ROM was validated using the solid volume fraction and gas velocity flow fields of a fluidized bed with immersed tubes, showing superior performance over both the PLSTM and PANN ROMs in accurately capturing temporal changes in the fluidization fields, especially in the region near immersed tubes where severe fluctuations appear. Moreover, the PBLSTM ROM improved the simulation speed by five orders of magnitude compared to traditional computational fluid dynamics simulations. These findings suggest that the PBLSTM ROM presents a promising approach for analyzing the complex fluid flows in engineering practice.

An Integrated Kernel PCA Neural Network and EGM for Number of Sources Estimation in Wireless Communication

The present work argues estimating number of sources in communication system using an integrated model of Principal Component Analysis (PCA) neural network and kernel method to produce Eigenvalue Grads Method (EGM). The essential advantage of this new suggested model is that, PCA neural is used to determine the covariance matrix instead of the traditional computation process which is time consuming. Simulation outcomes of this adopted model demonstrate wonderful responses through effectiveness, fast converge speed for (PCA) neural network, as well as achieving correct number of sources.

Reliability analysis of slope stability by neural network (NN), principal component analysis (PCA), and transfer learning (TL) techniques

The prediction of slope stability is considered as one of the critical concerns in geotechnical engineering. Conventional stochastic analysis with spatially variable slopes is time-consuming and highly computation-demanding. To assess the slope stability problems with a more desirable computational effort, many machine learning (ML) algorithms have been proposed. However, most ML-based techniques require that the training data must be in the same feature space and have the same distribution, and the model may need to be rebuilt when the spatial distribution changes. This paper presents a new ML-based algorithm, which combines the principal component analysis (PCA)-based neural network (NN) and transfer learning (TL) techniques (i.e. PCA–NN–TL) to conduct the stability analysis of slopes with different spatial distributions. The Monte Carlo coupled with finite element simulation is first conducted for data acquisition considering the spatial variability of cohesive strength or friction angle of soils from eight slopes with the same geometry. The PCA method is incorporated into the neural network algorithm (i.e. PCA-NN) to increase the computational efficiency by reducing the input variables. It is found that the PCA-NN algorithm performs well in improving the prediction of slope stability for a given slope in terms of the computational accuracy and computational effort when compared with the other two algorithms (i.e. NN and decision trees, DT). Furthermore, the PCA–NN–TL algorithm shows great potential in assessing the stability of slope even with fewer training data.

A Hybrid Model Using PCA and BP Neural Network for Time Series Prediction in Chinese Stock Market with TOPSIS Analysis

The stock price changes rapidly and is highly nonlinear in the financial market. One of the common concerns of many scholars and investors is how to accurately predict the stock price and the trend of rising and falling in a short time. Machine learning and deep learning techniques have found their place in financial institutions thanks to the ability of time series data prediction with high precision. However, the prediction accuracy of these models is still far from satisfactory. Most existing studies use original, single prediction algorithms that cannot overcome inherent limitations. This study proposes a hybrid model using principal component analysis (PCA) and backpropagation (BP) neural networks. The historical records of China Merchants Bank are used for data collection from 2015 to 2021. PCA preprocesses the original data to reduce the dimensionality and is then adopted by the BP neural network to predict the stock closing price of China Merchants Bank. We compare and analyze the PCA–BP model with three training algorithms, and the results indicate that the Bayesian regularization algorithm performs best. Besides, we perform the stock prediction using a traditional exponential smoothing approach. The experiment results show that the predicted stock closing price is close to the actual value, and the mean absolute percentage error can reach 0.0130, which is more significant than the traditional approach. Furthermore, A TOPSIS approach is utilized to evaluate the robustness of the proposed model. Finally, we demonstrate the usability of the designed hybrid model by predicting the stock price of another selected stock.

Monitoring of salinity of water on the THA CHIN River basin using portable Vis-NIR spectrometer combined with machine learning algorithms

The goal of this work is to study the alternative practices for monitoring the salinity of water using a combination of portable vis-NIR spectrometer and machine learning approachs. Along 80 km of the Tha Chin River basin from the Gulf of Thailand, the data of salinity and NIR spectrum were collected during winter and summer seasons of Thailand. Salinity of water samples was measured by using a handheld electrical conductivity meter and NIR spectra was recorded with portable FQA-NIR GUN in the wavelength range of 600 to 1100 nm. The 10 machine learning models including partial least square regression (PLS), support vector machine (SVR), decision tree (DT), random forest (RF), adaptive boosting (AB), gradient boosting (GB), bagging meta-estimator (BME), extremely randomized trees (ERT), backpropagation neural networks (BPNN) and hybrid principal component analysis-neural network (PCNN) were applied to train the NIRs models for predicting salinity. All machine learning algorithms showed good prediction results which Rp2 values were higher than 0.84. The models built by tree-based algorithms (DT, RF, AB, GB, BME and ERT) displayed higher performances of calibration set and prediction set than those of PLS, SVM, BPNN and PCNN. Among these, the ERT algorithm showed the best performance Rp2 of 0.97, RMSEP of 0.41 g/L and RPD of 6.00. It was shown that NIR spectroscopy coupled with machine learning could be an alternative simpler way for predicting salinity of water.

Determination of monophenolase activity based on backpropagation neural network analysis of three-dimensional fluorescence spectroscopy

Tyrosinase is pivotal for melanin formation. Measuring monophenolase activity is of great importance for both fundamental research and industrial applications. For the first time, a backpropagation (BP) artificial neural network with three-dimensional fluorescence spectroscopy was applied for the real-time determination of tyrosinase monophenolase activity. Principal component analysis (PCA) was utilized for the dimension reduction of three-dimensional fluorescence data. The four principal components served as inputs for the neural network. Network parameters were optimized using a genetic algorithm (GA). BP learning algorithm was applied to train the network model to determine tyrosine levels in a binary mixture containing tyrosine and L-DOPA without any chemical separation. The time course of tyrosine consumption by monophenolase was determined to calculate the initial velocity of the enzymatic reaction. The limit of detection of the monophenolase assay was 0.0615 U·mL−1. This combined strategy of PCA, GAs, and BP artificial neural networks for three-dimensional fluorescence spectroscopy was efficient for the real-time and in-situ determination of monophenolase activity in a cascade reaction.

A 3D attention U-Net network and its application in geological model parameterization

To solve the problems of convolutional neural network–principal component analysis (CNN-PCA) in fine description and generalization of complex reservoir geological features, a 3D attention U-Net network was proposed not using a trained C3D video motion analysis model to extract the style of a 3D model, and applied to complement the details of geologic model lost in the dimension reduction of PCA method in this study. The 3D attention U-Net network was applied to a complex river channel sandstone reservoir to test its effects. The results show that compared with CNN-PCA method, the 3D attention U-Net network could better complement the details of geological model lost in the PCA dimension reduction, better reflect the fluid flow features in the original geologic model, and improve history matching results.

An Index for Rail Weld Health Assessment in Urban Metro Using In-Service Train

Rail welds are considered as the weak part of a railway track. Their defects and health can directly affect wheel-rail interaction, track safety, and reliability. Current practices for rail welds health assessment are based on 2D vertical and lateral wear measurement which needs time and track blocking. The development of inertia-based condition monitoring methods such as measuring axle box acceleration (ABA) comes with a crucial question on criteria or index for each rail track component health monitoring. In this study, an index for evaluation of rail weld health is proposed through integrated numerical and field experiment data within a metro line using the ABA technique. The relationship between the speed, wheel structural vibration, and acceleration amplitude is investigated using fast Fourier transformation (FFT) and a nonlinear neural network principal component analysis (PCA) model. An index is introduced to assess weld severity level based on the statistical method. This index is simple and applicable for maintenance practice.

Automatic Scoring of Spoken English Based Principal Component Analysis and Convolutional Neural Network

Using computers to help people practice spoken language is a common method, but there are currently some problems. Firstly, because fluency feature is calculated depending on expert knowledge, the key information contained in the original data set may be lost. Secondly, optimize each model’s parameters separately to make the model’s performance in sub-optimal state. In order to solve these problems, a spoken English fluency scoring method based on convolutional neural network is proposed, in order to make the feature extraction consider the short-, medium-, and long-term characteristics of speech signal; three convolution layers are superimposed in this paper, which jointly learns feature extraction and scoring models from the original time-domain signal input. In the feature extraction process, we applied principal component analysis to make useful data extraction of audio features. The experimental results show that the scoring results of the proposed method are more accurate.

An effective classification approach for big data with parallel generalized Hebbian algorithm

Advancements in information technology is contributing to the excessive rate of big data generation recently. Big data refers to datasets that are huge in volume and consumes much time and space to process and transmit using the available resources. Big data also covers data with unstructured and structured formats. Many agencies are currently subscribing to research on big data analytics owing to the failure of the existing data processing techniques to handle the rate at which big data is generated. This paper presents an efficient classification and reduction technique for big data based on parallel generalized Hebbian algorithm (GHA) which is one of the commonly used principal component analysis (PCA) neural network (NN) learning algorithms. The new method proposed in this study was compared to the existing methods to demonstrate its capabilities in reducing the dimensionality of big data. The proposed method in this paper is implemented using Spark Radoop platform.

Unsupervised Clustering in Epidemiological Factor Analysis

Background: The analysis of epidemiological data at an early phase of an epidemiological situation, when the confident correlation of contributing factors to the outcome has not yet been established, may present a challenge for conventional methods of data analysis. Objective: This study aimed to develop approaches for the early analysis of epidemiological data that can be effective in the areas with less labeled data. Methods: An analysis of a combined dataset of epidemiological statistics of national and subnational jurisdictions, aligned at approximately two months after the first local exposure to COVID-19 with unsupervised machine learning methods, including principal component analysis and deep neural network dimensionality reduction, to identify the principal factors of influence was performed. Results: The approach and methods utilized in the study allow to clearly separate milder background cases from those with the most rapid and aggressive onset of the epidemics. Conclusion: The findings can be used in the evaluation of possible epidemiological scenarios and as an effective modeling approach to identify possible negative epidemiological scenarios and design corrective and preventative measures to avoid the development of epidemiological situations with potentially severe impacts.

Application of Neural Network Algorithm Based on Principal Component Image Analysis in Band Expansion of College English Listening.

With the development of information technology, band expansion technology is gradually applied to college English listening teaching. This technology aims to recover broadband speech signals from narrowband speech signals with a limited frequency band. However, due to the limitations of current voice equipment and channel conditions, the existing voice band expansion technology often ignores the high-frequency and low-frequency correlation of the audio, resulting in excessive smoothing of the recovered high-frequency spectrum, too dull subjective hearing, and insufficient expression ability. In order to solve this problem, a neural network model PCA-NN (principal components analysis-neural network) based on principal component image analysis is proposed. Based on the nonlinear characteristics of the audio image signal, the model reduces the dimension of high-dimensional data and realizes the effective recovery of the high-frequency detailed spectrum of audio signal in phase space. The results show that the PCA-NN, i.e., neural network based on principal component analysis, is superior to other audio expansion algorithms in subjective and objective evaluation; in log spectrum distortion evaluation, PCA-NN algorithm obtains smaller LSD. Compared with EHBE, Le, and La, the average LSD decreased by 2.286 dB, 0.51 dB, and 0.15 dB, respectively. The above results show that in the image frequency band expansion of college English listening, the neural network algorithm based on principal component analysis (PCA-NN) can obtain better high-frequency reconstruction accuracy and effectively improve the audio quality.

Design and Research of Mathematics Teaching Intelligent Classroom Based on PCA-NN Algorithm.

With the increasing importance of mathematics in basic education, how to evaluate and analyze the intelligent effect of mathematics teaching classroom through scientific methods has become one of the indicators to evaluate the intelligent classroom. This paper studies the design and application of mathematics teaching intelligent classroom based on the PCA-NN (principal component analysis-neural network) algorithm. Firstly, this paper briefly describes the current research status of mathematics teaching intelligent classroom design and PCA-NN algorithm. Secondly, combined with the key factors of mathematics teaching, it formulates specific standards and puts forward an adaptive strategy of intelligent and personalized intelligent mathematics teaching classroom. Finally, the algorithm is verified by experiments. The results show that, for students with different mathematics basic levels, the mathematics teaching intelligent classroom based on the PCA-NN algorithm can effectively improve the quality of mathematics classroom teaching. Through the research on the factors such as teaching quality, effect, and interaction mode involved in the process of mathematics teaching classroom design, the intelligent classroom design factors affecting teaching quality are determined. This paper analyzes and studies the system from different angles. The research results provide some help for the current quality evaluation of classroom teaching and use the PCA-NN algorithm to make quantitative analysis and multivariate verification of mathematics classroom teaching effect.

Business performance assessment of small and medium-sized enterprises: Evidence from the Czech Republic

Business performance assessment is one of the basic tasks of management. Business performance can be assessed using a number of methods. The basic ones include financial analysis, Balanced Scorecard or Economic Value Added (EVA). The paper is focused on SME business performance assessment based on Economic Value Added, calculated using the INFA build-up model. According to this method, companies were divided into four categories. The first category included companies with a positive EVA value. The second category included companies with negative EVA, but with the economic result above the risk-free rate. The third category included companies with a positive economic result above the risk-free rate. The fourth category included companies with a negative economic result. The model did not include companies with negative equity. The input represented 15 predictors based on their financial statements. The data were normalized and all extreme values, likely caused by a data rewriting error, were removed. Company performance is visualized by comparing Principal Component Analysis and Kohonen neural networks. Compared to similar research, the methods are compared using the data that analyzes the performance of companies. Both methods made it possible to visualize the given task. With regard to the purpose of facilitating the interpretation of the results, for the given case, the use of PC seems to be more appropriate. AcknowledgmentThis study has been supported by the Technology Agency of the Czech Republic under project No TL01000349.

Low-complexity neural network based DOA estimation for wideband signals in massive MIMO systems

Massive multiple-input multiple-output (MIMO) has become one of the most promising technologies for wireless communication systems, in which the direction-of-arrival (DOA) plays an important role in interference cancellation and transmission reliability. However, the challenge of conventional wideband DOA estimation algorithms is that their high computational complexity brings great difficulties for their effective application in massive MIMO systems. In this paper, we propose a wideband low-complexity DOA estimation algorithm based on a principal component analysis (PCA) neural network for massive MIMO systems. First, a new criterion for constructing a focusing matrix is proposed to avoid complex angle pre-estimation. To further reduce the complexity of the eigenvalue decomposition (EVD), we propose a signal subspace estimation algorithm based on PCA, which uses only a limited amount of self-organizing learning to estimate the weights of the network and the signal subspace and does not require prior sample training. Moreover, to increase the estimation accuracy, we use the Akaike information criterion (AIC) to divide signal and noise subspaces accurately. The theoretical analysis and simulation results show that the computational complexity of the proposed algorithm is effectively reduced, and the angles of wideband sources can be accurately estimated in massive MIMO systems.

A new recognition method for oil pipeline leakage using PCA and SOM neural networks

Oils are mainly transported by pipe in long distance for its high efficiency. While oil pipe leakage will cause serious social and environmental consequences, e.g. fire even life lost, water and soil pollution. Thus it is important to recognize pipe leakage at initial stage in engineering practice. In this research, a negative pressure wave based detection method was established for pipeline leakage recognition. Suitable parameters of negative pressure wave signals with significant difference for different working conditions were selected. Principal Component Analysis (PCA) method was conducted to reduce the dimensions of the negative pressure wave vector. Self-organizing map (SOM) Neural network was finally adopted to identify the signals for different working conditions. The proposed method was validated by experimental data, which shows that the methodology gives a high recognition rate, which can be referenced in pipe monitoring in engineering practice.

Automatic Recognition of Geomagnetic Suitability Areas for Path Planning of Autonomous Underwater Vehicle

Currently, integrated navigation systems with the inertial navigation system (INS)/geomagnetic navigation system (GNS) have been widely used in underwater navigation of autonomous underwater vehicle (AUV). Restricting AUV to navigate in the geomagnetic suitability areas (GSA) as far as possible can effectively improve the accuracy of integrated navigation systems. In order to improve the classification accuracy of GSA, a new optimal classification method based on principal component analysis (PCA) and improved back propagation (BP) neural network is proposed. PCA is used to extract the independent characteristic parameters containing the main components. Then, considering similarity coefficient, the initial weights and thresholds of BP neural network is optimized by improved adaptive genetic algorithm (IAGA). Finally, the correspondence between the geomagnetic characteristic parameters and matching performance is established based on PCA and improved adaptive genetic algorithm and back propagation (IAGA-BP) neural network for the automatic recognition of GSA. Simulated experiments based on PCA and IAGA-BP neural network shows high classification accuracy and reliability in the GSA selection. The method could provide important support for AUV path planning, which is an effective guarantee for AUV high precision and long voyage autonomous navigation.