Fraunhofer Institute for Integrated Circuits

Harounabadi M., Soleymani D.M., Bhadauria S., Leyh M., Roth-Mandutz E.

The 5G mobile network brings several new features that can be applied to existing and new applications. High reliability, low latency, and high data rate are some of the features that fulfill the requirements of vehicular networks. Vehicular networks aim to provide safety for road users and several additional advantages such as enhanced traffic efficiency and in-vehicle infotainment services. This article summarizes the most important aspects of NR-V2X, which is standardized by 3GPP, focusing on sidelink communication. The main part of this work belongs to 3GPP Release 16, which is the first 3GPP release for NR-V2X, and the work/study items of the future Release 17.

Matek C., Krappe S., Münzenmayer C., Haferlach T., Marr C.

Abstract Biomedical applications of deep learning algorithms rely on large expert annotated data sets. The classification of bone marrow (BM) cell cytomorphology, an important cornerstone of hematological diagnosis, is still done manually thousands of times every day because of a lack of data sets and trained models. We applied convolutional neural networks (CNNs) to a large data set of 171 374 microscopic cytological images taken from BM smears from 945 patients diagnosed with a variety of hematological diseases. The data set is the largest expert-annotated pool of BM cytology images available in the literature. It allows us to train high-quality classifiers of leukocyte cytomorphology that identify a wide range of diagnostically relevant cell species with high precision and recall. Our CNNs outcompete previous feature-based approaches and provide a proof-of-concept for the classification problem of single BM cells. This study is a step toward automated evaluation of BM cell morphology using state-of-the-art image-classification algorithms. The underlying data set represents an educational resource, as well as a reference for future artificial intelligence–based approaches to BM cytomorphology.

Kreller T., Distler T., Heid S., Gerth S., Detsch R., Boccaccini A.R.

• Bioprinting of alginate dialdehyde-gelatine demonstrated for cartilage tissue engineering. • Thermal pre-treatment of gelatine affects hydrogel mechanical and rheological characteristics. • Thermal pre-treatment of gelatine enables 3D printing of hierarchical complex structures. This work explored 3D printing to mimic the intrinsic hierarchical structure of natural articular cartilage. Alginate di-aldehyde- gelatine (ADA-GEL) hydrogel was used as ink to create hierarchically ordered scaffolds. In comparison to previously reported ADA-GEL compositions, we introduce a modified formulation featuring increased amounts of thermally modified gelatine. Gelatine was degraded by hydrolysis which resulted in tailorable printability characteristics further substantiated by rheological analysis. ADA (3.75 %w/v)-GEL (7.5 %w/v) with gelatine modified at 80 °C for 3 h could be printed in hierarchical complex structures reaching scaffold heights of over 1 cm. The hierarchical structure of the scaffolds was confirmed via µCT analysis. To examine mechanical properties as well as the suitability of the hydrogel as a proper matrix for cell seeding and encapsulation, nanoindentation was performed. Elastic moduli in the range of ~ 5 kPa were measured. Gelatine heat pre-treatment resulted in modifiable mechanical and rheological characteristics of ADA-GEL. In summary, this study demonstrates the possibility to enhance the printability of ADA-GEL hydrogels to fabricate hierarchical scaffold structures with shape stability and fidelity, without the necessity to change the initial hydrogel chemistry by the use of additives or crosslinkers, providing a valuable approach for fabrication of designed scaffolds for cartilage tissue engineering.

Hassan T., Seus D., Wollenberg J., Weitz K., Kunz M., Lautenbacher S., Garbas J., Schmid U.

Pain sensation is essential for survival, since it draws attention to physical threat to the body. Pain assessment is usually done through self-reports. However, self-assessment of pain is not available in the case of noncommunicative patients, and therefore, observer reports should be relied upon. Observer reports of pain could be prone to errors due to subjective biases of observers. Moreover, continuous monitoring by humans is impractical. Therefore, automatic pain detection technology could be deployed to assist human caregivers and complement their service, thereby improving the quality of pain management, especially for noncommunicative patients. Facial expressions are a reliable indicator of pain, and are used in all observer-based pain assessment tools. Following the advancements in automatic facial expression analysis, computer vision researchers have tried to use this technology for developing approaches for automatically detecting pain from facial expressions. This paper surveys the literature published in this field over the past decade, categorizes it, and identifies future research directions. The survey covers the pain datasets used in the reviewed literature, the learning tasks targeted by the approaches, the features extracted from images and image sequences to represent pain-related information, and finally, the machine learning methods used.

Gjoreski M., Gams M.Z., Lustrek M., Genc P., Garbas J., Hassan T.

It is only a matter of time until autonomous vehicles become ubiquitous; however, human driving supervision will remain a necessity for decades. To assess the driver's ability to take control over the vehicle in critical scenarios, driver distractions can be monitored using wearable sensors or sensors that are embedded in the vehicle, such as video cameras. The types of driving distractions that can be sensed with various sensors is an open research question that this study attempts to answer. This study compared data from physiological sensors (palm electrodermal activity (pEDA), heart rate and breathing rate) and visual sensors (eye tracking, pupil diameter, nasal EDA (nEDA), emotional activation and facial action units (AUs)) for the detection of four types of distractions. The dataset was collected in a previous driving simulation study. The statistical tests showed that the most informative feature/modality for detecting driver distraction depends on the type of distraction, with emotional activation and AUs being the most promising. The experimental comparison of seven classical machine learning (ML) and seven end-to-end deep learning (DL) methods, which were evaluated on a separate test set of 10 subjects, showed that when classifying windows into distracted or not distracted, the highest F1-score of 79% was realized by the extreme gradient boosting (XGB) classifier using 60-second windows of AUs as input. When classifying complete driving sessions, XGB's F1-score was 94%. The best-performing DL model was a spectro-temporal ResNet, which realized an F1-score of 75% when classifying segments and an F1-score of 87% when classifying complete driving sessions. Finally, this study identified and discussed problems, such as label jitter, scenario overfitting and unsatisfactory generalization performance, that may adversely affect related ML approaches.

Radder D.L., Nonnekes J., van Nimwegen M., Eggers C., Abbruzzese G., Alves G., Browner N., Chaudhuri K.R., Ebersbach G., Ferreira J.J., Fleisher J.E., Fletcher P., Frazzitta G., Giladi N., Guttman M., et. al.

Background Optimal management in expert centers for Parkinson's disease (PD) usually involves pharmacological and non-pharmacological interventions, delivered by a multidisciplinary approach. However, there is no guideline specifying how this model should be organized. Consequently, the nature of multidisciplinary care varies widely. Objective To optimize care delivery, we aimed to provide recommendations for the organization of multidisciplinary care in PD. Methods Twenty expert centers in the field of multidisciplinary PD care participated. Their leading neurologists completed a survey covering eight themes: elements for optimal multidisciplinary care; team members; role of patients and care partners; team coordination; team meetings; inpatient versus outpatient care; telehealth; and challenges towards multidisciplinary care. During a consensus meeting, outcomes were incorporated into concept recommendations that were reviewed by each center's multidisciplinary team. Three patient organizations rated the recommendations according to patient priorities. Based on this feedback, a final set of recommendations (essential elements for delivery of multidisciplinary care) and considerations (desirable elements) was developed. Results We developed 30 recommendations and 10 considerations. The patient organizations rated the following recommendations as most important: care is organized in a patient-centered way; every newly diagnosed patient has access to a core multidisciplinary team; and each team has a coordinator. A checklist was created to further facilitate its implementation. Conclusion We provide a practical tool to improve multidisciplinary care for persons with PD at the organizational level. Future studies should focus on implementing these recommendations in clinical practice, evaluating their potential applicability and effectiveness, and comparing alternative models of PD care.

Mahmood N.H., Böcker S., Moerman I., López O.A., Munari A., Mikhaylov K., Clazzer F., Bartz H., Park O., Mercier E., Saidi S., Osorio D.M., Jäntti R., Pragada R., Annanperä E., et. al.

The recently introduced 5G New Radio is the first wireless standard natively designed to support critical and massive machine type communications (MTC). However, it is already becoming evident that some of the more demanding requirements for MTC cannot be fully supported by 5G networks. Alongside, emerging use cases and applications towards 2030 will give rise to new and more stringent requirements on wireless connectivity in general and MTC in particular. Next generation wireless networks, namely 6G, should therefore be an agile and efficient convergent network designed to meet the diverse and challenging requirements anticipated by 2030. This paper explores the main drivers and requirements of MTC towards 6G, and discusses a wide variety of enabling technologies. More specifically, we first explore the emerging key performance indicators for MTC in 6G. Thereafter, we present a vision for an MTC-optimized holistic end-to-end network architecture. Finally, key enablers towards (1) ultra-low power MTC, (2) massively scalable global connectivity, (3) critical and dependable MTC, and (4) security and privacy preserving schemes for MTC are detailed. Our main objective is to present a set of research directions considering different aspects for an MTC-optimized 6G network in the 2030-era.

Potorti F., Torres-Sospedra J., Quezada-Gaibor D., Jimenez A.R., Seco F., Perez-Navarro A., Ortiz M., Zhu N., Renaudin V., Ichikari R., Shimomura R., Ohta N., Nagae S., Kurata T., Wei D., et. al.

Every year, for ten years now, the IPIN competition has aimed at evaluating real-world indoor localisation systems by testing them in a realistic environment, with realistic movement, using the EvAAL framework. The competition provided a unique overview of the state-of-the-art of systems, technologies, and methods for indoor positioning and navigation purposes. Through fair comparison of the performance achieved by each system, the competition was able to identify the most promising approaches and to pinpoint the most critical working conditions. In 2020, the competition included 5 diverse off-site off-site Tracks, each resembling real use cases and challenges for indoor positioning. The results in terms of participation and accuracy of the proposed systems have been encouraging. The best performing competitors obtained a third quartile of error of 1 m for the Smartphone Track and 0.5 m for the Foot-mounted IMU Track. While not running on physical systems, but only as algorithms, these results represent impressive achievements.

Mack W., Habets E.A.

Signal extraction from a single-channel mixture with additional undesired signals is most commonly performed using time-frequency (TF) masks. Typically, the mask is estimated with a deep neural network (DNN), and element-wise applied to the complex mixture short-time Fourier transform (STFT) representation to perform the extraction. Ideal mask magnitudes are zero for solely undesired signals in a TF bin and undefined for total destructive interference. Usually, masks have an upper bound to provide well-defined DNN outputs at the cost of limited extraction capabilities. We propose to estimate with a DNN a complex TF filter for each mixture TF bin which maps an STFT area in the respective mixture to the desired TF bin to address destructive interference in mixture TF bins. The DNN is optimized by minimizing the error between the extracted and the ground-truth desired signal allowing to learn the TF filters without having to specify ground-truth TF filters. We compare our approach with complex and real-valued TF masks by separating speech from a variety of different sound and noise classes from the Google AudioSet corpus. We also process the mixture STFT with notch-filters and zero whole time-frames, to simulate packet-loss during transmission, to demonstrate the reconstruction capabilities of our approach. The proposed method outperformed the baselines, especially when notch-filters and time-frame zeroing were applied.

Shih Y., Wu S., Zalkow F., Muller M., Yang Y.

Attention-based Transformer models have been increasingly employed for automatic music generation. To condition the generation process of such a model with a user-specified sequence, a popular approach is to take that conditioning sequence as a priming sequence and ask a Transformer decoder to generate a continuation. However, this prompt-based conditioning cannot guarantee that the conditioning sequence would develop or even simply repeat itself in the generated continuation. In this paper, we propose an alternative conditioning approach, called theme-based conditioning, that explicitly trains the Transformer to treat the conditioning sequence as a thematic material that has to manifest itself multiple times in its generation result. This is achieved with two main technical contributions. First, we propose a deep learning-based approach that uses contrastive representation learning and clustering to automatically retrieve thematic materials from music pieces in the training data. Second, we propose a novel gated parallel attention module to be used in a sequence-to-sequence (seq2seq) encoder/decoder architecture to more effectively account for a given conditioning thematic material in the generation process of the Transformer decoder. We report on objective and subjective evaluations of variants of the proposed Theme Transformer and the conventional prompt-based baseline, showing that our best model can generate, to some extent, polyphonic pop piano music with repetition and plausible variations of a given condition.