"This site requires JavaScript to work correctly"
minimize Header

Prof. Dr. Florian Wahl

  • Data Analytics
  • Machine Learning
  • Pattern Recognition
  • Embedded Systems
  • Ubiquitous Computing

Centre for Applied Research

Technology Campus Grafenau

Professor

A 011

0991/3615-8257

consulting time

by appointment via Mrs. Verena Windorfer-Bogner.

Sortierung:
Contribution
  • Florian Wahl
  • M. Milenkovic
  • O. Amft

A green autonomous self-sustaining sensor node for counting people in office environments.

In: 2012 5th European DSP Education and Research Conference (EDERC). pg. 203-207

IEEE

  • (2012)

DOI: 10.1109/EDERC.2012.6532255

show abstract

Energy consumption is of critical concern in large office buildings. While office spaces are dynamically used, current building automation systems lack information on space utilisation to adaptively adjust energy spending according to actual needs. In this work, we propose an approach to count people per office space using distributed strategically placed PIR sensor nodes. We present our concept of a self-powered PIR sensor node that is using a MSP430 family processor. The sensor node can be flexibly installed in building spaces providing specific advances over existing devices. We detail the design considerations, implementation, and evaluation of this novel embedded system. Our evaluations showed that the sensor node can emit triggers at 276 nAh, thus operating for 361 triggers in complete darkness on a single charge. The approach can be used for lighting, climate, and appliances control in office spaces.
Contribution
  • Florian Wahl
  • M. Milenkovic
  • O. Amft

A Distributed PIR-based Approach for Estimating People Count in Office Environments.

In: 2012 IEEE 15th International Conference on Computational Science and Engineering. pg. 640-647

IEEE

  • (2012)

DOI: 10.1109/ICCSE.2012.92

show abstract

Office buildings are key energy consumers and thus require attention to achieve efficient operation. While individual office spaces are dynamically used, current building automation does not receive information on utilisation that could be used to adaptively adjust energy consumption. In this work, we propose an approach to estimate people count per office space using distributed strategically placed PIR sensors and algorithms that can process the distributed sensor information. We detail our sensing node and evaluate its performance in an office installation. A sensor model was subsequently used in a floor-wide simulation of realistic occupant behaviours to investigate two algorithms to estimate people count per office space. The occupant behaviour simulations confirmed that our estimation algorithms can accurately predict people count in different office use scenarios. The errors introduced by the PIR masking time after a detection can be partially compensated when using distributed sensor information. Our approach can be used for dynamic, occupancy-dependent lighting, climate, and appliances control of office spaces.
Thesis
  • Florian Wahl

Gauss – A Green Autonomous Ubiquitous Self-Sustaining Sensor. Master Thesis.

Technical University of Eindhoven Eindhoven, Niederlande Faculty of Computer Science; Faculty of Electrical Engineering

  • 16.04.2012 (2012)

show abstract

With todays buildings being the largest CO2 producers in many world region the need to make tomorrows buildings more energy efficient emerges. An essential part of a buildings footprint is determined by the way its energy consuming installations such as heating, lighting and ventilation are controlled. In order to control these installations in a more sustainable way but without decreasing the users comfort, the number of people per building space (section or room) is an important measure as the need for heating, lighting, etc. strongly depends on it. The work proposed in this thesis introduces a whole system to measure the number of persons per building space without compromising the users privacy. This system consists of three main parts: 1) Sensor nodes based on passive infrared sensors (PIR) that rely solely on solar harvesting so no energy overhead is added to the buildings footprint. Furthermore the sensor nodes transmit their data through a wireless link which keeps the installation cost minimal. 2) An access point to collect the data sent by the nodes which then evaluates the data. 3) The algorithm used to evaluate the aggregated data and outputs the number of persons per building space as a result. In this work three different algorithms are introduced and then compared based on simulations. In addition to these three components, a test bench for automated testing of the node was built within the scope of this project. This test bench allows to artificially trigger the sensor and control the amount of light available to charge the node in programmable patterns. The sensor node prototype implementation was evaluated using the test bench. In complete darkness, the node could run for 269 triggers on a single charge. For benchmarking the proposed algorithms a complete simulation environment has been developed. Within this simulator it is possible to create an arbitrary building space, add persons that move around based on way points and sensors that work including an error model that allows to define the error probability. Simulations of the three developed estimation algorithms were performed. Results show that the best performing probabilistic algorithm achieves an error rate of one error or less at for sensor error probabilities of 20% or less.
Contribution
  • Florian Wahl
  • O. Amft

Using RFID tags as reference for phone location and orientation in daily life.

In: Proceedings of the 4th Augmented Human International Conference. pg. 194-197

  • Eds.:
  • A. Bulling
  • C. Holz
  • A. Schmidt

ACM New York, NY, USA

  • (2013)

DOI: 10.1145/2459236.2459269

show abstract

This paper investigates a novel approach to obtain location and orientation annotation for smartphones in real-life recordings. We attached RFID tags to places where phones are located in daily life, such as pockets and backpacks. The RFID reader integrated in modern smartphones was used to continuously scan for registered tags. In a first evaluation across several full-day recordings and using nine locations, our approach achieved an accuracy of 80 % when compared to a manual diary. Only 5.3 % of all tags were missed. We conclude that RFID-based location and orientation tagging is a viable option to obtain ground truth reference for real-life activity recognition algorithm developments.
Contribution
  • Florian Wahl
  • O. Amft

Personalised phone placement recognition in daily life using RFID tagging.

In: 2014 IEEE International Conference on Pervasive Computing and Communication Workshops (PERCOM WORKSHOPS). pg. 19-26

IEEE

  • (2014)

DOI: 10.1109/PerComW.2014.6815159

show abstract

We investigate the recognition of phone placement in the vicinity of their user using different pattern classification strategies and phone-integrated sensors. The novel approach in our work is to use RFID tags for annotating phone placement. We use the NFC function of smartphones to continuously read tags during training data acquisition at different phone sites. We show that the RFID-based annotation approach requires minimal effort from users to acquire annotated data, enabling users to personalise phone placement recognition. In an evaluation study with 39 hours of phone placement recordings from six participants and four frequently used phone sites, we compare the annotation accuracy of our RFID-based approach to expert-verified annotations. Our results show that RFID-based annotations perform approx. 2 % below the expert-verified variant. Personalised classification models outperform models trained from all participants, suggesting that our RFID-based approach is viable for a personalised phone placement recognition. Sub-sequently, we analyse the amount of training data, sensors, and features required to achieve an average recognition rate of 80 %.
Contribution
  • Florian Wahl
  • T. Kantermann
  • O. Amft

How much light do you get? Estimating daily light exposure using smartphones.

In: Proceedings of the 2014 ACM International Symposium on Wearable Computers. pg. 43-46

  • Eds.:
  • M. Beigl
  • T. Martin
  • L. Dunne

ACM New York, NY, USA

  • (2014)

DOI: 10.1145/2634317.2634346

show abstract

We present an approach to estimate a persons light exposure using smartphones. We used web-sourced weather reports combined with smartphone light sensor data, time of day, and indoor/outdoor information, to estimate illuminance around the user throughout a day. Since light dominates every human's circadian rhythm and influences the sleep-wake cycle, we developed a smartphone-based system that does not require additional sensors for illuminance estimation. To evaluate our approach, we conducted a free-living study with 12 users, each carrying a smartphone, a head-mounted light reference sensor, and a wrist-worn light sensing device for six consecutive days. Estimated light values were compared to the head-mounted reference, the wrist-worn device and a mean value estimate. Our results show that illuminance could be estimated at less than 20% error for all study participants, outperforming the wrist-worn device. In 9 out of 12 participants the estimation deviated less than 10% from the reference measurements.
Contribution
  • Florian Wahl
  • M. Freund
  • O. Amft

WISEglass: multi-purpose context-aware smart eyeglasses.

In: Proceedings of the 2015 ACM International Symposium on Wearable Computers (ISWC '15). pg. 159-160

  • Eds.:
  • D. Gatica-Perez
  • M. Langheinrich
  • K. Mase

ACM Press New York, New York, USA

  • (2015)

DOI: 10.1145/2802083.2808409

show abstract

We extend regular eyeglasses with multi-modal sensing and processing functions for context awareness. Our aim was to leverage eyeglasses as a platform to acquire and process context information according to the wearer's needs. The eyeglasses provide inertial motion, environmental light, and pulse sensors, data processing and wireless functionality, besides a rechargeable battery. We implemented prototypes of the smart eyeglasses and evaluated recognition performance in a study of daily activities with nine participants. The accuracy of recognising nine activity clusters from the smart eyeglasses motion sensors was 77% on average, confirming the benefit of smart eyeglasses for context-aware applications.
Journal article
  • O. Amft
  • Florian Wahl
  • S. Ishimaru
  • K. Kunze

Making Regular Eyeglasses Smart.

In: IEEE Pervasive Computing vol. 14 pg. 32-43

  • (2015)

DOI: 10.1109/MPRV.2015.60

show abstract

The authors discuss the vast application potential of multipurpose smart eyeglasses that integrate into the form factor of traditional spectacles and provide frequently needed sensing and interaction. In combination with software apps running on smart eyeglasses, the authors develop universal assistance systems that remain unobtrusive and thus can support wearers throughout their daily life. They describe a blueprint of the embedded architecture of smart eyeglasses and identify various software app clusters. They discuss findings from using smart eyeglasses prototypes in three case studies: to recognize cognitive workload, quantify reading habits, and monitor light exposure to estimate the circadian phase. This article is part of a special issue on digitally enhanced reality.
Contribution
  • Florian Wahl
  • M. Freund
  • O. Amft

Using smart eyeglasses as a wearable game controller.

In: Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2015 ACM International Symposium on Wearable Computers - UbiComp '15. pg. 377-380

  • Eds.:
  • K. Yatani
  • H. Gellersen
  • T. Choudhury
  • D. Gatica-Perez
  • M. Langheinrich
  • K. Mase

ACM Press New York, New York, USA

  • (2015)

DOI: 10.1145/2800835.2800914

show abstract

We investigated how regular eyeglasses fitted with sensing and processing capabilities can be used as a wearable game controller. For this purpose we built a demo based on our smart eyeglasses prototype. WISEglass allows the wearer to control the game Pac-Man through head motions. The control signals are extracted from a gyroscope mounted in the temple of WISEglass. Furthermore we integrated heart rate information into the game.
Journal article
  • Florian Wahl
  • J. Kasbauer
  • O. Amft

Computer Screen Use Detection Using Smart Eyeglasses.

In: Frontiers in ICT vol. 4

  • (2017)

DOI: 10.3389/fict.2017.00008

show abstract

Screen use can influence the circadian phase and cause eye strain. Smart eyeglasses with an integrated color light sensor can detect screen use. We present a screen use detection approach based on a light sensor embedded into the bridge of smart eyeglasses. By calculating the light intensity at the user’s eyes for different screens and content types, we found only computer screens to have a significant impact on the circadian phase. Our screen use detection is based on ratios between color channels and used a linear support vector machine to detect screen use. We validated our detection approach in three studies. A test bench was built to detect screen use under different ambient light sources and intensities in a controlled environment. In a lab study, we evaluated recognition performance for different ambient light intensities. By using participant-independent models, we achieved an ROC AUC above 0.9 for ambient light intensities below 200 lx. In a study of typical ADLs, screen use was detected with an average ROC AUC of 0.83 assuming screen use for 30% of the time.
Journal article
  • Florian Wahl
  • R. Zhang
  • M. Freund
  • O. Amft

Personalizing 3D-Printed Smart Eyeglasses to Augment Daily Life.

In: Computer vol. 50 pg. 26-35

  • (2017)

DOI: 10.1109/MC.2017.44

show abstract

Personalized 3D-printed eyeglasses equipped with sensing functions can enhance daily life through augmenting applications that enable wearers to monitor their vitals and behavior.
Journal article
  • Florian Wahl
  • O. Amft

Data and Expert Models for Sleep Timing and Chronotype Estimation from Smartphone Context Data and Simulations.

In: Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (Association for Computing Machinery, NY, USA) vol. 2 pg. 1-28

  • (2018)

DOI: 10.1145/3264949

show abstract

We present a sleep timing estimation approach that combines data-driven estimators with an expert model and uses smartphone context data. Our data-driven methodology comprises a classifier trained on features from smartphone sensors. Another classifier uses time as input. Expert knowledge is incorporated via the human circadian and homeostatic two process model. We investigate the two process model as output filter on classifier results and as fusion method to combine sensor and time classifiers. We analyse sleep timing estimation performance, in data from a two-week free-living study of 13 participants and sensor data simulations of arbitrary sleep schedules, amounting to 98280 nights. Five intuitive sleep parameters were derived to control the simulation. Moreover, we investigate model personalisation, by retraining classifiers based on participant feedback. The joint data and expert model yields an average relative estimation error of -2±62 min for sleep onset and -5±70 min for wake (absolute errors 40±48 min and 42±57 min, mean median absolute deviation 22 min and 15 min), which significantly outperforms data-driven methods. Moreover, the data and expert models combination remains robust under varying sleep schedules. Personalising data models with user feedback from the last two days showed the largest performance gain of 57% for sleep onset and 59% for wake up. Our power-efficient smartphone app makes convenient everyday sleep monitoring finally realistic.
Thesis
  • Florian Wahl

Methods for monitoring the human circadian rhythm in free-living. Dissertationsschrift.

Universität Passau Passau Fakultät für Informatik und Mathematik

  • 2019 (2019)

show abstract

Our internal clock, the circadian clock, determines at which time we have our best cognitive abilities, are physically strongest, and when we are tired. Circadian clock phase is influenced primarily through exposure to light. A direct pathway from the eyes to the suprachiasmatic nucleus, where the circadian clock resides, is used to synchronise the circadian clock to external light-dark cycles. In modern society, with the ability to work anywhere at anytime and a full social agenda, many struggle to keep internal and external clocks synchronised. Living against our circadian clock makes us less efficient and poses serious health impact, especially when exercised over a long period of time, e.g. in shift workers. Assessing circadian clock phase is a cumbersome and uncomfortable task. A common method, dim light melatonin onset testing, requires a series of eight saliva samples taken in hourly intervals while the subject stays in dim light condition from 5 hours before until 2 hours past their habitual bedtime. At the same time, sensor-rich smartphones have become widely available1 and wearable computing is on the rise. The hypothesis of this thesis is that smartphones and wearables can be used to record sensor data to monitor human circadian rhythms in free-living. To test this hypothesis, we conducted research on specialised wearable hardware and smartphones to record relevant data, and developed algorithms to monitor circadian clock phase in free-living. We first introduce our smart eyeglasses concept, which can be personalised to the wearers head and 3D-printed. Furthermore, hardware was integrated into the eyewear to recognise typical activities of daily living (ADLs). A light sensor integrated into the eyeglasses bridge was used to detect screen use. In addition to wearables, we also investigate if sleep-wake patterns can be revealed from smartphone context information. We introduce novel methods to detect sleep opportunity, which incorporate expert knowledge to filter and fuse classifier outputs. Furthermore, we estimate light exposure from smartphone sensor and weather information. We applied the Kronauer model2 to compare the phase shift resulting from head light measurements, wrist measurements, and smartphone estimations. We found it was possible to monitor circadian phase shift from light estimation based on smartphone sensor and weather information with a weekly error of 32±17 min, which outperformed wrist measurements in 11 out of 12 participants. Sleep could be detected from smartphone use with an onset error of 40±48 min and wake error of 42±57 min. Screen use could be detected smart eyeglasses with 0.9 ROC AUC for ambient light intensities below 200 lux. Nine clusters of ADLs were distinguished using Gaussian mixture models with an average accuracy of 77%. In conclusion, a combination of the proposed smartphones and smart eyeglasses applications could support users in synchronising their circadian clock to the external clocks, thus living a healthier lifestyle.
Lecture
  • Florian Wahl

Wieviel Personal brauche ich morgen?. Best Presentation Award.

In: 6. Tag der Forschung der THD 2019

Technische Hochschule Deggendorf Deggendorf

  • 10.04.2019 (2019)
Lecture
  • Florian Wahl

Wieviel Personal brauche ich morgen? Nachfrageprognose in der Stückgutlogistik. Posterpräsentation.

In: 6. Tag der Forschung der THD 2019

Technische Hochschule Deggendorf Deggendorf

  • 10.04.2019 (2019)
Lecture
  • Florian Wahl

Produktion 4.0 in KMUs - Datenerhebung und Datenanalyse.

KI Arbeitskreis Juni 2019 Deggendorf

  • 05.06.2019 (2019)
Lecture
  • Florian Wahl

Produktion 4.0 in KMUs - Datenerhebung und Datenanalyse.

XING Nutzergruppe FRG Schönberg

  • 06.06.2019 (2019)
Lecture
  • Florian Wahl

Data Science with Python.

Hochschulgruppe Deggendorf der Gesellschaft für Informatik Deggendorf

  • 27.06.2019 (2019)
Lecture
  • Florian Wahl

Building Industry 4.0 logistics applications with MicroPython and ESP32 MCUs.

In: Konferenz EuroPython 2019

Basel, Schweiz

  • 11.07.2019 (2019)
Lecture
  • Michael Fernandes
  • Florian Wahl

Tomatenkrimi - Der Foodscanner als Ermittler. Keynote.

In: Tag der offenen Türe des Technologie Campus Grafenau

Grafenau

  • 12.07.2019 (2019)
Lecture
  • Florian Wahl

Data Science with Python.

In: Meetup-Reihe League of Geeks

Passau

  • 17.10.2019 (2019)
Contribution
  • Florian Wahl

Methoden zum Monitoring des zirkadianen Rhythmus im Alltag.

In: Ausgezeichnete Informatikdissertationen 2019 - Komplettband. pg. 219-228

  • Eds.:
  • S. Hölldobler

Gesellschaft für Informatik e.V. Bonn

  • (2020)

show abstract

Unsere innere Uhr, die zirkadiane Uhr, regelt wann Aktivitäten im Körper stattfinden und bestimmt so z.B. wann wir die höchste Konzentrationsfähigkeit haben. Die zirkadiane Phase wird durch den Zeitpunkt und die Intensität von Lichtexposition verändert. Im Alltag stellt die Synchronisation von interner und externer Uhr eine zunehmende Herausforderung dar. Ein Leben gegen die innere Uhr birgt negative gesundheitliche Konsequenzen. Bisher kann die zirkadiane Phase nur mit erheblichem Aufwand gemessen werden. Ziel der Dissertation ist es Methoden zur Beobachtung der inneren Uhr im Alltag zu erforschen. Wir entwickeln dafür personalisierte Datenbrillen, welche Alltagsaktivitäten des Trägers erkennen und so z.B. vor Bildschirmbenutzung bei Nacht warnen können. Des Weiteren schätzen wir die Lichtexposition mit Smartphones, um so die Verschiebung der inneren Uhr vorherzusagen. Wir verwenden Daten von Smartphones, um Schlaf-Wach Zeiten zu erkennen. Expertenmodelle werden mit datengetriebenen Modellen kombiniert, um die Ergebnisse zu verbessern und Vorhersagen in relevante Domänen übersetzen
Journal article
  • Florian Wahl
  • Matthias Breslein
  • Benedikt Elser

On-demand forklift hailing system for Intralogistics 4.0.

In: Procedia Computer Science vol. 200 pg. 878-886

  • (2022)

DOI: 10.1016/j.procs.2022.01.285

show abstract

The shift to I4.0 is happening. While large companies have a range of solutions to implement that change, small and medium-sized enterprises (SME) fall short on solutions tailored for their specific needs. To support SMEs in their transformation toward I4.0, we propose a lightweight system to hail forklifts in a production facility of a medium-sized enterprise. Existing shop floor workflows are implemented within the system and allow machine operators to hail forklift drivers using an embedded or a web-based client. Forklift drivers receive driving instructions on their smartphones. Shift managers can monitor intralogistic activities on a dashboard. Management can extract relevant production and forklift KPIs from the system. In a two-week evaluation phase, we installed our system in a production facility for injection moulded plastic parts. We equipped 12 machines and two forklifts and registered a total of 690 jobs. We found half of the jobs were picked up in 4:05 min and 80% of all jobs were completed in less than 40:02 min.
Journal article
  • Florian Wahl
  • M. Freund
  • O. Amft

WISEglass: Smart eyeglasses recognising context.

In: EAI Endorsed Transactions on Pervasive Health and Technology vol. 2 pg. e4

  • (2022)

DOI: 10.4108/eai.28-9-2015.2261470

show abstract

We investigated how regular eyeglasses could be extended with multi-modal sensing and processing functions to support context-awareness applications. Our aim was to leverage eyeglasses as a platform for acquiring and processing context information according to the wearer’s needs. The WISEglass architecture consists of inertial motion, environmental light, and pulse sensors, processing and wireless data transmission functionality, besides a rechargeable battery. We implemented prototypes of WISEglass and evaluated them in three application scenarios: daily activity recognition, screen-use detection, and heart rate estimation. We conducted a daily activity study with nine participants, each wearing WISEglass and recording for one day. When evaluating daily activity recognition, we obtained 77 % average accuracy for continuous recognition using Gaussian Mixture Models and classifier reject to ignore null class data. Using the light sensor for detecting screen-use, yielded 80 % accuracy. Against a chest-worn ECG reference, our heart rate estimation showed an difference below 10 beats for stationary activities across the full recording day. We concluded that smart eyeglasses provide information from a single measurement spot that is relevant in various context recognition applications.
Lecture
  • Florian Wahl

Das Unterstützungspotential von KI in der Pflege.

In: INDIGO KI Campus Ostbayern: Interdisziplinäre Perspektiven auf KI

Netzwerk Internet und Digitalisierung Ostbayern Passau

  • 26.06.2022 (2022)
Contribution
  • Domenic Sommer
  • Sebastian Wilhelm
  • Diane Ahrens
  • Florian Wahl

Implementing an Intersectoral Telemedicine Network in Rural Areas: Evaluation from the Point of View of Telemedicine Users.

In: Proceedings of the 9th International Conference on Information and Communication Technologies for Ageing Well and e-Health (ICT4AWE). pg. 15-27

  • (2023)

DOI: 10.5220/0011755500003476

Contribution
  • Domenic Sommer
  • Tobias Greiler
  • Stefan Fischer
  • Sebastian Wilhelm
  • Lisa-Marie Hanninger
  • Florian Wahl

Investigating Use Requirements. A Participant Observation Study to Define the Information Needs at a Hospital Reception. (Short Paper).

In: HCI International 2023 Posters. 25th International Conference on Human-Computer Interaction, HCII 2023, Copenhagen, Denmark, July 23–28, 2023, Proceedings, Part II (Communications in Computer and Information Science) pg. 1-10

  • Eds.:
  • S. Ntoa
  • G. Salvendy
  • M. Antona
  • C. Stephanidis

Springer Nature Switzerland AG

  • (2023)

DOI: 10.1007/978-3-031-35992-7_23

Journal article
  • Roman-David Kulko
  • Alexander Pletl
  • H. Mempel
  • Florian Wahl
  • Benedikt Elser

OpenVNT: An Open Platform for VIS-NIR Technology.

In: Sensors vol. 23 pg. 3151

  • (2023)

DOI: 10.3390/s23063151

show abstract

Spectrometers measure diffuse reflectance and create a “molecular fingerprint” of the material under investigation. Ruggedized, small scale devices for “in-field” use cases exist. Such devices might for example be used by companies in the food supply chain for inward inspection of goods. However, their application for the industrial Internet of Things workflows or scientific research is limited due to their proprietary nature. We propose an open platform for visible and near-infrared technology (OpenVNT), an open platform for capturing, transmitting, and analysing spectral measurements. It is built for use in the field, as it is battery-powered and transmits data wireless. To achieve high accuracy, the OpenVNT instrument contains two spectrometers covering a wavelength range of 400–1700 nm. We conducted a study on white grapes to compare the performance of the OpenVNT instrument against the Felix Instruments F750, an established commercial instrument. Using a refractometer as ground truth, we built and validated models to estimate the Brix value. As a quality measure, we used coefficient of determination of the cross-validation (R2CV) between the instrument estimation and ground truth. With 0.94 for the OpenVNT and 0.97 for the F750, a comparable R2CV was achieved for both instruments. OpenVNT matches the performance of commercially available instruments at one tenth of the price. We provide an open bill of materials, building instructions, firmware, and analysis software to enable research and industrial IOT solutions without the limitations of walled garden platforms.
Contribution
  • Sebastian Wilhelm
  • Jakob Folz
  • Florian Wahl

Open Personal Data: Anonymisierung im Spannungsfeld zwischen Informationsgehalt und Robustheit.

In: Data Sharing: Datenkapitalismus by Default?. Posterproceedings - Forum Privatheit 2023 pg. 36

  • Eds.:
  • M. Friedewald
  • M. Karaboga

Fraunhofer-Institut für System- und Innovationsforschung ISI

  • (2023)
Contribution
  • Dietmar Jakob
  • Sebastian Wilhelm
  • A. Gerl
  • Florian Wahl
  • Diane Ahrens

Voice Controlled Devices: A Comparative Study of Awareness, Ownership, Usage, and Reservations Between Young and Older Adults.

In: Human Aspects of IT for the Aged Population. Proceedings (Part I) of the 9th International Conference ITAP 2023 - Human Aspects of IT for the Aged Population - Held as Part of the 25th HCI International Conference (HCII) 2023 (Copenhagen, Denmark; July 23–28, 2023) (Lecture Notes in Computer Science) vol. 14042 pg. 348-365

  • Eds.:
  • J. Zhou
  • Q. Gao

Springer Nature Switzerland Cham

  • (2023)

DOI: 10.1007/978-3-031-34866-2_25

Lecture
  • Domenic Sommer
  • Miloslav Kovacevic
  • Florian Wahl

Caregivers Workplace Expectations and Job Satisfaction. Online Survey of Caregivers In Bavaria. Abstract und Poster.

In: 7. Ambient Medicine®Forum

Hochschule Kempten Kempten

  • 23.-24.03.2023 (2023)
Lecture
  • Florian Wahl

Das Unterstützungspotential von künstlicher Intelligenz in der Pflege.

In: 7. Ambient Medicine® Forum

CARE REGIO Kempten

  • 24.03.2023 (2023)
Lecture
  • Florian Wahl

Unlocking the Potential of Artificial Intelligence in Care.

In: 30th IRIXYS Workshop

Institut Nationale des Sciences Appliqués (INSA) Lyon Lyon, France

  • 10.05.2023 (2023)
Lecture
  • Norbert Lichtenauer
  • Sebastian Wilhelm
  • Florian Wahl

EAsyAnon – Empfehlungs- und Auditsystem zur Anonymisierung.

In: Forschungsfrühstück der Technischen Hochschule Deggendorf am Gesundheitscampus Bad Kötzting

Bad Kötzting

  • 16.06.2023 (2023)
Contribution
  • Dietmar Jakob
  • Johannes Kuchler
  • Diane Ahrens
  • Florian Wahl

Activities to Encourage Older Adults’ Skills in the Use of Digital Technologies on the Example of Multigenerational Houses in Germany.

In: Human Aspects of IT for the Aged Population. (Lecture Notes in Computer Science) pg. 131-145

  • Eds.:
  • J. Zhou
  • Q. Gao

Springer Nature Switzerland Cham

  • (2024)

DOI: 10.1007/978-3-031-61543-6_10

show abstract

Against the backdrop of demographic change and advancing digitalization, digital skills are indispensable for older adults. Nevertheless, using digital technologies is not a matter of course for this group. Due to their structures and regional networking, multigenerational houses (MGHs) are suitable platforms for promoting media skills for older adults. Training programs consisting of courses and media consultation hours for older adults to strengthen their digital skills were initiated and carried out in Bavarian MGHs. The aim was to understand better the mechanisms, potential, and challenges of promoting digital skills among older adults in MGHs. To this end, expert interviews were conducted with managers of seven selected MGHs in April 2023. The results show that older adults respond positively to the training programs and see considerable added value. Providing programs to promote media skills in MGHs can help to reduce the digital divide and enable older adults to participate better in a digitally shaped society.
Contribution
  • Florian Wahl
  • Sebastian Wilhelm

Sensorik und künstliche Intelligenz in der Pflege.

In: Digitale Innovationen in der Pflege. pg. 307-324

  • Eds.:
  • N. Seifert
  • W. Swoboda

Springer Berlin Heidelberg Berlin, Heidelberg

  • (2024)

DOI: 10.1007/978-3-662-67914-2_12

show abstract

Pflegesysteme befinden sich im Dilemma zwischen einer steigenden Anzahl Pflegebedürftiger einerseits und dem Fachkräftemangel auf Seiten der Pflegekräfte andererseits. Bis 2030 erwartet die Bertelsmannstiftung eine Lücke von 260 bis 490 Tausend Pflegekräften. Der Einsatz von Technologien wie Sensorik und KI bietet hier vielversprechende Lösungen, um Pflegekräfte zu entlasten, die Effizienz in der Pflege zu steigern und gleichzeitig die Lebensqualität von Pflegebedürftigen zu erhöhen. Die Entwicklungen in den Bereichen KI und Sensorik erlauben uns künftig diese Technologien intesiver in der Pflege einzusetzen. In diesem Kapitel geben wir eine kurze Übersicht über die Grundlagen der (KI) und typische Sensormodalitäten. Anschließend stellen wir die typischen Analyseebenen vor, welche für KI-Anwendungen im Pflegebereich interessan sind. Bevor wir ein Fazit ziehen, beschreiben wir zwei Beispielanwendungen: Die Aktivitätserkennung mittels Sensorbrille sowie die Notfallerkennung auf Basis von Smart-Meter Daten. Wir sind der Überzeugung, dass KI in der Zukunft einen signifikanten Beitrag zur Effizienzsteigerung und Verbesserung der Pflege beitragen kann und wird.
Journal article
  • Norbert Lichtenauer
  • Lukas Schmidbauer
  • Sebastian Wilhelm
  • Florian Wahl

A Scoping Review on Analysis of the Barriers and Support Factors of Open Data.

In: Information vol. 15 pg. 5

  • 20 December 2023 (2024)

DOI: 10.3390/info15010005

show abstract

ackground: Using personal data as Open Data is a pervasive topic globally, spanning various sectors and disciplines. Recent technological advancements, particularly in artificial intelligence and algorithm-driven analysis, have significantly expanded the capacity for the automated analysis of vast datasets. There’s an expectation that Open Data analysis can drive innovation, enhance services, and streamline administrative processes. However, this necessitates a legally and ethically sound framework alongside intelligent technical tools to comprehensively analyze data for societal benefit. Methodology: A systematic review across seven databases (MEDLINE, CINAHL, BASE, LIVIVO, Web of Science, IEEExplore, and ACM) was conducted to assess the current research on barriers, support factors, and options for the anonymized processing of personal data as Open Data. Additionally, a supplementary search was performed in Google Scholar. A total of 𝑛=1192 studies were identified, and 𝑛=55 met the inclusion criteria through a multi-stage selection process for further analysis. Results: Fourteen potential supporting factors (𝑛=14) and thirteen barriers (𝑛=13) to the provision and anonymization of personal data were identified. These encompassed technical prerequisites as well as institutional, personnel, ethical, and legal considerations. These findings offer insights into existing obstacles and supportive structures within Open Data processes for effective implementation.
Contribution
  • Domenic Sommer
  • Stefan Fischer
  • Florian Wahl

Investigating hospital service robots: A observation study about relieving information needs at the hospital reception..

In: Human Aspects of IT for the Aged Population. (Lecture Notes in Computer Science) pg. 395–404

  • Eds.:
  • J. Zhou
  • Q. Gao

Springer Nature Switzerland Cham

  • (2024)

DOI: 10.1007/978-3-031-61932-8_45

show abstract

Hospital receptions (HRs) are a vital area to meet information needs. Deploying Service Robots (SRs) is increasingly important in HR due to staff shortages and increasing healthcare demands in Germany. To evaluate the effectiveness of SR in HR, we conducted a consecutive study during one week in September 2023 in a rural Bavarian hospital. The study involved 1,703 interactions, primarily handled by HR staff (89.9 %), with SRs addressing 10.1 %. HR was mainly requested from 10:00 to 15:00 and the SR between 13:00 to 19:00. Each interaction was mainly under one minute. The requests were predominantly regarding orientation by both the SR and the hospital staff. Our results indicate that SR can reduce workload, saving 2.15 working hours during the study. The findings suggest SRs’ utility in information provision yet highlight the need for more comprehensive studies with advanced SRs in healthcare to optimize their role in information management.
Journal article
  • Sebastian Wilhelm
  • Florian Wahl

Emergency Detection in Smart Homes Using Inactivity Score for Handling Uncertain Sensor Data.

In: Sensors vol. 24

  • 12.10.2024 (2024)

DOI: 10.3390/s24206583

show abstract

In an aging society, the need for efficient emergency detection systems in smart homes is becoming increasingly important. For elderly people living alone, technical solutions for detecting emergencies are essential to receiving help quickly when needed. Numerous solutions already exist based on wearable or ambient sensors. However, existing methods for emergency detection typically assume that sensor data are error-free and contain no false positives, which cannot always be guaranteed in practice. Therefore, we present a novel method for detecting emergencies in private households that detects unusually long inactivity periods and can process erroneous or uncertain activity information. We introduce the Inactivity Score, which provides a probabilistic weighting of inactivity periods based on the reliability of sensor measurements. By analyzing historical Inactivity Scores, anomalies that potentially represent an emergency can be identified. The proposed method is compared with four related approaches on seven different datasets. Our method surpasses existing approaches when considering the number of false positives and the mean time to detect emergencies. It achieves an average detection time of approximately 05:23:28 h with only 0.09 false alarms per day under noise-free conditions. Moreover, unlike related approaches, the proposed method remains effective with noisy data.
Contribution
  • Sebastian Schmidt
  • Domenic Sommer
  • Tobias Greiler
  • Florian Wahl

hospOS: A Platform for Service Robot Orchestration in Hospitals.

In: Proceedings of the 10th International Conference on Information and Communication Technologies for Ageing Well and e-Health. pg. 221-228

SCITEPRESS - Science and Technology Publications

  • (2024)

DOI: 10.5220/0012692200003699

show abstract

In a time where an ageing population, nurses shortage and manual labor routines are limiting rural healthcare, Service Robots (SR) are emerging. While SR could increase hospital staff efficiency, their healthcare use remains limited. Barriers are the robot’s task-specific inflexibility and a lack of interoperability. Existing SR are usually closed systems and focus on a single robot designed to fulfill all functional requirements, which results in complex and expensive solutions. In contrast, we propose to utilize and combine existing SR for various tasks. We argue that with the growing integration of SR in healthcare, a SR management system has become a necessity. We propose hospOS, a centralised system for SR orchestration in healthcare facilities. hospOS addresses this gap by providing a modular, flexible, user-friendly platform that seamlessly integrates SR into hospital IT infrastructures, alleviating the shortage of care workers and thus improving patient care. The platform is built with a focus on interoperability, modularity, and compliance with regulations. We evaluated hospOS in two rural hospitals by realising three example use cases: Telemedicine, transport, and orientation services. This paper offers an architecture blueprint and discusses the functionalities, and potential benefits of hospOS, along with its implementation in healthcare scenarios. The results from deployments indicate im-provements in service delivery and operational management.
Journal article
  • Domenic Sommer
  • Sebastian Wilhelm
  • Florian Wahl

Nurses’ Workplace Perceptions in Southern Germany—Job Satisfaction and Self-Intended Retention towards Nursing.

In: Healthcare vol. 12 pg. 172

  • (2024)

DOI: 10.3390/healthcare12020172

show abstract

Our cross-sectional study, conducted from October 2022 to January 2023, aims to assess post-COVID job satisfaction, crucial work dimensions, and self-reported factors influencing nursing retention. Using an online survey, we surveyed 2572 nurses in different working fields in Bavaria, Germany. We employed a quantitative analysis, including a multivariable regression, to assess key influence factors on nursing retention. In addition, we evaluated open-ended questions via a template analysis to use in a joint display. In the status quo, 43.2% of nurses were not committed to staying in the profession over the next 12 months. A total of 66.7% of our surveyed nurses were found to be dissatisfied with the (i) time for direct patient care. Sources of dissatisfaction above 50% include (ii) service organization, (iii) documentation, (iv) codetermination, and (v) payment. The qualitative data underline necessary improvements in these areas. Regarding retention factors, we identified that nurses with (i) older age, (ii) living alone, (iii) not working in elder care, (iv) satisfactory working hours, (v) satisfactory career choice, (vi) career opportunities, (vii) satisfactory payment, and (viii) adequate working and rest times are more likely to remain in the profession. Conversely, dissatisfaction in (ix) supporting people makes nurses more likely to leave their profession and show emotional constraints. We uncovered a dichotomy where nurses have strong empathy for their profession but yearn for improvements due to unmet expectations. Policy implications should include measures for younger nurses and those in elderly care. Nevertheless, there is a need for further research, because our research is limited by potential bias from convenience sampling, and digitalization will soon show up as a potential solution to improve, e.g., documentation and enhanced time for direct patient time.
Journal article
  • Domenic Sommer
  • Lukas Schmidbauer
  • Florian Wahl

Nurses’ perceptions, experience and knowledge regarding artificial intelligence: results from a cross-sectional online survey in Germany.

In: BMC Nursing vol. 23

  • (2024)

DOI: 10.1186/s12912-024-01884-2

show abstract

Background Nursing faces increasing pressure due to changing demographics and a shortage of skilled workers. Artificial intelligence (AI) offers an opportunity to relieve nurses and reduce pressure. The perception of AI by nurses is crucial for successful implementation. Due to a limited research state, our study aims to investigate nurses’ knowledge and perceptions of AI. Methods In June 2023, we conducted a cross-sectional online survey of nurses in Bavaria, Germany. A convenience sample via care facilities was used for the questionnaire oriented on existing AI surveys. Data analysis was performed descriptively, and we used a template analysis to evaluate free-text answers. Results 114 (♀67.5 %, ♂32.5 %) nurses participated. Results show that knowledge about AI is limited, as only 25.2 % can be described as AI experts. German nurses strongly associate AI with (i) computers and hardware, (ii) programming-based software, (iii) a database tool, (iv) learning, and (v) making decisions. Two-thirds of nurses report AI as an opportunity. Concerns arise as AI is seen as uncontrollable or threat. Administration staff are seen as the biggest profiteers. Conclusion Even though there is a lack of clear understanding of AI technology among nurses, the majority recognizes the benefits that AI can bring in terms of relief or support. We suggest that nurses should be better prepared for AI in the future, e.g., through training and continuing education measures. Nurses are the working group that uses AI and are crucial for implementing nursing AI.
Journal article
  • Domenic Sommer
  • Jakob Kasbauer
  • Dietmar Jakob
  • Sebastian Schmidt
  • Florian Wahl

Potential of Assistive Robots in Clinical Nursing: An Observational Study of Nurses’ Transportation Tasks in Rural Clinics of Bavaria, Germany.

In: Nursing Reports vol. 14 pg. 267-286

  • (2024)

DOI: 10.3390/nursrep14010021

show abstract

Transportation tasks in nursing are common, often overlooked, and directly impact patient care time in the context of staff shortages and an aging society. Current studies lack a specific focus on transportation tasks, a gap our research aims to fill. By providing detailed data on transportation needs in nursing, our study establishes a crucial foundation for the development and integration of assistive robots in clinical settings. In July and September 2023, we conducted weekly observations of nurses to assess clinical transportation needs. We aim to understand the economic impact and the methods nurses use for transportation tasks. We conducted a participant observation using a standardized app-based form over a seven-day observation period in two rural clinics. N = 1830 transports were made by nurses and examined by descriptive analysis. Non-medical supplies account for 27.05% (n = 495) of all transports, followed by medical supplies at 17.32% (n = 317), pharmacotherapy at 14.10% (n = 258) and other other categories like meals or drinks contributing 12.68% (n = 232). Most transports had a factual transport time of under a minute, with patient transport and lab samples displaying more variability. In total, 77.15% of all transports were made by hand. Requirements to collect items or connect transports with patient care were included in 5% of all transports. Our economic evaluation highlighted meals as the most costly transport, with 9596.16 € per year in the observed clinics. Budget-friendly robots would amortize these costs over one year by transporting meals. We support understanding nurses’ transportation needs via further research on assistive robots to validate our findings and determine the feasibility of transport robots.
Lecture
  • Norbert Lichtenauer
  • Sebastian Wilhelm
  • Lukas Schmidbauer
  • Florian Wahl

EAsyAnon - Empfehlungs- und Auditsystem zur Anonymisierung. Poster: "Analysis of barriers and support factors of open data" [unveröffentlicht].

In: Anonymisierung für eine sichere Datennutzung (AnoSiDat)

Lübeck

  • 16.-17.04.2024 (2024)
Lecture
  • Florian Wahl

Wearables und Robotik zur Unterstützung der Pflege.

In: Telemedizinkongress Süd

Online

  • 18.09.2024 (2024)
Lecture
  • Florian Wahl

Bedarf und Lösungen zur zukunftsorientierten, intersektoralen regionalen Versorgung. Teilnehmer an der Podiumsdiskussion.

In: Telemedizinkongress Süd

Online

  • 18.09.2024 (2024)
Lecture
  • Florian Wahl

Leveraging Large Language Models in the Care Domain.

In: IRIXYS Scientific Workshop

Institut Nationale des Sciences Appliqués (INSA) Lyon Lyon, France

  • 11.12.2024 (2024)
Contribution
  • Dietmar Jakob
  • Sebastian Schmidt
  • Florian Wahl

Planning and Installation of 5G Campus Networks in Hospitals in Rural Areas and Possible Use Cases: A Practical Example.

In: Advances in Information and Communication. (Lecture Notes in Networks and Systems) vol. 1284 pg. 684-705

  • Eds.:
  • K. Arai

Springer Nature Switzerland Cham

  • (2025)

DOI: 10.1007/978-3-031-85363-0_42

show abstract

The introduction of 5G technologies will result in significant changes in various industry areas and the healthcare sector. High data rates, low latency times, and diverse connectivity are just some of the features of this technology. 5G campus networks are particularly suitable for hospitals to improve healthcare. This article focuses on the planning and installation of 5G campus networks and their implementation in two rural hospitals in Germany. Using predefined use cases such as patient monitoring, televising, patient routing, and transport services, the article examines how 5G technology can be used in hospitals. The key findings are that insufficient interfaces for today’s robot-assisted applications and high acquisition costs limit the usefulness of 5G networks. Nevertheless, hospitals can benefit from the technology’s real-time data transmission and reliability to speed up healthcare processes and make them more effective, especially if the described limitations might be overcome in the future. For this reason, this paper aims to provide interested hospitals and counties with best practices for successful implementation.
Journal article
  • Dietmar Jakob
  • Sebastian Wilhelm
  • A. Gerl
  • Diane Ahrens
  • Florian Wahl

Adapting Voice Assistant Technology for Older Adults: A Comprehensive Study on Usability, Learning Patterns, and Acceptance.

In: Digital vol. 5 pg. 4

  • (2025)

DOI: 10.3390/digital5010004

show abstract

This study investigates the integration, usability, and learning patterns associated with voice assistant technology among older adults, focusing on the “Amazon Echo Show 10, 3rd generation” as a case study. Conducted with 32 participants aged 55 and above in senior and complementary households, this research employs a mixed-method approach, incorporating qualitative interviews and quantitative voice command logging over a twelve-week period. Our findings reveal a high level of learnability and usability of the voice assistant, with 90% of participants finding the device easy to learn and use. The study further explores the patterns of voice assistant use, highlighting a preference for listening to music and seeking information, predominantly on weekends. Despite initial reservations, participants reported a high satisfaction level, with most not feeling monitored by the device. Key recommendations for manufacturers include prioritizing the design and user experience to cater to older adults’ needs, aiming to enhance their digital inclusion and participation. This study contributes to the human–computer interaction (HCI) field by providing insights into older adults’ interactions with voice assistant technology, emphasizing the importance of designing accessible and user-friendly digital solutions for the aging population.
Journal article
  • Domenic Sommer
  • E. Lermer
  • Florian Wahl
  • L. Lopera G.

Assistive technologies in healthcare: utilization and healthcare workers perceptions in Germany.

In: BMC Health Services Research vol. 25 pg. 223

  • 10.02.2025 (2025)

DOI: 10.1186/s12913-024-12162-x

show abstract

BACKGROUND According to the WHO, assistive technology (AT) is defined as the superset of technologies that improve or maintain the functioning of different senses, mobility, self-care, well-being, and inclusion of patients. ATs also include technologies for healthcare workers (HCWs) to reduce workloads and improve efficiency and patient care outcomes. Software ATs for HCWs include communication software, artificial intelligence (AI), text editors, planning tools, decision support systems, and health records. Hardware ATs for HCWs can range from communication devices, sensors, and specialized medical equipment to robots. AIMS With this indicative study, we explore HCW utilization, perceptions, and adoption barriers of ATs. We emphasize ATs role in enhancing HCWs' efficiency and effectiveness in healthcare delivery. METHODS A cross-sectional online survey was conducted through August 2024 with HCWs in Bavaria via a network recruiting approach. We used convenience sampling but ensured that only HCWs were part of our study population. Our survey included (i) usage, (ii) usefulness, and (iii) perceptions regarding ATs. The survey comprised 11 close-ended and three open-ended questions, including story stems evaluated by a deductive qualitative template analysis. Our mixed-method evaluation also employed descriptive and bivariate statistics. RESULTS Three hundred seventy-one HCWs (♂63.9 %, ♀36.1 %) participated in our survey, primarily 133 administrators, 116 nurses, and 34 doctors. More than half of the study participants (58.6 %) reported having advanced technical skills. Regarding usage, communication platforms (82.2 %) and communication devices (86 %) were the most commonly used ATs. Advanced ATs such as body-worn sensors, medical devices with interfaces, identification devices, and robots were underutilized in our sample. ATs were reported to be helpful in all job roles but need improvements in capacity and integration. Key barriers to adoption included outdated infrastructure, interoperability, and a lack of training. CONCLUSION Our study suggests that HCWs may want to incorporate ATs into their workflows as they see how, in theory, these technologies would improve HCW's efficiency, resulting in better patient care. However, to realize this potential, efforts in ATs integration and accessibility are essential. Given this study's modest sample size and generalizability limitations, further research is needed to explore the adoption, implementation, and impact of ATs in healthcare.