Search results for "artificial neural"
showing 10 items of 696 documents
Neural network-based models for a vibration suppression system equipped with MR brake
2012
This paper is devoted to the modeling and simulation of a full-scale commercially available magnetorheological (MR) brake installed in a semi-active suspension (SAS) system. The analysis of the Bouc-Wen and Dahl mathematical models of MR damper is presented. Influence of their parameters on the response is explored. Subsequently, by using the neural networks, the parameters characterizing each model are estimated. This makes it possible to perform the comparative analysis of the suggested damper models responses with the measured experimental results. The novelty of the presented methodology is the application of artificial intelligence methods to estimate model parameters of a MR brake uti…
A Comparative Study of Nonlinear Machine Learning for the "In Silico" Depiction of Tyrosinase Inhibitory Activity from Molecular Structure.
2011
In the preset report, for the first time, support vector machine (SVM), artificial neural network (ANN), Baye- sian networks (BNs), k-nearest neighbor (k-NN) are applied and compared on two "in-house" datasets to describe the tyrosinase inhibitory activity from the molecular structure. The data set Data I is used for the identification of tyrosi- nase inhibitors (TIs) including 701 active and 728 inactive compounds. Data II consists of active chemicals for potency estimation of TIs. The 2D TOMOCOMD-CARDD atom-based quadratic indices are used as molecular descriptors. The de- rived models show rather encouraging results with the areas under the Receiver Operating Characteristic (AURC) curve …
Channel Capacity in Psychovisual Deep-Nets: Gaussianization Versus Kozachenko-Leonenko
2020
In this work, we quantify how neural networks designed from biology using no statistical training have a remarkable performance in information theoretic terms. Specifically, we address the question of the amount of information that can be extracted about the images from the different layers of psychophysically tuned deep networks. We show that analytical approaches are not possible, and we propose the use of two empirical estimators of capacity: the classical Kozachenko-Lonenko estimator and a recent estimator based on Gaussianization. Results show that networks purely based on visual psychophysics are extremely efficient in two aspects: (1) the internal representation of these networks dup…
Experimental studies on continuous speech recognition using neural architectures with “adaptive” hidden activation functions
2010
The choice of hidden non-linearity in a feed-forward multi-layer perceptron (MLP) architecture is crucial to obtain good generalization capability and better performance. Nonetheless, little attention has been paid to this aspect in the ASR field. In this work, we present some initial, yet promising, studies toward improving ASR performance by adopting hidden activation functions that can be automatically learned from the data and change shape during training. This adaptive capability is achieved through the use of orthonormal Hermite polynomials. The “adaptive” MLP is used in two neural architectures that generate phone posterior estimates, namely, a standalone configuration and a hierarch…
Classification of diabetes-related retinal diseases using a deep learning approach in optical coherence tomography
2019
Background and objectives: Spectral Domain Optical Coherence Tomography (SD-OCT) is a volumetric imaging technique that allows measuring patterns between layers such as small amounts of fluid. Since 2012, automatic medical image analysis performance has steadily increased through the use of deep learning models that automatically learn relevant features for specific tasks, instead of designing visual features manually. Nevertheless, providing insights and interpretation of the predictions made by the model is still a challenge. This paper describes a deep learning model able to detect medically interpretable information in relevant images from a volume to classify diabetes-related retinal d…
Optimal imaging of multi-channel EEG features based on a novel clustering technique for driver fatigue detection
2020
Abstract Fatigue may cause a decrease in mental and physical performance capacity, which is a serious safety risk for the drivers in the transportation system. Recently, various studies have demonstrated the deviations of electroencephalogram (EEG) indicators from normal vigilant state during fatigue in time and frequency domains. However, when considering spatial information, these feature descriptors are not satisfying the demand for reliable detection due to the well-known challenge of signal mixing. In this paper, we propose a novel approach based on clustering on brain networks (CBNs) to alleviate the problem to improve the performance of driver fatigue detection. The clustering algori…
Estimation of Leaf Area in Bell Pepper Plant using Image Processing techniques and Artificial Neural Networks
2021
Measurement and estimation of physical properties of plant leaves have always been considered as important requirements for monitoring and optimizing of plant growth. This study aimed at utilization of image processing and artificial intelligence techniques for non-invasive and non-destructive estimation of bell pepper leaves properties in the first month of growth. Physical properties of bell pepper plant leaves were extracted from RGB images. The algorithm makes use of gradient magnitude and watershed image. Leaf area as the most important index of growth was estimated as a function of other physical parameters including leaf length, width, perimeter etc. Using stereo imaging, the leaf di…
Combination of finite impulse response neural network technique with FDTD method for simulation of electromagnetic problems
1996
The finite difference time domain (FDTD) method requires long computation times for simulating resonant or high-Q structures. The authors incorporate the finite impulse response neural network technique as a predictor in order to save time in FDTD simulations. The applicability of the technique is demonstrated by carrying out an analysis of a waveguide filter.
Prefiltering for pattern recognition using wavelet transform and neural networks
2003
Publisher Summary Neural networks are built from simple units interlinked by a set of weighted connections. Generally, these units are organized in layers. Each unit of the first layer (input layer) corresponds to a feature of a pattern that is to be analyzed. The units of the last layer (output layer) produce a decision after the propagation of information. Before feeding the computational data to neural networks, the signal must undergo a preprocessing in order to (1) define the initial transformation to represent the measured signal, (2) retain important features for class discrimination and discard that is irrelevant, and (3) reduce the volume of data to be processed, for example, data …
Application of neural network to predict purchases in online store
2016
A key ability of competitive online stores is effective prediction of customers’ purchase intentions as it makes it possible to apply personalized service strategy to convert visitors into buyers and increase sales conversion rates. Data mining and artificial intelligence techniques have proven to be successful in classification and prediction tasks in complex real-time systems, like e-commerce sites. In this paper we proposed a back-propagation neural network model aiming at predicting purchases in active user sessions in a Web store. The neural network training and evaluation was performed using a set of user sessions reconstructed from server log data. The proposed neural network was abl…