Designing a Farmer Centred Ontology for Social Life Network

Anusha Indika Walisadeera

1,2

, Gihan Nilendra Wikramanayake

and Athula Ginige

School of Computing, Engineering & Mathematics, University of Western Sydney, Penrith, Australia

University of Colombo, School of Computing, Colombo, Sri Lanka

Keywords: Agricultural Knowledge, Social Life Network, Knowledge Representation, Ontology, Ontology Design.

Abstract: Rapid adoption of mobile phones has vastly improved access to information. Yet finding the information

within the context in which information is required in a timely manner is a challenge. To investigate some

of the underlying farmer centric research challenges a large International Collaborative Research Project to

develop mobile based information systems for people in developing countries has been launched. One major

sub project is to develop a Social Life Network; a mobile based information system for farmers in Sri

Lanka. Lack of timely information with respect to their preferences and needs to support farming activities

is creating many problems for farmers in Sri Lanka. For instance, farmers need agricultural information

within the context of location of their farm land, their economic condition, their interest and beliefs, and

available agricultural equipment. As a part of this project we investigated how we can create a knowledge

repository of agricultural information to respond to user queries taking into account the context in which the

information is needed. Because of the complex nature of the relationships among various concepts we

selected an ontological approach that supports first order logic to create the knowledge repository. We first

identified set of questions that reflect various motivation scenarios. Next we created a model to represent

user context. Then we developed a novel approach to derive the competency questions incorporating user

context. These competency questions were used to identify the concepts, relationships and axioms to

develop the ontology. Initial system was trialled with a group of farmers in Sri Lanka. There was universal

agreement among the farmers participated in the field trial to varying degree (strongly agree, agree,

moderately agree) to the question “All information for the crop selection stage is provided”.

1 INTRODUCTION

From time to time farmers need information such as

seasonal weather, best cultivars and seeds, fertilizes,

information on pest and diseases, control methods,

harvesting and post harvesting methods, accurate

market prices, and current supply and demand to

make informed decisions at various stages of the

farming lifecycle (De Silva et al., 2012; Lokanathan

and Kapugama, 2012). Some of this information is

available from government websites, leaflets and

mass media. Farmers require this information within

the context of their specific needs. Such information

could make a greater impact on their decision-

making process (Glendenning et al., 2010).

Not having an agricultural knowledge repository

that can be easily accessed by farmers within their

own context is a major problem.

Social Life Networks for the Middle of the

Pyramid (www.sln4mop.org) is an International

Collaborative research project aiming to develop

mobile based information system to support

livelihood activities of people in developing

countries.

The research work presented in this paper is part

of the Social Life Network project, aiming to

provide information to farmers based on their

context. For this we had to develop a knowledge

repository. Because of the complex nature of the

relationships among various concepts we selected an

ontological approach to create the knowledge

repository.

To represent the information in context-specific

manner, firstly, we need to identify farmers’ context

related to this application. We identified the context

specific to the farmers in Sri Lanka (i.e. farmers’

context) by analyzing information gathered from

various reliable knowledge sources. The Table 1

shows the farmers’ context that was identified

related to this application. The way of modeling the

farmers’ context and the farming stages related to

238

Indika Walisadeera A., Nilendra Wikramanayake G. and Ginige A..

Designing a Farmer Centred Ontology for Social Life Network.

DOI: 10.5220/0004495802380247

In Proceedings of the 2nd International Conference on Data Technologies and Applications (DATA-2013), pages 238-247

ISBN: 978-989-8565-67-9

 2013 SCITEPRESS (Science and Technology Publications, Lda.)

this application is outside the scope of this paper and

it is explain in (Walisadeera et al., 2013).

Table 1: Farmers’ Context.

Farmers’ Context Description

Farm

environment

Types of farmers

Preferences of

farmer

Farming stages

Information about environment

based on location of farm such

as elevation, rainfall, climate

zone, temperature, humidity,

sunlight, wind, soil, etc.

Farmers are classified based on

size of the cultivated farm land

and estimated budget for

cultivation. There are two main

categories; garden farmers and

commercial farmers.

Commercial farmers can be

further categorized as small-

scale farmers, medium-scale

farmers and large-scale farmers.

Farmers have their own

preferences such as high

yielding varieties, preferred

control methods and fertilizers,

low labour cost crops, high

disease and insect resistance

crops, desired farming systems

and techniques, etc.

Required information varies

based on different stages of the

farming lifecycle. To improve

overall decision making in

farming, we have defined six

farming stages covering all

required information needed by

farmers (refer Table 2 for

farming stages).

Recently, ontologies have emerged as a major

research topic in Information Systems. The term

‘ontology’ originated from philosophy and it is

concerned with the study of being or existence

(Rumbaugh et al., 1991). Lately, it has been used in

computer science and information science, for

knowledge engineering, databases and software

engineering purposes to define models that specify

reusable components and the relationships among

them. Ontologies are widely used for different

purposes (e.g. natural language processing,

knowledge management, e-commerce, intelligent

integration of information and semantic web) in

different communities (e.g. knowledge engineering

and databases).

An Ontology provides a structured view of

domain knowledge and act as a repository of

Table 2: Farming Stages.

Farming Stages Description

Crop Selection

Pre-Sowing

Growing

Harvesting

Post-Harvesting

Selling

Most important decision is

deciding which crops to grow.

Crop selection is a complex

process because it depends on

many factors. The environmental

factors mostly affected this

selection. Features of a crop,

farmer preferences, available

resources and market demand

are other key determinant for

this decision.

Refers to preparing the field for

selected crops. At this stage

farmer needs information on

quality agricultural inputs such

as seed rate, plant nutrients and

fertilizing, irrigation facilities

and new techniques for field

preparation.

Includes information related to

managing the crop through its

growing stages. Information on

planting methods, good

agriculture practices (traditional

and new technology), common

growing problems and their

management is required in this

stage.

At this stage farmer needs

information related to harvesting

such as maturity time, methods

and techniques of harvesting,

expected average yield, labour

cost and total production cost for

cultivation.

Refers to proper handling after

harvesting. Required

information includes post

harvesting issues and

management, packing, grading,

storing, standardization,

transportation and value added

products.

Refers to preparation for selling.

Mainly includes information

related to the market such as

market prices, consumer

behaviour and demand, and

alternative marketing channels.

concepts in the domain. This structured view is

essential to facilitate knowledge sharing, knowledge

DesigningaFarmerCentredOntologyforSocialLifeNetwork

239

aggregation, information retrieval and question

answering (Gruber, 1995). In addition, ontology

provides the means of deduction capabilities

provided by an inference mechanism and reasoning

support in order to generate further knowledge (i.e.

not explicitly known but can be deduced based on

the existing knowledge of the domain) (Fox et al.,

1996). Thus, ontology represents a better data model

(richer knowledge) than a normal data model.

Therefore, ontology can be used to find a response

to queries within a specified context in the domain

of agriculture. The most quoted definition of

ontology was proposed by Thomas Gruber as “an

ontology is an explicit specification of a

conceptualization” (Gruber, 1993). This definition is

adapted for our ontology.

The existing ontologies in the domain of

agriculture for example Thai Rice Ontology

(Thunkijjanukij, 2009) are crop-specific thus too

general and not specific enough to satisfy the

farmers’ needs for timely information in context.

To develop an ontology we need to carefully

identify suitable ontology development methodology

because there are several methodologies and

techniques for building ontologies reported in the

literature (Fernández-López and Gómez-Pérez,

2002). We select a first-order logic based approach;

Grüninger and Fox’s methodology (Grüninger and

Fox, 1995), to develop our ontology because its

expressiveness helps us to represent information in

context. Furthermore, this methodology provides a

formal approach to design ontology as well as a

framework for evaluating the adequacy of the

developed ontology. Its main strength is high degree

of formality and focuses on building ontology based

on First-Order Logic (FOL) by providing strong

semantics.

Since there is no technique for formulating the

competency questions incorporating user context,

we have an issue with regarding to correctness of the

contents of the ontology. Therefore, the main

contribution of this paper is a novel approach to

derive the competency questions incorporating user

context. We also introduce a framework for

ontology design that we developed to design the

ontology for farmers to represent the necessary

agricultural information and knowledge within the

farmers’ context.

The rest of the paper is organized as follows.

Section 2 describes the design of the ontology for

the crop selection stage. This design process, also

includes a systematic approach to generate the

competency questions. In section 3 we present a

genaralisation of the approach that evolved from this

work. The section 4 provides a summary of initial

field trial used to test the ontology for crop selection

phase. In section 5 we conclude the paper with a

summary and describe the future direction.

2 DESIGN OF THE ONTOLOGY

In this section we describe the process that we used

to design the agricultural ontology for farmers. Our

ontology creation begins with the definition of a set

of farmers’ problems identified by reviewing related

literature in the domain of agriculture (Decoteau,

2000; Kawtrakul, 2012; Babu et al., 2012) and the

outcomes of the interviews with Sri Lankan farmers

and agricultural specialists. We generalize these

problems and organize these according to the

farming lifecycle stages (see Table 2). We take these

real farmers’ problems as a motivation scenario of

our application to provide information in context

(see Table 3).

Table 3: Real-World Application Scenario.



What are the suitable crops to grow?

 What are the best cultivars?

 What are the best fertilizers for selected crops and

in what quantities?

 When is the appropriate time to apply fertilizer?

 What are the types of pests or crop diseases?

 How to protect crops from disease?

 Which are the most suitable control methods to a

particular disease?

 What are the symptoms of a specific disease?

 What are the most important factors to maintain

quality of harvested crops?

 Which post-harvest method is best for a particular

crop?

 What are the crops cultivated by other farmers and

in what amounts?

Next we identify areas of generic crop

knowledge required to answer these motivation

scenario questions. These broad areas of knowledge

we term as knowledge modules. The generic crop

knowledge consist of modules such as nursery

management, harvesting, post-harvesting, growing

problems, control methods, fertilizer, environmental

factors and basic characteristics of crops. A cultivar

(variety) is a group of crops that share common

qualities of crops of the same species (Decoteau,

2000). Each information module has related

information to answer the scenario questions. For

example, crop information module has information

about crops and cultivars. Next we identify

relationships among them. The following Figure 1

DATA2013-2ndInternationalConferenceonDataManagementTechnologiesandApplications

240

shows the generic crop knowledge module. To

represent agricultural knowledge within the farmer’s

context we need to associate this generic crop

knowledge with characteristics that describes the

farmers’ context.

Figure 1: Generic Crop Knowledge Module.

We begin our detail design process with first

question of the motivation scenario “What are the

suitable crops to grow?” Selecting proper crops and

cultivars is paramount for successful farming.

During initial interviews with vegetable farmers they

also identified this as a very important question.

Choosing the best crop for individual situations is

difficult since one has to consider many factors such

as environmental conditions which can vary based

on region and time period, preferences of farmer and

resources available for them for cultivation. We

have reviewed existing literature on crop selection

criteria to identify a suitable criterion which can be

used to assist farmers to make better decisions.

According to the Decoteau’s (2000), the crop

selection especially for vegetable crops depends on

four considerations; Crop Consideration, Farmer

Consideration, Labour Consideration and Marketing

Consideration. This criterion is designed only for

vegetable crops and for farmers in developed

countries. Therefore this criterion is not a good fit

for our application.

Bareja (2012) has identified following as major

crop selection factors for successful farming; Farm

conditions (an environmental scanning should be

conducted first), Crop or varieties adaptability (crops

and varieties should be selected based on

adaptability to farm conditions), Available

technology, Marketability and profitability,

Resistance to pests and diseases, Farming systems

and Security (crop selection may be done in favour

of security such as absence of security personnel).

This criterion is designed for multiple crops and

cultivars selection. However, it has not considered

the important factors such as labour cost and the

farmer types.

We next reviewed factors described in the

NAVAGOVIYA (CIC, 2012) web site which is one

of the important web sources in the domain of

agriculture in Sri Lanka for selecting suitable crops.

These factors are Climatic requirements, Soil

properties, Growing season, Labour availability and

cost, Raw material availability and Market demand.

According to the above analysis, environmental

condition has been identified as a most important

factor. Therefore, in our application, the

environmental conditions were given the first

priority. Also these conditions cannot be controlled

by the farmers. Next from the crops that meet the

environmental conditions farmers can choose the

best cultivars by considering factors such as high

yielding cultivars, the special characteristics of a

crop (e.g. colour, size, shape, flavour, hardiness,

nutritional quality, etc.), maturity and disease

resistance (Decoteau, 2000). These factors come

under farmer consideration because farmer can

decide importance of each of the factors according

to their interests. Based on various crop selection

criteria reviewed earlier we can see that only a few

preferences have been considered. However, in our

application we have included wide range of

preferences because this will help farmers to make

better decisions.

According to the collected information through

interviews with farmers and agricultural specialist in

Sri Lanka, information about what other farmers

grow in different regions and its quantities is also an

important factor when selecting crops because from

this information farmers can get an idea about

whether there is going to be an oversupply or not.

Farmers also consider the market information when

selecting crops; therefore, we take the market

information as a final consideration of our crop

selection criteria.

Finally farmers select the suitable crops and

cultivars by considering all the necessary factors

according to their own context. The following Table

4 provides a summary of the crop selection criteria

reviewed earlier.

We have defined a crop selection module (see

Figure 2) based on our crop selection criteria to

deliver information and knowledge related to crop

selection stage based on information needs of the

farmers. Environment, Crop, Cultivar and Basic

Characteristics are the same information modules

Crop

Basic

Characteristics

Growing Problems

Growing Practices

Fertilizer

Environment

Control Methods

Cultivar

Harvesting

Symptom

Nursery

Management

Post Harvesting

DesigningaFarmerCentredOntologyforSocialLifeNetwork

241

Table 4: Summary of Crop Selection Criteria.

Criteria

(Factors)

Different Sources

Decoteau

(2000)

Bareja

(2012)

CIC

(2012)

Our

Criteria

Environment

   

Farmer types



 



Labour





 

Crop

Characteristics



 



Market

 

 

Farmer

Preferences

limited

range

limited

range

limited

range

wide

range

Security









Other farmers’

information

  



identified in generic crop knowledge module. The

information modules such as Farmer, Farmer Types,

Preferences and Market are additional information

modules needed for the crop selection.

Figure 2: Crop Selection Module.

In this module, we can notice that the farmer is

the central concept and this very much motivated us

in selecting a farmer centred approach to develop

our ontology. Since a cultivar (variety) is a group of

crops that share common qualities, we have

identified a cultivar as a subset of a crop (i.e. a

cultivar is a crop). Types of farmers are classified

based on size of the cultivated farm land and

estimated budget for cultivation. In here

environment is designed with regard to farm

environment and crop environment. In this stage we

do not consider market information as a factor of

crop selection because our initial efforts have

focused only on the static information. Static

information represents data that rarely change over

time while dynamic information such as market

prices changes frequently and hard to obtain without

an elaborate network to gather market data in real

time.

The next step is formulation of a set of informal

competency questions based on the motivation

scenarios. Competency questions determine the

scope of the ontology and use to identify the

contents of the ontology. The ontology should be

able to represent the competency questions using its

terminologies, axioms and definitions. Then,

knowledge-base based on the ontology should be

able to answer these questions (Grüninger and Fox,

1995). These questions are benchmarks in the sense

that the ontology is necessary and sufficient to

satisfy the requirements specified by the competency

questions (Fox et al., 1996). Therefore, formulation

of the competency questions is a very important step

because these questions guide the development of

the ontology. Also as indicated in Fernández-López

(1999), the techniques for formulating the

competency questions are not mentioned in the

Grüninger and Fox’s methodology. We therefore

have reviewed the literature to search whether there

is a method to formulate the competency questions

of an ontology.

Fernandes, Guizzardi and Guizzzardi (2011)

have suggested to apply the Tropos methodology

(Bresciani et al., 2004) to formulate the competency

questions. Tropos is an agent-oriented software

engineering methodology. According to the

proposed approach competency questions are

defined to accomplish the goals of the actor.

Systematic analysis of the goals leads to the

understanding what are the objectives involved in an

organizational environment. To satisfy these goals,

the right kind of information is needed, thus, the

competency questions are defined based on this

information need. Since proposed approach is agent-

oriented, it deals with establishing the needs of

stakeholders that are to be solved by software.

Therefore, this approach is not suitable for our

application to model the competency questions.

Thus we had to develop our own approach to

formulate the competency questions. With the help

of the domain experts we first identified the breadth

of information required by farmers. Next based on

earlier identified user context what conditions we

can use to obtain a subset of information that can

satisfy a specific information need of users. Then,

we generate the competency questions on the above

basis as follows:

 covering all information of the farming stages

(e.g. crop selection to selling stage) and its

constraints (restrictions) – it represents the

knowledge needed by the farmers

 farmers’ conditions based on the farmers’

context (e.g. farm environment, farmer types,

farmer preferences and farming stages) – it

provides information in context.

As an example, the Figure 3 shows our basis for

formulating competency questions for crop selection

Farmer

Crop

Basic

Characteristics

Preferences

Environment

Market

Farmer Types

Cultivar

DATA2013-2ndInternationalConferenceonDataManagementTechnologiesandApplications

242

stage.

Figure 3: Basis of Modelling Competency Questions.

On this basis, formulation of competency

questions for crop selection depends on multiple

criteria such as the farmers’ context, general crop

knowledge, crop selection criteria and the farmers’

constraints. This serves as a basis for formulating the

competency questions in a user context because it

satisfies the expressiveness and reasoning

requirements of the ontology. Some examples for

competency questions related to each category of

crop selection are given in Table 5.

Table 5: Competency Questions for Crop Selection Stage.

Suitable crops based on the Environment:

 Which crops are suitable to grow in the

‘LowCountryDryZone’ agro-ecology region?

 Which crop’s cultivars are the most appropriate

for ‘WetZone’ and ‘Maha’ season?

 What are the suitable vegetable crops for

‘UpCountry’, applicable to the ‘Well-drained

Loamy’ soil, and average rainfall > 2000 mm?

Suitable crops based on Preferences of Farmers:

 What are the crops involving in high labour cost?

 What Brinjal’s cultivars are good for the ‘Bacterial

Wilt’ disease?

 What are the crops with high resistance to a

drought?

Suitable crops based on Farmer related Information:

 Which crops have been cultivated by vegetable

farmers and which quantities?

 What is the expected average yield of each

farmer?

 How many farmers are involving in vegetable

farming in ‘UpCountryWetZone’ zone and ‘Maha’

season?

Suitable crops based on Environment, Preferences and

Other Information:

 What is the best Brinjal’s cultivar which is

suitable for ‘DryZone’ and high-resistance to the

‘Bacterial Wilt’ disease?

Note that, when we are providing specific answers to

the questions, additional information related to the

questions can be provided to the farmers. For

example necessary environmental conditions which

are relevant to crops, because this additional

information will also affect their decision-making

process (especially crop selection, applying control

methods and fertilizing).

In order to answer these competency questions,

we need to identify the ontology components. There

are three main ontology components; concepts,

relationships and constraints. Concepts are classes,

entities, sets, collections that represent ideas about

physical or abstract concepts that constitute a

domain. Relationships specify the interaction among

concepts. Constraints capture additional knowledge

about the domain and it can be represented as

axioms (logical expressions that are always true).

In our ontology design, we use the middle-out

strategy to identify the main concepts (Uschold and

Gruninger, 1996). The main advantage of this

approach is that it starts with most important

concepts first. Once the higher level concepts are

defined the specialized and generalized hierarchies

get identified. Thus, these concepts are more likely

to be stable. This results in less re-work and less

overall effort.

There are few concepts which we can directly

elicit, for instance, we have identified Farmer as a

main concept of our ontology based on scope of the

ontology (i.e. represent agricultural knowledge for

farmers). We also identified Crop as a major concept

of this application. Next, we need to identify other

major concepts by analysing each competency

question.

For example: Which crops are suitable to grow

in the ‘LowCountryDryZone’ agro-ecology region?

The main concept of this query is Zone. Then we

need to define specialized and generalized (if

necessary) hierarchies based on the following

criteria:

 concept properties,

 nature of the instances (instances are used for

denoting specific members of a concept and

represented by constants or variables),

 generic crop knowledge structure, and

 the farmers’ context.

To represent the information in context we need

to identify the details of each concept in multiple

levels. Therefore, designing this type of ontology is

an extremely complex task. It needs to be done in a

very systematic way.

The concept Zone has properties such as

maximum rainfall and minimum rainfall. By

Farmer

Context

Generic

Crop Knowledge

Crop

Selection Criteria

Competency Questions

Additional

Information Modules

DesigningaFarmerCentredOntologyforSocialLifeNetwork

243

specializing Zone concept we have defined the

concept AgroZone (agro-ecology zone) as a subclass

of Zone, because there are several additional

properties specific to AgroZone such as maximum

and minimum temperature, and maximum and

minimum elevation. The properties of concept Zone

can be inherited by the AgroZone concept because

of the taxonomic hierarchy (is_a). AgroZone is a

subclass of Zone if and only if every instance of

AgroZone is also an instance of Zone.

Based on the definition of concept Zone (see

Table 8), we can categorize the instances as

DryZone, IntermediateZone and WetZone if there is

no further categorization (has only first level

categorization). To reduce complexity of the design

of the ontology, we restrict first level categorization

as a property of a concept (e.g. ConceptType). Then

Zone concept has three properties such as

ZoneType, maximum and minimum rainfall. In the

same manner, crops can be categorized based on the

types of crops such as vegetable, fruit, spices, onion,

chilly and a number of other tuber crops, grains, etc.

We define CropType as a property of a Crop. The

Table 6 shows few concepts and their properties

related to the crop selection stage.

Table 6: Concepts, Sub-concepts and Properties related to

Crop Selection.

Concept

Zone

AgroZone

Elevation

Season

SoilType

Crop

Cultivar

Farmer

Fertilizer

ControlM

ethod

Properties

ZoneType, MinimumRainfall,

MaximumRainfall

MaximumElevation, MinimumElevation,

MaximumTemperature, MinimumTemperature

ElevationType, MaximumElevation,

MinimumElevation

StartMonth, EndMonth

PhValue, Moisture, Nutrition, Texture,

Drainage, EdaphicProblem

CropType, Hardiness, Nutrition,

SpecialCharacteristics

Length, Colour, Shape, Flavour, Size, Quality,

Weight, DiseaseResistance,

DiseaseResistanceRate, DroughtResistance,

DroughtResistanceRate

SizeOfFarmLand, BudgetForCultivation,

MaxWorkers

FertilizerType, TimeOfApplication, Source,

ApplicationMethod, Quantity, Cost

MethodType, ApplicationMethod, Source,

TimeOfApplication, Quantity, Cost

In farmer-centric view, farmers need to retrieve

the agricultural information with respect to their

preferences, needs and their situation. Here farmer

can be grouped into two main categories such as

garden farmers and commercial farmers based on

size of the cultivated farm land and estimated budget

for cultivation. Commercial farmers can be further

categorised as small-scale farmers, medium-scale

farmers and large-scale farmers. Since there is a

more than one level categorisation, we have

organised this categorisation as a taxonomic

organisation (e.g. is_a relation not as a

ConceptType).

The associative relationships (non-taxonomic)

are specified as follows:

 identify the concepts and relationships with

meaningful relations,

 define the relationships and its inverse

relationships (if applicable).

For example, there is an associative relationship

with inverse relationship between Crop and Cultivar:

Crop hasCultivar Cultivar, Cultivar isCultivarOf

Crop (see Figure 4). The Table 7 shows some

relationships including associative relationships with

inverse.

Table 7: Associative Relationships with Inverse.

Concept

Crop

Disease

Crop

Disease

Farmer

Relationship

hasCultivar, isCultivarOf

hasSymptom,

isSymptomOf

isAffectedBy , affects

isCausedBy, causes

isControlledBy, controls

cultivates, isCultivatedBy

Concept

Cultivar

Symptom

Disease

Cause

Dise.ConMethod

Crop

Based on our analysis, Crop has main properties

such as Crop Type, Hardiness, Nutrition and Special

Characteristics. Since Cultivar is a subclass of Crop

these properties can be inherited. Other than these

properties Cultivars has properties such as Length,

Colour, Shape, Flavour, Size, Quality, Weight,

Disease Resistance and its Resistance Rate, and

Drought Resistance and its Rate. We have paid

special attention to properties specific to Cultivars

because, when selecting crops the farmers primarily

consider basic features of a Cultivar not a Crop.

Figure 4: Relationships about Environment Concept.

hasFarmEnvironment dependsOn isCultivarOf

hasCultivar

is-a is-a is-a is-a

is-a

Crop Farme

EnvironmentalFacto

Cultiva

ZonElevatio

Soil

Temperatur

…

AgroZon

DATA2013-2ndInternationalConferenceonDataManagementTechnologiesandApplications

244

Figure 4 represents how EnvironmentalFactor

relates to Farmer and Crop; hasFarmEnviornment

and dependsOn respectively. We have defined the

environmental factors to be Zone, Elevation, Soil,

Temperature, etc. which are subclasses of the

EnvironmentalFactor (superclass) because in our

application the union of these subclasses form the

environmental factors which need to be specified for

instances of crops as well as for farms. Since

AgroZone is a subclass of Zone, then AgroZone is

also subclass of EnvironmentalFactor. In here we

have used the subclasses as a set of mutually-disjoint

classes which covers EnvironmentalFactor. Every

instance of EnvironmentalFactor is an instance of

exactly one of the subclasses in the union.

Once the hierarchies and relationships have been

identified, the next step is to define the informal

competency questions (CQ) in a formal way using

formal terminologies. Few examples are given

below.

Note that, here we use unary predicates for

representing concepts, binary predicates for

properties and binary relationships. The

interpretation of C(x) is that x is individual belongs

to concept C.

CQ: Which crops are suitable to grow in the

‘LowCountryDryZone’ agro-ecology region?

Query 1:

x)(Crop(x)) 

(AgroZone(LowCountryDryZone))  dependsOn(x,

LowCountryDryZone);

CQ: What Brinjal’s cultivars are good for

‘Bacterial Wilt’ disease?

Query 2:

x) (Cultivar(x))  Crop(Brinjal) 

hasCultivar(Brinjal,x) isCultivarOf(x,Brinjal) 

isAffectedBy(x,BacterialWilt))

affects(BacterialWilt,x));

CQ: What is the best Brinjal’s cultivar which is

suitable for ‘DryZone’ and high-resistance to the

‘Bacterial Wilt’ disease?

Query 3:

x) (Cultivar(x)) (Crop(Brinjal))

isCultivarOf(x,Brinjal)  hasCultivar(Brinjal,x) 

hasDiseaseResistance(x,BacterialWilt) 

hasDiseaseResistanceRate(x,high)  (Zone(z)) 

dependsOn(x, z) hasZoneType(z,DryZone);

To perform above queries, definitions of the

terms and constrains in their interpretation are

specified using set of axioms in first-order logic.

Here we have defined the axioms to express these

definitions and constraints. The Table 8 shows some

of the axioms used to represent above queries.

Table 8: Formal Axioms.

Express main climate zones in Sri Lanka based on

annual rainfall (in mm):

 x (Zone(x) (y Integer(y) 

avgAnnualRainfall(x,y) (y<1750)) ↔

DryZone(x));

 x (Zone(x)  (y Integer(y) 

avgAnnualRainfall(x,y)  (1750

y2500))↔

IntermediateZone(x));

 x (Zone(x)  (y Integer(y)

avgAnnualRainfall(x,y)  (2500<y)) ↔

WetZone(x));

Express main farmer types based on his/her cultivated

land area:

 x (Farmer(x )(y Integer(y)sizeOf

FarmLand(x,y)(y<35))↔ SmallFarmer(x) ˅

GardenFarmer(x) );

 x(Farmer(x )(y Integer(y)

sizeOfFarmLand(x,y) (y>35)  (z

Integer(z)maxWorkers(x,z) (z>12))↔

LargeFarmer(x) ˅ CommercialFarmer(x));

Express the planted land types according to elevation in

meters:

 x(Elevation(x) (y Integer(y)

maxElevation(x,y) (y<600) ↔ LowLand(x) ˅

Pahatharata(x) ˅ LowCountry(x));

 x(Elevation(x)(y Integer(y)

maxElevation(x,y)(y<1200)( z Integer(z)

minElevation(x,z)(600<z)↔ MidLand(x) ˅

Medarata(x) ˅ MidCountry(x));

 x (Elevation(x )(y Integer(y)

minElevation(x,y)(y>1200) ↔ HighLand(x) ˅

Udarata(x) ˅ UpCountry(x));

In this ontology, inference capability is to be

represented by using inheritance and the first-order

logic based axioms, i.e. it refers to the implicit

knowledge derived from the ontology when

reasoning procedures are applied to the ontology.

3 GENERALISING APPROACH

We have now generalised the specific approach that

was first developed to create a farmer centric

ontology for Social Life Networks. The Figure 5

shows the generalised approach. According to this

approach, we first identify a set of questions that

reflect various motivation scenarios. Next we create

a model to represent user context. Then derive the

competency questions incorporating user context

with generic knowledge module. This step is a new

contribution we have made in this paper. These

competency questions are used to identify the

concepts, relationships and axioms to develop the

ontology.

DesigningaFarmerCentredOntologyforSocialLifeNetwork

245

Figure 5: Our Ontology Design Framework.

Using this framework, we can extend the

ontology for different scenario problems. For

example, when answering scenario question like

“Which are the most suitable control methods to a

particular disease?” we need to take into account

suitable criteria for selecting control methods and

farmers’ context. Then we can formulate the

competency questions based on this systematic

approach. These competency questions drive

development of the ontology and can represent

contextual information by satisfying user needs.

4 FIELD TESTING

A Mobile based application was developed to

provide information to farmers using this ontology

(De Silva et al., 2013). The ontology that we

developed for crop selection phase was tested with a

group of 32 farmers in Sri Lanka. These farmers

were selected with the help of Agriculture extension

officers from Matale District in Sri Lanka. In this

district high percentages of people are involved in

cultivating wide range of vegetables. The evaluation

study comprised of a demonstration session where

farmers were given a brief introduction to the

research project and what is expected from them.

First a training session was carried out to make

farmers familiar with the touch screen technology.

Next the crop selection prototype shown in Figure 6

was demonstrated while illustrating the key features

incorporated into the application. Crop selection

provides a list of crops that grow in the region based

on farm location and farmer preferences.

Figure 6: List of Crops related to Crop Selection.

After farmers used the application to select a

crop that they want to grow they were asked the

question “Is all information for the crop selection

stage provided”. They recorded the answer on a 1 to

5 Likert scale; strongly agree, agree, moderately

agree, disagree, strongly disagree. The responses 7%

strongly agree, 57% agree and 36% moderately

agree. The farmers also suggested few areas where

they would like to get more information.

5 CONCLUSIONS

In this paper we have presented a novel approach to

derive the competency questions incorporating user

context. These competency questions were used to

identify the concepts, relationships and axioms to

develop the ontology.

Overall objective of this research project is to

design an ontology to cover all stages of farming

lifecycle and to provide agricultural information and

knowledge to framers in their own context.

Designing this type of ontology is not a simple task,

because it depends on many factors. In this paper we

have briefly explained how we designed the

ontology for the crop selection stage. For this we

had to extend the ontology to incorporate user

Motivation Scenario

Information/Knowledge on the Literature and

Outcomes of Interviews with Farmers/Experts

Generic Crop

Knowled

analysing

gathered

information

Com

etenc

uestions

Main Ontolo

Com

onents

ecialization/Generalization

Classification

Farmers’ Context Criteria

Axioms

Ontolo

DATA2013-2ndInternationalConferenceonDataManagementTechnologiesandApplications

246

context. Based on the techniques that we discovered,

we developed a generalised framework for ontology

design that can be used to create knowledge

repositories which are capable of providing

information according to user context.

ACKNOWLEDGEMENTS

We acknowledge the financial assistance provided to

carry out this research work by the HRD Program of

the HETC project of the Ministry of higher

Education, Sri Lanka.

REFERENCES

Babu, S. C., Glendenning, C. J., Asenso-Okyere, K.,

Govindarajan, S. K., 2012. Farmers’ Information

Needs and Search Behaviors: Case study in Tamil

Nadu, India. Discussion paper.

Bareja, B. G. 2012. Crop Farming. Available from:

http://www.cropsreview.com/index.html [Accessed

December 2012].

Bresciani, P., Giorgini, P., Giunchiglia, F., Mylopouloset,

J., Perini, A., 2004. Tropos: An Agent-Oriented

Software Development Methodology. In International

Journal of Autonomous Agents and Multi Agent

Systems, 8(3), p. 203-236.

CIC (Private Sector) 2012. Available from:

http://www.navagoviya.org [Accessed May 2012].

De Silva, L. N. C., Goonetillake, J. S., Wikramanayake, G.

N., Ginige, A., 2012. Towards using ICT to Enhance

Flow of Information to aid Farmer Sustainability in Sri

Lanka. In 23rd Australasian Conference on

Information Systems. Geelong, Australia.

De Silva, L. N. C., Goonetillake, J. S., Wikramanayake, G.

N., Ginige, A., 2013. Farmer Response towards the

Initial Agriculture Information Dissemination Mobile

Prototype. In 2013 International Conference on

Computational Science and its Applications. Vietnam.

Decoteau, D. R., 2000. Vegetable Crops, Prentice- Hall,

Upper Saddle River, New Jersey.

Fernandes, P. C. B., Guizzardi, R. S. S., Guizzzardi, G.,

2011. Using Goal Modeling to Capture Competency

Questions in Ontology-based Systems. In Journal of

Information and Data Management, 2(3), p. 527-540.

Fernández-López, M., 1999. Overview of Methodologies

for Building Ontologies. In IJCAI-99 workshop on

Ontologies and Problem-Solving Methods. Sweden.

Fernández-López, M., Gómez-Pérez, A., 2002. Overview

and analysis of methodologies for building ontologies.

The Knowledge Engineering Review, 17(2),p.129-156.

Fox, M. S., Barbuceanu, M., Gruninger, M., 1996. An

organisation ontology for enterprise modeling:

Preliminary concepts for linking structure and

behaviour. Computers in Industry, 29, p. 123-134.

Glendenning, C. J., Babu, S. C., Asenso-Okyere, K., 2010.

Review of Agriculture Extension in India:Are Farmers'

Information Needs Being Met? International Food

Policy Research Institute. Discussion paper.

Gruber T. R., 1993. A Translation Approach to Portable

Ontology Specifications. In Technical Report KSL 92-

71, Knowledge System Laboratory. California.

Gruber, T. R., 1995. Toward principles for the design of

ontologies used for knowledge sharing. In

International Journal of Human-Computer Studies,

43, p. 907–928.

Grüninger, M., Fox, M. S., 1995. Methodology for the

Design and Evaluation of Ontologies. In Workshop on

Basic Ontological Issues in Knowledge Sharing,

IJCAI-95. Montreal, Canada.

Kawtrakul, A., 2012. Ontology engineering and

knowledge services for agriculture domain. In Journal

of Integrative Agriculture, 11(5), p. 741-751.

Lokanathan, S., Kapugama, N., 2012. Smallholders and

Micro-enterprises in Agriculture: Information needs

and communication patterns. LIRNEasia, Colombo,

Sri Lanka, p. 1-48.

Rumbaugh, J., Blaha, M., Premerlani, W., Eddy, F.,

Lorensen, W., 1991. Object-Oriented Modeling and

Design. Prentice-Hall Inc.

Thunkijjanukij, A., 2009. Ontology development for

Agricultural research Knowledge Management: a case

study for Thai rice. Thesis(PhD), Kasetsart University.

Uschold, M., Gruninger, M., 1996. ONTOLOGIES:

Principles, Methods and Applications. In Knowledge

Engineering Review, 11(2), p. 93-155.

Walisadeera, A. I., Wikramanayake, G. N., Ginige, A.,

2013. An Ontological Approach to Meet Information

Needs of Farmers in Sri Lanka. In 2013 International

Conference on Computational Science and its

Applications. Vietnam.

DesigningaFarmerCentredOntologyforSocialLifeNetwork

247