ABSTRACT
The research work is concerned with Fuzzy Cognitive Maps-based Conflict control Model. The objective of the work was to develop Conflict control model using Fuzzy Cognitive Map (FCM) and Non-liner Hebbian Learning (NHL) that will allows the users (or policy makers) to optimize the environmental factors which are major causative factors of the Tiv-Fulani in other to achieve peace. To achieve the objective, basic factors understood to be influential in Tiv-Fulani conflict were used to form FCM model that represents the conflict situation, while NHL was used to find levels of influences between these environmental factor that will minimize the conflict and maximize peace. Also, causative analyses of some of the factors were carried out in other to know their level of significance to the conflict situation. Soft Systems Methodology (SSM) and Object Oriented Analysis and Design (OOAD) methodology were used in the design of the system, while the system was implemented with Visual Basic.Net (VB.Net). The result of the work showed that keeping certain factors within some threshold and ensuring these factors interact at particular levels will reduce conflict and bring peace.
CHAPTER ONE
INTRODUCTION
1.0 Introduction
Ethnic conflict, communal clashes, terrorism and insurgency are major security challenges in the twenty-first century. These are responsible for the deaths of millions of people around the world. According to [1] and [2], these violent conflicts have occurred more in developing countries of the world, especially Africa.
For Nigeria in particular, who is endowed with several ethnic groups, numerous religious organisations, and diverse culture; conflict has been a continuous occurrence since her emergence as an independent state. These conflicts are of various dimensions – religions, political, ethnic, intra-communal, and inter-community. Of note in this work is the farmer (Tiv) and herdsmen (Fulani) conflict in middle belt (Benue state) of Nigeria.
Of recent, clashes between the farmers and the Fulani herdsmen have become a public concern in Nigeria. According some researchers like [3], this conflict ensued from a number of factors such as: environmental factors, and character, lifestyle, attitude, behaviour, ideology, etc of Fulani herdsmen and their host communities. Several regimes in Nigeria have struggled with this conflict with no success or permanent solution. The most recent measure is the use of military to stop escalation of such conflict any time it turns deadly. But this new measure only provides what is referred to as „false peace‟ in some conflict literatures.
With the end of the cold war, and spurred with increase in the number of conflicts that followed, United Nations initiated the call for development of models for analysing, understanding and preventing conflict. However, the daunting challenge lies in making sense
of large volume of data from past conflicts in other to draw up useful knowledge on conflicts and to control and manage present and future ones [2].
Models are basically abstract representation of the reality or events in a real world. They allow us to have an abstract picture of present situation and a forecast of what the future will looks like. Conflict models consist of mechanisms or standardized procedures for analysis of data on socio-political and armed conflict dynamics in other to forecast or detect early escalation of violence, as well as provide a causal interpretation of the results [4]. The causal interpretations provide understanding of the reasons for the conflict and ways to resolve or control them. These models which are either quantitative or qualitative make use of longer-term, society-wide, structural variables or event-data which are called indicators.
Quantitative models handle conflict as complex interdependencies of nonlinear, interactive and context-dependent factors [5]. They quantify conflict variables and use mathematical techniques to study the trends and to derive models of the relationship between certain factors or variables and occurrence of conflict.
Conflict is an active disagreement between people with opposing opinions or principles which could be violent or non-violent. Common approach to controlling conflict in many nations of the world is the use of military force to suppress it and bring it under control, yet the intensification of many conflicts and the difficulties that security agencies have experienced in many nations in tackling domestic conflict situations shows the inadequacy of this approach. Thus, need to redress this weakness by mathematical, statistical and computational models which can manipulate societal factors to manage and bring conflict under control.
According to [6], Conflict management theorists see violent conflicts as an ineradicable consequence of differences of values and interests within and between people in a society. The propensity to violence arises from existing institutions and historical relationships, as well as from the established distribution of other resources. Resolving such conflicts is viewed as unrealistic: the best that can be done is to manage and control them and occasionally to reach a historic compromise in which violence may be laid aside [6]. Conflict management therefore is the art of appropriate intervention by the powerful actors (especially government) having the power and resources to use various means to influence the conflict domain and conflicting parties in order to induce peace. This is done by engaging and transforming the relationships, interests, discourses, factors and, if necessary, the very constitution of society that supports the continuation of violent conflict [7]. Through this means, conflict is gradually transformed to peace or control, via series of smaller or larger changes by variety of actors that play important roles.
Using conflict control and conflict management interchangeably and adopting the above theoretical approaches, conflict control in this research work employ fuzzy cognitive maps to model conflict, using the environmental factors as inputs; while Nonlinear Hebbian Learning (NHL) provide the mechanism for controlling conflict.
1.1 Statement of the Problem
Nigeria is presently experiencing arise in insurgency, terrorism, and other cases of ethnic and communal conflicts, especially in states like Plateau and Benue. The resultant effects are the destruction of lives and economic losses. But the use of military force to control these conflicts (Tiv-Fulani conflict in Benue state) has not yielded the desired level of success, but rather a false level of peace, with conflict erupting again over time. Hence,
the need for a systematic approach that will use other factor to control and de-escalate violent conflict.
Secondly, on the forecasting side, there are several models of forecasting armed conflict; yet, statistical models seem too weak to handle the interrelationship among the causative factors and inadequate to provide causative explanation for predicted conflict. Also, while there are several forecasting models, very few have attempted to build non-liner models for control of armed conflicts. So this study provides a novel approach through combination of Fuzzy Cognitive Maps (FCM) for handling interrelationships among the causative variables and Nonlinear Hebbian Learning (NHL) for controlling armed conflict.
1.2 Aims and Objectives
The main aim of the project is to derive conflict control model using FCM and NHL. The specific objectives include
Development of conflict control model using FCM and NHL.
Development of software to implement the model
Running a case-based scenario of Tiv-Fulani conflict control.
1.3 Significance of the study
This work has two dimensional significances: firstly, virtually all government intervention is most current insurgency, armed and communal conflicts have been under dangerous and costly circumstances. They apply military force which do not deescalate conflict but rather escalate them. Applying Conflict control models will enable policymakers to minimize military involvement by exploiting other means within the society to control or minimize conflict and maximize peace.
Secondly, the general conflict forecasting models are still plagued with inability to provide causal interpretation for forecasted conflict, the approach use in this work can conveniently provide such support. Also, while there several conflict predictive models, conflict controlling models are rare; therefore, this work will provides a novel approach that can be built upon.
1.4 Scope of the work
The scope of this work covers the development conflict control model using FCM, and NHL and implementation of the model in visual basic .net programming language. Also it also extends to checking the causal influences of the various factor of the model.
1.5 Limitations
The major challenges of this work interpretation of the result and the assignment of the weights of the model. The qualitative nature of fuzzy cognitive map makes it difficult for the numerical interpretation of the result and the complex nature of the conflict domain and fuzzy cognitive maps makes the assignment of the weights a challenging task.
1.6 Definition of Terms
Conflict: Conflict is an escalated competition at any system level between groups whose aim is to gain advantage in the area of power, resources, interests, and needs and at least one of the groups believes that this dimension of the relationship is mutually incompatible
Armed conflict: Armed conflicts are defined as open, armed clashes between two or more centrally organised parties, with continuity between the clashes, in disputes about power over government and territory [8]
Communal conflictCommunal conflict is a violent conflict between nonstate groups that are organised along a shared communal identity. The conflict is considered violent if the parties use violence to gain control over some disputed and perceived indivisible resource, such as a piece of land.
Fuzzy cognitive maps: Fuzzy Cognitive Maps (FCMs) are symbolic representation for the description and modelling of the complex system. Fuzzy Cognitive Maps (FCMs) consist of concept nodes and weighted arcs, which are graphically illustrated as a signed weighted graph with feed-back.
Nonlinear hebbian learning (NHL): The NHL is a machine learning algorithm based on the nonlinear Hebbian-type learning rule that adjusts the weights based on initial experts‟ knowledge, i.e. initial sketch of the map, and additional information on the modelled system expressed by restrictions imposed on some concepts, to derive the connection matrix.
Learning involves updating the strengths of causal links so that FCM converge in a desired region. This is achieved by modifying or fine-tuning its initial causal link or edge strengths through training algorithms until in reach a steady state.
Quantitative conflict studies: The quantitative conflict studies or management is concerned with finding models which can be use to analyse conflict and provide a causal interpretation of the results [9].
This material content is developed to serve as a GUIDE for students to conduct academic research
A1Project Hub Support Team Are Always (24/7) Online To Help You With Your Project
Chat Us on WhatsApp » 09063590000
DO YOU NEED CLARIFICATION? CALL OUR HELP DESK:
09063590000 (Country Code: +234)
YOU CAN REACH OUR SUPPORT TEAM VIA MAIL: [email protected]
09063590000 (Country Code: +234)
