Citation
Expert system to determine lime requirements for soils of the humid tropics: version acid3b

Material Information

Title:
Expert system to determine lime requirements for soils of the humid tropics: version acid3b
Creator:
Centre for Soils Research, Bogor, Indonesia
Place of Publication:
Honolulu, Hawaii ; Raleigh, North Carolina ; Bogor, Indonesia
Publisher:
University of Hawaii and North Carolina State University
Language:
English

Subjects

Subjects / Keywords:
Farming ( LCSH )
Agriculture ( LCSH )
Farm life ( LCSH )

Notes

Funding:
Electronic resources created as part of a prototype UF Institutional Repository and Faculty Papers project by the University of Florida.

Record Information

Source Institution:
University of Florida
Holding Location:
University of Florida
Rights Management:
The University of Florida George A. Smathers Libraries respect the intellectual property rights of others and do not claim any copyright interest in this item. This item may be protected by copyright but is made available here under a claim of fair use (17 U.S.C. §107) for non-profit research and educational purposes. Users of this work have responsibility for determining copyright status prior to reusing, publishing or reproducing this item for purposes other than what is allowed by fair use or other copyright exemptions. Any reuse of this item in excess of fair use or other copyright exemptions requires permission of the copyright holder. The Smathers Libraries would like to learn more about this item and invite individuals or organizations to contact Digital Services (UFDC@uflib.ufl.edu) with any additional information they can provide.

Full Text
TROPSOILS
AnM Expont Syste)m
foT Sol o he! HM id T7opios(
By
The Centre for Soils Research, Bogor, Indonesia
University of Hawaii and North Carolina State University
VERSION ACID3B




About TropSoils
TropSoils is a collaborative research program whose goal is to develop improved soil management technology for developing countries in the tropics. Primary funding is provided by the U.S. Agency for International Development through Grant DAN 131 1-G-SS-1083-00. This action is in support of Title XII "Famine Prevention and Freedom from Hunger" of the Foreign Assistance Act.
For more information, contact TropSoils Project: Centre for Soil Research University of Hawaii Jalan I. H. Juanda No. 98 Dept. of Agronomy & Soil Science Bogor, Indonesia 1910 East-West Road
Honolulu, HI 96822




TABLE OF CONTENTS
I. OPERATING THE EXSYS-BASED ACID3B EXPERT SYSTEM ....... 1
A. HARDWARE REQUIREMENTS ....... ............... 1
B. DATA REQUIREMENTS ...... ................. 1
C. BEGINNERS GUIDE TO THE ACID3B EXPERT SYSTEM . 21
Starting the System ...... ................ 1
Entering Data ......... ................... 3
Conclusions ......... .................... 7
D. RERUNNING THE PROGRAM ....... ............... 7
Changing an Entry ........ ................. 8
Rerunning the Program with New Data ... ....... 9
E. DIRECTED GRAPH OF ACID3B ....... .............. 10
F. DISPLAY OF RULES ........ .................. 11
G. SITIUNG TRANSMIGRATION AREA, INDONESIA ......... .12
II. EVALUATION OF ACID3B ......... .................. 13
III. TEST DATA ........... ....................... 15
IV. AN OVERVIEW OF THE ACID3B EXPERT SYSTEM ............ 16
A. A BRIEF SUMMARY OF THE KNOWLEDGE BASE .. ....... .16
B. INTRODUCTION TO A RULE-BASED SYSTEM ... ........ 17




OPERATING THE EXSYS-BASED ACID3B EXPERT SYSTEM
A. HARDWARE REQUIREMENTS
256K RAM
IBM compatible machine with PC-DOS 2.0 or above
Monochrome or color monitor
Graphics optional (graph of Al tolerances to various crops
can be displayed if the machine has a graphics card and
a graphics monitor)
A double-sided double density (360K) drive
B. DATA REQUIREMENTS
Soil order
Soil great group (if known)
Crop (choices include: maize, soybean, upland rice, mung
bean, peanut, cassava, sweet potato, pasture legume,
pasture grass, cowpea)
Depth of incorporation
Bulk density
ECEC ("effective cation exchange capacity" obtained by
summing KCL extractable Al, exchangeable Ca, Mg, K, and
other cations units are cmol/kg (meq/100g)
EXTRAL (the extactable aluminum plus hydrogen as determined
by KCI batch extraction units are cmol/kg (meg/100g)
Green manure (choices include: not been applied, applied at
about 5 ton/ha or 10 ton/ha)
Fineness factor (the proportion of lime which passes a 60
mesh sieve (given in a fraction from 0 to 1.0)
CaCO3 equivalent (determined by adding excess HCl and backtitrating with NaOH; values should range from 0.0 to
1.8)
Soil pH
C. BEGINNERS GUIDE TO THE ACID3B EXPERT SYSTEM.
Starting ACID3B
Step 1. Start the machine
Step 2. Insert the operating system (PC-DOS 2.0, 2.1, 3.0, or
3.1) and load the operating system. A successful load is indicated by the display of the prompt, A>
Step 3. Remove the operating diskette. Insert the ACID3B diskette. Check that the following three files are on the diskette by typing dir and pressing : EXSYS.EXE, ACID3B.TXT, and ACID3B.RUL). If these files are not present, the ACID3B system will not run.




Step 4. At the A> prompt, type A>EXSYS ACID3B
The system will respond by identifying the EXSYS program and asking you to:
Press any key to start: Step 5. Press any key. The screen will say READING DATA
followed by:
Do you wish instructions on running the program (Y/N):
(If you respond with Y, you will be given background
information on the EXSYS program and will be instructed how to return to the program.) Step 6. Respond with N. The next question asked is:
Recover previously saved position Y/N (default = N): Step 7. Press N. The next question is:
Do you wish to have the rules displayed as
they are used (Y/N) (Default = Y):
If you respond with Y, the rules will be displayed that have been concluded to be true. If the response is N, the system will proceed with questions and display the conclusions directly without indicating the rules used. Step 8. Press N. As the title and the names of the authors appear you will be prompted
2




Press any key to start:
Step 9. Press any key. You will be given a description of the data used in making the recommendations and again asked to:
Press any key to start:
You have now started ACID3B.
Entering Data
This section includes a sample run of the program using as data soil order Ultisol, great group Paleudult, soybean cultivar Willis, DEPTH INCORP. 15, BULK DENSITY 1.1, ECEC 4.0, EXTRAL 3.2, no green manure added, Fineness factor .7, CaC03 equivalent 1.1, and pH 5.0-5.5.
Step 10. Press any key. The next screen will read:
You prefer to
1 continue
2 see more information about this expert system
Notice that along the bottom of the screen the following appears. These instructions will appear at the bottom of each screen that requests data.
Enter number(s) of appropriate value(s), WHY for information on the rule being applied QUIT to store data and exit or for help
(If you type H and then press at this point in the program you will be given an explanation of the WHY and QUIT functions. Help information is available throughout the program. If you type WHY you will be shown the rule which is being tested.)
Step 11. Press 1 and then . The following will appear:
Soil information:
1 soil location is in the Sitiung transmigration area
2 soil location is not in the Sitiung transmigration area
Step 12. Press 2 and then . You will then be asked for
soil order.
3




Soil order is
1 Histosols 2 Mollisols 3 Vertisols
4 Entisols
5 some Alfisols
6 Inceptisols
7 Oxisols 8 Ultisols 9 Spodosols 10 Aridisols 11 not known
Step 13. Press 8 then . Next, soil great group information is asked for.
Soil information
1 soil great group is known
2 soil great group is not known
Step 14. Press 1 then . All the Ultisol great groups will be listed.
Ultisol great group is
1 none of these
2 albaquults
19 rhodudults
Press any key for more values
Press any key and the rest of the great groups will be listed on the next screen.
Step 15. Press 12 (Paleudults) and then .
The crop is (Critical Al saturation is shown)
1 maize (corn) (30 %)
2 soybean (0 to 25 %)
3 upland rice (40 to 60 %)
4 mung bean (0 %)
5 peanut (40 %)
6 cassava (75 %)
7 sweet potato (30 %)
8 pasture legume(20 to 85%)
4




9 pasture grass (20 to 95%)
10 cowpea (60 %)
11 known but you prefer to enter your own critical level of
Al saturation
12 known but you would like to see a graph showing the Al
tolerances of the above crops.
Step 16. Press 2 and then . The next screen will ask for the cultivar.
(For some of the crops cultivar will not be asked.)
The cultivar is
1 Willis
2 Orba
3 unknown
Step 17. Press 1 and then .
The value of the variable DEPTH OF INCORP is needed.
Please input the value of DEPTH OF INCORP.: the depth of incorporation of the lime in centimeters (15 cm is a usual value).
Value:
Step 18. Type 15 and press
The value of the variable BULK DENSITY is needed.
Please input the value of BULK DENSITY: the usual soil bulk density that is needed to calculate weight/volume conversions. (values range from 0.6 to 1.8 or so) kg/L.
Value:
Step 19. Type 1.0 and press
Please input the value of ECEC: the "effective cation exchange capacity" obtained by summing KCl extractable Al, exchangeable Ca, Mg, K, and other cations units are cmol/kg.
5




Value:
Step 20. Type 4.0 and press . Please input the value of EXTRAL.: the extractable aluminum plus hydrogen as determined by KCl batch extraction units are cmol/kg
(meq/100g).
Value:
Step 21. Type 3.2 and press . Green manure has
1 not been applied
2 been applied at about 5 ton/ha fresh weight prior to this
crop
3 been applied at about 10 ton/ha fresh weight prior to
this crop
Step 22. Type 1 and press The value of the variable FINENESS FACTOR is needed. Please input the value of : the.proportion of lime which passes a 60 mesh sieve (given in fraction from 0 to 1.0).
Value:
Step 23. Type .7 and press . Please input the value of : the calcium carbonate equivalent as determined by adding excess HCl and back-titrating with NaOH according to standard procedures (ASA Monograph No. 9). Values should range from 0 to 1.8 (MgC03 about 1.8, CaCO3 about 1.0).
Value:
6




Step 24. Type 1,1 and press . The final data asked for will be pH.
Soil pH is
1 < 4.0
2 4.0 -5.0 3 5.0 -5.5 4 5.5 -6.0
5 > 6.0
6 not known
Step 25. Type 3 and press . Data entry is now complete.
Conclusions
1 Recommend you apply 3 to 4 tons of lime/ha. :95/100
2 Possible low exchangeable Mg, critical level is around
0.15 cmol/kg. :75/100.
All choices , value>0 , Print

, Change and rerun , Quit/store , New sort criteria , rules used ,, Help , Done :
The choices are now displayed with the most likely first.
The number following the choice reflects the degree of confidence given for the choice. You may ask how the computer arrived a particular answer by entering the line number. To print the final list of choices, press

.
You may change any of your data entries and see what effect
this has on the final conclusion by selecting the change and rerun option, . You will be shown a list of all the input you provided to the program. Enter the number or numbers of the items you wish to change and the computer will redisplay the screens which ask for the data. After you input the new data, the list of all the input will be redisplayed. If the data is the way you wish it, press to run the data.
An example of how to change an entry and rerun the system is given in the next section. If you press you will be given the option of running the program again from the beginning.
D. RERUNNING THE PROGRAM
There are two ways to rerun the program without having to
exit and re-enter. The first is to change one or more entries and rerun the program with the other data still the same. For
7




example, if you wish to change the crop you may do so without having to re-enter the rest of the data. The second way is to rerun the system using all new values.
Changing an entry
We will return again to the recommendations displayed at the end of the program.
1 Recommend you apply 3 to 4 tons of lime/ha :95/100
2 Possible low exchangeable Mg, critical level is around
0.15 cmol/kg. :75/100
All choices
, value>O , Change and rerun , Quit/store , New sort criteria , Help , Done (D>:
Step 1. Press and the following will appear at the bottom of the screen:
Do you wish to store the current values for comparison with the new values you will be calculating? (Y/N) (Default=):
Step 2. Press Y and the screen will read:
1 The crop is (Critical Al saturation is shown) soybean
(0 to 25%)
2 Soil pH is 5.0-5.5
3 Ultisol great group is paleudults
4 Soil order is Ultisols 5 You prefer to continue
6 Soil information: soil great group is known
7 The soybean cultivar is Willis
8 Green manure has not been applied
9 Soil information: soil location is not is the Sitiung
transmigration area
10 Variable [LIME FACTOR] = 1.65 11 Variable [EXTRAL] = 3.2 12 Variable [ECEC] = 4.0 13 Variable [DEPTH OF INCORP] = 15.0 14 Variable [BULK DENSITY] = 1.1 15 Variable [CaC03 EQUIVALENT] = 1.1 16 Variable [FINENESS FACTOR] = 0.7
You may change as many variables as you wish. In this example we will change the crop (line 1).
8




Step 3. Type 1 and press . The next screen will read:
The crop is (Critical Al saturation is shown)
1 maize (corn) (30 %)
2 soybean (0 to 25 %)
3 upland rice (40 to 60 %)
4 mung bean (0 %)
5 peanut (40 %)
6 cassava (75 %)
7 sweet potato (30 %)
8 pasture legume(20 to 85%) 9 pasture grass (20 to 95%)
10 cowpea (60 %)
11 known but you prefer to enter your own critical level of
Al saturation
12 known but you would like to see a graph showing the Al
tolerances of the above crops.
Step 4. Type 1 and press . The next screen will confirm your selection and display all the values you have entered.
1 The crop is (Critical Al saturation is shown) maize (corn)
(30%)
2 Soil pH is 5.0-5.5
3 Ultisol great group is paleudults
4 Soil order is Ultisols 5 You prefer to continue
6 Soil information: soil great group is known
7 The soybean cultivar is Willis
8 Green manure has not been applied
9 Soil information: soil location is not is the Sitiung
transmigration area
10 Variable [LIME FACTOR] = 1.65 11 Variable [EXTRAL] = 3.2 12 Variable [ECEC] = 4.0 13 Variable [DEPTH OF INCORP] = 15.0 14 Variable [BULK DENSITY] = 1.1 15 Variable [CaC03 EQUIVALENT] = 1.1 16 Variable [FINENESS FACTOR] = 0.7
Enter number of line to change, to run the data, for help or any other key to redisplay data:
Step 5. Press and the program will run again and give new recommendations.
Running the program again with new data.
Refer again to the instructions displayed at the bottom of the screen when recommendations are given.
9




Step 1. Type D and you will be given the option of running the program again and putting in new data.
Run again (Y/N) (Default=N) :
Step 2. Type Y and the following will appear:
Same file (Y/N) (Default = Y)
Step 3. Type Y and you will begin again at:
Do you wish instructions on running the program (Y/N):
E. DIRECTED GRAPH OF ACID3B
An information chart of ACID3B is available for those who wish additional information about the system. If we return to Step 10 under the section on starting the system and begin with:
You prefer to
1 continue
2 see more information about this expert system
Enter number(s) of appropriate value(s), WHY for information on the rule being applied, QUIT to store data and exit or for help
Step 1. Press 2 and then .
This leads to a directed graph of ACID3 expert system. (If you have a monochrome monitor and the screen is completely green, press until the chart is visible.) As indicated by the commands given at the bottom of the screen, it is possible to scroll the chart up or down and use the commands given (Key: PgUp PgDn Home End X=exit ?=Help).
Step 2. Press X. The system will display the following:
To restart the system PRESS D (Done) and run again.
All choices
, value>O , Print

, Change and rerun , Quit/store , New sort criteria , rules used , Help , Done :
10




You may reenter the system by pressing C and then following the same procedure as given in the previous section for changing an entry. In that case, the line you wish to change is
1 You prefer to see more information about this expert system
If you do not wish to continue by re-entering the system, you may type and have the option of either stopping or rerunning the system from the beginning.
F. DISPLAY OF RULES
There are at least three ways to see the rules tested for validity by the program:
1. Respond affirmatively to the question Do you wish to have the rules displayed as they are used (Y/N). Unlike the example used in C above, rules that have been found to be true will be displayed as the program proceeds.
2. When indicated by the program information line at the bottom of the paper, you may type WHY to see the rules used. Pressing when a rule is displayed will allow you to see previous rules in the chain.
3. When recommendations are given at the end of the
program, the program information line at the bottom of the page will instruct you to type the line number in order to see the rules used in making that recommendation.
Sample rule
RULE NUMBER; 2 2
IF:
(1) You prefer to continue
and (2) Soil order is some Alfisols or Inceptisols or Oxisols
or Ultisols
and (3) Soil information: soil great group is known or soil
great group of not known
and (4) Al or Mn toxicity is probable or not likely
and (5) [LIME FACTOR] > 0.5
and (6) [LIME REQ] < 0.3
THEN:




No lime is recommended. Probability=95/100
Input IF line number for info on how it was derived for reference for the topic, for help or to continue:
Typing the line number in the IF part will allow you see previous rules on the chain. The probability value assigned indicates the likelihood of the solution. For any rule, it is possible to see what reference materials were used by pressing . will give you more detailed information on the program.
G. SITIUNG TRANSMIGRATION AREA, INDONESIA
If in section C Step 12, we had selected 1 soil location is in the Sitiung transmigration area, the procedure would have been somewhat different. Because this program was developed using data from this area, and much more data is available, you are asked the location of the sample rather than soil order or great group. For example,
Soil sample was obtained from
1 Sitiung I (all Blocks)
2 Sitiung II (Blocks A, B or C)
3 Sitiung II (Block D or E)
4 Sitiung IV or V
5 none of the above
The data asked for here is different than for soils not in the Sitiung transmigration area. You will be asked:
Extractable K is
1 less than 0.12-0.15 cmol K/kg
2 greater than 0.12-0.15 cmol K/kg
3 not known
and
Olsen extractable P is
1 less than 10-12 mg P/kg
2 greater than 10-12 mg P/kg
3 not known
This information is used in determining P and K fertilizer requirement for areas within Sitiung.
12




EVALUATION OF ACID3B
Attached is a table with 10 test sets of soil conditions. Please enter these into the expert system and note the recommendations made. Your answers to the following questions together with any comments, data, and publications you think appropriate would be very much appreciated. (Responses may be sent to Russell S. Yost, Dept. of Agronomy and Soil Science, 1910 EastWest Road, Honolulu, HI 96822)
1. Do you agree with the predicted lime requirements given for the text soil and crop data? How do these compare with lime requirements you would make using the same data?
2. Do you feel that the interpretations, cautions and informative notes included in the output were sufficient?
13




3. Do you think the system asks the right questions in the right order? If not, please explain the sequence you would have preferred.
4. Do you have a different recommendation philosophy which you feel would be more appropriate?
5. Under what conditions do you think this system would be most useful? What modifications or additional considerations are important in your situation?
6. Did you have any particular difficulty using this system?
14




TEST DATA
1 2 3 4 5
Soil order Ultisol Oxisol Inceptisol Ultisol Ultisol
Great group Paleudult Haplorthox Sulfaquept Hapludult Hapludult
Crop Willis, soy. rice maize peanut cassava
Depth Incorp 15 10 20 12 10
Bulk Density 1.0 1.1 1.3 0.9 1.1
ECEC 4.0 3.2 4.2 5.5 2.2
EXTRAL 3.2 2.8 13.5 2.5 1.0
Green Manure 0 0 5 10 0
Fine. Factor 0.7 0.8 0.8 0.5 0.6
CaCO3 equiv. 1.1 0.7 0.7 0.8 0.9
Soil pH 5.0-5.5 4.0-5.0 4.0-5.0 5.0-5.5 4.0-5.0
P orK -- -- -- -- -Recommend.:
Cautions:
Notes:
TEST DATA
6 7 8 9 10
Soil order Ultisol Ultisol Ultisol Ultisol Mollisol
Great group Paleudult Paleudult Paleudult Paleudult -Crop soybean soybean soybean cassava soybean
Depth Incorp 15 15 15 15 15
Bulk density 1.1 1.1 1.1 1.1 1.1
ECEC 1.0 4.5 3.0 4.5 4.5
EXTRAL 0.3 3.8 4.5 3.8 3.8
Green manure 0 0 0 5 0
Fine. factor 0.8 0.8 0.9 0.7 0.5
CaCO3 equiv. 1.0 1.0 0.9 0.6 1.1
Soil pH 4.0-5.0 4.0-5.0 5.5-6.0 4.0-5.0 6.0
P and K -- -- -- -- -Recommend.:
Cautions:
Notes:
15




A BRIEF SUTMMIARY OF THE KNOWLEDGE BASE
Expert systems are designed to simulate a human expert's approach, knowledge and experience in making a diagnosis or recommendation. ACID3B is a prototype system for making lime recommendations in the humid tropics. The knowledge base is being developed from existing information and research experience. The primary objective, as part of the Tropsoils project, has been to address soil acidity problems in highly weathered soils of Sumatra, Indonesia. We have focused on extractable acidity (mostly exchangeable Al) as the primary cause of yield reduction due to soil acidity. A summary reference for the knowledge base is a review paper by Kamprath (1984). The main concepts in the database are:
1. Growth limiting effects are primarily due to exchangeable Al + H (exchangeable acidity) although if all cations are present in very small quantities some lime is probably needed to provide Ca. It is assumed that toxicity to exchangeable acidity is closely related with Al + H saturation.
2. crops vary considerably in their tolerance to
exchangeable acidity, extremes are represented by mung bean (very intolerant, tolerating no more than 0 % Al saturation) and cassava (very tolerant -- about 75% Al + H saturation.)
3. Organic material seems to reduce lime requirements. The approximation is currently 10 ton/ha of fresh organic material reduces lime requirement by 1 ton/ha.
4. Lime requirements need to be based on soil analyses in order to accurately reflect the soil conditions.
5. Although data is sparse, an attempt is made to determine the approximate effects of lime quality on the lime requirement. Included are the neutralization value relative to calcium carbonate and an estimate of physical reactivity as related to the particle size. The estimate of neutralization value is a relatively well defined laboratory procedure in which an excess of acid is added to the lime and allowed to fully react. The excess acid is back-titrated to estimate the unreacted acid for calculation.
Particle size fractions have been used to estimate the
physical reactivity of the limestone. Here many factors have been discussed and are relevant to field estimation of time required after application before crops can be planted. One of the simpler measurements of lime quality as affected by particle size is given by the estimate of the amount of lime of various particle sizes needed to give approximately equivalent yields.
The calculation of lime requirement is based on the need to neutralize sufficient Al to reduce Aluminum saturation to the 'critical Aluminum saturation' which has been established for the
16




various crops (Cochrane et al., 1980). Our modified form of the equation is :
Lime requirement (t/ha) = 1.4(exch. acidity (CAS*ECEC/100)
exch. acidity = 1 N KCl extractable Al + H
CAS = critical Aluminum saturation of the crop
ECEC = 'effective cation exchange capacity'
1.4 represents the relation of the cmol of CaCO3 required to
neutralize 1 cmole of Al + H in field studies adjusted for both bulk density and depth of incorporation. In this case 1.9 cmol of Ca was required for each cmol of Al + H, the bulk density was assumed to be 1.0, and the depth of incorporation was assumed to be 15 cm.
Preliminary data suggest approximately 0.53 cmol KClextractable acidity is neutralized for each cmol of Ca added as CaCO3 (Wade et al., 1985). This corresponds to a relation of 1.9 cmol of CaCO3 being required for each cmol of extractable acidity, a value much in keeping with results reported elsewhere (Kamprath, 1985). This reference points out the need to consider the effectiveness of lime in neutralizing the extractable acidity. Such data need to be obtained in field studies if possible because of the need to ensure that one is testing the liming material and soil reactivity in conditions that are representative of the situation or group of farmers to which the eventual recommendation is intended to apply.
The system is designed to apply to the Humid Tropics with
soils of the Ultisol, Oxisol, and Inceptisol orders. In addition, the system has additional information pertinent to the Sitiung region, Indonesia. The general recommendations are based on other relationships such as a general reactivity of 2 cmol of CaCO3 for each cmol of extractable acidity. Levels of critical aluminum saturation are, so far, the same for the general recommendation as for the specific location in Sitiung. Other data and results from the Tropsoils work in Sitiung are incorporated such as minimal requirements of P and K for soybean, rice, cowpea and peanut.
INTRODUCTION TO A RULE-BASED SYSTEM
ACID3B has been developed on a rule-based expert system
development shell, EXSYS. The shell provides editing facilities to design output formats, to run test datasets, and to ensure modifications have not disrupted the core logic flow of the system. The inference engine is backward chaining and provides probability accumulation in dependent, independent, and averaging modes. Only relatively simply WHY capability is provided which displays the rules which are being evaluated in the information input mode or provides the chain of fired rules in support of a recommendation. Programming effort is minimal with this software,
17




however with the usual loss in flexibility for certain types of expert system construction.
In EXSYS the search procedure follows several relatively
simple rules. These search rules will be dicussed in the sequence in which they operate.
1. Rule selection. The first search or "pattern matching" that is done on the knowledge base begins with the choiceses. Choices in EXSYS are all the potential conclusions from which the system can choose in presenting final results. None, one or several choices are possible with any consultation (or "run" of the system).
The first choice is selected to determine if it can be proved true or false. The search routine determines which rules have this choice in their THEN part. If there are more than one, the first rule (in numerical order) is the one chosen for analysis.
RULE 11.
IF:
You prefer to continue
The soil great group is Paleudults
THEN:
No lime is recommended probability (100/100) <- This is the first choice of the list of choices. This choice will cause RULE 11 to be selected first for analysis.
2. Condition selection. Once the rule is selected EXSYS then proceeds to analyze components of the rule -- the "conditions". In EXSYS a condition is composed of two parts: the "Qualifier" and the "Value". After selecting which rule to analyze EXSYS then determines which "condition" to analyze. This selection is quite logical -- the first condition in the IF part of the rule is selected for evaluation. The purpose of the evaluation is to determine if the condition is true or false. The system determines if the condition is true by first searching the file of facts or input already concluded to be true, if the condition is not in the list of facts, then the system searches rules which have the condition in their THEN parts. If the system finds a rule with the condition in the THEN part, it then determines whether the conditions in the IF part of that rule are true or can be concluded to be true from other rules by chaining. If our first condition can be determined to be true then the system will proceed otherwise it will, as a last resort, display the first condition in the rule that had our first condition in its THEN part. These conditions will be displayed in the form of the qualifier and values, asking the user to indicate which ones are successive conditions. For example:
18




Rule 11
IF: (qualifier) (value) (search order)
You prefer to continue <- first searched
The soil great group is Paleudults <- second searched
THEN:
No lime is recommended probability (100/100) <- This is the first choice of the list of choices. This choice caused this rule to be selected first for analysis.
RULE 22
IF:
If you have use this system before and you don't need to see details of this system. <-This condition will be searched
for and, if not found, will be
displayed for user selection
THEN:
You prefer to continue <-This condition matches the condition in Rule 11 and is
why RULE 22 was selected. (This relationship between rules is
also known as chaining.)
The search begins with the selection of a rule to analyze. The first "Choice" in the list of Choices is selected. A rule which has this choice in its THEN part is then selected. If there is more than one rule with the choice in its THEN part, the rule that has the smallest rule number will be selected. The IF part of the selected rule will then be looked at. The first condition will be selected and determined whether it can be proved true or false from information already determined to be true. If the condition cannot be determined to be true or false based on information already in the system, the system will put the condition on screen and ask the user directly which combination of qualifiers and values are true.
The order of the conditions in the first selected rule will determine the order of the questions asked of the user. For example, one would prefer that the most likely conditions be asked first. This can be done by placing the most commonly selected choice as the first in the choice list (Choice 1). This order should match the "directed graph" or decision tree that we recommend you first construct to document the logical organization of the expert system. In other words, the first condition in the rule should ask the most general information. This will ensure that the system will reduce the number of rules to be searched in subsequent steps. If a very specific condition were placed first, it might ask for information that is irrelevant to most of the system.
19