Refine
Document Type
- Conference proceeding (31)
- Book (20)
- Book chapter (3)
- Journal article (2)
- Journal (1)
- Report (1)
- Working Paper (1)
Language
- English (59) (remove)
Is part of the Bibliography
- yes (59)
Institute
- Informatik (25)
- Texoversum (22)
- ESB Business School (10)
- Life Sciences (1)
- Technik (1)
Publisher
- Hochschule Reutlingen (59) (remove)
Sleep analysis using a Polysomnography system is difficult and expensive. That is why we suggest a non-invasive and unobtrusive measurement. Very few people want the cables or devices attached to their bodies during sleep. The proposed approach is to implement a monitoring system, so the subject is not bothered. As a result, the idea is a non-invasive monitoring system based on detecting pressure distribution. This system should be able to measure the pressure differences that occur during a single heartbeat and during breathing through the mattress. The system consists of two blocks signal acquisition and signal processing. This whole technology should be economical to be affordable enough for every user. As a result, preprocessed data is obtained for further detailed analysis using different filters for heartbeat and respiration detection. In the initial stage of filtration, Butterworth filters are used.
Purpose: The purpose of this study was to investigate the value of the web representation of certain fashion hot spots and how these results can be shown on fashion maps in an illustrated way.
Design/methodology/approach: A new ranking was created, which was evaluated with a self-instructed index, to gain solid results. Numbers were collected from Google, Instagram, Facebook, Twitter and web.alert.io. Additionally, fashion maps were created for an illustrative visualization of the results.
Findings: Compared with the ranking of a trend forecasting agency, called Global Language Monitor, which concepted a ranking of non-virtual fashion cities, the web representation and therefore the ranking of the research project, differs mainly in the situation of the cities among the first 10, viz. the rank on which a city occurs, but fewer in the actual cities mentioned.
Research limitations: The research was limited to subjective analysis of data, leading to partly subjective results, as well as the selected number of social media platforms, that had been used.
Originality/value: This is the first study to explore the web representation value of fashion metropolises in comparison to their non-virtual ranking. The results are partly based on results that already existed, concerning transformations of fashion cities or in general which cities own the status of a fashion city.
This paper investigates the possibility to effectively monitor and control the respiratory action using a very simple and non invasive technique based on a single lightweight reduced-size wireless surface electromyography (sEMG) sensor placed below the sternum. The captured sEMG signal, due to the critical sensor position, is characterized by a low energy level and it is affected by motion artifacts and cardiac noise. In this work we present a preliminary study performed on adults for assessing the correlation of the spirometry signal and the sEMG signal after the removal of the superimposed heart signal. This study and the related findings could be useful in respiratory monitoring of preterm infants.
This research is about Omnichannel Retailing and addresses the question how the omnichanneling of retailers in the fashion market can be measured. Our sources will include books, interviews, newspapers and scientific databases.
Omnichanneling is a current topic in the fashion market, retailers all over the world face the question on how to adapt to the challenges Omnichannel Retailing sets. We are going to define what Omnichanneling is by explaining the differences between Multiple-, Multi-, Cross- and Omnichannel Retailing. After we defined omnichanneling itself, we took a set of 26 retailers to evaluate regarding their Omnichannel capabilities. Then we create an index with criteria that can measure the Omnichannel capability of each retailer.
The Omnichannel Score is based on 31 criteria, which analyze the retailers in offline, online, mobile and social aspects enables to see differences between retailers. Our findings were that retailers in the US fashion market are more advanced in Omnichannel Retailing than retailers in the German fashion market. Our top three Omnichannel retailers were Sears with an Omnichannel Score of 91, followed by KOHL’S and Marks&Spencer, both with a Omnichannel Score of 88. The best Omnichannel Retailer from Germany was Adidas with the fourth place and an Omnichannel Score of 81.
Determination of accelerometer sensor position for respiration rate detection: initial research
(2022)
Continuous monitoring of a patient's vital signs is essential in many chronic illnesses. The respiratory rate (RR) is one of the vital signs indicating breathing diseases. This article proposes the initial investigation for determining the accelerometric sensor position of a non-invasive and unobtrusive respiratory rate monitoring system. This research aims to determine the sensor position in relation to the patient, which can provide the most accurate values of the mentioned physiological parameter. In order to achieve the result, the particular system setup, including a mechanical sensor holder construction was used. The breathing signals from 5 participants were analyzed corresponding to the relaxed state. The main criterion for selecting a suitable sensor position was each patient's average acceleration amplitude excursion, which corresponds to the respiratory signal. As a result, we provided one more defined important parameter for the considered system, which was not determined before.
When wearing compressive garments, the tissue of the human body is altered in relation to its natural shape by the properties of the applied material and by the pattern construction used.
To check the fit of garments, both construction and selected materials can be virtually simulated in 3D on avatars in corresponding CAD programs before fabrication.
The software Blender allows the modelling of an avatar and to generate in respective to the different tissue zones with their specific properties to adjust them with soft body physics according to the testing of real soft tissue but the models in Blender are mainly using linear springs.
Imagine a world in which the search for tomorrow's trends of (software) products is not subject to a long and laborious data search but is possible with a single mouse click. Through the use of artificial intelligence (AI), this reality is made possible and is to be further advanced through research. The study therefore aims to provide an initial overview of the young research field. Based on research, expert interviews, company and student surveys, current application possibilities of AI in the innovation process (defined as Smart Innovation), existing challenges that slow down the further development are discussed in more detail and future application possibilities are presented. Finally, a recommendation for action is made for business, politics and science to help overcome the current obstacles together and thus drive the future of Smart Innovation.
Semi-automated image data labelling using AprilTags as a pre-processing step for machine learning
(2019)
Data labelling is a pre-processing step to prepare data for machine learning. There are many ways to collect and prepare this data, but these are usually associated with a greater effort. This paper presents an approach to semi-automated image data labelling using AprilTags. The AprilTags attached to the object, which contain a unique ID, make it possible to link the object surfaces to a particular class. This approach will be implemented and used to label data of a stackable box.
The data is evaluated by training a You Only Look Once (YOLO) net, with a subsequent evaluation of the detection results. These results show that the semi-automatically collected and labelled data can certainly be used for machine learning. However, if concise features of an object surface are covered by the AprilTag, there is a risk that the concerned class will not be recognized. It can be assumed that the labelled data can not only be used for YOLO, but also for other machine learning approaches.