Tabriz Islamic Art University

www.tabriziau.ac.ir
Tabriz, Iran
SEARCH FILTERS
Time filter
Source Type

Sekhavat Y.A.,Tabriz Islamic Art University
IEEE Transactions on Multimedia | Year: 2017

Virtual try-on applications make it possible for buyers to watch themselves wearing different garments without physically trying on them. The prevailing approach for virtual try-on has been based on virtual fitting rooms, in which several cameras are used to identify the skeleton and posture of a user in order to render a garment on the user's image. Although this approach has been implemented successfully using different techniques, the privacy of users can be compromised as some users might be reluctant to stand in front of cameras in a fitting room. This paper proposes an alternative approach that allows a customer to watch a three-dimensional (3D) model of her/him wearing garments on a personal mobile device using augmented reality (AR). Among 3D human models that are automatically generated, a model selection technique is proposed that makes it possible to find the right size model representing the anthropometric features of the user. This approach is accompanied by body customization and face generation modules to generate a realistic representation. Several quantitative experiments as well as user studies were performed to evaluate the accuracy, efficiency, usefulness, and privacy of the proposed technique. © 1999-2012 IEEE.


Sekhavat Y.A.,Tabriz Islamic Art University
2017 IEEE 5th International Conference on Serious Games and Applications for Health, SeGAH 2017 | Year: 2017

Generally, the difficulty level of a therapeutic game is regulated manually by a therapist. However, home-based rehabilitation games require a technique for automatic difficulty adjustment. This paper proposes a personalized difficulty adjustment technique for a rehabilitation game that automatically regulates difficulty settings based on a patient's skills in real-time. To this end, ideas from reinforcement learning are used to dynamically adjust the difficulty of a game. We show that difficulty adjustment is a multiple-objective problem, in which some objectives might be evaluated at different periods. To address this problem, we propose and use Multiple-Periodic Reinforcement Learning (MPRL) that makes it possible to evaluate different objectives of difficulty adjustment in separate periods. The results of experiments show that MPRL outperforms traditional Multiple-Objective Reinforcement Learning (MORL) in terms of user satisfaction parameters as well as improving the movement skills of patients. © 2017 IEEE.


Sekhavat Y.A.,Tabriz Islamic Art University | Parsons J.,Memorial University of Newfoundland
Proceedings - International Conference on Data Engineering | Year: 2017

Data exchange is the process of generating an instance of a target schema from an instance of a source schema such that source data is reflected in the target. The prevailing approach for data exchange is based on schema mappings, which are high level expressions that describe relationships between database schemas [1]. However, schema-mapping based data exchange techniques suffer from two problems: (1) entity fragmentation, in which information about a single entity is spread across several tuples in the target schema, and (2) ambiguity in generalization, in which incorrect mappings result from using different methods to represent entity type generalization in source and target schemas. In this paper, we propose the Scalable Entity Preserving Data Exchange (SEDEX) method, which combines schema-level and datalevel information to address these problems. We also provide extensive evaluation to demonstrate the benefits and scalability of the approach. © 2017 IEEE.


Sekhavat Y.A.,Tabriz Islamic Art University
International Journal on Artificial Intelligence Tools | Year: 2017

Although a Finite State Machine (FSM) is easy to implement the behaviors of None-Player Characters (NPC) in computer games, it is difficult to maintain and control the behaviors with increasing the number of states. Alternatively, Behavior Tree (BT), which is a tree of hierarchical nodes to control the ow of decision making, is widely used in computer games to address the scalability issues. This paper reviews the structure and semantics of BTs in computer games. Different techniques to automatically learn and build BTs as well as strengths and weaknesses of these techniques are discussed. This paper provides a taxonomy of BT features and shows to what extent these features are taken into account in computer games. Finally, the paper shows how BTs are used in practice in the gaming industry. © 2017 World Scientific Publishing Company.


Khataee A.R.,University of Tabriz | Kasiri M.B.,Tabriz Islamic Art University
Journal of Molecular Catalysis A: Chemical | Year: 2010

Artificial neural networks (ANNs) are computer based systems that are designed to simulate the learning process of neurons in the human brain. ANNs have been attracting great interest during the last decade as predictive models and pattern recognition. Artificial neural networks possess the ability to "learn" from a set of experimental data (e.g. processing conditions and corresponding responses) without actual knowledge of the physical and chemical laws that govern the system. Therefore, ANNs application in data treatment is especially important where systems present nonlinearities and complex behavior. In recent years "advanced oxidation processes" (AOPs), including homogeneous and heterogeneous nanocatalytic processes, have been proposed to oxidize quickly and non-selectively a broad range of water pollutants. Due to the complexity of reactions in AOPs, the effect of different operational parameters involved are very difficult to determine, leading to uncertainties in the design and scale-up of chemical reactors of industrial interest. It is evident that this problem can not be solved by simple linear multivariate correlation. Artificial neural networks are a promising alternative modeling technique. This paper briefly describes the application of artificial neural networks for modeling of water and wastewater treatment using various homogeneous and heterogeneous nanocatalytic processes. Examples of early applications of ANNs in modeling and simulation of photocatalytic, photooxidative and electrochemical treatment processes are reviewed. © 2010 Elsevier B.V. All rights reserved.


Khataee A.R.,University of Tabriz | Kasiri M.B.,Tabriz Islamic Art University
Journal of Molecular Catalysis A: Chemical | Year: 2010

Synthetic dyes are a major part of our life as they are found in the various products ranging from clothes to leather accessories to furniture. These carcinogenic compounds are the major constituents of the industrial effluents. Various approaches have been developed to remove organic dyes from the natural environment. Over the past few years, there has been an enormous amount of research with advanced oxidation processes (AOPs) as an effective method of wastewater treatment. Among AOPs, heterogeneous photocatalytic process using TiO2 nanomaterials appears as the most emerging destructive technology due to its cost effectiveness and the catalyst inert nature and photostability. This review deals with the photocatalytic degradation of organic dyes containing different functionalities using TiO2 nanomaterials in aqueous solution. It first discusses the photocatalytic properties of nanostructured TiO2. The photocatalytic degradation rate strongly depends on the basic structure of the molecule and the nature of auxiliary groups attached to the aromatic nuclei of the dyes. So, this review then explains the influence of structure of dyes on their photocatalytic degradation rates. The influences of different substitutes such as alkyl side chains, methyl, nitrate, hydroxyl and carboxylic groups as well as the presence of chloro atom have been discussed in detail. © 2010 Elsevier B.V.


Kasiri M.B.,Tabriz Islamic Art University | Khataee A.R.,University of Tabriz
Environmental Technology (United Kingdom) | Year: 2012

The effects of different operational parameters on the decolorization of a dye solution containing C.I. Acid Blue 92 (AB92) or C.I. Acid Black 1 (AB1) by the UV/H 2O 2 process were optimized using response surface methodology (RSM). The reaction time, dye and H 2O 2 initial concentrations and distance of the UV lamp from the solution were chosen as input variables. The removal process was performed according to a central composite design. Predicted results by the proposed models were in good agreement with experimental values (R 2 = 0.942 and 0.957 for AB92 and AB1, respectively). The optimum points were located by graphical response surfaces and contour plots. The removal process of the dyes was compared and the efficiency difference justified by considering the chemical structure of the dyes. Additionally, the electrical energy consumption and the related treatment costs were estimated employing the figure-of-merit electrical energy per order (E EO). © 2012 Taylor & Francis.


Khataee A.R.,University of Tabriz | Kasiri M.B.,Tabriz Islamic Art University
Clean - Soil, Air, Water | Year: 2011

A growing world population, unrelenting urbanization, increasing scarcity of good quality water resources, and rising fertilizer applications are the driving forces behind the accelerating upward trend in the use of efficient methods of water and wastewater treatment such as biological processes. Due to the complexity of the reactions in biological processes, a few studies have been performed involving the modeling of biological removal of water pollutants. Thus, the application of the artificial neural networks (ANNs) to predict the performance of the biological systems has been attempted. ANNs are computer-based systems that are designed to simulate the learning process of neurons in the human brain. One of the characteristics of modeling based on ANNs is that it does not require the mathematical description of the phenomena involved in the process. This review article describes the application of ANNs for modeling of biological water and wastewater treatment processes. Examples of early applications of ANNs in modeling and simulation of biological water and wastewater treatment processes in the presence of various microalgae, macroalgae, bacteria, microbes, yeasts, anaerobic sludge, aerated submerged biofilms, and submerged membrane bioreactors are reviewed. © 2011 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.


Kasiri M.B.,Tabriz Islamic Art University | Khataee A.R.,University of Tabriz
Desalination | Year: 2011

The present work deals with the application of Response Surface Methodology (RSM) to study the effects of operational parameters on the photooxidative decolorization of two dyes (C.I. Basic Blue 3 (BB3) and C.I. Acid Green 25 (AG25)) with different molecular structure under UV light illumination (30W) in the presence of hydrogen peroxide (H2O2). The variables investigated were the reaction time, dye and H2O2 initial concentrations and distance of UV lamp from the solution. Central Composite Design (CCD) was used for the optimization of photooxidative decolorization process. Predicted values were found to be in good agreement with experimental values (R2=98.43 and 95.06 and Adj-R2=97.05 and 90.74 for BB3 and AG25, respectively), which indicated suitability of the model and the success of CCD in optimization of UV/H2O2 process. Graphical response surface and contour plots were used to locate the optimum points. The photooxidative removal of the dyes in the optimal conditions was compared and a structure-degradability relationship was established. Moreover, the figure-of-merit electrical energy per order (EEO) was employed to estimate the electrical energy consumption. © 2010 Elsevier B.V.


Khataee A.R.,University of Tabriz | Kasiri M.B.,Tabriz Islamic Art University | Alidokht L.,University of Tabriz
Environmental Technology | Year: 2011

Response surface methodology is a widely used technique for modelling and optimization of the photocatalytic treatment processes of water and wastewater. This methodology not only estimates linear, interaction and quadratic effects of the factors on the response, but also provides a prediction model for the response at the range of the variables studied and the optimum conditions to achieve the highest performance. The present paper reviews the results of application of this innovative methodology in modelling and optimization of the photocatalytic treatment processes. Different experimental designs including 3 k factorial, Doehlert, Box-Behnken and central composite designs have been developed to describe the treatment processes of dyeing effluents, pharmaceutical agents and hazardous phenolic compounds. The results showed that response surface methodology can describe the behaviour of complex reaction systems, such as photocatalytic processes, in the range of experimental conditions adopted. Optimization based on response surface methodology can also estimate the conditions of the photocatalytic processes to achieve the highest performance. © 2011 Copyright Taylor and Francis Group, LLC.

Loading Tabriz Islamic Art University collaborators
Loading Tabriz Islamic Art University collaborators