Vous êtes sur la page 1sur 43

1. Which of the following is a clustering technique of data mining? Multilevel K-means Classifier Neural networks Score 0 of 1 (skipped) 2.

ata Mining is a multidisci!linar" field drawing works from###########. $tatistics ata%ase technolog" Knowledge acquisition &ll of the a%ove Score 0 of 1 (skipped) '. Which of the following data is included in the transactional data? $ales Cost (nventor" &ll of the a%ove Score 0 of 1 (skipped) ). *he whole logic of data mining is de!ending on####. Modeling $cattering $haring None of the a%ove Score 0 of 1 (skipped)

+. ######is the !rocess of anal",ing data from different !ers!ectives and summari,ing into useful information. ata !rocess ata management ata mining ata%ase management Score 0 of 1 (skipped) -. *he ne.us %etween######## and data mining is indis!uta%le. ata mining ata warehouse ata /rocessing 0M$

1. Which of the following are the ste!s of knowledge discover" in data%ases? Create a target dataset. ata cleaning and !re!rocessing. ata reduction and !ro1ection. &ll of the a%ove. Score 0 of 2 (skipped) 2. ata mining is also referred to as##########. Knowledge discover" in data%ases. Known discover" in data%ases. Knowledge domain data%ases. Knowledge discover" in data. Score 0 of 2 (skipped) '. ########## is defined as a !rocess of centrali,ed data management and retrieval.

ata mining ata warehousing ata stage ata%ase management Score 0 of 2 (skipped) ). Which of the following is the association technique of data mining? 2ne dimensional Multidimensional Multilevel &ll of the a%ove

1. (dentif" the true statements from the following3 1. 24&/ stands for 2nline &rithmetic /rocessing. 2. 24&/ is used to create decision su!!ort software. '. 24&/ summari,es data and makes forecasts. ). 24&/ su!!ort for multi!le user access and multi!le queries. $tatement 1 and 2 are false. $tatement 2 is false. $tatements ' and ) are false. 2nl" statement 1 is false. Score 0 of 4 (skipped) 2. (dentif" the true statement from the following3 1. /o!ular %usiness organi,ations use the data mining and data warehouse together.

2.

ata mining has emerged as a ke" %usiness intelligence technolog".

'. *he aim of data mining is to e.tract im!licit5 !reviousl" unknown information.

).

ata mining consists of man" useful techniques. $tatement 1 is false $tatement ' is false. $tatements 2 and ) are false. &ll the statements are true.

Score 0 of 4 (skipped) '. Which of the following statements are true? 1. 2!erational data includes sales5 cost5 inventor" and accounting.

2. Nono!erational data includes industr" sales5 forecast data.

'. Metadata is all a%out the data dictionar" definitions. ). 2!erational data includes sales5 forecast data.

$tatements 1 and 2 are false $tatement ' is false. $tatements ' and ) are false. 2nl" statement ) is false. 1. Which of the following is an e.am!le of multi!le heterogeneous data%ases? (0M ata 6oiner. Wi!ro ata 6oiner. 7C4 ata 6oiner. C$C ata 6oiner.

1. Which of the following is considered as the most !o!ular schema? $tar schema $now flake schema $now $chema

None of the a%ove Score 0 of 2 (skipped) 2. $tar schema is also referred as######### & fact schema & snow schema & constellation schema & fact constellation schema Score 0 of 2 (skipped) '. 8ach dimension have a ta%le associated with it5 called########. *a%le imension ta%le &ssociated ta%le Model ta%le Score 0 of 2 (skipped) ). ata warehouses and ######tools are %ased on a multidimensional data model. 24*/ 24&/ ata mining None of the a%ove

9ou have com!leted "our qui, attem!t. 9ou have scored : !oint;s<.

=uestion >esults Score 0 of 4 (skipped) 1. Which of the following statements are true? 1.&n 24*/ s"stem is customer ? oriented. 2.&n 24*/ s"stem manages current data that t"!icall" are too detailed to %e easil" used for decision making. '. &n 24*/ s"stem usuall" ado!ts an entit" ? relationshi! ;8>< data model

). *he access !atterns of an 24*/ s"stem consists mainl" of short5 atomic transactions. $tatements 1 and 2 are false $tatement ' is false. $tatements ) is false. &ll the a%ove statements are true. Score 0 of 4 (skipped) 2. Which of the following statement is true3 1. *he main characteristic of 24&/ is @information !rocessing@. 2. *he main characteristic of 24*/ is @o!erational !rocessing@. '. *he data%ase si,e of 24&/ is 1::M0 to A0. ). *he data%ase si,e of 24*/ is 1::A0 to *0. $tatement 1 is false $tatement ' is true. $tatements 2 and ) are false. $tatements 1 and 2 are true. Score 0 of 4 (skipped) '. (dentif" the true statements from the following3 1. *he to! ? down view allows the selection of the relevant information necessar" for the data warehouse.

2. ata warehouse view e.!oses the information %eing ca!tured5 stored5 and managed %" o!erational s"stems. '. ata source view includes fact ta%les and dimension ta%les.

). *he %usiness quer" view is the !ers!ective of data in the data warehouse from the view!oint of the end user. $tate true or false. $tatement 1 is false. $tatement 2 is true. $tatements ' and ) are false. $tatements 1 and ) true.

1. ########is a set of tools that ena%le an organi,ation to anal",e measura%le as!ects of %usiness. =uer" tools 0usiness intelligence 24&/ ata mining Score 0 of 1 (skipped) 2. ########## deals with all as!ects of managing the develo!ment5 im!lementation and o!eration of a data warehouse. ata mining ata stage ata warehousing &ll of the a%ove Score 0 of 1 (skipped) '. Converting data into knowledge and making it availa%le throughout the organi,ation are the 1o%s of !rocesses and a!!lications known as####. 0usiness (ntelligence

ata mining >( *wo-wa" integration Score 0 of 1 (skipped) ). Which of the following are the %usiness intelligence tools? 24&/ ata mining tools =uer" tools &ll of the a%ove Score 0 of 1 (skipped) +. ############is a term that encom!asses a %road range of anal"tical software and !rovide solution for gathering information. >( K( 0( None of the a%ove Score 0 of 1 (skipped) -. Which of following are the advantages of %usiness intelligence? Monitors financial health Maintains o!erational health >egulates (nformation feed %ack anal"sis &ll of the a%ove 1. Which of the following is su!!orted in the %usiness decisions? 0usiness intelligence Customer intelligence 2!erational intelligence

None Score 0 of 2 (skipped) 2. *he customer intelligence relates to#########. $ales $ervice Marketing &ll of the a%ove Score 0 of 2 (skipped) '. ############consists of relational and 24&/ cu%e services. (nformation la"er Warehouse la"er (ntelligence la"er 0usiness la"er Score 0 of 2 (skipped) ). ######## None la"er is required to e.tract5 cleanse and transform data into load files for the information warehouse.

1. Which of the following statement is true3 a. Multidimensional anal"sis is also known as 24&/. %. =ualit" tools allows the user to ask questions. c. ata mining tools automaticall" searches for significant !atterns.

d.24&/ software that gives the user the o!!ortunit" to look at the data from different dimensions. $tatement 1 is false.

$tatement 2 is false. $tatement ' and ) are false. &ll the a%ove statements are true. Score 0 of 4 (skipped) 2. Which of the following statements are true? 1. /ortals are usuall" organi,ed %" communities of users organi,ed for su!!liers5 customers5 em!lo"ers and !artners. 2./ortals can reduce the overall infrastructure costs of an organi,ation. '. We%-%ased !ortals are %ecoming common!lace as a single !ersonali,ed !oint of access for ke" %usiness information. ). /ortals will increases the overall infrastructure costs of organi,ation. $tatement 1 is false. $tatement 2 is false. $tatements ' and ) are true. $tatements 15 2 and ' are true. Score 0 of 4 (skipped) '. Which of the following statements are true3 1.2!erational (ntelligence relates to finance5 o!erations and manufacturing.

2.Customer intelligence related to !ricing5 forecasting and !romotion strateg".

'.Bisi%le la"er of the %usiness intelligence infrastructure is the a!!lications la"er.

). &!!lication la"er delivers the information to the %usiness users. $tatement 1 is false $tatement 2 is false $tatements 'C) are false &ll the a%ove statements are true. 1. (n #########each value in a %in is re!laced %" the mean value of the %in.

$moothing %" %in means $moothing %" %in medians $moothing %" %in %oundaries None of the a%ove Score 0 of 1 (skipped) 2. Which of the following method is hel!ful to re!lace all missing attri%ute values %" the same constant? Dill in the missing value manuall". Ese a glo%al constant to fill in the missing value. Ese the attri%ute mean to fill in the missing value. Ese the most !ro%a%le value to fill in the missing value. Score 0 of 1 (skipped) '. 0inning methods can !erform###########. 7ard smoothing 4ocal smoothing $mooth smoothing Nonlocal smoothing Score 0 of 1 (skipped) ). Which of the following a!!roach is a time consuming a!!roach? (gnore the tu!le Dill in the missing value manuall" Ese a glo%al constant to fill in the missing value None of the a%ove Score 0 of 1 (skipped) +. #############merges data from multi!le sources into coherent data store. ata integration ata mining

ata cleaning None of the a%ove Score 0 of 1 (skipped) -. ##########can %e a!!lied to remove noise and correct inconsistencies in the data. ata mining ata warehouse ata stage ata cleaning 1. Which of the following is the strateg" for data reduction? ata cu%e aggregation imension ata Com!ression Score 0 of 2 (skipped) 2. ata transformation involves in##########. $moothing &ggregation Aenerali,ation &ll of the a%ove Score 0 of 2 (skipped) '. Which of the following is a !ro%lem identified during data integration? (dentification !ro%lem (dentit" !ro%lem 8ntit" !ro%lem 8ntit" identification !ro%lem

Score 0 of 2 (skipped) ). *he !ro%lem of redundanc" can %e detected %" using#########. Correlation anal"sis >egression anal"sis Cluster anal"sis (dentification anal"sis 1. Which of the following statements are true3 1. ata Mining or knowledge discover" in data%ases. 2. ata Mining is the !rocess of discovering meaningful data. '. ata mining is the search for the relationshi!s. ). ata mining encom!asses a num%er of technical a!!roaches. $tatement 1 and 2 are false $tatement ' is false $tatement) is false &ll the a%ove statements are true Score 0 of 4 (skipped) 2. Which of the following statements are true? 1. & 0M$ is F ata Management $"stemF. 2. 0M$ manages data on !h"sical storage. '. 0M$ software !rovides the a%ilit" to store5 access and modif" the data. ). 2racle5 $=4G$erver5 02 and (nformi. in the relational ;> 0M$< world are the %est e.am!les of 0M$.

2nl" statement 1 is true $tatement 2 is false $tatements 25' and ) are true 2nl" statement 1 is true Score 0 of 4 (skipped) '. Which of the following statement is true3 1. 0M$ is an e.traction of detailed and summar" data. 2. 0M$ uses the induction method.

'. ata mining is the knowledge discover" of hidden !atterns and insights. ). ata mining uses the deduction method. $tatement 1 is false. $tatements 2 and ) are false. $tatement ' is false. $tatement ) is true.

1. ######is a hot %u,,word for a class of data%ase a!!lications that look for hidden !atterns in a grou! of data. ata stage Clustering $moothing %" %in %oundaries ata mining Score 0 of 1 (skipped) 2. Which of the following utili,es the induction model? ata mining $moothing Clustering 0M$ Score 0 of 1 (skipped) '. 8.traction of detailed and summar" data is a task of ######. 0M$ > 0M$ ata mining None Score 0 of 1 (skipped) ). Which of the following can manages the data on !h"sical storage devices?

ata stage 0M$ ata mining ata warehousing Score 0 of 1 (skipped) +. Which of the following are the techniques of data mining? Clustering ata summari,ation Classification &ll of the a%ove Score 0 of 1 (skipped) -. ########defined as the search for the relationshi!s. ata integration ata mining ata cleaning None of the a%ove 1. Which of the following are the !o!ular classification techniques? ecision trees Neural networks 0oth a and % Clustering Score 0 of 2 (skipped) 2. What are the ke" features of new algorithm develo!ed to discover the association rules? >educing the (G2 o!erations 0e efficient in com!uting

0oth a and % (ncreasing the (G2 o!erations Score 0 of 2 (skipped) '. ##########is a data mining technique used to !redict grou! mem%ershi! for data instances. $moothing Classification Aenerali,ation >egression Score 0 of 2 (skipped) ). Which of the following are the data%ase s"stems used in the organi,ations? *ransaction data%ase 4egac" data%ase Multimedia data%ase &ll of the a%ove 1. Which of the following statement is true3 1. ata cu%e aggregation o!erations are a!!lied to the data in the construction of a data cu%e. 2. imension reduction is hel!ful to detect the dimensions. '. 8ncoding mechanisms are used to reduce the data set si,e. ). Numerosit" reductions are used to re!lace the data. $tatement 1 is false. $tatement 2 is false. $tatement ' and ) are false. &ll the a%ove statements are true.

1. Esuall"5 the data is collected %" an#########s"stem running hundreds or thousands of transactions !er second. 2nline

2nline transaction !rocessing s"stem *ransaction ata mining Score 0 of 1 (skipped) 2. &ssociation mining can %e e.tended to ########. Mining ma.!atterns Drequent closed itemsets Correlation anal"sis &ll of the a%ove Score 0 of 1 (skipped) '. (f a rule descri%es associations %etween quantitative items or attri%utes5 then it is a ####association rule. =ualitative =uantitative Multilevel Multidimensional Score 0 of 1 (skipped) ). &ssociation rules are classified %ased on the #################. *"!es of values handled in the rule. imensions of data involved in the rule. 4evels of a%stractions involved in the rule set. &ll of the a%ove Score 0 of 1 (skipped) +. (f a concern associations %etween the !resence or a%sence of items5 it is a#########association rule. 0oolean Multilevel

$ingle dimensional Multidimensional Score 0 of 1 (skipped) -. ############rule mining searches for interesting relationshi!s among the items in a given data set. Clustering ata summari,ation &ssociation ata mining 1. *he algorithm uses two scans of the data%ase to discover all frequent sets. /riori /artition /ro!ortion /rior Score 0 of 2 (skipped) 2. & !riori algorithm is also known as#########. 4evel ? wise algorithm 4evel algorithm Wise algorithm /rior algorithm Score 0 of 2 (skipped) '. &n item set is a ######set if it is not a frequent set5 %ut all its !ro!er su%sets are frequent sets. (nfrequent Drequent 0order $u%set

Score 0 of 2 (skipped) ). Which among the following a!!roach esta%lishes a relationshi! %etween the required rate of return of a securit" and its s"stematic risks? Ca!ital asset !ricing model ividend forecast 8arnings !rice ratio >ealised "ield 1) 1. Which of the following statements are true3 1. Categorical attri%utes have a finite num%er of !ossi%le values5 with no ordering among the values. 2. =uantitative attri%utes are also called nominal attri%utes. '. =uantitative attri%utes are numeric and have an im!licit ordering among values ;e.g.5 age5 income5 !rice<. ). *echniques like hashing5 !artitioning5 and sam!ling ma" increase the !erformance. $tatement 1 is false $tatement 2 is true. $tatement ' is false. $tatements 15 ' and ) are true. Score 0 of 4 (skipped) 2. Which of the following statements are true3 .

1. &ssociation rules that involve two or more dimensions are referred to as multidimensional association rules. 2. Multidimensional association rules with no re!eated !redicates are called inter dimension association rules. '. Multidimensional association rules with re!eated !redicates h"%rid ? dimension association rules. ). ata%ase attri%utes can %e categorical or quantitative. $tatement 1 is false $tatement 2 is false $tatements 25' and ) are false &ll the statements are true Score 0 of 4 (skipped) '. Which of the following statements are true3

1. *he lower the a%straction level5 the smaller the corres!onding threshold. 2. 8ach level of a%straction does not has its own minimum su!!ort threshold. '. 8ach level of a%straction has its own minimum su!!ort threshold. ). >ules generated from association rule mining with conce!t hierarchies are called multi ? level association rules. $tatements 1 and 2 are false $tatement ' is false $tatements 15' and ) are true 2nl" statement ) is false Esuall"5 the data is collected %" an#########s"stem running hundreds or thousands of transactions !er second. 2nline 2nline transaction !rocessing s"stem *ransaction ata mining Score 0 of 1 (skipped) 2. &ssociation mining can %e e.tended to ########. Mining ma.!atterns Drequent closed itemsets Correlation anal"sis &ll of the a%ove Score 0 of 1 (skipped) '. (f a rule descri%es associations %etween quantitative items or attri%utes5 then it is a ####association rule. =ualitative =uantitative Multilevel Multidimensional Score 0 of 1 (skipped) ). (f a concern associations %etween the !resence or a%sence of items5 it is a#########association rule.

0oolean Multilevel $ingle dimensional Multidimensional Score 0 of 1 (skipped) +. &ssociation rules are classified %ased on the #################. *"!es of values handled in the rule. imensions of data involved in the rule. 4evels of a%stractions involved in the rule set. &ll of the a%ove Score 0 of 1 (skipped) -. ############rule mining searches for interesting relationshi!s among the items in a given data set. a Clustering ata summari,ation &ssociation ata mining

1. *he algorithm uses two scans of the data%ase to discover all frequent sets. /riori /artition /ro!ortion /rior Score 0 of 2 (skipped) 2. & !riori algorithm is also known as#########. 4evel ? wise algorithm

4evel algorithm Wise algorithm /rior algorithm Score 0 of 2 (skipped) '. Which of the following are the desira%le feature of an effective algorithm? *o reduce the (G2 o!erations *o moderate (G2 o!erations *o increase the (G2 o!erations Not much efficient in com!uting Score 0 of 2 (skipped) ). &n item set is a ######set if it is not a frequent set5 %ut all its !ro!er su%sets are frequent sets. (nfrequent Drequent 0order $u%set Which of the following statements are true3 1. Categorical attri%utes have a finite num%er of !ossi%le values5 with no ordering among the values. 2. =uantitative attri%utes are also called nominal attri%utes. '. =uantitative attri%utes are numeric and have an im!licit ordering among values ;e.g.5 age5 income5 !rice<. ). *echniques like hashing5 !artitioning5 and sam!ling ma" increase the !erformance. $tatement 1 is false . $tatement 2 is true. $tatement ' is false. $tatements 15 ' and ) are true. Score 0 of 4 (skipped) 2. Which of the following statements are true3 .

1. &ssociation rules that involve two or more dimensions are referred to as multidimensional association rules.

2. Multidimensional association rules with no re!eated !redicates are called inter dimension association rules. '. Multidimensional association rules with re!eated !redicates h"%rid ? dimension association rules. ). ata%ase attri%utes can %e categorical or quantitative. $tatement 1 is false $tatement 2 is false $tatements 25' and ) are false &ll the statements are true Score 0 of 4 (skipped) '. Which of the following statements are true3 1. *he lower the a%straction level5 the smaller the corres!onding threshold. 2. 8ach level of a%straction does not has its own minimum su!!ort threshold. '. 8ach level of a%straction has its own minimum su!!ort threshold. ). >ules generated from association rule mining with conce!t hierarchies are called multi ? level association rules. $tatements 1 and 2 are false $tatement ' is false $tatements 15' and ) are true 2nl" statement ) is false

1. ############can %e easil" converted to classification rules. ecision trees ata mining Classification Clustering Score 0 of 1 (skipped) 2. ######## anal"sis ma" %e !erformed on the data with the aim of removing an" irrelevant attri%utes from the learning !rocess. >edundant >elevance

Cluster Classification Score 0 of 1 (skipped) '. Which of the following technique refers to the !re!rocessing of data in order to remove the noise? ata mining ata cleaning ata warehousing ata stage Score 0 of 1 (skipped) ). $ome of the !re!rocessing ste!s ma" %e a!!lied to the data in order to im!rove the #########of the classification. &ccurac" 8fficienc" $cala%ilit" &ll of the a%ove Score 0 of 1 (skipped) +. Which of the following are the forms of data anal"sis? Classification /rediction 0oth a and % Clustering Score 0 of 1 (skipped) -. #######with hidden information can %e used for making intelligent %usiness decisions. Classification ata summari,ation

Cauteri,ation None of the a%ove 1. ##########measure is used to select the test attri%ute at each node in the tree. Aain (nformation (nformation gain Areed" Score 0 of 2 (skipped) 2. Which of the following is the %asic strateg" followed %" greed" algorithm? *ree starts as a single node. (f the sam!les are all of the same class5 then the node %ecomes a leaf. (t uses the same !rocess recursivel" to form a decision tree for the sam!les at each !artition. &ll of the a%ove Score 0 of 2 (skipped) '. Which of the following is the %asic algorithm for decision tree induction? $ingle-link clustering Com!lete-link Areed" algorithm ecision algorithm Score 0 of 2 (skipped) ). Which of the following is having a goal of im!roving classification accurac" on unseen data? ecision tree *ree !runing Clustering None of the a%ove. 1. Which of the following statements are true3 1.*he (D ? *78N rules ma" %e easier for humans to understand5

2. *he (D ? *78N rules ma" not %e easier for humans to understand. '. *he knowledge re!resented in decision trees can %e e.tracted and re!resented in the form of classification (D ? *78N rules. ).*he knowledge re!resented in decision trees cannot %e e.tracted and re!resented in the form of classification (D ? *78N rules. $tatement 1 is false $tatements 2 and ' are false. $tatements 1 and ' are true $tatement ) is true. Score 0 of 4 (skipped) 2. Which of the following statements are true3 1. *ree !runing methods address this !ro%lem of over fitting the data. 2. *ree !runing methods t"!icall" use statistical measures to remove the least relia%le %ranches. '. /ost !runing5 a tee is H!runedI %" halting its construction earl". ). /re!rinting a!!roach5 removes %ranches from a Hfull" grownI tree. $tatement 1 is false $tatements 1 and 2 are true $tatements ' and ) are true $tatement ) is true Score 0 of 4 (skipped) '. Which of the following statements are true3 Classification and !rediction methods can %e com!ared and evaluated through3 1. /redictive accurac"- refers to the a%ilit" of the model to correctl" !redict the class la%el of new or !reviousl" unseen data. 2. $!eed- refers to the com!utation costs involved in generating and using the model. '. >o%ustness-indicates the a%ilit" of the model to make correct !redictions given nois" data or data with missing values. ). $cala%ilit"- refers to the a%ilit" to construct the model efficientl" given large amount of data. $tatement 1 is false $tatement ' is false $tatements 2 and ) are false &ll the a%ove statements are true . Which of the following site offering !re-sale su!!ort5 !roducts for sale or after sales service and %acku!?

Eser 8-commerce Click stream /age view Score 0 of 1 (skipped) 2. Which of the following is hel!ful to !rovide the information regarding the user@s %ehavior? Eser Biew Eser /age Eser /rofile ata mining Score 0 of 1 (skipped) '. &#########is a click-stream record s!anning the entire We% and5 t"!icall"5 onl" that !ortion relating to the s!ecific site is availa%le. ata mining Eser Eser views Eser sessions Score 0 of 1 (skipped) ). #########is the series of !age-views that the user takes through the site. Click-stream We% !age /age view /age review Score 0 of 1 (skipped) +. Which of the following is the most valua%le resources for information retrievals and knowledge discoveries? World Wide We%

ata summari,ation ata mining 9ahoo Score 0 of 1 (skipped) -. Which of the following technologies are the right solutions for knowledge discover" on the we%? ata mining /rediction We% mining Clustering . *hree categories of data mining are mainl" concentrates on###########. rocess of knowledge discover" of im!licit /reviousl" unknown information /otentiall" useful information from the we% &ll of the a%ove Score 0 of 2 (skipped) 2. Which of the following algorithm is used %" the content mining in order to search and e.amine the data? Areed" $earch engine algorithms ecision tree algorithms ata mining algorithms Score 0 of 2 (skipped) '. Which of the following can %e used to e.amine the structure of !articular we%site? Content mining $tructure mining Esage mining None of the a%ove

Score 0 of 2 (skipped) ). Which of the following is a categor" of data mining? We% Content Mining We% $tructure Mining We% Esage Mining &ll of the a%ove 1. Which of the following statements are true3 1.2!en source software for we% mining includes >a!idMiner5 which !rovides modules for te.t clustering5 te.t categori,ation. 2.(nformation e.traction from we% !ages also utili,es >a!idMiner to create mash-u!s which com%ine information from various we% services and we% !ages5 to !erform we% log mining and we% usage mining. '.$&$ ata =ualit" $olution !rovides an enter!rise solution for !rofiling5 cleansing5 augmenting and integrating data to create consistent5 relia%le information. ). Weka is a collection of machine learning algorithms for data mining tasks. $tatement 1 is false . $tatement 2 is false. $tatements ' and ) are false &ll the statements are true Score 0 of 4 (skipped) 2. Which of the following statements are true3 1.*he data%ase a!!roach to We% mining involves the develo!ment of so!histicated &( ;&rtificial (ntelligence< s"stems. 2. $everal intelligent We% agents have %een develo!ed that search for relevant information using characteristics of a !articular domain to organi,e and inter!ret the discovered information. '.& num%er of We% agents use various information retrieval techniques and characteristics of o!en h"!erte.t We% documents to automaticall" retrieve5 filter5 and categori,e them. ). We% Watcher5 $"skill C We%ert are the e.am!les of we% agents. $tatement 1 is false $tatements 1 and 2 are true $tatements 25 ' and ) are true $tatement ) is false. Score 0 of 4 (skipped) '. Which of the following statements are true3

1. We% Content Mining5 We% $tructure Mining and We% Esage Mining are the three categories of data mining. 2. We% Content Mining is mainl" focused on the *e.t and Multimedia documents. '. We% $tructure Mining is mainl" focused on the 7"!erlink structure. ). We% Esage Mining is mainl" focused on the We% 4og records. $tatement 1 is false $tatement 2 is false &ll the a%ove statements are true $tatements ' and ) are false 1. Which of the following !ro%lems of data mining are usuall" not !resent in information retrieval s"stems? Concurrenc" control >ecover" *ransaction management &ll of the a%ove Score 0 of 2 (skipped) 2. #########is concerned with the organi,ation and retrieval of information from a large num%er of te.t%ased documents. (nformation retrieval $earch engine algorithms *raditional information retrieval techniques None of the a%ove Score 0 of 2 (skipped) '. *he significance of #####data%ases has %een increasing with the increased amount of information availa%le in electronic form. Multimedia data%ases *e.t data%ases >elational data%ases None of the a%ove Score 0 of 2

(skipped) ). *he########### contains a color la"out vector and an edge la"out vector. 4a"out descri!tor Deature descri!tor Bectors Deature vector

MCQ-Unit 10-4 Mark Questions

9ou have com!leted "our qui, attem!t. 9ou have scored : !oint;s<.

=uestion >esults Score 0 of 4 (skipped) 1. Which of the following statements are true3 1. =0(C su!!ort %oth sam!le-%ased and image feature s!ecification queries.

2. (mage-sam!le-%ased queries find all of the images that are similar to the given image sam!le.

'. (mage feature s!ecification queries s!ecif" or sketch image features.

). =0(C onl" su!!orts sam!le %ased queries. $tatement 1 is false $tatement 2 is false $tatements ' and ) are false $tatements 15 2 and ' are true Score 0 of 4 (skipped) 2. Which of the following statements are true3

1. &ssociation rules involving multimedia o%1ects can %e mined in image and video data%ases. 2. & multi resolution mining strateg" reduces the overall data mining cost without loss of the qualit".

'.Content-%ased retrieval s"stems5 which %uild indices. ). escri!tion -%ased retrieval s"stems su!!ort retrieval %ased on the image content. $tatement 1 is false 2nl" statements 1 and 2 are true $tatements 25 ' and ) are true $tatement ) is true Score 0 of 4 (skipped) '. Which of the following statements are true3 1. Multimedia information is u%iquitous and required in man" a!!lications. 2.& multimedia data%ase s"stem stores and manages a large collection of multimedia data. '.Multimedia data%ase s"stems are increasingl" common owing to the !o!ular use of audio video equi!ment5 digital cameras5 C ->2Ms5 and the (nternet. ). *"!ical multimedia data%ase s"stems include N&$&Js 82$5 audio-video data%ases5 and (nternet data%ases. $tatement 1 is false $tatement 2 is false &ll the a%ove statements are true $tatements ' and ) are false 1. Which of the following statements are true3 1. Market management is mainl" concentrates on target marketing5 customer relationshi! management and market %asket anal"sis. 2. >isk management is mainl" deals with forecasting5 customer retention and im!roved underwriting. '. Market management is mainl" deals with qualit" control and com!etitive anal"sis. ). >isk management is mainl" concentrates on market %asket anal"sis5 cross-selling and market segmentation.

$tatement 1 is false $tatement 2 is false $tatements 2 and ' are true

2nl" statements ' and ) are false 1. *he !redictive !rofiling a!!roach is %ased on a########model. 4a"out Deature descri!tor Dle.i%le !ro%a%ilistic None of the a%ove 1. ata mining has %een a!!l"ing in a wide variet" of areas like############. 0usiness a!!lications $cientific a!!lications 0oth a and % None of the a%ove 1. ################are ra!idl" growing due to the increasing amount of information availa%le in electronic form. (nformation retrieval ocument ranking methods *e.t data%ases *erm ta%le Score 0 of 1 (skipped) 2. $ome s"stems5 such as################5su!!ort %oth sam!le-%ased and image feature s!ecification queries. =0(C ;=uer" 0" (mage Content< (mage 8.cavator Deature descri!tor 4a"out descri!tor Score 0 of 1 (skipped) '. ########### uses semantic information em%edded in link structures as well as document content to create cluster hierarchies of h"!erte.t documents and structure an information s!ace.

We%watcher 7"/ursuit $"skill (4& Score 0 of 1 (skipped) ). #############retrieves !roduct information from a variet" of vendor sites using onl" general information a%out the !roduct domain. $ho!0ot (4& 2CC&M (nformation Manifold Score 0 of 1 (skipped) +. (n client $ide monitoring5 %" inserting ######### into each We% !age5 looks to %e a !romising a!!roach %ut raises !rivac" issues in an organisation. Birus $!"wares 0ugs Direwall Score 0 of 1 (skipped) -. ########## is a collection of machine learning algorithms for data mining tasks. Weka 6ava code 2!en source software $&$ data qualit" solution Score 0 of 1 (skipped) K. *he to! - most node in a tree is the ##########. *ree node

(nternal node 4eaf node >oot node Score 0 of 1 (skipped) L. #################### refers to the level of understanding and insight that is !rovided %" the model. (nter!reta%ilit" $cala%ilit" >o%ustness $!eed Score 0 of 1 (skipped) M. ################ involves scaling all values for a given attri%ute so that the" fall within a small s!ecified range. /redictive accurac" Normalisation *ree !runing Classification Score 0 of 1 (skipped) 1:. ################ refers to the !re!rocessing of data in order to remove or reduce noise and the treatment of missing values. >elevance anal"sis ata transformation Normalisation ata cleaning 1. ################are ra!idl" growing due to the increasing amount of information availa%le in electronic form. (nformation retrieval ocument ranking methods *e.t data%ases

*erm ta%le Score 0 of 1 (skipped) 2. ########### uses semantic information em%edded in link structures as well as document content to create cluster hierarchies of h"!erte.t documents and structure an information s!ace. We%watcher 7"/ursuit $"skill (4& Score 0 of 1 (skipped) '. #############retrieves !roduct information from a variet" of vendor sites using onl" general information a%out the !roduct domain. $ho!0ot (4& 2CC&M (nformation Manifold Score 0 of 1 (skipped) ). ########## is a collection of machine learning algorithms for data mining tasks. Weka 6ava code 2!en source software $&$ data qualit" solution Score 0 of 1 (skipped) +. (n client $ide monitoring5 %" inserting ######### into each We% !age5 looks to %e a !romising a!!roach %ut raises !rivac" issues in an organisation. Birus $!"wares 0ugs Direwall

Score 0 of 1 (skipped) -. ##################### is la%our-intensive if !erformed manuall". Content-%ased retrieval escri!tion-%ased retrieval (mage sam!le-%ased queries Colour histogram?%ased signature Score 0 of 1 (skipped) K. $ome s"stems5 such as################5su!!ort %oth sam!le-%ased and image feature s!ecification queries. =0(C ;=uer" 0" (mage Content< (mage 8.cavator Deature descri!tor 4a"out descri!tor Score 0 of 1 (skipped) L. Most of the We% information retrieval tools onl" use the ##################5 while the" ignore the link information that could %e ver" valua%le. Multi-level data%ase We% Esage Mining *e.tual information $tructure mining Score 0 of 1 (skipped) M. Which of the following search for relevant information5 uses characteristics of a !articular domain ;and !ossi%l" a user !rofile5< to organise and inter!ret the discovered information? /ersonalised we% agents (nformation filtering (ntelligent We% agents We% =uer" $"stems

Score 0 of 1 (skipped) 1:. *he to! - most node in a tree is the ##########. *ree node (nternal node 4eaf node >oot node 1. 2n-line li%rar" catalog s"stems5 on-line document management s"stems and the more recentl" develo!ed We% search engines are e.am!les of #################. *raditional data%ase s"stems *e.t >etrieval Methods ocument ta%le (nformation >etrieval s"stems Score 0 of 1 (skipped) 2. ###############is essentiall" a !rocess of mining useful ke"words from the to! retrieved documents. (t also often leads to im!roved retrieval !erformance. >elevance feed%ack /seudo-feed%ack escri!tion-%ased retrieval s"stems Wavelet-%ased signature Score 0 of 1 (skipped) '. (n data classification5 each tu!le is assumed to %elong to a !redefined class5 as determined %" one of the attri%utes5 called the #################. *raining sam!les Class la%el attri%ute *est set sam!les *raining data set Score 0 of 1 (skipped)

). & good measure to use with##################clusters is the difference %etween the distance value at which it was formed and the distance value at which it is merged into the ne.t level. K-means 7ierarchical &gglomerative ivisive Score 0 of 1 (skipped) +. #############5 offers clustering %ased on 4ocalisation of &nomalies ;4&< algorithm. 0a"esia 4a% Cvi, (0M (ntelligent miner /ol"&nal"st Score 0 of 1 (skipped) -. *he################a!!roach to clustering starts out with a fi.ed num%er of clusters and allocates all records into e.actl" that num%er of clusters. Com!lete linkage method 7ierarchical clustering K-means Centroid distance Score 0 of 1 (skipped) K. (n##############clustering5 we consider the distance %etween one cluster and another cluster to %e equal to shortest distance from an" mem%er of one cluster to an" mem%er of the other cluster. $ingle-link Com!lete-link &verage-link $ingle linkage Score 0 of 1 (skipped) L. & ################## is a frequent !attern5 !5 such that an" !ro!er su!er!attern of ! is not frequent.

Ma.!attern Drequent closed itemset Ma.imal frequent set 0order set Score 0 of 1 (skipped) M. ###############algorithm was !ro!osed %" 0in et al. in 1MMK. *he rationale %ehind like a train running over the data5 with sto!s at intervals M %etween transactions. /riori &lgorithm /artition algorithm /incers - search algorithm "namic (temset Counting &lgorithm Score 0 of 1 (skipped) 1:. &n item set is a ######################5 if it is not a frequent set5 %ut all its !ro!er su%sets are frequent sets. (temsets Ma.imal frequent set 0order sets $u%sets 1. *o design an effective data warehouse one needs to understand and anal"se ################## and construct a %usiness anal"sis framework. 0usiness needs 0usiness model 0usiness risks 0usiness !rofit Score 0 of 1 (skipped) 2. ################is a visualisation o!eration that rotates the data a.es in view5 in order to !rovide an alternative !resentation of the data. $lice and ice rill-down (C is that it works

/ivot >oll-u! Score 0 of 1 (skipped) '. *he most !o!ular data model for a data warehouse is a #############################. fact constellation schema Dact ta%le $tar schema Multi-dimensional model Score 0 of 1 (skipped) ). *he : ? cu%oid5 which holds the highest level of summarisation5 is called the ###########.

&!e. cu%oid 0ase cu%oid 7"%rid 24&/ ;724&/< >24&/ Score 0 of 1 (skipped) +. &################facilitates customer relationshi! management since it !rovides a consistent view of customers and items across all lines of %usiness5 all de!artments and all markets. *o! ? down view ata warehouse ata warehouse view 0ottom ? u! a!!roach Score 0 of 1 (skipped) -. Knowledge discover" in data%ases is the non-trivial !rocess of ################# valid novel !otentiall" useful and ultimatel" understanda%le !atterns in the data. Marking $!otting

Calculating (dentif"ing Score 0 of 1 (skipped) K. 2ne of the data mining software is ############. (ntelligent miner (0M 2racle $A( Score 0 of 1 (skipped) L. *he anal"tical techniques used in data mining are often well-known ######################### and techniques. Mathematical algorithms Machine learning $tatistics &rtificial (ntelligence Score 0 of 1 (skipped) M. ata mining methods or techniques find the relations %etween varia%les or data in the given data %ase and e.!ress these relations using ####################. $et thoer" &lgorithm relations $tatistical nomenclature &lge%raic e.!ression Score 0 of 1 (skipped) 1:. 24&/ is a technolog" that is used to create############ software. (mage !rocessing ecision su!!ort ata su!!ort

>elational data%ase

Vous aimerez peut-être aussi