Filters








152,239 Hits in 4.8 sec

Discovering Characterization Rules from Rankings

Ansaf Salleb-Aouissi, Bert Huang, David Waltz
2009 2009 International Conference on Machine Learning and Applications  
These rules are discovered by contrasting attributes of items drawn from both the top and bottom of a ranking list, looking for items that have high leverage, corresponding to rules with broad coverage  ...  We describe and demonstrate a new approach that can work in conjunction with any ranking algorithm to discover explanations for the items at the top of the rankings.  ...  This work has been partly supported by a research contract from Consolidated Edison New York.  ... 
doi:10.1109/icmla.2009.67 dblp:conf/icmla/Salleb-AouissiHW09 fatcat:ivkxnghml5cnpoisy3vfjippl4

Work in progress - programming misunderstandings discovering process based on intelligent data mining tools

Paola Britos, Elizabeth Jimenez Rey, Dario Rodriguez, Ramon Garcia-Martinez
2008 2008 38th Annual Frontiers in Education Conference  
We present research work in progress that focuses on data mining tools used for helping teachers to apply a three step knowledge discovering process to diagnose students' misunderstandings (and their causes  ...  From the database developed in Step 1 of the course on programming examinations, we apply Step 2: and using TDIDT algorithm we obtain the following set of rules: From this set of rules we can identified  ...  INTRODUCTION Data mining has been addressed as an effective way of discovering new knowledge from data sets of educational processes, data generated by learning systems or experiments, as well as how discovered  ... 
doi:10.1109/fie.2008.4720499 fatcat:dfiswt7425g77kqklxs3g2olce

Multi-agent Web Recommendation Method Based on Indirect Association Rules [chapter]

Przemysław Kazienko
2004 Lecture Notes in Computer Science  
Both rule types are combined into complex rules which are used to obtain ranking lists needed for recommendation of pages in the web site.  ...  Recommendation systems often use association rules as main technique to discover useful links among the set of transactions, especially web usage data -historical user sessions.  ...  Direct association rules represent regularities discovered from a large data-set [1] .  ... 
doi:10.1007/978-3-540-30133-2_154 fatcat:fa4k3osgv5aozh22zvoo6qvnye

Characterizing nucleosome dynamics from genomic and epigenetic information using rule induction learning

Ngoc Le, Tu Ho, Dang Tran
2009 BMC Genomics  
Table 5 shows some selected rules from these rule sets. Analyzing these rules, we discovered that the enrichness of some specific DNA motifs has special impact on nucleosome stability.  ...  In this paper, we proposed a novel method based on induction rule learning to computationally characterize nucleosome dynamics from both genomic and histone modification information.  ...  This file contains 60 rules characterizing nucleosome dynamics on chromosome III.  ... 
doi:10.1186/1471-2164-10-s3-s27 pmid:19958491 pmcid:PMC2788380 fatcat:2w7ieir475ealmfvmj3y3t5v5e

Applying Objective Interestingness Measures in Data Mining Systems [chapter]

Robert J. Hilderman, Howard J. Hamilton
2000 Lecture Notes in Computer Science  
We show h o w this two-step process can be applied to ranking characterizedègeneralized association rules and data cubes.  ...  In this paper, we describe a two-step process for ranking the interestingness of discovered patterns that utilizes the chi-square test for independence in the aerst step and objective measures of interestingness  ...  Thus, the rank order of the four association rulesfrom most to least interestingङ is C ङ A घDivisionङ, B ङ C घDivisionङ, B ङ C घCityङ, and C ङ A घCityङ.  ... 
doi:10.1007/3-540-45372-5_47 fatcat:6alnbuzkyrb63ahqpczm7hy7yy

Mining market basket data using share measures and characterized itemsets [chapter]

Robert J. Hilderman, Colin L. Carter, Howard J. Hamilton, Nick Cercone
1998 Lecture Notes in Computer Science  
Our algorithm combines the Apriori algorithm for discovering association rules between items in large databases, and the AOG algorithm for attribute-oriented generalization in large databases.  ...  We propose the share-confidence framework for knowledge discovery from databases which addresses the problem of mining itemsets from market basket data.  ...  In Section 3, we describe characterized itemsets and an algorithm for generating characterized itemsets from market basket data.  ... 
doi:10.1007/3-540-64383-4_14 fatcat:snuokc5p55daxgy25ihhsq2x7i

Ontology-Driven Method for Ranking Unexpected Rules

Mohamed Said Hamani, Ramdane Maamri
2009 Conférence Internationale sur l'Informatique et ses Applications  
Several rule discovery algorithms have the disadvantage to discover too much patterns sometimes obvious, useless or not very interesting to the user.  ...  In this paper we propose a new approach for patterns ranking according to their unexpectedness using semantic distance calculated based on a prior background knowledge represented by domain ontology organized  ...  In [15] , the subjective interestingness (unexpectedness) of a discovered pattern is characterized by asking the user to specify a set of patterns according to his/her previous knowledge or intuitive  ... 
dblp:conf/ciia/HamaniM09 fatcat:yk7u56cdefhmxfhykaanujhcue

Taming the metadata mess

V. M. Megler, David Maier
2013 2013 IEEE 29th International Conference on Data Engineering Workshops (ICDEW)  
We propose an approach that uses a blend of automated and "semi-curated" methods to extract metadata from large archives of scientific data, then evaluates ranked searches over this metadata.  ...  Creating metadata wrangling process for archive from composable components 2. Running & rerunning process 3.  ...  We briefly characterize the problem and describe our initial thoughts on resolving it.  ... 
doi:10.1109/icdew.2013.6547465 dblp:conf/icde/Megler13 fatcat:mr5fbjmpajdshlnf7znkw3fvbe

Finding interesting patterns using user expectations

Bing Liu, Wynne Hsu, Lai-Fun Mun, Hing-Yan Lee
1999 IEEE Transactions on Knowledge and Data Engineering  
To prevent the user from being overwhelmed by the large number of patterns, techniques are needed to rank them according to their interestingness.  ...  Given these expectations, the system uses a fuzzy matching technique to match the discovered patterns against the user's expectations, and then rank the discovered patterns according to the matching results  ...  From this ranking, we can see that discovered rule 6 and 8 conforms to user-expected rule 1 and 2 to a certain extent.  ... 
doi:10.1109/69.824588 fatcat:jeseklqnobebpgqeyqdsk6fqce

Characterizing Thermal Energy Consumption through Exploratory Data Mining Algorithms

Tania Cerquitelli, Evelina Di Corso
2016 International Conference on Extending Database Technology  
Each computed cluster is then locally characterized through a set of association rules to ease the manual inspection of the most interesting correlations between thermal consumption and weather conditions  ...  Nowadays large volumes of energy data are continuously collected through a variety of meters from different smartcity environments.  ...  Association rules extraction FARTEC discovers correlations from the cluster set identified by the K-Means algorithm.  ... 
dblp:conf/edbt/CerquitelliC16 fatcat:untwnpkvsfem5axkojfwe7ry3a

Comparative Study of Work Output and Wages of Construction Craftsmen in the Nigerian Public Sector

Philip O. Lawal
2011 Mediterranean Journal of Social Sciences  
, GSP) in order to achieve the goal to discover useful knowledge from the Moodle LMS.  ...  Recently, Educational Data Mining has become an emerging research field used to extract knowledge and discover patterns from E-learning systems.  ...  SELECT time,ip,userid,module,action,url FROM moodle.mdl_log WHERE course_id=5 Results Ranking Results The results of activity ranking are obtained using Rapid Miner v5.0 (see Figure 2 ).  ... 
doi:10.5901/mjss.2011.v2n3p138 fatcat:ts3o6ab4afbbjlwpbnsfkrcacq

Morpheus

Yiming Jing, Ziming Zhao, Gail-Joon Ahn, Hongxin Hu
2014 Proceedings of the 30th Annual Computer Security Applications Conference on - ACSAC '14  
• We have discovered more than 10,000 red pills, characterized them, and measured their accuracies Outline 3 • 3 Android malware, emulators, and red pills • Design & Implementation: Morpheus • Discovered  ...  red pills Photo from The Matrix, © 1999 Warner Bros.  ... 
doi:10.1145/2664243.2664250 dblp:conf/acsac/JingZAH14 fatcat:mi6dcuqodjd73fy3y5n3uignw4

Search Engine Optimization by Fuzzy Classification and Prediction

N. K. SenthilKumar, K. Kishore Kumar, N. Rajkumar, K. Amsavalli
2016 Indian Journal of Science and Technology  
Methods/Statistical Analysis: Accounting the characteristics such as page rank as usual, mouse movements of a user and the eye movements of a user while surfing a web page.  ...  Findings: The proposed algorithm takes each and every parameter in user point of view and also the usual page ranking and applies fuzzy logic intelligence to predict the subsequent search results.  ...  Introduction As a rule, a search engine comprises of crawler, indexer and ranker. A crawler retrieves web archives from the web 1 .  ... 
doi:10.17485/ijst/2016/v9i2/85818 fatcat:aqlz3gvd4jfrdctn67oo4ayaa4

On Ranking Discovered Rules of Data Mining by Data Envelopment Analysis: Some Models with Wider Applications [chapter]

Mehdi Toloo, Soroosh Nalchigar
2011 New Fundamental Technologies in Data Mining  
Many applications have used association rule mining techniques to discover useful information, including market basket analysis, product recommendation, web page pre-fetch, gene regulation pathways identification  ...  Using these algorithms, various rules may be obtained and only a small number of these rules may be selected for implementation due, at  ...  After the rules have been discovered from the association rule mining algorithms, DEA is used to rank those discovered rules based on the specified criteria.  ... 
doi:10.5772/13659 fatcat:hf6cjwskyrfudh6tlmxfnyxwyi

Ontology Knowledge Mining Based Association Rules Ranking

Rihab Idoudi, Karim Saheb Ettabaa, Basel Solaiman, Kamel Hamrouni
2016 Procedia Computer Science  
Medical association rules induction is used to discover useful correlations between pertinent concepts from large medical databases.  ...  We apply the method in our domain of interest -mammographic domain-using an existing mammographic ontology called Mammo * , with the goal of deriving interesting rules from past experiences, to discover  ...  In [22] , authors have proposed an additional gene ontology layer via discovering cross-ontology association rules from GO annotations.  ... 
doi:10.1016/j.procs.2016.08.147 fatcat:u6oi2aw7rnendmbcidf2clsjtm
« Previous Showing results 1 — 15 out of 152,239 results