Das Verbundprojekt LivingSmart verfolgt das Ziel, eine digitale Quartiersplattform für Bewohner*innen zu entwickeln. Auf dieser Plattform sollen vor allem soziale Dienstleistungen sowie regionale Angebote gebündelt und bedarfsgerecht zur Verfügung gestellt werden. Hierfür wurde die bereits bestehende Plattform von ANIMUS zu einer Dienstleistungsplattform weiterentwickelt und um Dienstleistungen der Johanniter-Unfall-Hilfe e. V., des pme Familienservices, des OFFIS-Instituts sowie des BFE Oldenburg ergänzt. Zudem wird mithilfe der digitalen Vernetzung der soziale Austausch, die Nachbarschaftshilfe sowie die Teilhabe im Quartier gestärkt. Die auf der Plattform angebotenen ServicesServices zielen darauf ab, Einzelpersonen, Familien, Alleinerziehende, Pflegende und vor allem Risikogruppen, die durch die Covid-19-Pandemie besonders betroffen sind, zu unterstützen.

Major Depressive Disorder (MDD) has a significant impact on the daily lives of those affected. This concept paper presents a project that aims at addressing MDD challenges through innovative therapy systems. The project consists of two use cases: a multimodal neurofeedback (NFB) therapy and an AI-based virtual therapy assistant (VTA). The multimodal NFB integrates EEG and fNIRS to comprehensively assess brain function. The goal is to develop an open-source NFB toolbox for EEG-fNIRS integration, augmented by the VTA for optimized efficacy. The VTA will be able to collect behavioral data, provide personalized feedback and support MDD patients in their daily lives. This project aims to improve depression treatment by bringing together digital therapy, AI and mobile apps to potentially improve outcomes and accessibility for people living with depression.

Das Projekt „LivingSmart“ verfolgt das Ziel, personennahe DienstleistungenDienstleistungenpersonennahe rund um das Thema Ökosystem der Wohnung bis hin zum Wohnquartier in Zeiten der Digitalisierung zu erforschen. Im Rahmen des Teilprojekts „Intelligente LivingSmart-Auswertemodule“ wurden Daten aus dem Hausnotrufsystemservice der Johanniter-Unfall-Hilfe hinsichtlich der Frage untersucht, inwieweit sich Muster zeigen, aus denen sich für die Kunden des Systems relevante Informationen ableiten lassen. Konkret wurden der Zusammenhang zwischen Perioden großer Hitze und dem Auftreten ischämischer Herzerkrankungen sowie die Muster untersucht, die Meldungen zu Stürzen im häuslichen Bereich aufzeigen. In beiden Fällen lassen sich Korrelationen aufzeigen, die aber für eine individuelle Prognose im Rahmen einer Dienstleistung zu schwach sind. Der zweite Schwerpunkt, die Informationsmodule, ist im Zuge einer thematischen Neuausrichtung des Projekts LivingSmart aufgrund der Covid-19-Pandemie entstanden. Die Informationsmodule sollen vor allem die Risikogruppe der älteren Personen, welche im besonderen Maße von der Pandemie betroffen wurde, unterstützen. Innerhalb der LivingSmart-Plattform stellen sie Informationen bereit, die im Rahmen der Covid-19-Pandemie von besonderer Bedeutung sind – zur Pandemie und den aktuell geltenden Maßnahmen einerseits und zu Bewegung und Ernährung andererseits, da Bewegungsmangel und Mangelernährung und das daraus ggf. resultierende Frailty-Syndrom unter Pandemiebedingungen eine besondere Gefährdung für ältere Nutzer darstellen.

Due to the physical, psychological, or socioeconomic changes that accompany aging, many people will be affected by geriatric frailty syndrome, which can lead to multimorbidity and premature death. Nutrition counseling is often used to prevent and intervene in frailty syndrome, especially in geriatric rehabilitation. To this end, the consumption behavior of geriatric patients is recorded using paper-based, as well as retrospective memory logs in face-to-face interviews between patients and nutritionists. To simplify this procedure, a digital nutrition diary was developed that is specially adapted to the needs of geriatric patients (>=70 years), enabling them to record their consumption behavior themselves. In an initial study (Study 1), conducted in a geriatric rehabilitation division with twelve subjects (ten male, two female, mean age 79.2 ±5.9 years), feedback about the usability of the digital nutrition diary, and how to improve it, was surveyed. In addition, the usability of an activity tracker and a body composition scale was surveyed to determine whether geriatric patients are generally able to use these devices. In a second study (Study 2), also conducted in the geriatric rehabilitation division, this time with sixteen subjects (ten male, six female, mean age 79.3 ±3.9 years), the usability of the digital nutrition diary was surveyed again to evaluate its modifications based on the feedback from Study 1. In Study 1, the usability rating of the system (0–100) was 82.5 for the activity tracker, 29.71 for the body composition scale, and 51.66 initially for the digital nutrition diary, which increased to 76.41 in Study 2.

Although digitization and artificial intelligence are already being used in many areas, nutritional counseling for frailty patients is largely retrospective and based on analog questionnaires. In order to enable a broad spectrum of frailty patients to independently keep a digital nutrition diary, this paper presents a hybrid input method based on object detection using artificial intelligence in combination with a dynamic and interactive interview mode. The interview mode dynamically queries for possible missing inputs based on the objects detected by the artificial intelligence. The artificial intelligence was trained with open source and specifically for this use case generated data. A study with 21 subjects compared the hybrid approach with four other approaches and mobile applications based on usability, time effort, and detection accuracy. Especially in the area of usability, the hybrid approach came out on top.

A person's stool can tell a lot about his or her state of health. Among other things, diarrhea or constipation lead to a reduced digestive efficiency. For many people their own stool is a shameful topic. However, the effectiveness of digestion of food has a direct influence on the recommendations for patients undergoing a nutritional therapy. This paper outlines a prototypical system for an automatic and ambient classification of stool forms into three classes: thin, normal, and hard stool based on the Bristol Stool Scale. The stool is recorded in transit after exiting the anus until it reaches the toilet floor to avoid the problems of conventional procedures. Corresponding data were generated under laboratory conditions. Various algorithms from the field of machine learning and deep learning were applied to this data. The evaluation results show that two out of five of these algorithms achieve classification rates of 100%

Stereoscopic cameras allow for the capturing of three-dimensional objects and their volumes in an efficient and ambient way. This work evaluates to what extent this technology can be used to estimate consumption quantities to improve the data basis for nutritionists in the geriatric context for people affected by the frailty syndrome. For this purpose, a system that allows measurements without manual calibrations or additional markers was developed. These measurements result in so-called point clouds that have to be post-processed for further analysis since they they cannot be used directly for the calculation of consumption food quantities. Due to the high dimension of the parameter space of the possible filters and statistical methods and their permutations, a preliminary evaluation is outlined that results in a set of configurations that generally allow for stable measurements. The determined configurations are then further investigated for their accuracy and stability under different lighting conditions and consumption food quantities. Estimated quantities are compared with the plate protocol as one state of the art method in the geriatric and rehabilitation context. The results show that stereoscopic cameras have the potential to be used for the estimation of food intake quantities.

The goal of the DiDiER project is to verifiably improve services in the field of dietary counselling. This will be achieved by digitising information to increase counselling intensity and to improve workflows for the service provider. The project will develop an IT-based support system for dietary counselling, covering two use cases, facilitation and support of the work of nutritionists in ambulatory allergological nutrition counselling and of nutritionists involved in the care of geriatric patients, especially of those with frailty. One of the project's significant features is that the user's sensitive data remain under his or her personal control at all times.

The electron beam induced deposition process is a versatile and promising technology to improve and build a variety of different targets. The technique works in scanning electron microscope environment and is applicable from the micro-down to the nanometer scale. The fundamental working principle is well known and investigated. However, its application as standard process is still lacking, since repeatability and throughput are infancy. Especially, as this technique is performed manually. An automation and stabilization of the EBID process is desirable but challenging, since the SEM working environment is accompanied with many disturbing effects. Therefore, this work outlines automation strategies to handle those effects and achieve high repeatability and high throughput. These strategies are validated on an external offthe-shelf computer that is connected with the scanning electron microscope via self-developed scan generator. Analyzing these strategies show high repeatability and a reasonable throughput. An outlook is given about the possibilities on extending the scan generator to be able to do an online control of the electron beam induced depositions process.

Research as well as industrial projects in the field of micro- and nanorobotics often incorporate complex experimental setups using different devices with varying and often complex interfaces. In order to provide an easier interface to these devices, this paper outlines the extension of a versatile software framework called OFFIS Automation Framework, for automation, image processing and controlling purposes in this field of application. Especially, features like the integration of a macro world robot operating system, an industrial level and real-time capable automation system and the support of a standard laboratory device interface are introduced in this work. Furthermore, applications are presented for each of these new features. Finally, the field of applications is summarized and a brief outlook is given on future developments of this software framework.

Template matching is an important image processing algorithm for object detection and tracking tasks especially because of its very high accuracy. Yet, one major disadvantage of this algorithm is its very high computational effort due to its high complexity which results in low update rates using conventional software-based systems. Additionally, these systems are often afflicted by latency and jitter. Pre-calculating small and robust templates allows for using FPGA-based template matching as an approach to solve these problems. Therefore, the paper outlines three successive software-based approaches to find these small and robust templates. The first approach contains the basic algorithm and is refined by the following two approaches using pre-processing. The resulting templates allow for using the programmable hardware of an FPGA to cache necessary image information and, more importantly, to derive the best matching of template and source image, which results in high update rates. This paper shows novel approaches to high-speed template matching on FPGAs. The validation of these approaches has shown that the resulting tracking quality and feasibility is highly dependent on the relative size of the template in regard to the object to track. The results show tracking uncertainties between one single pixel for low and hundreds of pixels for high resolution videos.