Video recording of the Dr. Khaled's session can be found at https://youtu.be/TFNhvAXNU5E.
The presentation explores how Artificial Intelligence (AI) can be used in the Project Management field. The origins and history of AI are discussed followed by a brief simplified explanation of the theories behind its application. The actual utilization of AI tools in the Project Management domain is discussed covering diverse areas such as Engineering Design, Cost Estimating and Bidding, Planning and Scheduling, Risk Management, Performance Prediction as well as Project Monitoring and Control. The presentation concludes by a brief discussion about Data Management and Knowledge Engineering and how they are used today to simplify (or complicate) our lives.
7. Contents
• What is Artificial Intelligence?
• Definition
• DifferentTypes of Artificial Intelligence
• History of Artificial Intelligence
• Theories behind Artificial Intelligence
• Artificial Intelligence in Project Management
• Engineering Design
• Cost Estimation and Bidding
• Planning and Scheduling
• Risk Management
• Prediction of Project Performance
• Data Mining and Knowledge Engineering
8. Definition of AI
• AI is a machine’s ability to:
• Perceive
• Reason
• Learn
• Act
Sensors (Perceive)
Environment
Perceptions
Actions
Effectors (Act)
Reason & Learn
9. Another Definition of AI
• AI is the ability of a computer (or a
machine) to perform certain tasks thought
to require intelligence including:
• Logical deduction and inference
• Learning and adaptation
• Ability to make decisions based on:
• Past Experience
• Insufficient Information
• Conflicting Information
• Ability to understand spoken/natural language
10.
11. Different Types of AI
AI
Cognitive
Science
Robotics
Natural
Interface
• Expert Systems
• Learning Systems
• Fuzzy Logic
• Genetic Algorithms
• Neural Networks
• IntelligentAgents
• Visual Perception
• Tactility
• Dexterity
• Locomotion
• Navigation
• Natural Languages
• Speech Recognition
• Virtual Reality
• Multisensory Interfaces
12. History of AI
• A branch of Computer Science
• Around for Decades
• Term first created in 1956
• One of the definitive references
on AI (still used today) was LAST
published in 1992
• Still used as a text book at MIT
13. ALVINN learns to Drive in 1989
Computer
100 Million FLOPS (Floating-Point Operations per second)
1/10 Computing Power of the AppleWatch
15. Reasons for AI Prominence
2. Exceptional (Exponential) Growth in
Computing Power 1980’s – 3 CRAY
Supercomputers
2017 – iPhone 7
More Powerful than
80’s CRAYS
19. Artificial Intelligence -
The Science behind the Magic
• Algorithms that tell computers and other
machines how to think and act intelligently
• Many tools and techniques including:
• Knowledge Based Expert System
• Artificial Neural Network
• GeneticAlgorithm
• Fuzzy Logic
20. Knowledge Based Expert System
(KBES)
• Consist of a Knowledge Base and Inference Engine
• The knowledge base is created by collecting the facts
and opinions from Subject Matter Experts
• The Inference Engine utilizes IF-THEN statements to
provide expertise
21. Artificial Neural Network (ANN)
• A machine learning approach that
models the human brain and consists
of a number of artificial neurons
linked by weighted connections
• ANNs demonstrate the ability to
learn, recall, and generalize from
training patterns or data (numeric,
non-numeric or both).
22. Artificial Neural Network (ANN)
Input
Layer
Hidden
Layer (s)
Output
Layer
Inputs
Numeric or
Non-Numeric
Outputs
Numeric or
Non-Numeric
Neuron
Neuron
Connections
Connections
24. Genetic Algorithms (GA)
• Iterative search methods that mimic the natural
biological evolution process and/or the social
behavior of species.
• GAs utilize the natural evolution processes of
selection, mutation and cross-over to arrive at
near-optimum solutions to large-scale
optimization problems, for which traditional
mathematical search techniques may fail.
26. Fuzzy Logic
• Fuzzy logic is an approach to computing based on
"degrees of truth" rather than the usual "true or
false" (1 or 0) Boolean logic on which the modern
computer is based
• A form of many-valued logic in which the truth
values of variables may be any real number
between 0 and 1
27. Fuzzy vs Boolean Logic
Boolean Logic
Not
Tall (0)
150 cm
Tall (1)
180 cm
Fuzzy Logic
Not very
Tall (0.2)
150 cm
Definitely
Tall (0.9)
180 cm
28. Contents
• What is Artificial Intelligence?
• Artificial Intelligence in Project Management
• Data Mining and Knowledge Engineering
29. AI in Engineering Design
• ANN to select the most suitable
structural system for High Rise Buildings
subjected to wind and seismic loads
• GA to optimize the LCC of Buildings
in hot climates using different
combinations of location, orientation
and construction materials
30. AI in Project Planning
• KBES to provide estimates of the duration and
resource requirements for project activities based on
expert knowledge
• ANN to automate the sequencing of project
activities based on functional requirements.
• GA to optimize the schedule of
construction project activities in order to
minimize the total cost with resource
constraints
• Fuzzy Logic to determine project
priorities in the Portfolio Management
Process
31. AI in Cost Estimation
• ANN to estimate the suitable mark-up to increase
the possibility of winning tenders
• ANN to predict the possible cost over-runs based
on the selected contractor, the competence of the
project manager, the project size and the type of
contract used
• Fuzzy Logic to optimize the cost-time trade-offs in
construction projects
32. AI in Risk Management
• ANN to estimate the probability of occurrence for
project risks allowing a more accurate quantitative
approach to risk analysis.
• ANN combined with Monte Carlo Simulation to
mimic the human procedure of risk evaluation
and adaptation
• Fuzzy Logic to assess risks in Construction
projects to model probability distributions
33. AI in Performance Management
• ANN to predict the performance of future projects
based on the project parameters such as the Project
Manager’sCompetence, the Contractor’s ability and
the contracting method used.
• KBES to assess claims and provide
expert decisions based on the claim
conditions
• Fuzzy Logic to improve Project
Management Efficiency in
Construction Projects
34. AI in PM
AITools Design Planning
Cost
Estimation
Risk
Management
Performance
Management
KBES
ANN
GA
Fuzzy
Logic
35. AI in PM
• AI can be and has been used in
several applications in Project
Management enabling better
project performance
• AI can make the life of project
managers less (or maybe more)
miserable
36. Contents
• What is Artificial Intelligence?
• Artificial Intelligence in Project Management
• Data Mining and Knowledge Engineering
37. Data Mining &
Knowledge Engineering
• Sources of Data:
• Machine Data
• Organizations Data
• People Data
• Data-Information-Knowledge-Wisdom
43. People Data
• Sources:
• Facebook
• Twitter
• Instagram
• YouTube
20,000 Years
The time people
spend on Facebook
everyday
342,239 Years Of Video is
watched every
month on
YouTube
44. People Data
• Characteristics:
• Un-Structured (80% ofWorld Data)
• Fragmented
• Variability
• HUGE
How Huge
is HUGE?
30+ PB vs 2 PB
48. Data Mining in Project
Management
• Knowledge Discovery in Data (KDD) used to
extract useful knowledge from large sets of
resources data to improve resource
management practices
• Data Mining used to improve Project Cost
Estimation and Scheduling for Software
Projects