At the first Spark Summit Europe, a presentation by
Intel researchers in cooperation with the Michael J. Fox
Foundation proposed that Big Data could be the key to
unlocking the mysteries of Parkinson’s disease. Summit Europe is the premier
event bringing together the community known as Apache Spark, a fast and general
Open Source engine for big data processing, with built-in modules for
streaming, SQL, machine learning and graph processing.
Summit attendees convened
from Tuesday, Oct. 27, through Thursday, Oct. 29, meeting in celebrated
Dutch architect Berlages magnum opus Beurs Van Berlage in Amsterdam. They heard
from leading production users of Spark, Spark SQL, Spark Streaming and related
projects, discovered where project development is going, and learned how
to use the Spark stack in a variety of applications.
Big Data analytics’ architect and
development manager Ido Karavany, with
Intel’s Advanced
Analytics group, addressed the Summit on leading edge
technology projects within Intel involving Big Data & Stream analytic
solutions in the Internet of Things (IoT) and in Parkinson disease (PD)
research. Mr. Karavany has more than eight years of experience in software
development in the domains of data analytics and distributed computing
solutions.
In his Oct. 28 presentation
entitled “Using Spark in an IoT Analytics Platform Enable breakthroughs in
Parkinson Disease Research,” Mr. Karavney presented a partnership-developed
approach that may enable breakthroughs in Parkinson’s disease
research by leveraging wearable sensors, smartphones and big data analytics to
monitor PD patients’ motor movements 24/7.
He explained that the research
team has built an IoT Big Analytics platform (on Amazon Cloud Drive) based on
open source technologies, such as Cloudera Distribution for Hadoop, to enable
collection and processing of high data streams (up to 1 GB per patient per
day). Mr. Karavney noted that the platform has been successfully used in
multiple clinical trials and the project has started ramping up to connect thousands
of patients 24/7 by the end of 2015.
The platform uses HBase &
HDFS as its main scalable storage layer. The analytics batch layer leverages
Apache Spark (over HBase & HDFS) and includes a set of complex machine
learning algorithms, sophisticated event-based rule engine, an automatic change
detection engine and a variety of PD-related measurements.
Examples for those are activity
recognition, patients’ sleep quality, tremor detection, PD gait recognition,
and others. Mr. Karavney’s presentation included an explanation of the way
researchers are using Spark for implementing their machine learning algorithms.
“We’ll focus on our challenges
using Spark, starting with data extracting from HBase challenges and solutions
for our batch and near-real time calculations, [and] we’ll also review our
solution evolution and will show what worked and didn’t work for us (i.e. Many
small jobs vs. fewer consolidated larger jobs, multiple vs. single Spark
contexts),” Mr.Karavney said.
You can view and download the
slideshow from Mr. Karavney’s presentation here.
A YouTube video of the
presentation also can be viewed
here.
Parkinson’s disease (PD) is a
chronic, progressive, degenerative neurological disorder of poorly understood
cause, in which the nerve cells that produce the natural brain chemical
dopamine are damaged and unable to produce enough of the biochemical agent. The
resulting diminished dopamine levels cause a variety of problems associated
with movement, including tremors (shaking), stiffness, and slowness of
movement. There is currently no known cure for Parkinson’s.
“Nearly 200 years after
Parkinson’s disease was first described by Dr. James Parkinson in 1817, we are
still subjectively measuring Parkinson’s disease largely the same way doctors
did then,” Michael J. Fox
Foundation CEO Todd Sherer, PhD told Special Guest Correspondent
Chrissie Cluney reporting for
IoT Evolution News. “Data science and wearable computing hold the
potential to transform our ability to capture and objectively measure patients
actual experience of disease, with unprecedented implications for Parkinson’s
drug development, diagnosis and treatment.”
| Diane M. Bryant, Senior Vice President and General Manager of the Intel Data Center Group |
The variability in Parkinson’s
symptoms creates unique challenges in monitoring progression of the disease,” Diane M. Bryant,
Senior Vice President and General Manager of the Intel Data Center Group, told
Ms. Cluney. “Emerging technologies can not only create a new paradigm for
measurement of Parkinson’s, but as more data is made available to the medical
community, it may also point to currently unidentified features of the disease
that could lead to new areas of research.”
Ms. Bryant leads the worldwide
organization that develops the data center platforms for the digital services
economy, generating more than $14 billion in revenue in 2014. In her current
role, she is building the foundation for continued growth by driving new
products and technologies from high-end co-processors for supercomputers to
high-density systems for the cloud, to solutions for big data analytics.
Sources:
Spark Summit Europe
Intel
Michael J. Fox Foundation
http://parkinsonsnewstoday.com/2015/11/16/might-parkinsons-unlocked-via-big-data-internet-things/
No comments:
Post a Comment