arXiv subjects

Martin Steinert

Publications and source records attributed to Martin Steinert.

10 recordsLinked to original sources

arXiv2025

Circuit-free cardiovascular monitoring via skin-interfaced nanophotonics

Nanoscale mechano-optical surfaces enable electronics-free strain sensing, attractive for skin-interfaced devices, yet reported implementations require laser/spectrometer interrogation, negating this advantage. Here, we report electrically passive mechanical transduction of arterial pulsation into diffractive colour shifts read by unmodified smartphone cameras, enabled by a dual-function monolithic poly-dimethylsiloxane (PDMS) film. Using large-area double-sided nanoimprinting, we achieve a strain-sensitive nanophotonic surface on one face of the film and a bio-inspired 3D structural adhesive on the other. We measure strain-dependent optical response and reproduce it in colour-mixing optical simulations. In uniaxial cyclic loading tests, 2% strain produces a 9% RGB-intensity modulation, stable over 1000 cycles. Further, 3D structuring improves adhesive shear strength by 65% on skin over flat PDMS. Hand-held smartphone recordings in humans ($n=13$) resolve sub-beat hemodynamics in agreement with clinical reference (per-beat waveform $\rho=0.94 \pm 0.03$), exceeding established non-invasive techniques such as active reflectance photoplethysmography (PPG), imaging PPG, and piezoelectric pulse-force sensors in simultaneous recordings. Importantly, mechanical transduction at the elastomer--air interface presents an optical cardiovascular monitoring approach agnostic to dermal-melanin, a known PPG confounder. Together, these advances establish camera-readable mechanochromic elastomers as versatile materials platforms for wearable cardiovascular monitoring, point-of-care diagnostics, and electronics-free human-machine interfaces.

physics.app-ph↗

arXiv2025

Foundation models on the bridge: Semantic hazard detection and safety maneuvers for maritime autonomy with vision-language models

The draft IMO MASS Code requires autonomous and remotely supervised maritime vessels to detect departures from their operational design domain, enter a predefined fallback that notifies the operator, permit immediate human override, and avoid changing the voyage plan without approval. Meeting these obligations in the alert-to-takeover gap calls for a short-horizon, human-overridable fallback maneuver. Classical maritime autonomy stacks struggle when the correct action depends on meaning (e.g., diver-down flag means people in the water, fire close by means hazard). We argue (i) that vision-language models (VLMs) provide semantic awareness for such out-of-distribution situations, and (ii) that a fast-slow anomaly pipeline with a short-horizon, human-overridable fallback maneuver makes this practical in the handover window. We introduce Semantic Lookout, a camera-only, candidate-constrained VLM fallback maneuver selector that selects one cautious action (or station-keeping) from water-valid, world-anchored trajectories under continuous human authority. On 40 harbor scenes we measure per-call scene understanding and latency, alignment with human consensus (model majority-of-three voting), short-horizon risk-relief on fire hazard scenes, and an on-water alert->fallback maneuver->operator handover. Sub-10 s models retain most of the awareness of slower state-of-the-art models. The fallback maneuver selector outperforms geometry-only baselines and increases standoff distance on fire scenes. A field run verifies end-to-end operation. These results support VLMs as semantic fallback maneuver selectors compatible with the draft IMO MASS Code, within practical latency budgets, and motivate future work on domain-adapted, hybrid autonomy that pairs foundation-model semantics with multi-sensor bird's-eye-view perception and short-horizon replanning. Website: kimachristensen.github.io/bridge_policy

cs.RO↗

arXiv2024

GluPredKit: Development and User Evaluation of a Standardization Software for Blood Glucose Prediction

Blood glucose prediction is an important component of biomedical technology for managing diabetes with automated insulin delivery systems. Machine learning and deep learning algorithms hold the potential to advance this technology. However, the lack of standardized methodologies impedes direct comparisons of emerging algorithms. This study addresses this challenge by developing GluPredKit, a software platform designed to standardize the training, testing, and comparison of blood glucose prediction algorithms. GluPredKit features a modular, open-source architecture, complemented by a command-line interface, comprehensive documentation, and a video tutorial to enhance usability. To ensure the platform's effectiveness and user-friendliness, we conducted preliminary testing and a user study. In this study, four participants interacted with GluPredKit and provided feedback through the System Usability Scale (SUS) and open-ended questions. The findings indicate that GluPredKit effectively addresses the standardization challenge and offers high usability, facilitating direct comparisons between different algorithms. Additionally, it serves an educational purpose by making advanced methodologies more accessible. Future directions include continuously enhancing the software based on user feedback. We also invite community contributions to further expand GluPredKit with state-of-the-art components and foster a collaborative effort in standardizing blood glucose prediction research, leading to more comparable studies.

cs.SE↗

arXiv2024

ChatGPT as an inventor: Eliciting the strengths and weaknesses of current large language models against humans in engineering design

This study compares the design practices and performance of ChatGPT 4.0, a large language model (LLM), against graduate engineering students in a 48-hour prototyping hackathon, based on a dataset comprising more than 100 prototypes. The LLM participated by instructing two participants who executed its instructions and provided objective feedback, generated ideas autonomously and made all design decisions without human intervention. The LLM exhibited similar prototyping practices to human participants and finished second among six teams, successfully designing and providing building instructions for functional prototypes. The LLM's concept generation capabilities were particularly strong. However, the LLM prematurely abandoned promising concepts when facing minor difficulties, added unnecessary complexity to designs, and experienced design fixation. Communication between the LLM and participants was challenging due to vague or unclear descriptions, and the LLM had difficulty maintaining continuity and relevance in answers. Based on these findings, six recommendations for implementing an LLM like ChatGPT in the design process are proposed, including leveraging it for ideation, ensuring human oversight for key decisions, implementing iterative feedback loops, prompting it to consider alternatives, and assigning specific and manageable tasks at a subsystem level.

cs.HC↗

arXiv2020

Digitally Capturing Physical Prototypes During Early-Stage Engineering Design Projects for Initial Analysis of Project Output and Progression

Aiming to help researchers capture output from the early stages of engineering design projects, this article presents a new research tool for digitally capturing physical prototypes. The motivation for this work is to collect observations that can aid in understanding prototyping in the early stages of engineering design projects, and this article investigates if and how digital capture of physical prototypes can be used for this purpose. Early-stage prototypes are usually rough and of low-fidelity and are thus often discarded or substantially modified through the projects. Hence, retrospective access to prototypes is a challenge when trying to gather accurate empirical data. To capture the prototypes developed through the early stages of a project, a new research tool has been developed for capturing prototypes through multi-view images, along with metadata describing by whom, why, when and where the prototypes were captured. Over the course of 17 months, this research tool has been used to capture more than 800 physical prototypes from 76 individual users across many projects. In this article, one project is shown in detail to demonstrate how this capturing system can gather empirical data for enriching engineering design project cases that focus on prototyping for concept generation. The authors also analyse the metadata provided by the system to give understanding into prototyping patterns in the projects. Lastly, through enabling digital capture of large quantities of data, the research tool presents the foundations for training artificial intelligence-based predictors and classifiers that can be used for analysis in engineering design research.

cs.HC↗

arXiv2019

On Applying Machine Learning/Object Detection Models for Analysing Digitally Captured Physical Prototypes from Engineering Design Projects

While computer vision has received increasing attention in computer science over the last decade, there are few efforts in applying this to leverage engineering design research. Existing datasets and technologies allow researchers to capture and access more observations and video files, hence analysis is becoming a limiting factor. Therefore, this paper is investigating the application of machine learning, namely object detection methods to aid in the analysis of physical porotypes. With access to a large dataset of digitally captured physical prototypes from early-stage development projects (5950 images from 850 prototypes), the authors investigate applications that can be used for analysing this dataset. The authors retrained two pre-trained object detection models from two known frameworks, the TensorFlow Object Detection API and Darknet, using custom image sets of images of physical prototypes. As a result, a proof-of-concept of four trained models are presented; two models for detecting samples of wood-based sheet materials and two models for detecting samples containing microcontrollers. All models are evaluated using standard metrics for object detection model performance and the applicability of using object detection models in engineering design research is discussed. Results indicate that the models can successfully classify the type of material and type of pre-made component, respectively. However, more work is needed to fully integrate object detection models in the engineering design analysis workflow. The authors also extrapolate that the use of object detection for analysing images of physical prototypes will substantially reduce the effort required for analysing large datasets in engineering design research.

cs.CV↗

arXiv2019

Development and verification of a simulation for leveraging results of a human subjects programming experiment

Quantitatively evaluating and comparing the performance of robotic solutions that are designed to work under a variety of conditions is inherently challenging because they need to be evaluated under numerous precisely repeatable conditions Manually acquiring this data is time consuming and imprecise. A deterministic simulation can reproduce the conditions and can evaluate the solutions autonomously, faster and statistically significantly. We developed such a simulation designated to leverage data from a human-subject experiment post-experimentally. We present the development of the simulation and the verification that it actually reproduces the results obtained with the physical robot. The aim of this publication is to provide insight into the development details such that other researchers can replicate the setup and to show the degree of validity of the simulation.

cs.RO↗

arXiv2018

Resource and Competence (Internal) View vs. Environment and Market (External) View when defining a Business

Startups is a popular phenomenon that has a significant impact on global economy growth, innovation and society development. However, there is still insufficient understanding about startups, particularly, how to start a new business in the relation to consequent performance. Toward this knowledge, we have performed an empirical study regarding the differences between a Resource and Competence View (Internal) vs Environment and Market View (External) when defining a Business. 701 entrepreneurs have reflected on their startups on nine classes of Resources (values, vision, personal objectives, employees and partners, buildings and rental contracts, cash and credit, patents, IPR's and brands, products and services and finally revenues and grants) and three elements of the Business Mission ("KeyContribution", "KeyMarket" and "Distinction"). It seems to be a tendency to favour the Internal View over the External View. This tendency is clearer in Stable Economies (Europe) than in Emerging Economies (South Africa). There seems to be a co-variation between the tendency to favour the Internal View and the tendency to focus on adding Resources. Finally, we found that an order-based analysis seems to explain the differences between the two views better than a number-based method.

q-fin.GN↗

arXiv2017

Building an Entrepreneurship Data Warehouse

The main principle of the Lean Startup movement is that static business planning should be replaced by a dynamic development, where products, services, business model elements, business objectives and activities are frequently changed based on constant customer feedback. Our ambition is to empirically measure if such changes of the business idea, the business model elements, the project management and close interaction with customers really increases the success rate of entrepreneurs, and in what way. Our first paper, Does Lean Startup really work? - Foundation for an empirical study presented the first attempt to model the relations we want to measure. This paper will focus on how to build and set up a test harness (from now on called the Entrepreneurship Platform or EP) to gather empirical data from Companies and how to store these data together with demographical and financial data from the PROFF-portal in the Entrepreneurial Data Warehouse (from now called the EDW). We will end the paper by discussing the potential methodological problems with our method, before we document a test run of our set-up to verify that we are actually able to populate the Data Warehouse with time series data

cs.CY↗

arXiv2017

Towards understanding startup product development as effectual entrepreneurial behaviors

Software startups face with multiple technical and business challenges, which could make the startup journey longer, or even become a failure. Little is known about entrepreneurial decision making as a direct force to startup development outcome. In this study, we attempted to apply a behaviour theory of entrepreneurial firms to understand the root-cause of some software startup s challenges. Six common challenges related to prototyping and product development in twenty software startups were identified. We found the behaviour theory as a useful theoretical lens to explain the technical challenges. Software startups search for local optimal solutions, emphasise on short-run feedback rather than long-run strategies, which results in vague prototype planning, paradox of demonstration and evolving throw-away prototypes. The finding implies that effectual entrepreneurial processes might require a more suitable product development approach than the current state-of-practice.

cs.CY↗