Authors: Oruç, Sercan; Eren, P. Erhan; Koçyiğit, Altan
Abstract: Decision-making in everyday life has an essential role in effectively completing ...
Expand
Abstract: Decision-making in everyday life has an essential role in effectively completing personal tasks and processes. The complexity of these processes and the resulting cognitive load of managing them may vary significantly. To decrease the cognitive load created by such decision-making efforts and to obtain better outcomes, recom mendation systems carry significant potential. In order to investigate the benefits provided by decision support systems (DSS) in personal process management (PPM), we first build a constraint programming (CP) model and a prototype context-aware-mobile application employing this CP model. Then, we evaluate the application and the model via two exemplary real-world scenarios. The scenarios form the core of the experiments conducted with 50 participants. We compare the participants’ planning performances with and without the PPM system with quantitative metrics such as planning times and scenario objective values. In addition, System Usability Scale (SUS) questionnaires and open-ended questions provide qualitative evaluation results. Throughout the study, we apply the Design Science Research methodology to rigorously conduct research activities by proof of concept, proof of use, and proof of value. The empirical results clearly show that our proposed model for PPM is effective, and the developed prototype solution generates positive participant comments as well as a high SUS score. Overall, the prototype PPM system with CP implementation leads to better planning in less time in the planning phase, and it lets the user do fast replanning in the execution phase, which is invaluable in dynamically changing situations such as daily activities.
Collapse
Abstract: This paper addresses the problem of determining the work schedule, called medica ...
Expand
Abstract: This paper addresses the problem of determining the work schedule, called medical planning, of oncologists for chemotherapy of oncology patients at ambulatory care units. A mixed integer programming (MIP) model is proposed for medical planning in order to best balance bed capacity requirements under capacity constraints of key resources such as beds and oncologists. The most salient feature of the MIP model is the explicit modeling of specific features of chemotherapy such as treatment protocols. The medical planning problem is proved to be NP-complete. A three-stage approach is proposed for determining good medical planning in reasonable computational time. From numerical experiments based on field data, the three-stage approach takes less than 10min and always outperforms the direct application of MIP solvers with 10h CPU time. Compared with the current planning, the three-stage approach reduces the peak daily bed capacity requirement by 20h to 45h while the maximum theoretical daily bed capacity is 162h.
Collapse