Search results

Enhancing a simulation-based Allocator Software with machine learning and genetic algorithms for improving the gate assignment problem

Assigning gates to flights considering physical, operational, and temporal constraints is known as the Gate Assignment Problem. This article proposes the novelty of coupling a commercial stand and gate allocation software with an off-the-grid optimization algorithm. The software provides the assignment costs, verifies constraints and restrictions of an airport, and provides an initial allocation solution. The gate assignment problem was solved using a genetic algorithm. To improve the robustness of the allocation results, delays and early arrivals are predicted using a random forest regressor, a machine learning technique and in turn they are considered by the optimization algorithm. Weather data and schedules were obtained from Zurich International Airport. Results showed that the combination of the techniques result in more efficient and robust solutions with higher degree of applicability than the one possible with the sole use of them independently.

Particulate matter in the workplace: effects of a mental models-based folder combined with a practical assignment

Background: With increasing knowledge on the adverse health efects of certain constituents of PM (particulate matter), such as silica, metals, insoluble ions, and black carbon, PM has been under the attention of work safety experts. Previously, we investigated the perceptions of blue-collar workers in highly exposed areas of work. Subsequently, we developed an instruction folder highlighting the most important aspects of PM risk and mitigation, and tested this folder in a digital experiment. The digital experiment yielded positive results with regards to acquired knowledge about PM, but did not on risk perception or safety behavior. Methods: In this study, we investigate the efects of the folder when combined with a practical assignment involving a PM exposimeter, showing the amount of particulate matter in microgram per cubic meter in real time on its display for various activities. We tested this at six workplaces of four companies in the roadwork and construction branch. Results: The results indicate that the folder itself yields an increased knowledge base in employees about PM, but the efects of the practical assignment are more contentious. Nevertheless, there is an indication that using the assignment may lead to a higher threat appraisal among employees for high exposure activities. Conclusion: We recommend implementing our folder in companies with high PM exposure and focusing further research on appropriate methods of implementation.

Dynamic assignment vehicle routing problem with time windows

Offering time windows to receivers of last-mile delivery is becoming a distinguishing factor. However, we see that in practice carriers have to create routes for their vehicles based on destination information, that is just being revealed when a parcel arrives in the depot. The parcel has to be assigned directly to a vehicle, making this a Dynamic Assignment Vehicle Routing Problem. Incorporating time windows is hard in this case. In this paper an approach is presented to solve this problem including Time Windows. A comparison is made with a real observation and with a solution method for the base problem

Assignments

Presenting a complex project assignment through selected video formats

The qualities and availability of different video formats offer many opportunities within the context of Higher Education (Hansch et al., 2015; Johnson et al., 2016; van Huystee, 2016). There is a shift within Higher Education to transition from the traditional face to face approach, to a more ‘blended’ approach in which face to face and online delivery of content are blended (Bates, 2015). More delivery of content is now provided online in video format, viewed before the class, as part of a flipped classroom (Bishop & Verleger, 2013; Yousef, Chatti, & Schroeder, 2014) and this is impacting the traditional role of the lecturer from ‘sage on the stage’, to ‘guide on the side’ (Tapscott, 2009). When creating video, a lecturer needs to have an understanding of the particular pedagogic affordances of the different types of video (Koumi, 2014; Thomson, Bridgstock, & Willems, 2014) and to know how to implement and embed these effectively into the teaching environment as part of a blended approach (Dankbaar, Haring, Moes, & van Hees, 2016; Fransen, 2006; Woolfitt, 2015). There needs to be awareness of how to embed the video from a didactic perspective to create meaningful learning (Karppinen, 2005) and an understanding of some of the financial and technical issues which include the relationship between cost of video production and the user experience (Hansch et al., 2015) and creating the correct combination of multimedia visual and audio elements (Colvin Clark & Mayer, 2011). As the role of the lecturer changes, there are a number of challenges when navigating through this changing educational environment. Massive Open Online Courses (MOOCs) provide lots of data for analysis and research shows that students in this environment stop watching videos after about six minutes (Guo, Kim, & Rubin, 2014) and that the most common video style used in MOOCs was the talking head with Power Point (Reutemann, 2016). Further research needs to be conducted regarding student preferences of video styles and correlation between video styles and course drop-out rates. As part of its research, the Inholland research group ‘Teaching, Learning and Technology’ (TLT) examines the use of ICT and video to support teaching and learning within Inholland. In 2015-2016, several pioneers (Fransen, 2013) working at Inholland explored different approaches to using video to support the teaching and learning process within a number of educational environments. TLT supported the pioneers in establishing their role within their faculty, creating a framework within which the pioneer can design the video intervention, collecting data and reflecting on what was learned through this process. With some of the projects, a more formal research process was followed and a full research report could be compiled. In other cases, the pioneer took a more exploratory and experimental approach. In these cases, the pioneer may not have conducted the video intervention under a formal research framework. However, during this process the pioneer may have uncovered interesting and valuable practical examples that can inspire and be shared with other educators. This current report falls under the category Research Type 3 as defined by TLT. It describes and assesses an ICT application (in this case, video) in order to share the original approach that could have high potential to be implemented in a broader educational context.

Reducing airport environmental footprint using a disruption-aware stand assignment approach

Modern airport management is challenged by the task of operating aircraft parking positions most efficiently while complying with environmental policies, restrictions, schedule disruptions, and capacity limitations. This study proposes a novel framework for the stand allocation problem that uses a divide-and-conquer approach in combination with Bayesian modelling, simulation, and optimisation to produce less-pollutant solutions under realistic conditions. The framework presents three innovative aspects. First, inputs from the stochastic analysis module are used in a multivariate optimisation for generating variability-robust solutions. Second, a combination of optimisation and simulation is used to finely explore the impact of realistic uncertainty uncaptured by the framework. Lastly, the framework considers the role of human beings as the final control of operational conditions. A case study is presented as a proof of concept and demonstrates results achievable and benefits of the framework proposed. The experimental results demonstrate that the framework generates less-pollutant solutions under realistic conditions.