Chapter 6: Knowledge Acquisition and Its Process

133-154

The chapter presents the knowledge acquisition process of the

JESS based Expert System for Rice Plant Disease Diagnosis: Ph.D. Thesis: Kh. Robindro Singh:
Department of Computer Science, Gauhati University, 2013 133
 Knowledge Acquisition and Its Process

Knowledge Acquisition and Its Process

6.1. Knowledge Acquisition

Knowledge acquisition is the process to extract structure and

organize the knowledge from various sources of human experts and

is also consider as the process of adding new knowledge and to

change which was anonymously acquired to the knowledge base. It is

mainly used in the system development. The purpose of knowledge

acquisition is to elaborate the capability of the system to improve the

specific task of the performance consisting of facts, rules, concepts,

procedures, heuristics, formulas, relationships or other useful

information [80].

Knowledge acquisition process facilitates the assimilation of

knowledge and experiences of different specialties. For example, an

agricultural diagnostic expert system requires the integration of

specialists in various fields such as nutrition, plant pathology,

entomology, breading, and production. When problem occurs, the

system can help the user more efficiently in identifying the cause of

the problem. It then helps in consulting a document that handles a

specific problem [35].

JESS based Expert System for Rice Plant Disease Diagnosis: Ph.D. Thesis: Kh. Robindro Singh:
Department of Computer Science, Gauhati University, 2013 134
 Knowledge Acquisition and Its Process

The existing knowledge and newly acquired knowledge should

be incorporated in a significant way to draw inferences from resultant

body of knowledge which will be effective and many of the important

conclusions for which the systems can be intended. The knowledge

should be accurate, non-redundant, consistent, non-contradictory and

fairly complete in the sense that it will be possible to rely reasonably.

6.2. Issues in Knowledge Acquisition

Knowledge acquisition of an expert system is a crucial part of

the knowledge engineering of the system which is the difficult part of

the expert system development and also time consuming. The

knowledge contained in the system determines the effectiveness of

the expert system. It is the process of gathering relevant information

from an expert about a specific domain. Therefore, one of the

pronominal issues in the knowledge acquisition process of an expert

system development is the domain specific expert of the system [81].

Identifying the domain expert is very essential as the experts had an

immense knowledge in the specified domain. The knowledge engineer

of the system must ensure that the identified domain expert is

unquestionably an expert in his/her domain area. If the identified

expert is not a perfect expert in his/her domain or does not possess

the satisfactory expertise needed, the acquired knowledge may be

rudimentary which may lead the expert system failure.

JESS based Expert System for Rice Plant Disease Diagnosis: Ph.D. Thesis: Kh. Robindro Singh:
Department of Computer Science, Gauhati University, 2013 135
 Knowledge Acquisition and Its Process

Another issue which focalizes in knowledge acquisition is the

availability of the expert throughout the process of the system

design, explicitly the verification and validation process. Imparting

the knowledge and expertise truthfully of the consenting domain

expert also became a cardinal issue. Even though expert agreed in

serving but they may keep hold the information which may precede

the expert system discredit by the users. Sometimes withdrawal of

the domain expert became threatening issues in the knowledge

acquisition for various reasons such as conflict with their work, time

constraints, or loss of interests. During the development process of

the expert system, substituting of an expert may not only decelerate

result in inconsistencies, redundancies, and incompleteness. Some of

the issues which arise in the knowledge acquisition that add to the

complexity of the knowledge acquisition from the experts are:

imperfect articulation knowledge; lack of time and unwillingness to

cooperate; complication of testing and refining knowledge;

inadequate knowledge elicitation methods; collect knowledge from

one source ; incomplete collection of knowledge documents ; lack of

recognizing specific knowledge when mixed up with irrelevant data;

change of behaviour when observed or interviewed and affecting

knowledge engineer and the expert due to Problematic interpersonal

communication [82].

JESS based Expert System for Rice Plant Disease Diagnosis: Ph.D. Thesis: Kh. Robindro Singh:
Department of Computer Science, Gauhati University, 2013 136
 Knowledge Acquisition and Its Process

6.3. Selection of Domain Area and Its Expert

Knowledge Acquisition is the process by which expert system

developers find the knowledge where domain experts use to perform

the task of interest. The knowledge acquired is then implemented to

form an expert system. The essential part of an expert system is its

knowledge. Therefore, knowledge acquisition is probably the most

important task in the development of an expert system. Hence, the

selection of an appropriate domain and its expert of the system are

very important in the knowledge acquisition of the system.

6.3.1. Selecting Domain

Selecting an appropriate domain for the expert system

development is one of the important criterions of the knowledge

acquisition. The domain should be such that the expert system does

not have to perform the entire task to be useful. Some degree of

incomplete coverage can be tolerated. In this way, the expert system

development process can be started by developing a system to cover

one sub domain and then expand by adding other sub domains. This

method of development allows the knowledge acquisition for a large

domain to be focused on one sub domain at a time [83, 84].

The domain should be fairly stable for the long validity of the

system. An unstable domain can yield a situation where a large

JESS based Expert System for Rice Plant Disease Diagnosis: Ph.D. Thesis: Kh. Robindro Singh:
Department of Computer Science, Gauhati University, 2013 137
 Knowledge Acquisition and Its Process

number of knowledge structures found early in the knowledge

acquisition and are no longer valid but cannot easily be changed

without redoing a major part of the knowledge acquisition process.

6.3.2. Selecting a Domain Expert and its importance

A domain expert is the source of knowledge for the expert

system. Therefore, even before the actual process of knowledge

acquisition begins, a decision crucial to its success must be made: the

choice of the project's expert(s). Because of the significance of this

decision, among the important criteria for selecting an appropriate

expert system domain are considerations related to the choice of a

domain expert. These considerations primarily relate to the degree

that the expert will function well in the role of knowledge source.

Significant time and effort is needed to select an expert as

knowledge acquisition is critical to the overall expert system

development. The selection of an appropriate expert is an important

element in the knowledge acquisition. The expert must have enough

experience to be able to develop the domain insights that result in

heuristics. These heuristics most distinguish the knowledge in an

expert system from that in a conventional program and are in the

main goal of the knowledge acquisition process. An expert should be

introspective, able to describe those reasoning process clearly. The

JESS based Expert System for Rice Plant Disease Diagnosis: Ph.D. Thesis: Kh. Robindro Singh:
Department of Computer Science, Gauhati University, 2013 138
 Knowledge Acquisition and Its Process

expert should be cooperative in the whole process of knowledge

acquisition to get the full effort required for the system [81].

6.4. Techniques on Knowledge Acquisition

Knowledge Acquisition technique is added to the process of

collection, elicitation, interpretation and formalization of the data

concerning to the functioning of expertise in a particular domain.

Reducing the communication gap between the expert and the

knowledge engineer and allowing them to become self-sustaining of

its sources is the main objectives of the knowledge acquisition

technique. It is a crucial component of an expert system and also

time consuming task in gathering the relevant information about the

domain from the specified expert. The aim is to reduce the

communication gap between the domain specific expert and the

knowledge engineer, allowing the knowledge to become independent

of its sources.

Numerous techniques and tools of knowledge acquisition are

present in the expert system development [85]. An Integrated

knowledge acquisition environment describes an integrated

acquisition interface that includes several techniques which are

previously developed to support users in various ways as new

knowledge are added up to the system [86]. Some of the main

JESS based Expert System for Rice Plant Disease Diagnosis: Ph.D. Thesis: Kh. Robindro Singh:
Department of Computer Science, Gauhati University, 2013 139
 Knowledge Acquisition and Its Process

categories in knowledge acquisition techniques are described briefly

as below:

6.4.1. Interviewing

Interviewing is the method of asking questions to the domain

expert about the domain interest and their task performance. The

tools of interviewing can be unstructured, semi-structured, or

structured. The success of an interview session depends on how the

questions are being asked. Difficulties may arise when the interviewer

is not familiar with the domain of which questions to be asked. The

ability of the expert to articulate their knowledge also plays a big role

in the success of the interview. The expert may not remember exactly

how they perform a task, especially the task being performed

automatically. Some interviews used to build a particular type of

model of the task. Therefore, based on information obtained during

the interview, model is built by the knowledge engineer and then

reviewed with domain expert. In some cases, the models can be built

interactively with the expert, especially on the availability of software

tools for model creation [87].

6.4.1.1. Unstructured Interviewing Technique

The most common technique currently used by knowledge

engineers is unstructured interviewing technique which is difficult to

JESS based Expert System for Rice Plant Disease Diagnosis: Ph.D. Thesis: Kh. Robindro Singh:
Department of Computer Science, Gauhati University, 2013 140
 Knowledge Acquisition and Its Process

describe as a true technique because it is wandering conversation

between the expert and the knowledge engineer [88, 89]. But still

unstructured interviewing is an important toolkit in the knowledge

engineering since it allows the greatest possible freedom for

knowledge engineer and expert alike to explore the topic.

Consequently, most of the researchers have documented and

described its usage, although it usually downplays its value as a real

tool. It had been cited that the use of the unstructured interview as

one of the biggest drawback of knowledge engineers who were

attempting to develop expert systems as an anthropological study of

knowledge engineering describes [90].

Many authors have suggested different types of unstructured

interviews used in general surveys of knowledge acquisition

techniques. Ultimately in acute cases, the knowledge engineer

doesn't have a prepared set of detailed questions and the expert does

not have ready replies or information at his/her fingertips. As a

result, the interview taken by the knowledge engineer in the form of

a wandering dialog asking open-ended questions. However, it is

helpful both to get acquainted, the expert and knowledge engineer to

the ideas of artificial intelligence and to learn general ideas about the

problem domain. Hence, it serves the additional purpose of building

an essential rapport between the system developer and the human

source.

JESS based Expert System for Rice Plant Disease Diagnosis: Ph.D. Thesis: Kh. Robindro Singh:
Department of Computer Science, Gauhati University, 2013 141
 Knowledge Acquisition and Its Process

Unfortunately, this has been shown to be a time consuming and

inefficient process and can offend the expert as being a waste of time

[90]. The difficulties of the unstructured interview become apparent

when one views a sample from an actual interview and sees how

inefficient it can be [88, 91, 92].

6.4.1.2. Structured Interviewing Techniques

Recognizing that unstructured interviews are inefficient,

researchers have been developing structured interviewing techniques

for many years [93]. Basically, they provided structure by developing

a carefully pre-planned series of ordered questions. From this work,

other interviewing techniques and tools were developed which were

designed to structure the interview process. This work has been

generally applied to the knowledge elicitation problem. These

techniques can often be applied to situations where the expert is

being interviewed while actually performing a task or where the task

is simulated or reconstructed by case studies or scenarios or simply

from the expert's own past experience.

Elicitation techniques most commonly discussed in the literature

include protocol analysis, repertory grids, prototyping,

multidimensional scaling, cluster analysis, event recall, discourse

analysis, and card sorting [28]. Some rudimentary structuring can be

JESS based Expert System for Rice Plant Disease Diagnosis: Ph.D. Thesis: Kh. Robindro Singh:
Department of Computer Science, Gauhati University, 2013 142
 Knowledge Acquisition and its Process

given to the interview process by having the expert perform a

particular task while the knowledge engineer asks questions freely.

The task may be typical of the problem-solving situation which

the knowledge engineer wishes to explore or it may be a special case

which the knowledge engineer wishes to use to have the expert

refines previously elicited knowledge. The simplest task the

knowledge engineer could give the expert could be to prepare a brief

lecture designed to lay out the main themes and ideas associated

with the particular problem domain. Obviously, this type of task

would be more appropriate for early knowledge acquisition sessions

whereas the special task would be better for when the knowledge

engineer was more familiar with the particular domain [88].

It should be noted that the tasks which are used as the basis

for structuring the interview can be either actual tasks or simulated

tasks. This method of structuring the interview process by using

specific tasks has been termed constrained-processing.

6.4.2. Protocol Analysis

Protocol analysis is one of the most frequently mentioned

elicitation techniques in the knowledge acquisition literature found it

to be second only to unstructured interviews in actual usage [89].

Suggested by Newell and Simon, subjects are asked to think aloud

JESS based Expert System for Rice Plant Disease Diagnosis: Ph.D. Thesis: Kh. Robindro Singh:
Department of Computer Science, Gauhati University, 2013 143
 Knowledge Acquisition and Its Process

while solving a problem or making a decision. These verbalizations

are usually taped and then transcribed and the transcription is

analyzed using a particular coding scheme. The transcript itself is

termed a 'protocol' and may be used to refer to a word-for-word

record or a summary of the major points. Whatever the form of the

protocol, it should enable the knowledge engineer to easily access,

index, and code specific pieces of information.

Depending on the problem domain it may be desirable to

generate motor protocols or even eye-movement protocols to more

clearly understand an expert's performance of a task. Motor protocols

require that the expert's physical movements be closely observed and

noted by the knowledge engineer, which may appropriate for

acquiring certain types of expertise. At an even more subtle level,

noting the movement and visual focus of the eyes of the expert as a

task is being performed may reveal something of the sensory

experience of the expert as he/she performs the task [94].

However, all protocols can be classified as being either

'concurrent' or 'retrospective'. Concurrent protocols are records of the

expert's thought processes at the same time he/she is solving a

problem while retrospective protocols are records of the expert's

review of his/her verbalizations after the task is completed. These are

often used when it is felt that the task of verbalization has interfered

JESS based Expert System for Rice Plant Disease Diagnosis: Ph.D. Thesis: Kh. Robindro Singh:
Department of Computer Science, Gauhati University, 2013 144
 Knowledge Acquisition and Its Process

with the expert's performance of the actual task [95]. The transcript

may in turn be translated by the knowledge engineer into a more

formal protocol which attempts to summarize the major points in a

format designed for easy access.

Once the protocol has been worked into the desired format, the

actual analysis of such a protocol by a knowledge engineer can begin.

The usual method knowledge engineers use is something called

process tracing drawn from cognitive psychology. Analysis involves

breaking down the decision rules used by the expert into typical,

naturally recurring decision rules. These can then be refined further

by either the domain expert or another, external expert before and

after they are implemented in the final system.

While protocol analysis involves little interaction between the

expert and the knowledge engineer, several elicitation techniques

have been suggested which require the knowledge engineer to

actively participate in the problem-solving process. These techniques

capitalize on the idea that the knowledge engineer must become

somewhat of an expert in order to successfully translate the expert's

knowledge into a machine representation. Thus the interview may be

treated as a tutorial where the expert delivers a lecture which the

knowledge engineer may paraphrase or use to solve similar

problems. The knowledge engineer may become even more actively

JESS based Expert System for Rice Plant Disease Diagnosis: Ph.D. Thesis: Kh. Robindro Singh:
Department of Computer Science, Gauhati University, 2013 145
 Knowledge Acquisition and Its Process

involved by playing the role of an apprentice or otherwise

participating in the expert's problem-solving process. Making the

knowledge engineer become like the expert is certainly the most

time-consuming approach to knowledge elicitation but ensures the

highest quality resulting system. The inherent difficulties of requiring

the knowledge engineer to learn all the expertise in order to translate

it into a suitable machine representation are what have motivated

much of the work at designing expert system shells with more

naturalistic interfaces which enable the expert to enter his/her

expertise directly into the system.

6.5. Knowledge Acquisition Process

The identification and understanding the major characteristics

of the problem that we have to solve in the expert system is very

important in the process of knowledge acquisition. The input problem

for our knowledge acquisition process is regarding the diagnosis of

diseases in the rice plant occurring during their life span. There are

many approaches in the process of knowledge acquisition.

The process of knowledge acquisition is described in the system

developed by Shikhar Kr. Sarma, Kh. Robindro Singh and Abhijeet

Singh [77]. The developed system is the application of expert system

in agriculture. "Some Approaches to Knowledge Acquisition" is also an

approach of knowledge acquisition in the development of an expert

JESS based Expert System for Rice Plant Disease Diagnosis: Ph.D. Thesis: Kh. Robindro Singh:
Department of Computer Science, Gauhati University, 2013 146
 Knowledge Acquisition and Its Process

system [97]. Different approaches of knowledge acquisition are

described in their paper.

We have proposed a knowledge acquisition process in the

development of an expert system for diagnosis of rice plant diseases.

The main areas in central modules and experts taking part in the

proposed knowledge acquisition process that require consideration in

ES are Interactive Expert Module for knowledge acquisition,

Coordinating Module for knowledge database, Expert System Program

Module for knowledge formatting, domain specific experts and

contents and Interactive System Expert which are describe as below.

Figure 6.1: Framework of the Knowledge Acquisition Process

6.5.1. Coordinating Module for Knowledge Database

An expert system plays a basic role in replicating a human

expert and replacing it in problem solving activities. To perform this,

JESS based Expert System for Rice Plant Disease Diagnosis: Ph.D. Thesis: Kh. Robindro Singh:
Department of Computer Science, Gauhati University, 2013 147
 Knowledge Acquisition and Its Process

the key information from a human expert must be transferred into

the knowledge database and to the inference engine when

appropriate. The two types of knowledge emerge from the human

expert are: facts and procedural or heuristic information.

Facts include the absolutely known data and the defined

variables that contain any given activity. The if-then logic is picked up

so that the expert would use in any given activity. Expert databases

are developed through a formal knowledge acquisition process which

includes identification, conceptualization, formalization,

implementation, and testing. To extract information from human

expert, we are using the common means of extracting methods like

interviews, transactional tracking, observation, case study, and self-

reporting choices. Expert Systems put together the investigation and

interpretation of data input with specific rules of actions and facts to

arrive at a recommended outcome using programmatic and physical

representation of logic, data and choice.

The knowledge-acquisition module assists in translating

knowledge acquired from experts to the required internal format of

the system and serves as an interface between human expert and

knowledge database. It provides a means for entering domain-

specific knowledge into the knowledge base and revising this when

necessary. It could include a debugging facility to ensure the

JESS based Expert System for Rice Plant Disease Diagnosis: Ph.D. Thesis: Kh. Robindro Singh:
Department of Computer Science, Gauhati University, 2013 148
 Knowledge Acquisition and Its Process

translation of knowledge into the required format and to check

different types of available knowledge representations, e.g. the

production rule system, procedural methods and the declarative

format [98].

The Knowledge Acquisition process are carried out to create the

knowledge database through series of interacting sub modules

integrating with the coordinating module until the best conclusion is

obtained.

The coordinating module for knowledge database has different

set of works and it plays different roles for each module in the

process of acquiring the knowledge from the experts. Since the

knowledge can be acquired from different sources in different

formats. It is the coordinating module which acts as supervisor to all

the knowledge acquiring modules in order to ensure and accept the

knowledge in the standard format which can be further processed to

form the knowledge database of the expert system.

6.5.1.1. Domain Specific Experts and Contents

The domain specific expert and contents are very important in

our proposed knowledge acquisition process. Here, the domain

specific expert and their contents are mainly the human experts and

JESS based Expert System for Rice Plant Disease Diagnosis: Ph.D. Thesis: Kh. Robindro Singh:
Department of Computer Science, Gauhati University, 2013 149
 Knowledge Acquisition and Its Process

standard literatures related to rice plant diseases. The domain specific

expertise knowledge is contained in it.

It provides the fuel for the inference engine where the contents

are composed of facts, records, rules, books, and countless other

resources and materials. They are the absolute values and

documented evidence which are associated with the database

structure. Important parts of the knowledge database are If-then

procedures and pertinent rules. Heuristics use logic to record expert

processing steps and requirements by imitating human ways of

reasoning. Logic, facts, and past experience are gathering together to

make an expert database. As a result knowledge transfer, significant

experiences, skills, and facts are blend in a representation of

expertise. Therefore, knowledge-based information system is

considered as the fuel for the inference engine in which it must be

accurately and reliably conceived, planned, and realized for optimum

performance. The knowledge database must be validated and

confirmed as accurate and reliable. Inaccurate information of expert

databases containing procedural steps result bad advice and

potentially destructive to operate the Expert System [99].

6.5.1.2. Interactive Expert Module

The domain specific expertise knowledge is acquired from the

domain specific experts and their contents in this interactive expert

JESS based Expert System for Rice Plant Disease Diagnosis: Ph.D. Thesis: Kh. Robindro Singh:
Department of Computer Science, Gauhati University, 2013 150
 Knowledge Acquisition and Its Process

module and the acquired knowledge is analysed and then processed

to obtain a best conclusion for the problem. The common problems

related to the rice plant are mostly acquired in this module.

Interactive expert module is associated through countless

potential paths and possibilities based on some combination of rules,

cases, models, or theories such as predicate logic, mimic human

reasoning and offer various mathematical arguments to any query.

Probability with rules and information are synthesized with a decision

tree branching steps and actions to arrive at a recommendation.

Probabilities mirror the human expert's own experience with an

activity or problem. Through a problem-solving exercise in different

ways, models or cases structure some systematic movement. To

simulate human reasoning specific incidents or models of behaviour

uses Case-based reasoning modules [99].

6.5.1.3. Interactive System Expert (IS Expert)

In the above module it has discuss that the processed

knowledge is transferred to the Interactive System Expert to verify

for converting into expert system program which is continued until

the process obtained the best conclusion for the problem

The static analysis of the rules and processed knowledge can

detect many potential problems that exist in a knowledge base. First,

JESS based Expert System for Rice Plant Disease Diagnosis: Ph.D. Thesis: Kh. Robindro Singh:
Department of Computer Science, Gauhati University, 2013 151
 Knowledge Acquisition and Its Process

we identify knowledge base problems that can be detected by

performing an analysis of goal-driven rules and then give definitions

and examples of such problems. Later in this article, we look at how

these definitions must be modified for data-driven rules. Knowledge

base problems can only be detected if the rule syntax is restrictive

enough to allow one to examine two rules and determine whether

situations exist in which both can succeed and whether the results of

applying the two rules are the same, conflicting, or unrelated. In rule

languages that allow an unrestricted syntax, it is difficult or

impossible to implement the algorithms [100].

All these problems of V&V (verification and validation) is taken

care by the IS Expert module in this system model. Only after

properly passed through this filter the knowledge base is passed to

Expert System program module for any reference and condition

checking to put any advice based on this knowledge base.

6.5.1.4. Expert System Program Module

The acquired knowledge in the interactive expert module which

is acquired from domain specific experts and verified by the IS

Experts is transferred to the expert system program module. This

verified knowledge is processed here for converting into expert

system rule for formatting and representing the knowledge into

knowledge base.

JESS based Expert System for Rice Plant Disease Diagnosis: Ph.D. Thesis: Kh. Robindro Singh:
Department of Computer Science, Gauhati University, 2013 152
 Knowledge Acquisition and Its Process

The importance of assuring the quality of expert systems is now

widely recognized. Quality assurance is a major issue in the

development of expert systems. A consensus has been reached in the

literature that the evaluation of expert systems to ensure their

reliability involves two principle activities, usually called verification

and validation. Studies have shown that verification, can lead to the

early detection of errors that otherwise would have remained even

after extensive validation tests. This verification and validation

process is moulded in IS Expert module of the system prototype

[101, 102, 103].

An expert system program module offers to solve a problem by

correctly analysing and identifying with the likelihood of a problem or

disturbance. From the past observation and difficulties inferred,

possible problems where identifies in expert system while presenting

possible advice or solutions. Diagnostic systems typically conclude

causes of problems which are included in the application of a

multitude of narrowly focused problem areas.

Based on the description of the previous situations, interpretive

systems explain observations by inferring their meaning. The expert

system program module takes an interpretive rather than diagnostic

role. The likelihood of being an accurate representation is quantified

as probability of uncertainty. It emphasized as chances of being right.

JESS based Expert System for Rice Plant Disease Diagnosis: Ph.D. Thesis: Kh. Robindro Singh:
Department of Computer Science, Gauhati University, 2013 153
 Knowledge Acquisition and Its Process

In a predictive role, the expert system forecasts future events and an

activity based on past information and in an instructive role, it

teaches and evaluates the successful transfer of education

information back to the user.

For our knowledge acquisition process, expert knowledge has

been acquired from standard literatures related to the rice plants and

an agricultural scientist, Dr. M, Thoithoi Singh, at Krishi Vigyan

Kendra, Thoubal, Manipur and Dr. Kh. Ibohal Singh, Asst. Professor of

Entomology at Central Agricultural University (CAU), Iroisemba,

Imphal, Manipur. "Illustrated guide to integrated pest management in

rice in tropical Asia," by W. H. Reissig, E. A. Heinrichs, J. A. Litsinger,

K. Moody, L. Fiedler, T. W. Mew, and A.T. Barrion is a literature on

rice plant used to get expertise knowledge about rice diseases in the

development of the system [104]. In this book, most of the common

problems related to the rice plant are described. "Diagnosis of

common diseases of rice", by Francisco Elazegui and Zahirul Islam is

also used to acquire knowledge about rice diseases in this expert

system development [105]. The common diseases of rice plant are

found in this book.

JESS based Expert System for Rice Plant Disease Diagnosis: Ph.D. Thesis: Kh. Robindro Singh:
Department of Computer Science, Gauhati University, 2013 154