“In some scenarios, such as nature
scenes, people didn’t mind if the trees
were a little different or the giraffe was a dif-
ferent giraffe; they cared more about them
not being blurry, which means traditional
computer compression ranked lower,”
says researcher Shubham Chandak. “But
for human faces, people would rather have
the same face even if it’s blurry.”
This apparent weakness in human-
based image sharing would improve as
more people upload images of themselves
to the internet. The researchers are also
teaming with a police sketch artist to see
how his expertise might make a difference.
Even though this work shows the value of
human input, the researchers would even-
tually try to automate the process.
“Machine learning is working on bits and
parts of this, and hopefully we can get them
working together soon,” says researcher
Kedar Tatwawadir. “It seems like a practical
compressor that works with this kind of
ideology is not very far away.”
NewsIDENTIFYING CANCER CELL TYPES in a Hurry
FOR DOCTORS TO determine the best
treatment for cancer patients, they must
know what types of cancer cells they are
dealing with, which is not an easy task.
Even within the same tumor, for example,
cancer cells can differ in their genetics,
behavior, and susceptibility to chemother-
apy drugs.
Cancer cells are generally much more
metabolically active than healthy cells, sosome insight into a cancer cell’s behavior
and type can be gathered by analyzing
its metabolic activity. But getting an ac-
curate assessment of metabolic activity
has proven difficult. Several methods, in-
cluding position emission tomography (or
PET) scans, fluorescent dyes, and con-
trast agents have been used, but each is
limited it is usefulness.
According to a medical and electrical
engineering professor at Caltech, Lihong
Wang, photoacoustic microscopy (PAM)
would help in identifying cancer cells. It
uses a laser to induce ultrasonic vibra-
tions in samples. Those vibrations can
image cells, blood vessels, and tissues.
Wang is using PAM to improve an existing
technology for measuring cells’ oxygen-
consumption rate (OCR).
OCR takes many cancer cells, each in
a container filled with blood. Cells with
higher metabolisms use up more oxygen22
Drive Your Assembly Process Forward;
Without Missing A Beat!Along with all the smart features you’ve come to expect,
Visumatic now offers a chance to jump way ahead of the game with
this streamlined combination of rapid deployment technology.
Simple to support and maintain, the VCM-3X.2 collaborative
robot fastening system comes bundled with the latest and greatest,
including pre-programmed fault recovery logic.INTERESTED? VIEW THE VIDEO.... .>
Smarter Machines:
Creatively Engineered for Smart CustomersVISUMATIC.COM • 859.255.79071
st INTRODUCING
VISUMATIC’S
NEW COBOT
FASTENING
SYSTEMMAY 2019 MACHINE DESIGN