Autoassociative Neural Network Research Articles

Effective analysis of malware detection in cloud computing

Cloud services are relied upon to be always on and have a significant nature; acordingly, security and versatility are progressively imperative perspectives. Accessing the cloud environment is performed via internet services in which information stored on cloud environment are easier to both internal and external Malwares. To detect intruders, a variety of malware detection systems were focused on machine learning techniques, which are not delivering major results based on detection rate. To overcome this drawback, we propose novel consolidated Weighted Fuzzy K-means clustering algorithm with Auto Associative Neural Network(WFCM-AANN). Our proposed classifier successfully identifies the malwares and it is obvious that the proposed framework can identify the anomalies with high detection precision thereby outperforming existing classifiers.

Gas path fault diagnostics using a hybrid intelligent method for industrial gas turbine engines

There are many challenges against an accurate gas turbine fault diagnostics, such as the nonlinearity of the engine health, the measurement uncertainty, and the occurrence of simultaneous faults. The conventional methods have limitations in effectively handling these challenges. In this paper, a hybrid intelligent technique is devised by integrating an autoassociative neural network (AANN), nested machine learning (ML) classifiers, and a multilayer perceptron (MLP). The AANN module is used as a data preprocessor to reduce measurement noise and extract the important features for visualisation and fault diagnostics. The features are extracted from the bottleneck layer output values based on the concept of the nonlinear principal component analysis (NLPCA). The nested classifier modules are then used in such a manner that fault and no-fault conditions, component and sensor faults, and different component faults are distinguished hierarchically. As part of the classification, evaluation of the fault classification performance of five widely used ML techniques aiming to identify alternative approaches is undertaken. In the end, the MLP approximator is utilised to estimate the magnitude of the isolated component faults in terms of flow capacity and isentropic efficiency indices. The developed system was implemented to diagnose up to three simultaneous faults in a two-shaft industrial gas turbine engine. Its robustness towards the measurement uncertainty was also evaluated based on Gaussian noise corrupted data. The test results show the derivable benefits of integrating two or more methods in engine diagnostics on the basis of offsetting the weakness of the one with the strength of another.

Performance-based fault diagnosis of a gas turbine engine using an integrated support vector machine and artificial neural network method

An effective and reliable gas path diagnostic method that could be used to detect, isolate, and identify gas turbine degradations is crucial in a gas turbine condition-based maintenance. In this paper, we proposed a new combined technique of artificial neural network and support vector machine for a two-shaft industrial gas turbine engine gas path diagnostics. To this end, an autoassociative neural network is used as a preprocessor to minimize noise and generate necessary features, a nested support vector machine to classify gas path faults, and a multilayer perceptron to assess the magnitude of the faults. The necessary data to train and test the method are obtained from a performance model of the case engine under steady-state operating conditions. The test results indicate that the proposed method can diagnose both single- and multiple-component faults successfully and shows a clear advantage over some other methods in terms of multiple fault diagnosis. Moreover, 5-8 sets of measurements have been used to assess the prediction accuracy, and only a 2.3% difference was observed. This result indicates that the proposed method can be used for multiple fault diagnosis of gas turbines with limited measurements.

Performance of Speaker Verification Using CSM and TM

In this paper, we presented the performance of a speaker verification system based on features computed from the speech recorded using a Close Speaking Microphone(CSM) and Throat Microphone(TM) in clean and noisy environment. Noise is the one of the most complicated problem in speaker verification system. The background noises affect the performance of speaker verification using CSM. To overcome this issue, TM is used which has a transducer held at the throat resulting in a clean signal and unaffected by background noises. Acoustic features are computed by means of Relative Spectral Transform-Perceptual Linear Prediction (RASTA-PLP). Autoassociative neural network (AANN) technique is used to extract the features and in order to confirm the speakers from clean and noisy environment. A new method is presented in this paper, for verification of speakers in clean using combined CSM and TM. The verification performance of the proposed combined system is significantly better than the system using the CSM alone due to the complementary nature of CSM and TM. It is evident that an EER of about 1.0% for the combined devices (CSM+TM) by evaluating the FAR and FRR values and the overall verification of 99% is obtained in clean speech.

Automatic Detection of Melanoma and Non Melanoma Skin Cancer: Using Classification Framework of Neural Network

In Automatic Detection of Melanoma and Non Melanoma skin Cancer, the relationship of skin cancer image across different type of neural network are studied with different types of preprocessing and compare the result with two method Discrete wavelet transformation and lifting wavelet transformation. The collected images are feed into the system, and across different image processing procedure to enhance the image properties. Then the normal skin is removed from the skin affected area and the cancer cell is left in the image. Useful information can be extracted from these images and pass to the classification system for training and testing. Recognition accuracy of the 3-layers back-propagation neural network classifier is 90.2% in LWT and 89.1% in DWT method. Auto-associative neural network is 81.2% in LWT method and 80.2% in DWT method .The image in database include dermoscopy photo and digital photo.

Concurrence of form and function in developing networks and its role in synaptic pruning

A fundamental question in neuroscience is how structure and function of neural systems are related. We study this interplay by combining a familiar auto-associative neural network with an evolving mechanism for the birth and death of synapses. A feedback loop then arises leading to two qualitatively different types of behaviour. In one, the network structure becomes heterogeneous and dissasortative, and the system displays good memory performance; furthermore, the structure is optimised for the particular memory patterns stored during the process. In the other, the structure remains homogeneous and incapable of pattern retrieval. These findings provide an inspiring picture of brain structure and dynamics that is compatible with experimental results on early brain development, and may help to explain synaptic pruning. Other evolving networks—such as those of protein interactions—might share the basic ingredients for this feedback loop and other questions, and indeed many of their structural features are as predicted by our model.

Collective variable discovery and enhanced sampling using autoencoders: Innovations in network architecture and error function design.

Auto-associative neural networks ("autoencoders") present a powerful nonlinear dimensionality reduction technique to mine data-driven collective variables from molecular simulation trajectories. This technique furnishes explicit and differentiable expressions for the nonlinear collective variables, making it ideally suited for integration with enhanced sampling techniques for accelerated exploration of configurational space. In this work, we describe a number of sophistications of the neural network architectures to improve and generalize the process of interleaved collective variable discovery and enhanced sampling. We employ circular network nodes to accommodate periodicities in the collective variables, hierarchical network architectures to rank-order the collective variables, and generalized encoder-decoder architectures to support bespoke error functions for network training to incorporate prior knowledge. We demonstrate our approach in blind collective variable discovery and enhanced sampling of the configurational free energy landscapes of alanine dipeptide and Trp-cage using an open-source plugin developed for the OpenMM molecular simulation package.

Improving corporate bond recovery rate prediction using multi-factor support vector regressions

In the multi-factor framework described in this paper, we use instrument-specific characteristics, several macroeconomic variables, and industry-specific characteristics as our explanatory variables for predicting recovery rates for corporate bonds. By including the principal components derived from a large number of macroeconomic variables, all three least-squares support vector regression methods, as well as the ordinary linear regression, exhibit higher out-of-sample predictive accuracy than the models that included only the few macroeconomic variables suggested in the literature. We compare the prediction accuracies of all techniques by incorporating sparse principal components, nonlinear principal components from an auto-associative neural network, and kernel principal components. Our results show that sparse principal components generate more interpretable and accurate estimations compared to the other principal component techniques. Moreover, we apply gradient boosting to generate a ranking of the 104 macroeconomic variables, from best to worst, based on their prediction power in recovery rate estimation. The three categories with the most informative macroeconomic predictors are micro-level factors, business cycle variables, and stock market indicators.

ЗАСОБИ ЗБЕРЕЖЕННЯ, ОПРАЦЮВАННЯ ТА ЗАХИСТУ ДАНИХ БАГАТОРІВНЕВОЇ СИСТЕМИ УПРАВЛІННЯ ЕНЕРГОЕФЕКТИВНІСТЮ РЕГІОНУ

Визначено, що для ефективного управління енергоефективністю багаторівнева система управління повинна забезпечувати збір енергетичних даних у реальному часі, створення єдиного інформаційного простору з достовірною, повною та оперативною інформацією, захист даних від несанкціонованого доступу, зберігання, опрацювання, аналіз накопичених даних, прогнозування енергоефективності, визначення шляхів зменшення технологічних і невиробничих втрат енергоресурсів. Розроблено структуру засобів збереження трирівневої системи управління енергоефективністю, у якій перший рівень використовують для збереження енергетичних даних від підприємств регіону, а другий та третій рівні – зберігають інформацію відповідно економічно-виробничого та технологічного характеру про діяльність підприємства. Розроблено структуру інформаційно-аналітичної системи, основними компонентами якої є засоби: ETL, збереження та захисту даних, аналітичного опрацювання, набування знань, інтелектуального аналізу даних, прогнозування енергоефективності, підтримки прийняття рішень і візуалізації. Вибрано підходи в інтеграції та консолідації даних і сформовано перелік задач для засобів опрацювання даних. Розроблено засоби захисту даних у сховищі від несанкціонованого доступу на базі нейромережевих технологій.

A visual familiarity account of evidence for orthographic processing in pigeons (Columbia livia): a reply to Scarf, Corballis, Güntürkün, and Colombo (2017).

Scarf et al. (Proc Natl Acad Sci 113(40):11272-11276, 2016) demonstrated that pigeons, as with baboons (Grainger et al. in Science 336(6078):245-248, 2012; Ziegler in Psychol Sci. https://doi.org/10.1177/0956797612474322 , 2013), can be trained to display several behavioural hallmarks of human orthographic processing. But, Vokey and Jamieson (Psychol Sci 25(4):991-996, 2014) demonstrated that a standard, autoassociative neural network model of memory applied to pixel maps of the words and nonwords reproduces all of those results. In a subsequent report, Scarf et al. (Anim Cognit 20(5):999-1002, 2017) demonstrated that pigeons can reproduce one more marker of human orthographic processing: the ability to discriminate visually presented four-letter words from their mirror-reversed counterparts (e.g. "LEFT" vs. " "). The current report shows that the model of Vokey and Jamieson (2014) reproduces the results of Scarf et al. (2017) and reinforces the original argument: the recent results thought to support a conclusion of orthographic processing in pigeons and baboons are consistent with but do not force that conclusion.

Two-Stage Approach to Image Classification by Deep Neural Networks

The paper demonstrates the advantages of the deep learning networks over the ordinary neural networks on their comparative applications to image classifying. An autoassociative neural network is used as a standalone autoencoder for prior extraction of the most informative features of the input data for neural networks to be compared further as classifiers. The main efforts to deal with deep learning networks are spent for a quite painstaking work of optimizing the structures of those networks and their components, as activation functions, weights, as well as the procedures of minimizing their loss function to improve their performances and speed up their learning time. It is also shown that the deep autoencoders develop the remarkable ability for denoising images after being specially trained. Convolutional Neural Networks are also used to solve a quite actual problem of protein genetics on the example of the durum wheat classification. Results of our comparative study demonstrate the undoubted advantage of the deep networks, as well as the denoising power of the autoencoders. In our work we use both GPU and cloud services to speed up the calculations.

A Comprehensive Study on the Applications of Artificial Intelligence for the Medical Diagnosis and Prognosis of Asthma

An estimated 300 million people worldwide suffer from asthma, and this number is expected to increase to 400 million by 2025. Approximately 250,000 people die prematurely each year from asthma out of which, almost all deaths are avoidable. Most of these deaths occur because the patients are unaware of their asthmatic morbidity. If detected early, asthmatic mortality rate can be reduced by 78%, provided that the patients carry appropriate medication for the same and/or are in lose vicinity to medical equipment like nebulizers. This study focuses on the development and valuation of algorithms to diagnose asthma through symptom intensive questionary, clinical data and medical reports. Machine Learning Algorithms like Back-propagation model, Context Sensitive Auto-Associative Memory Neural Network Model, C4.5 Algorithm, Bayesian Network and Particle Swarm Optimization have been employed for the diagnosis of asthma and later a comparison is made between their respective prospects. All algorithms received an accuracy of over 80%. However, the use of Auto Associative Memory Model (on a layered Artificial Neural Network) displayed much better results. It reached to an accuracy of over 90% and an inconclusive diagnosis rate of less than 1% when trained with adequate data. In the end, naive mobile based applications were developed on Android and iOS that made use of the self-training auto associative memory model to achieve an accuracy of nearly 94.2%.

A new reconstruction-based auto-associative neural network for fault diagnosis in nonlinear systems

Auto-associative neural network (AANN) is a typical nonlinear principal component analysis method, which is widely used in industry for fault diagnosis purposes, especially in nonlinear systems. However, the basic AANN often suffers from “smearing effects” problems that may lead to misdiagnosis, particularly with regards to the complex faults involving multiple variables. In this work, a new reconstruction-based AANN (RBAANN) method is proposed to enhance the capacity of fault diagnosis. In RBAANN, a generic derivative equation is developed to investigate the effects of AANN model inputs on the prediction error between model inputs and outputs. Based on the derivative equation, the reconstruction-based index for single or multiple variables, which is defined as the minimum prediction error, is obtained by tuning the corresponding model inputs iteratively. However, without the prior knowledge of the real faulty variables, all the possible variable sets need to be evaluated by the reconstruction-based index, and this may result in an exhaustive search and cause a huge computational burden. Thus, a branch and bound algorithm is introduced into RBAANN to solve the variable selection problem. Finally, an efficient fault diagnosis strategy by integrating RBAANN and branch and bound algorithm (BAB-RBAANN) is implemented to further pinpoint the source of the detected faults. This BAB-RBAANN method can handle both single and multiple variable(s) faults for nonlinear systems without prior knowledge efficiently. The effectiveness of the proposed methods is evaluated on a validation example and an industrial example. Comparisons with other methods, including principal component analysis techniques, are also presented.

Damage detection using vibration data and dynamic transmissibility ensemble with auto-associative neural network

In this paper, a transmissibility based damage detection methodology using artificial intelligence is proposed. Structural health monitoring requires accurate damage detection in real engineering while the environmental uncertain-ties make this a challenge. In order to reduce this effect, artificial intelligence, such as artificial neural networks might be a possible strategy for achieving a better interpretation of the monitored data during operational condition. In this study, transmissibility is taken into account as damage sensitive feature because it accounts for the response data only. Then, auto-associative neural network is employed for detecting the structural damage and predicting its severity. In order to validate our proposed technique, a ten-floor structure is simulated and studied. The results show good perfor-mance in detecting damages. DOI: http://dx.doi.org/10.5755/j01.mech.23.5.15339

Shallow and deep learning for image classification

The paper is focused on the idea to demonstrate the advantages of deep learning approaches over ordinary shallow neural network on their comparative applications to image classifying from such popular benchmark databases as FERET and MNIST. An autoassociative neural network is used as a standalone program realized the nonlinear principal component analysis for prior extracting the most informative features of input data for neural networks to be compared further as classifiers. A special study of the optimal choice of activation function and the normalization transformation of input data allows to improve efficiency of the autoassociative program. One more study devoted to denoising properties of this program demonstrates its high efficiency even on noisy data. Three types of neural networks are compared: feed-forward neural net with one hidden layer, deep network with several hidden layers and deep belief network with several pretraining layers realized restricted Boltzmann machine. The number of hidden layer and the number of hidden neurons in them were chosen by cross-validation procedure to keep balance between number of layers and hidden neurons and classification efficiency. Results of our comparative study demonstrate the undoubted advantage of deep networks, as well as denoising power of autoencoders. In our work we use both multiprocessor graphic card and cloud services to speed up our calculations. The paper is oriented to specialists in concrete fields of scientific or experimental applications, who have already some knowledge about artificial neural networks, probability theory and numerical methods.

Statistical analysis of rock-burst events in underground mines and excavations to present reasonable data-driven predictors

ABSTRACTRock bursts are sudden and violent failures of surrounding rockmasses in underground mines and excavations. In this paper, a database consisting of 188 case histories was collected. Each case history contains some of the predictor variables ‘overburden thickness, maximum tangential stress, uniaxial compressive strength of rock, tensile strength of rock, stress ratio, brittleness ratio and elastic energy index’ and one of the four defined classes for the dependent variable ‘rock burst intensity’. A strategy, including ‘outlier detection and substitution, normality evaluation, deduction of distribution functions, estimation of mean and mean variation ranges, evaluation of mean-equality and distribution function-equality hypotheses, correlation analysis and factor analysis for in-review variables’, was implemented. The strategy led to conclude that some predictor variables with available case histories have no contributions for rock burst prediction. These inferences were in accordance with the results of regression techniques for qualitative dependent variables. Besides, many predictor variable arrangements were incompatible with factor analysis. In the case of compatible arrangements, the variation of the predictor variables cannot be considerably reflected. Application of nonlinear principal component analysis using auto-associative neural networks did not also lead to representative components. Therefore, the significant predictor variables can only be used to design new classifiers.

Assessment of the water quality monitoring network of the Piabanha River experimental watersheds in Rio de Janeiro, Brazil, using autoassociative neural networks.

Water quality monitoring is a complex issue that requires support tools in order to provide information for water resource management. Budget constraints as well as an inadequate water quality network design call for the development of evaluation tools to provide efficient water quality monitoring. For this purpose, a nonlinear principal component analysis (NLPCA) based on an autoassociative neural network was performed to assess the redundancy of the parameters and monitoring locations of the water quality network in the Piabanha River watershed. Oftentimes, a small number of variables contain the most relevant information, while the others add little or no interpretation to the variability of water quality. Principal component analysis (PCA) is widely used for this purpose. However, conventional PCA is not able to capture the nonlinearities of water quality data, while neural networks can represent those nonlinear relationships. The results presented in this work demonstrate that NLPCA performs better than PCA in the reconstruction of the water quality data of Piabanha watershed, explaining most of data variance. From the results of NLPCA, the most relevant water quality parameter is fecal coliforms (FCs) and the least relevant is chemical oxygen demand (COD). Regarding the monitoring locations, the most relevant is Poço Tarzan (PT) and the least is Parque Petrópolis (PP).

Fault detection in the Tennessee Eastman benchmark process with nonlinear singular spectrum analysis

Multivariate statistical process monitoring methods aim at detecting and identifying faults in the performance of processes over time in order to keep the process under control. Singular spectrum analysis (SSA) is a potential tool for multivariate process monitoring. It allows the decomposition of dynamic process variables or time series into additive components that can be monitored separately to identify hidden faults that may otherwise not be detectable. However, SSA is a linear method and can give misleading information when it is applied to dynamic processes with strong nonlinearity. Therefore, in this paper, nonlinear versions of SSA based on the use of auto-associative neural networks or auto-encoders and dissimilarity matrices are considered. This is done based on the benchmark Tennessee Eastman process that is widely used in the evaluation of statistical process monitoring methods.

Big Data Approximating Control (BDAC)—A new model-free estimation and control paradigm based on pattern matching and approximation

This paper introduces a new approach to estimation and control problems called “BDAC,” for Big Data Approximating Control. It includes a training process and an estimation & control process. The training process creates and maintains an online training set of representative trajectories, updating them for adaptation to changing processes or sustained unmeasured disturbances. Trajectories are acquired by online monitoring, usually with some automated testing to speed up the process. Training and adaptation can occur in manual mode, test mode, and under closed loop control by BDAC or other controls. BDAC does not use models or state space representation, bypassing the usual “silos” of model identification, state estimation, and control. BDAC solves estimation and control problems by approximate pattern matching directly on the training set. It should benefit from rapid progress in “Big Data” techniques such as nearest neighbor search and clustering. A new data clustering technique and its specialization for real time filtering in causal systems is also introduced: “Real Time Exponential Cluster Filtering” (RTECF). BDAC is centered on solutions or approximate solutions to the “BDAC approximation problem,” which includes multivariable overdetermined or underdetermined control problems. A linear approach based on orthogonalization is given, as well as a nonlinear approach based on nearest neighbor interpolation. Even the linear method captures nonlinearity in individual training set trajectories, and the “kernel trick” is demonstrated for directly addressing nonlinearity with the linear controller. Simulation results in supplementary materials demonstrate combined feedforward and feedback control, dealing with setpoint and load changes, nonlinearities, dead times, integrating processes, adaptation, noise, unmeasured disturbances, co-linearity in measurements, estimating missing sensor values, and control while some controller outputs remain in manual or test modes. The well-known quadruple tank simulation shows control of a process switching between nonminimum phase behavior and minimum phase behavior. Integral action and adaptation approaches to avoid offset from setpoints due to changing processes or unmeasured disturbances are demonstrated. Comparisons of parts of the overall process are drawn to K-means clustering, Kalman filtering, linear optimal control/LQG, multivariable predictive control (MPC), and missing data replacement based on Kalman filtering, PCA or autoassociative neural networks.

Hierarchical Wavelet-Aided Neural Intelligent Identification of Structural Damage in Noisy Conditions

A sophisticated hierarchical neural network model for intelligent assessment of structural damage is constructed by the synergetic action of auto-associative neural networks (AANNs) and Levenberg-Marquardt neural networks (LMNNs). With the model, AANNs aided by the wavelet packet transform are firstly employed to extract damage features from measured dynamic responses and LMNNs are then utilized to undertake damage pattern recognition. The synergetic functions endow the model with a unique mechanism of intelligent damage identification in structures. The model is applied for the identification of damage in a three-span continuous bridge, with particular emphasis on noise interference. The results show that the AANNs can produce a low-dimensional space of damage features, from which LMNNs can recognize both the location and the severity of structural damage with great accuracy and strong robustness against noise. The proposed model holds promise for developing viable intelligent damage identification technology for actual engineering structures.