scholarly journals Using the Quantization Error from Self-Organizing Map (SOM) Output for Fast Detection of Critical Variations in Image Time Series

2018 ◽  
Author(s):  
Birgitta Dresp-Langley ◽  
John Mwangi Wandeto ◽  
Henry Okola Nyongesa
Keyword(s):  
Time Series ◽  
Linear Trend ◽  
Satellite Image ◽  
Quantization Error ◽  
Environmental Data ◽  
Self Organizing Map ◽  
Statistical Decision ◽  
Fast Analysis ◽  
Image Series ◽  
Self Organizing

The quantization error (QE) from Self-Organizing Map (SOM) output after learning is exploited in this studies. SOM learning is applied on time series of spatial contrast images with variable relative amount of white and dark pixel contents, as in monochromatic medical images or satellite images. It is proven that the QE from the SOM output after learning provides a reliable indicator of potentially critical changes in images across time. The QE increases linearly with the variability in spatial contrast contents of images across time when contrast intensity is kept constant. The hitherto unsuspected capacity of this metric to capture even the smallest changes in large bodies of image time series after using ultra-fast SOM learning is illustrated on examples from SOM learning studies on computer generated images, MRI image time series, and satellite image time series. Linear trend analysis of the changes in QE as a function of the time an image of a given series was taken gives proof of the statistical reliability of this metric as an indicator of local change. It is shown that the QE is correlated with significant clinical, demographic, and environmental data from the same reference time period during which test image series were recorded. The findings show that the QE from SOM, which is easily implemented and requires computation times no longer than a few minutes for a given image series of 20 to 25, is useful for a fast analysis of whole series of image data when the goal is to provide an instant statistical decision relative to change/no change between images.

Degradation assessment of ball bearings utilizing curvilinear component analysis

2018 ◽  
Vol 233 (3) ◽  
pp. 714-730 ◽  
Author(s):  
Prashant Tiwari ◽  
SH Upadhyay
Keyword(s):  
Feature Space ◽  
Component Analysis ◽  
Performance Degradation ◽  
Quantization Error ◽  
Mapping Technique ◽  
Nonlinear Mapping ◽  
Ball Bearings ◽  
Self Organizing Map ◽  
Feature Vectors ◽  
Self Organizing

The performance degradation assessment of ball bearings is of great importance to increase the efficiency and the reliability of rotating mechanical systems. The large dimensionality of feature space introduces a lot of noise and buries the potential information about faults hidden in the feature data. This paper proposes a novel health assessment method facilitated with two compatible methods, namely curvilinear component analysis and self-organizing map network. The novelty lies in the implementation of a vector quantization approach for the sub-manifolds in the feature space and to extract the fault signatures through nonlinear mapping technique. Curvilinear component analysis is a nonlinear mapping tool that can effectively represent the average manifold of the highly folded information and further preserves the local topology of the data. To answer the complications and to accomplish reliability and accuracy in bearing performance degradation assessment, the work is carried out with following steps; first, ensemble empirical mode decomposition is used to decompose the vibration signals into useful intrinsic mode functions; second, two fault features i.e. singular values and energy entropies are extracted from the envelopes of the intrinsic mode function signals; third, the extracted feature vectors under healthy conditions, further reduced with curvilinear component analysis are used to train the self-organizing map model; finally, the reduced test feature vectors are supplied to the trained self-organizing map and the confidence value is obtained. The effectiveness of the proposed technique is validated on three run-to-failure test signals with the different type of defects. The results indicate that the proposed technique detects the weak degradation earlier than the widely used indicators such as root mean square, kurtosis, self-organizing map-based minimum quantization error, and minimum quantization error-based on the principal component analysis.

Performance Analysis Using a Deep Belief Network by a Self-Organizing Map

2021 ◽  
pp. 2150007
Author(s):  
Yongquan Yan ◽  
Yu Zhu ◽  
Yanjun Li
Keyword(s):  
Neural Networks ◽  
Linear Trend ◽  
Time Series Prediction ◽  
Resource Consumption ◽  
Series Data ◽  
Self Organizing Map ◽  
Software Aging ◽  
Existing Problems ◽  
Consumption Prediction ◽  
Self Organizing

Since resource consumption is the main reason for software aging occurrences, many methods have been applied to accurately predict the resource consumption series. Among these methods, neural networks are powerfully applied to forecast the series data. For some existing problems of artificial neural networks such as the choice of initialization and local optimization, the improvements of neural networks are not only a hot research topic in the field of time series prediction but also a research hotspot in resource consumption prediction of software aging. In this paper, we propose a method for resource consumption prediction of software aging using deep belief nets (DBNs) with the restricted Boltzmann machine (RBM). This presented method contains the following steps. First, a pre-processing is introduced by two parts: smoothing data by a self-organizing map (SOM) and removing a linear trend by a difference method. Second, a method, DBN with two RBMs, is presented to capture the features and forecast future values. Third, a glowworm swarm optimization (GSO) method is used to learn the hyper-parameters of DBN with two RBMs. In the experiments, two types of resource consumption series are used to validate our proposed method compared with some state-of-the-art algorithms.

scholarly journals HYBRID MODEL OF SELF-ORGANIZING MAP AND ADAPTIVE NEURO FUZZY INFERENCE SYSTEM IN STOCK INDEXES FORECASTING

2021 ◽  
Vol 9 (2) ◽  
pp. 70-80
Author(s):  
M. Kushnir ◽  
K. Tokarieva
Keyword(s):  
Time Series ◽  
Stock Market ◽  
Stock Prices ◽  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Financial Time Series ◽  
Self Organizing Map ◽  
Inference System ◽  
Neuro Fuzzy ◽  
Self Organizing

The paper investigates methods of artificial intelligence in the prognostication and analysis of financial data time series. It is uncovered that scholars and practitioners face some difficulties in modelling complex system such as the stock market because it is nonlinear, chaotic, multi- dimensional, and spatial in nature, making forecasting a complex process. Models estimating nonstationary financial time series may include noise and errors. The relationship between the input and output parameters of the models is essentially non-linear, where stock prices include higher-level variables, which complicates stock market modeling and forecasting. It is also revealed that financial time series are multidimensional and they are influenced by many factors, such as economics, politics, environment and so on. Analysis and evaluation of multi- dimensional systems and their forecasting should be carried out by machine learning models. The problem of forecasting the stock market and obtaining quality forecasts is an urgent task, and the methods and models of machine learning should be the main mathematical tools in solving the above problems. First, we proposed to use self-organizing map, which is used to visualize multidimensional data by configuring neurons to quantize or cluster the input space in the topological structure. These characteristics of this algorithm make it attractive in solving many problems, including clustering, especially for forecasting stock prices. In addition, the methods discussed, encourage us to apply this cluster approach to present a different data structure for forecasting. Thus, models of adaptive neuro-fuzzy inference system combine the characteristics of both neural networks and fuzzy logic. Given the fact that the rule of hybrid learning and the theory of logic is a clear advantage of adaptive neuro-fuzzy inference system, which has computational advantages over other methods of parameter identification, we propose a new hybrid algorithm for integrating self-organizing map with adaptive fuzzy inference system to forecast stock index prices. This algorithm is well suited for estimating the relationship between historical prices in stock markets. The proposed hybrid method demonstrated reduced errors and higher overall accuracy.

Sign in / Sign up

Export Citation Format

Share Document