Do you want to publish a course? Click here

Comparative Study of Subspace Clustering Algorithms

مقارنة بين خوارزميات العنقدة بتجزيء الفضاء

1365   2   40   0 ( 0 )
 Publication date 2018
and research's language is العربية
 Created by Nabil Alsaadi




Ask ChatGPT about the research

choose the right way to dividing set of data with high dimensions to clusters in specific field and comparison the different subspace clustering algorithms and present the applications and usage

References used
http://ijcsit.com/docs/Volume%206/vol6issue05/ijcsit2015060566.pdf
http://interscience.in/IJCSI_Vol1_Iss2/paper3.pdf
http://www.kdd.org/exploration_files/parsons.pdf
rate research

Read More

This research aims to developing new method for breast tumors extraction and features detection in breast magnetic resonance images by depending on clusteringand image processing algorithms. At the beginning, one of clustering algorithms was used f or image segmentation and grouping pixels by their gray scale values. Then morphological operations were implemented in order to remove noise and undesired regions, after that suspected areas were extracted. Finally some shape features for extracted area were detected, this features could be very useful for tumors diagnosis. A database consisted of 96breast magnetic resonance images were used and proposed approach was appliedby MATLAB program, and we obtainedbreast tumors extraction and its features and compared them with the doctor's opinion .
The shortest path problem can be categorized in to two different problems; single source shortest path problem (SSSP) and all pair shortest algorithm (APSP). In this paper, analysis and comparison between complexity of the famous shortest path al gorithms have been made, and the obtained results have shown that researchers have got remarkable success in designing better algorithms in the terms of time complexity to solve shortest path algorithms.
Language representations are known to carry stereotypical biases and, as a result, lead to biased predictions in downstream tasks. While existing methods are effective at mitigating biases by linear projection, such methods are too aggressive: they n ot only remove bias, but also erase valuable information from word embeddings. We develop new measures for evaluating specific information retention that demonstrate the tradeoff between bias removal and information retention. To address this challenge, we propose OSCaR (Orthogonal Subspace Correction and Rectification), a bias-mitigating method that focuses on disentangling biased associations between concepts instead of removing concepts wholesale. Our experiments on gender biases show that OSCaR is a well-balanced approach that ensures that semantic information is retained in the embeddings and bias is also effectively mitigated.
نلاحظ في الآونة الأخيرة الانتشار الهائل لأدوات التعلم الإلكتروني ( )E-Learningومنها المحاضرات التعليمية التي تعد جزء مهم منها، وهذه المحاضرات يتم تجميعها في المواقع الإلكترونية بناءا على العنوان الذي تحمله على الرغم من احتواءها على مواضيع مختلفة في مجالات متعددة وبالتالي عندما يتم البحث عن هذه المحاضرات بكلمات معينة يتم عرض المحاضرات ذات العناوين القريبة والمشابهة لجملة البحث ولكن هذه ليست النتيجة المطلوبة، ولذلك وانطلاقا من هذه المشكلة تم اقتراح طريقة لتصنيف هذه المحاضرات بناء على المواضيع التي تحويها وليس فقط على عناوينها وعمل عنقدة لها اعتمادا على هذه المواضيع. تعتمد هذه الطريقة على الترجمة المرفقة ( )captionsمع الفيديوهات التعليمية في عملية استخراج المواضيع ومن ثم عنقدتها، ومن جهة أخرى تم الاعتماد على مقالات من موقع Wikipediaوذلك بهدف تحديد وتعريف كل عنقود من العناقيد ومن ثم حساب التشابهات بين المواضيع المعبرة عن كل محاضرة مع مراكز العناقيد، وبعد ذلك تم تطبيق عنقدة ضبابية بناء على هذه التشابهات.

suggested questions

comments
Fetching comments Fetching comments
Sign in to be able to follow your search criteria
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا