Robot-assisted therapy has become increasingly popular and useful in post-stroke neurorehabilitation. This paper presents an overview of the design and control of the dual-arm Recupera exoskeleton to provide intense therapist-guided as well as self training for sensorimotor rehabilitation of the upper body. The exoskeleton features a lightweight design, high level of modularity, decentralized computing, and various levels of safety implementation. Due to its modularity, the system can be used as a wheel-chair mounted system or as a full-body system. Both systems enable a wide range of therapies while efficiently grounding the weight of the system and without compromising the patient’s mobility. Furthermore, two rehabilitation therapies implemented on the exoskeleton system, namely teach & replay therapy and mirror therapy, are presented along with experimental results.

Goal: Current brain-computer interfaces (BCIs) are usually based on various, often supervised, signal processing methods. The disadvantage of supervised methods is the requirement to calibrate them with recently acquired subject-specific training data. Here, we present a novel algorithm for dimensionality reduction (spatial filter), that is ideally suited for single-trial detection of event-related potentials (ERPs) and can be adapted online to a new subject to minimize or avoid calibration time. Methods: The algorithm is based on the well-known xDAWN filter, but uses generalized eigendecomposition to allow an incremental training by recursive least squares (RLS) updates of the filter coefficients. We analyze the effectiveness of the spatial filter in different transfer scenarios and combinations with adaptive classifiers. Results: The results show that it can compensate changes due to switching between different users, and therefore allows to reuse training data that has been previously recorded from other subjects. Conclusions: The presented approach allows to reduce or completely avoid a calibration phase and to instantly use the BCI system with only a minor decrease of performance. Significance: The novel filter can adapt a precomputed spatial filter to a new subject and make a BCI system user independent.

A current trend in the development of assistive devices for rehabilitation, for example exoskeletons or active orthoses, is to utilize physiological data to enhance their functionality and usability, for example by predicting the patient’s upcoming movements using electroencephalography (EEG) or electromyography (EMG). However, these modalities have different temporal properties and classification accuracies, which results in specific advantages and disadvantages. To use physiological data analysis in rehabilitation devices, the processing should be performed in real-time, guarantee close to natural movement onset support, provide high mobility, and should be performed by miniaturized systems that can be embedded into the rehabilitation device. We present a novel Field Programmable Gate Array (FPGA) -based system for real-time movement prediction using physiological data. Its parallel processing capabilities allows the combination of movement predictions based on EEG and EMG and additionally a P300 detection, which is likely evoked by instructions of the therapist. The system is evaluated in an offline and an online study with twelve healthy subjects in total. We show that it provides a high computational performance and significantly lower power consumption in comparison to a standard PC. Furthermore, despite the usage of fixed-point computations, the proposed system achieves a classification accuracy similar to systems with double precision floating-point precision.

In neuroscience large amounts of data are recorded to provide insights into cerebral information processing and function. The successful extraction of the relevant signals becomes more and more challenging due to increasing complexities in acquisition techniques and questions addressed. Here, automated signal processing and machine learning tools can help to process the data, e.g., to separate signal and noise. With the presented software pySPACE (http://pyspace.github.io/pyspace), signal processing algorithms can be compared and applied automatically on time series data, either with the aim of finding a suitable preprocessing, or of training supervised algorithms to classify the data. pySPACE originally has been built to process multi-sensor windowed time series data, like event-related potentials from the electroencephalogram (EEG). The software provides automated data handling, distributed processing, modular build-up of signal processing chains and tools for visualization and performance evaluation. Included in the software are various algorithms like temporal and spatial filters, feature generation and selection, classification algorithms and evaluation schemes. Further, interfaces to other signal processing tools are provided and, since pySPACE is a modular framework, it can be extended with new algorithms according to individual needs. In the presented work, the structural hierarchies are described. It is illustrated how users and developers can interface the software and execute offline and online modes. Configuration of pySPACE is realized with the YAML format, so that programming skills are not mandatory for usage. The concept of pySPACE is to have one comprehensive tool that can be used to perform complete signal processing and classification tasks. It further allows to define own algorithms, or to integrate and use already existing libraries.

Renewable energy production is one of the most important strategies to reduce the emission of greenhouse gases. However, wind and solar energy especially depend on time-varying properties of the environment, such as weather. Hence, for the control and stabilization of electricity grids, the accurate forecasting of energy production from renewable energy sources is essential. This study provides an empirical comparison of the forecasting accuracy of electricity generation from renewable energy sources by different deep learning methods, including five different Transformer-based forecasting models based on weather data. The models are compared with the long short-term memory (LSTM) and Autoregressive Integrated Moving Average (ARIMA) models as a baseline. The accuracy of these models is evaluated across diverse forecast periods, and the impact of utilizing selected weather data versus all available data on predictive performance is investigated. Distinct performance patterns emerge among the Transformer-based models, with Autoformer and FEDformer exhibiting suboptimal results for this task, especially when utilizing a comprehensive set of weather parameters. In contrast, the Informer model demonstrates superior predictive capabilities for onshore wind power and photovoltaic (PV) power production. The Informer model consistently performs well in predicting both onshore wind and PV energy. Notably, the LSTM model outperforms all other models across various categories. This research emphasizes the significance of selectively using weather parameters for improved performance compared to employing all parameters and a time reference. We show that the suitability and performance of a prediction model can vary significantly, depending on the specific forecasting task and the data that are provided to the model.

Most human activity recognition (HAR) systems are based on computer vision or wearable sensors. However, these methods have limitations, such as privacy concerns, the need for high computational power, and the requirement for frequent battery recharging. In this paper, we present a distributed multisensor system for the recognition of human activities based on ambient audio and vibration data. The system comprises several ambient multisensor nodes (AMSNs) located within a smart home environment, along with a data transfer and analysis system. The data transfer and analysis system includes an IoT gateway and an MQTT broker. The data obtained by the AMSNs is classified using various machine learning algorithms. We utilized a ResNet model to analyze ambient acoustic signals and an encoder network for the classification of vibrational data. An empirical evaluation of the proposed approachwas conducted using a dataset recorded in a real-world environment and different combinations of modalities and sensor setups. The results indicate that audio and vibration-based data can be leveraged for accurate activity detection, eliminating the need for specialized sensor equipment. These findings have several implications for smart home environments, such as improving user experience and comfort or enhancing safety and security for inhabitants.