A retargetable model-driven framework for the development of mobile user interfaces. - In: Journal of circuits, systems, and computers, ISSN 1793-6454, Bd. 31 (2022), 1, 2250018
Since the emergence of mobile devices, the architecture of mobile applications has been transformed significantly. In mobile applications, the User Interface (UI) is one of the major elements, but its development is complex and time-consuming. Existing practices do not support various presentation issues of the UI at a higher abstraction level, in a retargetable fashion, with complete tool support. Therefore, it is critical to develop a simple and automated framework for the development of mobile UIs by exploiting model-driven engineering concepts. In this paper, a Unified Modeling language (UML) profile for Mobile User Interfaces (UMMUI) has been proposed, which employs some standard UML notations for representing the mobile UI requirements at a higher abstraction level. Subsequently, a complete open-source transformation engine has been developed to automatically transform the high-level source models (in UMMUI) into the target low-level React Native implementation. Finally, the applicability of the proposed framework is validated through two benchmark case studies, i.e., Patient Management System and Library Application. The results verify that the proposed framework allows the modeling of UIs with simplicity and generates the target code automatically with minimum transformation losses.
https://doi.org/10.1142/S0218126622500189
Model-based design and evaluation of future fail-operational electric drivetrains. - In: 22. Internationales Stuttgarter Symposium, (2022), S. 71-85
In highly and fully automated vehicles, a driver is not required to permanently supervise the driving task. This leads to new requirements on fail-operational system behavior with the goal to reach a safe state in case of a fault. With fail-operability of the propulsion system, a vehicle can be stopped outside of active traffic, increasing the safety of passengers. Thus, it is assumed as a requirement for future electric powertrains. Fail-operability is generally achieved with redundancy at different architecture levels to ensure a minimum required level of functionality in case of a fault. This also leads to additional degrees of freedom for enhanced control in fault-free operation. In this work, a model-based methodology including dynamic safety analysis to support architectural decisions of drivetrain systems in the early design process is presented. Further, the proposed methodology is applied to examine feasible drivetrain design variants with respect to their fail-operability, relative acquisition cost, and relative energy efficiency. The results show that a high degree of fail-operability can be achieved either with two electric axles with one electric drive each or one electric axle with two electric drives on the same input shaft of the transmission. Drivetrain topologies with two electric axles and clutches, disconnecting the faulty parts, are recommended when mechanical faults are also considered. Furthermore, drivetrain topologies with multiple electrical machines show benefits with respect to energy efficiency by minimizing the losses through optimal torque distribution.
https://doi.org/10.1007/978-3-658-37009-1_5
Applying novel EMBRACE technological solutions to measure and optimize brain response to exercise.. - In: Alzheimer's and dementia, ISSN 1552-5279, Bd. 18 (2022), e069057, insges. 1 S.
Background: Extensive evidence supports the notion that physical activity (PA) promotes healthy aging and contributes to the prevention of brain damage and dementia. However, there are relevant differences in individual response to exercise that could mediate the extent of the PA-induced benefits. Here, we propose the application of the novel technology that is currently being developed by the EMBRACE project researchers to the characterization of the individual physiological response to exercise in older adults. Method: EMBRACE is an intersectoral and international consortium that brings together experts in biomedical engineering, material science, signal processing, neuroscience and social psychology from 3 academic and 3 industrial partners across 3 EU countries to develop: 1) a new mobile and wireless dry electrode EEG system suitable for monitoring brain activity during full body movements; 2) novel body network sensors and a multimodal alignment system for simultaneously recording of neural, physiological and kinematic signals from two interacting subjects; 3) novel analytical solutions for motion artefact removal and multi-level analysis of multimodal data; and 4) a new research dyadic paradigm to exploit the technological advances. Result: The novel technological solutions that are being currently developed by the EMBRACE consortium will enable the study of joint action at the neural, cognitive, behavioral and social levels while the participant engages in PA (individually or in social interaction), wearing a comfortable and long-lasting acquisition system. Conclusion: A detailed characterization of the individual response to exercise will help in the optimization of exercise routines with the aim to elicit the desired physiological response to enhance brain health and prevent dementia.
https://doi.org/10.1002/alz.069057
Using consensual biterms from text structures of requirements and code to improve IR-based traceability recovery. - In: ASE '22, (2022), 114, insges. 13 S.
Traceability approves trace links among software artifacts based on whether two artifacts are related by system functionalities. The traces are valuable for software development, but are difficult to obtain manually. To cope with the costly and fallible manual recovery, automated approaches are proposed to recover traces through textual similarities among software artifacts, such as those based on Information Retrieval (IR). However, the low quality & quantity of artifact texts negatively impact the calculated IR values, thus greatly hindering the performance of IR-based approaches. In this study, we propose to extract co-occurred word pairs from the text structures of both requirements and code (i.e., consensual biterms) to improve IR-based traceability recovery. We first collect a set of biterms based on the part-of-speech of requirement texts, and then filter them through the code texts. We then use these consensual biterms to both enrich the input corpus for IR techniques and enhance the calculations of IR values. A nine-system-based evaluation shows that in general, when solely used to enhance IR techniques, our approach can outperform pure IR-based approaches and another baseline by 21.9% & 21.8% in AP, and 9.3% & 7.2% in MAP, respectively. Moreover, when used to collaborate with another enhancing strategy from different perspectives, it can outperform this baseline by 5.9% in AP and 4.8% in MAP.
https://doi.org/10.1145/3551349.3556948
Generalizability of code clone detection on CodeBERT. - In: ASE '22, (2022), 143, insges. 3 S.
Transformer networks such as CodeBERT already achieve outstanding results for code clone detection in benchmark datasets, so one could assume that this task has already been solved. However, code clone detection is not a trivial task. Semantic code clones, in particular, are challenging to detect. We show that the generalizability of CodeBERT decreases by evaluating two different subsets of Java code clones from BigCloneBench. We observe a significant drop in F1 score when we evaluate different code snippets and functionality IDs than those used for model building.
https://doi.org/10.1145/3551349.3561165
Nutritional assessment of ready-to-eat salads in German supermarkets: comparison of the nutriRECIPE-Index and the Nutri-Score. - In: Foods, ISSN 2304-8158, Bd. 11 (2022), 24, 4011, S. 1-21
Globally, an unbalanced diet causes more deaths than any other factor. Due to a lack of knowledge, it is difficult for consumers to select healthy foods at the point of sale. Although different front-of-pack labeling schemes exist, their informative value is limited due to small sets of considered parameters and lacking information on ingredient composition. We developed and evalauated a manufacture-independent approach to quantify ingredient composition of 294 ready-to eat salads (distinguished into 73 subgroups) as test set. Nutritional quality was assessed by the nutriRECIPE-Index and compared to the Nutri-Score. The nutriRECIPE-Index comprises the calculation of energy-adjusted nutrient density of 16 desirable and three undesirable nutrients, which are weighted according to their degree of supply in the population. We show that the nutriRECIPE-Index has stronger discriminatory power compared to the Nutri-Score and discriminates as well or even better in 63 out of the 73 subgroups. This was evident in groups where seemingly similar products were compared, e.g., potato salads (Nutri-Score: C only, nutriRECIPE-Index: B, C and D). Moreover, the nutriRECIPE-Index is adjustable to any target population’s specific needs and supply situation, such as seniors, and children. Hence, a more sophisticated distinction between single food products is possible using the nutriRECIPE-Index.
https://doi.org/10.3390/foods11244011
Development of torque vectoring controller tuned with neural networks. - In: Advances in dynamics of vehicles on roads and tracks II, (2022), S. 1175-1182
The paper introduces an adaptive Torque Vectoring (TV) controller for all-wheel-drive electric vehicles. The main focus of this study lies in tuning procedures of controller gains in accordance with the manoeuvre conditions. For this purpose, a pre-trained neural network predicts the vehicle behaviour and adjusts the PID gains of the TV controller. The proposed method extends the applicability of the TV system and increases its efficiency as compared to the non-adaptive baseline control methods.
EEG/MEG source reconstruction : textbook for electro-and magnetoencephalography. - Cham : Springer, 2022. - 1 Online-Ressource (XIX, 415 Seiten) ISBN 978-3-030-74918-7
https://ebookcentral.proquest.com/lib/kxp/detail.action?docID=7102592
Preface to the special issue “Scientific and Clinical Applications of Magnetic Carriers 2022”. - In: Journal of magnetism and magnetic materials, ISSN 1873-4766, Bd. 564 (2022), 2, 170205
https://doi.org/10.1016/j.jmmm.2022.170205
GANSet - generating annnotated datasets using Generative Adversarial Networks. - In: Proceedings of the International Conference on Cyber-Physical Social Intelligence (ICCSI 2022), (2022), S. 615-620
The prediction of soil moisture for automated irrigation applications is a major challenge, as it is affected by various environmental parameters. The Application of Convolutional Neural Networks (CNN), to this end, has shown remarkable results for soil moisture prediction. These models, however, typically need large datasets, which are scarce in the agriculture field. To this end, this paper presents a Deep Convolutional Generative Adversarial Network (DCGAN) that can learn good data representations and generate highly realistic samples. Traditionally, Generative Adversarial Networks (GANs) have been used for generating data for segmentation and classification tasks or used in conjunction with CNNs or Multi Layer Perceptrons (MLPs) for regression tasks. In this paper, we propose a novel approach in which GANs are used to generate conjointly training images for plants as well as realistic regression values for their corresponding moisture levels without the use of any additional network. The generated images and regression vector targets, together with the training data, are then used to train a CNN which is then evaluated with actual test data from the dataset. We observe an improvement of error rate by 33 percent which shows the validity of our approach.
https://doi.org/10.1109/ICCSI55536.2022.9970561