Routine immunization (RI) of children is the most effective and timely public health intervention for decreasing child mortality rates around the globe. Pakistan being a low-and-middle-income-country (LMIC) has one of the highest child mortality rates in the world occurring mainly due to vaccine-preventable diseases (VPDs). For improving RI coverage, a critical need is to establish potential RI defaulters at an early stage, so that appropriate interventions can be targeted towards such population who are identified to be at risk of missing on their scheduled vaccine uptakes. In this paper, a machine learning (ML) based predictive model has been proposed to predict defaulting and non-defaulting children on upcoming immunization visits and examine the effect of its underlying contributing factors. The predictive model uses data obtained from Paigham-e-Sehat study having immunization records of 3,113 children. The design of predictive model is based on obtaining optimal results across accuracy, specificity, and sensitivity, to ensure model outcomes remain practically relevant to the problem addressed. Further optimization of predictive model is obtained through selection of significant features and removing data bias. Nine machine learning algorithms were applied for prediction of defaulting children for the next immunization visit. The results showed that the random forest model achieves the optimal accuracy of 81.9% with 83.6% sensitivity and 80.3% specificity. The main determinants of vaccination coverage were found to be vaccine coverage at birth, parental education, and socio-economic conditions of the defaulting group. This information can assist relevant policy makers to take proactive and effective measures for developing evidence based targeted and timely interventions for defaulting children.
MULTIFILE
In this study, a data feedback program to improve teachers’ science and technology (S&T) teaching skills was designed and tested. The aim was to understand whether and how the four design principles underlying this program stimulated the intended teacher support. We examined how teachers in different phases of their career applied and experienced the employed design principles’ key aspects. Eight in-service teachers and eight pre-service teachers attended the data feedback program and kept a logbook in the meantime. Group interviews were held afterwards. Findings show that applying the four employed design principles’ key aspects did support and stimulate in- and pre-service teachers in carrying out data feedback for improving their S&T teaching. However, some key aspects were not applied and/or experienced as intended by all attending teachers. The findings provide possible implications for the development and implementation of professional development programs to support in - and pre-service teachers’ S&T teaching using data feedback.
DOCUMENT
Paralympic wheelchair athletes solely depend on the power of their upper-body for their on-court wheeled mobility as well as for performing sport-specific actions in ball sports, like a basketball shot or a tennis serve. The objective of WheelPower is to improve the power output of athletes in their sport-specific wheelchair to perform better in competition. To achieve this objective the current project systematically combines the three Dutch measurement innovations (WMPM, Esseda wheelchair ergometer, PitchPerfect system) to monitor a large population of athletes from different wheelchair sports resulting in optimal power production by wheelchair athletes during competition. The data will be directly implemented in feedback tools accessible to athletes, trainers and coaches which gives them the unique opportunity to adapt their training and wheelchair settings for optimal performance. Hence, the current consortium facilitates mass and focus by uniting scientists and all major Paralympic wheelchair sports to monitor the power output of many wheelchair athletes under field and lab conditions, which will be assisted by the best data science approach to this challenge.
DOCUMENT
In order to stay competitive and respond to the increasing demand for steady and predictable aircraft turnaround times, process optimization has been identified by Maintenance, Repair and Overhaul (MRO) SMEs in the aviation industry as their key element for innovation. Indeed, MRO SMEs have always been looking for options to organize their work as efficient as possible, which often resulted in applying lean business organization solutions. However, their aircraft maintenance processes stay characterized by unpredictable process times and material requirements. Lean business methodologies are unable to change this fact. This problem is often compensated by large buffers in terms of time, personnel and parts, leading to a relatively expensive and inefficient process. To tackle this problem of unpredictability, MRO SMEs want to explore the possibilities of data mining: the exploration and analysis of large quantities of their own historical maintenance data, with the meaning of discovering useful knowledge from seemingly unrelated data. Ideally, it will help predict failures in the maintenance process and thus better anticipate repair times and material requirements. With this, MRO SMEs face two challenges. First, the data they have available is often fragmented and non-transparent, while standardized data availability is a basic requirement for successful data analysis. Second, it is difficult to find meaningful patterns within these data sets because no operative system for data mining exists in the industry. This RAAK MKB project is initiated by the Aviation Academy of the Amsterdam University of Applied Sciences (Hogeschool van Amsterdan, hereinafter: HvA), in direct cooperation with the industry, to help MRO SMEs improve their maintenance process. Its main aim is to develop new knowledge of - and a method for - data mining. To do so, the current state of data presence within MRO SMEs is explored, mapped, categorized, cleaned and prepared. This will result in readable data sets that have predictive value for key elements of the maintenance process. Secondly, analysis principles are developed to interpret this data. These principles are translated into an easy-to-use data mining (IT)tool, helping MRO SMEs to predict their maintenance requirements in terms of costs and time, allowing them to adapt their maintenance process accordingly. In several case studies these products are tested and further improved. This is a resubmission of an earlier proposal dated October 2015 (3rd round) entitled ‘Data mining for MRO process optimization’ (number 2015-03-23M). We believe the merits of the proposal are substantial, and sufficient to be awarded a grant. The text of this submission is essentially unchanged from the previous proposal. Where text has been added – for clarification – this has been marked in yellow. Almost all of these new text parts are taken from our rebuttal (hoor en wederhoor), submitted in January 2016.
Predictive maintenance, using data of thousands of sensors already available, is key for optimizing the maintenance schedule and further prevention of unexpected failures in industry.Current maintenance concepts (in the maritime industry) are based on a fixed maintenance interval for each piece of equipment with enough safety margin to minimize incidents. This means that maintenance is most of the time carried out too early and sometimes too late. This is in particular true for maintenance on maritime equipment, where onshore maintenance is strongly preferred over offshore maintenance and needs to be aligned with the vessel’s operations schedule. However, state-of-the-art predictive maintenance methods rely on black-box machine learning techniques such as deep neural networks that are difficult to interpret and are difficult to accept and work with for the maintenance engineers. The XAIPre project (pronounce Xyper) aims at developing Explainable Predictive Maintenance algorithms that do not only provide the engineers with a prediction but in addition, with a risk analysis on the components when delaying the maintenance, and what the primary indicators are that the algorithms use to create inference. To use predictive maintenance effectively in Maritime operations, the predictive models and also the optimization of the maintenance schedule using these models, need to be aware of the past and planned vessel activities, since different activities affect the lifetime of the machines differently. For example, the degradation of a hydraulic pump inside a crane depends on the type of operations the crane but also the vessel is performing. Thus the models do not only need to be explainable but they also need to be aware of the context which is in this case the vessel and machinery activity. Using sensor data processing and edge-computing technologies that will be developed and applied by the Hanze University of Applied Sciences in Groningen (Hanze UAS), context information is extracted from the raw sensor data. The XAIPre project combines these Explainable Context Aware Machine Learning models with state-of-the-art optimizers, that are already developed and available from the NWO CIMPLO project at LIACS, in order to develop optimal maintenance schedules for machine components. The resulting XAIPre prototype offers significant competitive advantages for maritime companies such as Heerema, by increasing the longevity of machine components, increasing worker safety and decreasing maintenance costs.
