Expert Systems Lab 1

Rule based fish classification key

By John Monson

Introduction

Many times people encounter wildlife and are only able to place it in a very general category – like fish, bird or mammal. Using my program, a person can use the characteristics of the wildlife to be more specific in their identification. Using Clips, I have written a rule base classification system to identify several common species of fish that spend all or part of their lives in freshwater.

Background

To identify a fish, the system requires to the user to examine specific traits of their fish. The traits examined include:

· Scales: Small plates covering the body of the fish.

· Dorsal Fin: The main fin located on the fish’s back.

· Body Shape: The broadness or length of the fish’s body

· Jaw Hinge: Location of the Jaw hinge.

· Patterns and Coloring: Coloring or visible patterns, such as spots and lines of

the fish.

· Barbels: One of the slender, whisker like tactile organs extending from the head

of certain fishes, such as Cat Fishes.

· Texture: Texture of the body.

· Head: The shape of the head.

· Caudal Fin: The tail of the fish.

· Anal Fin: Single fin located in front of the caudal fin on the ventral side of the

fishes. Acts as a stabilizer to prevent rolling

· Adipose Fin: Sits between the dorsal fin and the caudal fin.

The information for this classification key comes from my mother who is the biology teacher at Edinburg Public High School. She obtained most of the information from the Holt Science Biology book and has adapted it to meet the needs of her students.

What I did

My system looks the physical characteristics of the fish, one at a time. The first pair of questions begins by asking two questions about the same trait. This pair (and all others) describes contrasting forms of the same trait. The user selects which question describes that trait of the fish. When the user determines which question in the pair describes their fish, they will be directed to the next pair of questions that best describe the fish and simply go to the next pair of questions. Eventually, they will find the name of the species instead of a new pair of questions concerning a new trait. At this point, the user will know the species of fish they were viewing. Then the user is ready to identify a different species of fish. They must start at the beginning, with the first pair of questions just as they did before. The user will continue to take directions each time they examine a new trait until they arrive at the name of the species of fish.

Sample Run

Error Situation:

If the enter correctly enters input, the system will not have an error situation. If the user enters input a value other than what is prompted (1 or 2) the fish classification system will exit and return the user to the Clips prompt.

Limitations:

· The program only handles expected input.

· Only supports eighteen freshwater fishes.

Goodness:

Biologist may determine water quality by identifying what inhabits the waters.

Of course this involves knowing the water quality requirements of each

Species to accomplish this. This type of analysis always begins with a scientific sampling of what inhabits the water, followed by identification of each specimen.

This expert system would be very useful for this. Then the scientist would use tables of water quality standards for the specimens to finish the task. The scientist may have to develop these tables. However, this would be very useful for training new field workers and even experienced ones

Future Enhancements:

· Add additional species of fishes.

· Refine the algorithm to better facilitate classifying a

larger group of fishes.

· Add error handling for invalid input.