Patient-ventilator asynchrony is one of the largest challenges in mechanical ventilation and is associated with prolonged ICU stay and increased mortality. The aim of this paper is to automatically detect and classify the different types of patient-ventilator asynchronies during a patient's breath using the typically available data on commercially available ventilators. This is achieved by a detection and classification framework using an objective definition of asynchrony and a supervised learning approach. The achieved detection performance of the near-real time framework on a clinical dataset is a significant improvement over current clinical practice, therewith and, this framework has the potential to significantly improve the patient comfort and treatment outcomes.

Repetitive control (RC) has shown to achieve superior rejection of periodic disturbances. Many nonlinear systems are subject to repeating disturbances. The aim of this article is to develop a continuous-time RC design with stability guarantees for nonlinear Lur'e-type systems. Approximate output tracking is achieved by combining an internal model, consisting of a finite number of linear oscillators with frequencies at the reference frequency and at its multiples, with a stabilizer that guarantees a convergence property of the closed-loop system. The developed RC approach is applied to a nonlinear mechanical ventilation system for intensive care units (ICUs), which can be modeled as a Lur'e-type system. The experimental study confirms that the RC scheme is able to successfully follow the desired target pressure profile to properly support the ventilation needs of an adult patient.

Cooperative adaptive cruise control (CACC) is a potential solution to decrease traffic jams caused by shock waves, increase the road capacity, decrease fuel consumption and improve safety. This paper proposes an integrated solution to a combination of four challenges in these CACC systems. One of the technological challenges is how to guarantee string stability (the ability to avoid amplification of dynamic vehicle responses along the string of vehicles) under nominal operational conditions. The second challenge is how to apply this solution to heterogeneous vehicles. The third challenge is how to maintain confidentiality of the vehicle parameters. Finally, the fourth challenge is to find a method which improves robustness against wireless packet loss. This paper proposes a model predictive control approach in combination with a feed-forward control design, which is based on a shared vector of predicted accelerations over a finite time horizon. This approach is shown to be applicable to a heterogeneous sequence of vehicles, while the vehicle parameters remain confidential. In previous works such an approach has shown to increase robustness against packet losses. Conditions for string stability are presented for the nominal operational conditions. Experimental results are presented and indeed demonstrate string stable behavior.