No / his book explores a new framework of Adaptive Water Management (AWM) for evaluating existing approaches in urban water management. It highlights the need to adopt multidisciplinary strategies in water management while providing an in-depth understanding of institutional interactions amongst different water related sectors. The key characteristics of AWM i.e. polycentric governance, organisational flexibility and public participation are investigated and described through a critical review of the relevant literature. The book presents an empirical case study undertaken in a selected developing-country city to investigate the potential gaps between the current water management approaches and possible implementation of AWM. Feasibility of AWM operations is examined in an environment surrounded by established water management structure with centralised governance and an institutional process based on technical flexibility. The key elements of AWM performance are (re)structured and transformed into decision support systems. Multi criteria decision models are developed to facilitate quantification and visualization of the elements derived from the case study, which is involved with water companies and water consumers. The book describes how the concept of AWM, along with structuring suitable decision support systems, can be developed and applied to developing-country cities. The book highlights the barriers for applying the AWM strategies that include established centralised decision making, bureaucratic interactions with external organisations, lack of organisational flexibility within the institutions, and lack of recognition of public role in water management. The findings outline that despite the lack of adaptability in the current water management in the case study, as an example of developing countries, there are positive attitudes among water professionals and the public towards adaptability through public-institutional participation.

Providing products that are customized to meet a specific customer's unique needs is challenging for companies. Product configuration systems are tools that enables parts of these activities to be performed automatically. However, there is a lack of systems designed to ensure that the configured products are based on customer needs. Decision support systems based on Multi-criteria decision making methods have the potential to solve this problem. Yet, there is a lack of knowledge regarding various multi-criteria decision making methods. Moreover, there is a need to reduce the complexity of the methods by incorporating them into user-friendly software’s. This research therefore investigates how the architecture of a decision support system based on multi-criteria decision making methods could be structured to include customer needs and suggest product configurations based on them. Through a literature review various methods are analyzed. In collaboration with an aircraft towing tractor manufacturer as a representative of customizable products the architecture of the system is developed. The study shows that a system based on a combination of Analytical Hierarchy Process, Quality Function Deployment and Expert system can solve the problem. This is to the authors knowledge the first study to use this combination. It provides an approach of how to ensure that product configurations can be aligned with customer needs and that the consistency of these needs is assured.

專家決策支援系統（Expert Decision Support System）是一種結合專家 系統與決策支援系統功能於一體的電腦化資訊系統；它同時具備有處理定 性資料與定量資料的能力，可以進行各種知識法則的推論及數量模式的執 行與分析，以完整的支援問題之求解過程。 / The expert decision support system(EDSS) is a computer-based nformation system which integrates functions of the expert systemnd the decision support system. EDSS, which is capable ofrocessing symbolic and numerical data, provides the

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%.

The selection of the most appropriate traffic control actions to solve non-recurrent traffic congestion is a complex task which requires significant expert knowledge and experience. In this thesis we develop and investigate the application of an intelligent traffic control decision support system for road traffic management to assist the human operator to identify the most suitable control actions in order to deal with non-recurrent and non-predictable traffic congestion in a real-time situation. Our intelligent system employs a Fuzzy Neural Networks (FNN) Tool that combines the capabilities of fuzzy reasoning in measuring imprecise and dynamic factors and the capabilities of neural networks in terms of learning processes. In this work we present an effective learning approach with regard to the FNN-Tool, which consists of three stages: initializing the membership functions of both input and output variables by determining their centres and widths using self-organizing algorithms; employing an evolutionary Genetic Algorithm (GA) based learning method to identify the fuzzy rules; tune the derived structure and parameters using the back-propagation learning algorithm. We evaluate experimentally the performance and the prediction capability of this three-stage learning approach using well-known benchmark examples. Experimental results demonstrate the ability of the learning approach to identify all relevant fuzzy rules from the training data. A comparative analysis shows that the proposed learning approach has a higher degree of predictive capability than existing models. We also address the scalability issue of our intelligent traffic control decision support system by using a multi-agent based approach. The large network is divided into sub-networks, each of which has its own associated agent. Finally, our intelligent traffic control decision support system is applied to a number of road traffic case studies using the traffic network in Riyadh, in Saudi Arabia. The results obtained are promising and show that our intelligent traffic control decision support system can provide an effective support for real-time traffic control.

投資人在投資決策之過程中，所分析之資料可分為財務性與非財務性資訊兩大類，然而受限於傳統財務資料格式之不一致，可能需花費額外之財力與物力來處理，甚至浪費精力於資料的重新輸入。另一方面，非財務資訊在投資決策過程中日益重要，但其龐大的資訊揭露量卻往往徒增投資人閱讀與搜尋上之不便，甚至降低了可閱讀性。 有鑑於上述兩大投資分析不便之處，本研究運用文字探勘(Text mining)技術，嘗試處理股東會年報中與企業策略相關之非財務性資訊，以協助閱讀者有效率地分析、整理這些半結構化，甚至是非結構化文字資訊。另一方面，本研究利用可延伸企業報導語言(eXtensible Business Reporting Language, XBRL)不受軟體平台限制，可於網路上自由下載流通等特性，作為財務資訊之資料來源，同時建立一種新的分析模式，透過連結機制之設計以連接非財務性與財務性資訊，並運用ROMC系統分析法與雛型系統設計法完成本企業策略分析決策支援系統，希冀能協助投資人能於短時間內瞭解並印證標的公司之產業發展與競爭策略，提升決策品質。 / There are two main data types in investment decision process: financial and non-financial. Because the inconsistent of data type in traditional financial data, investors may have more additional costs to solve this problem. In addition, non-financial data become more and more important in investment decision process, but huge amount of non-financial disclosure may reduce the readability and increase the difficulty of searching. To solve the above problems, we try to use text mining technology to handle the semi-structured or unstructured non-financial data related to business strategies in the annual reports of public companies effectively and efficiently. In addition, we use XBRL (eXtensible Business Reporting Language) to be our financial data resources because of its interoperability and re-usability. We also develop a new analytic method to link financial and non-financial data together. Finally, we use two system methodologies: R.O.M.C. and prototyping to design and build our business strategy analysis decision support system in order to help investors understand and prove strategies in companies, and improve the decision quality which they make.

This work focuses on the need for new knowledge to allow hierarchical multi-project management to be conducted in the construction industry, which is characterised by high uncertainty, fragmentation, complex decisions, dynamic changes and long-distance communication. A dynamic integrated project management approach is required at strategic, tactical and operational levels in order to achieve adaptability. The work sees the multi-project planning and control problem in the context of supply chain management at main contractor companies. A portfolio manager must select and prioritise the projects, bid and negotiate with a wide range of clients, while project managers are dealing with subcontractors, suppliers, etc whose relationships and collaborations are critical to the optimisation of schedules in which time, cost and safety (etc) criteria must be achieved. Literature review and case studies were used to investigate existing approaches to hierarchical multi-project management, to identify the relationships and interactions between the parties concerned, and to investigate the possibilities for integration. A system framework was developed using a multi-agent-system architecture and utilising procedures adapted from literature to deal with short, medium and long-term planning. The framework is based on in-depth case study and integrates time-cost trade-off for project optimisation with multi-attribute utility theory to facilitate project scheduling, subcontractor selection and bid negotiation at the single project level. In addition, at the enterprise level, key performance indicator rule models are devised to align enterprise supply chain configuration (strategic decision) with bid selection and bid preparation/negotiation (tactical decision) and project supply chain selection (operational decision). Across the hierarchical framework the required quantitative and qualitative methods are integrated for project scheduling, risk assessment and subcontractor evaluation. Thus, experience sharing and knowledge management facilitate project planning across the scattered construction sites. The mathematical aspects were verified using real data from in-depth case study and a test case. The correctness, usefulness and applicability of the framework for users was assessed by creating a prototype Multi Agent System-Decision Support System (MAS-DSS) which was evaluated empirically with four case studies in national, international, large and small companies. The positive feedback from these cases indicates strong acceptance of the framework by experienced practitioners. It provides an original contribution to the literature on planning and supply chain management by integrating a practical solution for the dynamic and uncertain complex multi-project environment of the construction industry.

The research presented in this thesis is based in the Humanities discipline of Ancient History and begins by attempting to understand the interpretation process involved in reading ancient documents and how this process can be aided by computer systems such as Decision Support Systems (DSS). The thesis balances between the use of IT tools to aid Humanities research and the understanding that Humanities research must involve human beings. It does not attempt to develop a system that can automate the reading of ancient documents. Instead it seeks to demonstrate and develop tools that can support this process in the five areas: remembering complex reasoning, searching huge datasets, international collaboration, publishing editions, and image enhancement. This research contains a large practical element involving the development of a DSS prototype. The prototype is used to illustrate how a DSS, by remembering complex reasoning, can aid the process of interpretation that is reading ancient documents. It is based on the idea that the interpretation process goes through a network of interpretation. The network of interpretation illustrates a recursive process where scholars move between reading levels such as ‘these strokes look like the letter c’ or ‘these five letters must be the word primo’. Furthermore, the thesis demonstrates how technology such as Web Services and XML can be used to make a DSS even more powerful through the development of the APPELLO word search Web Service. Finally, the conclusion includes a suggestion for a future development of a working DSS that incorporates the idea of a layer-based system and focuses strongly on user interaction.

Il ne passe pas une semaine sans que l'on entende les termes « crise », « catastrophe » ou « désastre ». Ces notions font donc maintenant partie de notre quotidien, mais connaît- n vraiment leur signification. Sait-on réagir face à ces situations, et surtout comment peut- n être sûrs de les résoudre de la façon la plus performante possible ? Ces interrogations sont le point de départ de ce travail. En effet, nos recherches ont consisté à mettre en œuvre une méthode pour aider les acteurs d'une crise à mieux contrôler la réponse à apporter pour la résoudre. Lors de la survenu d'une crise, quelle qu'elle soit, le système est déstabilisé, il faut donc réagir vite afin de revenir à une situation stable. Or, actuellement les décideurs ne disposent pas de suffisamment d'éléments (1) pour prendre des décisions sereinement et (2) pour suivre l'impact de leur décision. C'est pour pallier ce manque que nous avons développé une méthode d'évaluation de performance qui permet aux décideurs de suivre et d'évaluer, selon les critères qu'ils ont définis, de façon précise le déroulement de la réponse à la crise. Ainsi les décideurs peuvent réagir, c'est-à-dire prendre une décision a posteriori, lorsqu'ils découvrent un problème dans la réponse et également anticiper, c'est-à-dire, prendre une décision a priori avant même que le problème ait lieu, en se fondant sur des prévisions renseignant sur l'état futur de la crise. Ces travaux ont un intérêt d'un point de vue académique étant donné qu'ils se positionnent sur une problématique en plein essor dans la recherche et d'un point de vue opérationnel car la méthode mise en oeuvre répond à un réel besoin émis par des acteurs de la réponse aux crises. De plus, comme le montre le dernier chapitre, nos travaux sont déjà applicables. Ce sujet est donc utile à tous, puisque chacun peut être victime d'une crise et en particulier aux acteurs de la gestion de crise qui y sont confrontés quotidiennement. / During a crisis, the main goal for decision-makers consists in restoring a stabilized nominal mode. The stakeholders face considerable pressure and drastic constraints in response time and coordination. This study proposes a method to support these stakeholders in making responsive and accurate decisions while carrying out a performance evaluation of the activities run during the crisis response process. This method is composed of four steps: (1) characterization of the crisis response system, (2) selection of system components to evaluate in priority, (3) determination of performance dimensions to consider and (4) creation of indicators. Currently, performance evaluation is only used subsequent to a crisis, due to difficulties in gathering and aggregating information into trustable performance indicators. This paper proposes a method to obtain a relevant and dynamic decision-support system. Decision-makers will use it to resolve the crisis based on performance evaluation, in addition to the essential experience they undergo. A case study of crisis management within the French Red Cross non-governmental organization is developed, through a web-based prototype, in order to explain how performance indicators can both support crisis response management and also improve the collaboration of stakeholders.

Il existe différents systèmes de localisation de navires en mer qui favorisent une aide à la navigation et une sécurisation du trafic maritime. Ces systèmes sont également utilisés en tant qu’outils de surveillance et d’aide à la décision par les centres de surveillance basés à terre. Le Système d’Identification Automatique (AIS) déployé par l’Organisation Maritime Internationale, bien qu’étant le système de localisation de navires le plus utilisé de nos jours, est faiblement sécurisé. Cette vulnérabilité est illustrée par des cas réels et détectés tels que des usurpations d’identité ou des disparitions volontaires de navires qui sont sources de risques pour les navires, les infrastructures offshores et côtières et l’environnement.Nous proposons dans cette thèse une démarche méthodologique d’analyse et d’évaluation des messages AIS fondée sur les dimensions de la qualité de la donnée, dont l’intégrité considérée comme la plus importante de ces dimensions. Du fait de la structure complexe de l’AIS, une liste d'indicateurs a été établie, afin d’évaluer l'intégrité de la donnée, sa conformité avec les spécifications techniques du système et la cohérence des champs des messages entre eux et au sein d’un seul ou plusieurs messages. Notre démarche repose également sur l’usage d’informations additionnelles telles que des données géographiques ou des registres de navires afin d’évaluer la véracité et l’authenticité d’un message AIS et de son expéditeur.Enfin, une évaluation des risques associés est proposée, permettant une meilleurecompréhension de la situation maritime ainsi que l’établissement de liens de causalité entre les vulnérabilités du système et les risques relevant de la sécurité et sûreté de la navigation maritime. / At sea, various systems enable vessels to be aware of their environment and on the coast, those systems, such as radar, provide a picture of the maritime traffic to the coastal states. One of those systems, the Automatic Identification System (AIS) is used for security purposes (anti-collision) and as a tool for on-shore bodies as a control and surveillance and decision-support tool.An assessment of AIS based on data quality dimensions is proposed, in which integrity is highlighted as the most important of data quality dimensions. As the structure of AIS data is complex, a list of integrity items have been established, their purpose being to assess the consistency of the data within the data fields with the technical specifications of the system and the consistency of the data fields within themselves in a message and between the different messages. In addition, the use of additional data (such as fleet registers) provides additional information to assess the truthfulness and the genuineness of an AIS message and its sender.The system is weekly secured and bad quality data have been demonstrated, such as errors in the messages, data falsification or data spoofing, exemplified in concrete cases such as identity theft or vessel voluntary disappearances. In addition to message assessment, a set of threats have been identified, and an assessment of the associated risks is proposed, allowing a better comprehension of the maritime situation and the establishment of links between the vulnerabilities caused by the weaknesses of the system and the maritime risks related to the safety and security of maritime navigation.