Title Promoter Affiliations Abstract "Flexible bus services for smart cities." "Kenneth Sörensen" "Katholieke Universiteit Leuven, Engineering Management" "Frustration is a common emotion among regular bus users, as bus transport tends to be slow, inefficient, and inflexible. Typically, a bus service (i.e., a set of bus routes and timetables) remains the same throughout the day, even when the demand for bus transport varies considerably over time. The main reason for this inflexibility was that, until very recently, public bus operators had no way of knowing the demand for transportation at any given moment, and were therefore forced to use fixed bus schedules. This lack of knowledge is, however, likely to change with the advent of the ""smart city"". In the near future, sensors, mobile devices, and other smart city technology will empower public transport operators to roll out flexible bus services that respond to the actual demand for transportation, the current traffic conditions, etc. Also the on-line communication between potential passengers and bus operators, in both directions, will work smoothly. This increases the number of opportunities to improve and tailor the route, stops or timetable of a bus line, also during operations. The aim of this project is to develop the optimization models and algorithms to fully exploit these opportunities and to evaluate the added value of flexible services over conventional fixed-line fixedtimetable services. The goal is to obtain a flexible and demand oriented public transport system which is more efficient from an operator cost perspective and sustainable from a societal perspective." "Search behavior in the marriage market, household formation and economic decisions: a revealed preference analysis." "Sam Cosaert, Luca Paolo Merlino" "Katholieke Universiteit Leuven, Economics" "The aim of this project is to explicitly integrate marriage decisions in the wider context of household decisions when divorce is a possible option. This project wants to better understand the interplay between the search for partners, household formation and economic decisions. The idea is that making an investment in the ability to search for a better partner affects the characteristics of the match, but also the bargaining position in the relationship by determining the quality of the outside options in case of divorce. We will introduce search frictions in the marriage market using two approaches. First, we will propose a matching model where search frictions are captured by a matching function. Secondly, motivated by the empirical observation that most spouses meet through friends, we will study a marriage market where the choice of partners is constrained by one's social networks. We will estimate non-parametrically the models using revealed preferences to provide a structural description of the within-household allocation as a function of the search behavior defining the current and future outside options on marriage markets. Overall, modeling search behavior implies a better description of the intra-household decision process, which in turn yields a more powerful analysis of household choice behavior and its welfare implications on spouses and their children." "A simulation-optimisation framework for analysing and managing emergency departments." "Kris BRAEKERS" Logistics "Emergency departments (EDs) constitute an important component in a health care system. Due to a remarkable growth in demand and the ever tightening budgets, the need for ED services often exceeds the available resources in the ED. In this project, the aim is to analyse and optimise ED operations in order to reduce ED crowding and to find opportunities to improve their efficiency without reducing the quality of care. In this respect, simulation and simulation-optimisation techniques are used. These techniques enable to capture the complex and stochastic nature of an ED and to test improvement options without having to implement them in practice." "Economic valuation of climate change impacts on ecosystem services provided by dry heathland." "Robert MALINA" "Environmental Biology, Environmental Economics" "Dry heathlands have economic value because they provide society with ecosystem goods and services such as climate regulation, biodiversity conservation and recreation. The provision of these ecosystem services may decrease in the future because heathland surfaces are expected to decline in favor of more resilient grasses as a result of longer and more frequent summer droughts. This may change the climate regulating function of the ecosystem, because grasslands have different soil carbon pools and surface albedo. It may also reduce the recreational value provided by heathland areas. However, the rate and extent to which heathland shift into grassland under climate change is unknown. In this research the rate and extent to which heathland shift into grassland under climate change-induced droughts will be estimated based on primary data from the Ecotron Facility. Subsequently, an economic valuation of this shift will be prepared by means of an Integrated Assessment Model. In addition, a contingent visitation analysis for the case of recreational value provided by heathland in the National Park Hoge Kempen (Belgium) will be conducted. The results will inform decision-makers about climate adaptive heathland management in Flanders and Europe." "A matheuristic routing algorithm in support of a dynamic, integrated mobility system" "An CARIS" Logistics "In a traditional mobility policy, public transport is supplemented with (private) dial-a-ride services, providing demand-dependent door-to-door transport to people with reduced mobility. For efficiency reasons, many governments are currently implementing an innovative demand-driven mobility policy in which private dial-a-ride services also replace unprofitable public transport in rural areas. This FWO postdoctoral research project focuses on developing a dynamic matheuristic routing algorithm which provides integrated solutions, combining public transport and dial-a-ride services by ensuring synchronization between routes and modes." "Explaining deep learning models for behavioral data." "David Martens" "Engineering Management" "As a consequence of digitalization, more aspects of people's lives are being captured. Examples include visiting particular physical locations or webpages, liking Facebook pages, etc. This behavioral data holds significant predictive power. For example, what you like on Facebook can be predictive for your IQ, product interest, and even creditworthiness. Deep learning has been shown to outperform other prediction techniques in making accurate predictions using behavioral data. Combining behavioral data and deep learning unfortunately results in incomprehensible black box predictions. Three reasons why: (1) behavioral data is very high-dimensional (up to millions of features), (2) the data is sparse, so every feature is only of relevance for a few data instances, and (3) the deep learning model is complex and non-linear. Consequently, although the combination of deep learning and behavioral data is so predictive, it is very difficult to understand why the model is making certain predictions, leading to skepticism to use it in practice. The main contribution of this research proposal is to design new algorithms that explain the complex deep learning prediction models. This comprehensibility issue is a research area that has gained attention in the data mining community because of the implications it has on model deployment and transparency towards users. We will validate our findings in several applications." "Triaging and Referring In Adjacent General and Emergency departements (the TRIAGE-trial): a cluster randomised controlled trial." "Veronique Verhoeven" "Herman Deleeck Centre for Social Policy, Economics, Primary and interdisciplinary care Antwerp (ELIZA)" "Introduction: Patients who might also go to the general practitioner (GP) frequently consult emergency departments (ED). This leads to additional costs for both government and patient and a high workload for emergency physicians in Flanders. The Belgian government wants to address this problem by improved collaboration between EDs and general practice cooperatives (GPCs). Intervention: Patients presenting at the ED during out-of-hours (OOH) will be triaged and allocated to the most appropriate service. For this purpose the Manchester Triage System (MTS) which is commonly used in Flemish hospitals, will be extended (eMTS). By doing so a trained nurse will be able to diverge suitable patients towards the GPC. Methodology: We will conduct a cluster RCT in which eligible ED patients will be diverged to the GPC using the eMTS. We will collect data using our operational anonymous database for OOH care (iCAREdata). We will study the use of the eMTS, the effectiveness and effects of triage, work load changes, epidemiology at both departments, patient safety, health insurance (HIS) and patient expenditures. Furthermore facilitators and barriers will be studied and an incident analysis of problem cases will be performed. Outcome: The primary outcome is the proportion of patients who enter the ED and are handled by the GP after triage. Secondary outcome measurements are related to safety: referral rate to the ED by the GP, proportion of patients visiting the ED again within two weeks, proportion of patients not following the triage advice and file review for selected patients. Results: We will generate a generic model of triage applicable to all Belgian EDs and GPCs. The model will consist of a validated triage instrument, a manual for setting up triage and scientific support for both effectiveness and safety. In addition we expect to achieve financial savings for the HIS and for the patient." "Multi-criteria capacity optimization in emergency departments" "Inneke VAN NIEUWENHUYSE" Logistics "The proposed project focuses specifically on capacity optimization in emergency departments (EDs). It is novel in the sense that we (1) explicitly account for bed capacity as well as personnel capacity, (2) take into account many realistic aspects that impact patient flow through the ED (such as patients leaving the ED without treatment when the waiting times are too long, or patients remaining blocked when no beds are available in the inpatient unit), and (3) consider the problem as a constrained stochastic multi-objective optimization problem, where the traditional objective of minimizing the capacity cost is complemented with objectives and constraints that reflect the quality of care provided. Despite its relevance in many real-life settings, the literature on constrained stochastic multi-objective optimization is rather scarce. We intend to develop and test two novel simulation-optimization approaches (a metamodel-based approach and a model enhancement approach), that aim to outperform existing heuristics in terms of effectiveness (i.e., ability to provide a high-quality approximation of the Pareto frontier), and efficiency (computational effort). The performance will be evaluated using real-life data from the ED department of a large regional hospital in Belgium." "Data-driven logistics" Logistics "Logistics involves different types of activities such as warehousing, transport, terminal operations and loading. Each of these activities involves various complex operational decisions which are often interrelated and subject to rapidly changing market conditions and environments. Therefore, good decision support software is essential for companies to remain competitive. Recent developments enabled logistics companies to digitally monitor and store data regarding their operations. Additionally, computational advances enabled software developers to implement advanced algorithms for optimising operational schedules. However, these two activities, monitoring and decision-making, currently represent two separate processes and only limited data is exchanged between them. This project seeks to develop innovative methodologies for data-driven optimisation in logistics. Such an approach would enable the use available data to learn and find patterns, thereby continuously and automatically adapting and improving logistics optimisation processes. Furthermore, it offers a stepping stone to solve complex interrelated problems in an integrated manner. This is expected to pave the way for a new generation of logistics optimization software, yielding substantial benefits over the rigid traditional methods. The developed techniques will be validated and evaluated on a number of case studies in different logistics contexts, thereby enabling an accurate assessment of the benefits of a data-driven approach to logistics decision-making." "A new value chain for the Flemish bio-economy through inventive wood refining towards highly valuable agro-industrial chemicals (BIOWOOD)." "Engineering Management" "The BioWood project aims at boosting the economic and environmental performance of the Flemish bio- economy by providing the knowledge base to create a novel wood-based value chain for the chemical and agro-industries. This value chain will be based on inventive conversion technologies, starting from local, inexpensive and available woody biomass resources and targeting highly valuable agro-industrial applications. The main objectives are: (i) detailed inventory of currently available woody biomass feedstock from forests, landscapes, imports and waste flows in Flanders, and determination of their current value to develop a a spatio- temporal optimisation tool for the best allocation of woody biomass and best location of a new biofactory in Flanders using sustainability and cost efficiency criteria; (ii) Design of a flexible refinery process for complex and variable lignocellulose feeds to synthesise novel organic products for agro-industrial applications; (iii) Proof-of-concept of novel products for agro-industrial applications with a performance at least equalling the performance of current agro-industrial products; (iv) techno-economic and real options analysis of the entire value chain of a bio-based production unit, from woody biomass feedstock to agro-industrial products by analysis of uncertainties and flexibility options."