VIRTUAL PRESENCE

1
VIRTUAL PRESENCE
Authors
Voislav Galic, vgalic_at_bitsyu.net
Duan Zecevic, zdusan_at_softhome.net
Ðorde Ðurdevic, madcat_at_tesla.rcub.bg.ac.yu
Veljko Milutinovic, vm_at_etf.bg.ac.yu
http//galeb.etf.bg.ac.yu/vm/tutorial
2
DEFINITION
Virtual presence is a term with various shades
of meanings in different industries, but its
essence remains constant it is a new tool that
enables some form of telecommunication in which
the individual may substitute their physical
presence with an alternate, typically,
electronic presence
3
SUMMARY
- Introduction to Virtual Presence - Data Mining
for Virtual Presence - A New Software
Paradigm - Selected Case Studies
4
INTRODUCTION TO VP

• - Definitions
• VP applications
• Psychological aspects

5
DATA MINING FOR VP

• Why Data Mining?
• What can Data Mining do?
• Growing popularity of Data Mining
• - Algorithms

6
SOFTWARE AGENTS

• A new software paradigm
• Standardization
• FIPA specifications
• Agent management
• Agent Communication Language

7
GoodNews (CMU)

• Categorization of financial news articles
• Co-located phrases
• Domain Experts
• Implementation and results

Carnegie Mellon University, Pittsburgh, USA
8
iMatch (MIT)

• The idea
• - associate MIT students and staff in order to
  ease their cooperation
• - help students find resources they need
• Implementation
• advanced, agent-based system architecture
• - Tomorrow?

Massachusetts Institute of Technology, USA
9
Tourist city (ETF)

• A qualitative step forward in the domain of
  maximization of customer satisfaction
• Technologies
• Data Mining
• Software Agents (mobile)

Faculty of Electrical Engineering, University
of Belgrade, Serbia and Montenegro
10
CONCLUSION

• This tutorial will attempt to familiarize you
  with
• The concept of VP (Virtual Presence) as a
  new technological challenge
• The new paradigms and technologies that will
  bring the VP to everyday life
• - Data Mining - Software Agents

11
INTRODUCTION

• Virtual presence will arguably be one of the
  most important aspects of personal communication
  in the twenty-first century

12
Essence of VP

• The usefulness and reliability of virtual
  presence
• The ability to conduct everyday tasks by being
  virtually or electronically present

13
How to Accomplish it?

• The presence is accomplished through the
  Internet, video, or other communications,
  perhaps even psychically one day
• Technological advance will sophisticate virtual
  presence, altering the very meaning of the word
  presence

14
VP Applications

• VP in government
• Sunshine laws
• Voting

15
VP Applications

• VP in business
• Online board meetings
• Shareholder voting online

16
VP Applications

• VP in education
• interactive lectures and courses

17
VP Applications

• VP in medicine
• Telemedicine
• Diagnostics
• Remote surgery
• Risks
• Privacy

18
VP Applications

• VP in everyday life
• Telecommuting/Telework
• Software agents as our virtual shadows

19
Psychological Aspects

• Cyberspace and Mind
• Presence in Virtual Space
• Communal Mind and Virtual Community

20
DATA MINING

• Knowledge discovery is a non-trivial process of
  identifying valid, novel, potentially useful, and
  ultimately understandable patterns in data

21
Many Definitions

• Data mining is also called data or knowledge
  discovery
• It is a process of inferring knowledge from
  large oceans of data
• Search for valuable information in large volumes
  of data
• Analyzing data from different perspectives and
  summarizing it into useful information

22
Why Data Mining ?

• DM allows you to extract knowledge from
  historical data and predict outcomes of future
  situations
• Optimize business decisions and improve
  customers satisfaction with your services
• Analyze data from many different angles,
  categorize it, and summarize the relationships
  identified
• Reveal knowledge hidden in data and turn this
  knowledge into a crucial competitive advantage

23
What Can Data Mining Do?

• Identify your best prospects and then retain
  them as customers
• Predict cross-sell opportunities and make
  recommendations
• Learn parameters influencing trends in sales and
  margins
• Segment markets and personalize communications
• etc.

24
The Power of Data Mining

• Having a database is one thing, making sense of
  it is quite another
• It does not rely on narrow human queries to
  produce results, but instead uses AI related
  technology and algorithms
• Inductive reasoning
• Using more than one type of algorithm to search
  for patterns in data
• Data mining produces usually more general (more
  powerful) results than those obtained by
  traditional techniques
• Relational DB storage and management technology
  is OK for data mining applications less than 50
  gigabytes

25
Reasons for the Growing Popularity of Data Mining

• Growing Data Volume
• Low Cost of Machine Learning
• Limitations of Human Analysis

26
Tasks Solved by Data Mining

• Predicting
• Classification
• Detection of relations
• Explicit modeling
• Clustering
• Market basket analysis
• Deviation detection

27
Algorithms

• Generally, their complexity is around n (log
  n)(n is the number of records)
• Data mining includes three major components,
  with corresponding algorithms
• Clustering (Classification)
• Association Rules
• Sequential Analysis

28
Classification Algorithms

• The aim is to develop a description or model for
  each class in a database, based on the features
  present in a set of class-labeled training
  data
• Data Classification Methods
• Statistical algorithms
• Neural networks
• Genetic algorithms
• Nearest neighbor method
• Rule induction
• Data visualization

29
Classification-rule Learning

• Data abstraction
• Classification-rule learning finding rules or
  decision trees that partition given data into
  predefined classes
• Hunts method
• Decision tree building algorithms
• ID3 / C4.5 algorithm
• SLIQ / SPRINT algorithm (IBM)
• Other algorithms

30
Parallel Algorithms

• Basic Idea N training data items are randomly
  distributed to P processors. All the processors
  cooperate to expand the root node of the
  decision tree
• There are two approaches for future progress
  (the remaining nodes)
• Synchronous approach
• Partitioned approach

31
Association Rule Algorithms

• Association rule implies certain association
  relationship among the set of objects in a
  database
• These objects occur together, or one implies
  the other
• Formally X ? Y, where X and Y are sets of items
  (itemsets)
• Key terms
• Confidence
• Support
• The goal to find all association rules that
  satisfy user-specified minimum support and
  minimum confidence constraints.

32
Association Rule Algorithms

• Apriori algorithm and its variations
• AprioriTid
• AprioriHybrid
• FT (Fault-tolerant) Apriori
• Distributed / Parallel algorithms (FDM, )

33
Sequential Analysis

• Sequential Patterns
• The problem finding all sequential patterns
  with user-specified minimum support
• Elements of a sequential pattern need not to be
• consecutive
• simple items
• Algorithms for finding sequential patterns
• count-all algorithms
• count-some algorithms

34
Conclusion

• Drawbacks of existing algorithms
• Data size
• Data noise
• There are two critical technological drivers
• Size of the database
• Query complexity
• The infrastructure has to be significantly
  enhanced to support larger applications
• Solutions
• Adding extensive indexing capabilities
• Using new HW architectures to achieve
  improvements in query time

35
THE NEW SOFTWARE PARADIGM

• All software agents are programs, but not all
  programs are agents

36
Many Definitions

• Computational systems that inhabit some dynamic
  environment, sense and act autonomously and
  realize a set of goals or tasks for which they
  are designed
• Hardware or (more usually) software-based
  computer system that enjoys the following
  properties

- Reactive (sensing and acting) - Autonomous -
Goal-oriented (pro-active purposeful) -
Temporally continuous - Communicative (socially
able)
- Learning (adaptive) - Mobile - Flexible -
Character
37
Interesting Topic of Study

• They draw on and integrate many diverse
  disciplines of computer science and other areas
• objects and distributed object architectures
• adaptive learning systems
• artificial intelligence and expert systems
• collaborative online social environments
• security
• knowledge based systems, databases
• communications networks
• cognitive science and psychology

38
What Problems do Agents Solve ?

• Client/server network bandwidth problem
• In the design of a client/server architecture
• The problems created by intermittent or
  unreliable network connections
• Attempts to get computers to do real thinking for
  us

39
The New Software Paradigm

• Unless special care has been taken in the design
  of the code, two software programs cannot
  interoperate
• The promise of agent technology is to move the
  burden of interoperability from software
  programmers to programs themselves
• This can happen if two conditions are met
• A common language (Agent Communication Language
  ACL)
• An appropriate architecture

40
The Need for Standards

• Anywhere, anytime consumer access to the
  Universal bouquet of information and services is
  the new goal of the information revolution
• The scope of Internet standards makes the scope
  of choices extreme
• The Foundation for Intelligent Physical Agents
  (FIPA), established in 1996 in Geneva
• international non-profit association of companies
  and organizations
• specifications of generic agent technologies.

41
FIPA Specifications

• Agent Management
• Agent Communication Language
• Agent/Software Integration
• Agent Management Support for Mobility
• Human-Agent Interaction
• Agent Security Management
• Agent Naming
• FIPA Architecture
• Agent Message Transport
• etc.

42
Agent Management

• Provides the normative framework within which
  FIPA agents exist and operate
• Establishes the logical reference model for the
  creation, registration, location, communication,
  migration and retirement of agents

• The entities contained in the reference model are
  logical capability sets and do not imply any
  physical configuration
• - Additionally, the implementation details of
  individual APs and agents are the design choices
  of the individual agent system developers

43
Components of the Model

• Agent

- computational process - fundamental actor on an
AP - as a physical software process has a life
cycle that has to be managed by the AP

• Directory Facilitator

• - yellow pages to other agents
• supported function are
• register
• deregister
• modify
• search

• Agent Management System

• - white pages services to other agents
• - maintains a directory of AIDs which contain
  transport addresses
• supported function are
• register
• deregister
• modify
• search
• get-description
• operations for underlying AP

• Message Transport Service

- communication method between agents

• Agent Platform

- physical infrastructure in which agents can be
deployed

• Software

- all non-agent, executable collections of
instructions accessible through an agent
44
Agent Life Cycle

• FIPA agents exist physically on an AP and utilize
  the facilities offered by the AP for realising
  their functionalities
• In this context, an agent, as a physical software
  process, has a physical life cycle that has to
  be managed by the AP

The state transitions of agents can be described
as
- create - invoke - destroy - quit - suspend
- resume - wait - wake up - move - execute
45
Agent Communication Language

• The specification consists of a set of message
  types and the description of their meanings
• Requirements
• Implementing a subset of the pre-defined message
  types and protocols
• Sending and receiving the not-understood message
• Correct implementation of communicative acts
  defined in the specification
• Freedom to use communicative acts with other
  names, not defined in the specification
• Obligation of correctly generating messages in
  the transport form
• Language must be able to express propositions,
  objects and actions
• The use of Agent Management Content Language and
  ontology

46
ACL Syntax Elements

• Pre-defined message parameters

sender receiver content reply-with in-reply-t
o envelope language ontology reply-by protoco
l conversation-id

• Communicative acts

accept-proposal agree cancel cfp confirm disconfir
m failure inform inform-if inform-ref
not-understood propose query-if query-ref refuse r
eject-proposal request request-when request-whenev
er subscribe
47
Communication Examples

• Agent i confirms to agent j that it is,
• in fact, true that it is snowing today
• (confirm     sender i     receiver j   
  content "weather( today, snowing )"   
  language Prolog
• )

- Agent i asks agent j if j is registered with
domain server d1 (query-if     sender i    
receiver j    content       (registered
(server d1) (agent j))    reply-with
r09) ... (inform    sender j    receiver
i    content (not (registered (server d1)
(agent j)))    in-reply-to r09)
- Agent j replies that it can reserve trains,
planes and automobiles (inform     sender j
    receiver i    content       ( (iota ?x
(available-services j ?x))         
((reserve-ticket train)          
(reserve-ticket plane)           (reserve
automobile))       )    )

• Agent i, believing that agent j thinks that a
  shark is a
• mammal, attempts to change j's belief
• (disconfirm     sender i     receiver j   
  content (mammal shark)
• )

- Agent j refuses to i reserve a ticket for i,
since i there are insufficient funds in i's
account (refuse     sender j     receiver
i    content      (       (action j
(reserve-ticket LHR, MUC, 27-sept-97))      
(insufficient-funds ac12345)      )   
language sl)
- Auction bid (inform    sender agent_X    
receiver auction_server_Y    content      
(price (bid good02) 150) in-reply-to
round-4 reply-with bid04 language sl
ontology auction)
- Agent i did not understand an query-if message
because it did not recognize the
ontology (not-understood    sender i   
receiver j    content ((query-if sender j
receiver i )              (unknown (ontology
www)))    language sl )
- Agent i asks agent j for its available
services (query-ref     sender i    
receiver j    content       (iota ?x
(available-services j ?x))    )
48
Agent/Software Integration

• Integration of services provided by non-agent
  software into a multi-agent community
• Definition of the relationship between agents
  and software systems
• Allowing agents to describe, broker and negotiate
  over software systems
• Allowing new software services to be dynamically
  introduced into an agent community
• Defining how software resources can be described,
  shared and dynamically controlled in an agent
  community

49
New Agent Roles

• To support specification, two new agent roles
  have been identified
• Agent Resource Broker (ARB)
• WRAPPER Agent

50
GoodNews

• A system that automatically categorizesnews
  reports that reflect positively or negativelyon
  a companys financial outlook

51
Introduction

• Correlation between news reports on a companys
  financial outlook and its attractiveness as an
  investment
• Volume of such reports is huge
• A new text classification algorithm Domain
  Experts with self-confident sampling
  technique
• Two types of data
• (Human-)labeled
• Unlabeled
• The algorithm classifies financial news into the
  predefined five categories
• (good) ? (good, uncertain) ? (neutral) ? ? (bad,
  uncertain) ? (bad)

52
Introduction

• Text categorization task
• FCP (Frequently Co-located Phrase) the building
  elementfor the categorization algorithm
• Text categorization very difficult domainfor
  the use of machine learning
• Very large number of input features
• High level of attribute and class noise
• Large percent of irrelevant features
• Very expensive labeled data, while unlabeled
  data are cheaply available

53
Categorization

• The algorithm categorizes each given news article
  into the predefined categories in terms of
  referred companys financial well-being
• GOOD strong and explicit evidences of the
  companys financial status
• shares of ABC company rose 2 percent to
  24-15/16
• GOOD, UNCERTAIN predictions and forecasts of
  future profitability
• ABC company predicts fourth-quarter earnings
  will be high

54
Categorization

• NEUTRAL nothing is mentioned about the
  financial well-being of the company
• ABC announced plans to focus on products based
  on recycledmaterials
• BAD, UNCERTAIN predictions of future loses
• ABC announced today that fourth-quarter results
  couldfall short of expectations
• BAD explicitly bad evidences
• shares of ABC fell 0.57 to 44.65 in early NY
  trading
• Problems with construction of the training (i.e.
  labeled)data set inter-indexer inconsistency

55
Co-located Phrase

• The proposed algorithm labels the unlabeled
  news articlesthrough voting process among
  experts that are FCPs
• Definition a co-located phrase is a sequence of
  nearby, but not necessarily consecutive words
• shares of ABC rose 8.5 (shares, rose) GOOD
• ABC presented its new product (present,
  product) NEUTRAL
• Contextual information
• The use of heuristics to cope with enormous
  phrase space(amount of possible phrases)

56
Naive-Bayes v Domain Experts

• Naive-Bayes with EM (Expectation Maximization)
• Problems with small sets of labeled (training)
  data
• EM (Expectation Maximization) a class of
  iterative algorithms for maximum likelihood
  estimation in problems with incomplete data
• Domain Experts algorithm is able to deal with
  inconsistent hypotheses
• Iterative building of the training set

57
Implementation and Results

• The experiment focused on two performance
  criteria
• Using unlabeled data for improving categorization
  accuracy
• The categorization itself
• The accuracy is around 75 (total of 2000 news
  articles)
• Comparison of a few different methods (picture)

58
Conclusions

• Domain Experts with SC sampling outperform naive
  Bayes with EM
• collocation property and vote entropy are
  appropriate to such a domain
• The accuracy of around 75 is the limit with the
  techniques used
• Better performance could be achieved by using
  some natural language processing techniques
• Such techniques are pretty rudimental today

59
iMatch

• The vision of each MIT student
• having a personal software agent,
• which helps to manage its owner's academic life

60
Introduction

• The aim bring together MIT students and staff
  who may usefully collaborate with each other
• This collaboration can have several goals
• completing final projects
• studying for exams
• tutoring one another
• iMATCH agents are supposed to facilitate students
  and faculty matching for
• Research
• Teaching
• Internship
• opportunities within and across campuses

61
iMatch Agent Architecture

• iMatch agents are situated within an environment
• Sensors of the agent convert environmental
  inputsinto representations that can be
  manipulated within the agent
• Effectors translate actions planned by the
  agentinto executable statements for the
  environment
• The action planner selects the action with the
  highest utilityaccording to the owners
  preference specification

62
Impacts and Benefits

• MIT
• Benefit MIT students by matching them to
  appropriate resources
• Aid the recruitment of student researchers
• Help students manage their lives
• Use iMATCH in Medical Computing
• GLOBAL
• Facilitate Cross Community Collaboration

63
Research Topics

• Knowledge representation
• preference specification
• Multi-agents systems
• reputation management system
• static interest matching
• dynamic interest matching
• Infrastructure
• distributed security infrastructure

64
Ceteris Paribus Preference

• Ceteris paribus relations express a preference
  over sets of possible outcomes
• All possible outcomes are considered to be
  describable by some (large) set of binary
  features (true or false)
• The specified features are instantiated to either
  true or false
• Other features are ignored

65
CPP Agent Configuration

• Specify a domain for preference
• Agent methods of communication and notification
• Different security settings of different servers
• Preference statements themselves
• How to get users to easily adjust C.P. rules
  (graphical interface)
• Pose hypothetical preference questions to user to
  help complete the preferences of an ambivalent
  user
• People will only put down their true profile, if
  they know that the system is secure

66
Static Interest Matching

• Group together similar users for specific context
• This enables viewing a human user as a
  resourcefor dynamic resource discovery
• (locate experts, enthusiasts,...)
• The approach 
• Keyword matching
• Ontological matching using Kulbeck-Leiber (KL)
  distance

67
Dynamic Interest Matching

• Location and/or temporal specific resource
  matching
• As students and their agents move from one
  physical location to another, iMatch services for
  matching the closest resources can be offered
• The idea anything worthwhile is locatable
• The approach
• Intentional naming scheme
• Reputation based resource discovery

68
Technology

• Components
• Distributed Multi-Agent Infrastructures
• Ceteris Paribus preference-based Interest
  Matching
• Reputation Management Infrastructure
• Technology
• Microsoft.Net
• Bluetooth
• IEEE 802.11
• Smartcards (PC/SC)
• INS (International Naming System)

69
Conclusion

• Benefit MIT students by matching them to
  appropriate resources
• Static interest matching
• Group together similar users for specific context
• This enables viewing a human user as a resource
  for dynamic resource discovery (locate experts,
  enthusiasts,...)
• Dinamic interest matching
• Location and/or temporal specific resource
  matching As students and their agents move from
  one physical location to another, iMatch
  services for matching the closest resources can
  be offered
• Help students manage their lives

70
The near future

• The focus of the research is on e-tourism after
  the year 2005, but the applications of the
  proposed infrastructure are multifold

71
Introduction

• The assumptions
• after the year 2005, each tourist in Europe will
  be equiped with a cell phone of the power same or
  better than the Pentium IV
• whenever a tourism-based service or product is
  purchased, a mobile agent is assigned to that
  cell phone PC, to monitor the behaviour of the
  customer
• all tourist cell phone PCs create an AD-HOC
  networkaround the points of touristic
  attractions, and link to a data mine that
  collects all information of interest

72
How to accomplish it?

• The information of interest is not collected by
  asking the customer to fill out the forms, but by
  monitoring the behaviour of the customer
• The collected information, sorted in the data
  mine, is made available to other tourists, as an
  on-line owner-independent source of information
  about the given services and/or products

73
What can be done

• If a tourist would like to know, at that very
  moment, what restaurant has good food/atmosphere
  and happy customers, he/she can access the data
  mine (via the Internet) and obtain the
  information that is linked to that very moment,
  and is not created by the owner of the business,
  but by the customers themselves
• Accessing the given restaurants website has two
  drawbacks
• the information is not fresh - periodically
  updated
• the information is made by the owner of the
  restaurant, and therefore not completely objective

74
Conclusion

• Consequently, the proposed approach works much
  better , and represents a qualitative step
  forward in the domain of maximization of
  customer satisfaction
• This may mean that the privacy of the person is
  jeopardized,however, if the monitored behaviour
  is non-personalized, and if the customer obtains
  a discount based on the fact that mobile agents
  are welcome, the privacy stops to be an issue,
  and people will sign up voluntarily

75
Appendix

• A Survey of the Data Mining Algorithms

76
Apriori Algorithm

• The task mining association rules by finding
  large itemsets and translating them to the
  corresponding association rules
• A ? B, or A1 ? A2 ?? Am ? B1 ? B2 ?? Bn, where
  A ? B ?
• The terminology
• Confidence
• Support
• k-itemset a set of k items
• Large itemsets the large itemset A, B
  corresponds to the following rules
  (implications) A ? B and B ? A

77
Apriori Algorithm

• The ? operator definition
• n 1 S2 S1 ? S1 A, B, C ? A, B,
  C AB, AC, BC
• n k Sk1 Sk ? Sk X ? Y X, Y ? Sk, X ?
  Y k-1
• X and Y must have the same number of elements,
  and must have exactly k-1 identical elements
• Every k-element subset of any resulting set
  element (an element is actually a k1 element
  set) has to belong to the original set of
  itemsets

78
Apriori Algorithm

• Example

79
Apriori Algorithm

• Step 1 generate a candidate set of 1-itemsets
  C1
• Every possible 1-element set from the database is
  potentially a large itemset, because we dont
  know the number of its appearances in the
  database in advance (á priori ?)
• The task adds up to identifying (counting) all
  the different elements in the database every
  such element forms a 1-element candidate set
• C1 A, B, C, D, E
• Now, we are going to scan the entire database, to
  count the number of appearances for each one of
  these elements (i.e. one-element sets)

80
Apriori Algorithm

• Now, we are going to scan the entire database, to
  count the number of appearances for each one of
  these elements (i.e. one-element sets)

81
Apriori Algorithm

• Step 2 generate a set of large 1-itemsets L1
• Each element in C1 with support that exceeds some
  adopted minimum support (for example 50) becomes
  a member of L1
• L1 A, B, C,E and we can omit D in
  further steps (if D doesnt have enough support
  alone, there is no way it could satisfy
  requested support in a combination with some
  other element(s))

82
Apriori Algorithm

• Step 3 generate a candidate set of large
  2-itemsets, C2
• C2 L1 ? L1 AB, AC, AE, BC, BE,
  CE
• Count the corresponding appearances
• Step 4 generate a set of large 2-itemsets, L2
• Eliminate the candidates without minimum
  support
• L2 AC, BC, BE, CE

83
Apriori Algorithm

• Step 5 (C3)
• C3 L2 ? L2 BCE
• Why not ABC and ACE because their 2-element
  subsets AB and AE are not the elements of
  large 2-itemset set L2 (calculation is made
  according to the operator ? definition)
• Step 6 (L3)
• L3 BCE, since BCE satisfies the required
  support of 50 (two appearances)
• There can be no further steps in this particular
  case, because L3 ? L3 ?
• Answer L1 ? L2 ? L3

84
Apriori Algorithm

• L1 large 1-itemsets
• for (k2 Lk-1 ? ? k)
• Ck apriori-gen(Lk-1)
• forall transactions t ? D do begin
• Ct subset (Ck, t)
• forall candidates c ? Ct do
• c.count
• end
• Lk c ? Ck c.count ? minsup
• end
• Answer ?k Lk

85
Apriori Algorithm

• Enhancements to the basic algorithm
• Scan-reduction
• The most time consuming operation in Apriori
  algorithm is the database scan it is originally
  performed after each candidate set generation, to
  determine the frequency of each candidate in the
  database
• Scan number reduction counting candidates of
  multiple sizes in one pass
• Rather than counting only candidates of size k in
  the kth pass, we can also calculate the
  candidates Ck1, where Ck1 is generated from
  Ck (instead Lk), using the ? operator

86
Apriori Algorithm

• Compare Ck1 Ck ? Ck Ck1 Lk ? Lk
• Note that Ck1 ? Ck1
• This variation can pay off in later passes, when
  the cost of counting and keeping in memory
  additional Ck1 - Ck1 candidates becomes less
  than the cost of scanning the database
• There has to be enough space in main memory for
  both Ck and Ck1
• Following this idea, we can make further scan
  reduction
• Ck1 is calculated from Ck for k gt 1
• There must be enough memory space for all Cks (k
  gt 1)
• Consequently, only two database scans need to be
  performed (the first to determine L1, and the
  second to determine all the other Lks)

87
Apriori Algorithm

• Abstraction levels
• Higher level associations are stronger (more
  powerful), but also less certain
• A good practice would be adopting different
  thresholds for different abstraction levels
  (higher thresholds for higher levels of
  abstraction)

88
DHP Algorithm

• DHP Direct Hashing and Pruning another
  algorithm for mining association rules
• Based on the Apriori algorithm (Ck/Lk generation
  in the kth step)
• Empirical analysis of the Apriori algorithm shows
  that candidate sets (Ck) are much larger than
  corresponding sets of large itemsets (Lk),
  especially in a first few iterations
• DHP introduces more efficient candidate set
  generation method
• The idea is to insert into Ck only those
  candidate sets that are likely to become large
  itemsets

89
DHP Algorithm

• Additional improvement is accomplished through
  two-dimensional search base reduction
  length(number of records in the search base)
  and width (number of relevant attributes in a
  record)
• Large itemsets characteristics
• Every non-empty subset of a large itemset is a
  large itemset as well, for example, BCD ? L3 ?
  BC, CD, BD ? L2
• It implies that a record is relevant for
  discovering large k1-itemsets only if it
  contains at least k1 large k-itemsets

90
DHP Algorithm

• During the Ck ? Lk phase we might count large
  k-itemsets in each record if their number in a
  particular record is less than k1, we omit that
  record during the Ck1 generation
• Similarly, if a record contains one or more large
  k1-itemsets, each element (item) of these
  itemsets appears in, at least, k candidates from
  Ck
• Hashing
• Hashing boosts the performance of the DHP
  algorithm
• The algorithm does not specify any hash function
  in particular, it depends on the application
• Likewise, it does not specify the size of the
  hash table (number of groups/addresses)

91
DHP Algorithm

• Application example

92
DHP Algorithm

• Step 1 generate a candidate set of 1-itemsets
  C1
• C1 A, B, C, D, E
• Simultaneously with counting each elements
  support, a hash tree is generated that contains
  all the elements from the database, in order to
  improve the counting performance
• For each new element, DHP checks whether the
  element is already in the tree or not
• If yes, DHP increments the current number of
  appearances for that element otherwise, the
  element is added to the hash tree, and the number
  of its appearances is set to 1

93
DHP Algorithm

• Having counted each C1 element appearances, all
  possible 2-element subsets are generated and
  inserted into H2 hash table
• The address of a particular subset could be
  calculated with respect to the position of its
  elements in C1 candidate set, using chosen hash
  function h(x, y)

94
DHP Algorithm

• For example, lets adopt the following hash
  function h(x y) (posC1(x)10 posC1(y))
  mod 7
• The corresponding H2 hash table is shown below

95
DHP Algorithm

• Whenever a new element is added to the hash
  table, the weight of the particular address is
  increased by one
• C2 is generated out of L1 (just like in Apriori
  case)
• Besides that, only those elements that map to the
  addresses whose weight is greater or equal than
  specified minimum support (let the minimum
  support be 50), will be taken into consideration
  during the C2 generation
• C2 AC, BC, BE, CE
• It contains two elements less (!) than the C2 set
  generated by the Apriori algorithm for the same
  example database

96
DHP Algorithm

• In general, the Hk hash table is used for the Ck
  candidate set generation in the kth step of the
  algorithm Hk is created in the previous (k-1)th
  step
• Each address of the Hk hash table contains a
  number of k-element subsets as elements its
  weight denotes the number of elements
• The fact that an address doesnt satisfy minimum
  support requirement means that neither element
  (set) that is mapped to the address can satisfy
  the requirement alone ? all the elements (sets)
  at such Hk addresses are omitted for the Ck
  generation
• During the kth step, Ck is generated starting
  from Lk-1, with the restrictions described above

97
DHP Algorithm

• Conclusions
• DHP outperforms Apriori, for the same input data
• The time spent for the hash tables generation
  (especially H2) is overcome by extremely reduced
  candidate sets (C2, )
• The same improvements applied on Apriori, may as
  well be applied here (scan reduction, abstraction
  levels, )

98
References

• http//www.marconi.com
• http//www.blueyed.com
• http//www.fipa.org
• http//www.rpi.edu
• http//research.microsoft.com
• http//imatch.lcs.mit.edu

99
THE END

• Quatenus nobis denegatum diu vivere, relinquamus
  aliquid, quo nos vixisse testemur

Authors
Voislav Galic, vgalic_at_bitsyu.net
Duan Zecevic, zdusan_at_softhome.net
Ðorde Ðurdevic, madcat_at_tesla.rcub.bg.ac.yu
Veljko Milutinovic, vm_at_etf.bg.ac.yu
http//galeb.etf.bg.ac.yu/vm/tutorial