Sebastian Wilhelm, M.Sc.

  • Applied Research in Engineering Sciences
  • Smart Region
  • BLADL - Besser Leben im Alter durch digitale Lösungen

Wissenschaftlicher Mitarbeiter

Grafenau

08552/975620-25


Beitrag (Sammelband oder Tagungsband)
  • Sebastian Wilhelm
  • Dietmar Jakob
  • Jakob Kasbauer
  • Diane Ahrens
GeLaP: German Labeled Dataset for Power Consumption. [Accepted for publication]
  • 2021
Due to the increasing spread of smart meters numerous researchers are currently working on disaggregating the power consumption data. This procedure is commonly known as Non-Intrusive Load Monitoring (NILM). However most approaches to energy disaggregation first require a labeled dataset to train these algorithms.In this paper we present a new labeled power consumption dataset that was collected in 20 private households in Germany between September 2019 and July 2020. For this purpose the total power consumption of each household was measured with a commercial available smart meter and the individual consumption data of 10 selected household appliances were collected.
  • TC Grafenau
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Sebastian Wilhelm
Activity-Monitoring in Private Households for Emergency Detection: A Survey of Common Methods and Existing Disaggregable Data Sources. [Accepted for publication]
  • 2021
Ambient-Assisted Living (AAL) technologies can enable the elderly people to live a self-determined life in their own home environment instead of hospitals and retirement homes for a longer period of time. Hence AAL systems are not only used for everyday support but also for the detection of potential emergency situ- ations and for triggering notification chains. For this purpose the people are usually continuously monitored within their residents by ambient or wearable sensors to detect deviations in their daily behavior.This work surveys common used technologies for Human Activity Recognition (HAR) / Human Presence De- tection (HPD) which is the basis for emergency detection. Furthermore by examining various home automa- tion software existing data sources from the residential infrastructure are identified that would be suitable for detecting personal activities.
  • TC Grafenau
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Sebastian Wilhelm
Exploiting Home Infrastructure Data for the good: Emergency Detection by reusing existing Data Sources. [Accepted for publication]
  • 2021
Monitoring people within their residence can enable elderly to live a self-determined life in their own home environment for a longer period of time. Therefore commonly activity profiles of the residents are created using various sensors in the house. Deviations from the typical activity profile may indicate an emergency situation. An alternative approach for monitoring people within their residence we investigates within our research is reusing existing data sources instead of installing additional sensors. In private households there are already numerous data sources such as smart meters weather station routers or voice assistants available. Intelligent algorithms can be used to evaluate this data and conclude on personal activities. This in turn allows the creation of activity profiles of the residents without using external sensor technology.This work outlines the research gap in reusing existing data sources for Human Activity Recognition (HAR) and emergency detection which we intend to fill with our further work.
  • TC Grafenau
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Sebastian Wilhelm
  • Dietmar Jakob
  • Diane Ahrens
Human Presence Detection by monitoring the indoor CO2 concentration, pg. 199-203.
  • 2020

DOI: 10.1145/3404983.3409991

Presence detection systems are becoming more and more important and are used in smart home environments in the Ambient Assisted Living (AAL) domain or in surveillance technology. Common systems focus on using motion sensors or cameras which have only a limited viewing angle and therefore monitoring gaps can easily occur within a room. Humans produce carbon dioxide (CO2) through their respiration which is distributed in rooms. As a result if one (or more) persons are in a room a significant increase in CO2 concentration in the room can be noted. With this work we investigate an approach to detect the presence or absence of people indoors by monitoring the CO2 concentration in the ambient air.
  • TC Grafenau
  • Angewandte Wirtschaftswissenschaften
  • DIGITAL
Vortrag
  • Sebastian Wilhelm
Activity Monitoring reusing Home Infrastructure Data

In: Digital French-German Summer School with Industry 2020

  • 2020
  • TC Grafenau
  • Angewandte Wirtschaftswissenschaften
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Sebastian Wilhelm
  • Dietmar Jakob
  • Jakob Kasbauer
  • M. Dietmeier
Organizational, Technical, Ethical and Legal Requirements of Capturing Household Electricity Data for Use as an AAL System
  • 2020

DOI: 10.1007/978-981-15-5856-6_38

Due to demographic change elderly care is one of the major challenges for society in near future fostering new services to support and enhance the life quality of the elderly generation. A particular aspect is the desire to live in one’s homes instead of hospitals and retirement homes as long as possible. Therefore it is essential to monitor the health status i.e. the activity of the individual. In our data-driven society data is collected at an increasing rate enabling personalized services for our daily life using machine-learning and data mining technologies. However the lack of labeled datasets from a realistic environment hampers research for training and evaluating algorithms. In the project BLADL we use data mining technologies to gauge the health status of elderly people. Within this work we discuss the challenges and caveats both from a technical and ethical perspectives to create such a dataset.
  • TC Grafenau
  • Angewandte Wirtschaftswissenschaften
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Dietmar Jakob
  • Sebastian Wilhelm
Amazon Echo: A Benchmarking Model Review
  • 2020
Smart speakers are becoming increasingly popular. The market leader for smart speakers are the products of the Echo family from Amazon. There are currently 9 different models with different technical specifications available in Germany. With this paper, the models was benchmarked against each other in terms of (i) speech recognition reliability, (ii) output sound pressure and (iii) power consumption in a laboratory experiment. Previous works in this area has only considered individual models of the product family. Significant differences in speech recognition accuracy, output sound pressure and power consumption were identified between the models. In general it was observed, that the Echo Show 8 model was the most efficient in terms of the above criterias.
  • Angewandte Wirtschaftswissenschaften
  • TC Grafenau
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Dietmar Jakob
  • Sebastian Wilhelm
  • A. Gerl
Data Privacy Management (DPM) - A Private Household Smart Metering Use Case
  • 2020

DOI: 10.18420/muc2020-ws119-003

The automated collection of real life data in private households places special requirements on a Data Privacy Management (DPM) concept. The development and implementation of a DPM concept for use in a scientific environment is demonstrated according to a successful use case – the project BLADL. The intention of this paper is to provide a guideline for ethical and privacy-preserving data collection and management in research projects in the EU. 
  • TC Grafenau
  • Angewandte Wirtschaftswissenschaften
  • DIGITAL
Vortrag
  • Dietmar Jakob
  • Sebastian Wilhelm
Prozessablauf von automatisierten Datenerhebungen in privaten Haushalten – Erfahrungsbericht

In: Data2Day 2020 - Konferenz für Big Data, Data Science und Machine Learning

  • 2020
Smarte Technologien erzeugen Datenströme, die unter anderem für personalisierte Mehrwertdienste genutzt werden können. Zur Entwicklung entsprechender Dienste und intelligenter Algorithmen ist es häufig notwendig, gelabelte Rohdaten zu sammeln.  Dabei sind neben den technischen Herausforderungen auch Datenschutzbestimmungen und ethische Fragestellungen zu berücksichtigen.  In unserem Vortrag präsentieren wir einen Erfahrungsbericht über die Erhebung von Stromverbrauchsdaten in 20 privaten Haushalten, beginnend bei der Auswahl der Testhaushalte, der Sicherstellung einer informierten Zustimmung, die Installation der technischen Komponenten bis zur Anonymisierung und Veröffentlichung der Daten.
  • TC Grafenau
  • DIGITAL
Buch (Monographie)
  • S. Sczogiel
  • A. Busch
  • A. Göller
  • A. Gabber
  • B. Williger
  • S. Schmitt-Rüth
  • Diane Ahrens
  • Dietmar Jakob
  • Sebastian Wilhelm
Digital fit im Alter. Handlungsempfehlung für Gemeinden zu Bildungsangeboten für Senioren (Hg.: Fraunhofer-Institut für Integrierte Schaltungen [IIS]; Technische Hochschule Deggendorf [THD])
  • 2020

DOI: 10.13140/RG.2.2.23245.05609

Ziel der Broschüre ist es, Gemeinden insbesondere im ländlichen Raum, über die Konzeption von Bildungsangeboten für ältere Menschen zu informieren und sie dazu zu befähigen, ähnliche Initiativen in ihren Gemeinden zu starten.
  • TC Grafenau
  • DIGITAL
Vortrag
  • Sebastian Wilhelm
Activity Monitoring reusing Home Infrastructure Data

In: IRIXYS - Young Scientists’ Workshop

  • 2020
  • TC Grafenau
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Sebastian Wilhelm
  • Dietmar Jakob
  • M. Dietmeier
Development of a senior-friendly training concept for imparting media literacy, pg. 699-710.

In: INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik - Informatik für Gesellschaft. 49. GI-Jahrestagung INFORMATIK 2019 (Lecture Notes in Informatics (LIN))

  • 2019

DOI: 10.18420/inf2019_83

The use of digital solutions to support rural areas, and in particular elderly people, is the goal of the ‘Digitales Dorf’ and ‘BLADL’ research projects. This work assessed seniors’ media literacy in two model communities; with the result that fear of fraudster and lack of knowledge are the most common causes that prevent elderly people from using digital technologies. Based on these evaluation results, a combined training offer of tutorial and digital consultation hour was developed and evaluated.
  • Angewandte Informatik
  • TC Grafenau
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Sebastian Wilhelm
  • Dietmar Jakob
Digital support for managing Organized Neighborhood Assistance, pg. 531-535.
  • 2019
In the context of demographic change and an aging society, neighborhood help is playing an increasingly important role in our society. Within this work a framework for developing a digital platform to manage an Organized Neighborhood Assistance is developed. A special focus lies on analyzing the functional, technical and legal requirements.
  • Angewandte Informatik
  • TC Grafenau
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Sebastian Wilhelm
  • A. Gerl
Policy-based Authentication and Authorization based on the Layered Privacy Language, pg. 245-255.
  • 2019

DOI: 10.18420/btw2019-ws-25

In 2018 the General Data Protection Regulation (GDPR) has been enforced providing a new legal framework with rules and regulations for processing personal data. The requirement for distinguishing between purposes has been introduced, leading to the necessity of adapting existing authentication and authorization processes. We introduce a detailed authentication and authorization extension, which is able to verify requests on personal data based on the Layered Privacy Language (LPL). This extension is evaluated in the form of a benchmark, utilizing the Policy-based De-identification, to demonstrating its efficiency and suitability for data-warehouses.
  • Angewandte Informatik
  • TC Grafenau
  • DIGITAL