nisis malta nov. 07 perceptive swarms, data and computable habitats: swarm intelligence in...

60
NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST, Evolutionary Systems and Biomedical Engineering Lab., Technical University of Lisbon, IST, Lisbon, PORTUGAL http://www.laseeb.org/vramos/ Perceptive Swarms, Data and Computable Habitats:

Upload: mervin-hill

Post on 20-Jan-2016

218 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

NiSIS Malta Nov. 07

PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS:

Swarm Intelligence in Clustering and Pattern Recognition

Vitorino RamosLaSEEB-IST, Evolutionary Systems and Biomedical Engineering Lab.,

Technical University of Lisbon, IST, Lisbon, PORTUGAL http://www.laseeb.org/vramos/

Perceptive Swarms, Data and Computable Habitats:

Page 2: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

What is Swarm Intelligence?

Swarm Intelligence (SI) is the property of a system whereby the collective behaviours of (unsophisticated) entities interacting locally with their environment cause coherent functional global patterns to emerge.

SI provides a basis with which it is possible to explore collective (or distributed) problem solving without centralized control or the provision of a global model.

To tackle the formation of a coherent social collective intelligence from individual behaviours, several bio-inspired concepts related to Self-Organization, Stigmergy and Social Foraging in animals are normally used.

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 3: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Stigmergy:

An example could be provided by two individuals, who interact indirectly when one of them modifies the environment and the other responds to the new environment at a later time. In other words, stigmergy could be defined as a typical case of environmental synergy.

Grassé showed that the coordination and regulation of building activities do not depend on the workers themselves but are mainly achieved by the nest structure: a stimulating configuration triggers the response of a termite worker, transforming the configuration into another configuration that may trigger in turn another (possibly different) action performed by the same termite or any other worker in the colony.

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 4: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

AB

La VallettaSt. Julians

A kind of Environmental SynergyA Collective geographic Memory

Old Trails are used as memory, while the new ones are used for innovation, adaptation and for the construction of new feasible solutions.

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 5: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Example - Swarms of social insects construct trails and networks of regular traffic via a process of pheromone (a chemical substance) laying and following. These patterns constitute what is known in brain science as a cognitive map. The main differences lies in the fact that insects write their spatial memories in the environment, while the mammalian cognitive map lies inside the brain.

Forming a Cognitive Map

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 6: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Natures trick: To combine signal reinforcement with its simultaneous evaporation

Nest

2

1

nest

food Foraging area

Foraging area

Nest

12

.5 c

m

4 mn 8 mn

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 7: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

source 1

source 2

source 3

nest

a b

c d

Memory and Robustness through Reinforcement Innovation through Evaporation

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Natures trick: To combine signal reinforcement with its simultaneous evaporation

Page 8: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

3. Trail forming model

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 9: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Chialvo & Millonas model:

- Is the simplest (local, memoryless, homogeneous and isotropic) model which leads to trail forming that we could find in the litterature, and the formation of trails and networks of ant traffic is not imposed by any special boundary conditions, lattice topology, or additional behavioral rules.

- Its assumed that each organism emits pheromone at a given rate, and there is no spatial diffusion. Also global pheromone evaporates after all ants have moved at a given rate.

- The ants are not allowed to have any memory and the individual’s spatial knowledge is restricted to local information about the pheromone density.

- The pheromonal field (Cognitive map) contains information about past movements and decisions of the organisms, but not arbitrarily far in the past since the field “forgets” its distant history due to evaporation in time.

- Toroidal boundary conditions are imposed on the lattice to remove, as far as possible, any boundary effects.

- Nonlinear response or directional bias are introduced in order to form trails, or to persist on past trails that are already formed.

3. Trail forming model

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 10: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Transition rule between cells by use ofa pheromone weighting function:

11W

Measures the relative probabilities ofmoving to cell r with pheromone density, r

This parameter is associated with theosmotropotaxic sensitivity. Controls thedegree of randomness with which the antfollows the gradient of pheromone.

For low values the pheromone concentrationdoes not greatly affect its choice, while highvalues cause it to follow pheromone gradientwith more certainty.

1

can be seen as the sensorycapacity. This parameter describes the fact that the ant’sability to sense pheromone athigh concentrations.

Chialvo & Millonas model:

3. Trail forming model

Perceptive Swarms, Data and Computable Habitats:

Page 11: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Normalised Transition probabilitieson the lattice to go from cell k to cell i:

kj jj

iiik wW

wWP

Measures the magnitude of thedifference in orientation:

w (0) = 1w (1) = 1/2w (2) = 1/4w (3) = 1/12w (4) = 1/20

Measures the relative probabilities ofmoving to cell i with pheromone density, i

e.g.: Coming from North

w = 1/12

w = 1/4

w = 1/2w = 1/2

w = 1/20

w = 1

w = 1/4

w = 1/12

4 3

2

1

3

2

01

Indicates the sum over all the cells jwhich are in local neighbourhood of k.

Chialvo & Millonas model:

3. Trail forming model

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 12: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Coming from North

w = 1/12

w = 1/4

w = 1/2w = 1/2

w = 1/20

w = 1

w = 1/4

w = 1/12

Coming from SouthWest

w = 1

w = 1/2

w = 1/4w = 1/20

w = 1/2

w = 1/12

w = 1/12

w = 1/4

Coming from NorthEast

w = 1/20

w = 1/12

w = 1/4w = 1

w = 1/12

w = 1/2

w = 1/2

w = 1/4

Coming from East

w = 1/12

w = 1/20

w = 1/12w = 1/2

w = 1/4

w = 1/4

w = 1

w = 1/2

E

N

S

WDirectional Bias (w) needed to computeNormalised Transition Probabilities on greylevel 8 x 8 windows (some Examples):

Chialvo & Millonas model:

3. Trail forming model

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 13: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

“Deciding where to go” by Roulette Wheel selection:

11W

kj jj

iiik wW

wWP

w = 1

w = 1/2

w = 1/4w = 1/20

w = 1/2

w = 1/12

w = 1/4

w = 1/12

= 1

SW S SE W E NW N NE

Chialvo & Millonas model:

3. Trail forming model

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 14: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Results:

2.0

5.3

015.0

07.0

%30307

3232

k

LatticeNants

cellsxLattice

Parameters used:

Pheromone deposition rate

Pheromone evaporation rate

Osmotropotaxic sensitivity

Inverse of sensory capacity

Chialvo & Millonas model:

3. Trail forming model

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 15: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

4. Emerged Collective Perception

One big CROSS or to manylittle SQUARES ?!

Question: Can we solve this without a priori knowledge ?!

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 16: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Extended modelto grey level habitats

-Instead of constant pheromone deposition rate, a term not constant is included:

cmpT

Pheromone deposition ratefor a specific ant at a

specific cell

Chialvo & MillonasPheromone deposition rate

(constant)

Gives a measure of similaritybetween two different lattice

windows, in terms of grey levelspatial arrangement;

0 <= Dcm <= 1(Matching Properties)

Constant

1st Extension

4. Emerged Collective Perception

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 17: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Extended modelto grey level habitats

-Pheromone deposition rate for a specific ant at a specific cell depends on grey level matching properties between 2 window lattices:

2nd Extension

Ant comes from Center and goes to NE:

??

MAXS

S

MAXmmMAX

mmcm

22

21

22

21

21

21

4. Emerged Collective Perception

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 18: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Extended modelto grey level habitats

This measures differences ongrey level overall intensity

This measures differences onwindows grey level homogeneity This measures successful matching

properties between windows evenconsidering all permutations;

S equals the difference between thefrequency of each class, for 2

grey level histograms (representing the2 windows); Smax = 18.

cbaS

Sc

MAXb

mmMAX

mmacm

MAX

22

21

22

21

21

21

n

nggn

iwi

9

1

22

2

.

= 1

255

0

i

iii ffS

Max. variance differenceis 126.711on 3x3 windows

using 8 bit images

Max. average difference is 255using 8 bit images

4. Emerged Collective Perception

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 19: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

4. Emerged Collective Perception

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 20: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

4. Emerged Collective Perception

Figure - Colony cognitive maps (pheromonal fields) for several iterations, on images Cross, Einstein, Map, Marble and Road. Except when indicated, parameters are those from [1]. In A2 and Z, ants are allowed to step on each other; habitats are respectively Cross and an homogeneous image. In this last case, results are similar with those found by Chialvo and Millonas [1]. A3) k=0.011. A4) k=0.019. A5) =4.5. A6) =2.5.

A-Cross B-Einstein C-Map D-Marble E-Road

t=1 t=1 t=1 t=30 t=30

t=10 t=10 t=10 t=1000 t=1000

t=50 t=50 t=50 A2 / t=1000 A3/ t=1000

t=1000 t=1000 t=1000 A4/ t=1000 A5/ t=1000

t=3000 t=3000 t=3000 A6/ t=1000 Z / t=1000

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 21: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

= + +

= + +

Ant_System_2D applied for 200 iterations (OUTPUT= Pheromone Distribution)

Negative Colour Image

Channel Combining(Mono to RGB)

Channel Splitting(RGB to Mono)

R G B

R G B

Page 22: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Original Colour Image

Pheromone Distribution in Colour (after 200 iterations), the respective R,G and B channels, and the colour negative.

Page 23: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Adaptation and emerged perception between two imagesusing self-organized swarms

4. Emerged Collective Perception

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 24: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

4. Emerged Collective Perception

B-Einstein t=1 t=100 t=110 t=120

t=130 t=150 t=200 t=300 t=400

t=500 t=800 t=900 t=1000 C-Map

Figure - One swarm (3000 ants) is thrown to explore Einstein image for 1000 iterations. At t=100, the Einstein habitat is replaced by Map image. Evolution of swarm cognitive maps (pheromonal fields) are shown for several iterations.

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 25: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Fig. - Emerging pheromone maps in dynamic landscapes. The self-regulated swarm starts to evolve over "Einstein" image. After 100 iterations, the image changes to "Map".

Adaptation and emerged perception between two images using self-organized swarms

4. Emerged Collective Perception

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 26: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

5. MM Watershed vs. Swarm Image Perception

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 27: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Fig. - Emerging pheromone maps in dynamic landscapes. The self-regulated swarm starts to evolve over "Einstein" image. After 100 iterations, the image changes to "Map".

Emerging Perception and Adaptation between two different images

Watershed Watershed+SVPSWatershed+SFPS

Watershed Watershed+SVPSWatershed+SFPS

5

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 28: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

6. Swarm Intelligence based Gastric bypass Video Segmentation

Figure. Typical film image: the stomach, the duodenum and the bypassed intestine are visible.

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 29: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

6. Swarm Intelligence based Gastric bypass Video Segmentation

Figure. Swarm Intelligence based (last column) versus Classical Mathematical Morphology Watershed based (second column) frame segmentation. 1st column) Original images (frame 100 up, and 220 down), 2nd column) Watershed segmentation, 3rd column) Pheromone distribution after applying the present proposal, and 4th column) final results after processing images on the 3rd column.

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 30: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

7. Optimization

In here, this additional term should naturally be related with specific characteristics of cells around one ant, like their altitude (z value or function value at coordinates x,y), having in mind our present aim.

So, our pheromone deposition rate T, for a specific ant, at one specific cell i (at time t), should change to a dynamic value (p is a constant = 1.93) expressed by equation 3.

In this equation, Δmax = | zmax – zmin |, being zmax the maximum altitude found by the colony so far on the function habitat, and zmin the lowest altitude.

The other term Δ[i] is equivalent to (if our aim is to minimize any given landscape): Δ[i] = | zi – zmax |, being zi the current altitude of one ant at cell i. If on the contrary, our aim is to maximize any given dynamic landscape, then we should instead use Δ[i] = | zi – zmin |.

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 31: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Application to Optimization Problems

Ants are randomly placed on the landscape/function.

All ants move on each time step: the direction is chosen according to the pheromone levels around the ant and it is constrained by a directional bias.

Environment is NxN toroidal grid with different values according to a function.

Each time step, all ants deposit a certain amount of pheromone that is proportional to the value of the function on that site.

t = 0 t=1000 t = 50 t = 100 t = 500

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 32: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

7. Optimization

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 33: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

7. Optimization

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 34: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

7. Optimization

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 35: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Fig.- A self-organized swarm emerging a characteristic flocking migration behaviour between one deep valley (South region) and one peak (North region), surpassing in intermediate steps (Mickey Mouse shape) some local optima. Over each foraging step, the population self-regulates.

7. Optimization

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 36: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Mediumvalleys

Highestpeak

Mediumvalley

Lowestvalley

MediumpeakMedium

peaks

Mediumvalley

Targets change:

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 37: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

8. Bacterial foraging (BFOA) vs. Self-Regulated Swarms (SRS)

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 38: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

9. Dynamic Optimization

When facing dynamic optimization problems the goal is no longer to find the extrema, but to track their progression through the space as closely as possible.

Over these kind of over changing, complex and ubiquitous real-world problems, the explorative-exploitive subtle counterbalance character of our current state-of-the-art search algorithms should be biased towards an increased explorative behavior.

While counterproductive in classic problems, the main and obvious reason of using it in severe dynamic problems is simple: while we engage ourselves in exploiting the extrema, the extrema moves elsewhere

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 39: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

9. Dynamic Optimization

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 40: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Figure - (LEFT) A 3D toroidal changing landscape describing a Dynamic Optimization (DO) Control Problem (8 frames in total). (RIGTH) A self- organized swarm emerging a characteristic flocking migration behaviour surpassing in intermediate steps some local optima over the 3D toroidal landscape above, describing a Dynamic Optimization (DO) Control Problem. Over each foraging step, the swarm self-regulates his population and keeps tracking the extrema (44 frames in total).

9. Dynamic Optimization

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 41: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

9. Dynamic Optimization

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 42: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

9. Dynamic Optimization

Page 43: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

9. Dynamic Optimization: Population Size

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 44: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

9. Dynamic Optimization: Mean altitude

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 45: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

11. Binary Ant Algorithm (BAA)

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 46: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

11. Binary Ant Algorithm (BAA)

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 47: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

12. Other Applications

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 48: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Clustering and Classification 6

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 49: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Results withint = 1E6 time steps

t = 1, Etotal = 2.910 t = 50,000, Etotal = 1.264

t = 10,000, Etotal = 1.744 t = 75,000, Etotal = 1.182

t = 20,000, Etotal = 1.513 t = 1E6, Etotal = 0.906

FEATURES in 2D

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Clustering and Classification

Page 50: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

t = 1E6, Etotal = 0.906

FINAL RESULT:

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Clustering and Classification

Page 51: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Results:

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Clustering and Classification

Page 52: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

RESULTS: Latent semantic analysis and document filtering: preliminary results on newspapers (with JJ Merelo, 2002)

The present work uses LSA as a feature extraction method, in order to map 931 words of an article at a Spanish newspaper. In the LSA model [6, 13], terms and documents are represented by an m x n incidence matrix A. Each of the ni unique terms in the document

collection are assigned a row in the matrix, while each document is assigned a column. SVD is applied to the resulting matrix, and the main "axes" are them obtained. Words are projected onto those axes, resulting similar vector values for words with a similar meaning.

Thus, each word uses a 50 feature vector. Since we had 931 items (words) to self-organize by the swarm, 91 ants were used, on a 61 x 61 non-parametric toroidal grid. Figure 5 shows the final result at t=106.

Clustering for text Mining

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 53: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

(A) anunció, bilbao, embargo, titulos, entre, hacer, necesídad, tras, vida, lider, cualquier, derechos, medida.(B) dirigentes, prensa, ciu. (C) discos, amigos, grandes. (D) hechos, piloto, miedo, tipo, cd, informes. (E) dificil, gobierno, justicia, crisis, voluntad, creó, elección, horas, frente, técnica, unas, tarde, familia, sargento, necesídad, red, obra . (F) voz, puenlo, papel, asseguró. (G) nuestro, europea, china, ahora, poder, hasta, mucho, compañía, nacionalistas, cambio, asesinado, autor, nuevo, estamos, no.

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Clustering for text Mining

Page 54: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

RESULTS: Image Retrieval

Figure 5 – Spatial distribution of 244 images (representing 14 types of Portuguese Granites + 2 types of Chinese Granites), at t=1,000,000. Each image (point in the environment) is composed by 117 morphological and intensity features. Type 1 probability function was used with k1=0.1 and k2=0.3.

Clustering for text Mining

Page 55: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

DNA Protein Sequence Data Peng-Yeng Yin (Taiwan), Vitorino Ramos

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 56: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Figure - Self-Organized Ant-based clustering results on IDS data (MIT Lincoln Labs) using a full data set with 11982 samples (41 features each) in the initial and final steps

Intrusion detection Systems

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 57: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Web Usage Mining Vitorino Ramos, Ajith Abraham (USA)

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 58: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Web Usage Mining Vitorino Ramos, Ajith Abraham (USA)

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 59: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Web Usage Mining Vitorino Ramos, Ajith Abraham (USA)

NiSIS Malta Nov. 07Perceptive Swarms, Data and Computable Habitats:

Page 60: NiSIS Malta Nov. 07 PERCEPTIVE SWARMS, DATA AND COMPUTABLE HABITATS: Swarm Intelligence in Clustering and Pattern Recognition Vitorino Ramos LaSEEB-IST,

Other Data Mining examples include:

NiSIS Malta Nov. 07

- Ant-based Knowledge Discovery

- ACO-based Data Mining

- Construction of Rule-based Classifiers

- Real Time Continuous Clustering

- Ant-based Feature Selection and Extraction

- Video Processing

- Text and Document Mining

- Web Usage Mining