فهرست مطالب

  • Volume:10 Issue:2, 2019
  • تاریخ انتشار: 1398/09/10
  • تعداد عناوین: 20
|
  • S. Vakili *, H. Toosianshandiz Pages 1-10
    In this paper, based on a fractional order Bergman minimal model, a robust strategy for regulationof blood glucose in type 1 diabetic patients is presented. Glucose/insulin concentration in the patientbody is controlled through the injection under the patients skin by the pump. Many various con-trollers for this system have been proposed in the literature. However, most of them have considerthe system as an integer order system. Moreover, the majority of the presented methods suffer froman important disadvantage that is long settling time of the control system. Thus, the contribution ofthis paper in comparison with previous related works is presenting a fractional back-stepping slidingmode control that considerably reduces the required time for glucose to reach its desired level. Dueto the sliding mode design, the proposed controller is robust against external disturbances. Due tothe back-stepping design, convergence of each state variable of the system to its desired value canbe guaranteed separately. Simulation results verify the satisfactory performance of the proposedcontroller.
    Keywords: Fractional order control, sliding mode control, back-stepping design, blood glucose regulation, Fractional Bergman minimal model, Lyapunov fractional
  • M. Iranpour Mobarakeh *, H. Yarmohammadi Pages 11-21

    Word spotting is to make searchable unindexed image documents by locating word/words in a doc-ument image, given a query word. This problem is challenging, mainly due to the large numberof word classes with very small inter-class and substantial intra-class distances. In this paper, asegmentation-based word spotting method is presented for multi-writer Persian handwritten doc-uments using attribute-based classi cation and label-embedding. For this purpose, a hierarchicalframework is proposed, in which at rst, the candidate are selected based on connected compo-nents(CCs) sequence. Then, the query word is segmented to constructor CCs, and similar CCs countin the candidate region of document are selected based on their distances to the CCs count of thequery word. As a result, the candidate regions are extracted. In the nal phase, the query wordis located only in the candidate regions of the document. A well known Persian handwritten textdataset, namely FTH, is chosen as a benchmark for the presented method. The results shows thatthe proposed method outperforms the state-of-the-art methods, 81.02 percent for unseen word classretrieval.

    Keywords: Persian handwritten documents, connected component, attribute-based classifi cation, label embedding
  • Jahangir Mobarezpour, Reza Khosrowabadi *, Reza Ghaderi, Keivan Navi Pages 23-33
    AbstractAccuracy in identifying the subjects’ intentions for moving their different limbs from EEG signals is regarded as an important factor in the studies related to BCI. In fact, the complexity of motor-imagination and low amount of signal-to-noise ratio for EEG signal makes this identification as a difficult task. In order to overcome these complexities, many techniques such as various feature extraction methods, learning algorithms, and classifier schemes have been developed in this regard. However, conducting more research is necessary for improvement. The present study aimed to use an ensemble learning approach to improve the performance of MI-BCI systems. Therefore, filter bank common spatial pattern (FBCSP), as a well-known feature extraction method, was used to produce separable features from EEG signals. Accordingly, error correcting output codes (ECOC) was applied on several learning algorithms to classify four classes of motor imagery tasks. The proposed ECOC ensemble technique was tested on the data set 2a from BCI competition IV. Based on the results, the ECOC can lead to an improvement by using the naive Bayesian parzen window algorithm, compared to the winner algorithm of BCI competition IV, which is superior to other selected state of the art algorithms.
    Keywords: Brain computer interface (BCI), Error Correcting Output Codes (ECOC), Electroencephalography (EEG), Motor imagery, Filter bank common spatial pattern (FBCSP)
  • Gholamhossein Yari * Pages 35-46
    In this paper, we investigate some inferential properties of the upper record Lomax distribution. Also, we will estimate the upper record of the Lomax distribution parameters using methods, Moment (MME), Maximum Likelihood (MLE), Kullback-Leibler Divergence of the Survival function (DLS) and Baysian. Finally, we will compare these methods using the Monte Carlo simulation.
    Keywords: Lomax distribution, Upper record, Entropy, Parameter estimation, Simulation
  • Yadollah Hemmati, Seyed Ali Nabavi Chashmi *, Rahmat Alizadeh Pages 47-85

    In recent years, banks and financial institutions have always been at the forefront of identifying and assessing the operational risk of banking products and activities, processes and banking systems for effective risk management as an essential element of the Bank's risk management program of Banks. So that banks were able to reduce or even annihilate the potential risks of their banking activities. Therefore, the main objective of this study is to evaluate the strategic risks of credit processes in the banking system of Iran. The research method is also descriptive-applied and statistical population includes experts of banking and risk management. Data collection was performed by laboratory and field (questionnaire distribution) methods. In order to analyze the data, we used statistical tests (descriptive and inferential), factor analysis and multiple regression analysis. Therefore, the findings of this study illustrate that strategic risks of credit processes have a major effect on the performance of management of credit risks and operational risks in the banking system of Iran.

    Keywords: Operational risk, Credit processes, Banking system of Iran
  • Mohammad Abdolahi *, Morteza Zahedi Pages 87-96
    Word embeddings (WE) have received much attention recently as word to numeric vectors architecture for all text processing approaches and has been a great asset for a large variety of NLP tasks. Most of text processing task tried to convert text components like sentences to numeric matrix to apply their processing algorithms. But the most important problems in all word vector-based text processing approaches are different sentences size and as a result, different dimension of sentences matrices. In this paper, we suggest an efficient but simple statistical method to convert text sentences into equal dimension and normalized matrices Proposed method aims to combines three most efficient methods (averaging based, most likely n-grams, and word’s mover distance) to use their advantages and reduce their constraints. The unique size resulting matrix does not depend on language, Subject and scope of the text and words semantic concepts. Our results demonstrate that normalized matrices capture complementary aspects of most text processing tasks such as coherence evaluation, text summarization, text classification, automatic essay scoring, and question answering.
    Keywords: Text Preprocessing, Sentence Normalization, Word Embedding, Word Vector, Sentence Vector
  • Ahmadreza Ghaznavi, SMT Almodarresi * Pages 97-110
    This research investigates the delay sensitivity of discrete-time consensus among agents which communicate over a scale-free network with hubs. In this paper, a novel hierarchical consensus algorithm, based on the idea of virtual communication graph degree reduction, is proposed. As a result, a significant consensus speed gain is obtained which provides a potential time margin for applying cyber-physical techniques that cause systematic input delay. This approach provides robustness and resiliency in case of any communication topology disturbance during cyber- physical attacks or plug-and-play events. The feasibility of plug- and-play, which has the potential to increase the input delay, is presented based on the gained margin as a sample scenario. The algorithm application in the coordination of distributed photovoltaic resources of several nano-grids communicating over a scale-free network, is assessed via simulation as well.
    Keywords: Discrete-time consensus, delay, DC nano-grid, hierarchical control, multi-agent system, network with hub, plug- and-play, robust, resilient consensus, scale-free network
  • A Jabbari, F Hosseinzadehlotfi *, Gh Jahanshahloo, M Rostamy Malkhalifeh Pages 111-129

    Data envelopment analysis (DEA) helps the managers to separate and classify the efficient and inefficient units in a homogenous group. DEA is a set of methods inferred from mathematics and other sciences in which the branch of unit ranking can be significantly effective in improving managerial decisions. Although this branch in DEA is considered still young, it has proved its ability in solving some problems like production planning, resource allocation, inventory control, etc. The managers who care about their results quality cannot be indifferent to units ranking. In this article, to rank the units which are under-evaluated, firstly the decision-making unit (DMU) is removed from the production possibility set (PPS), and then the new PPS is produced. The unit under evaluation is inside or outside of the new PPS. Therefore, to benchmark the under-evaluation DMU to new frontiers, two models are solved. If the removed unit is outside of the new PPS, the first model is feasible, and the second model is infeasible. If the removed unit is inside or on the frontier of the new PPS, both models are feasible. The method presented in this article for ranking the under-evaluation units has these characteristics: 1- this model can distinguish extreme and non-extreme efficient units and inefficient units. 2- Also, the presented models for ranking DMUs can be changed into a linear model. 3- This method shows stability in changing small or near-zero data. 4- It does not assign a false ranking. The presented methods in this article are able to distinguish the set of extreme and non-extreme efficient and inefficient units as well as being able to overcome the common problems in ranking. In this article, suggested models are introduced in subsec3.1 which are able to rank all under evaluation units except non-extreme efficient units, this problem is solved in subsec3.2, in other words in subsec3.2 all DMUs are ranked

    Keywords: DEA, Ranking, Pareto-efficient, Infeasibility, Extreme efficient, Non-extreme efficient
  • Hadi Yarmohammadi *, Hossein Marvi, Hamid Hassanpour Pages 131-140
    In this paper, a novel method for video content summarization has been proposed by calculating the fractal dimension of frames. Summarization of the video is the first step in automatic video analysis. In this paper, we use the support vector machine (SVM) and the decision - tree to identify the shot boundary and classify them. In order to compute the fractal dimension, the numerical method has been expressed. The results of this implementation were also reported on TRECVID 2006 data collection. The results show that the relative advantage of the method presented in this paper is compared to other articles.
    Keywords: Video summarization, Shot boundary detection, Key frame extraction, Support Vector Machine
  • Heliasadat Hosseinian *, Hamidreza Damghani, Leila Damghani, Erfan Kouhi, Mahdi Kouhi Pages 141-152
    Asia is creating, and its urban areas are going to assume a noteworthy job in this undertaking to coordinate created partners. Asian exchange, populace, the geographic size of its urban areas and commitment to worldwide advancement will just increment in the years to come. Country settlements or immature towns are quickly changing over themselves to little towns; little towns are changing over themselves into little urban communities, and existing little urban communities are moving forward into getting to be megacities. This statistic change in the urban scene will just build the utilization of assets like land, water, clean air, sanitation, control, transport system, and security so as to endure and develop. The amount and nature of venture that Asian urban communities make today in these assets will enable them to support and continue their prospering populace later on. It is in this manner basic that urban arranging, utilization of innovation, modern vision and control procedures that are fused, work in a joint effort to make progress. Present-day megacities like Tokyo, Seoul, Beijing, Shanghai, Manila, Jakarta, Mumbai, Delhi, Karachi, Istanbul, Tehran, Moscow, and so forth have them a lot of issues.
    Keywords: Smart Cities, IoT, Development
  • Iman Firouzian *, Morteza Zahedi, Hamid Hassanpour Pages 153-166
    Process Mining is a rather new research area in artificial intelligence with handles event logs usually recorded by information systems. Although, remaining time prediction of ongoing business instances has been always a research question in this area, most of the existing literature does not take into account dynamicity of environment and the underlying process commonly known as concept drift. In this paper, a two-phase approach is presented to predict the remaining time of ongoing process instances; in the first phase, future path of process instances is predicted using an annotated transition system with Fuzzy Support Vector Machine probabilities based on case data and in the second phase, the remaining time is predicted by summing up the duration of future activities each estimated by Support Vector Regressor. Finally, a concept drift adaptation method is proposed. To benchmark the proposed prediction method along with the proposed concept drift adaptation method, experiments are conducted using a real-world event log and a simulation event log. The results show that the proposed approach gained 13% improvement on remaining time prediction in case of concept drift.
    Keywords: Business Process, Process Mining, Remaining Time Prediction, Concept Drift
  • S. Vakili *, H. Toosianshandiz Pages 167-176
    In this study, based on Bergman minimal model, a robust techniqe for adjust of blood glucose in type 1 diabetic patients is presented. Glucose-insulin concentration in the patient body is controlled through the injection under the patient’s skin by the pump. Many various controllers for this system have been proposed in the articles. However, most of them suffer from an important disadvantage that is long settling time of the control system. Thus, the contribution of this paper in comparison with previous related works is presenting a backstepping sliding mode control that considerably reduces the required time for glucose to reach its desired level. Due to the sliding mode design, the proposed controller is robust against external disturbances. Due to the back-stepping design, convergence of each state variable of the system to its desired value can be guaranteed separately. Simulation results, verify the satisfactory performance of the proposed controller.
    Keywords: sliding mode control, back-stepping design, blood glucose regulation, Bergman minimal model
  • A. Pourghaffari *, M. Barari Pages 177-188
    With advances in virtualization technology, cloud computing has become the most powerful and promising platform for business, academia, public and government organizations. Scheduling these workflows and load balancing to get better success rate becomes a challenging issue in cloud computing. In this paper, we used Cats and Dragonfly Optimization (CSO-DA) algorithm to balance the Load in the process of allocating resources to virtual machines in cloud computing in order to improve the speed and accuracy of scheduling. The proposed method consists of the following steps: initialization of the algorithm and cloud computing, determining the number of virtual machines and the number of tasks, implementing a dragonfly optimization algorithm for choosing the best host and implementing a cat collapse algorithm for balancing the load and Schedule tasks between virtual machines. Our experiments show that as far as run time, response time, task immigration and significant load balances are concerned, our proposed model combining cat and dragonfly optimization algorithms achieved better performance in allocating resources and load balance between virtual machines than other methods.
    Keywords: Task Scheduling, Load Balance, Cat Optimization Algorithm, Dragonfly Optimization, cloud computing
  • Mohammad Mahdi Nematollahi *, Omid Reza Marouzi Pages 189-196
    Open information extraction is a new technology in the text mining process which is still at the beginning and requires many attempts and considerations for improvement. These attempts includes both the representation and extraction of information. The complication and instability of language intensify the problems of the open information extraction. In this article an advanced representation of information is presented for the Persian language; a representation which can be a favorable cover for the open information extraction by identifying dependency analysis relationships. In the present article, it is tried to reach the feasibility of this representation, the representation correspondence using syntactic labeling, and plausible representation of information extraction. By making this attempts, the threshold for the information extraction goes far beyond its simple  epresentation state, which is a tripple. Although this article tries to overally outline the approach of using an advanced representation of information extraction, it specifically investigates the use of this representation in QA systems.
    Keywords: Open Information Extraction, Representation of Information, Syntactic Labeling, Question, Answer Systems
  • Elif Turanli, Izzettin Demir *, Oya Bedre Ozbakir Pages 197-211
    In this paper, we introduce the soft $mathcal{I}$-paracompact spaces and the soft $mathcal{I}$-S-paracompact spaces. First, we investigate the relationships between these spaces and soft paracompact spaces. Also, we give some fundamental properties of these spaces. Finally, we prove that soft $mathcal{I}$-S-paracompact spaces are invariant under perfect mappings.
    Keywords: soft set, soft ideal, soft paracompact space, soft S-paracompact space, soft $mathcal{I}$-paracompact space, soft $mathcal{I}$-S-paracompact space, soft perfect mapping
  • Ulam-Hyers-Rassias stability for stochastic integral equations of Volterra type
    Vu Ho *, Le Si Dong Pages 213-225
    In this paper, we study the Ulam--Hyers--Rassias stability for stochastic integral equations of Volterra type by using fixed point theorem and Pachpatte's inequality.
  • Cristian Alecsa * Pages 227-254
    It is well known that fixed point problems of contractive-type mappings defined on cone metric spaces over Banach algebras are not equivalent to those in usual metric spaces (see [3] and [10]). In this framework, the novelty of the present paper represents the development of some fixed point results regarding sequences of contractions in the setting of cone metric spaces over Banach algebras. Furthermore, some examples are given in order to strengthen our new concepts. Also, based on the powerful notion of a cone metric space over a Banach algebra, we present important applications to systems of differential equations and coupled functional equations, respectively, that are linked to the concept of sequences of contractions.
    Keywords: Banach algebras, (G)-convergence, (H)-convergence, differential equations, fixed points, sequences of contractions
  • Farah Balaadich *, Elhoussine Azroul Pages 255-266
    In this paper, we consider the boundary value problem of a quasilinear elliptic system in degenerate form with data belongs to the dual of Sobolev Spaces. The existence result is proved by means of Young measures and mild monotonicity assumptions.
    Keywords: Quasilinear elliptic systems, weak solution, Sobolev space, Young measure
  • Morteza Essmaili * Pages 267-273
    Let $A$ be a Banach algebra and $X$ be an arbitrary Banach $A$-module. In this paper, we study the second transpose of derivations with value in dual Banach $A$-module $X^{*}.$ Indeed, for a continuous derivation $D:Alongrightarrow X^{*}$ we obtain a necessary and sufficient condition such that the bounded linear map $Lambdacirc D^{primeprime}:A^{**}longrightarrow X^{***}$ to be a derivation, where $Lambda$ is composition of restriction and canonical injection maps. This characterization generalizes some well known results in [2].
    Keywords: Derivation, second transpose, Banach module, module actions
  • Artion Kashuri *, Muhammad Ali, Mujahid Abbas, Huseyin BUDAK Pages 275-299
    In the present work, we prove a parametrized identity for a differentiable function via generalized integral operators. By applying the established identity and the new so-called generalized m-convex function, some generalized trapezium, Ostrowski and Simpson type integral inequalities have been discovered. Various special cases have been studied as well. Some applications of the present results to special means and new error estimates for the trapezium and midpoint quadrature formula have been investigated. It is hoped that the methods and techniques of this paper could further stimulate the research conducted in the field of integral inequalities.
    Keywords: Trapezium inequality, Ostrowski inequality, Simpson inequality, convexity, general fractional integrals