به جمع مشترکان مگیران بپیوندید!

تنها با پرداخت 70 هزارتومان حق اشتراک سالانه به متن مقالات دسترسی داشته باشید و 100 مقاله را بدون هزینه دیگری دریافت کنید.

برای پرداخت حق اشتراک اگر عضو هستید وارد شوید در غیر این صورت حساب کاربری جدید ایجاد کنید

عضویت
جستجوی مقالات مرتبط با کلیدواژه

Optimization Algorithms

در نشریات گروه فناوری اطلاعات
تکرار جستجوی کلیدواژه Optimization Algorithms در نشریات گروه فنی و مهندسی
تکرار جستجوی کلیدواژه Optimization Algorithms در مقالات مجلات علمی
  • علی جهانبخش، مهدی جهانگیری *

    تکامل سریع فناوری و پیچیدگی روزافزون محیط های آموزشی، رویکردهای نوآورانه ای را برای آموزش زبان ضروری می کند. این مقاله به بررسی تلاقی تکنیک های بهینه سازی در محاسبات نرم و کاربرد آنها در آموزش زبان انگلیسی (ELT) در ایران می پردازد. ضرورت و اهمیت این بازنگری ناشی از چالش هایی است که مربیان در انطباق روش های تدریس سنتی برای برآوردن نیازهای متنوع فراگیران در یک چشم انداز دیجیتالی به سرعت در حال تغییر با آن مواجه هستند. این مطالعه پتانسیل آنها را برای افزایش تجارب یادگیری شخصی، بهبود طراحی برنامه درسی و تسهیل استراتژی های ارزیابی تطبیقی ​​با ترکیب ادبیات موجود در مورد روش های محاسباتی نرم مانند منطق فازی، شبکه های عصبی و الگوریتم های ژنتیک برجسته می کند. این کار به شکلی نوآورانه این تکنیک های بهینه سازی را در چارچوب های ELT ادغام می کند و مدلی را پیشنهاد می کند که از بینش های داده محور برای تنظیم استراتژی های آموزشی با توجه به پروفایل های فردی یادگیرنده استفاده می کند. یافته های کلیدی نشان می دهد که هنگام استفاده از روش های محاسباتی نرم، پیشرفت های قابل توجهی در تعامل دانش آموزان، میزان حفظ و مهارت زبان وجود دارد. علاوه بر این، نتایج نشان می دهد که چنین رویکردهایی می توانند چالش های زبانی و فرهنگی منحصربه فردی را که زبان آموزان ایرانی با آن مواجه هستند، برطرف کرده و محیط آموزشی فراگیرتر و موثرتری را ایجاد کنند. این مقاله با ارائه شواهدی از مزایای بهینه سازی در محاسبات نرم، به گفتمان جاری در مورد آموزش زبان پیشرفته با فناوری کمک می کند. این امر بر ضرورت پذیرش این روش ها برای متحول کردن آموزش زبان انگلیسی توسط مربیان و سیاست گذاران در ایران تاکید می کند و در نهایت زبان آموزان را به مهارت های لازم برای پیشرفت در دنیایی به هم پیوسته مجهز می کند.

    کلید واژگان: محاسبات نرم، آموزش زبان انگلیسی (ELT)، الگوریتم های بهینه سازی، ارزیابی یادگیری گرا (LOA).
    Ali Jahanbakhsh, Mehdi Jahangiri *

    The rapid evolution of technology and the increasing complexity of educational environments necessitate innovative approaches to language instruction. This paper explores the intersection of optimization techniques in soft computing and their application to English language teaching (ELT) in Iran. The necessity and importance of this review stem from the challenges faced by educators in adapting traditional teaching methodologies to meet the diverse needs of learners in a rapidly changing digital landscape. This study highlights their potential to enhance personalized learning experiences, improve curriculum design, and facilitate adaptive assessment strategies by synthesising existing literature on soft computing methods such as fuzzy logic, neural networks, and genetic algorithms. The work innovatively integrates these optimization techniques into ELT frameworks, proposing a model that leverages data-driven insights to tailor instructional strategies according to individual learner profiles. Key findings reveal significant improvements in student engagement, retention rates, and language proficiency when soft computing methods are employed. Moreover, the results indicate that such approaches can address the unique linguistic and cultural challenges faced by Iranian learners, fostering a more inclusive and effective educational environment. This paper contributes to the ongoing discourse on technology-enhanced language education by providing evidence of the benefits of optimization in soft computing. It underscores the imperative for educators and policymakers in Iran to embrace these methodologies to transform ELT, ultimately equipping learners with the skills necessary to thrive in an interconnected world.

    Keywords: Soft Computing, English Language Teaching (ELT), Optimization Algorithms, Learning-Oriented Assessment (LOA)
  • Zeinab Kalantari, Marzieh Gerami, Mohammad eshghi

    Reversible logic has been emerged as a promising computing paradigm to design low power circuits in recent years. The synthesis of reversible circuits is very different from that of non-reversible circuits. Many researchers are studying methods for synthesizing reversible combinational logic. Some automated reversible logic synthesis methods use optimization algorithms Optimization algorithms are used in some automated reversible logic synthesis techniques. In these methods, the process of finding a circuit for a given function is a very time-consuming task, so it’s better to design a processor which speeds up the process of synthesis. Application specific instruction set processors (ASIP) can benefit the advantages of both custom ASIC chips and general DSP chips. In this paper, a new architecture for automatic reversible logic synthesis based on an Application Specific Instruction set Processors is presented. The essential purpose of the design was to provide the programmability with the specific necessary instructions for automated synthesis reversible. Our proposed processor that we referred to as ARASP is a 16-bit processor with a total of 47 instructions, which some specific instruction has been set for automated synthesis reversible circuits. ARASP is specialized for automated synthesis of reversible circuits using Genetic optimization algorithms. All major components of the design are comprehensively discussed within the processor core. The set of instructions is provided in the Register Transform Language completely. Afterward, the VHDL code is used to test the proposed architecture.

    Keywords: Reversible logic, Optimization Algorithms, Application Specific Instruction Set Processors, ASIP, RTL
  • Mohammad Hassanzadeh, Farshid Keynia *
    Metaheuristic algorithms are typically population-based random search techniques. The general framework of a metaheuristic algorithm consisting of its main parts. The sections of a metaheuristic algorithm include setting algorithm parameters, population initialization, global search section, local search section, and checking the stopping conditions in a metaheuristic algorithm. In the parameters setting section, the user can monitor the performance of the metaheuristic algorithm and improve its performance according to the problem under consideration. In this study, an overview of the concepts, classifications, and different methods of population initialization in metaheuristic algorithms discussed in recent literature will be provided. Population initialization is a basic and common step between all metaheuristic algorithms. Therefore, in this study, an attempt has been made that the performance, methods, mechanisms, and categories of population initialization in metaheuristic algorithms. Also, the relationship between population initialization and other important parameters in performance and efficiency of metaheuristic algorithms such as search space size, population size, the maximum number of iteration, etc., which are mentioned and considered in the literature, are collected and presented in a regular format.
    Keywords: Classification, Clustering, metaheuristic algorithms, Optimization Algorithms
  • Zeynab Sedreh *, Mehdi Sadeghzadeh
    In path planning Problems, a complete description of robot geometry, environments and obstacle are presented; the main goal is routing, moving from source to destination, without dealing with obstacles. Also, the existing route should be optimal. The definition of optimality in routing is the same as minimizing the route, in other words, the best possible route to reach the destination. In most of the routing methods, the environment is known, although, in reality, environments are unpredictable;But with the help of simple methods and simple changes in the overall program, one can see a good view of the route and obstacles ahead. In this research, a method for solving robot routing problem using cellular automata and genetic algorithm is presented.In this method, the working space model and the objective function calculation are defined by cellular automata, and the generation of initial responses and acceptable responses is done using the genetic algorithm.During the experiments and the comparison we made, we found that the proposed algorithm yielded a path of 28.48 if the lengths of the paths obtained in an environment similar to the other algorithm of 15 / 32, 29.5 and 29.49, which is more than the proposed method.
    Keywords: Robot Path Planning, Optimization Algorithms, Cellular Automata, Genetic algorithm, Optimal Routing
  • Farnaz Hoseini, Asadollah Shahbahrami, Peyman Bayat
    Deep learning is one of the subsets of machine learning that is widely used in Artificial Intelligence (AI) field such as natural language processing and machine vision. The learning algorithms require optimization in multiple aspects. Generally, model-based inferences need to solve an optimized problem. In deep learning, the most important problem that can be solved by optimization is neural network training, but training a neural network can involve thousands of computers for months. In the present study, basic optimization algorithms in deep learning were evaluated. First, a performance criterion was defined based on a training dataset, which makes an objective function along with an adjustment phrase. In the optimization process, a performance criterion provides the least value for objective function. Finally, in the present study, in order to evaluate the performance of different optimization algorithms, recent algorithms for training neural networks were compared for the segmentation of brain images. The results showed that the proposed hybrid optimization algorithm performed better than the other tested methods because of its hierarchical and deeper extraction.
    Keywords: Deep Learning, Optimization Algorithms, Stochastic Gradient Descent, Momentum, Nestrove, Adam
  • Peyman Goli, Mohammad Reza Karami, Mollaei
    A new speech intelligibility improvement method for near-end listening enhancement in noisy environments is proposed. This method improves speech intelligibility by optimizing energy correlation of one-third octave bands of clean speech and enhanced noisy speech without power increasing. The energy correlation is determined as a cost function based on frequency band gains of the clean speech. Interior-point algorithm which is an iterative procedure for the nonlinear optimization is used to determine the optimal points of the cost function because of nonlinearity and complexity of the energy correlation function. Two objective intelligibility measures, speech intelligibility index and short-time objective intelligibility measure, are employed to evaluate the noisy enhanced speech intelligibility. Furthermore, the speech intelligibility scores are compared with unprocessed speech and a baseline method under various noisy conditions. The results show large intelligibility improvements with the proposed method over the unprocessed noisy speech.
    Keywords: Near, end Speech Enhancement, Intelligibility Improvement, Energy Correlation, Optimization Algorithms
نکته
  • نتایج بر اساس تاریخ انتشار مرتب شده‌اند.
  • کلیدواژه مورد نظر شما تنها در فیلد کلیدواژگان مقالات جستجو شده‌است. به منظور حذف نتایج غیر مرتبط، جستجو تنها در مقالات مجلاتی انجام شده که با مجله ماخذ هم موضوع هستند.
  • در صورتی که می‌خواهید جستجو را در همه موضوعات و با شرایط دیگر تکرار کنید به صفحه جستجوی پیشرفته مجلات مراجعه کنید.
درخواست پشتیبانی - گزارش اشکال