Beruflich Dokumente
Kultur Dokumente
• Introduction
• Importance of AI and its Trend
• What is AI and ML
• ML applications in CEM
• Augmented Reality
• Robotics
• Robotics Process Automation
• Knowledge Based System
• Digital Twins
• How to get Started
Introduction
• Alan Turing suggested in 1950 that computers can be trained to think
and perform like humans.
• 1955 – The term AI is coined by John McCarthy – The science and
engineering of making intelligent machines.
• Up until 1990s, very little development – AI Winter.
• Rebirth of AI (1990s- Now)
• New formulations in Bayesian probability, Markov models, information theory,
stochastic modeling, and optimization brought a wealth of new tricks to the
trade.
• Advancements in microprocessors, computers, data storage, and data transfer
have addressed earlier concerns about speed, computational cost, and
information requirements.
AI demand - 2018
AI demand - 2019
Machine Learning
What's AI?
Artificial Intelligence can be defined as any code, technique or
algorithm which enables a machine to mimic human cognitive
processes.
* Arthur Lee Samuel - American pioneer in the field of computer gaming and artificial intelligence.
The Samuel Checkers-playing Program was among the world's first successful self-learning programs, and as such a
very early demonstration of the fundamental concept of artificial intelligence.
Machine Learning
How does it learn without being programmed?
DATA – Huge amounts of data. (Big Data Analytics)
The machines are fed huge amounts of data, that helps the
defined set of algorithms in training themselves to perform a task
automatically.
Supervised –
In supervised learning the algorithm learns from a training data
set.
The data scientist functions as the “teacher”, who guides the
algorithm towards achieving the desired conclusions.
Unsupervised –
All data is unlabelled and the algorithms learn by themselves, the
output is not defined by the data scientist.
Machine Learning
• Supervised Learning
Features of an apple
and a cupcake are
explained to the
algorithm
Examples -
Whether India will WIN or LOSE a Cricket match? Whether an email is SPAM or GENUINE?
WIN, LOSE, SPAM, GENUINE are the predefined classes. And output has to fall among these
depending on the input.
Machine Learning
• Unsupervised Learning
I can see a
pattern
To sum it up -
Cost estimation model for predicting construction costs taking into account economic variables
and indices
Algorithms used: Unsupervised Deep Boltzmann Machine (DBM) learning model, with softmax
layer and SVM
Results obtained by this model were compared to BPNN only models and SVM models.
Journal of Computing in Civil Engineering, ASCE, Publication – April 18, 2020
Journal of Computing in Civil Engineering, ASCE, Publication – December 21, 2019
Augmented Reality
• Augmented reality and artificial
intelligence are distinct
technologies, but they can be used
together to create unique
experiences.
• In augmented reality, a 3D
representation of the world must be
constructed to allow digital objects
to exist alongside physical ones.
• Deep neural networks can detect
vertical and horizontal planes,
estimate depth and segment images
for realistic occlusion, and even
infer 3D positions of objects in real-
time.
Augmented Reality in Use
Physical Robotics
• Rover on top of the Dozer
tracks the NEZ coordinates in
real time with Satellite via GPS.
• Elsevier
• Automation in Construction
Data Sets
• Biggest Drawback in to solve Civil Engineering Problems
• Not many datasets are available on dataset websites
• You have to create your own datasets – Images, Videos, Estimation
project costs, schedules.
• Another Problem – Algorithms need labelled datasets in Millions to
learn.
Computing Power
Recommended -
• Processor – Intel Xeon E2630 v4 – 10 core processor, 2.2 GHz with Turbo boost
up to 3.1 GHz. 25 MB Cache
• RAM – 128 GB DDR4 2133 MHz
• 2 TB Hard Disk (7200 RPM) + 512 GB SSD
• GPU – NVidia TitanX Pascal (12 GB VRAM) (Around Rs. 2 Lakhs)
• Push your limits to understand the MATH behind the Algorithms and
connect it to Civil Engineering.