Integration of Multi Criteria Analysis ICAASE'2014 Methods to a Spatio Temporal Decision Support System for Epidemiological Monitoring Integration of Multi Criteria Analysis Methods to a Spatio Temporal Decision Support System for Epidemiological Monitoring Farah Amina Zemri Djamila Hamdadou LIO Laboratory LIO Laboratory BP 1524 EL M’ Naouer, Oran University, Algeria BP 1524 EL M’ Naouer, Oran University, Algeria zemriamina@gmail.com dzhamdadoud@yahoo.fr Abstract – The present study aims to integrate Multi Criteria Analysis Methods (MCAM) to a decision support system based on SOLAP technology, modeled and implemented in other work. The current research evaluates on the one part the benefits of SOLAP in detection and location of epidemics outbreaks and discovers on another part the advantages of multi criteria analysis methods in the assessment of health risk threatening the populations in the presence of the risk (presence of infectious cases) and the vulnerability of the population (density, socio-economic level, Habitat Type, climate...) all that, in one coherent and transparent integrated decision-making platform. We seek to provide further explanation of the real factors responsible for the spread of epidemics and its emergence or reemergence. In the end, our study will lead to the automatic generation of a risk map which gives a classification of epidemics outbreaks to facilitate intervention in order of priority. Keywords – Multi criteria Analysis Decision Support (MCAM), Spatial Data Mining (SDM), Spatial on Line Analysis Processing (SOLAP), Data warehouse (DW), Epidemiological Surveillance (SE). devoted to the PROMETHEE method tool used for the development of multi criteria decision 1. INTRODUCTION support system suggested. A real case study which is a first validation step of our proposed Epidemic prevention is a public health concern. approach is detailed in section 8 and finally, we It is a real challenge. Identification of residential conclude our discussion in Section 9, giving areas (urban and non-urban) exposed to some perspectives. epidemics would help in riding of these phenomena of public health with prevention strategy and careful management. The medical 2. PROBLEMATIC AND CONTRIBUTION management of these diseases would be more effective. The use of information technologies Business intelligence provides new solutions for greatly facilitates the realization of such modeling, querying and visualization of data in objective. In order to identify a good prevention an objective decision support. Multidimensional strategy against epidemics and to ensure a or hyper-cube models allow structuring the data reflect management of propagation for policy analysis by clarifying the notion of phenomenon, a good epidemiological dimension. surveillance system must be developed for The integration of spatial data into OLAP monitoring of the disease and identifying areas systems is a major challenge. Indeed, with epidemics outbreaks. geographic information is frequently present The article describes in section 2 our implicitly or explicitly in the data, but generally contribution. In section 3, the main works in the under-used in the decision making process. field of spatial decision support using MCAM are Coupling OLAP systems and Geographical presented. Section 4 describes, EPISOLAP Information Systems in Spatial OLAP (SOLAP) system and the proposed approach is illustrated systems is promising. We believe that the in details in section 5. Multi Criteria formulation combination of SOLAP technology once problem is given in section 6 and section 7 is designed and implemented with Multi Criteria International Conference on Advanced Aspects of Software Engineering ICAASE, November, 2-4, 2014, Constantine, Algeria. 116 Integration of Multi Criteria Analysis ICAASE'2014 Methods to a Spatio Temporal Decision Support System for Epidemiological Monitoring Analysis Methods (MCAM) is an interesting surveillance data identified in different voice because it can lead to richer data analysis. specialized health structures. 3. RELATED WORKS In the context of single-actor decision support, several decision support systems in TP (Territory Planning) caught our attention. In [3], the system MEDUSAT is proposed for locating the site of a waste treatment plant in Tunisia. MEDUSAT combines a GIS tool allowing creation of homogenous areas determined from spatial data and common land (constituting a similarity index); these areas constitute the set of actions which are then processed by Multi Criteria Analysis Methods (MCAM). The author in [5] proposed a decision process for water management in urban environment and in [6]; authors presented some tools for decision support in local communities in order to address water management problems. In [7], Multi Criteria analysis was used as a tool for decision making for spatial localization of areas under heavy human pressure, a case study of the department of Naama in Algeria was presented in the same work. Various decision support systems rich in spatial tools and Multi Criteria Analysis Methods were developed for management and decision making in territorial problems (water, air, natural areas, transportation, energy, waste, health planning, risk management, . . . ) [13]. Figure 1: Decision Support System in All these systems integrate in various levels Epidemiological Monitoring “EPISOLAP” multi criteria analysis tools coupled with GIS, but The analysis is done by SOLAP tool, but it is they consider criteria as independent and unable limited to alphanumeric data and does not to model any interaction between them exploit the geographical location and the link (interchangeability, correlation, preferential neighborhood. Our current work aims to emerge dependence . . .). In [14], we have already from all these data, the relevant structures of the discussed significantly the inclusion of health risk that can support the effort of correlation criteria, in the MCDA methods, surveillance, direct action eradication and particularly”ELECTRE TRI”, by introducing the strengthen the system of prevention. Choquet integral (instead of the arithmetic sum) More specifically, it is also spending limits of as an aggregation operator. In [9], the main "EPISOLAP" and integrate the spatial nature of objective is to develop a decision support the data (here the epidemic outbreaks) and the system, for itinerary road modification in the interaction with the geographical environment case of hazardous materials transport. In [10], a especially that this is a disease (Tuberculosis) multicriteria decision support system for which is rapidly spreading (or the concept of industrial diagnosis was developed. neighborly relations is very important) allowing, in this application example, to explain and 4. DESCRIPTION OF EPISOLAP SYSTEM predict health risks threatening the population, taking into account their geographical context. The study that was conducted by our previous We show in Figure 2 some results obtained from works in "EPISOLAP” project [8] aimed to the analysis of surveillance data by EPISOLAP identify and predict the health risk according to system. International Conference on Advanced Aspects of Software Engineering ICAASE, November, 2-4, 2014, Constantine, Algeria. 117 Integration of Multi Criteria Analysis ICAASE'2014 Methods to a Spatio Temporal Decision Support System for Epidemiological Monitoring  The role of MCAM is the classification of disease outbreaks to facilitate intervention in order of priority. Our objective is to model the problem of epidemiological surveillance to a Multi criteria problem taking into account the various criteria affecting the spread of the disease. 6. MULTI CRITERIA FORMULATION PROBLEM Figure 2: Geo location and Map Display on SQL The proposed decisional model based on Multi server 2012 & ArcGis 10.0 Criteria Decision support is largely inspired from that proposed in [8] A: Number of cases per municipality B: Incidence rates by age and municipality 6.1 The structuring phase C: Incidence rate per municipality D: Incidence Rates by Type of TB and municipality. This first phase aims to identify the problem (geographical location of study area using the GIS, identification of different criteria) and the 5. OUR CONTRIBUTION basic choices on how to approach it. This phase aims, also, to formalize two basic elements of In the present study, we began a new SOLAP the decisional situation: formulation which aims to integrate Multi criteria analysis methods to answer to the requirements  Identify actions: the identification of all of epidemiological surveillance and to the most the potential actions is a very significant boring questions of decision makers in public step in any decision support approach, health, allowing them to prevent the emergence especially when the multi-criteria of new epidemics outbreaks (prediction) and analysis method proceeds by partial taking into account the socio-environmental aggregation. It is very important that the factors favoring contamination. set of all the actions is complete because its modification during the The "EPISOLAP" system had as main objective analysis can cause a recurrence of the detection and localization of disease multi-criteria analysis. outbreaks; it remains to know which outbreaks are the most at-risk; we therefore proposed a  Identify criteria: the list of criteria classification of these outbreaks using different obtained by aggregating the criteria which fall in the identification of health corresponding factors (sub-criteria) risk. We study the possibility of integration of should be as complete as possible. multi-criteria analysis methods that are formal These criteria must be related to methods that have proven their efficiency in constraints and objectives used in the space and have demonstrated their ability to generation activities. The family of the identify spatial problems. These methods have most relevant criteria must verify the been applied in different studies conducted in conditions of exhaustively, consistency our team for a decade and in different fields and independence. (Transport, Planning territory, Production Management and Industrial domain) where we 6.2 The operational phase come the idea of designing a spatial decision This second phase is the analytical process of support system based on the integration of the study. Its two main objectives are the SOLAP technology and Multi criteria analysis evaluation criteria, then the aggregation of this methods whose objective is to identify the information by a multi-criteria analysis exploiting epidemiological spread phenomenon and make the multi-criteria methods of classification it controlled problem consequently increased namely (PROMETHEE family methods). and effective epidemiological surveillance.  The role of SOLAP would be the location of outbreaks of epidemics. International Conference on Advanced Aspects of Software Engineering ICAASE, November, 2-4, 2014, Constantine, Algeria. 118 Integration of Multi Criteria Analysis ICAASE'2014 Methods to a Spatio Temporal Decision Support System for Epidemiological Monitoring 6.3 The implementation phase 7. PROMETHEE MULTI CRITERIA METHOD This third phase is primarily the result of social The multi-criteria analysis method PROMETHEE acceptance. However, it also includes the (Preference Ranking Organisation Method for implementation of the decision and the control of Enrichment Evaluations) [11] treats a γ problem. this implementation. The main phases and The main advantages of PROMETHEE are: stages of the proposed model are designed in Figure 3.  The simplicity and intuitive aspect of the method  The power of its preference function  The simplicity of the operating phase of the method The method PROMETHEE I provides the user with a ranking of different actions (outbreaks). The problem is that this method does not classify all actions. Some actions may remain unmatched. PROMETHEE II method allows removing this incomparability. The principle of this method is to establish a numerical process of comparing each action relative to all other actions. Thus, it is possible to calculate more (merit) or less (demerit) of each action compared to all others. The result of this comparison allows the orderly classification of actions. The implementation of the method can Figure 3: The proposed decisional model [4] be reduced to perform the following three steps: The functional architecture of the proposed 7.1 Choice of generalized criteria Decision Support System based on MCAM is each criterion C1, C2 ... Cm be associated with illustrated on the flow chart of figure 4. a generalized criterion chosen based on a preference function and scale effects are eliminated. 7.2 Determination of an outranking relation in a second phase, it is necessary to determine a relationship outranking through a preference index that quantifies the preferences of the decision maker. The preference intensity is calculated as follows: p (d) = 0 if d qj, p(d) = (d-qj) / (pj, qj) if qj