Data-informed reservoir computing for efficient time-series prediction.

We propose a new approach to dynamical system forecasting called data-informed-reservoir computing (DI-RC) that, while solely being based on data, yields increased accuracy, reduced computational cost, and mitigates tedious hyper-parameter optimization of the reservoir computer (RC). Our DI-RC approach is based on the recently proposed hybrid setup where a knowledge-based model is combined with a machine learning prediction system, but it replaces the knowledge-based component by a data-driven model discovery technique. As a result, our approach can be chosen when a suitable knowledge-based model is not available. We demonstrate our approach using a delay-based RC as the machine learning component in conjunction with sparse identification of nonlinear dynamical systems for the data-driven model component. We test the performance on two example systems: the Lorenz system and the Kuramoto-Sivashinsky system. Our results indicate that our proposed technique can yield an improvement in the time-series forecasting capabilities compared with both approaches applied individually, while remaining computationally cheap. The benefit of our proposed approach, compared with pure RC, is most pronounced when the reservoir parameters are not optimized, thereby reducing the need for hyperparameter optimization.

Master Memory Function for Delay-Based Reservoir Computers With Single-Variable Dynamics.

We show that many delay-based reservoir computers considered in the literature can be characterized by a universal master memory function (MMF). Once computed for two independent parameters, this function provides linear memory capacity for any delay-based single-variable reservoir with small inputs. Moreover, we propose an analytical description of the MMF that enables its efficient and fast computation. Our approach can be applied not only to single-variable delay-based reservoirs governed by known dynamical rules, such as the Mackey-Glass or Stuart-Landau-like systems, but also to reservoirs whose dynamical model is not available.

[Early Detection of Psychological Comorbidity in Patients Admitted to Dermatological and Internal Medicine Wards: A New Care Model for Psychosomatic Consultation Service]. / Früherkennung von psychischer Komorbidität in der stationären dermatologischen und internistischen Versorgung: Darstellung eines neuen Versorgungskonzeptes.

This article explains the development and implementation of a psychosomatic screening and consultation service for inpatient somatic care. Approximately one in six somatic inpatients has a mental disorder. It is estimated that only half of these cases are properly identified. Consequently, a large proportion of patients remains untreated. To address this gap in care, a psychosomatic early detection programme was developed by an interdisciplinary working group. This programme is based on the Patient Health Questionnaire-4 (PHQ-4), a psychometrically very well evaluated ultra-short screening questionnaire for the detection of depressive and anxiety disorders. For implementation in routine inpatient care, the PHQ-4 was programmed as a form in the electronic medical record and administered by nursing staff during the admission interview. If the PHQ-4 screening result indicates the presence of a mental comorbidity and the patient expresses a wish for assessment of this disorder, a psychosomatic consultation is automatically ordered. The PHQ-4 was implemented into the clinical routine in four internal medicine and three dermatology wards of the University Medical Center Hamburg-Eppendorf. Documentation of the early diagnosis in the electronic patient record is a minimally costly, less time-consuming and practicable method of providing patients with holistic care through rapid interdisciplinary referral. An evaluation of cost-effectiveness, clinical efficiency, and acceptance is still pending.

[Screening for mental comorbidities in dermatology : Successful implementation of a screening for mental comorbidities in the field of inpatient dermatological treatment]. / Screening auf psychische Komorbiditäten in der Dermatologie : Erfolgreiche Implementierung eines Screenings auf psychische Komorbiditäten im Bereich der stationären dermatologischen Versorgung.

BACKGROUND: Anxiety and depression are common in the field of inpatient somatic treatment. Especially in dermatology in which the treatment of chronic diseases is very common and the risk of stigmatization by society is particularly high, mental disorders appear in every third patient. Dermatological diseases and mental disorders often negatively interact with each other leading to increased morbidity. Dermatological guidelines recommend early detection, but this is often not adequately done in practice. MATERIALS AND METHODS: We present the implementation of an easy screening for mental comorbidities in the field of inpatient dermatological treatment by using a short questionnaire. This so-called Patient Health Questionnaire­4 (PHQ-4) consists of four questions regarding anxiety disorders and depression. Upon reaching a certain number of points, a psychosomatic consult is automatically requested. As a result the patient's stress is relieved and the necessary holistic treatment becomes possible. RESULTS: In 2019, 83% of inpatients in our clinic were screened using the PHQ­4; 98 psychosomatic consults were performed. CONCLUSION: Our findings so far have shown the benefit of the screening with a minimal investment of time. We recommend its comprehensive use in the field of inpatient dermatological treatment.

Deep time-delay reservoir computing: Dynamics and memory capacity.

The deep time-delay reservoir computing concept utilizes unidirectionally connected systems with time-delays for supervised learning. We present how the dynamical properties of a deep Ikeda-based reservoir are related to its memory capacity (MC) and how that can be used for optimization. In particular, we analyze bifurcations of the corresponding autonomous system and compute conditional Lyapunov exponents, which measure generalized synchronization between the input and the layer dynamics. We show how the MC is related to the systems' distance to bifurcations or magnitude of the conditional Lyapunov exponent. The interplay of different dynamical regimes leads to an adjustable distribution between the linear and nonlinear MC. Furthermore, numerical simulations show resonances between the clock cycle and delays of the layers in all degrees of MC. Contrary to MC losses in single-layer reservoirs, these resonances can boost separate degrees of MC and can be used, e.g., to design a system with maximum linear MC. Accordingly, we present two configurations that empower either high nonlinear MC or long time linear MC.