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

algorithm

در نشریات گروه فنی و مهندسی
  • K. Raghavendra Rao, R. Ramya Kalangi, B. Balaji *, V. Agarwal
    The use of mobile devices with multiple interfaces has transformed communication by enabling simultaneous data transfers. This capability has driven the adoption of the Multipath Transmission Control Protocol (MPTCP), which leverages multiple interfaces to transmit data concurrently over different paths, improving overall connectivity. However, several factors affect MPTCP performance, including fluctuations in sub-flows, out-of-order (OOO) packet delivery, and inefficiencies in retransmitting lost packets. Addressing these challenges is crucial for enhancing MPTCP efficiency. Optimizing retransmission strategies can improve both throughput and reliability while mitigating sub-flow irregularities ensuring stable communication. Although various methodologies have been proposed, most existing approaches primarily focus on packet scheduling, with limited emphasis on lost packet retransmission as a distinct issue. This work highlights the importance of retransmission alongside scheduling mechanisms. The proposed approach consists of three key modules, identification of packets requiring retransmission, selection of the optimal path, and transmission of these packets through an active and available route. To achieve this, our methodology marks lost packets with a retransmission flag and efficiently routes them through the selected path, enhancing MPTCP and minimizing delays in data delivery. The proposed scheme was implemented in NS-3.4 and evaluated using delay-sensitive applications. The results demonstrate that our methodology significantly outperforms existing approaches, making it a promising solution for improving MPTCP performance. Specifically, FBMPTCP-CWND and FBMPTCP-SSTHRESH achieve superior performance over the existing methodology by increasing throughput by 5%, reducing jitter by 13%, lowering packet retransmissions by 33%, and decreasing delay by 8%.
    Keywords: Algorithm, Flow Control, Buffer, Sender, Latency
  • Hamidreza Hanif *

    Quantum computing and artificial intelligence are two advanced and emerging areas of science and technology, each of which has the potential to bring about massive changes in various industries. Combining these two technologies could lead to significant innovations. Quantum computing uses the principles of quantum physics to perform computational operations, which helps to achieve faster solutions to complex problems. Artificial intelligence uses its algorithms to build and improve intelligent systems capable of designing, thinking, and making decisions. Combining these two technologies will lead to greater power in solving complex problems and improving the efficiency of artificial intelligence systems. Although quantum computing has great potential, it is still in the early stages of development and faces many technical challenges. These include the stability of qubits, quantum errors, and the need for extremely cold environments for quantum systems to operate. As research in both fields’ advances, the interaction of quantum computing and artificial intelligence is expected to lead to significant results and create a huge transformation in various industries, including medicine, finance, logistics, and information technology. In quantum artificial intelligence, quantum computing power is used to optimize this problem. For example, a quantum algorithm known as a “quantum search algorithm” can process the search space in parallel and quickly converge to an optimal solution. Suppose we have a quantum network that can put qubits into different states at the same time. This property allows us to explore all possible paths in parallel. Then, using quantum algorithms such as Grover’s Algorithm, we can reach the optimal path faster than classical algorithms.

    Keywords: Algorithm, Artificial Intelligence, ‎Quantum Computing, Optimization.‎
  • Amin Asgari *, Mohammad Mehrad, Imandokht Mostafavi, Misha Pezeshki
    The static Young’s modulus (Esta) and the uniaxial compressive strength (UCS) are key parameters in the geomechanical study of hydrocarbon reservoirs. These parameters are typically estimated using empirical models that relate the strength and elastic parameters of the rock to their petrophysical properties. In the present research, the existing empirical models in the literature (specifically for carbonate rocks) were compiled and investigated, this was followed by performing experimental tests on 27 core samples to measure the porosity (n), the density (ρ), the compressive and shear wave velocities (Vp and Vs, respectively), Esta and UCS for a carbonate gas reservoir in the south of Iran. Next, particle swarm optimization (PSO) and regression analysis (RA) were conducted to develop estimator models for the Esta and UCS. Results of this study showed that the best models produced by the PSO algorithm were more accurate than not only the best models produced by the RA, but also the models proposed by previous researchers by 7% and 48%, respectively, for the Esta and by 10% and 7%, respectively, for the UCS. On this basis, it was strongly recommended to apply the empirical correlations developed through the PSO for more accurate estimation of the studied parameters across the investigated field and similar fields.
    Keywords: Young’S, Modulus, UCS, Carbonate, Reservoir, PSO, Algorithm
  • یاشار سلامی*، یاسر عبازاده، مهدی همرنگ، نوشین الله بخشی

    با رشد سریع اینترنت اشیاء (IoT)، تعداد دستگاه های متصل به شبکه های مختلف به طور قابل توجهی افزایش یافته است. این دستگاه ها مقادیر زیادی داده تولید می کنند و غالبا در محیط های باز و ناامن مستقر می شوند که آن ها را در معرض حملات سایبری مختلف قرار می دهد. بنابراین، اطمینان از امنیت شبکه های IoT به یک نگرانی اصلی برای محققان تبدیل شده است. یکی از موثرترین روش ها برای حفظ امنیت شبکه، استفاده از سیستم های تشخیص نفوذ (IDS) است. تشخیص نفوذ، داده های ورودی را نظارت و تحلیل می کند تا فعالیت های مشکوک و حملات احتمالی را شناسایی کند. با توجه به محدودیت های منابع دستگاه های IoT و پیچیدگی شبکه ها، بهبود دقت و کارآیی IDS بسیار حائز اهمیت است. هدف اصلی این تحقیق، ارائه یک IDS جدید و بهینه سازی شده برای شبکه های IoT است. یک روش انتخاب ویژگی ترکیبی برای افزایش دقت و کاهش پیچیدگی محاسباتی به کار گرفته شده است که شامل فیلتر کردن مبتنی بر همبستگی و روش های پوششی با استفاده از الگوریتم بهینه سازی شاهین هریس (HHO) می باشد. در این رویکرد، ویژگی های غیرضروری حذف و ویژگی های ضروری برای طبقه بندی انتخاب می شوند. نتایج شبیه سازی نشان می دهد که این روش به دقت 96.46% دست یافته است و در مقایسه با روش های سنتی مانند DT و SVM عملکرد بهتری داشته و نرخ های مثبت کاذب و منفی کاذب را بهبود بخشیده است.

    کلید واژگان: اینترنت اشیا، تشخیص نفوذ، بهینه سازی، الگوریتم
    Yashar Salami *, Yaser Ebazadeh, Mehdi Hamrang, Nooshin Allahbakhshi

    With the rapid growth of the IoT, the number of devices connected to various networks has significantly increased. These devices generate vast amounts of data and are often deployed in open and unsecured environments, making them vulnerable to cyber-attacks. Therefore, ensuring the security of IoT networks has become a primary concern for researchers. One of the most effective methods for maintaining network security is using IDS. Intrusion detection monitors and analyzes incoming data to detect suspicious activities and potential attacks. Given the resource constraints of IoT devices and the complexity of the networks, improving the accuracy and efficiency of IDS is crucial. The primary goal of this research is to present a novel and optimized IDS for IoT networks. A hybrid feature selection method has been employed to enhance accuracy and reduce computational complexity, combining correlation-based filtering and wrapper methods using the (HHO) algorithm. In this approach, unnecessary features are removed, and essential features for classification are selected. Simulation results indicate that this method has achieved a 96.46% accuracy, outperforming traditional methods such as DT and SVM while improving false positive and false negative rates.

    Keywords: Iot, IDS, Optimization, Algorithm
  • Mohammadhossein Darvish Motevalli, Fariba Salahi *, Ladan Riazi, Adel Pourghader Chobar

    Taking into account the fact that social media are today known as a platform to express and relieve the emotions, stress, and concerns that adolescents face in their daily lives, the ground has been provided for self-seekers. This is to the extent that these websites have been raised as a place for serious social problems and that vulnerable people, especially adolescents, are harassed on the Internet, commit suicide, or become bullies who harm others. Many new research papers are published every day in which various artificial intelligence (AI) techniques are applied to various tasks and applications related to sentiment analysis.

    Keywords: Sentiment Analysis, Support Vector Machine, Algorithm, Grey Wolf Optimization
  • B. Saham, A. Sarraf *, B. Aminnejad
    The aim of this study is to optimize water resource management in the Jarrahi River Basin with an environmental sustainability approach for the Shadgan International Wetland. The Jarrahi River is one of the rivers in the Persian Gulf and Oman Sea drainage basin, with most of its course located in Khuzestan province. The river's catchment area lies on the southwestern slopes of the Middle Zagros Mountains and is located between 48°45' and 51°10' East longitude and 30°30' to 31°40' North latitude. Its area is 24,300 square kilometers. A water resource planning model for the entire Marun and Jarrahi river system was developed using an optimization approach. The entire Marun-Jarrahi watershed was simulated in a monthly time step over a 60-year period using the WEAP simulator, and five scenarios were defined. The results were then integrated and analyzed using the powerful Shahin Harin meta-exploration algorithm. Based on the results, the release pattern for water utilization within the standard benchmark four and ten tank system using Harris Hawks Optimization (HHO), FPA, and SOS algorithms, the exploitation policies derived from the HHO algorithm with a more optimal release pattern yielded the highest benefit. Additionally, the model with the least water shortage was identified using this approach. These results demonstrate the superior efficiency of the HHO algorithm compared to the other meta-exploration algorithms employed. As a further innovation, study proposes and develops a novel hybrid model combining HHO and Cat Swarm Optimization (CSO) algorithms, referred to as the HHO-CSO algorithm.
    Keywords: Algorithm, Jarrahi River, Hybrid Harris Hawks-Cat Swarm Optimization, Water Resource Management
  • علی حدادی*، مهدی پارسا
    در قرن بیستم جمع آوری، پردازش و توزیع اطلاعات توسط بکارگیری شبکه های توزیعی و رویکردهای نوین مرتبط متحول گشته و در بین سایر پیشرفت ها، شاهد راه اندازی و توسعه انواع شبکه های توزیعی جهانی، تولید و رشد بی سایقه صنعت کامپیوتر و پرتاب ماهواره های ارتباطی بوده ایم.با پیشرفت های فناور محور این دستاوردها درحال همگرایی است و تفاوت های بین رویکردهای جمع آوری، انتقال، ذخیره و پردازش اطلاعات به شدت در حال محو شدن است و اصولا با افزایش قدرت جمع آوری، پردازش و توزیع اطلاعات، تقاضای پردازش اطلاعات پیچیده تر در محیط شبکه های توزیعی افزایش می یابد. بمنظور برقراری ارتباط بین نودها در شبکه ها نیازمند ستون فقراتی بنام رویکردهای مسیریابی در شبکه های توزیعی می باشیم. این کارکردها اساسا از تعداد زیادی مسیریاب تشکیل شده است وظیفه انتقال اطلاعات را دارند. بر روی این مسیریاب ها باید الگوریتم هایی اجرا شوند تا بتوانند بهترین مسیر را برای انتقال اطلاعات در این دهکده جهانی انتخاب کنند. در این مقاله قصد داریم دیدگاه های کاربردی درخصوص مسیریابی در شبکه های توزیعی و الگوریتم های عمومی مرتبط را بررسی و تحلیل نماییم.
    کلید واژگان: شبکه های توزیعی، روش مسیریابی، الگوریتم، دیدگاه مسیریابی تطابقی، روش غیرتطبیقی
    Ali Haddadi *, Mahdi Parsa
    In the 20th century, the collection, processing and distribution of information has been transformed by the use of distribution networks and related new approaches, and among other developments, we have seen the launch and development of various global distribution networks, the production and growth of the computer industry, and the launch of satellites. We have been in communication.With technological advancements, these achievements are converging and the differences between the approaches to collecting, transmitting, storing and processing information are rapidly disappearing, and basically, with the increase in the power of collecting, processing and distributing information, the demand for more complex information processing in The environment of distributed networks increases. In order to communicate between nodes in networks, we need a backbone called routing approaches in distributed networks. These functions are basically composed of a large number of routers, they have the task of transmitting information. Algorithms should be implemented on these routers so that they can choose the best path for information transfer in this global village. In this article, we are going to review and analyze the practical views of routing in distributed networks and related general algorithms.
    Keywords: Distribution Networks, Routing Method, algorithm, Adaptive Approach, non-adaptive method
  • جاوید رضانیا*، مسعود حامیان، علیرضا راسخی
    در دنیای مدرن امروزی ردپای هوش مصنوعی را می توان تقریبا در هر زمینه ای جست و جو کرد. عرصه های مهندسی ساختمان و مدیریت پروژه های ساخت و ساز نیز در سال های اخیر چالش های جدیدی را با ورود الگوریتم ها و ماشین ها تجربه می کنند که این روند از بهینه سازی فرآیندها و بهبود طراحی محصول گرفته تا خودکار سازی وظایف و طراحی پارامتریک را شامل می شود. هوش مصنوعی در مهندسی سازه شامل استفاده از الگوریتم های پیشرفته و تکنیک های یادگیری ماشین برای ساده سازی و بهبود جنبه های مختلف فرآیند طراحی و تحلیل است. همچنین، نرم افزارهای هوش مصنوعی مربوط به ساخت و ساز دسته ای از ابزارها و راه حل های تکنولوژیکی هستند که از هوش مصنوعی برای بهینه کردن عملکردهای مختلف این صنعت استفاده می کنند. از طرف دیگر، یکی از موضوعات نسبتا جدیدی که هوش مصنوعی می تواند به آن ورود کند، بررسی انواع خرابی ها از جمله خرابی پیشرونده در طراحی و نگه داری سازه ها است. در این مقاله تلاش شده است تا با تعریف هوش مصنوعی و نیز یادگیری ماشین، به تبیین کارکرد های مختلف این تکنولوژی، الگوریتم های کاربردی و معرفی نرم افزارهای مفید و راه گشا در مهندسی عمران که هوش مصنوعی صحنه گردان اصلی آن ها است، پرداخته شود. همچنین پارامترهای اساسی تاثیرگذار در مطالعه خرابی پیشرونده، مانند شناسایی مسیر بحرانی و الگوهای بار فوق العاده مورد بررسی قرار گرفته اند. با توجه به کارکرد های بیان شده در این پژوهش، اهمیت به کارگیری هوش مصنوعی در مطالعات تئوری و پروژه های کاربردی آینده به وضوح مشخص است. به خصوص پروژه های بزرگ مانند سازه های فضایی و یا ساختمان های با سیستم باربر لرزه ای خاص مانند خرپا های متناوب و سازه های با نیاز شکل پذیری بالا که نیازمند تحلیل، طراحی و پایش ویژه هستند.
    کلید واژگان: هوش مصنوعی، یادگیری ماشین، الگوریتم، خرابی پیشرونده، تجزیه و تحلیل
    Javid Rezania *, Massoud Hamian, Alireza Rasekhi
    In today's modern world, traces of artificial intelligence can be found in almost any field. In recent years, with the introduction of algorithms and machines, the fields of building engineering and construction project management have also experienced new challenges, from optimizing processes and improving product design to automating tasks and parametric design. Artificial intelligence in structural engineering involves the use of advanced algorithms and machine learning techniques to simplify and improve various aspects of the design and analysis process. Also, artificial intelligence software related to construction is a group of technological tools and solutions that use artificial intelligence to optimize various functions of this industry. On the other hand, one of the relatively new topics that artificial intelligence can enter into is the investigation of various types of damage, including progressive damage in the design and construction of structures. In this article, an attempt has been made to define artificial intelligence and machine learning, to explain the various functions of this technology, and practical algorithms, plus introduce useful and pioneering software in civil engineering, where artificial intelligence is the main origin. Also, the basic influencing parameters in the study of progressive collapse, such as critical path identification and extreme load patterns, have been investigated. According to the functions stated in this research, the importance of using artificial intelligence in theoretical studies and future applied projects is clearly known. Especially vital projects such as Spatial Structures or buildings with a special seismic bearing system such as Staggered Truss Systems and structures with high ductility requirements that need special analysis, design, and monitoring.
    Keywords: Artificial intelligence, Machine Learning, Algorithm, Progressive collapse, Analysis
  • مرضیه دریکوندی، حسین زینی وند*، ناصر طهماسبی پور، علی حقی زاده
    مکانیابی بهینه تحلیل مکانی است که به دلیل کم کردن هزینه های پایش نقش مهمی در راه اندازی پروژه های اجرایی دارد. به دلیل ملاحظات اقتصادی و کم کردن هزینه های پایش، رویکرد بهینه سازی در این پژوهش کاهش ایستگاه های پایش کیفی آب زیرزمینی و توزیع مکانی مناسب آنها در حوزه آبریز دز در محدوده استان لرستان است. در این رابطه، با استفاده از الگوریتمی بر اساس اصل حداکثر شاخص اختلال شانون و بر مبنای شاخص آلودگی متغیرهای ,TH, SAR, EC, SO4, Cl, HCO3, K, ,Na, Ca, Mg TDSو pH نسبت به بهینه سازی شبکه پایش موجود با 63 ایستگاه در دوره آماری 1396 تا 1387 اقدام شد. نخست برای هر ایستگاه در یک دوره 10 سال آماری، میانگین رتبه محاسبه شد. سپس با توجه به تعداد ایستگاه و زمان مربوطه برای شاخص اختلال شانون شبکه مدل هایی متناسب ارایه شد. پس از برازش بهترین مدل برای هر پارامتر، نتایج نشان داد که بر اساس پارامترهای ,SO4 ,Cl ,HCO3 ,K ,Na ,Ca ,Mg ,pH ,TH SAR ,TDS و EC از میان 63 ایستگاه به ترتیب تعداد 33، 34، 41، 24، 40، 34، 30، 43، 33، 33، 41 و 28 ایستگاه برای پایش آب زیرزمینی منطقه مورد مطالعه کافی است. همچنین، برای اعتبارسنجی نتایج از میانگین مربعات خطا و میانگین قدر مطلق خطا استفاده شد. در نهایت، در میان 12 شاخص کیفی ارزیابی شده، بیشترین مقدار شاخص اختلال شانون برای آب زیرزمینی برای پارامتر پتاسیم (K) بدست آمد. بنابراین شاخص پتاسیم دارای حداکثر شاخص اختلال شانون در منطقه بوده و به عنوان شاخص برتر انتخاب گردید.
    کلید واژگان: بهینه سازی، الگوریتم، اختلال شانون، آنتروپی
    Marzieh Derikvandi, Hossein Zeinivand *, Nasser Tahmasebipour, Ali Haghizadeh
    Site location is one of the spatial analyzes that has a great impact on reducing the costs incurred and launching various activities. So, this is one of the most important and effective steps in executive projects. Due to economic considerations and reduction of monitoring costs, optimization approaches in this study are to reduce groundwater quality monitoring stations in Dez watershed in Lorestan province. In this regard, using an algorithm based on the principle of maximum Shannon disorder index and based on the pollution index of TH, SAR, EC, SO4, Cl, HCO3, K, Na, Ca, Mg TDS and PH parameters, optimization was done for the available 63 monitoring stations in the statistical period of 1387 to 1396 (2008-2017). First, the average rank of each station in the 10 years data was obtained. Then, appropriates models were proposed for the network Shannon disorder index regarding the number of stations and time. After fitting the best model, the results showed that based on SO4, Cl, HCO3, K, Na, Ca, Mg, PH, TH SAR, TDS and EC parameters, 33, 34, 41, 24, 40, 34 , 30, 43, 33, 33, 41 and 28 stations are sufficient for groundwater in the study area, respectively. Also, among the 12 quality indicators evaluated for groundwater, potassium (K) had the highest value of Shannon disorder index. Therefore, it had the maximum Shannon disorder index and was selected as the superior index. The mean squared error and the mean absolute error value were used to validate the results.
    Keywords: optimization, Algorithm, Shannon disorder, Entropy
  • Hadis Rezaei Mirghaed, Ladan Khedri Gharibvand *
    Urban land use maps, in addition to different classes of land use with spatial patterns, specify the type and intensity of land use; therefore, they can be used for current and future planning of urban land. In this study, land use changes in Lali city in 30 years (1987-2017) were investigated. To evaluate the land use changes in this time interval, several spectral images of Landsat satellites 5, 7, and 8 from the years 1987, 2001 and 2017 were utilized. After collecting data and the application of necessary pre-processing on them, also for the preparation of land use maps for the specified time intervals, data analysis was carried out by Maximum Likelihood Classification Algorithm. The findings obtained each year were monitored and controlled through field operations, and land use maps in 7 classes of agriculture, rangeland, forest, mountain, residential, river, and other areas were produced. Then, the changes in each land use were determined in the specified periods during 1987 to 2001, 2001 to 2017, and eventually 1987 to 2017. While the results obtained from the final changes illustrate that the overall level of vegetation compared to the beginning of the period has declined markedly which is an indication of deforestation in the region, urban areas, agriculture, and rangelands have maintained an ascending trend which can be due to increasing urban development and rural expansion, and the growing need of residents for housing, agriculture, and gardens.
    Keywords: Lali City, Maximum likelihood, algorithm, land use
  • Abbas Bashiri *, Hasan Hasanimoghaddam, Adel Tabeshkar
    Most underwater intelligent vehicles and marine remote-control vehicles are equipped with optical cameras for underwater imaging. However, due to the properties of water and its impurity, the quality of the images taken by these imaging devices is not good enough, because the water weakens the light, and the deeper the water, the more the intensity of the light will decreases. Since different wavelengths show different behavior in the collision with the water column, processing and study of these wavelengths is very important to obtain the desired image. The spectral signature can be used for underwater applications. In this research, to increase the quality of underwater images, a new method has been introduced to improve image contrast. In this method, first, with structured lighting, different wavelengths are irradiated to the underwater target in a laboratory environment, then underwater images are processed by the proposed algorithm, and finally, a multispectral image is achieved by stacking images with different wavelengths. The results showed the relative superiority of the proposed method over other methods.
    Keywords: Underwater imaging, Spectral, Underwater target, algorithm
  • محمدنبی امیدوار، صمد نجاتیان*، حمید پروین، کرم الله باقری فرد، وحیده رضایی

    بهینه سازی یک فعالیت مهم و تعیین کننده در طراحی ساختاری است. طراحان زمانی قادر خواهند بود طرح های بهتری تولید کنند که بتوانند با روش های بهینه سازی در صرف زمان و هزینه طراحی صرفه جویی نمایند. بسیاری از مسایل بهینه سازی در مهندسی، طبیعتا پیچیده تر و مشکل تر از آن هستند که با روش های مرسوم بهینه سازی نظیر روش برنامه ریزی ریاضی و نظایر آن قابل حل باشند. جهان اطراف ما می تواند پایه بسیاری از رفتارهای هدفمند باشد که دقت در اشیاء پیرامون، ما را در شناخت این رفتارها و  نظم رو به سمت هدف یاری می رساند. در این مقاله یک الگوریتم بهینه سازی جدید بر پایه الگوی بازی دومینو ارایه گردیده است. بازی دومینو متشکل از مجموعه ای از تکه هایی است که با یک وحدت گروهی، یک نظم روبه هدف را شکل داده اند. تلاش برای ایجاد یک الگوریتم بهینه سازی جدید بر پایه تیوری این بازی، ما را به انجام این تحقیق رهنمون ساخت. الگوی حرکت دومینویی در یک محیط شبیه ساز پیاده سازی گردید و نتایج نشان داد که الگوریتم حاصل، الگوی مناسبی برای یافتن پاسخ های بهینه جهت مسایل پیچیده می باشد.

    کلید واژگان: الگوریتم، بهینه سازی، دومینو، تابع هزینه، رفتار
    Mohammadnabi Omidvar, Samad Nejatian*, Hamid Parvin, Karamolla Bagherifard, Vahideh Rezaie

    Optimization is a very important process in engineering. Engineers can create better production only if they make use of optimization tools in reduction of its costs including consumption time. Many of the engineering real-word problems are of course non-solvable mathematically (by mathematical programming solvers). Therefore, meta-heuristic optimization algorithms are needed to solve these problems. Based on this assumption, many new meta-heuristic optimization algorithms have been proposed inspired by natural phenomena, such as IWO [58], BBO [59], WWO [61], and so on. Inspired by domino toppling theory, we proposed an optimization algorithm. Using domino pieces, we can create countless complex structures. To simulate the domino movement in the search space of a problem, we consider the particles in the search space as the domino pieces and, by creating an optimal path, we will try to direct the dominoes to the optimal path. The optimal paths will be updated in each iteration. After initializing the dominoes randomly at the beginning of each evaluation, the picking piece or the first moving piece will be identified and then the particles will be selected by the optimal path. Applying a motion equation to each domino will move the dominoes forward in that direction. At first, a predefined dominoes will be randomly distributed in the problem space. Choosing the optimal path will accelerate the convergence of the domino particles towards the target. After choosing the path in current iteration, we now have to do the domino movement. The particles will move to a new location by applying the new location equation. By applying this equation, each domino piece will sit on the track ahead of itself. The front piece will also move to a new location by applying an equation separate from the rest. After moving the dominoes to the new location, the worst iteration of the previous iteration will be removed from the problem space. In the new iteration, the optimal domino path, the new locations of domino pieces and the global optimum will be updated. At the end of the algorithm, the global optimum will be determined as the optimal solution. This method is implemented in a simulator environment. To evaluate the performance of the Domino Optimization algorithm, we use a complete benchmark including 30 objective functions called CEC 2014 [67] that are single-objective numerical functions. In all cases, we set the population size to 50, the dimension size to 30, and the number of fitness function evaluation to 150,000. We compare the proposed Domino Optimization algorithm (DO) with the algorithms LOA [57], ICS [62], NPSO [63], MOHS [64], BCSO [65] and FFFA [66]. The results obtained from the 3 unimodal functions show that the proposed method is able to achieve a better solution than any of the state of the art algorithms at the equal resources. Results in the multimodal functions show that the proposed method has the best performance in finding the optimal solution in all of the available 13 functions in this section. In all of 6 functions in the hybrid section, the quality of the proposed method is better than all of the state of the art algorithms at the equal resources. The standard deviation values ​​of the proposed method, which are often small numbers, indicate algorithm convergence around the optimal solution. Also among the available methods, two algorithms, named NPSO and LOA, have good results after the proposed method. In the convergence analysis of dominoes, the diversity of objective functions in 100 distinct iterations shows a big value at the beginning of the algorithm, and a low value at the end of the algorithm.

    Keywords: Algorithm, Optimization, Dominoes, Cost Function, Behavior
  • Hadis Rezaei Mirghaed, Ladan Khedri Gharibvand *
    Urban land use maps, in addition to different classes of land use with spatial patterns, specify the type and intensity of land use; therefore, they can be used for current and future planning of urban land. In this study, land use changes in Lali city in 30 years (1987-2017) were investigated. To evaluate the land use changes in this time interval, several spectral images of Landsat satellites 5, 7, and 8 from the years 1987, 2001 and 2017 were utilized. After collecting data and the application of necessary pre-processing on them, also for the preparation of land use maps for the specified time intervals, data analysis was carried out by Maximum Likelihood Classification Algorithm. The findings obtained each year were monitored and controlled through field operations, and land use maps in 7 classes of agriculture, rangeland, forest, mountain, residential, river, and other areas were produced. Then, the changes in each land use were determined in the specified periods during 1987 to 2001, 2001 to 2017, and eventually 1987 to 2017. While the results obtained from the final changes illustrate that the overall level of vegetation compared to the beginning of the period has declined markedly which is an indication of deforestation in the region, urban areas, agriculture, and rangelands have maintained an ascending trend which can be due to increasing urban development and rural expansion, and the growing need of residents for housing, agriculture, and gardens.
    Keywords: Lali City, Maximum likelihood, algorithm, land use
  • یوسف الفت میری، ابراهیم جباری، مسعود بحرینی مطلق*، حسین علیزاده، امیرحسین حسن آبادی

    پیش بینی کوتاه مدت نرخ جریان رودخانه ها اهمیت فراوانی در مدیریت منابع آب و کنترل سیلاب دارد. یکی از مشکلاتی که محققین در این نوع از پیش بینی ها همواره با آن مواجه هستند؛ نبود یک بانک داده ای دقیق و با تفکیک پذیری زمانی بالا می باشد. فناوری تیکه نگاری صوتی یکی از روش های داده برداری نوین است که علاوه بر دقت بالای داده های برداشت شده دارای تفکیک پذیری زمانی بالایی نیز است؛ بنابراین با کاربرد داده های برداشت شده با استفاده از این فناوری به همراه یک مدل پیش بینی مناسب می توان به یک پیش بینی کوتاه مدت دقیق از نرخ جریان رودخانه ها دست یافت. در این تحقیق تاثیر کاربرد داده های برداشت شده توسط فناوری تیکه نگاری صوتی در پیش بینی کوتاه مدت نرخ جریان توسط مدل ترکیبی الگوریتم دسته بندی گروهی داده ها، بررسی شده و با داده های به دست آمده از روش دبی-اشل مقایسه شده است. به منظور جلوگیری از بیش برازش شدن مدل پیش بینی از معیار اعتبارسنجی کا-فولد استفاده شده است. نتایج این تحقیق نشان داد که کاربرد داده های تیکه نگاری صوتی باعث افزایش دقت پیش بینی کوتاه مدت می شود؛ به طوری که ضریب نش- ساتکلیف برای پیش بینی 1، 6، 12، 24، 48 و 72 ساعته دبی بر روی داده های برداشت شده با روش تیکه نگاری صوتی به ترتیب (98/0، 96/0، 94/0، 88/0، 73/0 و 54/0) به دست آمد. درحالی که این مقادیر برای داده های برداشت شده با روش دبی - اشل به ترتیب (97/0، 84/0، 61/0، 27/0، 12/0 و 11/0) محاسبه شد. از دلایل بالا بودن دقت پیش بینی انجام شده بر روی داده های تیکه نگاری صوتی نسبت به داده های دبی- اشل می توان به تفکیک پذیری زمانی بالا و دقت بیشتر داده های برداشت شده توسط تیکه نگاری صوتی نسبت به دبی- اشل اشاره کرد.

    کلید واژگان: الگوریتم دسته بندی گروهی داده ها، پیش بینی کوتاه مدت، فناوری تیکه نگاری صوتی، دبی اشل، الگوریتم جی ام دی اچ
    Yousef Olfatmiri, Ebrahim Jabbari, Masoud Bahreinimotlagh *, Hossein Alizadeh, Amirhossein Hassanabadi

    Short-term forecasting of streamflow is one of the most important goals in water resources management and flood control. However, one of the problems that researchers always face in this type of prediction is the Lack of an accurate and high time resolution database. The Fluvial Acoustic Tomography (FAT) is an innovative method of data gathering which has both high accuracy and high-resolution time. Therefore, by using the data collected from this technology with a suitable forecast model, accurate short-term streamflow forecasting can be achieved. In this research, the effect of FAT data on short-term streamflow forecasting by Combinatorial GMDH Algorithm (CGA) has been investigated and compared with one obtained from the Rating Curve method. The k-fold cross-validation criterion has been used to prevent over-fitting. The results showed that the FAT data increases the accuracy of short-term forecasting. As an example, the Nash-Sutcliffe coefficient (ENS) for the 1, 6, 12, 24, 48, and 72 hours forecast were 0.98, 0.96, 0.94, 0.88, 0.73, and 0.54, respectively. While these values for the Rating Curve ones were 0.97, 0.84, 0.61, 0.27, 0.12, and 0.11, respectively.

    Keywords: GMDH Algorithm, short-term forecasting, Acoustic tomography, Rating Curve, algorithm
  • ریحانه مسجودی شچانی *

    واحد پردازش عصبی در جهان امروز، در بسیاری از تجهیزات مورد استفاده قرار می گیرد. تلفن های هوشمند، کامپیوترها، ماشین های خودران و فناوری اطلاعات. با این حال در چند سال گذشته تغییرات و نوآوری های باورنکردنی در یادگیری ماشین ایجاد شده است. واحد پردازش عصبی سخت افزاری است که برای پردازش عصبی خاص مورد استفاده قرار می گیرد. به طور معمول واحد پردازش عصبی زمانی میتواند کارآمد عمل کند که یک مدل نرم افزاری با نام شبکه عصبی مصنوعی در دسترس باشد. یادگیری عمیق نیز زیر مجموعه ای از شبکه عصبی مصنوعی است که اساسا در دستکاری الگوریتمهای پیچیده استفاده میشود. این مقاله مروری بر رابطه و هماهنگی بین واحد پردازش عصبی، شبکه عصبی مصنوعی و یادگیری عمیق ارایه میدهد، همچنین بر نحوه عملکرد یادگیری عمیق و همکاری آن با شبکه عصبی مصنوعی و واحد پردازش عصبی، کاربردهای مختلف آن و مزایا و معایب آن تمرکز دارد.

    کلید واژگان: واحد پردازش عصبی، شبکه عصبی مصنوعی، یادگیری عمیق، الگوریتم، شبکه عصبی عمیق
    Reihane masjoudi shachani

    The neural processing unit is used in many equipments in today's world. Smartphones, computers, automobiles and information technology. In the last few years, however, there have been incredible changes and innovations in machine learning. Neural processing unit is hardware that is used for specific neural processing. Normally a neural processing unit can work efficiently when a software model called an artificial neural network is available. Deep learning is also a subset of artificial neural networks that are primarily used to manipulate complex algorithms. This article provides an overview of the relationship and coordination between neural processing unit, artificial neural network and deep learning. It also focuses on how deep learning works and its cooperation with artificial neural network and neural processing unit, its different applications and its advantages and disadvantages.

    Keywords: Neural Processing Unit, Artificial Neural Network, Deep Learning, Algorithm, Deep Neural Network
  • Hadis Rezaei Mirghaed, Ladan Khedri Gharibvand *
    Urban land use maps, in addition to different classes of land use with spatial patterns, specify the type and intensity of land use; therefore, they can be used for current and future planning of urban land. In this study, land use changes in Lali city in 30 years (1987-2017) were investigated. To evaluate the land use changes in this time interval, several spectral images of Landsat satellites 5, 7, and 8 from the years 1987, 2001 and 2017 were utilized. After collecting data and the application of necessary pre-processing on them, also for the preparation of land use maps for the specified time intervals, data analysis was carried out by Maximum Likelihood Classification Algorithm. The findings obtained each year were monitored and controlled through field operations, and land use maps in 7 classes of agriculture, rangeland, forest, mountain, residential, river, and other areas were produced. Then, the changes in each land use were determined in the specified periods during 1987 to 2001, 2001 to 2017, and eventually 1987 to 2017. While the results obtained from the final changes illustrate that the overall level of vegetation compared to the beginning of the period has declined markedly which is an indication of deforestation in the region, urban areas, agriculture, and rangelands have maintained an ascending trend which can be due to increasing urban development and rural expansion, and the growing need of residents for housing, agriculture, and gardens.
    Keywords: Lali City, Maximum likelihood, algorithm, land use
  • Mosa Hajipoor

    This work proposes a new meta-mathematical method called arithmetic optimization algorithm that uses the distributive behavior of the main arithmetic operators in mathematics, including division, subtraction, and addition for now the number of distinct entries in the multiplication table n. Therefore, there is some interest in algorithms for calculating M (n) exactly or as an approximation. We compare several algorithms for exact calculation of M (n) and come up with a new algorithm with suborder execution time. We also present two Monte Carlo algorithms to approximate M (n). We give exact calculation results for values of n to 230 and compare our experimental results with Ford's order of magnitude results. Experimental results show that INTEGERS provides very promising results in solving difficult optimization problems compared to 11 other well-known optimization algorithms.

    Keywords: Integer, calculation, algorithm
  • Z. Dai, K. Gao, X. Zheng

    In this paper, two inventory models with starting shortages and without shortages for perishable products in supply chain are proposed. The demand for perishable products is dependent on price and stock. Supply chain is composed of one manufacturer, one distribution center, and one retailer. The objective of these two models is to maximize the average profit per unit time by determining the optimal replenishment cycle, frequency, and quantity. The property of optimal solutions for two cases of two models is discussed to verify the existence of optimal solutions. Algorithms for searching optimal solutions are presented. In order to investigate the effect of parameters on optimal solutions and obtain some management insights, computational experiments with sensitivity analyses are carried out. Finally, conclusions and future researches are provided.

    Keywords: Optimizing, Algorithm, Multi-echeloninventory systems, Perishable productswith price, stockdependent demand, Supply chain
  • مریم نعمتی*، نفیسه فارغ زاده

    امروز اینترنت و برنامه های کاربردی تحت شبکه به سرعت در حال رشد هستند، از این رو نیاز بهمحافظت و تامین امنیت چنین برنامه هایی نیز افزایش یافته است. الگوریتمهای رمزنگاری در دنیای سایبر امروزی که همیشه خطر دسترسی غیرمجاز به همه نوع داده وجود دارد امری حیاتی محسوب میشوند. حساسترین و آسیبپذیرترین داده، داده های سیستم مالی و پرداختی است که میتواند اطلاعات شناسایی شخصی یا مشخصات کارت پرداخت مشتریان و سایر اطلاعات شخصی را در معرض خطر قرار دهد. الگوریتمهای رمزنگاری برای محافظت از این اطلاعات و کاهش خطراتی که مشاغل در انجام معاملات پرداخت با آن روبرو هستند، بسیار مهم است . درواقع، الگوریتمهای رمزنگاری نقش اصلی را در امنیت اطلاعات سیستمها و تولید امضای دیجیتال بازی می کنند. امضاهای دیجیتال موجود غالبا مبتنی بر الگوریتمهای رمزنگاری بوده و باعث به رسمیت شناسی اطلاعات الکترونیکی شده به طوریکه هویت پدیدآورنده سند و جامعیت اطلاعات آن، قابل بازبینی و کنترل میباشد. در این مقاله کوشش می کنیم علاوه بر تعریف و دسته بندی الگوریتمهای رمزنگاری رایج ،و مقایسه ای بر روی قدرت و میزان تاثیرگذاری انجام دهیم. این بررسی و مقایسه می تواند منجر به بهبود کارکردها و اصلاح رویکردهای بکارگیری این الگوریتم ها بشود.

    کلید واژگان: رمزنگاری، امنیت شبکه، رمزگذاری، الگوریتم، کلید عمومی
    Maryam Nemati *, Nafiseh Fareghzadeh

    Recently, the distributed internet applications under the scalable networks are growing rapidly, so the need to protect and secure such applications has also increased. Encryption algorithms are vital in today's cyber world, where there is always the risk of unauthorized access to all types of data. The most sensitive and vulnerable data is financial and payment system data, which can compromise personal identification information or customer payment card details and other personal information. Cryptographic algorithms are critical to protecting this information and reducing the risks that business face in conducting payment transactions. In fact, cryptographic algorithms play a major role in the information security of systems and the production of digital signatures. Existing digital signatures are often based on cryptographic algorithms and lead to the recognition of electronic information so that the identity of the author of the document and the comprehensiveness of its information can be reviewed and controlled. In this article, in addition to defining and classifying common cryptographic algorithms, we try to make a comparison on power and effectiveness of applicable algorithms in this area. This review and comparison can lead to improved functions and improved approaches to using these algorithms.

    Keywords: Cryptography, Network Security, Encryption, algorithm, Public Key
  • Hadis Rezaei Mirghaed, Ladan khedri gharibvand

    Urban land use maps, in addition to different classes of land use with spatial patterns, specify the type and intensity of land use; therefore, they can be used for current and future planning of urban land. In this study, land use changes in Lali city in 30 years (1987-2017) were investigated. To evaluate the land use changes in this time interval, several spectral images of Landsat satellites 5, 7, and 8 from the years 1987, 2001 and 2017 were utilized. After collecting data and the application of necessary pre-processing on them, also for the preparation of land use maps for the specified time intervals, data analysis was carried out by Maximum Likelihood Classification Algorithm. The findings obtained each year were monitored and controlled through field operations, and land use maps in 7 classes of agriculture, rangeland, forest, mountain, residential, river, and other areas were produced. Then, the changes in each land use were determined in the specified periods during 1987 to 2001, 2001 to 2017, and eventually 1987 to 2017. While the results obtained from the final changes illustrate that the overall level of vegetation compared to the beginning of the period has declined markedly which is an indication of deforestation in the region, urban areas, agriculture, and rangelands have maintained an ascending trend which can be due to increasing urban development and rural expansion, and the growing need of residents for housing, agriculture, and gardens.

    Keywords: Lali City, Maximum Likelihood, Algorithm, Land Use
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