Refine
Document Type
- Journal article (1244)
- Conference proceeding (1039)
- Book chapter (381)
- Book (223)
- Doctoral Thesis (54)
- Working Paper (38)
- Anthology (32)
- Report (25)
- Patent / Standard / Guidelines (24)
- Issue of a journal (19)
Is part of the Bibliography
- yes (3088)
Institute
- ESB Business School (1107)
- Informatik (875)
- Technik (509)
- Life Sciences (343)
- Texoversum (220)
- Zentrale Einrichtungen (16)
Publisher
- Springer (473)
- IEEE (252)
- Elsevier (243)
- Hochschule Reutlingen (191)
- MDPI (99)
- Wiley (72)
- Gesellschaft für Informatik e.V (69)
- Universität Tübingen (65)
- De Gruyter (60)
- VDE Verlag (48)
The digitization of our society changes the way we live, work, learn, communicate, and collaborate. This disruptive change interacts with all information processes and systems that are important business enablers for the context of digitization since years. Our aim is to support flexibility and agile transformations for both business domains and related information technology with more flexible enterprise information systems through adaptation and evolution of digital enterprise architectures. The present research paper investigates the continuous bottom-up integration of micro-granular architectures for a huge amount of dynamically growing systems and services, like microservices and the Internet of Things, as part of a new digital enterprise architecture. To integrate micro granular architecture models to living architectural model versions we are extending more traditional enterprise architecture reference models with state of art elements for agile architectural engineering to support the digitization of products, services, and processes.
Mit dem Kunstbegriff "Virtuelle Realität" beschreibt man die Darstellung von künstlichen Welten und die Interaktion mit den selbigen. Meist verbindet man damit teure Spiel- und Filmproduktionen. Doch durch derzeitige Entwicklungen können auch kleine Entwicklerstudios und Endanwender auf Bewegungserkennungssysteme zurückgreifen. In dieser Ausarbeitung werden zwei Prototypen vorgestellt, die auf eben diese Systeme zurückgreifen. In den Prototypen soll eine Interaktion mit der Umwelt und ein "Mittendringefühl" im Rahmen von Serious Games ermöglicht werden.
An interactive clothing design and a personalized virtual display with user’s own face are presented in this paper to meet the requirement of personalized clothing customization. A customer interactive clothing design approach based on genetic engineering ideas is analyzed by taking suit as an example. Thus, customers could rearrange the clothing style elements, chose available color, fabric and come up with their own personalized suit style. A web 3D customization prototype system of personalized clothing is developed based on the Unity3D and VR technology. The layout of the structure and functions combined with the flow of the system are given. Practical issues such as 3D face scanning, suit style design, fabric selection, and accessory choices are addressed also. Tests to the prototype system indicate that it could show realistic clothing and fabric effect and offer effective visual and customization experience to users.
Usually battery chargers have two stages and DC charging current is considered to by necessary for a proper charging. To decrease the charger volume, a single stage LLC battery charger is investigated in this paper. PFC stage is eliminated, therefore no bulky capacitor is necessary any more, and battery is charged with a sinusoidal-like charging current. However, previous studies show that such a pulsating charging current has only minimal impact on battery life and efficiency. Design considerations of the resonant tank and optimal transformer design are presented. A 360W single stage LLC converter prototype for e-bike charger achieves a power factor of 0.98, efficiency of 0.93 and power density of 1,8kW/dm³.
Background
The actual task of electrocardiographic examinations is to increase the reliability of diagnosing the condition of the heart. Within the framework of this task, an important direction is the solution of the inverse problem of electrocardiography, based on the processing of electrocardiographic signals of multichannel cardio leads at known electrode coordinates in these leads (Titomir et al. Noninvasiv electrocardiotopography, 2003), (Macfarlane et al. Comprehensive Electrocardiology, 2nd ed. (Chapter 9), 2011).
Results
In order to obtain more detailed information about the electrical activity of the heart, we carry out a reconstruction of the distribution of equivalent electrical sources on the heart surface. In this area, we hold reconstruction of the equivalent sources during the cardiac cycle at relatively low hardware cost. ECG maps of electrical potentials on the surface of the torso (TSPM) and electrical sources on the surface of the heart (HSSM) were studied for different times of the cardiac cycle. We carried out a visual and quantitative comparison of these maps in the presence of pathological regions of different localization. For this purpose we used the model of the heart electrical activity, based on cellular automata.
Conclusions
The model of cellular automata allows us to consider the processes of heart excitation in the presence of pathological regions of various sizes and localization. It is shown, that changes in the distribution of electrical sources on the surface of the epicardium in the presence of pathological areas with disturbances in the conduction of heart excitation are much more noticeable than changes in ECG maps on the torso surface.
This paper presents a permanent magnet tubular linear generator system for powering passive sensors using vertical vibration harvesting energy. The system consists of a permanent magnet tubular linear vibration generator and electric circuits. By using the design of mechanical resonant movers, the generator is capable of converting low frequencies small amplitude vertical vibration energy into more regular sinusoidal electrical energy. The distribution of the magnetic field and electromotive force are calculated by Finite Element Analysis. The characteristics of the linear vibration generator system are observed. The experimental results show the generator can produce about 0.4W~1.6W electrical power when the vibration source's amplitude is fixed on 2mm and the frequencies are between 13Hz and 22Hz.
Purpose
Computerized medical imaging processing assists neurosurgeons to localize tumours precisely. It plays a key role in recent image-guided neurosurgery. Hence, we developed a new open-source toolkit, namely Slicer-DeepSeg, for efficient and automatic brain tumour segmentation based on deep learning methodologies for aiding clinical brain research.
Methods
Our developed toolkit consists of three main components. First, Slicer-DeepSeg extends the 3D Slicer application and thus provides support for multiple data input/ output data formats and 3D visualization libraries. Second, Slicer core modules offer powerful image processing and analysis utilities. Third, the Slicer-DeepSeg extension provides a customized GUI for brain tumour segmentation using deep learning-based methods.
Results
The developed Slicer-DeepSeg was validated using a public dataset of high-grade glioma patients. The results showed that our proposed platform’s performance considerably outperforms other 3D Slicer cloud-based approaches.
Conclusions
Developed Slicer-DeepSeg allows the development of novel AI-assisted medical applications in neurosurgery. Moreover, it can enhance the outcomes of computer-aided diagnosis of brain tumours. Open-source Slicer-DeepSeg is available at github.com/razeineldin/Slicer-DeepSeg.
Intraoperative imaging can assist neurosurgeons to define brain tumours and other surrounding brain structures. Interventional ultrasound (iUS) is a convenient modality with fast scan times. However, iUS data may suffer from noise and artefacts which limit their interpretation during brain surgery. In this work, we use two deep learning networks, namely UNet and TransUNet, to make automatic and accurate segmentation of the brain tumour in iUS data. Experiments were conducted on a dataset of 27 iUS volumes. The outcomes show that using a transformer with UNet is advantageous providing an efficient segmentation modelling long-range dependencies between each iUS image. In particular, the enhanced TransUNet was able to predict cavity segmentation in iUS data with an inference rate of more than 125 FPS. These promising results suggest that deep learning networks can be successfully deployed to assist neurosurgeons in the operating room.
A hybrid deep registration of MR scans to interventional ultrasound for neurosurgical guidance
(2021)
Despite the recent advances in image-guided neurosurgery, reliable and accurate estimation of the brain shift still remains one of the key challenges. In this paper, we propose an automated multimodal deformable registration method using hybrid learning-based and classical approaches to improve neurosurgical procedures. Initially, the moving and fixed images are aligned using classical affine transformation (MINC toolkit), and then the result is provided to the convolutional neural network, which predicts the deformation field using backpropagation. Subsequently, the moving image is transformed using the resultant deformation into a moved image. Our model was evaluated on two publicly available datasets: the retrospective evaluation of cerebral tumors (RESECT) and brain images of tumors for evaluation (BITE). The mean target registration errors have been reduced from 5.35 ± 4.29 to 0.99 ± 0.22 mm in the RESECT and from 4.18 ± 1.91 to 1.68 ± 0.65 mm in the BITE. Experimental results showed that our method improved the state-of-the-art in terms of both accuracy and runtime speed (170 ms on average). Hence, the proposed method provides a fast runtime for 3D MRI to intra-operative US pair in a GPU-based implementation, which shows a promise for its applicability in assisting the neurosurgical procedures compensating for brain shift.
Glioblastomas are the most aggressive fast-growing primary brain cancer which originate in the glial cells of the brain. Accurate identification of the malignant brain tumor and its sub-regions is still one of the most challenging problems in medical image segmentation. The Brain Tumor Segmentation Challenge (BraTS) has been a popular benchmark for automatic brain glioblastomas segmentation algorithms since its initiation. In this year, BraTS 2021 challenge provides the largest multi-parametric (mpMRI) dataset of 2,000 pre-operative patients. In this paper, we propose a new aggregation of two deep learning frameworksnamely, DeepSeg and nnU-Net for automatic glioblastoma recognition in pre-operative mpMRI. Our ensemble method obtains Dice similarity scores of 92.00, 87.33, and 84.10 and Hausdorff Distances of 3.81, 8.91, and 16.02 for the enhancing tumor, tumor core, and whole tumor regions, respectively, on the BraTS 2021 validation set, ranking us among the top ten teams. These experimental findings provide evidence that it can be readily applied clinically and thereby aiding in the brain cancer prognosis, therapy planning, and therapy response monitoring. A docker image for reproducing our segmentation results is available online at (https://hub.docker.com/r/razeineldin/deepseg21).
Intraoperative brain deformation, so called brain shift, affects the applicability of preoperative magnetic resonance imaging (MRI) data to assist the procedures of intraoperative ultrasound (iUS) guidance during neurosurgery. This paper proposes a deep learning-based approach for fast and accurate deformable registration of preoperative MRI to iUS images to correct brain shift. Based on the architecture of 3D convolutional neural networks, the proposed deep MRI-iUS registration method has been successfully tested and evaluated on the retrospective evaluation of cerebral tumors (RESECT) dataset. This study showed that our proposed method outperforms other registration methods in previous studies with an average mean squared error (MSE) of 85. Moreover, this method can register three 3D MRI-US pair in less than a second, improving the expected outcomes of brain surgery.
Purpose: Gliomas are the most common and aggressive type of brain tumors due to their infiltrative nature and rapid progression. The process of distinguishing tumor boundaries from healthy cells is still a challenging task in the clinical routine. Fluid attenuated inversion recovery (FLAIR) MRI modality can provide the physician with information about tumor infiltration. Therefore, this paper proposes a new generic deep learning architecture, namely DeepSeg, for fully automated detection and segmentation of the brain lesion using FLAIR MRI data.
Methods: The developed DeepSeg is a modular decoupling framework. It consists of two connected core parts based on an encoding and decoding relationship. The encoder part is a convolutional neural network (CNN) responsible for spatial information extraction. The resulting semantic map is inserted into the decoder part to get the full-resolution probability map. Based on modified U-Net architecture, different CNN models such as residual neural network (ResNet), dense convolutional network (DenseNet), and NASNet have been utilized in this study.
Results: The proposed deep learning architectures have been successfully tested and evaluated on-line based on MRI datasets of brain tumor segmentation (BraTS 2019) challenge, including s336 cases as training data and 125 cases for validation data. The dice and Hausdorff distance scores of obtained segmentation results are about 0.81 to 0.84 and 9.8 to 19.7 correspondingly.
Conclusion: This study showed successful feasibility and comparative performance of applying different deep learning models in a new DeepSeg framework for automated brain tumor segmentation in FLAIR MR images. The proposed DeepSeg is open source and freely available at https://github.com/razeineldin/DeepSeg/.
Accurate and safe neurosurgical intervention can be affected by intra-operative tissue deformation, known as brain-shift. In this study, we propose an automatic, fast, and accurate deformable method, called iRegNet, for registering pre-operative magnetic resonance images to intra-operative ultrasound volumes to compensate for brain-shift. iRegNet is a robust end-to-end deep learning approach for the non-linear registration of MRI-iUS images in the context of image-guided neurosurgery. Pre-operative MRI (as moving image) and iUS (as fixed image) are first appended to our convolutional neural network, after which a non-rigid transformation field is estimated. The MRI image is then transformed using the output displacement field to the iUS coordinate system. Extensive experiments have been conducted on two multi-location databases, which are the BITE and the RESECT. Quantitatively, iRegNet reduced the mean landmark errors from pre-registration value of (4.18 ± 1.84 and 5.35 ± 4.19 mm) to the lowest value of (1.47 ± 0.61 and 0.84 ± 0.16 mm) for the BITE and RESECT datasets, respectively. Additional qualitative validation of this study was conducted by two expert neurosurgeons through overlaying MRI-iUS pairs before and after the deformable registration. Experimental findings show that our proposed iRegNet is fast and achieves state-of-the-art accuracies outperforming state-of-the-art approaches. Furthermore, the proposed iRegNet can deliver competitive results, even in the case of non-trained images as proof of its generality and can therefore be valuable in intra-operative neurosurgical guidance.
Purpose
Artificial intelligence (AI), in particular deep neural networks, has achieved remarkable results for medical image analysis in several applications. Yet the lack of explainability of deep neural models is considered the principal restriction before applying these methods in clinical practice.
Methods
In this study, we propose a NeuroXAI framework for explainable AI of deep learning networks to increase the trust of medical experts. NeuroXAI implements seven state-of-the-art explanation methods providing visualization maps to help make deep learning models transparent.
Results
NeuroXAI has been applied to two applications of the most widely investigated problems in brain imaging analysis, i.e., image classification and segmentation using magnetic resonance (MR) modality. Visual attention maps of multiple XAI methods have been generated and compared for both applications. Another experiment demonstrated that NeuroXAI can provide information flow visualization on internal layers of a segmentation CNN.
Conclusion
Due to its open architecture, ease of implementation, and scalability to new XAI methods, NeuroXAI could be utilized to assist radiologists and medical professionals in the detection and diagnosis of brain tumors in the clinical routine of cancer patients. The code of NeuroXAI is publicly accessible at https://github.com/razeineldin/NeuroXAI.
Automatic segmentation is essential for the brain tumor diagnosis, disease prognosis, and follow-up therapy of patients with gliomas. Still, accurate detection of gliomas and their sub-regions in multimodal MRI is very challenging due to the variety of scanners and imaging protocols. Over the last years, the BraTS Challenge has provided a large number of multi-institutional MRI scans as a benchmark for glioma segmentation algorithms. This paper describes our contribution to the BraTS 2022 Continuous Evaluation challenge. We propose a new ensemble of multiple deep learning frameworks namely, DeepSeg, nnU-Net, and DeepSCAN for automatic glioma boundaries detection in pre-operative MRI. It is worth noting that our ensemble models took first place in the final evaluation on the BraTS testing dataset with Dice scores of 0.9294, 0.8788, and 0.8803, and Hausdorf distance of 5.23, 13.54, and 12.05, for the whole tumor, tumor core, and enhancing tumor, respectively. Furthermore, the proposed ensemble method ranked first in the final ranking on another unseen test dataset, namely Sub-Saharan Africa dataset, achieving mean Dice scores of 0.9737, 0.9593, and 0.9022, and HD95 of 2.66, 1.72, 3.32 for the whole tumor, tumor core, and enhancing tumor, respectively.
Recent advances in artificial intelligence have enabled promising applications in neurosurgery that can enhance patient outcomes and minimize risks. This paper presents a novel system that utilizes AI to aid neurosurgeons in precisely identifying and localizing brain tumors. The system was trained on a dataset of brain MRI scans and utilized deep learning algorithms for segmentation and classification. Evaluation of the system on a separate set of brain MRI scans demonstrated an average Dice similarity coefficient of 0.87. The system was also evaluated through a user experience test involving the Department of Neurosurgery at the University Hospital Ulm, with results showing significant improvements in accuracy, efficiency, and reduced cognitive load and stress levels. Additionally, the system has demonstrated adaptability to various surgical scenarios and provides personalized guidance to users. These findings indicate the potential for AI to enhance the quality of neurosurgical interventions and improve patient outcomes. Future work will explore integrating this system with robotic surgical tools for minimally invasive surgeries.
Purpose
Artificial intelligence (AI), in particular deep learning (DL), has achieved remarkable results for medical image analysis in several applications. Yet the lack of human-like explanations of such systems is considered the principal restriction before utilizing these methods in clinical practice (Yang, Ye, & Xia, 2022).
Methods
Explainable Artificial Intelligence (XAI) provides a human-explainable and interpretable description of the “black-box” nature of DL (Gulum, Trombley, & Kantardzic, 2021). An effective XAI diagnosis generator, namely NeuroXAI (refer to Fig. 1), has been developed to extract 3D explanations from convolutional neural networks (CNN) models of brain gliomas (Zeineldin et al., 2022). By providing visual justification maps, NeuroXAI can help make DL models transparent and thus increase the trust of medical experts.
Results
NeuroXAI has been applied to two applications of the most widely investigated problems in brain imaging analysis, i.e. image classification and segmentation using magnetic resonance imaging (MRI). Visual attention maps of multiple XAI methods have been generated and compared for both applications, which could help to provide transparency about the performance of DL systems.
Conclusion
NeuroXAI helps to understand the prediction process of 3D CNN networks for brain glioma using human-understandable explanations. Results revealed that the investigated DL models behave in a logical human-like manner and can improve the analytical process of the MRI images systematically. Due to its open architecture, ease of implementation, and scalability to new XAI methods, NeuroXAI could be utilized to assist medical professionals in the detection and diagnosis of brain tumors. NeuroXAI code is publicly accessible at https://github.com/razeineldin/NeuroXAI
Intracranial brain tumors are one of the ten most common malignant cancers and account for substantial morbidity and mortality. The largest histological category of primary brain tumors is the gliomas which occur with an ultimate heterogeneous appearance and can be challenging to discern radiologically from other brain lesions. Neurosurgery is mostly the standard of care for newly diagnosed glioma patients and may be followed by radiation therapy and adjuvant temozolomide chemotherapy.
However, brain tumor surgery faces fundamental challenges in achieving maximal tumor removal while avoiding postoperative neurologic deficits. Two of these neurosurgical challenges are presented as follows. First, manual glioma delineation, including its sub-regions, is considered difficult due to its infiltrative nature and the presence of heterogeneous contrast enhancement. Second, the brain deforms its shape, called “brain shift,” in response to surgical manipulation, swelling due to osmotic drugs, and anesthesia, which limits the utility of pre-operative imaging data for guiding the surgery.
Image-guided systems provide physicians with invaluable insight into anatomical or pathological targets based on modern imaging modalities such as magnetic resonance imaging (MRI) and Ultrasound (US). The image-guided toolkits are mainly computer-based systems, employing computer vision methods to facilitate the performance of peri-operative surgical procedures. However, surgeons still need to mentally fuse the surgical plan from pre-operative images with real-time information while manipulating the surgical instruments inside the body and monitoring target delivery. Hence, the need for image guidance during neurosurgical procedures has always been a significant concern for physicians.
This research aims to develop a novel peri-operative image-guided neurosurgery (IGN) system, namely DeepIGN, that can achieve the expected outcomes of brain tumor surgery, thus maximizing the overall survival rate and minimizing post-operative neurologic morbidity. In the scope of this thesis, novel methods are first proposed for the core parts of the DeepIGN system of brain tumor segmentation in MRI and multimodal pre-operative MRI to the intra-operative US (iUS) image registration using the recent developments in deep learning. Then, the output prediction of the employed deep learning networks is further interpreted and examined by providing human-understandable explainable maps. Finally, open-source packages have been developed and integrated into widely endorsed software, which is responsible for integrating information from tracking systems, image visualization, image fusion, and displaying real-time updates of the instruments relative to the patient domain.
The components of DeepIGN have been validated in the laboratory and evaluated in the simulated operating room. For the segmentation module, DeepSeg, a generic decoupled deep learning framework for automatic glioma delineation in brain MRI, achieved an accuracy of 0.84 in terms of the dice coefficient for the gross tumor volume. Performance improvements were observed when employing advancements in deep learning approaches such as 3D convolutions over all slices, region-based training, on-the-fly data augmentation techniques, and ensemble methods.
To compensate for brain shift, an automated, fast, and accurate deformable approach, iRegNet, is proposed for registering pre-operative MRI to iUS volumes as part of the multimodal registration module. Extensive experiments have been conducted on two multi-location databases: the BITE and the RESECT. Two expert neurosurgeons conducted additional qualitative validation of this study through overlaying MRI-iUS pairs before and after the deformable registration. Experimental findings show that the proposed iRegNet is fast and achieves state-of-the-art accuracies. Furthermore, the proposed iRegNet can deliver competitive results, even in the case of non-trained images, as proof of its generality and can therefore be valuable in intra-operative neurosurgical guidance.
For the explainability module, the NeuroXAI framework is proposed to increase the trust of medical experts in applying AI techniques and deep neural networks. The NeuroXAI includes seven explanation methods providing visualization maps to help make deep learning models transparent. Experimental findings showed that the proposed XAI framework achieves good performance in extracting both local and global contexts in addition to generating explainable saliency maps to help understand the prediction of the deep network. Further, visualization maps are obtained to realize the flow of information in the internal layers of the encoder-decoder network and understand the contribution of MRI modalities in the final prediction. The explainability process could provide medical professionals with additional information about tumor segmentation results and therefore aid in understanding how the deep learning model is capable of processing MRI data successfully.
Furthermore, an interactive neurosurgical display has been developed for interventional guidance, which supports the available commercial hardware such as iUS navigation devices and instrument tracking systems. The clinical environment and technical requirements of the integrated multi-modality DeepIGN system were established with the ability to incorporate: (1) pre-operative MRI data and associated 3D volume reconstructions, (2) real-time iUS data, and (3) positional instrument tracking. This system's accuracy was tested using a custom agar phantom model, and its use in a pre-clinical operating room is simulated. The results of the clinical simulation confirmed that system assembly was straightforward, achievable in a clinically acceptable time of 15 min, and performed with a clinically acceptable level of accuracy.
In this thesis, a multimodality IGN system has been developed using the recent advances in deep learning to accurately guide neurosurgeons, incorporating pre- and intra-operative patient image data and interventional devices into the surgical procedure. DeepIGN is developed as open-source research software to accelerate research in the field, enable ease of sharing between multiple research groups, and continuous developments by the community. The experimental results hold great promise for applying deep learning models to assist interventional procedures - a crucial step towards improving the surgical treatment of brain tumors and the corresponding long-term post-operative outcomes.
DMOS transistors are often subject to high power dissipation and thus substantial self-heating. This limits their safe operating area because very high device temperatures can lead to thermal runaway and subsequent destruction. Because the peak temperature usually occurs only in a small region in the device, it is possible to redistribute part of the dissipated power from the hot region to the cooler device areas. In this way, the peak temperature is reduced, whereas the total power dissipation is still the same. Assuming that a certain temperature must not be exceeded for safe operation, the improved device is now capable of withstanding higher amounts of energy with an unchanged device area. This paper presents two simple methods to redistribute the power dissipation density and thus lower the peak device temperature. The presented methods only require layout changes. They can easily be applied to modern power technologies without the need of process modifications. Both methods are implemented in test structures and investigated by simulations and measurements.
DMOS transistors often suffer from substantial self-heating during high power dissipation, which can lead to thermal destruction if the device temperature reaches excessive values. A successfully demonstrated method to reduce the peak temperature is the redistribution of power dissipation density from the hotter to the cooler device areas by careful layout modification. However, this is very tedious and time-consuming if complex-shaped devices as often found in industrial applications are considered.
This paper presents an approach for fully automatic layout optimization which requires only a few hours processing time. The approach is applied to complex shaped test structures which are investigated by measurements and electro-thermal simulations. Results show a significantly lower peak temperature and an energy capability gain of 84 %, offering potential for a 18 % size reduction of active area.
The general conclusion of climate change studies is the necessity of eliminating net CO2 emissions in general and from the electric power systems in particular by 2050. The share of renewable energy is increasing worldwide, but due to the intermittent nature of wind and solar power, a lack of system flexibility is already hampering the further integration of renewable energy in some countries. In this study, we analyze if and how combinations of carbon pricing and power-to-gas (PtG) generation in the form of green power-to-hydrogen followed by methanation (which we refer to as PtG throughout) using captured CO2 emissions can provide transitions to deep decarbonization of energy systems. To this end, we focus on the economics of deep decarbonization of the European electricity system with the help of an energy system model. In different scenario analyses, we find that a CO2 price of 160 €/t (by 2050) is on its own not sufficient to decarbonize the electricity sector, but that a CO2 price path of 125 (by 2040) up to 160 €/t (by 2050), combined with PtG technologies, can lead to an economically feasible decarbonization of the European electricity system by 2050. These results are robust to higher than anticipated PtG costs.
Vehicles have been so far improved in terms of energy-efficiency and safety mainly by optimising the engine and the power train. However, there are opportunities to increase energy-efficiency and safety by adapting the individual driving behaviour in the given driving situation. In this paper, an improved rule match algorithm is introduced, which is used in the expert system of a human-centred driving system. The goal of the driving system is to optimise the driving behaviour in terms of energy-efficiency and safety by giving recommendations to the driver. The improved rule match algorithm checks the incoming information against the driving rules to recognise any breakings of a driving rule. The needed information is obtained by monitoring the driver, the current driving situation as well as the car, using in-vehicle sensors and serial-bus systems. On the basis of the detected broken driving rules, the expert system will create individual recommendations in terms of energy-efficiency and safety, which will allow eliminating bad driving habits, while considering the driver needs.
Detecting the adherence of driving rules in an energy-efficient, safe and adaptive driving system
(2016)
An adaptive and rule-based driving system is being developed that tries to improve the driving behavior in terms of the energy-efficiency and safety by giving recommendations. Therefore, the driving system has to monitor the adherence of driving rules by matching the rules to the driving behavior. However, existing rule matching algorithms are not sufficient, as the data within a driving system is changing frequently. In this paper a rule matching algorithm is introduced that is able to handle frequently changing data within the context of the driving system. 15 journeys were used to evaluate the performance of the rule matching algorithms. The results showed that the introduced algorithm outperforms existing algorithms in the context of the driving system. Thus, the introduced algorithm is suited for matching frequently changing data against rules with a higher performance, why it will be used in the driving system for the detection of broken energy-efficiency of safety-relevant driving rules.
In the last decades, several driving systems were developed to improve the driving behaviour in energy efficiency or safety. However, these driving systems cover either the area of energy-efficiency or safety. Furthermore, they do not consider the stress level of the driver when showing a recommendation, although stress can lead to an unsafe or inefficient driving behaviour. In this paper, an approach is presented to consider the driver stress level in a driving system for safe and energy-efficient driving behaviour. The driving system tries to suppress a recommendation when the driver is in stress in order not to stress the driver additionally with recommendations in a stressful driving situation. This can lead to an increase in the road safety and in the user acceptance of the driving system, as the driver is not getting bothered or stressed by the driving system.
The evaluation of the approach showed, that the driving system
is able to show recommendations to the driver, while also reacting
to a high stress level by suppressing recommendations in
order not to stress the driver additionally.
Energy-efficiency and safety became an important factor for car manufacturers. Thus, the cars have been optimised regarding the energy consumption and safety by optimising for example the power train or the engine. Besides the optimisation of the car itself, energy-efficiency and safety can also be increased by adapting the individual driving behaviour to the current driving situation. This paper introduces a driving system, which is in development. Its goal is to optimise the driving behaviour in terms of energy-efficiency and safety by giving recommendations to the driver. For the creation of a recommendation the driving system monitors the driver and the current driving situation as well as the car using in-vehicle sensors and serial-bus systems. On the basis of the acquired data, the driving system will give individual energy-efficiency and safety recommendations in real-time. This will allow eliminating bad driving habits, while considering the driver needs.
Besides the optimisation of the car, energy-efficiency and safety can also be increased by optimising the driving behaviour. Based on this fact, a driving system is in development whose goal is to educate the driver in energy-efficient and safe driving. It monitors the driver, the car and the environment and gives energy-efficiency and safety relevant recommendations. However, the driving system tries not to distract or bother the driver by giving recommendations for example during stressful driving situations or when the driver is not interested in that recommendation. Therefore, the driving system monitors the stress level of the driver as well as the reaction of the driver to a given recommendation and decides whether to give a recommendation or not. This allows to suppress recommendations when needed and, thus, to increase the road safety and the user acceptance of the driving system.
Besides the optimisation of the car, energy-efficiency and safety can also be increased by optimising the driving behaviour. Based on this fact, a driving system is in development whose goal is to educate the driver in energy efficient and safe driving. It monitors the driver, the car and the environment and gives energy-efficiency and safety relevant recommendations. However, the driving system tries not to distract or bother the driver by giving recommendations for example during stressful driving situations or when the driver is not interested in that recommendation. Therefore, the driving system monitors the stress level of the driver as well as the reaction of the driver to a given recommendation and decideswhether to give a recommendation or not. This allows to suppress recommendations when needed and, thus, to increase the road safety and the user acceptance of
the driving system.
Saving energy and road safety became important in the last decades, hence several driving assistant systems were developed that help to improve the driving behaviour. However, these driving systems cover the area of either energy-efficiency or safety. Furthermore, they do not consider the reaction of the driver to a shown recommendation and the driver stress level. In this paper, the decision process of showing a recommendation to the driver in an energy-efficient and safety relevant driving system is presented. The decision process considers the driver's reaction to a shown recommendation and the driver stress in order to increase the user acceptance and the road safety. The results of the evaluation showed that the driving system was able to show recommendations when needed, while suppressing recommendations when the driver ignored a recommendation repeatedly or when the driver was in stress.
Saving energy and protecting the environment became fundamental for society and politics, why several laws were enacted to increase the energy-efficiency. Furthermore, the growing number of vehicles and drivers leaded to more accidents and fatalities on the roads, why road safety became an important factor as well. Due to the increasing importance of energy-efficiency and safety, car manufacturers started to optimise the vehicle in terms of energy-effciency and safety. However, energy-efficiency and road safety can be also increased by adapting the driving behaviour to the given driving situation. This thesis presents a concept of an adaptive and rule based driving system that tries to educate the driver in energy-efficient and safe driving by showing recommendations on time. Unlike existing driving-systems, the presented driving system considers energy-efficiency and safety relevant driving rules, the individual driving behaviour and the driver condition. This allows to avoid the distraction of the driver and to increase the acceptance of the driving system, while improving the driving behaviour in terms of energy-efficiency and safety. A prototype of the driving system was developed and evaluated. The evaluation was done on a driving simulator using 42 test drivers, who tested the effect of the driving system on the driving behaviour and the effect of the adaptiveness of the driving system on the user acceptance. It has been proven during the evaluation that the energy-efficiency and safety can be increased, when the driving system was used. Furthermore, it has been proven that the user acceptance of the driving system increases when the adaptive feature was turned on. A high user acceptance of the driving system allows a steady usage of the driving system and, thus, a steady improvement of the driving behaviour in terms of energy-efficiency and safety.
In dieser Arbeit wird eine optimierte Bandgap-Referenz zur Erzeugung einer temperaturstabilen Spannung und eines Referenzstroms vorgestellt. Für Low-Power-Anwendungen wurde die Bandgap-Referenz, basierend auf der Brokaw-Zelle, mit minimaler Stromaufnahme und optimierter Chipfläche durch Multi-Emitter-Layout der Bipolartransistoren implementiert. Zusätzliches Merkmal ist ein verbreiteter Versorgungsspannungsbereich von 2,5 bis 5,5 V. Simulationen zeigen, dass eine stabile Ausgangsspannung von 1,218 V und ein Referenzstrom von 1,997 μA realisiert wird. Im Temperaturbereich -40 °C … 50 °C sowie dem gesamten Bereich der Versorgungsspannung beträgt die Genauigkeit der Referenzspannung ± 0,04 % mit einer Gesamtstromaufnahme zwischen 3,5 und 10 μA. Es wird eine Temperaturdrift von 2,18 ppm/K erreicht. Durch das elektronische Trimmen von Widerständen wird der Offset der Ausgangsspannung, bedingt durch Herstellungstoleranzen, auf ±3,5 mV justiert. Die Referenz wird in einer 0,18 μm BiCMOS-Technologie implementiert.
In vitro, hydrogel-based ECMs for functionalizing surfaces of various material have played an essential role in mimicking native tissue matrix. Polydimethylsiloxane (PDMS) is widely used to build microfluidic or organ-on-chip devices compatible with cells due to its easy handling in cast replication. Despite such advantages, the limitation of PDMS is its hydrophobic surface property. To improve wettability of PDMS-based devices, alginate, a naturally derived polysaccharide, was covalently bound to the PDMS surface. This alginate then crosslinked further hydrogel onto the PDMS surface in desired layer thickness. Hydrogel-modified PDMS was used for coating a topography chip system and in vitro investigation of cell growth on the surfaces. Moreover, such hydrophilic hydrogel-coated PDMS is utilized in a microfluidic device to prevent unspecific absorption of organic solutions. Hence, in both exemplary studies, PDMS surface properties were modified leading to improved devices.
Palladium-doped silica materials with SiCH3 groups were fabricated by sol-gel method under various calcination atmospheres and membranes were made thereof by coating process. The results showed that air atmosphere can lead to the partial oxidation of metallic Pd0 to PdO while N2 and H2 atmospheres can effectively prevent metallic Pd0 from being oxidized. H2 atmosphere is proved to be a more prominent way to slow down the decomposition of organic SiCH3 group than N2 and air atmospheres. The surface area, micropore volume and porosity of palladium-doped silica membrane material calcined in H2 atmosphere are much higher than those calcined in N2 atmosphere. Compared with N2 atmosphere, the palladium-doped silica membranes calcined in H2 atmosphere showed higher H2 permeability and H2/CO2 selectivity before and after the steam exposure. The apparent activation energy of H2 permeation through the palladium-doped silica membrane calcined under H2 atmosphere (2.51 ± 0.05 kJ/mol) was slightly lower than that calcined under N2 atmosphere (2.84 ± 0.04 kJ/mol). Calcination atmosphere plays some role in membrane performance, which has greater influence on the permeance than on the gas permselectivity. Calcination under H2 atmosphere is well conducive to improve the gas permeance and H2 permselectivity of palladium-doped silica membrane.
Introducing continuous experimentation in large software-intensive product and service organisations
(2017)
Software development in highly dynamic environments imposes high risks to development organizations. One such risk is that the developed software may be of only little or no value to customers, wasting the invested development efforts.Continuous experiment ation, as an experiment-driven development approach, may reduce such development risks by iteratively testing product and service assumptions that are critical to the success of the software. Although several experiment-driven development approaches are available, there is little guidance available on how to introduce continuous experimentation into an organization. This article presents a multiple-case study that aims at better understanding the process of introducing continuous experimentation into an organization with an already established development process. The results from the study show that companies are open to adopting such an approach and learning throughout the introduction process. Several benefits were obtained, such as reduced development efforts, deeper customer insights, and better support for development decisions. Challenges included complex stakeholder structures, difficulties in defining success criteria, and building experimen- tation skills. Our findings indicate that organizational factors may limit the benefits of experimentation. Moreover, introducing continuous experimentation requires fundamental changes in how companies operate, and a systematic introduction process can increase the chances of a successful start.
Context: Companies need capabilities to evaluate the customer value of software intensive products and services. One way of systematically acquiring data on customer value is running continuous experiments as part of the overall development process. Objective: This paper investigates the first steps of transitioning towards continuous experimentation in a large company, including the challenges faced. Method: We conduct a single-case study using participant observation, interviews, and qualitative analysis of the collected data. Results: Results show that continuous experimentation was well received by the practitioners and practising experimentation helped them to enhance understanding of their product value and user needs. Although the complexities of a large multi-stakeholder business to-business (B2B) environment presented several challenges such as inaccessible users, it was possible to address impediments and integrate an experiment in an ongoing development project. Conclusion: Developing the capability for continuous experimentation in large organisations is a learning process which can be supported by a systematic introduction approach with the guidance of experts. We gained experience by introducing the approach on a small scale in a large organisation, and one of the major steps for future work is to understand how this can be scaled up to the whole development organisation.
Purpose: Human breath analysis is proposed with increasing frequency as a useful tool in clinical application. We performed this study to find the characteristic volatile organic compounds (VOCs) in the exhaled breath of patients with idiopathic pulmonary fibrosis (IPF) for discrimination from healthy subjects. Methods: VOCs in the exhaled breath of 40 IPF patients and 55 healthy controls were measured using a multi-capillary column and ion mobility spectrometer. The patients were examined by pulmonary function tests, blood gas analysis, and serum biomarkers of interstitial pneumonia. Results: We detected 85 VOC peaks in the exhaled breath of IPF patients and controls. IPF patients showed 5 significant VOC peaks; p-cymene, acetoin, isoprene, ethylbenzene, and an unknown compound. The VOC peak of p-cymene was significantly lower (p < 0.001), while the VOC peaks of acetoin, isoprene, ethylbenzene, and the unknown compound were significantly higher (p < 0.001 for all) compared with the peaks of controls. Comparing VOC peaks with clinical parameters, negative correlations with VC (r =−0.393, p = 0.013), %VC (r =−0.569, p < 0.001), FVC (r = −0.440, p = 0.004), %FVC (r =−0.539, p < 0.001), DLco (r =−0.394, p = 0.018), and %DLco (r =−0.413, p = 0.008) and a positive correlation with KL-6 (r = 0.432, p = 0.005) were found for p-cymene. Conclusion: We found characteristic 5 VOCs in the exhaled breath of IPF patients. Among them, the VOC peaks of p-cymene were related to the clinical parameters of IPF. These VOCs may be useful biomarkers of IPF.
This review gives a short overview of the physical processes involved in the formation of the polyelectrolyte multilayers (PEMs) and their destruction. These two processes are vital for the formation of PEMs with desired physical and chemical structures, and for loading them with active substances and their spatial controlled release. It includes a survey of the physical and chemical properties that are key points for controlling film nanostructure in relation to biological processes and different possibilities for controlling cell behavior by means of film composition, bioactivity, mechanical properties, and three-dimensional organization.
In this paper, it aims to model wind speed time series at multiple sites. The five-parameter Johnson distribution is deployed to relate the wind speed at each site to a Gaussian time series, and the resultant m-dimensional Gaussian stochastic vector process Z(t) is employed to model the temporal-spatial correlation of wind speeds at m different sites. In general, it is computationally tedious to obtain the autocorrelation functions (ACFs) and cross-correlation functions (CCFs) of Z(t), which are different to those of wind speed times series. In order to circumvent this correlation distortion problem, the rank ACF and rank CCF are introduced to characterize the temporal-spatial correlation of wind speeds, whereby the ACFs and CCFs of Z(t) can be analytically obtained. Then, Fourier transformation is implemented to establish the cross-spectral density matrix of Z(t), and an analytical approach is proposed to generate samples of wind speeds at m different sites. Finally, simulation experiments are performed to check the proposed methods, and the results verify that the five-parameter Johnson distribution can accurately match distribution functions of wind speeds, and the spectral representation method can well reproduce the temporal-spatial correlation of wind speeds.
Die Coronapandemie hat Deutschland seit dem Frühjahr 2020 fest im Griff. Eine zentrale Maßnahme zur Verlangsamung der Ausbreitung des Coronavirus war von Beginn an die Schließung von Schulen. In einer ersten Studie wurden die Lernzeitverluste durch die Corona-bedingten Schulschließungen im Frühjahr 2020 quantifiziert (Wößmann, Freundl, Lergetporer, Grewenig, Werner & Zierow, 2020). Es zeigte sich, dass sich die Lernzeit der Schülerinnen und Schüler durch die Schulschließungen halbiert hatte und die Verluste bei leistungsschwächeren Schülerinnen und Schülern besonders groß waren. Im Frühjahr 2020 wurde die Verringerung der Lernzeit von den Schulen nicht kompensiert: Nur ein kleiner Teil der Schülerinnen und Schüler hatte in dieser Phase regelmäßigen Distanzunterricht und täglichen Kontakt mit Lehrkräften. Während der Sommer- und Herbstmonate seit der Phase der ersten Schulschließungen hatten Schulverwaltung, Schulen und Lehrkräfte Zeit, sich auf Distanzunterricht und digitale Lehrmethoden umzustellen, um Lernausfällen während etwaiger erneuter Schulschließungen entgegenzuwirken. Inwiefern dies dazu geführt hat, dass die Schülerinnen und Schüler während der Schulschließungen Anfang 2021 tatsächlich mehr Zeit mit Lernen verbracht haben als im Frühjahr 2020, ist jedoch bislang weitgehend unbekannt.
Um zu erfahren, mit welchen Aktivitäten die Schulkinder die Zeit der Schulschließungen Anfang 2021 verbracht haben, wurde erneut eine deutschlandweite Umfrage durchgeführt, diesmal unter mehr als 2.000 Eltern von Schulkindern. Die Ergebnisse liefern umfassende Einblicke in den Alltag von Schulkindern, Eltern und Schulen während der Schulschließungen Anfang 2021. Sie zeigen, wie viele Stunden die Schulkinder in dieser Phase mit Lernen und anderen kreativen und passiven Tätigkeiten verbracht haben, welche konkreten Maßnahmen die Schulen ergriffen haben, um den Schulbetrieb aufrechtzuerhalten, wie effektiv das Lernen zu Hause war, und wie die Eltern das häusliche Lernumfeld einschätzen. Dabei vergleichen wir die Aktivitäten während der Schulschließungen Anfang 2021 mit den Aktivitäten während der ersten Corona-bedingten Schulschließungen im Frühjahr 2020 sowie mit den Aktivitäten vor Corona (vgl. Wößmann et al., 2020). Wir berichten zudem Ergebnisse zum sozio-emotionalen Wohlbefinden der Kinder nach einem Jahr Coronapandemie und zu den Einschätzungen der Eltern, welche breiteren Auswirkungen die Schulschließungen auf verschiedene Lebensbereiche ihrer Kinder haben. Die Befragung liefert somit neue empirische Erkenntnisse über mögliche Folgen der Corona-Krise für den Bildungserfolg von Kindern in Deutschland. Dabei untersuchen wir auch, inwiefern sich die Auswirkungen der Schulschließungen zwischen leistungsstärkeren und -schwächeren Schülerinnen und Schülern sowie zwischen Akademikerkindern und Nicht-Akademikerkindern unterscheiden.
Continuous refactoring is necessary to maintain source code quality and to cope with technical debt. Since manual refactoring is inefficient and error prone, various solutions for automated refactoring have been proposed in the past. However, empirical studies have shown that these solutions are not widely accepted by software developers and most refactorings are still performed manually. For example, developers reported that refactoring tools should support functionality for reviewing changes. They also criticized that introducing such tools would require substantial effort for configuration and integration into the current development environment.
In this paper, we present our work towards the Refactoring-Bot, an autonomous bot that integrates into the team like a human developer via the existing version control platform. The bot automatically performs refactorings to resolve code smells and presents the changes to a developer for asynchronous review via pull requests. This way, developers are not interrupted in their workflow and can review the changes at any time with familiar tools. Proposed refactorings can then be integrated into the code base via the push of a button. We elaborate on our vision, discuss design decisions, describe the current state of development, and give an outlook on planned development and research activities.
Lehr- und Übungsbuch sowie Nachschlagewerk zur CAD-Software Creo Parametric und zu den Grundlagen der Produktdatenverwaltung mit Windchill. Vermittelt werden die Volumenmodellierung, die 3D Flächenmodellierung, die Blechmodellierung, die Baugruppen- und Zeichnungserstellung, das Erstellen von Animationen, die Definition und Anwendung kinematischer sowie dynamischer Analysen und die Definition von Baugruppen, die Konstruktionsvarianten "Top-Down" und "Bottom-Up" sowie die Organisation von Konstruktionsprojekten über Skelett Techniken.
Weiter werden die Grundlagen des Produktdatenmanagements im Konstruktionsbereich unter Windchill vermittelt. Alle Verfahren werden handlungsorientiert an einem weitgehend durchgehenden Modellierungsprojekt erarbeitet. Aufgrund des ausführlichen Inhalts- und Sachwortverzeichnisses sowie einer Vielzahl an Bildern ist das Buch als Grundlage für Vorlesungen, Schulungen oder Praktika und insbesondere auch zum Selbststudium sowie als Nachschlagewerk geeignet.
Lehrbuch zur CAD-Software Creo Parametric und zur Produktdatenverwaltung mit Windchill.
3D-Volumenmodellierung, 3D-Flächenmodellierung, Blechmodellierung, Baugruppen- und Zeichnungserstellung, Definition von Normteilen, Erstellen von Animationen und dynamischen Analysen.
Verfahren zum Umgang mit großen Baugruppen und zur flexiblen Modellierung, Konstruk-tionsvarianten "Top-Down" und "Bottom-Up", Organisation von Konstruktionsprojekten über Skeletttechnik.
Neu: Konstruktion von und mit Mehrkörperobjekten, Rahmenkonstruktion in der Profilumgebung (AFX), intelligente Verbindungen (IFX), Live Simulation und Generatives Design.
Here, we report the mechanical and water sorption properties of a green composite based on Typha latifolia fibres. The composite was prepared either completely binder-less or bonded with 10% (w/w) of a bio-based resin which was a mixture of an epoxidized linseed oil and a tall-oil based polyamide. The flexural modulus of elasticity, the flexural strength and the water absorption of hot pressed Typha panels were measured and the influence of pressing time and panel density on these properties was investigated. The cure kinetics of the biobased resin was analyzed by differential scanning calorimetry (DSC) in combination with the iso-conversional kinetic analysis method of Vyazovkin to derive the curing conditions required for achieving completely cured resin. For the binderless Typha panels the best technological properties were achieved for panels with high density. By adding 10% of the binder resin the flexural strength and especially the water absorption were improved significantly.
Powder coating of engineered wood panels such as medium density fibreboards (MDF) is gaining industrial interest due to ecological and economic advantages of powder coating technology. For transferring powder coating technology to temperature-sensitive substrates like MDF, a thorough understanding of the melting, flowing and curing behaviour of the used low-bake resins is required. In the present study, thermo-analysis in combination with iso-conversional kinetic data analysis as well as rheometry is applied to characterise the properties of an epoxy-based powder coating. Neat resin and cured powder coating films are examined in order to define an ideal production window within which the resin is preferably applied and processed to yield satisfactory surface performance on the one hand and without exposing the carrier MDF too high a temperature load on the other hand to prevent the panel from deteriorating in mechanical strength. In order to produce powder coated films of high surface gloss – a feature that has not yet successfully been realized on MDF with powder coatings – a new curing technology, in-mould surface finishing, has been applied.
Within the scope of the present cumulative doctoral thesis six scientific papers were published which illustrates that modern reaction model-free (=isoconversional) kinetic analysis (ICKA) methods represents a universal and effective tool for the controlled processing of thermosetting materials. In order to demonstrate the universal applicability of ICKA methods, the thermal cure of different thermosetting materials having a very broad range of chemical composition (melamine-formaldehyde resins, epoxy resins, polyester-epoxy resins, and acrylate/epoxy resins) were analyzed and mathematically modelled. Some of the materials were based on renewable resources (an epoxy resin was made from hempseed oil; linseed oil was modified into an acrylate/epoxy resin). With the aid of ICKA methods not only single-step but also complex multi-step reactions were modelled precisely. The analyzed thermosetting materials were combined with wood, wood-based products, paper, and plant fibers which are processed to various final products. Some of the thermosetting materials were applied as coating (in form of impregnated décor papers or powder and wet coatings respectively) on wood substrates and the epoxy resin from hempseed oil was mixed with plant fibers and processed into bio-based composites for lightweight applications. From the final products mechanical, thermal, and surface properties were determined. The activation energy as function of cure conversion derived from ICKA methods was utilized to predict accurately the thermal curing over the course of time for arbitrary cure conditions. Furthermore the cure models were used to establish correlations between the cross-linking during processing into products and the properties of the final products. Therewith it was possible to derive the process time and temperature that guarantee optimal cross-linking as well as optimal product properties
A millimeter-wave power amplifier concept in an advanced silicon germanium (SiGe) BiCMOS technology is presented. The goal of the concept is to investigate the impact of physical limitations of the used heterojunction bipolar transistors (HBT) on the performance of a 77 GHz power amplifier. High current behavior, collectorbase breakdown and transistor saturation can be forced with the presented design. The power amplifier is manufactured in an advanced SiGe BiCMOS technology at Infineon Technologies AG with a maximum transit frequency fT of around 250 GHz for npn HBT’s [1]. The simulation results of the power amplifier show a saturated output power of 16 dBm at a power added efficiency of 13%. The test chip is designed for a supply voltage of 3.3 V and requires a chip size of 1.448 x 0.930 mm².
The dawn of the 21st Century has witnessed a tremendous increase in trade pacts among nations, resulting in renewed hopes for sustainable enterprise development in emerging economies worldwide. Ghana and other sub-Saharan African (SSA) countries have signed onto several North-South and South-South free trade agreements with the hope of strengthening their presence in the international trade arena, and to promote economic growth in SSA. For over two decades, however, very little has changed, and many have dashed their high hopes as enterprises continue to struggle in SSA. Not even the African Continental Free Trade Agreement (AfCFTA) could renew the hopes of sceptics. Several studies opined that enterprises in SSA could improve their domestic and international competitiveness by establishing mutually beneficial partnerships with their counterparts from the Global North and South. This study delved into the issues that affect North-South and South-South business collaborations and recommends key success factors that could help promote mutually beneficial cross-border business partnerships. The research includes both literature and empirical information on the key success factors of business partnerships between African enterprises as well as between African enterprises and firms from the Global North. We approached the study qualitatively using a phenomenological research design. Research participants included important stakeholders in Africa and Europe's international trade and sustainable enterprise development ecosystem. The study identified several challenges with the current business collaborations and recommended new ways of making such partnerships more beneficial.
CODE RED FOR HUMANITY. The alarm bells are deafening, and the evidence is irrefutable: greenhouse-gas emissions from fossil-fuel burning and deforestation are choking our planet and putting billions of people at immediate risk. Global heating is affecting every region on Earth, with many of the changes becoming irreversible. (Guterres 2021)
The digitalisation ongoing in households and sustainability-related challenges are multifaceted and complex. The introducing quote of the United Nations Secretary-General refers to the latest report of the Intergovernmental Panel on Climate Change (IPCC), emphasising the urgency to act – now. As of today, becoming a sustainable population is still a distant destination. As outlined in the previous chapters, the challenges associated with that transformation remain huge, complex, and largely unsolved. Recent dramas such as the power incident in Texas (2021), the floods in Germany (2021), or the drought in sub-Saharan Africa (2020s) – are just a few of the uncountable issues stirring up the debate about fossil-fuel abandonment and the timing of climate neutrality. Business research can actually be accused of referring to the persistent focus on gains and growth, despite early warnings for society at large (e.g., Meadows et al., 1972; Kölsch & Veit, 1981; Veit & Thatcher, 2023). However, academic researchers, corporations, and society are now waking up, as shown by the climate change conference. In fact, it appears that the information systems (IS) discipline just began tackling mammoth challenges around climate change within the last decade (Melville, 2010; Watson et al., 2010). The central discussion in emerging work revolves around the role and use of digital technologies on the path to a healthy planet. But while early studies have focused on organisational settings (e.g., Gholami et al., 2016; Seidel et al., 2013), increasingly research addresses private settings (e.g., Wunderlich et al., 2019).
Aimed at the problem that the accuracy of face image classification in complex environment is not high, a network model F-Net suitable for aesthetic classification of face images is proposed. Based on LeNet-5, the model uses convolutional layers to extract facial image features in complex backgrounds, optimized parameters in the network model, and changes the number of convolutional layers and fully connected layer feature elements in the model. The experimental results show that the F-Net network model proposed in this paper has a face image classifation accuracy of 73% in complex environment background, which is better than other classical convolutional neural network classification models.