Blockchain: A Game Changer for Securing IoT Data

Madhusudan Singh Abhiraj Singh Shiho Kim

Yonsei Institute of Convergence Department of Mechanical School of Integrated Technology,
Technology Engineering Yonsei University,
Yonsei University IIT-Roorkee, Seoul, South Korea
Songdo South Korea Roorkee, India

Abstract
very soon, it is going to influence almost every day-to-day items
we use. The more it will be included in our lifestyle, more will be
the threat of it being misused. There is an urgent need to make
IoT devices secure from getting cracked. Very soon IoT is going
to expand the area for the cyber-attacks on homes and businesses
by transforming objects that were used to be offline into online
systems. Existing security technologies are just not enough to deal
with this problem. Blockchain has emerged as the possible
solution for creating more secure IoT systems in the time to
come. In this paper, first an overview of the blockchain
technology and its implementation has been explained; then we
have discussed the infrastructure of IoT which is based on
Blockchain network and at last a model has been provided for the
security of internet of things using blockchain.
Index Terms
Network.

I. INTRODUCTION (HEADING 1)
Blockchain technology is now getting too much of attention
from software scientists since it has been cre- ated. Fig 1 shows
the basic pillars of blockchain technology in internet world.
Actually, it has the ability to revolutionize and optimize the
global infrastructure of the technologies connected with each
other through internet. It has mainly two fields that are going to
be influenced by it which are:
By creating a decentralized system, it removes the
indulgence of central servers and provides peer-to-peer
interaction.
It can create a fully transparent and open to all database,
which could bring transparency to the governance and
elections.
Blockchain technology basically has 4 pillars, first,
Consensus, which provides the proof of work (PoW) and
verifies the action in the networks, second is ledger, which
provides the complete details of transaction within networks.
Third, Cryptography, it makes sure that all data in ledger and
networks gets encrypted and only authorized user can decrypt
the information and fourth is smart contract, it is used to verify
and validate the participants of the network.
IoT is maturing very fast and making its presence felt in
almost every field of technology. However, with its rapid
evolution, it has made itself more prone to cyber-attacks. Now
there is an urgency to make IoT more secure [1].
Fig. 1. Pillars of Blockchain Technology
Internet-Of-Things (IoT) refers to a loosely coupled, a
system of multiple heterogeneous and homogeneous devices
having the power of sensing, processing, and network
capabilities [2]. Internets of Things have been discussed aptly
with semantic touch in the IoT vision [3].The current scenario
for making a safe and secure car is to lock your car
automatically or manually. We become sure of its safety and
security [4]. Our future generation cars would be having all
sensors based devices and at the same time connected in to the
system [5]. The cars with these devices make our car smart but
are they safe? This is the pertinent question which compels us
to write a more safe architecture for making our cars based on
IoT devices safe and secure and connected to the Internet every
time[6].
The purpose of this research paper is to provide guidance
for the use of blockchain technology, through cases to make a
more secure and trustable IoT model.
We proceed further to explain our article in following
section VI section. Section II has describes need of security for
IoT environment, Section III introduce the blockchain
technology, section IV has mentioned the explanation of
Internet of things structure based on blockchain technology. In
section V shows the security strengths of blockchain for IoT
architecture. In Section VI, we have conclude our article.
Published in : IEEE International Symposium on Technologies for Homeland Security (HST)
Woburn, MA, USA : 23-24 Oct. 2018
Machine Learning for Efficient Assessment and
Prediction of Human Performance in Collaborative
Learning Environments
Pravin Chopade, Saad M Khan, David Edwards, and Alina von Davier
Artificial Intelligence and Machine Learning
ACTNext, ACT Inc.
Iowa City, IA, USA
Abstract—The objective of this work is to propose a machine
learning-based methodology system architecture and algorithms
to find patterns of learning, interaction, and relationship and
effective assessment for a complex system involving massive data
that could be obtained from a proposed collaborative learning
environment (CLE). Collaborative learning may take place
between dyads or larger team members to find solutions for real-
time events or problems, and to discuss concepts or interactions
during situational judgment tasks (SJT). Modeling a collaborative,
networked system that involves multimodal data presents many
challenges. This paper focuses on proposing a Machine Learning -
(ML)-based system architecture to promote understanding of the
behaviors, group dynamics, and interactions in the CLE. Our
framework integrates techniques from computational
psychometrics (CP) and deep learning models that include the
utilization of convolutional neural networks (CNNs) for feature
extraction, skill identification, and pattern recognition. Our
framework also identifies the behavioral components at a micro
level, and can help us model behaviors of a group involved in
learning.
Keywords-Machine Learning, Collaborative Learning, Deep
Learning, Computational Psychometrics, Skills, Human Behavior.
I. INTRODUCTION
Collaborative learning methods have been implemented
broadly by organizations at all stages, as research recommends
that active human involvement in cohesive and micro group
communications is critical for effective learning [1]. In current
research, an important line of inquiry focuses on finding accurate
evidence and valid assessment of these micro-level interactions
which supports collaborative learning. Even though there is a
long practice of using mathematical models for modeling human
behavior, Cipresso (2015) [2] introduced a computational
psychometrics-based method for modeling characteristics of real
behavior. Cipresso’s [2] article provides us with a way to extract
dynamic interaction features from multimodal data for modeling
and analyzing actual situations.
In this paper, we propose a three-stage method to explore and
study collaborative group behaviors. The first stage integrates
and processes multimodal data obtained in a collaborative
learning environment (CLE) that includes sensor input, audio,
video, eye tracking, facial expressions, movement, posture,
gestures, and behavioral interaction log data. The second stage
performs feature extraction and cloud computation using
© ACT, Inc. 2018. Licensed to IEEE for publication. All other rights
reserved.
978-1-5386-3443-1/18/$31.00 ©2018 IEEE
computational psychometrics (CP) and convolutional neural
network (CNN)-based deep learning for skill, pattern, and trend
identification. Finally, the third stage uses the parameters
measured in the previous two stages to understand and model
group interactions, competencies, and collaborative behavior at
a micro-level. The third stage uses machine learning for effective
assessment and visualization of group dynamics such as
correctly assessing the increase in the groups’ level of shared
understanding of different perspectives, and ability to clarify
misconceptions.
This paper is an extension of our ongoing work [3], [4] and
here we present details regarding the ML architecture for data-
intensive computing and efficient assessment. Our paper is
organized as follows: in Section II we briefly discuss our related
work on ML for multi-modal human interaction analytics. In
Section III we discuss a three-stage architecture for large-scale
CLE and the layout of the functional components. Based on the
architecture discussed in section III, preliminary
experimentation analysis is discussed in Section IV. In Section
V we discuss scalable applications of our framework for next-
generation collaborative learning and assessment systems, as
well as for the Department of Homeland Security (DHS) and the
Department of Defense (DoD). Section VI concludes with
directions for future work.
II. RELATED WORK
In the past few years, the Artificial Intelligence (AI) and
Machine Learning (ML) communities have been putting their
efforts into presenting and publishing advanced methods for
processing and analyzing human behavior related multi-modal
data. Due to page limitations, it is not possible to cover and cite
all of these works, but we will provide brief highlights regarding
our own work.
In our most recent work, Chopade et al [3], [4], [5], presented
a framework which incorporates computational psychometrics
(CP), Artificial Intelligence (AI), and a Machine Learning (ML)-
based system architecture, methodology, and related algorithms
to find patterns of interactions, learning, team relationships, and
effective teamwork assessment of collaborative problem solving
(CPS) and a collaborative learning environment (CLE).
Khan [6] presented an approach which uses multimodal
telemetry data for two pilot studies from the domains of
2016 IEEE 3rd World Forum on Internet of Things (WF-IoT)
Reston, VA, USA : 12-14 Dec. 2016

Energy Efficient IoT-Based Smart Home

Laila Salman, Safa Salman, Saeed Jahangirian, Mehdi Abraham, Fred German, Charlotte Blair, Peter Krenz
ANSYS Inc.
Canonsburg, PA, USA
Laila.Salman@ANSYS.com, Safa.Salman@ANSYS.com, Saeed.Jahangirian@ANSYS.com, Mehdi.Anraham@ANSYS.com,
Fred.German@ANSYS.com, Charlotte.Blair@ANSYS.com, Peter.Krenz@ANSYS.com

Abstract— Smart Home technology is the future of residential
related technology which is designed to deliver and distribute
number of services inside and outside the house via networked
devices in which all the different applications & the intelligence
behind them are integrated and interconnected. These smart
devices have the potential to share information with each other
given the permanent availability to access the broadband internet
connection. Hence, Smart Home Technology has become part of
IoT (Internet of Things). In this work, a home model is analyzed
to demonstrate an energy efficient IoT based smart home.
Several Multiphysics simulations were carried out focusing on
the kitchen of the home model. A motion sensor with a
surveillance camera was used as part of the home security
system. Coupled with the home light and HVAC control systems,
the smart system can remotely control the lighting and heating or
cooling when an occupant enters or leaves the kitchen.
Index Terms— IoT, Smart Home, Energy Efficient, Multi-band
Antenna, HVAC, LED, Compact Printed Antennas, Thermal
Management, Energy Efficiency.
I. INTRODUCTION
The concept of “automated home/smart home” was first
introduced over 80 years ago, and has been facing different
technical limitations since then. Recently, service providers
and home appliance manufacturers have launched a new
initiative to bring the concept of smart homes to reality [1-3].
This Smart Home initiative allows subscribers to remotely
manage and monitor different home devices from anywhere
via smart phones or over the web with no physical distance
limitations. With the ongoing development of mass-deployed
broadband internet connectivity and wireless technology, the
concept of a Smart Home has become a reality where all
devices are integrated and interconnected via through the
wireless network [4]. These “smart” devices have the potential
to share information with each other given the permanent
availability to access the broadband internet connection.
Hence, the Smart Home Technology has become part of
Internet of Things (IoT), the wireless sharing of information
[5-7].
A new challenge is now present in the design process of a
Smart Home. In today’s world, the Smart Home is not enough
to the environmentally-conscious user, but energy efficiency is
a key. The IoT provides a strong tool that not only connects
wireless communication devices but wireless sensors for
heating/cooling or any needed utility within the house to better
manage energy usage as well as enhance the living experience
in modern homes.
In this work, a house model is analyzed to demonstrate the
comprehensive simulation studies on consumed energy
reduction for lighting as well as home cooling and heating.
Various Multiphysics simulations were carried out on the
kitchen room using ANSYS products [8]. Integration of the
different smart technologies is also studied including
smartwatch communication with home control unit as an
example of customizing the Smart Home for the user-based
experience. Camera/motion sensor were used as part of the
home security system as discussed in Section II and were
coupled with the home light and HVAC control system,
introduced in Section IV, to remotely switch on/off the lights
and turn on/off the heating/cooling system when a person
enters or leaves the room. Finally, the coupling/RF
interference (RFI) between the antennas integrated within the
house’s smart devices within their RF circuitries are
investigated as well in Section III. Signal integrity is examined
to ensure IoT-enabled devices can communicate seamlessly to
execute an energy saving protocol. This protocol turns on the
LED light bulb and an actuator to open the HVAC duct
damper when an occupant enters the kitchen area and gets
sensed by the security/motion sensor/camera. The simulation
strategies addressed in this work can be utilized to create a
virtual smart model of an IoT-enabled smart home and the
fundamental elements. Such computational methodologies can
be extended to other home parts and buildings such as
warehouses, commercial buildings, stadiums, and shopping
malls.
II. IN-HOUSE SMART WIRELESS COMMUNICATION
The IoT relies on wireless communication enabled by
antennas. Depending on antenna placement, communication
can degrade due to obstructions in the antenna path and
multipath signal propagation and fading. Figure 1 shows the
complete model of the simulated smart home as well as the
kitchen room where the different smart devices are populated.
Therefore, it is vital for the integrity of the system to study the
fields generated by the different antennas employed by the
smart devices: triple band energy control unit (900 MHz, 2.45
GHz, 5.8 GHz) [9], security/motion sensor and surveillance
camera (5.8 GHz), LED light bulbs (2.45 GHz), and actuator
of the HVAC duct dampers (900 MHz) [10].

526