The real time monitoring of environment context aware activities, based on distributed detection, is becoming a standard in public safety and service delivery in a wide range of domains (child and elderly care and supervision, logistics, circulation, and other). The safety of people, goods and premises depends on the prompt immediate reaction to potential hazards identified in real time, at an early stage to engage appropriate control actions. Effective emergency response can be supported only by available and acquired expertise or elaborate collaborative knowledge in the domain of distributed detection that include indoor sensing, tracking and localizing. This research proposes a hybrid conceptual multi-agent framework for the acquisition of collaborative knowledge in dynamic complex context aware environments for distributed detection. This framework has been applied for the design and development of a hybrid intelligent multi-agent decision system (HIDSS) that supports a decentralized active sensing, tracking and localizing strategy, and the deployment and configuration of smart detection devices associated to active sensor nodes wirelessly connected in a network topology to configure, deploy and control ad hoc wireless sensor networks (WSNs). This system, which is based on the interactive use of data, models and knowledge base, has been implemented to support fire detection and control access fusion functions aimed at elaborating: An integrated data model, grouping the building information data and WSN-RFID database, composed of the network configuration and captured data, A virtual layout configuration of the controlled premises, based on using a building information model, A knowledge-based support for the design of generic detection devices, A multi-criteria decision making model for generic detection devices distribution, ad hoc WSNs configuration, clustering and deployment, and Predictive data models for evacuation planning, and fire and evacuation simulation. An evaluation of the system prototype has been carried out to enrich information and knowledge fusion requirements and show the scope of the concepts used in data and process modelling. It has shown the practicability of hybrid solutions grouping generic homogeneous smart detection devices enhanced by heterogeneous support devices in their deployment, forming ad hoc networks that integrate WSNs and radio frequency identification (RFID) technology. The novelty in this work is the web-based support system architecture proposed in this framework that is based on the use of intelligent agent modelling and multi-agent systems, and the decoupling of the processes supporting the multi-sensor data fusion from those supporting different context applications. Although this decoupling is essential to appropriately distribute the different fusion functions, the integration of several dimensions of policy settings for the modelling of knowledge processes, and intelligent and pro-active decision making activities, requires the organisation of interactive fusion functions deployed upstream to a safety and emergency response.

Denna fallstudie syftar till att undersöka effekterna av ett intelligent beslutsstöd på beslutsprocessen i en konsultverksamhet. Vi har utvecklat ett intelligent beslutsstöd och sedan undersökt beslutsprocessen vid kompetensmatchning av konsulter och kundförfrågningar. Vår forskningsfråga är således: Hur kan beslutsprocessen vid kompetensmatchning påverkas av ett intelligent beslutsstöd i en konsultverksamhet? Det finns studier som visar effekten av ett vanligt beslutsstöd och beslutsforskaretror att mer utvecklade beslutsstöd har potential. Dock studeras inte denna typ av intelligent beslutsstöd vanligtvis i kombination med beslutsprocessen. Syftet med studien är att bidra till forskningsläget, på grund av bristen på forskning inom detta område. För att undersöka detta fall behövde vi samla in kvalitativa data, som gjordes med semistrukturerade intervjuer och observationer, före och efter införandet av ett intelligent beslutsstöd. När vi analyserade den insamlade datan användes en kvalitativ innehållsanalys för att hitta teman och kategorier, som vi sedan jämförde resultaten före och efter meden teoretisk referensram. Vi fann att det intelligenta beslutsstödet kunde tillgängliggöra informationen i beslutsprocessen som kunde frigöra tid. Utifrån det kunde tiden istället fokusera på utvärdering. Detta ledde till att beslutsprocessen blev mer rationell i tre av fyra steg. Avslutningsvis fann vi att det intelligenta beslutsstödet hjälpte beslutsprocessen att bli mer rationell. / This case study aims to investigate the impact of an intelligent decision support system on the decisionmaking in a consulting firm. We have developed an intelligent decision support system and then investigated the decision-making when competence matching consultants and customer requests. Thus, our research question: How can the decision-making process when competence matching be affected by an intelligent decision support system in a consulting business? Studies shows the effect of an ordinary decision support system, and decision scientists thinks that more evolved decision support system has potential. However, this type of intelligent decision support system is not usually researched in combination with the decision-making process. The purpose of this study is to contribute to the gap of missing research in this area. To investigate this case, we needed to collect qualitative data, which was done with semi structured interviews and observations, before and after the introduction of the intelligent decision support system. When analyzing our data, we used a qualitative content analysis to find themes and categories, which we then compared the before and after results with theoretical input. We found that the intelligent decision support system could enable the information in the decisionmaking process which could make more time available. With that extra time, the focus of the time could shift to evaluation. This led the decision-making process to become more rational in three of four steps. In conclusion we found that the intelligent decision support system helped the decision-making process to become more rational.

The aim of this thesis is to provide to the governmental decision-maker/user, an instrument that can assist him/her in improving the infrastructure investment decision in the economical, environmental and sustainable aspects. This means that, the Return on Investment (ROI) of the concerned transport infrastructure, satisfying environmental and sustainable constraints must be positive, and corresponding to an optimal investment cost. The decision support system can be applied in two dimensions. One dimension is where the real negotiation process is occurring between private and public stakeholders, called “real time negotiation process”. The second dimension is where the negotiation process is impelled by the user (public part) without private stakeholders interaction (but with interaction through simulation), called “virtual negotiation process”. The simulation and local optimization techniques, in phase with agent technology, used in the “virtual negotiation process” enable us to achieve a certain amount of alternative decisions to the primary/suggested decision to be evaluated. The CommonKADS methodology with mathematical modeling, and agent technology have been the support respectively for extracting and implementing the knowledge in the domain, monitoring, automating and updating the decision process. The principle of “Joint logistic” [1] in my effort concerns by the means of sharing financial and information resources; This leads to the empowerment of the supply chain feedbacks (roles), involved in the earlier stages of public transport decision making-process. It appears that within the decision-making process, the government is often dealing with the conflicting objectives, while interacting with the business stakeholders. For instance, the estimated investment cost of a specific transport infrastructure can exceed the income generated by this infrastructure, thus the ROI of the concerned transport infrastructure (TI) will be negative. From this perspective the government faces three choices: a) increase the rate of the taxes applied on that transport infrastructure or any other taxes, in order to make ROI positive, this can be matter of discussion/disagreement for the business community b) reduce the investment cost which means suggest a different TI with a lower quality standard compared to the previous; this can also be a matter of disagreement between the two concerned stakeholders. c) delay of the investment in the specific transport infrastructure. In fact in the most situations the government uses the first approach, which effects might be consequently unpredictable and disastrous in the economical and environmental sense for the government. From this point of view my attempt is to propose an intelligent decision support system for governments or project groups (e.g. East West project group), involving conceptually as components web portal, database, simulator and knowledge base, that bases on an approach, that enables this negotiation/information exchange at the earlier steps of decision-making situation. This is concretized by gathering in real time accurate and relevant information from the private sector; furthermore the knowledgebase of the designed system is conceived via the experience and historical knowledge of the concerned experts in the domain. / Please contact me via email : yjeanyv@hotmail.com or phone: +224 64 97 43 79

This thesis proposes intelligent decision support System in diabetes eHealth care in order to improve the quality of life of Diabetes patients. Diabetes is one of the chronic diseases that can cause the serious health complication. Patients of diabetes especially elder people need more care than others as well as regularity in medicine. Only patients themselves or doctors cannot provide the care that patient needs. To improve the quality of daily life of patient a team of care providers work together. This thesis covers the different fields of intelligent decision support system for the diabetes type2 patients. The proposed intelligent decision support system is 24-hours accessible for the patients and care providers. The system stores the patients’ information and gives them optimal advices according to their condition entered by them. It also provides adequate and detail information about the patient to the health-care providers that help them to take an optimal decision about the patients. If system analyzes any alarming condition of the patient, it generates automatic alarming message for the health-care providers to help the patients. We validate our study by conducting interviews with diabetes health-care providers and perform questionnaires filled from diabetes type2 patients.

This thesis has explored the development and potential effects of an intelligent decision support system (IDSS) to predict potential buyers for commercial real estate property. The overarching need for an IDSS of this type has been identified exists due to information overload, which the IDSS aims to reduce. By shortening the time needed to process data, time can be allocated to make sense of the environment with colleagues. The system architecture explored consisted of clustering commercial real estate buyers into groups based on their characteristics, and training a prediction model on historical transaction data from the Swedish market from the cadastral and land registration authority. The prediction model was trained to predict which out of the cluster groups most likely will buy a given property. For the clustering, three different clustering algorithms were used and evaluated, one density based, one centroid based and one hierarchical based. The best performing clustering model was the centroid based (K-means). For the predictions, three supervised Machine learning algorithms were used and evaluated. The different algorithms used were Naive Bayes, Random Forests and Support Vector Machines. The model based on Random Forests performed the best, with an accuracy of 99.9%. / Denna uppsats har undersökt utvecklingen av och potentiella effekter med ett intelligent beslutsstödssystem (IDSS) för att prediktera potentiella köpare av kommersiella fastigheter. Det övergripande behovet av ett sådant system har identifierats existerar på grund av informtaionsöverflöd, vilket systemet avser att reducera. Genom att förkorta bearbetningstiden av data kan tid allokeras till att skapa förståelse av omvärlden med kollegor. Systemarkitekturen som undersöktes bestod av att gruppera köpare av kommersiella fastigheter i kluster baserat på deras köparegenskaper, och sedan träna en prediktionsmodell på historiska transkationsdata från den svenska fastighetsmarknaden från Lantmäteriet. Prediktionsmodellen tränades på att prediktera vilken av grupperna som mest sannolikt kommer köpa en given fastighet. Tre olika klusteralgoritmer användes och utvärderades för grupperingen, en densitetsbaserad, en centroidbaserad och en hierarkiskt baserad. Den som presterade bäst var var den centroidbaserade (K-means). Tre övervakade maskininlärningsalgoritmer användes och utvärderades för prediktionerna. Dessa var Naive Bayes, Random Forests och Support Vector Machines. Modellen baserad p ̊a Random Forests presterade bäst, med en noggrannhet om 99,9%.