Sharif Digital Repository

Hand pose estimation is one of the most attractive research areas for image processing. Among the human body parts, hands are particularly important for human–machine interactions. The advent of commercial depth cameras along with the rapid growth of deep learning has made great progress in all image processing fields, especially in hand pose estimation. In this study, using depth data, we introduce two hybrid deep neural networks to estimate 3D hand poses with fewer computations and higher accuracy compared with their counterparts. Due to the fact that the dimensions of data are reduced while passing through successive layers of networks, which causes data to be lost, we use the concept of... 

Hand pose estimation is one of the most attractive research areas for image processing. Among the human body parts, hands are particularly important for human–machine interactions. The advent of commercial depth cameras along with the rapid growth of deep learning has made great progress in all image processing fields, especially in hand pose estimation. In this study, using depth data, we introduce two hybrid deep neural networks to estimate 3D hand poses with fewer computations and higher accuracy compared with their counterparts. Due to the fact that the dimensions of data are reduced while passing through successive layers of networks, which causes data to be lost, we use the concept of... 

In feed forward neural networks, hidden layer neurons' saturation conditions, which are the cause of flat spots on the error surface, is one of the main disadvantages of any conventional gradient descent learning algorithm. In this paper, we propose a novel complementary scheme for the learning based on a suitable combination of anti saturated hidden neurons learning process and accelerating methods like the momentum term and the parallel tangent technique. In our proposed method, a normalized saturation criterion (NSC) of hidden neurons, which is introduced in this paper, is monitored during learning process. When the NSC is higher than a specified threshold, it means that the algorithm... 

Phase equilibrium data are required to estimate the capacity of a geological formation to sequester CO2. In this paper, a comprehensive study, including both thermodynamic and neural network modeling, is performed on CO2 solubility in brine. Brine is approximated by a NaCl solution. The Redlich-Kwong equation of state and Pitzer expansion are used to develop the thermodynamic model. The equation of state constants are adjusted by genetic algorithm optimization. A novel approach based on a neural network model is utilized as well. The temperature range in which the presented model is valid is 283-383K, and for pressure is 0-600bar, covering the temperature and pressure... 

We consider joint optimization of data routing and resource allocation in multicast multihop wireless networks where interference between links is taken into account. The use of network coding in such scenarios leads to a nonconvex optimization problem. By applying the probability collectives (PCs) technique the original problem is turned into a new problem which is convex over probability distributions. The resulting problem is then further decomposed into a data routing subproblem at network layer and a power allocation subproblem at physical layer in order to achieve a cross-layer distributed solution for the whole range of SINR values. The proposed approach is also extended to minimum... 

Node cooperation approaches improve physical layer security in wireless networks without applying data encryption. Selecting the appropriate nodes to cooperate as relays or friendly jammers, to degrade eavesdropper's link, is a challenging problem which has attracted a lot of attention in recent years. Various approaches, based on conventional exhaustive search, have been suggested for optimal relay-jammer selection and power allocation in the literature. The complexity of these methods is proportional to the number of intermediate nodes. As the number of intermediate nodes exceeds a specific bound, conventional exhaustive search appears infeasible due to high computational complexity. In... 

Wax precipitation may occur in production or transportation of crude oil form field which is a serious problem in petroleum industry. Flow assurance issues concerning wax precipitation make it necessary to develop a precise thermodynamic model to predict the wax appearance temperature and amount of precipitation at different conditions. In this work a new procedure has been proposed to characterize crude oil based on the SARA test considering the wax and asphaltene as single pseudo components. Two scenarios have been investigated for the survey of the crude oil characterization, with and without asphaltene pseudo component. Also, in this work, the Perturbed Chain form of the Statistical... 

Although different broadcasting techniques are widely deployed in wireless networks, there are limited comprehensive analytical frameworks to evaluate the performance of such schemes. In this paper, based on a rigorous theoretical analysis, upper bounds on the network coverage and the total number of transmissions (corresponding to network energy consumption) of flooding and its popular variant probabilistic flooding are derived. The analysis is performed for a static multihop ad hoc wireless network when the network is in saturated condition. To consider a realistic medium-access control (MAC) layer algorithm, successful signal reception is based on the protocol model, and nodes employ... 

Ambient Intelligence is the future of computing where devices predict what users need and help them carry out their everyday life activities easier. To make this prediction possible these environments should be aware of the context. Activity recognition is one of the most complex problems in context-aware environments. In this paper we propose a layered Dynamic Bayesian Network (DBN) to recognize activities in an oral presentation. The layered architecture gives us the opportunity to recognize complex activities using the classification results of sensory data in the first layer regardless of the physical environment. Our model is event-driven meaning the classification takes place only when... 

In this paper, a cross-layer approach introducing new design parameters is developed for multi-rate wireless links. The novel design jointly exploits the finite-length queuing at the data link layer and the adaptation capability of the adaptive modulation and coding (AMC) scheme at the physical layer to optimize system performance for a wireless link. The analytical framework is based on discrete time Markov Chain. The performance metrics such as packet drop probability, channel packet error rate and packet loss rate are derived. Using these metrics, a constrained optimization problem is solved numerically to maximize the overall system throughput  

This article is the first attempt to employ deep learning to estimate the frequency performance of the rotating multi-layer nanodisks. The optimum values of the parameters involved in the mechanism of the fully connected neural network are determined through the momentum-based optimizer. The strength of the method applied in this survey comes from the high accuracy besides lower epochs needed to train the multi-layered network. It should be mentioned that the current nanostructure is modeled as a nanodisk on the viscoelastic substrate. Due to rotation, the centrifugal and Coriolis effects are considered. Hamilton’s principle and generalized differential quadrature method (GDQM) are presented... 

This article is the first attempt to employ deep learning to estimate the frequency performance of the rotating multi-layer nanodisks. The optimum values of the parameters involved in the mechanism of the fully connected neural network are determined through the momentum-based optimizer. The strength of the method applied in this survey comes from the high accuracy besides lower epochs needed to train the multi-layered network. It should be mentioned that the current nanostructure is modeled as a nanodisk on the viscoelastic substrate. Due to rotation, the centrifugal and Coriolis effects are considered. Hamilton’s principle and generalized differential quadrature method (GDQM) are presented... 

This paper presents a novel approach for power allocation and cooperative node selection to enhance physical layer security in presence of an eavesdropper in a wireless network. Our network consists of a source–destination pair and a number of cooperative nodes which can be used as relays to increase throughput at the destination, or as friendly jammers to confuse eavesdropper. First, we introduce a low complexity method, for which relay−jammer selection and power allocation are performed, simultaneously. Then, we propose self-adaptive genetic algorithm to solve the non-linear non-convex programing problem. Using the proposed method, the number of friendly jammers that ensure the secrecy... 

Overlay multicast has gained much attention in recent years as an alternative method to network layer multicast, especially for mobile ad hoc networks (MANETs). In this paper, we propose a new overlay multicast protocol to achieve simplicity of deployment, rapid adaptation of overlay structure when nodes move, and reduced delay. In our algorithm, to join or leave a multicast group, it is only sufficient for a member node to inform its first upstream member node. This updates the tree structure more rapidly when nodes move. In addition, join and leave delays are reduced and this makes the protocol suitable for multimedia multicasting in MANETs. Simulation results compared to that of ODMRP and... 

Unstructured wireless networks such as mobile ad hoc networks and wireless sensor networks have been rapidly growing in the past decade. Security is known as a challenging issue in such networks, in which there is no fixed infrastructure or central trusted authority. Further, node limitations in processing power, storage, and energy consumption add further complexity to addressing security in such networks. While cryptography has proven to be an effective solution capable of satisfying most network security requirements, it requires the use of efficient key pre-distribution algorithms compatible with the limitation of unstructured wireless networks. Typically, a key pre-distribution... 

In this paper, a novel method for capturing the information of a powerful and trained deep convolutional neural network and distilling it into a training smaller network is proposed. This is the first time that a saliency map method is employed to extract useful knowledge from a convolutional neural network for distillation. This method, despite of many others which work on final layers, can successfully extract suitable information for distillation from intermediate layers of a network by making class specific attention maps and then forcing the student network to mimic producing those attentions. This novel knowledge distillation training is implemented using state-of-the-art DeepLab and... 

Analytical Jacobian, nonlinear least square and three layer artificial neural network models are employed to predict deformation of mouse embryos under needle injection, based on experimental data captured from literature. The Maximum Absolute Error (MAE), coefficient of determination ( R2), Relative Error of Prediction (REP), Root Mean Square Error of Prediction (RMSEP), NashSutcliffe coefficient of efficiency ( Ef) and accuracy factor ( Af) are used as the basis for comparison of these three models. Analytical Jacobian, nonlinear least square and ANN models have yielded the correlation coefficient of 0.9985, 0.9964 and 0.9998, respectively. The REP between the models predicted values and... 

Coordination strategies in large-scale systems are mainly based on two principles: interaction prediction and interaction balance. Using these principles, Model coordination and Goal coordination were proposed. The interactions in the first method and the Lagrangian coefficients in the second method were considered as coordination parameters. In this paper, the concept of coordination is introduced within the framework of two-level large-scale systems and a new intelligent approach for Model coordination is introduced. For this purpose, the system is decomposed into several subsystems, and the overall problem is considered as an optimization problem. With the aim of optimization, the control... 

Absorption of carbon dioxide (CO2) in aqueous solutions can be improved by the addition of other compounds. However, this requires a large amount of equilibrium data for solubility estimation in a wide ranges of temperature, pressure and concentration. In this paper, a model based on an artificial neural network (ANN) was proposed and developed with mixtures containing monoethanolamine (MEA), diethanolamine (DEA), methyldiethanolamine (MDEA), 2-amino-2-methyl-1-propanol (AMP), methanol, triethanolamine (TEA), piperazine (PZ), diisopropanolamine (DIPA) and tetramethylensulfone (TMS) to predict solubility of CO2 in mixed aqueous solution (especially in binary and ternary mixtures) over wide... 

The ways in which an innovation (e.g., new behaviour, idea, technology, product) diffuses among people can determine its success or failure. In this paper, we address the problem of diffusion of innovations over multiplex social networks where the neighbours of a person belong to one or multiple networks (or layers) such as friends, families, or colleagues. To this end, we generalise one of the basic game-theoretic diffusion models, called networked coordination game, for multiplex networks. We present analytical results for this extended model and validate them through a simulation study, finding among other properties a lower bound for the success of an innovation. While simple and leading...