Mind reading computers

SSM-S 401 SEMINAR ON-
MIND READING
COMPUTERS
SUBMITTED TO-
Dr. R.N. Katiyar
Seminar In-Charge
SUBMITTED BY-
ANSHU MAURYA
CSJMA13001390005

 INTRODUCTION
 PREVIOUS AND CURRENT RESEARCH OUTCOMES
 HOW DOES IT WORKS?
 TECHNIQUES
 ALGORITHMS AND MODELS
 DATABASES
 ADVANTAGES
 DISADVANTAGES AND PROBLEMS
 CONCLUSION
 REFERENCES

INTRODUCTION
 People express their mental states, including
emotions, thoughts and desires, all the time through
facial expressions and gestures. This is true when
they are interacting with machines.
 Mind reading machine is co-ordination of human
psychology, neuro-science and computer techniques.

 Japanese scientists have discovered that the electrical
activity in our brain is same when a word is spoken or
left unsaid after thinking.
 Scientists have identified distinct brainwaves produced
for different words.
 Prior knowledge of how particular mental states are
expressed in the face is combined with analysis of facial
expressions and head gestures occurring in real time.

 The relationship between observable head and facial
displays and the corresponding hidden mental states
over time is modeled.
 In recent years, scientists have done tremendous jobs in
decoding human thoughts. In a 2011 study, researchers
translated brain waves into the movie clips people were
watching at the time.
 Current projects in Cambridge are considering further
inputs such as body posture and gestures to improve the
results.

HOW DOES IT WORKS?
Futuristic Head Band:
 The mind reading actually involves measuring the
volume and oxygen level of the blood around the
subjects brain, using technology called functional
near-infrared spectroscopy(FNIRS) which has shown
83% times accurate results.
 The user wears a sort of futuristic
headband that sends light rays
into the tissues of the head where
it is absorbed by active,
blood-filled tissues.

1. Facial Affect Detection-
Patterns of face and gestures are
analyzed of a person.
2. Emotional Classification-
Classification by Paul Ekman Anger, Fear, Happiness,
Disgust ,Sadness, Surprise.
3. Facial Electromyography-
It is used to measure the electrical
activity of the facial muscles. Muscles
used are “corrugator supercilii muscle”

4. Galvanic Skin Response-
It is a measure of skin conductivity,
which is dependent on how moist
the skin is.
5. Blood Volume Pulse-
It is measured by a process called
photoplethysmography and it
produces a graph indicating
blood flow through the extremities.

 LDA (Linear Discriminant Analysis)
Used in statistics, pattern recognition and machine learning to
find a linear combination of features. Its time & space computation
is expensive. time complexity=O(mnt+t^3),
m,n are no of samples & features respectively & t=min(m,n).
 k-Nearest Neighbors(k-NN) – Classify an unknown example
with the most common class among k closest examples.
time complexity= O(nk+nd) , where n= no. of examples,
k=closest examples, d= distance to all examples.
 Hidden Markov models(HMM)- used in pattern recognition ,
gesture recognition.
Time complexity = O(T*N^T), where T= length of sequence,
N= no of symbols .

 SVM(Support Vector Machines)– used in statistics and machine
learning to find a linear combination which decides which of the
two (or more) possible classes, each input may fall into.
Its time complexity depends on techniques involved in it.
 ANN(Artificial Neural Networks)-is a mathematical model,
inspired by biological neural networks, that can better grasp
possible non-linearities of the feature space.
Time complexity = between O(n^2) and O(n^3).
 GMM(Gaussian mixture model)- is a probabilistic model used for
representing the existence of sub-populations within the overall
population.
Time complexity = O(kn), where n=no. of data points,
k=final no. of k mixture components.

The first attempt to produce such database was the FAU
Aibo Emotion Corpus for CEICES (Combining Efforts for
Improving Automatic Classification of Emotional User
States)
three types of databases
 database of peak expression images
 database of image sequences of
emotion from neutral to its peak
 video clips with emotional annotations.

 Two widely used databases CK+ and JAFFE.
Extended Cohn-Kanade (CK+)-
CK was created in 2000 but was not much efficient.
CK+ was created after 10 years, in which
no of img. Sequence was increased by 22%
& no of subjects was increased by 27%.
 Japanese Female Facial Expression(JAFFE)-
it contains 213 images of 7 facial expressions of
Japanese models.

ADVANTAGES
 Mind-controlled wheelchair- was developed from the
University of Electro Communications in Japan.
 Web Search- Search engines can detect
what the user wants to browse.
 e-learning applications- when a learner is bored,
interested, frustrated, or pleased.
 Robotic systems capable of processing information from
our minds

 Social monitoring- such as alerting other vehicles if it
detects the driver to be angry.
 Physical Disability- Affective
computing is also being applied
to the development of communicative
technologies for use by people
with autism.
 military purposes, sting operations and severe
investigations (as in the form of lie detector).
 combined with consoles and used for mind gaming.

 Marketing- One idea, put forth by the Romanian
researcher Dr. Nicu Sebe , is the analysis of a person’s
face while they are using a certain product .
 help injured astronauts control machines, or aid
disabled people.

DISADVANTAGES AND PROBLEMS
It can become a threat in privacy and can extract
important and confidential information through the
person.
Also these mind reading computers cannot be 100%
accurate as human mind is much more complex than a
computer.
 If used by Sinners , can be highly dangerous.

CONCLUSION
 Tufts University researchers have begun a three-year
research project which, if successful, will allow
computers to respond to the brain activity of the
computer's user.
 Hence if we get 100% accuracy these computers may
find various applications in many fields of electronics
where we have very less time to react.
 Due to lack of database and complexity in neuroscience
a lot of more research is required in this field.

References-
• www.newscientist.com/article/dn4795-nasa-develops-
mindreading-system
• www.wikipedia.org
• ieeexplore.ieee.org
• Hudlicka, Eva (2003). "To feel or not to feel: The role of
affect in human-computer interaction". International
Journal of Human-Computer Studies
• Cambria, Erik (2016). "Affective computing and
sentiment analysis" (PDF). IEEE Intelligent Systems.

Mind reading computers

More Related Content

What's hot (20)

Viewers also liked (11)

Similar to Mind reading computers (18)

Recently uploaded (20)

Mind reading computers