Pushing physiological sensing into the wild: this work equips our ultra-low-power physiological BI-Vital sensor with an int8-quantized autoencoder that produces a real-time signal-quality index (SQI) for electrocardiograms (ECG) beside standard heart rate computations. The supervised model, trained on PhysioNet CinC2017 and three newly annotated BI-Vital single-lead ECG datasets, combines a compact encoder-decoder with a lightweight classifier head. On the STM32L476JE microcontroller from BI-Vital, the model uses 31 kB of RAM and 85 kB of flash memory, completes inference in 195 ms and still leaves room for parallel sensor services. Across eight train/test splits the approach generalizes well, reaching an F1 score of 0.988 while maintaining$2 \cdot 10^{-3}$performance loss after quantization. By converting raw continuous ECG data into periodic heart rate and SQI recordings, storage space on the device is reduced by 99.6%, demonstrating a practical way for reliable, data-efficient monitoring outside the laboratory.

This paper addresses the need for an indoor-focused, easy-to-replicate road-sign dataset that captures unprocessed raw image data. Existing datasets typically focus on processed RGB images, which limits their usefulness for research on embedded, end-to-end machine learning. To fill this gap, a Raspberry Pi Camera Module v1.3 was mounted on autonomous mini robots, which ran continuously in various indoor settings. Over a period of two months, approximately 70,000 10-bit, 5-megapixel images were stored as TIFF files. Exposure and ISO were intentionally varied to introduce motion blur, noise, overexposure, and underexposure. The resulting labeled dataset comprises around 47,000 bounding boxes for 87 sign categories, including danger, regulatory, directional, demo-specific, and unknown signs. This work provides a compact, low-cost framework that enables researchers and educators to explore algorithms on raw images in a reproducible indoor setting through both long-term data collection and in-classroom demonstrations.

This paper explores a method for generating plausible cable routings in free space by combining curve-energy formulations from structural dynamics, knot theory, and robot path planning. The approach minimizes a composite energy functional—accounting for smoothness and collision avoidance—while encouraging a predefined cable length through an arc-length energy term. Preliminary results demonstrate the method’s ability to produce smooth, collision-free cable curves in simple example tasks, offering a physics-inspired foundation for early-stage design of electrical wiring in free space.

The integration of data-driven models and specifically machine learning for conditon monitoring and predictive maintenance into companies, especially small and medium-sized enterprises, offers significant opportunities in reducing costs, operating more sustainably, and maintaining long-term competitiveness. However, many small and medium-sized enterprises lack the necessary resources and expertise to derive knowledge from data and integrate their own machine learning based solutions. To address this challenge, a framework is presented that enables the automated generation of data-driven models with a particular focus on condition monitoring and predictive maintenance, but applicable to other use cases as well. Using a dataset from the 2022 data challenge of the prognostics and health management society, it is demonstrated that the framework can generate high-performing models, achieving F1-scores up to 0.998, exemplarily for a classification task.

Although digital twins are increasingly being used to represent physical assets in industrial automation, most of them remain passive, merely building a digital shadow of the asset. Their potential as active, autonomous components in cognitive control architectures remains largely unexplored. This paper presents a novel approach to realize executable digital twins within cognitive operators by embedding the Sense–Plan–Act paradigm into standardized submodels of the Asset Administration Shell. Specifically, the submodel Time Series Data is used to capture dynamic system state for the sensing phase, while the Asset Interfaces Description represents executable interactions for the planning phase. By enabling each assets’ cognitive operator to interpret these submodels, distributed systems can reason and act through their digital representation, while maintaining semantic interoperability and compliance with standards. The concept is validated in a decentralized task allocation scenario using modular autonomous robots. Initial results confirm the technical feasibility and reusability of the approach and highlight the potential of semantically enriched digital twins in future industrial systems.

Klarhorst C, Quirin D, Hesse M, Rückert U. A Digital Twin Implementation for the AMiRo. In: 2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA). IEEE; 2024: 1-4.

The holistic application of data-driven value-adding services (DDSs) to shop-floor assets (SFAs; e.g. equipment, machines, components) is a major obstacle, particularly for small and medium-sized enterprises (SMEs): Due to the high complexity and required expertise in various disciplines. It is necessary to i) select suitable DDSs for a relevant component in production, ii) provide data for their training, iii) deploy the DDSs in the given IT/OT infrastructure, and iv) setup data-streams between SFAs, DDSs, and dashboards. Currently, many companies are implementing flagship projects that go through the necessary steps for individual components, but these isolated solutions are not scalable due to the need for manual intervention. This paper describes how to completely automatize the four steps and their consolidation in a scalable Industry 4.0 one-stop-shop solution. To achieve this goal, each asset is equipped with an Asset Administration Shell (AAS) that specifies, in particular, the represented asset's capabilities, the data required to apply such a capability and the data generated by a capability. Based on the AASs of SFAs, DDSs, and computing resources (CRs), a matching service suggests automatically which DDSs would add value to which SFAs and, for each SFA-DDS match, in which CR to deploy the DDS. A trade fair demonstration provides strong support for the statements made: The one-stop-shop solution including the automatic matching greatly simplifies the application of data-driven services and, in some cases, even makes it possible at all.

Addressing the demand for scalable and efficient deployment of machine learning (ML) models on mobile devices and especially microcontrollers, this research introduces a hardware-in-the-loop (HIL) deployment setup within the producer-consumer software architecture of the BI-Vital, a chest-mounted body sensor designed by our research group. The sensor provides real-time monitoring of various physiological and environmental parameters, enhanced by the integration of tiny machine learning (TinyML). Leveraging the UCI-HAR dataset for Human Activity Recognition (HAR), this study focuses on optimizing ML models’ hyperparameters to balance inference time, memory, accuracy, and power consumption. An efficiency score E is proposed to assess models in this unique context. The results illustrate the trade-offs between the models: Decision Trees offer reduced power usage, Multilayer Perceptrons ensure high accuracy with minimal memory requirements, while Convolutional Neural Networks present limitations due to extended inference times. The results emphasize the potential of TinyML in wearable physiological monitoring, especially for optimizing models for resource-limited devices in real-world applications.

One necessary part of Industry 4.0 is the availability and accessibility of data processing pipelines. This paper shows the ongoing development of ML4ProFlow, a framework that brings together the following parts: First, it provides the management of execution environments. Second, it specifies processing modules that focus on reusability and cross-platform usage. Third, it comes with a benchmarking automation to help developers implementing and analyzing modules and their combination. Those three integral parts of the framework are presented and the usability is shown.

Today's high complexity and required expertise in various disciplines for data-based evaluations of shop-floor assets is challenging. This paper describes the ongoing development towards an Industry 4.0 ecosystem enabling Smart Services and shop-floor assets to network autonomously. Three partial solutions are combined for this purpose: Industry 4.0 digital twins, automated data streams and a Smart Service toolbox. A prototypical implementation proves the general practicability. Furthermore, future work is outlined to achieve full autonomy.

We present a novel approach of multi-modal deep generative models and apply this to coordinated heterogeneous multi-agent active sensing. A major approach to achieve this objective is to train a multi-modal variational Auto Encoder (M2VAE) that integrates the information of different sensor modalities into a joint latent representation. Furthermore, we derive an objective from the M2VAE that enables the maximization of the evidence lower bound via selection of sensor modalities. Using this approach as a direct reward signal to a multi-modal and multi-agent deep reinforcement learning setup leads intuitively to an epistemic active sensing behavior that coordinately resolves the ambiguity of observations.

In the past, several contributions and proposals for the implementation of Ultra-wideband (UWB)-based localization and positioning solutions on the system level were made. However, most of them are limited to a unidirectional approach, i.e. data communication is in one direction (from a transmitter to a receiver). This restricts the systems' use-case to either navigation or tracking. In this paper, we demonstrate an UWB-based bidirectional localization system which is capable of acting as both a navigation and tracking system in a single wireless platform. Regarding this, we proposed a complete set of such a system and outline the implementation process in the paper. A true-range multilateration method is used as a positioning algorithm in the implemented system, for which we proposed a novel Non-Line-of-Sight (NLOS) mitigation technique. The experimental evaluation of the proposed system was done in comparison with a commercially available UWB system. In the experiments, we used a Vicon camera system as a reference.

Brain-Computer Interfaces (BCIs) based on Steady-State Visually Evoked Potentials (SSVEPs) can be used as hand-free control device. To utilize this control method in a real life scenario, we created a system in which a smart home is controlled by BCI. Six devices in the smart home environment could be controlled with the BCI system: The entrance door, the wardrobe, the kitchens' worktop and drawers, the light system of all the rooms and a guide light. In the presented paper, the visual stimuli for the BCI were placed at multiple screens in the smart home (placed at different locations such as the kitchen and the living room). The processing was done on one computer, located in the living room. The placement of the visual stimuli corresponded to the actuators that were controlled, e.g. the kitchen drawers were linked to the stimuli displayed in the kitchen. An online experiment was conducted where participants went through a scenario consisting of thirteen SSVEP-BCI selections in total. Eight healthy participants took part in the experiments. For BCI signal acquisition, a mobile EEG amplifier was used. Participants walked freely around the rooms during the experiment. An average accuracy of 81 % was achieved, which suggests that the SSVEP-system is suitable to control the external devices in the smart home, and that the system can be expanded to involve more actuators.

In absence of clock synchronization, Two-Way Ranging (TWR) is the most commonly used technique for measuring the distance between two wireless transceivers. The existing time-of-flight (TOF) error estimation model, the IEEE 802.15.4-2011 standard, is specifically based on clock drift error. However, it is insufficient when an in-depth comparative analysis of different TWR methods is required. In this paper, we propose an extended TOF error estimation model for TWR methods, based on the IEEE 802.15.4 standard. Using the proposed model, we perform an analytical study of TOF error estimation among different TWR methods. The model is validated with numerical simulation results. Moreover, we demonstrate the pitfalls of the symmetric double-sided TWR (SDS-TWR) method, which is commonly used to reduce the TOF error due to clock drifts.

The connected chair is part of the Supportive Personal Coach in the KogniHome project, which offers guided fitness training, relaxation, and assistive functions. The chair comes with integrated sensors, actuators, control logic and wireless transceiver. The sensors are able to measure respiration and heart rate as well as the user's actions. The actuators are used to adjust the chair to the actual user's needs and the transceiver is used to connect wireless sensor nodes and to exchange data with a base station. Additional value is generated by connecting the chair to the smart home environment, which enables and expands novel features and applications.

Energy efficiency is the most outstanding design criterion for wireless sensor nodes and especially wireless body sensors. Because a detailed measurement of the system's power consumption is not possible during the design process and often too complex for already manufactured devices, the power consumption has to be estimated. This leads to the need for a comprehensive and modular model for the power consumption of WSNs, which is proposed in this work. Due to the modular structure of the model the user is able to get a first estimate in an early stage of the design process (e.g. choose components) and to get a more accurate estimation later in the design process by lowering the abstraction level. This tackles the demanding trade-off between accuracy and usability in modeling.

Body sensors have a promising contribution to health promotion in many areas of daily life (telemedicine, corporate health care or recreational sports). However, the valid measurement of vital signs and kinematic data strongly depends on the signals' quality and the users' compliance (proper usage). Although, there is a lot of research work concerning accuracy and calibration of wireless body sensors the human user is typically not involved. Thus, in this work, we present a software assistant (wizard) that guides users during the process of attaching and setting up a wireless body sensor. Furthermore, insights of the implemented software as well as the utilized quality measures and calibration steps are given (ECG, respiration sensor and accelerometer). With the proposed software assistant, the users are instructed to correctly attach the body sensor and calibrate or verify the operability of the various sensor elements. The primary goal is to encourage compliance and the users' sense of control. In this way, we want to reduce faulty operation and ensure optimal signal quality.

Raising the awareness of being physically active by utilizing wearable body sensors has become a popular research topic. Recent approaches combine physical and physiological information to obtain a precise prediction of a person;s physical activity ratio. However, the error in the determination of physical activity due to invalid physiological values that are resulting from underlying signal disturbances, has so far not been considered. We therefore present a robust measure of activity that fuses accelerometer data, heart rate and other personalized features, and is adaptively responding to missing physiological sensor data. To set up the model, we make use of regression analysis (MARS). Our findings indicate the need for considering signal quality when estimating physical activity. The predictive model shows close agreement (R2= 0.97) to the reference from indirect calorimetry, even if the physiological information is partly corrupted.