CONSENSUS FUNCTIONS FOR CLUSTER ENSEMBLES

2012 ◽  
Vol 26 (6) ◽  
pp. 598-614 ◽  
Author(s):  
Ghaith Manita ◽  
Riadh Khanchel ◽  
Mohamed Limam
2012 ◽  
Vol 193 ◽  
pp. 1-32 ◽  
Author(s):  
Xavier Sevillano ◽  
Francesc Alías ◽  
Joan Claudi Socoró

Author(s):  
Yalamarthi Leela Sandhya Rani ◽  
V. Sucharita ◽  
K. V. V. Satyanarayana

<p class="PreformattedText">Data analysis plays a prominent role in interpreting various phenomena. Data mining is the process to hypothesize useful knowledge from the extensive data. Based upon the classical statistical prototypes the data can be exploited beyond the storage and management of the data. Cluster analysis a primary investigation with little or no prior knowledge, consists of research and development across a wide variety of communities. Cluster ensembles are melange of individual solutions obtained from different clusterings to produce final quality clustering which is required in wider applications. The method arises in the perspective of increasing robustness, scalability and accuracy. This paper gives a brief overview of the generation methods and consensus functions included in cluster ensemble. The survey is to analyze the various techniques and cluster ensemble methods.</p>


1986 ◽  
Vol 18 (4) ◽  
pp. 427-454 ◽  
Author(s):  
Weal B. Hallaq

Sunni Islam recognizes four sources from and through which the laws governing its conduct are derived. These are the Qur'an, the Sunna of the Prophet, the consensus (ljmā') of the community and its scholars, and qiyās, the juridicological method of inference. The first two sources provide the jurist with the material from which he is to extract through qiyas and ijtihād (the disciplined exercise of mental faculty) the law which he believes to the best of his knowledge to be that decreed by God. Except for a relatively limited number of cases where the Qu'an and the Sunna offer already-formulated legal judgments, the great majority of furū' cases, which constitute the body of positive and substantive law, are derived by qiyas. Thus, qiyas may be used to “discover” the judgment of a new case provided that this case has not already been solved in the two primary sources. The process of legal reasoning which qiyas involves is charged with innumerable difficulties not the least of which is finding the circle of common similarity, the 'illa, between the original case in the texts and the new case which requires a legal judgment. Since finding the 'illa entails a certain amount of guesswork (zann) on the part of the jurist and since it is highly probable that the 'illa is extracted from a text which is not entirely reliable or a text capable of more than one interpretation, Sunni jurists deemed the results of qiyas to be probable (zannī). It is only at this point that consensus may enter into play in the legal process. Should Muslims, represented by their jurists, reach an agreement on the validity of a zanni legal judgment, such judgment is automatically transferred from the domain of juristic speculation to that of certainty (qat', yaqīn). Consensus then renders this judgment irrevocable, not to be challenged or reinterpreted by later generations. Furthermore, this judgment, being so irrevocable, acquires a validity tantamount to that of the Qur'an and the highly reliable traditions embodied in the Sunna of the Prophet. Thus, such a case with its established judgment becomes a precedent according to which another new legal question may be solved. It is only in this sense that consensus functions as a source of law, a source which is infallible.


2013 ◽  
Vol 1 (4) ◽  
pp. 1-15 ◽  
Author(s):  
Hiroki Nomiya ◽  
Atsushi Morikuni ◽  
Teruhisa Hochin

An emotional scene detection method is proposed in order to retrieve impressive scenes from lifelog videos. The proposed method is based on facial expression recognition considering that a wide variety of facial expression could be observed in impressive scenes. Conventional facial expression techniques, which focus on discriminating typical facial expressions, will be inadequate for lifelog video retrieval because of the diversity of facial expressions. The authors thus propose a more flexible and efficient emotional scene detection method using an unsupervised facial expression recognition based on cluster ensembles. The authors' approach does not need to predefine facial expressions and is able to detect emotional scenes containing a wide variety of facial expressions. The detection performance of the proposed method is evaluated through some emotional scene detection experiments.


Sign in / Sign up

Export Citation Format

Share Document