scholarly journals Nonlinear Representation of the Quasi-Biennial Oscillation

2009 ◽  
Vol 66 (7) ◽  
pp. 1886-1904 ◽  
Author(s):  
Bei-Wei Lu ◽  
Lionel Pandolfo ◽  
Kevin Hamilton
Keyword(s):  
Principal Component Analysis ◽  
Principal Component ◽  
Component Analysis ◽  
Test Bed ◽  
Feed Forward Neural Network ◽  
Quasi Biennial Oscillation ◽  
Wind Variability ◽  
Hidden Layer ◽  
Hemisphere Winter ◽  
Biennial Oscillation

Abstract A nonlinear principal component analysis (NLPCA) is applied to monthly mean zonal wind observations from January 1956 through December 2007 taken at seven pressure levels between 10 and 70 hPa in the stratosphere near the equator to represent the well-known quasi-biennial oscillation (QBO) and investigate its variability and structure. The NLPCA is conducted using a simplified two–hidden layer feed-forward neural network that alleviates the problems of nonuniqueness of solutions and data overfitting that plague nonlinear techniques of principal component analysis. The QBO is used as a test bed for the new compact model of NLPCA. The two nonlinear principal components of the dataset of the equatorial stratospheric zonal winds, determined by the compact NLPCA, offer a clear picture of the QBO. In particular, their structure shows that the QBO phase consists of a predominant 28.3-month cycle that is modulated by an 11-yr cycle as well as by longer cycles. The differences in wind variability between westerly and easterly regimes and between Northern Hemisphere winter and summer seasons and the tendency for a seasonal synchronization of the QBO phases are well captured.

scholarly journals Aircraft Engine Prognostics Based on Informative Sensor Selection and Adaptive Degradation Modeling with Functional Principal Component Analysis

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 920
Author(s):  
Bin Zhang ◽  
Kai Zheng ◽  
Qingqing Huang ◽  
Song Feng ◽  
Shangqi Zhou ◽  
...  
Keyword(s):  
Principal Component Analysis ◽  
Principal Component ◽  
Aircraft Engine ◽  
Component Analysis ◽  
Sensor Selection ◽  
Functional Principal Component Analysis ◽  
Test Bed ◽  
Future Health ◽  
Degradation Modeling ◽  
Functional Principal Component

Engine prognostics are critical to improve safety, reliability, and operational efficiency of an aircraft. With the development in sensor technology, multiple sensors are embedded or deployed to monitor the health condition of the aircraft engine. Thus, the challenge of engine prognostics lies in how to model and predict future health by appropriate utilization of these sensor information. In this paper, a prognostic approach is developed based on informative sensor selection and adaptive degradation modeling with functional data analysis. The presented approach selects sensors based on metrics and constructs health index to characterize engine degradation by fusing the selected informative sensors. Next, the engine degradation is adaptively modeled with the functional principal component analysis (FPCA) method and future health is prognosticated using the Bayesian inference. The prognostic approach is applied to run-to-failure data sets of C-MAPSS test-bed developed by NASA. Results show that the proposed method can effectively select the informative sensors and accurately predict the complex degradation of the aircraft engine.

scholarly journals Exploration of machine learning methods for the classification of infrared limb spectra of polar stratospheric clouds

2020 ◽  
Vol 13 (7) ◽  
pp. 3661-3682
Author(s):  
Rocco Sedona ◽  
Lars Hoffmann ◽  
Reinhold Spang ◽  
Gabriele Cavallaro ◽  
Sabine Griessbach ◽  
...  
Keyword(s):  
Machine Learning ◽  
Principal Component Analysis ◽  
Infrared Spectra ◽  
Principal Component ◽  
Component Analysis ◽  
Support Vector ◽  
Polar Stratospheric Clouds ◽  
Hemisphere Winter ◽  
Stratospheric Clouds ◽  
Polar Ozone

Abstract. Polar stratospheric clouds (PSCs) play a key role in polar ozone depletion in the stratosphere. Improved observations and continuous monitoring of PSCs can help to validate and improve chemistry–climate models that are used to predict the evolution of the polar ozone hole. In this paper, we explore the potential of applying machine learning (ML) methods to classify PSC observations of infrared limb sounders. Two datasets were considered in this study. The first dataset is a collection of infrared spectra captured in Northern Hemisphere winter 2006/2007 and Southern Hemisphere winter 2009 by the Michelson Interferometer for Passive Atmospheric Sounding (MIPAS) instrument on board the European Space Agency's (ESA) Envisat satellite. The second dataset is the cloud scenario database (CSDB) of simulated MIPAS spectra. We first performed an initial analysis to assess the basic characteristics of the CSDB and to decide which features to extract from it. Here, we focused on an approach using brightness temperature differences (BTDs). From both the measured and the simulated infrared spectra, more than 10 000 BTD features were generated. Next, we assessed the use of ML methods for the reduction of the dimensionality of this large feature space using principal component analysis (PCA) and kernel principal component analysis (KPCA) followed by a classification with the support vector machine (SVM). The random forest (RF) technique, which embeds the feature selection step, has also been used as a classifier. All methods were found to be suitable to retrieve information on the composition of PSCs. Of these, RF seems to be the most promising method, being less prone to overfitting and producing results that agree well with established results based on conventional classification methods.

Performance Comparison between ANN and PCA Techniques for Road Signs Recognition

2013 ◽  
Vol 393 ◽  
pp. 611-616 ◽  
Author(s):  
Nursabillilah Mohd Ali ◽  
Yasir Mohd Mustafah ◽  
Nahrul Khair Alang Md Rashid
Keyword(s):  
Neural Network ◽  
Principal Component Analysis ◽  
Back Propagation ◽  
Principal Component ◽  
Component Analysis ◽  
Performance Comparison ◽  
Feed Forward Neural Network ◽  
Classification Rate ◽  
The Road ◽  
Road Signs

This study reports about a comparison in recognizing road signs between Neural Network and Principal Component Analysis (PCA). The road sign with circular, triangular, octagonal and diamond shapes have been used in this study. Two recognition systems to determine the classes of the road signs class were implemented which are based on Feed Forward Neural Network and Principal Component Analysis (PCA). The performance of the trained classifier using Scaled Conjugate Gradient (SCG) back propagation function in Neural Network and PCA technique were evaluated on our test datasets. The experiments show that the system using PCA has a higher accuracy as compared to Neural Network with a minimum of 94% classification rate of road signs.

Nonlinear Autoassociation Is Not Equivalent to PCA

2000 ◽  
Vol 12 (3) ◽  
pp. 531-545 ◽  
Author(s):  
Nathalie Japkowicz ◽  
Stephen José Hanson ◽  
Mark A. Gluck
Keyword(s):  
Neural Network ◽  
Principal Component Analysis ◽  
Principal Component ◽  
Component Analysis ◽  
Reconstruction Error ◽  
Network Community ◽  
Error Surface ◽  
Nonlinear Classification ◽  
The Neural Network ◽  
Hidden Layer

A common misperception within the neural network community is that even with nonlinearities in their hidden layer, autoassociators trained with backpropagation are equivalent to linear methods such as principal component analysis (PCA). Our purpose is to demonstrate that nonlinear autoassociators actually behave differently from linear methods and that they can outperform these methods when used for latent extraction, projection, and classification. While linear autoassociators emulate PCA, and thus exhibit a flat or unimodal reconstruction error surface, autoassociators with nonlinearities in their hidden layer learn domains by building error reconstruction surfaces that, depending on the task, contain multiple local valleys. This interpolation bias allows nonlinear autoassociators to represent appropriate classifications of nonlinear multimodal domains, in contrast to linear autoassociators, which are inappropriate for such tasks. In fact, autoassociators with hidden unit nonlinearities can be shown to perform nonlinear classification and nonlinear recognition.

scholarly journals PENGENALAN WAJAH DUA DIMENSI MENGGUNAKAN MULTI-LAYER PERCEPTRON BERDASARKAN NILAI PCA DAN LDA

2013 ◽  
Vol 2 (1) ◽  
Author(s):  
Shofwatul Uyun ◽  
Muhammad Fadzlur Rahman
Keyword(s):  
Principal Component Analysis ◽  
Discriminant Analysis ◽  
Linear Discriminant Analysis ◽  
Principal Component ◽  
Component Analysis ◽  
Multi Layer Perceptron ◽  
Linear Discriminant ◽  
Output Layer ◽  
Input Layer ◽  
Hidden Layer

Manusia memiliki kecerdasan multi intelligence yang sangat kompleks sehingga secara otomatis mampu mengenali seseorang yang pernah ditemui. Saat ini banyak sekali sistem pengenalan wajah yang sedang dikembangkan baik secara supervised maupun unsupervised. Jaringan Syaraf Tiruan (JST) merupakan salah satu metode supervised, dimana salah satu metode pembelajarannya disebut dengan Multi-Layer Perceptron (MLP). Penentuan banyaknya node pada hidden layer secara tepat mempengaruhi kinerja dari MLP pada sistem pengenalan wajah. Penelitian ini menggunakan 12 citra wajah sebagai data latih yang diekstraksi menjadi covarian matriks lalu diambil nilai eigen dari setiap data citra menggunakan metode principal component analysis (PCA) dan linear discriminant analysis (LDA). Setiap data menghasilkan 4 nilai eigen yang menjadi masukan pada algoritma pelatihan MLP yang menghasilkan nilai bobot optimal yang menjadi acuan untuk mengenali citra wajah. Berdasarkan hasil pengujian dan perbandingan variasi nilai parameter yang digunakan untuk mengenali citra wajah telah didapatkan nilai akurasi optimal sebesar 77,77%. Aristektur dari MLP tersebut terdiri atas : 4 node di input layer, 8 node di hidden layer dan 3 node di output layer dengan nilai epoch pelatihan sebesar 60x104.

scholarly journals IDENTIFIKASI CITRA TANDA TANGAN BERDASARKAN GRID ENTROPY DAN PCA MENGGUNAKAN MULTI LAYER PERCEPTRON

2019 ◽  
Vol 1 (2) ◽  
pp. 89-96
Author(s):  
Muhammad Zidny Nafan ◽  
Agung Wisnu Anggoro ◽  
Elisa Usada
Keyword(s):  
Principal Component Analysis ◽  
Cross Validation ◽  
Principal Component ◽  
Component Analysis ◽  
Multi Layer Perceptron ◽  
Hidden Layer

Tanda tangan merupakan tanda yang bertujuan sebagai lambang dari nama seseorang yang dituliskan menggunakan tangan orang itu sendiri sebagai penanda pribadi. Penggunaan tanda tangan tidak luput dalam kehidupan sehari-hari, penting untuk mengenal bentuk tanda tangan seseorang untuk melakukan verifikasi apakah tnada tangan tersebut milik orang yang bersangkutan atau orang lain. Pada penelitian ini penulis membuat penelitian mengenai identifikasi tanda tangan dengan menggunakan Grid Entropy dan Principal Component Analysis sebagai ekstraksi ciri. Model pembelajaran dataset menggunakan Multi Layer Perceptron dan Cross Validation menggunakan nilai parameter yang berbeda pada hidden layer dan node dalam Multi Layer Perceptron. Hasil pengujian terbaik didapatkan dari pembelajaran dataset menggunakan 2 hidden layer dengan node sebanyak 40 node di setiap hidden layer, dari skenario tersebut didapatkan akurasi sebesar 87,22%.

scholarly journals Pengenalan Genus Diatom Menggunakan Principal Component Analysis dan Jaringan Saraf Tiruan Propagasi Balik Sebagai Classifier

2013 ◽  
Vol 2 (1) ◽  
pp. 38
Author(s):  
Silvia Rahmi ◽  
Toto Haryanto ◽  
Niken TM Pratiwi
Keyword(s):  
Principal Component Analysis ◽  
Principal Component ◽  
Component Analysis ◽  
Hidden Layer

Diatom merupakan suatu mikroalga unisel (kadang berkoloni) yang mempunyai peranan penting dalam dunia riset dan penelitian. Identifikasi diatom merupakan pekerjaan yang rumit. Hal ini dikarenakan diatom memiliki ratusan taksa dengan banyak variasi bentuk dan karakteristik biologi yang menyebabkan proses identifikasinya tidak mudah bahkan bagi seorang pakar. Penelitian ini menerapkan Principal Component Analysis (PCA) untuk reduksi data dan Jaringan Saraf Tiruan (JST) untuk identifikasi diatom. Proporsi PCA yang digunakan ialah 80% dan 90%. JST yang digunakan adalah propagasi balik dengan satu hidden layer. Data yang dipakai pada penelitian ini adalah citra diatom berformat JPG yang diambil menggunakan mikroskop elektrik. Hasil penelitian menunjukkan bahwa generalisasi terbaik sebesar 90% diperoleh pada percobaan menggunakan proporsi PCA 90% dengan persentase data latih 80%.

Drivability evaluation model using principal component analysis and optimized extreme learning machine

2019 ◽  
Vol 25 (16) ◽  
pp. 2274-2281 ◽  
Author(s):  
Wei Huang ◽  
Hai Jiang Liu ◽  
Yi Fei Ma
Keyword(s):  
Principal Component Analysis ◽  
Extreme Learning Machine ◽  
Evaluation Method ◽  
Evaluation Model ◽  
Principal Component ◽  
Component Analysis ◽  
Optimal Number ◽  
Pass Rate ◽  
Learning Machine ◽  
Hidden Layer

The accuracy of the evaluation method is essential to optimize the control system and improve a vehicle’s drivability quality. This study aimed at exploring a more effective drivability evaluation method and a drivability evaluation model was proposed on the basis of principal component analysis and optimization of an extreme learning machine. The drivability evaluation model was built using an extreme learning machine. The input of the model was determined by the principal component analysis method, and the optimal number of neurons in the hidden layer of the drivability evaluation model was obtained by a particle swarm optimization algorithm. The experimental results show that considering the evaluation index coupling factors can improve the prediction accuracy of the evaluation model. The R correlation between the score predicted by the drivability evaluation model proposed in this paper and the actual score reached 0.979, and the predicted pass rate also reached 95%, which indicate the model was more accurate and stable than others. The evaluation model can be extended to fuel economy and handling stability. It also has theoretical guidance and application value in practical problems.

Sign in / Sign up

Export Citation Format

Share Document