Habib Rostami

SCESN, SPESN, SWESN: Three recurrent neural echo state networks with clustered reservoirs for prediction of nonlinear and chaotic time series

Echo state networks (ESNs) with very simple and linear learning algorithm are a new approach to recurrent neural network training. Recently, these networks have aroused a lot of interest in their nonlinear dynamic system modeling capacities. In previous studies, the largest eigenvalue of the reservoir connectivity matrix (spectral radius) is used as a predictor for the stable network dynamics, but recent evidences show that in the presence of reservoir substructures like clusters, stability criteria in these kind of networks are altered. Some researchers have also demonstrated that network approximation ability in ESN networks is improved by the characteristics of small-world and scale-free. In this paper, we used three classic clustering algorithms called K-Means (C- Centeriod), partitioning Around Medoids (PAM) and ward algorithm, for clustering the internal neurons. After that, we refer to mean nodes in each cluster as backbone units and refer to the other neurons in a cluster as local neurons. Connections between neurons are such that the resulting networks have small-world topology and neurons in the new networks follow a power-law distribution. At first, we demonstrate that resulting clustered networks have some characteristics of biological neural system like power-law distribution, small-word feature, community structure, and distributed architecture. For investigating the prediction power and the range of spectral radius of resulting networks, we use new ESNs on the Mackey-Glass dynamic system and the laser time series prediction problem and compared the results with the previous works. Then we evaluate echo state property and performance of approximating highly complex nonlinear dynamic systems of proposed networks rather than previous approaches. Results show that the proposed methods outperform the previous ones in terms of prediction accuracy of chaotic time series.

Energy efficient spherical divisions for VBF-based routing in dense UWSNs

Three main problems for wireless sensor networks are communication traffic, energy consumption and routing security. In this paper we are going to analyze performance improvement of an underwater sensor network in dense mode applications via creation of forbidden regions in spherical divisions. Obviously, non-essential nodes deletion from packet forwarding process or routing process is an idea for network parameters enhancement in network theory. In this literature, our goal is only energy consumption and deletion process over physical routing space finally causes improvement in energy consumption and also network reliability/network lifetime. However, PDR are not worse than previous conditions and it is necessary to say that our scheme is useful.

MRF-Based Multispectral Image Fusion Using an Adaptive Approach Based on Edge-Guided Interpolation

In interpretation of remote sensing images, it is possible that some images which are supplied by different sensors become incomprehensible. For better visual perception of these images, it is essential to operate series of pre-processing and elementary corrections and then operate a series of main processing steps for more precise analysis on the images. There are several approaches for processing which are depended on the type of remote sensing images. The discussed approach in this article, i.e. image fusion, is the use of natural colors of an optical image for adding color to a grayscale satellite image which gives us the ability for better observation of the HR image of OLI sensor of Landsat-8. This process with emphasis on details of fusion technique has previously been performed; however, we are going to apply the concept of the interpolation process. In fact, we see many important software tools such as ENVI and ERDAS as the most famous remote sensing image processing tools have only classical interpolation techniques (such as bi-linear (BL) and bi-cubic/cubic convolution (CC)). Therefore, ENVI- and ERDAS-based researches in image fusion area and even other fusion researches often dont use new and better interpolators and are mainly concentrated on the fusion algorithms details for achieving a better quality, so we only focus on the interpolation impact on fusion quality in Landsat-8 multispectral images. The important feature of this approach is to use a statistical, adaptive, and edge-guided interpolation method for improving the color quality in the images in practice. Numerical simulations show selecting the suitable interpolation techniques in MRF-based images creates better quality than the classical interpolators.

Efficient routing for dense UWSNs with high-speed mobile nodes using spherical divisions

Three major problems of wireless sensor networks can be summarized into communication traffic, energy consumption and routing security. In this paper, we analyze performance of an underwater sensor network in dense mode under creation of spherical division-based forbidden regions. Obviously, unnecessary smart node removal from the packet forwarding process of a flooding-based routing policy is theoretically an idea for enhancing the known network parameters. In this research, our purposed approach is to improve energy consumption by using a removal process over physical routing space toward more network reliability and better network lifetime. Clearly, our aim is performance improvement in terms of a network protocol in an underwater wireless sensor networks with a huge number of high-speed mobile nodes. The nodes generally consist of different underwater instruments such as sensors, robots, modems and batteries and are categorized into two groups of autonomous unmanned underwater vehicles and remotely operated vehicles. The proposed approach is a hybrid solution based on vector-based forwarding routing protocol and spherical divisions which is named spherical division-based vector-based forwarding. The proposed protocol can successfully reduce energy consumption and equivalently increase the network lifetime while packet delivery ratio is in a saturation level. In details, our proposed method works on preservation of sensors’ energy in which we physically remove some additional paths of routing process (based on a multipath forwarding using a basic routing algorithm). In this regard, we apply a spherical division-based physical restriction on the routing space. However, removing these additional sensor nodes/routers is conditionally done under keeping the suitable traffic performance in terms of PDR because it is essential to say that a new scheme is effective.

Application of Artificial Neural Network-Particle Swarm Optimization Algorithm for Prediction of Asphaltene Precipitation During Gas Injection Process and Comparison With Gaussian Process Algorithm

Asphaltene precipitation is a major problem in the oil production and transportation of oil. Changes in pressure, temperature, and composition of oil can lead to asphaltene precipitation. In the case of gas injection into oil reservoirs, the injected gas causes a change in oil composition and may lead to asphaltene precipitation. Accurate determination and prediction of the precipitated amount are vital, for this purpose there are several approaches such as experimental method, scaling equation, thermodynamics models, and neural network as the most recent ones. In this paper, we propose a new artificial neural network (ANN) optimized by particle swarm optimization (PSO) to predict the amount of asphaltene precipitation. This is conducted during the process of gas injection into oil reservoirs for enhanced oil recovery purposes. In the developed models, (1) oil composition, (2) temperature, (3) pressure, (4) oil specific gravity, (5) solvent mole percent, (6) solvent molecular weight, and (7) asphaltene content are considered as input parameters to the neural network. The weight of asphaltene and asphaltene content are considered as input parameters to the neural network and the weight of asphaltene precipitation as an output parameter. A comparison between the results of the proposed new model with Gaussian Process algorithm and previous research shows that the predictive model is more accurate.

Application of evolutionary Gaussian processes regression by particle swarm optimization for prediction of dew point pressure in gas condensate reservoirs

One of the most critical quantities for characterizing a gas condensate reservoir is dew point pressure. But, accurate determination of dew point pressure is a very challengeable task in reservoir development. Experimental measurement of dew point pressure in PVT (Pressure, Volume, Temperature) cell is often difficult, especially in the case of lean retrograde gas condensate. So, different empirical correlations and equations of state are developed by researchers to calculate this property. Empirical correlations do not have ability to reliably duplicate the temperature behavior of constant composition fluids, and equations of state have convergence problem and need to be tuned against some experimental data. In addition, these approaches are not generalizable to unseen data, and they usually memorize the data used to develop them. In this paper, we develop an intelligent model to predict dew point pressure of gas condensate reservoirs using Gaussian processes optimized by particle swarm optimization. The developed model is generalizable and can estimate unseen data with the same distribution of training data accurately. Results show that the proposed method in this paper outperforms the previous published models and correlations.

Label switched protocol routing with guaranteed bandwidth and end to end path delay in MPLS networks

Abstract Rapid growth of multimedia applications has caused a tremendous impact on how people communicate. Next generation networks (NGN) have been proposed to support newly emerged multimedia IP based applications such as voice over IP (VOIP), video on-demand (VOD), and IPTV using a core IP backbone. The development of technologies like Multi-Protocol Label Switching (MPLS) has laid the foundation for NGN to support multimedia applications like Voice over IP. One of the important concepts in MPLS Traffic Engineering (TE) is Label Switched Path (LSP) routing. The objective of the routing algorithm is to increase the number of accepted request while satisfying Quality of Service (QoS) constraints. Although much work has been done on laying MPLS paths to optimize performance, most of them have focused on satisfying bandwidth requirements. Relatively little research has been done on laying paths with both bandwidth and delay constraints. In this paper, we present a new bandwidth and end to end delay (bandwidth-delay) constrained routing algorithm which uses data of the ingress–egress node pairs in the network. In this algorithm we use LR-Servers theory to compute path delay. We name the proposed algorithm as Minimum Delay and Maximum Flow (MDMF). We do extensive simulations to evaluate the performance of MDMF algorithm. In addition, we compare the performance of MDMF against some previous related works such as MHA, WSP, MIRA, BCRA, MIRAD, BGDG, BGLC, and SAMCRA. The simulation results show that MDMF rivals them in terms of flow management and outperform them in terms of end to end delay management, maximum flow and number of accepted request (call blocking ratio).

Prediction of Asphaltene Precipitation in Live and Tank Crude Oil Using Gaussian Process Regression

The study of asphaltene precipitation properties has been motivated by their propensity to aggregate, flocculate, precipitate, and adsorb onto interfaces. The tendency of asphaltenes to precipitation has posed great challenges for the petroleum industry. Since the nature of asphaltene solubility is yet unknown and several unmodeled dynamics are hidden in the original systems, the existing models may fail in prediction the asphaltene precipitation in crude oil systems. The authors developed some Gaussian process regression models to predict asphaltene precipitation in crude oil systems based on different subsets of properties and components of crude oil. Using feature selection techniques they found some subsets of properties of crude oil that are more predictive of asphaltene precipitation. Then they developed prediction models based on selected feature sets. Results of this research indicate that the proposed predictive models can successfully predict and model asphaltene precipitation in tank and live crude oils with good accuracy.

Distributed random cooperation for VBF-based routing in high-speed dense underwater acoustic sensor networks

AbstractMost of underwater wireless sensor applications need reliable data transfer timely and efficiently. Because radio waves do not travel well through good electrical conductors like saltwater, underwater distributed systems use acoustic waves to communicate data. However, energy conservation is a major challenge in underwater acoustic-based systems/networks. Different methods are developed to enhance energy efficiency in these networks. In this paper, we improve energy efficiency of the networks by enhancing routing scheme. The enhancement is done by defining some constraints on traditional packet flooding. A strategy based on physical constraints has been introduced in our previous work for creating an indirect 1-D random mechanism to remove additional nodes from routing process and save energy. Now here, a better mechanism in terms of simplicity, scalability and efficiency is introduced to improve energy consumption. The approach is to use an intelligent 3-D random node removal mechanism considering traffic status of the network. Simulation results show that the proposed approach significantly improves energy efficiency of the underwater acoustic wireless sensor networks.

Pgu-Face: A dataset of partially covered facial images.

In this article we introduce a human face image dataset. Images were taken in close to real-world conditions using several cameras, often mobile phone׳s cameras. The dataset contains 224 subjects imaged under four different figures (a nearly clean-shaven countenance, a nearly clean-shaven countenance with sunglasses, an unshaven or stubble face countenance, an unshaven or stubble face countenance with sunglasses) in up to two recording sessions. Existence of partially covered face images in this dataset could reveal the robustness and efficiency of several facial image processing algorithms. In this work we present the dataset and explain the recording method.