Search

Automated vehicles in public traffic are subject to a number of expectations: Among other aspects, their behavior should be safe, conforming to the rules of the road and provide mobility to their users. This poses challenges for the developers of such systems: Developers are responsible for specifying this behavior, for example, in terms of requirements at system design time. As we will discuss in the article, this specification always involves the need for assumptions and trade-offs. As a result, insufficiencies in such a behavior specification can occur that can potentially lead to unsafe system behavior. In order to support the identification of specification insufficiencies, requirements and respective assumptions need to be made explicit. In this article, we propose the Semantic Norm Behavior Analysis as an ontology-based approach to specify the behavior for an Automated Driving System equipped vehicle. We use ontologies to formally represent specified behavior for a targeted operational environment, and to establish traceability between specified behavior and the addressed stakeholder needs. Furthermore, we illustrate the application of the Semantic Norm Behavior Analysis in a German legal context with two example scenarios and evaluate our results. Our evaluation shows that the explicit documentation of assumptions in the behavior specification supports both the identification of specification insufficiencies and their treatment. Therefore, this article provides requirements, terminology and an according methodology to facilitate ontology-based behavior specifications in automated driving.

Most clinical information is only available as free text. Large language models (LLMs) are increasingly applied to clinical data to streamline communication, enhance the accuracy of clinical documentation, and ultimately improve healthcare delivery. This study focuses on a corpus of anonymized clinical narratives in German. On the one hand it evaluates the use of ChatGPT for text cleansing, i.e., the automatic rephrasing of raw text into a more readable and standardized form, and on the other hand for retrieval-augmented generation (RAG). In both tasks, the final goal was medical concept normalization (MCN), i.e., the annotation of text segments with codes from a controlled vocabulary using natural language processing. We found that ChatGPT (GPT-4) significantly improves precision and recall compared to simple dictionary matching. For all scenarios, the importance of the underlying terminological basis was also demonstrated. Maximum F1 scores of 0.607, 0.735 and 0.754 (i.e, for top 1, 5 and 10 matches) were achieved through a pipeline including document cleansing, bi-encoder-based term matching based on a large domain dictionary linked to SNOMED CT, and finally re-ranking using RAG.

Infrared object detection is one of the critical technologies for maritime search and rescue. However, it is still challenging due to the strong background clutter interference and the lack of small object information. We proposed a temporal-spatial pyramid network for infrared maritime object detection. We proposed a nested temporal pyramid to represent the temporal features through motion differences maps and energy accumulation maps to distinguish the wave clutter and objects. We proposed a dense spatial pyramid to learn the spatial features and the differences between temporal maps and then to clarify and locate objects. For training, we designed a scale-related composite loss function with correlated location description and weighted confidence loss. Finally, based on the ablation and comparison experiments, the proposed method performs better on maritime infrared sequences.

This work proposes and investigates a solution approach to the urban air transportation network optimization problem, considering the perspectives of different stakeholders, including societal interests. Given logistic hub positions and a set of optimized paths connecting them pairwise, we aim for a Pareto-optimal and three-dimensional air corridor network structure. This work demonstrates a way to merge the given paths into a network and provides a framework to optimize the network further regarding multiple objectives. It proposes three objective functions that evaluate the network from the economic perspectives of network providers and users and the city residents’ social point of view. Using geospatial data from Frankfurt, Germany, we conducted different experiments including and excluding the social objective function under a varying input set of pre-optimized paths. Our analysis showed that taking social aspects into account results in traffic networks whose increase in social acceptance far outweighs the extra monetary costs. We conclude that it is beneficial to integrate social criteria into optimization problems when the solutions obtained are the basis for decisions in the area of conflict between the economy and human welfare.

Ensuring cutting tools are in optimal condition is essential for achieving peak machining performance, given their direct impact on both workpiece quality and process efficiency. However, accurately assessing wear on end mills, especially those with complex geometries, pose a significant challenge due to their reflective surfaces and varied wear patterns. Presented here is a novel method that addresses this challenge by employing a customized illumination unit in conjunction with a convolutional neural network (CNN) for end mill wear analysis. This innovative approach involves utilizing the specially designed illumination unit to capture high-quality images, enabling precise examination of material wear on helically shaped end mills. Notably, this method is tailored to illuminate reflective surfaces and represents a pioneering application in the realm of wear testing.We validate the viability of this approach by employing CNN-based models to segment wear on complex-shaped end mills coated with titanium carbonitride (TiCN) and titanium nitride (TiN). We achieved remarkable mean Intersection over Union (mIoU) results in wear detection on a test dataset: 0.99 for tool segmentation, 0.78 for abnormal wear, and 0.71 for normal wear segmentation.

The upcoming 3GPP global mobile communication standard 6G strives to push the technological limits of radio frequency (RF) communication even further than its predecessors: Sum data rates beyond 100Gbit/s, RF bandwidths above 1GHz per link, and sub-millisecond latency necessitate very high performance development tools. We propose a new SDR firmware and software architecture designed explicitly to meet these challenging requirements. It relies on Ethernet and commercial off-the-shelf network and server components to maximize flexibility and to reduce costs. We analyze state-of-the-art solutions (USRP X440 and other RFSoC-based systems), derive architectural design goals, explain resulting design decision in detail, and exemplify our architecture’s implementation on the XCZU48DR RFSoC. Finally, we validate its performance via measurements and outline how the architecture surpasses the state of the art with respect to sustained RF recording, while maintaining high Ethernet bandwidth efficiency. Building a 6G integrated sensing and communication (ISAC) example, we demonstrate its real-time and rapid application development capabilities.

Prosthetic hands are of paramount importance in the rehabilitation of upper limbs amputees. Gesture recognition using surface electromyography (sEMG) data has emerged as a great option for controlling prosthetic devices, since these data are acquired by non-intrusive sensors. This work presents a real-time classification system based on artificial neural networks with individualized muscle activity segmentation and using dynamic time warping (DTW) based features. For real-time classification, we modify the size of the sliding windows so that their length is sufficient to fully capture the muscle activity signal. For data segmentation, we propose an enhanced muscle activity detection in which validation is used to fine-tune the thresholds needed to determine the beginning and end of muscle contraction. We used two validation methods: cross-validation and multi-holdout. Moreover, we propose a post-processing technique to choose the most representative class when there are multiple classifications for a given data. By combining all the proposed techniques, the accuracy of the resulting system was (97.2 ± 0.3)% in the classification of 6 hand gestures from 10 healthy people, representing an increase of 7.1% in the mean accuracy compared with the baseline model.

The motivation of this study was to solve the high $\rm I_{D,off}$ problem in 8 Volt N-channel MOSFET. We experimented with implanting nitrogen into LDD at various doses. As a result, $\rm I_{D,off}$ increases and $\rm BV_{DSS}$ decreases as the dose increases. When it exceeds 1.0E15 cm $^{-2}$ , the occurrence of tail-type $\rm I_{D,off}$ and $\rm BV_{DSS}$ that deviate from the normal distribution increases. Implanted nitrogen enhances the diffusion of dopants in the LDD bulk but suppresses it on the silicon surface. As a result, the depletion curvature at the LDD edge becomes a negative shape and increases the electric field. We performed the same experiment on logic MOSFETs to comprehensively analyze other electrical effects. Nitrogen improves the HCI immunity of MOSFETs but degrades for 2.5 Volt and 8 Volt MOSFETs when the dose is above 1.0E15 cm $^{-2}$ . The short-channel effect of 2.5 Volt MOSFET is insensitive to nitrogen but is suppressed in CORE MOSFET when the dose is over 1.3E15 cm $^{-2}$ . Nitrogen changes $\rm I_{D,sat}$ through interactions with co-implanted species and nitrogen dose. As a result, nitrogen co-implanted with phosphorus shows a parabolic-like $\rm I_{D,sat}$ trend. However, in the case of CORE MOSFET implanted with arsenic, $\rm I_{D,sat}$ does not show a parabolic-like trend but increases continuously. This experiment did not find much benefit from nitrogen implantation for 2.5 Volt and 8 Volt MOSFETs. For all MOSFETs, it is recommended that the nitrogen dosage not exceed 1.0E15 cm $^{-2}$ .

Radio detection and ranging-based (radar) sensing offers unique opportunities for biomedical monitoring and can help overcome the limitations of currently established solutions. Due to its contactless and unobtrusive measurement principle, it can facilitate the longitudinal recording of human physiology and can help to bridge the gap from laboratory to real-world assessments. However, radar sensors typically yield complex and multidimensional data that are hard to interpret without domain expertise. Machine learning (ML) algorithms can be trained to extract meaningful information from radar data for medical experts, enhancing not only diagnostic capabilities but also contributing to advancements in disease prevention and treatment. However, until now, the two aspects of radar-based data acquisition and ML-based data processing have mostly been addressed individually and not as part of a holistic and end-to-end data analysis pipeline. For this reason, we present a tutorial on radar-based ML applications for biomedical monitoring that equally emphasizes both dimensions. We highlight the fundamentals of radar and ML theory, data acquisition and representation and outline categories of clinical relevance. Since the contactless and unobtrusive nature of radar-based sensing also raises novel ethical concerns regarding biomedical monitoring, we additionally present a discussion that carefully addresses the ethical aspects of this novel technology, particularly regarding data privacy, ownership, and potential biases in ML algorithms.

Joint communication and sensing (JCAS) is one of the key topics of the upcoming 6G mobile communication standard. We propose a novel three-step method to extract the position of reflectors from channel impulse responses (CIRs) obtained by multiple bi-static RADAR measurements. The method consists of the extraction of angle-of-departure (AoD) and angle-of-arrival (AoA), the computation of potential reflecting points and the classification of the propagation paths. For the extraction of AoD and AoA, we propose a novel algorithm with low computational effort. It has a better resolution than the step size of the underlying beam search process by utilizing the antenna beam pattern together with the evaluation of the CIR. The algorithm is compared to a straightforward approach in a raytracing simulation. The evaluation shows that the proposed novel algorithm outperforms the state-of-the-art approach. Furthermore, we discuss the limitations of the proposed room reconstruction method and the potential impacts of physical effects not covered in the simulation.

The drug design process currently requires considerable time and resources to develop each new compound that enters the market. This work develops an application of hybrid quantum generative models based on the integration of parameterized quantum circuits into known molecular generative adversarial networks and proposes quantum cycle architectures that improve model performance and stability during training. Through extensive experimentation on benchmark drug design datasets, quantum machine 9 (QM9) and PubChemQC 9 (PC9), the introduced models are shown to outperform the previously achieved scores. Most prominently, the new scores indicate an increase of up to 30% in the quantitative estimation of druglikeness. The new hybrid quantum machine learning algorithms, as well as the achieved scores of pharmacokinetic properties, contribute to the development of fast and accurate drug discovery processes.

Ensuring security is of paramount importance in microservice architectures, given their distributed nature, involving numerous services and network-spanning interactions. This architectural style, which can comprise hundreds to thousands of services, inherently presents a more extensive attack surface compared to traditional monolithic applications. Moreover, the polyglot nature of microservices, which encompasses services developed and deployed using diverse programming languages and technologies, further complicates the security landscape. This paper presents a systematic literature review, analyzing 54 publications specifically in the context of security threats and mitigation strategies within the area of inter-service security in microservice architectures. We observed that the majority of studies focus on presenting methods, models, and guidelines for microservice security, with a significant portion validating these approaches. Publications in the field have increased since 2015, with conference papers being the most common type. Security threats identified are mainly related to security perimeters, attack surfaces, and inadequate monitoring and intrusion detection. There is a notable lack of comprehensive analysis on specific security threats, particularly in inter-service authentication and communication. Mitigation strategies receive more attention than security threats, with extensive discussion on infrastructure defense and secure coding practices. The identified research gap highlights the need for establishing a connection between security threats and their mitigation strategies in microservice architectures. It also underscores the necessity for a standardized taxonomy in microservice security to clarify terminology and consolidate best practices, addressing inconsistencies in the literature and guiding future empirical studies on the practical challenges of implementing security measures.

Data from production environments is now available in unprecedented volumes, making the problem-solving of incidents through root cause analysis straightforward. However, the root cause analysis process remains time-consuming. This study employs the Kitchenham standard systematic literature review methodology to explore how information models and deep learning can streamline this process. By conducting a comprehensive search across four major databases, we evaluate the current technological advancements and their application in root cause analysis. The aim of this study is to assesses the impact of information models for root cause analysis in a production environment. Our findings reveal that integrating knowledge graphs, association rule mining, and deep learning algorithms significantly improves the speed and depth of root cause analysis compared to traditional methods. Specifically, the use of neural networks in recent literature shows substantial advancements in analyzing complex datasets, facilitating large-scale data integration, and enabling automated learning capabilities. Comparing our findings with other recent studies highlights the advantages of using information modeling and deep learning technologies in root cause analysis. This comparison underscores the superior accuracy and efficiency of these advanced methodologies over traditional manual interpretation methods. The effective implementation of these technologies requires a robust foundation of clean, standardized data, giving rise to the concept of “Production IT.” Furthermore, it is crucial for this data to be openly available to facilitate academic research, thereby enabling the development of new methods for more efficient and effective root cause analysis.

The ImageNet moment was a turning point for Convolutional Neural Networks (CNNs), as it demonstrated their potential to revolutionize computer vision tasks. This triumph of CNNs has motivated solving even more complex problems involving multiple tasks from multiple data modalities. Conventionally, a single CNN accelerator has been optimized to perform just one task or multiple correlated tasks. This study presents a shared-layers approach that leverages the pattern-learning capabilities of CNNs to perform multiple uncorrelated tasks from different modalities using a single hardware accelerator. We overcame the challenge of data imbalance in multi-modal learning by synthetic data generation. We achieved an average classification accuracy above 90% on a single CNN accelerator, which would otherwise require three accelerators. Due to the reliability concerns imposed by transistor shrinking and aging, we extended the shared layers methodology and introduced a fault-tolerant CNN accelerator with reconfigurable capabilities supporting fault-tolerant (FT), high-performance (HP), and de-stress (DS) modes. FT mode provides high reliability against soft errors utilizing double/triple modular redundancy, HP mode offers peak performance of 0.979 TOPs using parallel execution, and DS mode reduces dynamic power consumption by up to 68.6% in clock-gated design and even more using a partial reconfiguration method, contributing to decelerating the aging process of the circuit. We have comprehensively evaluated two different CNN architectures (i.e., fused and branched), for three distinct tasks, in three different operating modes, based on accuracy, quantization, pruning, hardware resource utilization, power, energy, performance, and reliability.

We describe a Bayesian estimation approach to infer on the frequency noise characteristics of narrow-linewidth semiconductor lasers from delayed self-heterodyne beat note measurements. Our technique is grounded in a statistical model of the measurement process that accounts for both the impact of the interferometer and the detector noise. The approach yields accurate results, even in scenarios where the intrinsic linewidth plateau is obscured by detector noise. The analysis is carried out using a Markov-chain Monte Carlo method in the frequency domain and exploits prior knowledge about the statistical distribution of the data. The method is validated using simulated time series data from a stochastic laser rate equation model incorporating $1/f$-type non-Markovian noise.

In this work we investigate the ultrabroadband dynamics of transverse coupled cavity VCSELs. This study is based on a multimode rate equation model, whose parameters are directly provided by a full-wave vectorial electromagnetic solver. This approach sets a step towards the comprehensive physics-based modeling of transverse-coupled cavity VCSELs, providing a relation between the features of the optical supermodes and the enhancements of the intensity modulation response. The approach emphasizes how the bandwidth enhancement, ascribable to a photon-photon resonance picture, can be triggered by forcing asymmetries in the bias and modulation contacting scheme of the device, and the importance of collecting the fields from each single cavity, providing an interpretation of recent experimental observations and paving the way towards more systematic design strategies.

Although AI algorithms and applications become more and popular in the healthcare sector, only few institutions have an operational AI strategy. Identifying the best suited processes for ML algorithm implementation and adoption is a big challenge. Also, raising human confidence in AI systems is elementary to building trustworthy, socially beneficial and responsible AI. A commonly agreed AI auditing framework that provides best practices and tools could help speeding up the adoption process. In this paper, we first highlight important concepts in the field of AI auditing and then restructure and subsume them into an ML auditing core criteria catalog. We conducted a scoping study where we analyzed sources being associated with the term “Auditable AI” in a qualitative way. We utilized best practices from Mayring (2000), Miles and Huberman (1994), and Bortz and Döring (2006). Based on referrals, additional relevant white papers and sources in the field of AI auditing were also included. The literature base was compared using inductively constructed categories. Afterwards, the findings were reflected on and synthesized into a resulting ML auditing core criteria catalog. The catalog is grouped into the categories: Conceptual Basics, Data & Algorithm Design and Assessment Metrics. As a practical guide, it consists of 30 questions developed to cover the mentioned categories and to guide ML implementation teams. Our consensus-based ML auditing criteria catalog is intended as a starting point for the development of evaluation strategies by specific stakeholders. We believe it will be beneficial to healthcare organizations that have been or will start implementing ML algorithms. Not only to help them being prepared for any upcoming legally required audit activities, but also to create better, well-perceived and accepted products. Potential limitations could be overcome by utilizing the proposed catalog in practice on real use cases to expose gaps and to further improve the catalog. Thus, this paper is seen as a starting point towards the development of a framework, where essential technical components can be specified.

While current automotive safety standards provide implicit guidance on how unreasonable risk can be avoided, manufacturers are required to specify risk acceptance criteria for Automated Driving Systems (SAE Level 3 and higher). However, the ‘unreasonable’ level of risk of Automated Driving Systems is not yet concisely defined. Solely applying current safety standards to such novel systems could potentially not be sufficient for their acceptance. As risk is managed with implicit knowledge about safety measures in existing automotive standards, an explicit alignment with risk acceptance criteria is challenging. Hence, we propose an approach for an explicit representation and management of risk, which we call the Risk Management Core. The proposal of this process framework is based on requirements elicited from current safety standards and is applied to the task of specifying safe behavior for an Automated Driving System in an example scenario.

Literature reviews on artificial intelligence (AI) have focused on the different applications of AI in higher education, the AI techniques used, and the benefits/risks of the use of AI. One of the greatest potentials of AI is to personalize higher education to the needs of students and offer timely feedback. This could benefit students with disabilities tremendously if their needs are also considered in the development of new AI educational technologies (EdTech). However, current reviews have failed to address the perspective of students with disabilities, which prompts ethical concerns. For instance, AI could treat people with disabilities as outliers in the data and end up discriminating against them. For that reason, this systematic literature review raises the following two questions: To what extent are ethical concerns considered in articles presenting AI applications assessing students (with disabilities) in higher education? What are the potential risks of using AI that assess students with disabilities in higher education? This scoping review highlights the lack of ethical reflection on AI technologies and an absence of discussion and inclusion of people with disabilities. Moreover, it identifies eight risks associated with the use of AI EdTech for students with disabilities. The review concludes with suggestions on how to mitigate these potential risks. Specifically, it advocates for increased attention to ethics within the field, the involvement of people with disabilities in research and development, as well as careful adoption of AI EdTech in higher education.

Fusing of terrestrial laser scanning (TLS) and airborne laser scanning (ALS) point cloud data has been recognized as an effective approach in forest studies. In this regard, co-registration of point clouds is considered one of the crucial steps in the integration process. Co-registering point clouds in forest environments faces various challenges, including unstable features, extensive occlusions, different viewpoints, and differences in point cloud densities. To address these intricate challenges, this study introduces an automated and robust method for co-registering TLS and ALS point clouds based on the correspondence of individual tree locations in forest environments. Initially, the positions of individual trees in both TLS and ALS data are extracted. Then, a filtering approach is applied to eliminate positions with low potential for corresponding matches in the TLS and ALS dataset. Since larger trees in the TLS data have a higher potential for corresponding matches in the ALS data, an iterative process is applied to identify correspondences between trees in both datasets. After estimating transformation parameters, the co-registration process is executed. The proposed method is applied on six datasets with varying forest complexities. The results demonstrate a high success rate up to 100% if the starting position of the TLS plots are located within ∼4 hectares (∼2000 trees). Additionally, the potential of the proposed method for co-registering TLS data with ALS data across different search areas and varying number of trees is evaluated in detail. The outcomes indicate that successful co-registration of TLS plot with 50 m diameter to ALS data is successful in the best case within a search radius of approximately 113 hectares (∼60,000 tree locations) and in the worst case for around 20 hectares (∼10,000 tree locations) depending on the forest complexity.

Spin Transfer Torque Random Access Memory (STT-RAM) is an emerging Non-Volatile Memory (NVM) technology that has garnered attention to overcome the drawbacks of conventional CMOS-based technologies. However, such technologies must be evaluated before deployment under real workloads and architecture. But there is a lack of available open-source STT-RAM-based system evaluation framework, which hampers research and experimentation and impacts the adoption of STT-RAM in a system. This paper proposes a novel, extendable STT-RAM memory controller design integrated inside the gem5 simulator. Our framework enables understanding various aspects of STT-RAM, i.e., power, delay, clock cycles, energy, and system throughput. We will open-source our HOPE framework, which will fuel research and aid in accelerating the development of future system architectures based on STT-RAM. It will also facilitate the user for further tool enhancement.

The efficient operation of cellular networks requires careful tuning of configuration parameters, such as the transmit power or antenna tilts, to adequately balance interference while providing the necessary capacity to the connected UEs. As manual tuning of these parameters is typically unfeasible, several automated coverage and capacity optimization methods have been proposed. However, most existing solutions are either based on poorly scalable black-box optimization methods or solely consider interference management, while omitting the potential of congested cells. In this work, we instead propose a differentiable framework for cellular network optimization, centered around the end-user throughput, that enables load-aware tuning of network parameters through gradient descent. Hereby, we approach the problem from a data-driven perspective, and include dedicated model subcomponents derived from monitoring data, which enable the calibration to site-specific traffic patterns and KPI measurements. We validate our approach for joint transmit power optimization in a real-world network layout with $\approx 150$ cells in two frequency bands. In our evaluation, the gradient descent-based optimization reliably reduces the outage ratio for different levels of demand, while the black-box baseline struggles to explore the large search space. Our results further reveal substantial differences between the proposed load-aware and commonly used SINR-based objectives, for which we repeatably obtain unbalanced network configurations with severely congested cells. In contrast, the proposed end-user throughput objective promotes a balanced network configuration, providing adequate resources to the connected UEs while also limiting interference.

Synthetic Aperture Radar (SAR) has become, nowadays, one of the most important techniques in remote-sensing, and the increasing interest in Earth monitoring reinforces this trend. Next-generation SAR sensors will enhance the radar resolution capabilities by means of digital beamforming (DBF) techniques along with multistatic systems. In order to support the technological development of future spaceborne SAR missions, airborne sensors become an essential scope of research. Thereby, future airborne SAR systems demand enhanced DBF capabilities that involve phased array antennas with a high density of array elements. However, the antenna aperture size is significantly limited in airborne applications, which leads to low-profile and highly integrated antenna solutions, becoming a more challenging task for lower frequency operations such as L-band. In this work, a compact L-band dual-polarized multilayer phased array antenna with beam steering in elevation, developed for the next-generation German Aerospace Center (DLR) airborne SAR system, is presented. The proposed design makes use of truncated cavities to improve the array element isolation and provides 66% more antenna elements than the previous L-band phased array of the current DLR airborne SAR sensor with the same antenna aperture size. Measurements of a manufactured prototype show an antenna bandwidth of almost 20%, matching levels better than 17 dB, up to 15 dB gain, and cross-polarization suppression values higher than 35 dB. Thus, the proposed work will allow the application of advanced DBF techniques in the upcoming first pulsed bistatic L-band airborne SAR sensor.

Addressing the trends of digitalization, decentralization, democratization, and decarbonization, local peer-to-peer (P2P) markets have the potential to significantly accelerate decarbonization at the communal level. However, due to an increase in the number of energy consumers, such as electric vehicles or heat pumps, grid congestion can occur since actual low-voltage grids are not designed to transmit large loads. This paper introduces a novel concept for a platform to combine the advantages of P2P trading with the need for secure, automated low-voltage grid control, ensuring effective congestion management. Therefore, a dual local energy market has been developed, comprising a P2P energy market and a flexibility market with the latter ensures preventively managing congestion. Furthermore, mechanisms exist to provide curative, real-time congestion management. Additionally, the platform empowers prosumers, i.e. end users that produce and consume electrical energy, with intelligent market strategies to maximize their financial outcomes by participating in both markets. To provide a secure trading mechanism, the novel concept of Self-Sovereign-Identity is integrated into the platform. The platform is based on a multi-agent-system developed using the Java Development Environment (JADE) in conjunction with the Energy Option Model (EOM) for the effective modelling of energy systems. Tested in a smart grid laboratory at the University of Wuppertal, the platform provides financial gains for prosumers and effectively manages current- and voltage-related grid congestions.

This paper deals with the evolution of downlink codebook based multiple-input multiple-output (MIMO) within the third generation partnership project (3GPP) through release 15 to 17. There exist already several tutorials on this topic. However, to the authors’ knowledge, the comparison in terms of complexity performance trade-off between practical precoder selection strategies in frequency or delay domain has not been tackled so far in the literature. This paper describes with matrix formalism the two main codebook types specified within 3GPP, i.e., Type-I codebook (low resolution) and Type-II codebook (high resolution). The Rel. 17 port selection is also detailed as well as the multi-user MIMO (MU-MIMO) precoding strategy to be applied relying on Type-II codebook feedback. For the enhanced Type-II codebook, two main practical precoder selection strategies are detailed at the UE side (i) based on singular value decomposition per sub-band in the frequency domain, (ii) based on wideband singular decomposition in the delay domain. Monte Carlo simulations demonstrate that the delay domain strategy performance may suffer from spatial interference for single user MIMO high rank transmissions when the channel is both spatially correlated and frequency selective. On the other hand, the frequency domain strategy complexity increases linearly with the number of sub-bands while it is not the case for the delay domain selection strategy. As a result, the delay domain selection strategy is particularly relevant for Rel. 17 Type-II codebook port selection or for a low frequency selective channel with few significant consecutive delays.

Deep learning models for image segmentation achieve high-quality results, but need large amounts of training data. Training data is primarily annotated manually, which is time-consuming and often not feasible for large-scale 2D and 3D images. Manual annotation can be reduced using synthetic training data generated by generative adversarial networks that perform unpaired image-to-image translation. As of now, large images need to be processed patch-wise during inference, resulting in local artifacts in border regions after merging the individual patches. To reduce these artifacts, we propose a new method that integrates overlapping patches into the training process. We incorporated our method into CycleGAN and tested it on our new 2D tiling strategy benchmark dataset. The results show that the artifacts are reduced by 85% compared to state-of-the-art weighted tiling. While our method increases training time, inference time decreases. Additionally, we demonstrate transferability to real-world 3D biological image data, receiving a high-quality synthetic dataset. Increasing the quality of synthetic training datasets can reduce manual annotation, increase the quality of model output, and can help develop and evaluate deep learning models.

Existing software tools for specifying and executing multidrone missions are limited to route planning or tightly coupled to specific drone hardware. We introduce EAMOS (Execution of Aerial Multidrone Missions and Operations Specification Framework), which allows us to specify missions intuitively, text-based, and provides a mission compiler, a mission middle layer, and a distributed drone execution environment. The middle layer wraps the control of individual drone-specific capabilities, such as launch, fly to position, or perform a maneuver, into a public API that transparently utilizes the capabilities of numerous drone platforms. We exploit the Go programming language to implement critical components of the framework and provide an interface for ROS-based drone platforms. EAMOS automates the mission execution on real, virtual, and even hybrid robotic setups involving real and virtual drones. We demonstrate the successful deployment of EAMOS with four missions executed on Pixhawk/PX4-equipped quadcopters and virtual drones simulated with Airsim. We assess the performance of our proposed approach by analyzing the number of nodes and arcs of the mission graphs, which are an essential artifact of our mission compilation, the utilization of ROS service calls during mission execution, and the duration of compilation, deployment, and mission execution. Overall, our experiments showed that our drones correctly behaved during mission execution as expected and specified by their mission, the generated mission artifacts were efficiently manageable, and processing times allowed for a fluent workflow.

Although the adoption of Low Code Development Platforms (LCDPs) promises significant improvements in the efficiency and effectiveness of application development, their adoption requires further empirical research. This paper uses a combinatorial approach to research LCDP adoption and presents the results of a multiple mini case study with 36 cases on LCDP adoption. A combination of the Socio-Technical Systems theory and the Technology-Organisational-Environment model is used as a theoretical lens. In this paper, we show that LCDP adoption is a multifaceted phenomenon and identify three archetypes for LCDP adoption (i.e., Application Development Democratisers, Synergy Realisers, and IT Resource Shortage Mitigators) and one archetype for LCDP non-adoption (i.e., Intricacy Adversaries). Each archetype can be interpreted as an individual path to LCDP (non-)adoption. Based on these archetypes, we derive seven starting points for practitioners to adopt LCDPs in work systems. Furthermore, using the theoretical lenses, the paper shows that for LCDP adoption to occur, an optimisation of the social and technical sub-systems is required.

Natural disasters and epidemics are unfortunate recurring events that lead to huge societal and economic loss. Recent advances in supercomputing can facilitate simulations of such scenarios in (or even ahead of) real-time, therefore supporting the design of adequate responses by public authorities. By incorporating high-velocity data from sensors and modern high-performance computing systems, ensembles of simulations and advanced analysis enable urgent decision-makers to better monitor the disaster and to employ necessary actions (e.g., to evacuate populated areas) for mitigating these events. Unfortunately, frameworks to support such versatile and complex workflows for urgent decision-making are only rarely available and often lack in functionalities. This paper gives an overview of the VESTEC project and framework, which unifies orchestration, simulation, in-situ data analysis, and visualization of natural disasters that can be driven by external sensor data or interactive intervention by the user. We show how different components interact and work together in VESTEC and describe implementation details. To disseminate our experience three different types of disasters are evaluated: a Wildfire in La Jonquera (Spain), a Mosquito-Borne disease in two regions of Italy, and the magnetic reconnection in the Earth magnetosphere.

Planning flight paths for unmanned aerial vehicles in urban areas requires consideration of safety, legal, and economic aspects as well as attention to social factors for gaining public acceptance. To solve this many-objective path planning problem in the three-dimensional space, we propose a hybrid framework combining an exact Dijkstra search and a metaheuristic evolutionary optimization. Given a start and an endpoint, we optimize a path regarding the risk in case of a system failure, the radio signal disturbance between the aerial vehicle and a ground station, the energy consumption, and the noise immission on city residents. The optimization includes constraints for static obstacle collision avoidance and compliance with the minimum flight altitude. The result is a set of smooth and three-dimensional paths that realize different trade-offs between the defined objectives. As an example, we consider an urban transportation application for aerial vehicles in San Francisco. For all tests, we use real-world data from OpenStreetMap. In a statistical evaluation, we test the efficiency of our framework against different state-of-the-art optimizers. Moreover, we extend the framework with two features that allow the user to integrate arbitrary objectives and unknown scenarios into the path planning framework.

Reliably predicting the motion of contestant vehicles surrounding an autonomous racecar is crucial for effective and performant ego-motion planning. Although highly expressive, deep neural networks are black-box models, making their usage challenging in this safety-critical applications of autonomous racing. On the other hand, physics-based models provide high safety guarantees for the predicted trajectory but lack accuracy. The method presented in this paper targets this trade-off. We introduce a method to predict the trajectories of opposing racecars with deep neural networks considering physical constraints to restrict the output and to improve its feasibility. We report the method’s performance against an LSTM-based encoder-decoder architecture on data acquired from multi-agent racing simulations. The proposed method outperforms the baseline model in prediction accuracy and robustness. Still, it fulfills quality guarantees of smoothness and consistency of the predicted trajectory and prevents out-of-track predictions. Thus, a robust real-world application of the model with high prediction accuracy is proven. The presented model was deployed on the racecar of the Technical University of Munich for the Indy Autonomous Challenge 2021. The code used in this research is available as open-source software at https://www.github.com/TUMFTM/MixNet.

Autonomous vehicles are being developed to make road traffic safer in the future. The time when autonomous vehicles are actually safe enough to be used in real traffic is a current subject of discussion between industry, science, and society. In our work, we propose a new approach to the risk assessment of autonomous vehicles based on risk-benefit analysis, as it is already established in other areas, such as the registration of pharmaceuticals. In this context, we address the question of socially acceptable risk for mobility and investigate this concept as a decision-making criterion in trajectory planning. We make the first attempt to quantify an accepted risk by comparing autonomous vehicles with other types of mobility while taking into account the ethical and psychological effects important to the acceptance of autonomous vehicles. We show how an accepted risk contributes to the transparent decision-making of autonomous vehicles at the maneuver level. Finally, we present a method for considering accepted risk in trajectory planning. The evaluation of this algorithm in a simulation of 2,000 scenarios reveals that lower risk thresholds can actually reduce risks in trajectory planning. The code used in this research is publicly available as open-source software: https://github.com/TUMFTM/EthicalTrajectoryPlanning.

Automated vehicles and vehicle-to-everything (V2X) communication open the window for sharing of sensor data. This paper aims to provide a systematic view of the delay chain involved. We implemented collective perception (CP) into two street legal automated driving demonstrators (ADDs) to provide insight into the components’ delay. The implementation allowed us to gather highly accurate Quality of Service (QoS) measurements for V2X communication in practical field environments and to gather a set of delay measurements for a working CP system, accompanied by scalability discussions. The results provide a basis for evaluating the delay impact of single components and the applicability of CP use cases from the perspective of time advantage.

Earth imaging satellites are a crucial part of our everyday lives that enable global tracking of industrial activities. Use cases span many applications, from weather forecasting to digital maps, carbon footprint tracking, and vegetation monitoring. However, there are limitations; satellites are difficult to manufacture, expensive to maintain, and tricky to launch into orbit. Therefore, satellites must be employed efficiently. This poses a challenge known as the satellite mission planning problem, which could be computationally prohibitive to solve on large scales. However, close-to-optimal algorithms, such as greedy reinforcement learning and optimization algorithms can often provide satisfactory resolutions. This article introduces a set of quantum algorithms to solve the mission planning problem and demonstrate an advantage over the classical algorithms implemented thus far. The problem is formulated as maximizing the number of high-priority tasks completed on real datasets containing thousands of tasks and multiple satellites. This work demonstrates that through solution-chaining and clustering, optimization and machine learning algorithms offer the greatest potential for optimal solutions. This article notably illustrates that a hybridized quantum-enhanced reinforcement learning agent can achieve a completion percentage of 98.5% over high-priority tasks, significantly improving over the baseline greedy methods with a completion rate of 75.8%. The results presented in this work pave the way to quantum-enabled solutions in the space industry and, more generally, future mission planning problems across industries.

This paper provides an overview of the most recent advancements and outcomes of the European 6G flagship project Hexa-X, on the topic of in-network Artificial Intelligence (AI) and Machine Learning (ML). We first present a general introduction to the project and its ambitions in terms of use cases (UCs), key performance indicators (KPIs), and key value indicators (KVIs). Then, we identify the key challenges to realize, implement, and enable the native integration of AI and ML in 6G, both as a means for designing flexible, low-complexity, and reconfigurable networks (learning to communicate), and as an intrinsic in-network intelligence feature (communicating to learn or, 6G as an efficient AI/ML platform). We present a high level description of down selected technical enablers and their implications on the Hexa-X identified UCs, KPIs and KVIs. Our solutions cover lower layer aspects, including channel estimation, transceiver design, power amplifier and distributed MIMO related challenges, and higher layer aspects, including AI/ML workload management and orchestration, as well as distributed AI. The latter entails Federated Learning and explainability as means for privacy preserving and trustworthy AI. To bridge the gap between the technical enablers and the 6G targets, some representative numerical results accompany the high level description. Overall, the methodology of the paper starts from the UCs and KPIs/KVIs, to then focus on the proposed technical solutions able to realize them. Finally, a brief discussion of the ongoing regulation activities related to AI is presented, to close our vision towards an AI and ML-driven communication and computation co-design for 6G.

There are significant advances in GNSS-free cross-modality self-localization of self-driving vehicles. Recent methods focus on learnable features for both cross-modal global localization via place recognition (PR) and local pose tracking, however they lack means of combining them in a complete localization pipeline. That is, a pose retrieved from PR has to be validated if it actually represents the true pose. Performing this validation without GNSS measurements makes the localization problem significantly more challenging. In this contribution, we propose a method to precisely localize the ego-vehicle in a high resolution map without GNSS prior. Furthermore, sensor and map data may be of different dimensions (2D / 3D) and modality, i.e. radar, lidar or aerial imagery. We initialize our system with multiple hypotheses retrieved from a PR method and infer the correct hypothesis over time. This multi-hypothesis approach is realized using a Gaussian sum filter which enables an efficient tracking of a low number of hypotheses and further facilitates the inference of our deep sensor-to-map matching network at arbitrarily distant regions simultaneously. We further propose a method to estimate the probability that none of the currently tracked hypotheses is correct. We achieve successful global localization in extensive experiments on the MulRan dataset, outperforming comparative methods even if none of the initial poses from PR was close to the true pose. Due to the flexibility of the approach, we can show state-of-the-art accuracy in lidar-to-aerial-imagery localization on a custom dataset using our pipeline with only minor modifications of the matching model.

To cope with the megatrends electrification, automated driving, and connectivity, new functionalities and electric and/or electronic systems must be developed, which require a safe power supply. This leads to increased functional safety requirements for the power supply system, particularly regarding availability. Fault tolerance measures can be implemented to comply with a safety goal (SG) specifying a safety-related availability requirement. To verify an architecture concerning the residual risk of an SG violation, several quantitative target values are provided in ISO 26262. This technical elaboration presents a systematic and holistic approach how to gain benefit in the quantitative evaluation from cyclic safety mechanisms (SMs)– in a fault tolerant item– which have a fault handling time interval (FHTI) longer than the fault tolerant time interval. Modelling cyclic SMs only based on conventional AND-gates is not sufficient. Instead, the fault sequence is differentiated to enable ISO 26262-compliance. Within this paper, an innovative approach including its mathematical background is presented how cyclic SMs can be modelled in a fault tree analysis– with focus on multiple-point faults. The results are verified by a Monte-Carlo-Simulation. Besides the scalability of the approach regarding the number of considered cyclic SMs, the relevant FHTI of each cyclic SM can be considered in a traceable and comprehensible manner.

Unmanned aerial vehicles (UAVs) are widely used platforms to carry data capturing sensors for various applications. The reason for this success can be found in many aspects: the high maneuverability of the UAVs, the capability of performing autonomous data acquisition, flying at different heights, and the possibility to reach almost any vantage point. The selection of appropriate viewpoints and planning the optimum trajectories of UAVs is an emerging topic that aims at increasing the automation, efficiency, and reliability of the data capturing process to achieve a dataset with desired quality. On the other hand, 3-D reconstruction using the data captured by UAVs is also attracting attention in research and industry. This article investigates a wide range of model-free and model-based algorithms for viewpoints and path planning for 3-D reconstruction of large-scale objects. It presents a bibliography of more than 200 references to cover different aspects of the topic. The analyzed approaches are limited to those that employ a single-UAV as a data capturing platform for outdoor 3-D reconstruction purposes. In addition to discussing the evaluation strategies, this article also highlights the innovations and limitations of the investigated approaches. It concludes with a critical analysis of the existing challenges and future research perspectives.

Cellular operators tightly monitor their networks to keep up with the market demand and frequently benchmark their performance against competitors. Typical benchmarking tests compare key performance indicators, quality of service, and quality of experience parameters on the city- and regional levels using user-collected crowdsourced data or drive test measurements. However, time-variant parameters and different user mobility patterns can bias the performance comparison. Designing a measurement sampling strategy that deals with such issues is critical for achieving a valid benchmark. Whether we would like to determine how many tiles of a map have to be measured in drive tests or how many samples we need from crowdsourced data to reach an estimate with the required accuracy, sampling theory can provide us with an answer. Since propagation conditions depend on user mobility and measurement environment, splitting the data set into groups or strata allows us to attain an unbiased estimate with fewer samples, thus allowing for a fair comparison to other mobile network operators with minimum effort measurements. In this work, we characterize the performance of different sampling methods on the simulated data set while investigating specific use cases to reveal scenarios where the stratification method pays off. We further analyze the sampling methods on two real-world crowdsourced data sets from a major Austrian operator. By stratifying the data into meaningful strata, we obtain the required number of areas and measurements in each stratum while remaining under the pre-set estimation error level. To our knowledge, this is the first study on sampling methodologies applied to real-world crowdsourced cellular measurements.

Controlling multi-joint prostheses intuitively and effortlessly has been a research topic since the appearance of the first electric elbow prostheses. Researchers mainly focused on single handed tasks, however in daily life these are mostly executed with the healthy hand and the prosthetic arms only become relevant for two-handed manipulations. Thus, a new approach is presented in this paper addressing bilateral tasks. A taxonomy for bilateral tasks is elaborated in order to categorize and prioritize bilateral manipulations involving a prosthetic arm. Five different key figures for rating bilateral movements are introduced and used to form two quality criteria, which allow evaluation and comparison of different control strategies. Based on the proposed taxonomy and quality criteria, a generalized benchmark test environment is developed with five different evaluation scenarios and realized in virtual reality in an exemplary manner. Furthermore, a new controller-agent strategy, greatly facilitating the usage of prosthetic arms, is presented. The effectiveness of the criteria for evaluation of different control strategies is demonstrated with healthy subjects. With this evaluation concept, we provide the community a means to explore and compare controlling methods and inputs, facilitating the progress and development of new strategies.

The separation of music signals is a very challenging task, especially in case of polyphonic chamber music signals because of the similar frequency ranges and sound characteristics of the different instruments to separate. In this work, a joint separation approach in the time domain with a U-Net architecture is extended to incorporate additional time-dependent instrument activity information for improved instrument track extractions. Different stages are investigated to integrate the additional information, but an input before the deepest encoder block achieves best separation results as well as highest robustness against randomly wrong labels. This approach outperforms a label integration by multiplication and the input of a static instrument label. Targeted data augmentation by incoherent mixtures is used for a trio example of violin, trumpet, and flute to improve separation results. Moreover, an alternative separation approach with one independent separation model for each instrument is investigated, which enables a more flexible architecture. In this case, an input after the deepest encoder block achieves best separation results, but the robustness is slightly reduced compared to the joint model. The improvements by additional information on active instruments are verified by using real instrument activity predictions for both the joint and the independent separation approaches.

Organizations are under increasing pressure to develop applications within budget and time at high quality. Therefore, multiple organizations adopt a Low Code Development Platform (LCDP) to develop applications faster and cheaper compared to traditional application development. However, current research on LCDP adoption lacks empirical grounding as well as a deeper understanding of the importance of adoption drivers and inhibitors. We conducted semi-structured interviews and a Delphi study with 17 experts to address these gaps. As a result, we identified 12 drivers and 19 inhibitors for adopting LCDPs. We show that the experts have a consensus on the most and the least important drivers and inhibitors for LCDP adoption. Yet, the ranking of the drivers and inhibitors between the most and least important is context-dependent. For some drivers and inhibitors, the experts’ ranking is similar to academic literature, whereas, for others, it differs. In conclusion, the study at hand empirically validates drivers and inhibitors for LCDP adoption, adds six new drivers and six new inhibitors to the body of knowledge, and analyzes the importance of these factors.

The distribution of measurement noise is usually assumed to be Gaussian in the optimal phasor measurement unit (PMU) placement (OPP) problem. However, this is not always accurate in practice. This paper proposes a new OPP method for smart grids in which the effects of conventional measurements, limited channels of PMUs, zero-injection buses (ZIBs), single PMU loss contingency, state estimation error (SEE), and the maximum SEE variance (MSEEV) are considered. The SEE and MSEEV are both obtained using a robust $t$-distribution maximum likelihood estimator (MLE) because $t$-distribution is more flexible for modeling both Gaussian and non-Gaussian noises. The A- and G-optimal experimental criteria are utilized to form the SEE and MSEEV constraints. This allows the optimization problem to be converted into a linear objective function subject to linear matrix inequality observability constraints. The performance of the proposed OPP method is verified by the simulations of the IEEE 14-bus, 30-bus, and 118-bus systems as well as the 188-bus practical distribution system in China.

Automated driving systems operated at SAE levels 4 and 5 require a far-reaching fault-tolerant design. To meet this need at the actuator level, we present an integrated vehicle motion control approach that is able to tolerate a wide range of different actuator degradations and failures as well as tire blowouts in vehicles featuring four wheel-individual steering, drive, and brake actuators. The approach, which is based on non-linear model predictive control (MPC), tracks a temporal sequence of reference poses. Fault tolerance is achieved by reconfiguration of the MPC’s constraints, weights, and prediction model, which consists of a double-track vehicle and a brush tire model. The evaluation of the approach is based on two reference trajectories. The example of a simple single lane change trajectory in IPG CarMaker demonstrates the basic functionality of the approach. The example of a demanding decelerated single lane change trajectory shows that the approach is subject to limitations when tolerating different degradations and failures. Still, the observed limitations can be explained by the interplay of the specific degradation or failure and the demanding nature of the trajectory. Therefore, the results indicate that the suitability of fault-tolerant vehicle motion control as part of a system-wide safety concept is strongly connected to the range of possible driving scenarios that an automated driving system can encounter.

The sequential sampling impulse radar is a radar concept that has been known for a very long time. Ultrawideband (UWB) radar systems have been realized based on this concept long before the popular phrases UWB and UWB radar were created. Its hardware simplicity, low cost, potentially high bandwidth and high range resolution, as well as the unsurpassed low power consumption of some of its variants have made it one of the most widely used radar concepts in industrial automation today. Despite its widespread use in practice, however, there are only few publications, textbooks and tutorials that describe this concept in detail and all its varieties and aspects. Especially, the correlation properties and the resulting signal-to-noise ratio (SNR), as well as the phase injection locking of pulsed oscillators, that is required for power-efficient options, have rarely been described in detail. This tutorial introduces the typical sequential sampling impulse radar concept step by step and presents the characteristics and pros and cons. As for the correlation properties and the SNR, the concepts are compared to those of standard coherent impulse radar systems and of frequency modulated continuous wave (FMCW) radar. In addition to the system theory, selected applications are presented to illustrate the attractiveness and elegance, but also the limits, of this interesting and important radar concept. The shown applications range from those in the main field of use of this type of radar, that is, industrial automation, to former and current radar concepts in the areas of automotive radar, ground penetrating radar (GPR), security scanners, and biomedical radar systems.

To successfully launch automated vehicles into the consumer market, there must be credible proof that the vehicles will operate safely. However, finding a method to validate the vehicles’ safe operation is a challenging problem. While scenario-based test approaches seem to be possible solutions, they require the execution of a large number of test cases. Several test benches, ranging from actual test vehicles to partly or fully simulated environments, are available to execute these test cases. Each test bench provides different elements, which in turn, have different parameters and parameter ranges. The composition of elements with their specific parameter values at a specific test bench that is used to execute a test case is referred to as a test bench configuration. However, selecting the most suitable test bench configuration is difficult. The selected test bench configuration determines whether the execution of a specific test case provides sufficiently valid test case results with respect to the intended purpose, for example, validating a vehicle’s safe operation. The effective and efficient execution of a large number of test cases requires a method for systematically assigning test cases to the most suitable test bench configuration. Based on a proposed method for classifying test bench configurations, we propose and illustrate a method for systematically assigning test cases to test bench configurations in a scenario-based test approach for automated vehicles. This assignment method allows for the effective and efficient execution of a large number of test cases while generating sufficiently valid test case results.

New aerodynamic aircraft concepts enable the storage of volumetric liquid hydrogen (LH2). Additionally, the low temperatures of LH2 allow technologies such as the superconductivity of electrical components. An increased power density of the onboard wiring harness and the electrical machine can be expected. Nevertheless, the power electronic drive inverter has to deliver high power and high switching frequencies ( $f_{\mathrm {PWM}}\text{s}$ ) under challenging conditions. Therefore, knowledge of the electric behaviour of different semiconductor materials under cryogenic temperatures is essential to answer the question: “Are modern power electronics a technology enabler or a system bottleneck?” This publication shows a comprehensive novelty study for cryogenic power electronics based on experimental-driven semiconductor investigations, mission profile-based considerations, requirement analyses of superconducting electrical machines, and studies of the cooling concepts. All aspects are discussed within one interdisciplinary publication. A cryogenic system cannot be considered without a feasible cooling concept. Different semiconductor structures based on various materials (silicon (Si), silicon carbide (SiC) and gallium nitride (GaN)) are evaluated for their suitability. The collected data and the literature review draw a technology feasibility studies supported by detailed cooling system analyses and superconducting electrical machine requirements. The power demand and high $f_{\mathrm {PWM}}$ lead to a SiC non-cryogenic inverter approach. Due to the detailed cooling system assessment, a loss reduction is achieved by optimising the junction temperature ( $T_{\mathrm {J}}$ ) under various load cases (LCs) out of the mission profile.

Massive multiple-input multiple-output (mMIMO) technology is a way to increase spectral efficiency and provide access to the Internet of Things (IoT) and machine-type communication (MTC) devices. To exploit the benefits of large antenna arrays, accurate channel estimation through pilot signals is needed. Massive IoT and MTC systems cannot avoid pilot reuse because of the enormous numbers of connected devices. We propose a pilot reuse algorithm based on channel charting (CC) to mitigate pilot contamination in a multi-sector single-cell mMIMO system having spatially correlated channels. We show that after creating an interference map via CC, a simple strategy to allocate the pilot sequences can be implemented. The simulation results show that the CC-based pilot reuse strategy improves channel estimation accuracy, which subsequently improves the symbol detection performance and increases the spectral efficiency compared to other existing schemes. Moreover, the performance of the CC pilot assignment method approaches that of exhaustive search pilot assignment for small network setups.

In urban scenarios, network planning requires awareness of the notoriously complex propagation environment by accounting for blocking, diffraction, and reflection on buildings. To this end, deep learning-based signal-strength prediction directly operating on environmental data has recently gained attention, mainly as a computationally efficient alternative to ray-tracing. Our work combines RSRP measurements from an extensive drive-test campaign in a live 4G network with a 3D city model for the largest real-world assessment of such data-driven schemes to date. We compare three different encodings of the propagation environment and find that a neural network operating on a full 3D representation of the surroundings performs best with an RMSE of $7.06~dB$ . It is followed by a model using only the direct path profile with $7.78~dB$ and a reference neural network utilizing a binary line of sight indicator achieving $8.76~dB$ . The large size of our data set allows us to address several open questions regarding the inner workings of these black box approaches. In particular, we elaborate on different evaluation strategies, highlighting the importance of spatial separation of train and test areas, as the rich environmental data implicitly provides a spatial reference. Through model explainability, we further identify the area along the direct path between the user equipment and the transmitter as the input region with the highest feature importance — questioning the common practice of including large buffer areas. Evaluating the models in scenarios with artificially placed base stations reveals that the measurement campaign offers a sufficient basis for a prototypical network planner. The trained models, which we make publicly available, exhibit the dominant propagation mechanisms in urban areas and generate spatially consistent and physically sound signal-strength maps.

Context: The success or failure of any software development project significantly depends on the accuracy of its effort estimates. Software development effort estimation is the foundation for project bidding, budgeting, planning, and cost control. Problem: The literature shows that a lot of work has been done on software effort estimation. But still, there is a need for improvement in effort estimation by introducing new methodologies. The structured group-based and analogy-based effort estimations are the widely used estimation methods. Nevertheless, there are several shortcomings of using these methods such as lack of experts, lack of historical data, and biasness in expert opinion, which negatively affect the estimation results. Motivation: With the advancement of technologies, such limitations could be overcome. Such as leveraging the applicability of blockchain in several domains such as improvement in the software development process and network security. Method: In this article, we have proposed a Blockchain-Based Software Effort Estimation (BBSEE) methodology to improve the software effort estimation. We employ the proposed method using Web and blockchain technologies. Moreover, we also proposed evaluation criteria to assess the efficacy of the proposed method in terms of Mean Magnitude of Relative Error (MMRE), Mean Absolute Error (MAE) and percentage of successful predictions falling (PRED (25)). Result: We performed several case studies and analyses of expert opinions of 52 organizations to present the efficacy of the proposed method. Conclusion: We observe that the BBSEE method outperforms expert judgment and analogy-based effort estimation methodologies in terms of software effort estimation.