The aviation industry needs led to an increase in the number of aircraft in the sky. When the number of flights within an airspace increases, the chance of a mid-air collision increases. Systems such as the Traffic Alert and Collision Avoidance System (TCAS) and Airborne Collision Avoidance System (ACAS) are currently used to alert pilots for potential mid-air collisions. The TCAS and the ACAS use algorithms to perform Aircraft Trajectory Predictions (ATPs) to detect potential conflicts between aircrafts. In this paper, three different aircraft trajectory prediction algorithms named Deep Neural Network (DNN), Random Forest (RF) and Extreme Gradient Boosting were implemented and evaluated in terms of their accuracy and robustness to predict the future aircraft heading. These algorithms were as well evaluated in the case of adversarial samples. Adversarial training is applied as defense method in order to increase the robustness of ATPs algorithms against the adversarial samples. Results showed that, comparing the three algorithm’s performance, the extreme gradient boosting algorithm was the most robust against adversarial samples and adversarial training may benefit the robustness of the algorithms against lower intense adversarial samples. The contributions of this paper concern the evaluation of different aircraft trajectory prediction algorithms, the exploration of the effects of adversarial attacks, and the effect of the defense against adversarial samples with low perturbation compared to no defense mechanism.
DOCUMENT
For long flights, the cruise is the longest phase and where the largest amount of fuel is consumed. An in-cruise optimization method has been implemented to calculate the optimal trajectory that reduces the flight cost. A three-dimensional grid has been created, coupling lateral navigation and vertical navigation profiles. With a dynamic analysis of the wind, the aircraft can perform a horizontal deviation or change altitudes via step climbs to reduce fuel consumption. As the number of waypoints and possible step climbs is increased, the number of flight trajectories increases exponentially; thus, a genetic algorithm has been implemented to reduce the total number of calculated trajectories compared to an exhaustive search. The aircraft’s model has been obtained from a performance database, which is currently used in the commercial flight management system studied in this paper. A 5% average flight cost reduction has been obtained.
MULTIFILE
BACKGROUND: Patients' self-care behaviour is still suboptimal in many heart failure (HF) patients and underlying mechanisms on how to improve self-care need to be studied.AIMS: (1) To describe the trajectory of patients' self-care behaviour over 1 year, (2) to clarify the relationship between the trajectory of self-care and clinical outcomes, and (3) to identify factors related to changes in self-care behaviour.METHODS: In this secondary analysis of the COACH-2 study, 167 HF patients (mean age 73 years) were included. Self-care behaviour was assessed at baseline and after 12 months using the European Heart Failure Self-care Behaviour scale. The threshold score of ⩾70 was used to define good self-care behaviour.RESULTS: Of all patients, 21% had persistent poor self-care behaviour, and 27% decreased from good to poor. Self-care improved from poor to good in 10%; 41% had a good self-care during both measurements. Patients who improved self-care had significantly higher perceived control than those with persistently good self-care at baseline. Patients who decreased their self-care had more all-cause hospitalisations (35%) and cardiovascular hospitalisations (26%) than patients with persistently good self-care (2.9%, p < 0.05). The prevalence of depression increased at 12 months in both patients having persistent poor self-care (0% to 21%) and decreasing self-care (4.4% to 22%, both p < 0.05).CONCLUSION: Perceived control is a positive factor to improve self-care, and a decrease in self-care is related to worse outcomes. Interventions to reduce psychological distress combined with self-care support could have a beneficial impact on patients decreasing or persistently poor self-care behaviour.
DOCUMENT
The SPRONG-collaboration “Collective process development for an innovative chemical industry” (CONNECT) aims to accelerate the chemical industry’s climate/sustainability transition by process development of innovative chemical processes. The CONNECT SPRONG-group integrates the expertise of the research groups “Material Sciences” (Zuyd Hogeschool), “Making Industry Sustainable” (Hogeschool Rotterdam), “Innovative Testing in Life Sciences & Chemistry” and “Circular Water” (both Hogeschool Utrecht) and affiliated knowledge centres (Centres of Expertise CHILL [affiliated to Zuyd] and HRTech, and Utrecht Science Park InnovationLab). The combined CONNECT-expertise generates critical mass to facilitate process development of necessary energy-/material-efficient processes for the 2050 goals of the Knowledge and Innovation Agenda (KIA) Climate and Energy (mission C) using Chemical Key Technologies. CONNECT focuses on process development/chemical engineering. We will collaborate with SPRONG-groups centred on chemistry and other non-SPRONG initiatives. The CONNECT-consortium will generate a Learning Community of the core group (universities of applied science and knowledge centres), companies (high-tech equipment, engineering and chemical end-users), secondary vocational training, universities, sustainability institutes and regional network organizations that will facilitate research, demand articulation and professionalization of students and professionals. In the CONNECT-trajectory, four field labs will be integrated and strengthened with necessary coordination, organisation, expertise and equipment to facilitate chemical innovations to bridge the innovation valley-of-death between feasibility studies and high technology-readiness-level pilot plant infrastructure. The CONNECT-field labs will combine experimental and theoretical approaches to generate high-quality data that can be used for modelling and predict the impact of flow chemical technologies. The CONNECT-trajectory will optimize research quality systems (e.g. PDCA, data management, impact). At the end of the CONNECT-trajectory, the SPRONG-group will have become the process development/chemical engineering SPRONG-group in the Netherlands. We can then meaningfully contribute to further integrate the (inter)national research ecosystem to valorise innovative chemical processes for the KIA Climate and Energy.
Restoring rivers with an integrated approach that combines water safety, nature development and gravel mining remains a challenge. Also for the Grensmaas, the most southern trajectory of the Dutch main river Maas, that crosses the border with Belgium in the south of Limburg. The first plans (“Plan Ooievaar”) were already developed in the 1980s and were highly innovative and controversial, as they were based on the idea of using nature-based solutions combined with social-economic development. Severe floodings in 1993 and 1995 came as a shock and accelerated the process to implement the associated measures. To address the multifunctionality of the river, the Grensmaas consortium was set up by public and private parties (the largest public-private partnership ever formed in the Netherlands) to have an effective, scalable and socially accepted project. However, despite the shared long term vision and the further development of plans during the process it was hard to satisfy all the goals in the long run. While stakeholders agreed on the long-term goal, the path towards that goal remains disputed and depends on the perceived status quo and urgency of the problem. Moreover, internal and external pressures and disturbances like climate change or the economic crisis influenced perception and economic conditions of stakeholders differently. In this research we will identify relevant system-processes connected to the implementation of nature-based solutions through the lens of social-ecological resilience. This knowledge will be used to co-create management plans that effectively improve the long-term resilience of the Dutch main water systems.
Designing with the Sun is a KIEM-GoCI explorative research project on the theme Energy Transition and Sustainability. The project is aimed at network and agenda building and design research that explores new (cultural) practices of renewable energy consumption, based on a shift from ‘energy blindness’ to ‘energy awareness’. Up until now the solar industry has been propelled forward by technical innovations, offering mostly pragmatic, economic benefits to consumers. Innovation in this field mostly concerns making solar panels more efficient and less costly. However, to succeed, the energy transition also needs new cultural practices. These practices should reflect the ways renewables are different from fossil fuels. For solar, this means using more direct solar energy, when the sun is there, and being able to adapt to periods of low energy. Currently, consumers are mostly ‘blind’ to the infrastructure behind fossil-based energy. However, for energy sources such as solar and wind ‘awareness’ of their availability becomes more important. What could such an awareness look or feel like? How can it be enacted? And how can a change in practice that is more attuned to availability be experienced positively? Solar companies see opportunities in using design to help build motivating practices and narratives within the solar field, enabling awareness through personal relationships between consumer and solar energy. However, the knowledge of how to get there is lacking. In a research-through-design trajectory, and together with partners from the Creative Industries, Designing with the Sun aims to explore new ways of relating citizens to solar energy. Ultimately, these insights should enable the newly emerging field of solar design to contribute to the emergence of more sustainable and rewarding energy awareness and practices.
