Skip to content

Commit

Permalink
minor fix
Browse files Browse the repository at this point in the history
  • Loading branch information
rwuilbercq committed Jan 8, 2017
1 parent 137871c commit 0ca8cff
Showing 1 changed file with 6 additions and 8 deletions.
14 changes: 6 additions & 8 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,9 +2,7 @@
<img src="assets/logo/Hive.png">
</div>

https://rwuilbercq.github.io/Hive/

🍯**Hive** is a a swarm-based optimisation algorithm based on the intelligent foraging behaviour of honey bees. **Hive** implements the so-called **Artificial Bee Colony (ABC)** algorithm which is a swarm-based algorithms inspired by nature. Swarm intelligence refers to the collective behaviour of de-centralized, self-organized systems. The Artificial Bee Colony (ABC) was first proposed by Karaboga in 2005 (see **ref. ➀**). The overarching advantage of this algorithm is its relatively good balance between *exploration* and *exploitation*. In other words, exploitation, by definition, exploits known solution to minimize a cost function while exploration finds new solutions within un-explored parts of the search domain.
🍯**Hive** is a a swarm-based optimisation algorithm based on the intelligent foraging behaviour of honey bees. **Hive** implements the so-called **Artificial Bee Colony (ABC)** algorithm which is a swarm-based algorithms inspired by nature. Swarm intelligence refers to the collective behaviour of de-centralized, self-organized systems. The Artificial Bee Colony (ABC) was first proposed by Karaboga in 2005 (see **ref. ➀**). The overarching advantage of this algorithm is its relatively good balance between *exploration* and *exploitation*. In other words, exploitation, by definition, exploits known solution to minimize a cost function while exploration finds new solutions within un-explored parts of the search domain.

**Furthermore, the algorithm is pretty simple to use as it has almost no parameters to tune.**

Expand All @@ -13,11 +11,11 @@ This module is not implemented with **speed** in mind but, instead, it is a stra
### Intuition
----

In **Hive**, a swarm of artificial honey bees is made up of three types of individuals: employees, onlookers and scouts. The __Employed Bees (EB)__ and __Onlooker Bees (OB)__ exploit the nectar sources around the bee hive - i.e. this corresponds to the exploitation phase - while the **Scout Bees (SB)** explore the solution domain - i.e. this is the exploration phase.
In **Hive**, a swarm of artificial honey bees is made up of three types of individuals: employees, onlookers and scouts. The __Employed Bees (EB)__ and __Onlooker Bees (OB)__ exploit the nectar sources around the bee hive - i.e. this corresponds to the exploitation phase - while the **Scout Bees (SB)** explore the solution domain - i.e. this is the exploration phase.

The number of nectar sources (i.e. solution vectors) around the hive is equal to the number of actively employed bees and the number of employees is equal to the number of onlooker bees. EBs go to their nectar source and return to the hive to recruit onlooker bees via the honey bee waggle dance (i.e. figure-eight dance). The number of dance repetitions the worker performs is dependent on the quality of the food source. Workers that found poor nectar sources stop dancing sooner and are thus less likely to be followed by onlooker bees. After depletion of a given nectar source, an employed bee abandons its food source and becomes a Scout Bee (SB). A scout bee starts to randomly search around the hive to find a new nectar source around it.
The number of nectar sources (i.e. solution vectors) around the hive is equal to the number of actively employed bees and the number of employees is equal to the number of onlooker bees. EBs go to their nectar source and return to the hive to recruit onlooker bees via the honey bee waggle dance (i.e. figure-eight dance). The number of dance repetitions the worker performs is dependent on the quality of the food source. Workers that found poor nectar sources stop dancing sooner and are thus less likely to be followed by onlooker bees. After depletion of a given nectar source, an employed bee abandons its food source and becomes a Scout Bee (SB). A scout bee starts to randomly search around the hive to find a new nectar source around it.

### Algorithm
### Algorithm
------

As suggested in the previous summary of the algorithm, the ABC model of **Hive** consists of four phases that are accomplished sequentially, namely
Expand All @@ -27,7 +25,7 @@ As suggested in the previous summary of the algorithm, the ABC model of **Hive**
➋ An **Exploitation Phase** where new candidate solutions are generated for each employed bee using a cross-over and mutation operator. If the modified solution vector of a mutant bee is better than that of the original one, the new vector is assigned to the employed bee,

➌ A **Refinement Phase** during which onlooker bees attempt to locally improve the solution vectors of the employed bee they have decided to follow after the waggle dance phase. If they improve it, they will communicate their findings to the bee they initially watched waggle dancing,

➍ An **Exploration Phase** where scout bees are sent out to un-explored regions of the search domain.

### Constraints *(Not yet implemented)*
Expand Down Expand Up @@ -72,4 +70,4 @@ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
SOFTWARE.

0 comments on commit 0ca8cff

Please sign in to comment.