انجمن کامپیوتر ایران

با توجه به افزايش حجم مستندات متني، براي پاسخگويي به نيازهاي اطلاعاتي كاربران، ديگر تكنيكهاي بازيابي اطلاعات به تنهايي كارا نيستند . مطالعه حجم زياد متون ب راي كاربران بسيار سخت و زمانگير است و دراختيار داشتن خلاصه اي از مطالب مهم آنها، مي تواند بسيار مفيد باشد . فرآيند فشرده سازي يك منبع به صورتي كه حاصل حاوي اطلاعات مهم آن باشد را خلاصه سازي گويند . خلاصهسازي متون منجر به استفاده از منابع بيشتر با سرعت بالاتر و در نتيجه حاصل شدن اطلاعات غنيتر ميشود. در اين مقاله ابتدا به بررسي انواع سيستم هاي خلاصه سازي خودكار و مروري بر سيستم هاي خلاصه سازي فارسي خواهيم پرداخت . سپس به معرفي سيستم خلاصه سازي فارسي ساخته شده با نام PARSUMIST پرداخته و نتايج ارزيابي سيستم و مقايسه آن با نمونه هاي مشابه را ارائه خواهيم نمود . سيستم معرفي شده از تركيبي از روش هاي كلاسيك، آماري و معنايي براي توليد خلاصه مستخرج از متون تك سندي و چندسندي فارسي بهره ميبرد.

در اين مقاله روشي جديد از پياده سازي كدينگ سازگار با اعمال تغييراتي در پياده سازي الگوريتم هافمن سازگار ارائه شده است . تغييرات به وجود آمده موجب كاهش تعداد تغييرات بيتي در بيت هاي خروجي كد كننده و در نهايت كاهش مصرف توان در كدكننده و ديكدكننده مي شود. تغييراساسي اعمالي در روش ارئه شده ، شامل حذف مرحله ي به روز رساني درخت هافمن سازگار بعد از اولين رخداد هر نماد منبع، و تغيير در نحوه ي به روزرساني درخت است. به منظور - ارزيابي روش ارائه شده از دوگروه فايل به عنوان منبع استفاده شد : 1 فايل متني 2- فايل تصويري تبديل شده به فايل متني توسط MIME64 نتايج به دست آمده از به كار گيري روش فوق در كدكردن فايل هاي كاراكتري در 4 گروه با حجم هاي متفاوت از 100 بايت تا 1000 كيلو بايت، كاهش به طور متوسط 40 % و 17 % تغييرات بيتي به ترتيب نسبت به روش هاي كدينگ اسكي و هافمن سازگار را نشان داد. همچنين روش ارائه شده بر روي 14 تصوير محك كاهش تقريبي و به ترتيب 42 % و 23 % تغييرات بيتي را با استفاده از روش مذكور نس بت به روش هاي كدينگ اسكي و ويتر را نشان مي دهد.

در اين مقاله يک روش مبتني بر ناحيه براي ثبت تصاوير هوايي که نسبت به چرخش و ت غيير م قياس حساس ن ميباشد، ارائه شده است. متداولترين ا شياء موجود در تصا وير هوايي سطوح بامها ميباشن د که نوا حي با محتواي اطلاعا تي ک م ايجاد ميکنن د. با استفاده از اين خصوصيت هست ه هاي اوليه يافته شده و با کمک روش رشد ناحيه، نواحي مطلوب استخرا ج و مراکز جرم آنها بعنوان نقاط مشخصه انتخاب ميشوند. در شروع فرآيند جستجو براي يافتن نقاط متناظر، با استفاده از اطلاعات شکلي به هر ناحيه تعدادي کانديداي تناظر نسبت داده ميشود. بمنظور کاهش تعداد کانديداها شرط همساي گي را اعمال ميکني م. با توجه به شباهت توزيع زا ويه اي جفتهاي صحي ح نسبت به ه م در دو تصوير و اي نکه نسبت تغيير مقياس بين تمام جفتهاي صحي ح، داراي مقداري ثابت و برابر با تغيير مقياس بين دو تصوير ميباش د، بر اسا س مفهومي از برچسب گذاري relaxation relaxation عمومي در فرآيند جستجو ميشوند را م ي يابيم. در پ ايان با رأي گيري بين توابع تبديل ، جفته اي ص حيح نه ايي استخراج ميشوند. الگوريتم بر روي تصاوير متعددي از شهر تهران تست شده و در ۸۰ % از تصاوي ر با مقياس ۱تا ۳ و در ۱۰۰ % تصاوير با مقياس ۱ و چرخش صفر تا ۳۶۰ درجه نتايج صحيحي بدست آمده است.

In this paper we proposed a new approach for improving distribution and coverage of mobile sensors in a target filed. The goal is to deploy sensors such that a target area is optimally covered by them. Proposed method works based on number of neighbors. The nodes which have the minimum overlaps with its neighbors start to move away according to summation of forces from their neighbors, boundaries and obstacles. In order to achieve optimum coverage, the effect of field corners is also calculated. For evaluating the effectiveness of our proposed algorithm, we compared the performance of our algorithm with TRI and VEC which are well known algorithms in field of mobile sensors coverage. Simulation results show that our algorithm surely surpasses TRI and VEC in coverage.

A collection of web pages which are about a common topic and are created by individuals or any kind of associations that have a common interest on that specific topic is called a web community. Since at present, the size of the web is over 3 billion pages and it is still growing very fast, identification of web communities has become an increasingly hard task. In this paper, a method based on asynchronous cellular learning automata (ACLA) for identification of web communities is proposed. In the proposed method first an asynchronous cellular learning automaton is used to determine the related pages and their relevance degree (the relationship structure of web pages). For determination of relationship structure of web pages information about hyperlinks and the users’ behaviour in visiting the web pages are used. Then, an algorithm similar to the HITS algorithm is applied on the obtained structure to identify the web communities. One of the advantages of the proposed method is that the web community obtained using this method is not dependent on a specific web graph structure. To evaluate the proposed approach, it is implemented and the results are compared with the results obtained for two existing methods, HITS and a complete bipartite graph based method. Experimental results show the superiority of the proposed method.

Polynomials are one of the most powerful functions that have been used in many fields of mathematics such as curve fitting and regression. Low order polynomials are desired for their smoothness1, good local approximation and interpolation. Being smooth, they can be used to locally approximate almost any derivable function. This means that when linear functions fail in approximation (e.g. where the first order Taylor expansion equals zero) polynomial functions can be used in local approximation, such that one can achieve better estimations at extremums. In this paper, application of polynomial kernel functions in locally linear neurofuzzy models is shown. Using polynomial kernels in local models, better local approximations in prediction of chaotic time series such as Mackey-Glass is achieved, and the capability of the neurofuzzy network is enhanced.

Recently, a technique has been proposed for image hiding, that is based on block texture similarity where, blocks of secret image are compared with blocks of a set of cover images and the cover image with the most similar blocks to those of the secret image is selected as the best candidate cover image to conceal the secret image. In this paper, we propose a new image hiding method in which, the secret image is initially coded using a fuzzy coding/decoding method. By applying the fuzzy coder, each block of the secret image is compressed to a smaller block. In this way, after compressing the secret image to a smaller one, we hide it in a cover image. Obviously hiding a smaller secret image causes less distortion in the stego-image (the image that has secret image or data) and therefore higher quality stego-image is obtained. Consequently, the proposed method provides higher embedding rate and enhanced security.

This paper describes the theory and implementation of dynamic Bayesian networks in the context of speaker identification. Dynamic Bayesian networks provide a succinct and expressive graphical language for factoring joint probability distributions, and we begin by presenting the structures that are appropriate for doing speaker identification in clean and noisy environments. This approach is notable because it expresses an identification system using only the concepts of random variables and conditional probabilities. We present illustrative experiments in both clean and noisy environments and our experiments show that this new approach is very promising in the field of speaker identification.

In this paper a two step method based on Gauss- Newton and factor graphs algorithm is proposed for localization to enhance accuracy of localization. The Gauss-Newton algorithm is accurate method for positioning. The most important challenge of this method is senility to initial point; this problem is solved in positioning based on factor graphs. So, in this paper, first positioning equations using angle of arrival is considered based on factor graphs algorithm. Second, final location estimation is performed using Gauss Newton algorithm with error near to Cramer-Rao bound. Simulation results shows that positioning error using two step method has maximum 6% gap to Cramer-Rao Bound.